diff --git a/RDAS_RDOMICS/.gitignore b/RDAS_RDOMICS/.gitignore
new file mode 100644
index 0000000..1cd8e67
--- /dev/null
+++ b/RDAS_RDOMICS/.gitignore
@@ -0,0 +1,28 @@
+# Python
+__pycache__/
+*.py[cod]
+.pytest_cache/
+.mypy_cache/
+.venv/
+venv/
+.ipynb_checkpoints/
+
+# Environment and local overrides
+.env
+scripts/config/paths.local.yaml
+
+# Logs
+logs/
+*.log
+scripts/sample_characteristics_harmonization/logs/
+
+# macOS
+.DS_Store
+
+# Generated pipeline outputs
+scripts/data/geo_matrix_files/
+scripts/data/geo_final_tables/
+scripts/data/geo_final_tables_testing/
+scripts/data/node_csv_files/
+scripts/data/node_json_files/
+scripts/sample_characteristics_harmonization/sample_characteristics_harmonization_output/sample_import_resume.json
diff --git a/RDAS_RDOMICS/README.md b/RDAS_RDOMICS/README.md
new file mode 100644
index 0000000..6b02027
--- /dev/null
+++ b/RDAS_RDOMICS/README.md
@@ -0,0 +1,60 @@
+# RDAS_RDOMICS
+
+RDAS_RDOMICS is a rare-disease omics data extraction and graph-construction pipeline centered on GEO studies. The project takes disease-driven queries, gathers matching GEO accessions, extracts experiment and sample metadata, normalizes selected fields, and reshapes the results into graph-ready node and relationship tables that can be imported into Neo4j or Memgraph.
+
+The codebase supports two connected workflows. The first is the main RD-OMICS build pipeline, which moves from GEO search through metadata extraction, graph table generation, graph import, and experiment-property normalization. The second is a downstream sample-characteristics harmonization workflow that cleans noisy sample labels, applies rule-based and LLM-assisted grouping, and writes harmonized sample properties back onto graph `Sample` nodes.
+
+At a high level, the repository does the following:
+
+- searches GEO with rare-disease terms and records matched GSE studies
+- extracts study, platform, project, publication, and sample metadata from GEO/NCBI pages
+- converts extracted tables into graph node files and relationship mapping files
+- imports graph-ready exports into Neo4j or Memgraph
+- normalizes experiment assay fields for cleaner graph properties
+- harmonizes sample-characteristics labels into curated categories and subcategories
+
+## Repository Layout
+
+- `scripts/`: core pipeline scripts plus sample-characteristics harmonization utilities
+- `scripts/config/paths.yaml`: tracked default config with repo-relative paths
+- `scripts/data/`: small source inputs and templates that the pipeline reads; large generated graph outputs are intentionally not versioned here
+- `paper_materials/`: figures and supplementary files for the paper
+- `SCHEMA.md`: graph labels, identifiers, and relationship types
+
+## Setup
+
+```bash
+python -m venv .venv
+source .venv/bin/activate
+pip install -r requirements.txt
+```
+
+Optional LLM/HPC workflow:
+
+```bash
+pip install -r requirements-llm.txt
+```
+
+The LLM harmonization scripts under `scripts/sample_characteristics_harmonization/` assume a GPU-capable environment and local access to a vLLM-compatible model.
+
+## Configuration
+
+The default config lives at `scripts/config/paths.yaml` and now uses repo-relative paths. You can point the pipeline at a different config file with `--config` or by setting `RDAS_RDOMICS_CONFIG`.
+
+For the optional LLM steps, set `settings.llm_model_path` in the config or export `RDAS_LLM_MODEL_PATH`.
+For NCBI Entrez calls, set `ENTREZ_EMAIL` in your environment instead of editing source files.
+
+Example:
+
+```bash
+python -m scripts.main --step3-download-gse-number --step4-extract-to-table
+python -m scripts.main --step5-generate-node-mappings --step6-import-to-neo4j
+python -m scripts.main --step7-experiment-normalization
+python -m scripts.main --step7-1-import-normalized-experiment-properties
+```
+
+## Pipeline Order
+
+1. Core extraction and graph-building pipeline: `step1` through `step7.1` in `scripts/`
+2. Sample-characteristics harmonization: the scripts under `scripts/sample_characteristics_harmonization/`
+
diff --git a/RDAS_RDOMICS/SCHEMA.md b/RDAS_RDOMICS/SCHEMA.md
new file mode 100644
index 0000000..523bb4d
--- /dev/null
+++ b/RDAS_RDOMICS/SCHEMA.md
@@ -0,0 +1,34 @@
+# RD-OMICS Graph Schema
+
+This repository builds a graph-oriented export with six node types and six relationship types. The definitions below are inferred from `scripts/step6_import_to_neo4j.py`.
+
+## Node Labels
+
+| Node file | Graph label | Primary identifier |
+| --- | --- | --- |
+| `publication_node.csv` | `Publication` | `Pubmed_id` |
+| `project_node.csv` | `Project` | `Project_id` |
+| `experiment_node.csv` | `Experiment` | `Experiment_id` |
+| `sample_node.csv` | `Sample` | `Sample_id` |
+| `platform_node.csv` | `Platform` | `Platform_id` |
+| `condition_node.csv` | `Condition` | `GardId` |
+
+## Relationship Types
+
+The importer derives relationship type names from mapping filenames by uppercasing the basename without `_mapping`.
+
+| Mapping file | Start node | End node | Relationship type |
+| --- | --- | --- | --- |
+| `sample_platform_mapping.csv` | `Sample` | `Platform` | `SAMPLE_PLATFORM` |
+| `condition_project_mapping.csv` | `Condition` | `Project` | `CONDITION_PROJECT` |
+| `publication_project_mapping.csv` | `Publication` | `Project` | `PUBLICATION_PROJECT` |
+| `project_experiment_mapping.csv` | `Project` | `Experiment` | `PROJECT_EXPERIMENT` |
+| `experiment_platform_mapping.csv` | `Experiment` | `Platform` | `EXPERIMENT_PLATFORM` |
+| `sample_experiment_mapping.csv` | `Sample` | `Experiment` | `SAMPLE_EXPERIMENT` |
+
+## Pipeline Notes
+
+- `scripts/step5_generate_node_mappings.py` creates the node CSVs and relationship mapping CSVs.
+- `scripts/step6_import_to_neo4j.py` converts those CSVs to JSON and imports them into Memgraph/Neo4j.
+- `scripts/step7_experiment_normalization.py` adds normalized assay fields to `Experiment`.
+- `scripts/sample_characteristics_harmonization/7_import_to_sample_node.py` adds harmonized sample property fields to `Sample`.
diff --git a/RDAS_RDOMICS/paper_materials/figures/Figure 1. Project pipeline for RD-OMICS development.pdf b/RDAS_RDOMICS/paper_materials/figures/Figure 1. Project pipeline for RD-OMICS development.pdf
new file mode 100644
index 0000000..818316c
Binary files /dev/null and b/RDAS_RDOMICS/paper_materials/figures/Figure 1. Project pipeline for RD-OMICS development.pdf differ
diff --git a/RDAS_RDOMICS/paper_materials/figures/Figure 1. Project pipeline for RD-OMICS development.png b/RDAS_RDOMICS/paper_materials/figures/Figure 1. Project pipeline for RD-OMICS development.png
new file mode 100644
index 0000000..dedf708
Binary files /dev/null and b/RDAS_RDOMICS/paper_materials/figures/Figure 1. Project pipeline for RD-OMICS development.png differ
diff --git a/RDAS_RDOMICS/paper_materials/figures/Figure 2_new. RD-OMICS knowledge Graph Schema.pdf b/RDAS_RDOMICS/paper_materials/figures/Figure 2_new. RD-OMICS knowledge Graph Schema.pdf
new file mode 100644
index 0000000..e1a08e2
Binary files /dev/null and b/RDAS_RDOMICS/paper_materials/figures/Figure 2_new. RD-OMICS knowledge Graph Schema.pdf differ
diff --git a/RDAS_RDOMICS/paper_materials/figures/Figure 2_new. RD-OMICS knowledge Graph Schema.png b/RDAS_RDOMICS/paper_materials/figures/Figure 2_new. RD-OMICS knowledge Graph Schema.png
new file mode 100644
index 0000000..1e3bfbd
Binary files /dev/null and b/RDAS_RDOMICS/paper_materials/figures/Figure 2_new. RD-OMICS knowledge Graph Schema.png differ
diff --git a/RDAS_RDOMICS/paper_materials/figures/Figure 3_data_normalization.pdf b/RDAS_RDOMICS/paper_materials/figures/Figure 3_data_normalization.pdf
new file mode 100644
index 0000000..99924dd
Binary files /dev/null and b/RDAS_RDOMICS/paper_materials/figures/Figure 3_data_normalization.pdf differ
diff --git a/RDAS_RDOMICS/paper_materials/figures/Figure 3_data_normalization.png b/RDAS_RDOMICS/paper_materials/figures/Figure 3_data_normalization.png
new file mode 100644
index 0000000..f64a61b
Binary files /dev/null and b/RDAS_RDOMICS/paper_materials/figures/Figure 3_data_normalization.png differ
diff --git a/RDAS_RDOMICS/paper_materials/figures/Figure 4_Overview of multi-omics datasets in RD-OMICS.pdf b/RDAS_RDOMICS/paper_materials/figures/Figure 4_Overview of multi-omics datasets in RD-OMICS.pdf
new file mode 100644
index 0000000..8f8e3b6
Binary files /dev/null and b/RDAS_RDOMICS/paper_materials/figures/Figure 4_Overview of multi-omics datasets in RD-OMICS.pdf differ
diff --git a/RDAS_RDOMICS/paper_materials/figures/Figure 5_ALS_overview.pdf b/RDAS_RDOMICS/paper_materials/figures/Figure 5_ALS_overview.pdf
new file mode 100644
index 0000000..7244148
Binary files /dev/null and b/RDAS_RDOMICS/paper_materials/figures/Figure 5_ALS_overview.pdf differ
diff --git a/RDAS_RDOMICS/paper_materials/figures/Figure 5_ALS_overview.png b/RDAS_RDOMICS/paper_materials/figures/Figure 5_ALS_overview.png
new file mode 100644
index 0000000..a8fa89d
Binary files /dev/null and b/RDAS_RDOMICS/paper_materials/figures/Figure 5_ALS_overview.png differ
diff --git a/RDAS_RDOMICS/paper_materials/figures/Figure 6_ALS_Drug_Repurposing.pdf b/RDAS_RDOMICS/paper_materials/figures/Figure 6_ALS_Drug_Repurposing.pdf
new file mode 100644
index 0000000..8e8e406
Binary files /dev/null and b/RDAS_RDOMICS/paper_materials/figures/Figure 6_ALS_Drug_Repurposing.pdf differ
diff --git a/RDAS_RDOMICS/paper_materials/figures/Figure 6_ALS_Drug_Repurposing.png b/RDAS_RDOMICS/paper_materials/figures/Figure 6_ALS_Drug_Repurposing.png
new file mode 100644
index 0000000..99f87f1
Binary files /dev/null and b/RDAS_RDOMICS/paper_materials/figures/Figure 6_ALS_Drug_Repurposing.png differ
diff --git a/RDAS_RDOMICS/paper_materials/supplementary_files/Supp.file_1_RD_list.xlsx b/RDAS_RDOMICS/paper_materials/supplementary_files/Supp.file_1_RD_list.xlsx
new file mode 100644
index 0000000..6866b37
Binary files /dev/null and b/RDAS_RDOMICS/paper_materials/supplementary_files/Supp.file_1_RD_list.xlsx differ
diff --git a/RDAS_RDOMICS/paper_materials/supplementary_files/Supp.file_2_Experiment_metadata_normalization_rules.xlsx b/RDAS_RDOMICS/paper_materials/supplementary_files/Supp.file_2_Experiment_metadata_normalization_rules.xlsx
new file mode 100644
index 0000000..fa99cad
Binary files /dev/null and b/RDAS_RDOMICS/paper_materials/supplementary_files/Supp.file_2_Experiment_metadata_normalization_rules.xlsx differ
diff --git a/RDAS_RDOMICS/paper_materials/supplementary_files/Supp.file_3_Term_definition_source.docx b/RDAS_RDOMICS/paper_materials/supplementary_files/Supp.file_3_Term_definition_source.docx
new file mode 100644
index 0000000..e5a47b0
Binary files /dev/null and b/RDAS_RDOMICS/paper_materials/supplementary_files/Supp.file_3_Term_definition_source.docx differ
diff --git a/RDAS_RDOMICS/paper_materials/supplementary_files/Supp.file_4_Category_reference_information.csv b/RDAS_RDOMICS/paper_materials/supplementary_files/Supp.file_4_Category_reference_information.csv
new file mode 100644
index 0000000..fc916a0
--- /dev/null
+++ b/RDAS_RDOMICS/paper_materials/supplementary_files/Supp.file_4_Category_reference_information.csv
@@ -0,0 +1,11 @@
+standarized_term,synonym,Example_entrys,Definition
+External_sample_id,"patient_id, patient no, patient id, patient', Patient, patients, patient id, patientid, patient_id, patient id no","50,371,018",internal IDs for the patients involved in clinical trials. This id should be included as external sample id only.
+Biospecimen Organism,"species, cell organism, host organism, organism_status, source_organism, microorganism_source_of_infection, microorganism_blood","Homo sapiens, Mus musculus, Danio rerio",Any living biological system (from bacteria to plants to humans)
+Biospecimen Type,"sample type, Specimen type, type of sample, specimen type, physical sample type, specimen_type, Sample Type, Type of Biospecimen, Specimen Type, Biospecimen Type, physical_sample_type, SPEC, tissue type, cell lline, tissue location, cell type, cell name, organismpart, tissue anatomic site, Tissue type, name of tissue, tissue origin, tumor tissue source, tissue/cell info, tissue/cell type, cell line source tissue, cell line/tissue source, tissue location, brain tissue, tissue zone","blood, cell, tissue, feces, Cerebrospinal fluid, stem cell, iPSC, NK cell, liver tissue, brain tissue, red blood cell","The type of a material sample taken from a biological entity for testing, diagnostic, propagation, treatment or research purposes. This includes particular types of cellular molecules, cells, tissues, organs, body fluids, embryos, and body excretory substances. This category also include sub-type of biospecimen, such as cells, tissues, fluids"
+Biospecimen Age,"age, sample collection time, sample age, donor age, cell culture time, age in year, age(year), age of onset, age_weeks, age patient, subject age, age in yrs, age at draw, age at diagnosis","30 years old,24 hours",the age at the time of the collection of biospecimen. Years / months for human donor and hours / days for cell culture 
+Biospecimen Sex,"sex, gender, sugject gender, gender source, patient gender, source patient gender, donor gender, cell line source gender, sex/age, donor sex, animal sex, detal sex, biological sex, SEX, infantSex, sext of nodor mice","male, female",the sex at birth of the donor if the biospecimen is collected from a human donors or cell lines are derived from human tissues
+Biospecimen Race,"race, race/ethnicity, donor race, Ethnicity, self reported Ethnicity, donor ethnicity, race_ethinicity","Caucasian, Asian American, Hispanic, Latin-Americans",the race of the donor if the biospecimen is collected from human donors or cell lines are derived from human tissues. the Ethnicity of the donor if the biospecimen is collected from human donors or cell lines are derived from human tissues
+Biospecimen Disease Condition,"condition, disease status, diagnosis, cohort, stage, subject status, patient status, developmental stage, primary disease, disease classification, diesase group, stage of disease, disease subtpe, lung diseaes, disease condition, disease phase, disease subset, patient condition, sample condition, clinical condition, participant condition","disease (such as cancer), control, healthy, healthy contol, pseudo surgery, simulattion",the disease condition of the donor or other samples
+Treatment,"treatment, intervention, treatment condition, culture condition, growth condition, labeling condition, treatment type, treatment/group, genotype/treatment, culture/treatment, no treatment, treatment, active ingredient, drug treatment, antibody treatment, chemical treatment, treatment agent, treatment/agent, compound treatment, treatment term name, polarization treatment, growth medium/treatment, surgical treatment category, treatment art, treatment condition/type","treatment, placebo, oberservation, drug name, placebo, saline","the treatment group of specimen donor or cell line or animial models, and the name of the treatment"
+Treatment Dosage Regimen,"dosage, treatment description, treatment protocol, treatment dose, treatment_dose, treatment tming, time of drug treatment, days under treatment, duration of treatment, days under treatment, infectious_dose, dose group, vaccine doses, drug dose, lung radiation dose,  treatment dose, drug concentration, drug administration, agent concentration","treatment duration, treatment time, concentration","A Dosage Regimen is the schedule of doses of a medicine outlining the instructions for its safe and effective administration. It includes dose size frequency of administration time interval between administrations duration of treatment administration instructions route of administration dosage form and dosage modifications."
+Other,,,Other labels that do not belong to any other categories. 
\ No newline at end of file
diff --git a/RDAS_RDOMICS/paper_materials/supplementary_files/Supp.file_5_Semantic_categorization_sample_characteristics.csv b/RDAS_RDOMICS/paper_materials/supplementary_files/Supp.file_5_Semantic_categorization_sample_characteristics.csv
new file mode 100644
index 0000000..826da7f
--- /dev/null
+++ b/RDAS_RDOMICS/paper_materials/supplementary_files/Supp.file_5_Semantic_categorization_sample_characteristics.csv
@@ -0,0 +1,11 @@
+standardized_term,label_count,total_occurrence_count,labels
+Biospecimen Type,475,393113,"['tissue', 'cell type', 'cell line', 'tissue type', 'celltype', 'tissue anatomic site', 'cell description', 'cell sex', 'cell', 'Tissue', 'tissue source', 'tissue/cell type', 'cell subtype', 'country of serum collection', 'organ failure', 'cell_type', 'cell subset', 'tissue preparation', 'tissue of origin', 'cell karyotype', 'cell lineage', 'tissue_type', 'flowcell', 'sorted cells', 'cell population', 'organ/tissue', 'predicted celltype', 'predicted parent celltype', 'timepoint biopsy', 'lymphocyte_percent', 'lymphocyte_absolute', 'monocyte_percent', 'monocyte_absolute', 'cell projection', 'cell line code', 'white_blood_cell_count', 'tissue_depot', 'red blood cells', 'white blood cells', 'specimen', 'blood obtained', 'tissue substructure', 'tissue structure', 'organ', 'cell phenotype', 'per lymphocytes', 'per monocytes', 'TargetedCellType', 'CellLine', 'cells', 'tissue.type', 'specimen_name', 'biopsy', 'monocytes', 'blood collection tube coating', 'tissue subtype', 'tissue region', 'blood_group', 'cell types', 'responder cell line', 'cell line of origin', 'biopsy type', 'cell source', 'tissue/cell line', 'tissue archive method', 'spike-in cell_line', 'spike-in cell_type', 'tissue origin', 'blood.source', 'clinical diagnosis specimen', 'biopsy data, villus height to crypt depth', 'cell_line', 'tissue notes', 'cell fraction', 'responder cells', 'biopsy site', 'tissue-of-origin', 'tissue processing', 'cell part', 'serum type', 'cell culture', 'cell line source', 'cell type/line', 'primary tissues', 'transplanted organ', 'time of blood draw', 'cell stimulation', 'lymphocyte.reaction', 'cell state', 'cell compartment', 'cell subpopulation', 'tissue compartment', 'cell line background', 'cell density', 'number of cells', 'specimen site', 'cell number', 'tissue group', 'source tissue', 'cell lines', 'minimum reads per cell during initial processing', 'day blood taken', 'tissue status', 'cell markers', 'lymphocyte_count', 'source cell type', 'tissue/cell info', 'sorted cell_type', 'cells detected', 'tissue derivation', 'data tissue_collection', 'tissue collection', 'age at blood collection', 'organ system', 'day of tissue harvest', 'parental cell line', 'other organ lesion', 'stem cell', 'cell surface marker', 'developmental stage/tissue', 'lymphocytes_count', 'monocytes_count', 'tissue acquisition', 'cell surface markers', 'cell/tissue type', 'Tissue Factor', 'percentage of tumor cells', 'source cell', 'age at biopsy date', 'cells_loaded', 'Cell type', 'organ obtained', 'primary cells', 'Age at interview & blood sampling', 'biopsy vs surgical resection', 'Tissue type', 'cell tye', 'treated stem cells', 'cell treatment', 'cell line name', 'Cell line', 'Medication at blood sampling', 'cell culture condition', 'cell-type', 'derived cell line', 'source cell line', 'age at skin biopsy', 'tumor tissue source', 'cell passage', 'tumor organ site', 'cell line/type', 'cell cycle stage', 'tumor cell line', 'lymphocytes', 'biopsy collection date', 'bone marrow mononuclear cells sorted from', 'additional cell lineages present in dataset', 'cell type source', 'cell stage', 'tissues', 'primary cell line', 'tissue subgroup', 'cell line/tissue', 'cell line/tissue source', 'monocyte', 'sorted cell type', 'lymphocyte', 'cell or tissue type', 'starting cell', 'blood island injection', 'cell preparation', 'cell dissociation', 'peripheral blood', 'cells/condition', 'cell transduction', 'cell marker', 'cellular_component', 'tissue location', 'cell type origin', 'cell status', 'serum', 'cell line_name', 'cell_origin', 'tissue class', 'cell origin', 'age at blood draw', 'original cell line', 'cell lining', 'growth phase of cells', 'Tumor tissue', 'brain tissue', 'cell type background', 'age at biopsy', 'cell line type', 'isolation of tumor cells', 'primary cell type', 'cell line origin', 'tumor cell type', 'maturation to macrophage', 'melanoma cell type', 'histological findings of renal specimen', 'renal biopsy', 'name of tissue', 'cell line passage', 'blood pressure', 'area/tissue', 'cell line for infection', 'injected cell line', 'cell-subtype', 'parental cell type', 'neuroblastoma cell line', 'derived cell_type', 'cell number per well', 'macrophages', 'cell type depletion', 'cell type implantation', 'sorted subset of cells', 'cell subsets', 'sorted cell', 'derived cell type', 'cell morphology', 'stem cell clone', 'tissue storage', 'cell phase', 'biopsy position', 'tissue type type', 'cell line_infection', 'cell enrichment', 'Cells', 'blood', 'source organ', 'tissue zone', 'bacterial cells', 'tissue extraction', 'skin score at biopsy site', 'non-small cell lung cancer Derived from metastatic site', 'Organ', 'bacteria tissue', 'large cell lung cancer Derived from metastatic site', 'cell subpopulation/marker', 'cell characterization', 'source cells', 'cell line source gender', 'cell mixing ratio', 'BRAIN (CEREBELLUM), BIOPSY', 'cell line source age', 'cell line source tissue', 'cell mixture', 'small cell lung cancer Derived from metastatic site', 'cell lie', 'injected cells', 'stimulation', 'phenotype', 'well', 'morphology', 'case number', 'transduction', 'sorted compartment', 'population', 'source type', 'number of relapses', 'preparation', 'Phenotype', 'line type', 'clinical phenotype', 'case_phenotype', 'als phenotype', 'sub-population', 'health status', 'bacterial lysate', 'responder', 'simulation', 'karyotype', 'compartment', 'parental line', 'FISH origin', 'surface marker', 'body site', 'clinical phenotypes', 'phenotypes', 'clone phenotype', 'twin status', 'Karyotype', 'enrichment', 'lot number', 'surface markers', 'es line', 'clone name', 'efflux status', 'source muscle', 'fold enrichment', 'sediment', 'initial preparation', 'anatomic site', 'derived culture', 'genotype background', 'subpopulation', 'tic class', 'Morphology', 'chip antibody', 'antibody', 'molecule subtype', 'type', 'molecule type', 'library type', 'molecule', 'isolate', 'material', 'parity', 'background', 'genetic background', 'epithelial', 'culture_result', 'smear_results', 'full_genotype', 'hip_circumference', 'waist_circumference', 'microdissection', 'assayed molecule', 'lymphs', 'line', 'isolation_method', 'skin type', 'library well', 'library plate', 'platelet', 'antigen', 'markers', 'skin', 'colony of_origin', 'hemoglobin genotype', 'trachea region', 'intrinsic subtype', 'anatomic_location', 'anatomic location', 'microbiota status', 'sputum_smear', 'sputum_culture', 'growth', 'eye', 'brain bank', 'splice variant', 'transplant type', 'chip target', 'bal_culture', 'bal_smear', 'smear of index case', 'components', 'fibrinogen', 'target molecule', 'enzyme', 'marrow', 'variety', 'hemisphere', 'microglia media', 'histological..subtype', 'unsorted or sorted', 'input material', 'subclass', 'fracture site', 'immune_or_nasal', 'any_immune', 'Type', 'embryo', 'anatomical location', 'fetus', 'lesional (ls) vs. normal', 'Genetic background', 'Histological type', 'vs type', 'histological.type', 'lobe', 'cytology', 'aspiration site', 'vector constructs', 'sandwich type', 'types', 'modifications', 'library-type', 'lymph node number', 'upper or lower extremity', 'growth pattern', 'volar or non-volar', 'isolation method', 'specific heart region', 'lymph node', 'graft source', 'derived from', 'BREAST', 'type of library', 'fusion', 'hemolysis score', 'autopsy', 'resection', 'construct', 'mating type', 'location type', 'skin anatomy', 'pulldown', 'knock-in line', 'brain section', 'knockout status', 'mitotic activity', 'derived from metastatic site', 'kit expression', 'pulmonary compartment', 'sampling location', 'Body surface area', 'body part', 'anatomical site', 'resection_type', 'morphologic form', 'spinal cord region', 'Construct', 'extract', 'exogenous gene expressed', 'molecule source', 'generation', 'generation/colony', 'electrophysiology', 'glioma model', 'fus aggregation state', 'sort purification strategy', 'protein expression', 'menstrual phase', 'protein', 'clip antibody', 'viral', 'composite', 'osteogenic potential', 'aortic valve', 'adipogenic potential', 'lung section/portion', 'cytogenetic', 'sorted fraction', 'precursor', 'genotype abbreviation', 'sorting profile', 'receptor expression', 'material type', 'cag repeat', 'serology', 'density gradient region', 'pluripotent', 'MASTECTOMY', 'total/partial resection', 'model type', 'type of cultivation plate', 'urine protein', 'embryos pooled', 'lung section', 'anatomical region', 'microglia population', 'fus variant', 'portion of branchial arch', 'anatomic segment', 'allele', 'neural crest-derived', 'molecule subtypes', 'hairpin', 'pull-down', 'cytogenetics', 'marker', 'number of_tracheas', 'knock-in', 'embryo characteristic', 'immortalization method', 'OVARY', 'AXILLARY NODE', 'BREAST, LOCAL EXCISION', 'PARTIAL MASTECTOMY', 'COMPLETION MASTECTOMY', 'SENTINEL AXILLARY LYMPH NODE', 'BREAST, MASTECTOMY', 'small molecule']"
+Biospecimen Disease Condition,560,197439,"['disease state', 'disease', 'diagnosis', 'condition', 'infection', 'disease status', 'tumor type', 'housing condition', 'diseasestate', 'clinical diagnosis', 'histologic diagnosis', 'tumor grade', 'infection status', 'tumor location', 'infection states', 'disease group', 'final diagnosis', 'cancer status', 'hours post infection', 'disease severity', 'infection protocol', 'working_diagnosis', 'first_diagnosis', 'tumor grading', 'pathology', 'disease duration', 'disease_category', 'institutional tumor diagnosis', 'disease location', 'disease staging', 'cancer site', 'tumor', 'neuropathological_diagnosis', 'clinical_diagnosis', 'disease_duration_years', 'culture condition', 'site of infection', 'cancer type', 'infection code', 'culture conditions', 'disease_status', 'reference diagnosis', 'condition description', 'adjusted disease severity index', 'diagnosis date', 'growth condition', 'additional conditions', 'disease symptom', 'other diseases', 'disease type', 'disease subtype', 'DiseaseState', 'diagnosis.after.path.re.review', 'diagnosis.of.record', 'lung disease', 'chronic diseases', 'molecular.diagnosis', 'primary.tumor', 'tumor_name', 'radiation administered prior to tumor resection', 'histological diagnosis', 'tumor localization', 'broad diagnosis', 'behavior at diagnosis', 'tumor category', 'disease activity', 'stimulation condition', 'primary diagnosis', 'light condition', 'diagnosis total', 'diagnosis hep flex', 'diagnosis rectum', 'lung pathology', 'tumor_entity_subtype', 'diagnosis colonic', 'diagnosis details', 'diagnosis anal perianal', 'diagnosis oral', 'diagnosis rectal', 'disease_state', 'tumor full_name', 'disease_group_detailed', 'disease_group', 'pathology_note', 'distance from the tumor center', 'index_case_disease_site', 'tumor subgroup', 'years since diagnosis', 'histopathology', 'skin disease', 'Diagnosis', 'tumor subtype', 'clinical condition', 'infection group', 'worm infection', 'Tumor size', 'disease_extension', 'tumor status', 'culture_conditions', 'primary disease', 'incubation conditions', 'neuropathological diagnosis', 'Condition', 'tumor.in.left.right.lobe', 'tumor region', 'disease_duration', 'hour post infection', 'disease category', 'tumor type/grade', 'virus infection', 'exposure condition', 'bacterial infection', 'infection state', 'infection duration', 'parental tumor subtype', 'preliminary diagnosis', 'primary tumor site', 'malaria infection', 'tumor histology', 'metastatic tumor site', 'lesion_disease_factor', 'infection type exposure', 'primary tumor', 'duration of infection', 'experimental condition', 'malignant tumor', 'disease model', 'initial tumor increase/(-)decrease', 'tumor size', 'tumor_grading', 'tumor source', 'conditioning received', 'conditions', 'active_disease', 'Conditioning', 'Disease', 'tumor/control', 'disease phase', 'tumor.grade', 'qualifying condition', 'clinical.diagnosis.history', 'tumor vs. normal', 'viral infection', 'maximal prior disease extend', 'disease diagnosis', 'hours of infection', 'years of disease', 'disease subset', 'conditioned media type', 'conditioned media origin', 'Location tumor', 'Tumor type', 'growth conditions', 'infection type', 'plasmodium falciparum infection status', 'single or double infection', 'infection route', 'stress condition', 'pulmonary.disease', 'cancer.past', 'active cancer', 'cardiovascular.disease', 'oncologic diagnosis', 'environmental condition', 'molecular condition', 'disease course', 'disease onset', 'tumor_size', 'library outgrowth conditions', 'maternal disease status', 'disease condition', 'associated primary tumor no', 'tumor_site', 'Chief Disease', 'tumor model', 'tumor origin', 'disease outcome', 'mechanical condition', 'Wash Condition', 'Labeling Condition', 'location of tumors', 'brain tumor region', 'initial tumor volume', 'tumor class', 'disease classification', 'disease in non-fip', 'brain tumor', 'treatment condition', 'disease grade', 'tumor inoculation', 'original tumor', 'molarity of infection', 'duration of disease', 'genotype/disease state', 'infection rate', 'infection period', 'oxygen condition', 'conditioned medium', 'conditioned media source', 'growing media conditions', 'Disease state', 'disease feature', 'site of_disease_onset', 'disease name', 'tumor position', 'cancer predisposition', 'original tumor type', 'growth_condition', 'plasmodium infection', 'length of infection', 'molecular diagnosis', 'experimental conditions', 'months post infection', 'tumor who grade', 'reference condition', 'test condition', 'rounds of infection', 'Infection Status', 'clinical info', 'histology', 'primary site', 'brain region', 'who category', 'initial ich volume', 'who grade', 'number of malaria infections', 'section', 'infection_status', 'Histopathological diagnostic', 'hours post-invasion', 'hours post invasion', 'mechanical ventilation', 'antibody description', 'inflammation status', 'injection_type', 'Histology', 'localization', 'isolate type', 'location of onset', 'dissection', 'injection site', 'clinical indication', 'lesion status', 'clinic status', 'metastatic site', 'hours_post_infection', 'injection', 'er status', 'neuropathological.information', 'hours post fertilization', 'viral infected', 'infectious', 'water type', 'maternal health status', 'single or double infected', 'clone type', 'hours post-infection', 'channel type', 'interaction status', 'pair status', 'infection_state', 'vaccination status', 'type of insertion', 'clinical manifestation', 'incubation period', 'viral inactivation', 'environmental factor', 'nes status', 'zinc status', 'round of selection', 'reference lot', 'reference cat', 'histopathological diagnostic', 'cohort', 'smoking status', 'pasi', 'pathologic status', 'grade', 'surgical status', 'outcome', 'status', 'subtype', 'culture result', 'site_onset', 'metastasis', 'severity score', 'stress', 'smoker', 'severity', 'illness', 'Illness', 'viral_positivity', 'neoplastic', 'consortium lung phenotype', 'malaria_transmission', 'consortium lung phenotype surrogate variable', 'meconium ileus status', 'persistent ps aer status', 'malaria_status', 'dementia', 'diagnostic_mean', 'death', 'survival_status', 'progression', 'parasitemia', 'tst skin test', 'joint problems', 'family history', 'symptoms onset date', 'with or without clonal heterogeneity', 'international prognostic index', 'dead or alive at the end of follow-up', 'total number of genomic aberrations', 'seizure', 'asthma', 'smear_result', 'anti-centromere', 'recurrence', 'os.mos', 'surgical.outcome', 'psychiatric disorder', 'gastrointestinal disorder', 'cerebral palsy', 'mutational subclass', 'birth defects', 'neurological disorder', 'developmental/speech disorder', 'diabetes', 'percent_weight_loss', 'molecular classification', 'recurrent_status', 'dysplasia now', 'health state', 'cigarette smoker', 'medical.history', 'inflammation_status', 'pregnancy status', 'cirrhosis present', 'chronic hypertension', 'survival after surgery', 'death with metastasis', 'outcome related', 'infected/uninfected', 'neoplasia type', 'symptom severity', 'viral shedding', 'tst result', 'symptomatic', 'smoking', 'hypertension', 'cag_repeat', 'conversion', 'prognosis', 'parasitemia category', 'survival status', 'parasite density', 'malign', 'protect_outcome', 'isolate_sensitivity', 'exposure_latent', 'pasi score', 'obesity', 'stress exposure', 'genetic class', 'symptom', 'mutation_carrier_status', 'cag_repeats', 'phase', 'das score', 'infectivity', 'total cholesterol', 'fibrosis degree', 'interim pet response', 'primary/recurrent', 'pasi_total', 'Outcome', 'scar', 'lesion', 'lymphoma type', 'remission', 'swollen joints', 'pain', 'tender joints', 'viral load', 'current status', 'Smoking status', 'endoscopic_activity', 'mitotic index', 'survival characteristics', 'vascular.invasion', 'mutational.status', 'multifocal', 'smoker or non smoker', 'exposed to', 'familial anamnesis', 'onset', 'Status', 'progression_free_survival', 'primary recurrent', 'smoking_status', 'clinical outcome', 'metastasis site', 'glioma', 'subcutaneous neurofibromas', 'plexiform neurofibromas', 'cutaneous neurofibromas', 'facial dysmorphism', 'scoliosis', 'skin-fold freckling', 'Lymph node involvement', 'primary_recurrent', 'clinically_aggressive', 'total skin score', 'lesion_label', 'presence_of_parasites_lesion', 'infiltration', 'severity_score', 'lesion_size', 'bleeding', 'stool frequency', 'clinical presentation', 'alive', 'prodromal status', 'subtypes', 'local skin score', 'location of lesion', 'gene deletion status', 'mutation class', 'fever', 'dyspnea / tachypnea', 'cough', 'primary/metastasis', 'symptoms', 'tuberculosis_history', 'family_history', 'exitus', 'primary mutation', 'copy number gain', 'sofa score', 'als mutation', 'granuloma', 'brain metastasis', 'reason for intubation', 'pregnancy', 'clinical_history', 'cerebral performance category score', 'diplopia', 'mutations', 'decrease of vision', 'onset site', 'relapse', 'syndrome', 'systemic sclerosis subtype', 'parasite density on admission', 'serologic response status', 'digestives_symptoms', 'radiation sensitivity', 'major_organ_involvement', 'severity binary', 'severe_eosinophilia', 'receptor status', 'histological grade', 'clinical phenotype details', 'who class', 'cause.of.death', 'histological response', 'hereditary status', 'Family History', 'clinical information', 'parasite', 'primary vs metastatic', 'nonunion type', 'Dead/Alive', 'Location of distant metastasis', 'isolate sensitivity', 'sputum smear status', 'diffuse/limited', 'KIT mutation', 'antibody status', 'lymphoma subtype', 'primary_recurrence', 'neural tube defect', 'sofa_admission', 'affected status', 'skin phenotype', 'sum.risk.factors', 'psoriasis area-and-severity index', 'hospitalization', 'follicular lymphoma grade', 'psoriasis subtype', 'Scaling', 'skin score', 'previous severity', 'Overall erythema', 'degree of infiltrate', 'pathological type', 'fip status', 'mortality', 'gametocyte status', 'medical history', 'histological subtype', 'metastatic status', 'somatic mutation', 'respiratory score', 'gastrointestinal involvement', 'Death Cause', 'Inflammation', 'ocular involvement', 'vascular involvement', 'genital ulcer', 'arthritis', 'At Risk', 'oral ulcer', 'molecular subtype/phenotypic state', 'erythema nodule', 'reason for liver resection', 'injury model', 'febrile seizure', 'ar or asthma', 'autism diagnostic', 'alk mutation status', 'pulmonary cavitation', 'malignancy class', 'risk grade', 'glioma grade', 'immune infiltration', 'hind-limb paralysis', 'rift valley fever virus', 'engraftment', 'interstitial pneumonia', 'seizures/month', 'surgical indication', 'melanoma', 'major reason_for_surgery', 'primary/ recurrent', 'metastatic/primary', 'recurrent/primary', 'weight phenotype', 'resistance profile', 'embryo phenotype', 'etiology', 'myopathic motor_unit_potentials', 'mutation details', 'cognitive impairment', 'distant metastasis', 'tobacco use', 'parental/ne-like state', 'oocyst prevalence', 'post-symptom onset', 'invasive behavior', 'responder status', 'fibrosis', 'severity grade', 'diffuse vs limited', 'allergy', 'months_survival', 'progression_status', 'months_progression', 'mitotic rate', 'positive Down screening risk']"
+Biospecimen Age,413,197068,"['age', 'time', 'time point', 'timepoint', 'developmental stage', 'Stage', 'day', 'agent', 'age in years', 'Age', 'passage', 'tumor stage', 'passages', 'development stage', 'age_onset', 'age description', 'disease stage', 'treatment time', 'age group', 'infection time', 'year', 'passage_if_expanded', 'doubling time', 'infectious agent', 'collection time point', 'age_weeks', 'age_at_draw', 'time harvest', 'sampling time_point_label', 'time_to_malaria', 'reagent', 'age of enrollment', 'days_in_hospital', 'age_at_diagnosis', 'age of onset of persistent ps aer or censored age', 'days since vaccine', 'dev_stage', 'age_at_death_years', 'passage number', 'time.from.exposure.months', 'day of trial', 'day post infection', 'age at death', 'days since vaccination', 'sampling timepoint', 'gold stage', 'year of surgery', 'age in year', 'days of differentiation', 'age at_treatment', 'treatment age_group', 'animal age', 'treatment/time point', 'dosage', 'week', 'osteogenesis day', 'timepoint_months', 'InitialTimePoint', 'age at diagnosis', 'path.stage', 'differentiation stage', 'description of day', 'differentiation day', 'day_of_euthanasia', 'visit day', 'age_diagnosis_years', 'age of onset', 'Tumor stage', 'TimeUnit', 'sorter day', 'art start year', 'sampling_timepoint', 'time post-stimulation', 'developmental_stage', 'days_symptom_onset', 'overall.survival..days', 'sampling time', 'time_since_onset', 'stimulation time and condition', 'age at_diagnosis', 'dev stage', 'lineage', 'day of differentiation', 'survival time', 'days post drug', 'collection time point (#) or necropsy', 'parasite stage', 'time-point', 'days after infection', 'differentiation_stage', 'cage', 'age.days', 'infection.time.point.days', 'embryonic stage', 'excision year', 'time points', 'Time', 'ventilator-free days', 'day-post-infection', 'time post infection', 'day after seeding', 'os month', 'day of_tumor_harvest', 'infection agent', 'harvesting time', 'collection time', 'time after treatment', 'age at sampling', 'gestational age', 'Usage number', 'average library size', 'exposure time', 'age of psoriasis onset', 'treatment time point', 'ko induction_time', 'days post-vaccination', 'age at transplant', 'age.at.operation', 'disease_stage', 'days post onset of symptoms', 'age, months', 'survival_time', 'age of death', 'AGE', 'clinical stage', 'survival time in months', 'draw day', 'relapse time', 'stage of repair process', 'culture days', 'cancer stage', 'growth stage', 'activation agent', 'storage', 'age at initiation', 'ann arbor stage', 'sampling.time', 'harvest time', 'overall.survival.time', 'days post infection', 'life stage', 'time in culture', 'collection day', 'stage', 'days after stimulation', 'labeling agent', 'survival year', 'time after infection', 'treatment/timepoint', 'age and disease', 'year of isolation', 'timepoint_description', 'age at surgery', 'sporozoite age', 'age/gender', 'treatment stage', 'oxygen percentage', 'age in_yrs', 'injury/age', 'sex/age', 'experimental day', 'day post-infection', 'treatment_time', 'age fracture', 'days post-infection', 'time of sampling', 'day of collection', 'days ill', 'age/disease timepoint', 'age years', 'differentiation time', 'days post exposure', 'maternal age', 'time post-vaccination', 'days post_infection', 'post-treatment day', 'days post-prime', 'days post challenge', 'timepoint_in_hours', 'day transplantation', 'growth time mins', 'time post-treatment', 'Age of Onset', 'culture age', 'developmental stages', 'time_point', 'day of isolation', 'GOLD stage', 'Age at time of surgery', 'time post initiation of treatment', 'age at collection', 'time after treatment (and reversal) in hours', 'age post-hatch', 'age fraction', 'gestational stage', 'age at time of collection', 'post-operative day', 'growth time', 'induction time', 'pretreatment time', 'Time after induction', 'age at examination', 'dev_stage at treatment initiation', 'time infected', 'interval_death_symptoms_onset_days', 'intubation_days', 'time point days', 'time designation after sclerosis', 'time since sclerosis', 'time since transplant', 'Passage', 'culture stage', 'death_time', 'time post treatment', 'days post treatment', 'sampling time point', 'day of collection/passage', 'harvest time post treatment', 'time post_injury', 'differentiation_age', 'embryonic day', 'time post-infection', 'os_days', 'sepsis stage', 'fever day', 'injection age', 'MaternalAge', 'isolation stage', 'timepoint_progressors', 'time point post infection', 'time of treatment', 'age at onset', 'duration of untreated disease in month', 'cold ischemia time', 'donation time', 'time post-exposure', 'age_category', 'age of disease onset percentile', 'age of disease onset', 'age in months', 'day of development', 'parasite/gametocyte stage', 'cold ischemia_time', 'time of_treatment', 'incubation time', 'age tier', 'developmental age', 'treatment agent', 'day of protocol', 'differentiation time point', 'age of  culture', 'block storage', 'time to relapse', 'harvest time point', 'Tumor Stage', 'onset age', 'agent concentration', 'time after virus injection', 'days', 'time post-immunization', 'time point in the model of dormancy', 'age, yrs', 'developmental stage/tumor stage', 'chronological age', 'days under treatment', 'final age at death', 'death day', 'Developmental stage', 'gestational days', 'age at diagnosis in months', 'day post transplant', 'age at study start', 'time of last follow up in months', 'day after intubation', 'age at harvest', 'time of day', 'age range', 'exacerbation day', 'process day', 'age/time point', 'day after transplantation', 'age of_diagnosis', 'time since first diagnosis', 'age of_onset', 'life cycle stage', 'time point of infection', 'cartilage pellets', 'embryo stage', 'passage/days', 'developmental stage, weeks', 'time of_drug_treatment', 'time after exposure', 'treatment time-point', 'collection timepoint', 'developmental stage/age', 'days from treatment', 'time after stimulation', 'age category', 'day post neural induction', 'days_since_positive_test', 'days in culture', 'of passage', 'days of final differentiation', 'stage of disease', 'passages after establishing stable clones', 'culture time', 'treatment/agent', 'treatment / timepoint', 'infection time point', 'days_post_infection', 'postnatal day', 'stage of differentiation', 'passage no', 'experiment', 'datatype description', 'collection_method', 'tag', 'culture', 'clinical status', 'fraction', 'lab description', 'survival_yr', 'growth phase', 'case', 'date harvest', 'surgery number', 'survival', 'induction date', 'exposure', 'culture type', 'development', 'category', 'experiment type', 'description', 'state', 'differentiation batch', 'growth medium', 'Cause of death', 'survival cluster', 'differentiation', 'overall.survival.months', 'os_month', 'differentiation_method', 'cag', 'culture media', 'isolation source', 'growth media', 'infected', 'animal name', 'clinical type', 'culture method', 'experiment label', 'infectious challenge', 'experimental status', 'Degree of differentiation', 'Case', 'experimental set', 'sampling site', 'Differentiation Method', 'experiment batch', 'isolation', 'growth type', 'collection date', 'differentiation status', 'state of culture', 'collection', 'overall.survival', 'experimental batch', 'experimental', 'experimental design', 'Clinical Status', 'labversion description', 'Type of Surgery', 'parasite isolate', 'sampling point', 'differentiation state', 'experimental factor', 'culture status', 'harvesting', 'collection_date', 'os months', 'Cause of Death', 'type of death', 'collection buffer', 'collection point', 'overall survival', 'experimental variable', 'culture batch', 'source/differentiation', 'phase description', 'stim', 'experiment name', 'length of culture', 'long description', 'maternal state', 'culture medium', 'differentiation replicate', 'date of isolation', 'process order', 'activation', 'incubation', 'life cycle', 'Growth Medium', 'sorted', 'data type description', 'developmental state', 'cause of death', 'incubation partner', 'birth date', 'follow up years', 'ga', 'hours', 'phase of growth']"
+External_sample_id,415,166895,"['sample type', 'patient id', 'individual', 'subject id', 'donor', 'subject', 'patient', 'subject status', 'sample id', 'subjectid', 'sample', 'sample group', 'mouse id', 'donor id', 'slide no', 'participant id', 'controlid', 'donor_id', 'patientid', 'batch id', 'individual id', 'barcode', 'patient_id', 'animal id', 'patient diagnosis', 'provider', 'patient gender', 'cell line id', 'sampleID', 'donor_age', 'donor_sex', 'donor_health_status', 'donor_ethnicity', 'participant', 'patient viral load', 'patient group', 'sample source', 'chip_antibody_provider', 'sample alias', 'sample common name', 'sample collection site', 'patient sample id', 'sample.id', 'patient age', 'ID', 'covid_status', 'slide', 'donor age', 'sample_code', 'volunteer id', 'blood sample id', 'plate id', 'patient_asymptomatic', 'blood sample_id', 'in_covid_only_dataset', 'external_donor_name', 'cosmic id', 'patient classification_at_first_sample', 'days since_first_sample', 'external id', 'days since first sample', 'sample id alt', 'patient classification at first sample', 'sample class', 'patient category', 'vendor id', 'platform_id_id design', 'sample_name', 'slide_position', 'sample name', 'sample timing', 'covid cat', 'covid', 'subject_id', 'sample material', 'sample collection time', 'symptomatic or asymptomatic at sample collection', 'non human primate individual id', 'vaccine side effects', 'age at sample drawn', 'sample preparation', 'sample_group', 'slide id', 'subject group', 'sample group_label', 'sample number within subject', 'sample collection', 'animal_id', 'tissue id', 'monkey id', 'donor category', 'slide name', 'sample time', 'Individual', 'subject number', 'sample_set', 'donor_id_blinded', 'sample_group_granular', 'donor type', 'paired samples', 'patient.code', 'sample_type', 'subject condition', 'subject diagnosis', 'sample day', 'tissue/sample type', 'hybridization batch', 'diagnosis recto sigmoid', 'patient_age', 'patient_visit', 'patient sex', 'patient code', 'patient subgroup', 'patient number', 'hybridization protocol', 'study id', 'sample tissue', 'sample_id', 'long-covid symptoms', 'study participant', 'sample_site', 'clinical diagnosis patient', 'sample recovery type', 'sample_barcode', 'slide_id', 'deceased donors, only left kidney included in the analysis', 'side', 'identifier', 'patient treatment', 'subjects', 'sample origin', 'time since steroid dose', 'donor_genotype', 'sample collection time post infection', 'scan id', 'steroids', 'mouse_id', 'donor code', 'type of sample', 'patient population', 'sample age proxy', 'patient condition', 'family id', 'sample subseries', 'matched pair id', 'replicate id', 'donor number', 'individual identifier', 'specimen_barcode', 'mouse identifier', 'patient source', 'biopsy number for this subject', 'sample number', 'Patient', 'unique_subject_identifier', 'sample collection time post virus infection', 'tissue/treatment id', 'donor_type', 'animal identifier', 'library id', 'age patient', 'patient identifier', 'covid infection_status', 'covid severity_status', 'steroids_cat', 'nasal_steroids', 'pool id', 'number of pooled individuals', 'peptide', 'minimum counts per cell threshold used to remove background barcodes', 'sample plate', 'patient identification number', 'sample description', 'donor covid_status', 'steroid', 'with_lesion_sample', 'id sample', 'id simple', 'methylation_geo_id', 'geo_sample_id', 'ref id', 'time of sample collection', 'patient_no', 'patient no', 'subject age', 'pediatric patient', 'sample name in supplementary file', 'cartridge', 'covid status', 'rabbit id', 'patient response', 'alternative sample name', 'publication id', 'study_id', 'Sample ID', 'sample/subject id', 'samples of different individuals pooled', 'organoid line', 'tumor side', 'Mouse ID', 'swollen eyelid', 'sample prep', 'sample/time point', 'subject gender', 'slide tissue area', 'dissected embryo id number', 'patient/control id', 'sample id cat', 'run id', 'lane id', 'patient sample', 'subject/sample source id', 'Donor type', 'patient id no', 'patient reference', 'sample condition', 'batch_id', 'sample.name', 'repeated samples', 'sample pool', 'normal individual, Tissue', 'amyloid', 'sample_time', 'donor no', 'sample case', 'subject label', 'subject id/diagnosis', 'individuals', 'clone id', 'Twin Pair ID', 'person id', 'Sample code', 'virus taxon id', 'disrupted gene id', 'study sample number', 'paired patient', 'library barcode', 'sample beneath', 'number of individuals per sample', 'donor status', 'participant condition', 'cell samples', 'sample.type', 'Age of patient', 'donor group', 'organoid status', 'mouse exhibiting symptoms on the day of sample collection', 'array id', 'sex steroid priming', 'tumor identifier', 'donor line', 'tumor sample', 'flowcell id', 'sample status', 'Sample Group', 'hippocampal slice id', 'patient line', 'Sample Type', 'status sample', 'samples', 'animal id number', 'StudyID', 'donor strain', 'Sample', 'carcinoid syndrome', 'patient tumor related pain status', 'donor age, sex', 'donor race', 'Hybridization Time', 'mouse individual id', 'subject status/id', 'patient_status', 'mouse id tag', 'data analysis id', 'genotype of original donor', 'Patient Number', 'sample subgroup', 'manuscript library id', 'sample_label', 'incidence', 'patients', 'Lab ID', 'location/side', 'clone background/id', 'unique sample identifier', 'Sample group', 'strain id', 'group id', 'sample identifier', 'fetal lung tissue donor', 'internal patient id', 'internal sample id', 'donor fibroblasts', 'day of organoid differentiation', 'hydrogen peroxide treatment', 'donor id/status', 'array barcode', 'organoid generation', 'graft donor strain', 'original biopsy for this patient', 'cell model id', 'source id', 'tissue donor', 'treatment/sample type', 'subject identifier', 'number of_samples', 'peptide genotype', 'sample region', 'sample code', 'culture/clone_id', 'patient age at diagnosis', 'sample name synonym', 'Sample_reference', 'Subject_reference', 'source patient gender', 'strain donor', 'organoid formation', 'subject relationship', 'sample barcode', 'sample population', 'Sex of donor mice', 'tubules with elongated spermatids', 'tubules with round spermatids', 'age of donor/age of host', 'sample replicate number', 'fluid', 'sample state', 'hybrid', 'id', 'in-line barcodes', 'donor sex', 'donor gender', 'donor disease state', 'acidity', 'associate geo_sample', 'patient-derived cell line', 'sample age', 'antibody vendor id', 'control id', 'donor diagnosis', 'sample tag_information', 'organoid type', 'age of patient when tumor sample obtained', 'batch', 'replicate', 'plate', 'site', 'location', 'source', 'animal', 'clone', 'study', 'chip_antibody_lot', 'vital status', 'array', 'library date', 'chip antibody vendor', 'volunteer code', 'library', 'plate_number', 'volunteer', 'subset', 'family', 'line number', 'array batch', 'folder name', 'sort population', 'size', 'roi type', 'number of_mice', 'Subsets', 'replicates', 'library input', 'health_status', 'study number', 'bar code', 'person', 'vendor', 'pooled', 'Source', 'chip-antibody vendor', 'alternative_name', 'animal number', 'plate code', 'replicate type', 'antibody vendor name', 'library kit', 'vital_status', 'common name', 'family code', 'animal no', 'alternative name', 'sorted population', 'antibody vendor', 'radiation response', 'library backbone', 'number of animals', 'als status', 'nodal status', 'fraction/population', 'replicate number', 'hippocampal sclerosis', 'tubules with spermatocytes', 'number of_animals', 'associated geo', 'clip antibody vendor', 'enrollment batch', 'code', 'original geo accession', 'hospital', 'volunteer number', 'alias', 'pool no', 'Order Code', 'lab code']"
+Treatment,303,131474,"['treatment', 'group', 'vaccine', 'treatment description', 'treatmentshort', 'drug treatment', 'treatment group', 'control', 'control description', 'treatment duration', 'subgroup', 'groups', 'molecular subgroup', 'diagnostic_group', 'classification group', 'chemical compound', 'infected with/healthy control', 'vaccine doses', 'prior treatment', 'response_group', 'grouping', 'vaccine type', 'current medication', 'experiment group', 'treatment location', 'chemotherapy', 'Prior Treatment', 'treatment administration route', 'treatment frequency', 'study group', 'drug', 'experimental group', 'treatment dose', 'treatment arm', 'treatment withdrawal', 'treatment initiation', 'recreational drugs', 'prescription drugs', 'treatment-outcome code', 'radiation.therapy', 'treatment protocol', 'treatment response', 'enzymatic treatment', 'vaccine group', 'dose group', 'group description', 'inhibitor treatment', 'dose_group', 'batch group', 'previous treatments', 'vaccine regimen', 'drug dose', 'hours post-treatment', 'therapy used', 'Group', 'antibiotic treatment', 'healthy control', 'control/intervention', 'treatment status', 'ear treatment', 'therapy', 'compound', 'biological drug', 'treatment_duration', 'control or als', 'vector treatment', 'previous drug treatment', 'antibody group', 'surgical treatment', 'vaccine administered', 'rabbit group', 'treatment outcome', 'group label', 'treatment_duration_in_hours', 'treatment category', 'treatment prior to second surgery', 'vaccine administration', 'survival group', 'intervention group', 'prior chemotherapy', 'antibody treatment', 'main group', 'treatments', 'postsurgical-treatment', 'isogenic_group', 'drug concentration', 'first-line therapy', 'clinical group', 'treatment before challenge', 'chemical treatment', 'no treatment', 'treatment_effect', 'clinical_subgroup', 'treatment concentration', 'prior systemic therapy', 'current systemic therapy', 'treatment condition/type', 'pharmacologic treatment type', 'os_group_median', 'drug administration', 'treatment effect', 'duration of treatment', 'other treatment', 'growth medium/treatment', 'chemical probe', 'Treatment', 'treatment_type', 'drug response', 'drug resistance', 'compound concentration', 'experiment grouping', 'art treatment', 'treatment/infection', 'has_drug', 'seizure group', 'compound treatment', 'pretreatment', 'subset group', 'case or control', 'risk group', 'treatment of mice', 'treatment_dose', 'Drug', 'analysis group', 'chemical', 'chemical modification', 'chronic medication', 'acute medication', 'polarization treatment', 'treatment type', 'camp treatment/level', 'before or after treatment', 'knockout group', 'treatment timing', 'vaccine dose', 'selection pressure drugs', 'genotype/treatment', 'treatment/group', 'culture/treatment', 'exogenous treatment', 'animal treatment', 'genotype & treatment', 'group_tag', 'mice group', 'control source', 'treatment_term_name', 'segment type', 'response', 'resistance', 'animal replicate', 'classification', 'replicate description', 'genetic modification', 'brain location', 'experimental replicate', 'case/control', 'molecular subtype', 'protect outcome', 'other_medication', 'variant type', 'translocation', 'experimental repeat', 'genomic modification', 'donation source', 'tretment', 'genetic modifications', 'translocations', 'dementia status', 'polarization state', 'experimental run', 'antibody name', 'mutation frequency', 'nitrogen source', 'antibody lot', 'temperature', 'medium', 'tuberculin skin test', 'treated with', 'delivery', 'stimulus', 'chip_antibody', 'irradiated', 'first vaccination', 'second vaccination', 'selection marker', 'induced', 'injection_materials', 'curative_intent', 'media', 'amplification', 'ventilation', 'chip-antibody', 'diet', 'medications/vitamin names', 'stimulant', 'vaccination.assignment', 'surgical_interval_mo', 'active ingredient', 'knockout', 'primed', 'rip antibody', 'antibody manufacturer', 'diabetes_medication', 'chip antibody lot', 'knockdown', 'exposed stress', 'watch and wait', 'Exposures', 'vector', 'trial arm', 'surgery', 'prophylaxis', 'exercise intensity', 'challenge', 'surgery type', 'radiation', 'bone-marrow grafting status', 'bone-marrow grafting type', 'injected virus', 'alcohol', 'number of immunization boost', 'rounds_to_cure', 'clinical trial phase', 'other biologic medicines use', 'pathogen exposure', 'viral challenge', 'culture platform', 'debris removal', 'perturbation class', 'perturbation', 'cross-linked', 'route administered', 'vehicle', 'over-expression', 'length of exposure', 'nicotine', 'oxygen flow', 'radiation exposure', 'library prep kit', 'virus-stimulation', 'perturbation type', 'environment', 'inhibitor removal', 'medicine', 'untreated/treated', 'cultivation', 'growth temperature', 'implantation', 'vasopressor', 'modification', 'oxygen level', 'injected with', 'antibody target description', 'fed with', 'Shear exposure', 'desiccation', 'genetic engineering', 'construct expression', 'culture format', 'expression construct', 'fasting', 'mode of growth', 'gene_knockout', 'vaccination_status', 'antigenic stimulation', 'transplant', 'autophagy induction', 'oxygen tension', 'angiography', 'genetic_modification', 'surgical approach', 'plating', 'antibody used', 'antigen capture', 'rescue', 'intensive care', 'growth factors in the culture medium', 'antibody maker', 'overexpressing', 'growth phase/media', 'secondary antibody', 'primary antibody', 'transient expression', 'testosterone treated', 'gene induction', 'overexpressed target', 'methylation-enrichment', 'media supplement', 'chip antibody reference', 'stable knockdown', 'antibody cat', 'depletion', 'spike protein used', 'phase growth', 'oxygen status', 'strategy', 'media additions', 'culture supplement', 'affinity purification', 'ligation', 'selection media', 'solvent', 'transplanted with']"
+Biospecimen Organism,144,124692,"['strain', 'strain background', 'organismpart', 'organism part', 'cell organism', 'strain/background', 'mouse strain', 'background strain', 'mouse model', 'strain description', 'host', 'source_organism', 'Strain', 'strain/genotype', 'mouse number', 'mouse', 'parasite strain', 'OrganismPart', 'virus strain', 'malaria strain', 'strain name', 'host cell', 'mouse genotype/variation', 'replicate mouse', 'viral strain', 'host genotype', 'mouse line abbreviation', 'infected host', 'bacterial strain', 'host strain', 'mouse line', 'host mice strain', 'host vendor', 'host strain/background', 'mouse selection', 'genotype/strain', 'mouse age', 'laboratory strain', 'organism_status', 'recipient strain', 'organism_part', 'infection strain', 'strain info', 'parental strain', 'host cell line', 'cell line / strain', 'strain source', 'host organism', 'age and_strain', 'host cell type', 'Virus Strain', 'Mouse model', 'strain  background', 'host_cell_line', 'plasmodium strain', 'parental-strain', 'microorganism_source_of_infection', 'microorganism_blood', 'strain origin', 'spike-in organism', 'strain/isolate', 'pathogen strain', 'Mouse strain', 'mouse dietary condition', 'organism', 'human tissue source', 'strains', 'infection host', 'mouse group', 'parent_strain', 'strain/model', 'specific-host', 'host age', 'mouse status', 'mouse stain', 'species', 'graft recipient strain', 'host mouse strain', 'original strain', 'infectious strain', 'Species', 'host tissue', 'strain recipient', 'cell strain', 'Cell strain', 'mouse cell genotype/variation', 'human cell genotype/variation', 'human tumor cell line', 'strain_recipient', 'infrequent clonal strain code', 'host mouse_tissue', 'mouse genotype', 'mouse tissue', 'host cells', 'bacteria strain', 'mammalian host', 'genotype', 'genotype/variation', 'infected with', 'os_status', 'selection', 'OS status', 'genome/variation', 'couple number', 'pathogens', 'immune status', 'parasite line', 'viral status', 'parental origin', 'Genotype', 'specificity', 'specific', 'series', 'strand', 'genotype/varation', 'malaria status', 'ps status', 'stain', 'background mice', 'hot', 'virus', 'companion animals', 'agricultural animals', 'os', 'origin', 'pathogen', 'breed', 'bacterium', 'living', 'litter', 'virus type', 'cattle breed', 'viral genus', 'viral family', 'mosquito', 'Pathogen', 'geographical origin', 'virus subtype', 'bacteria', 'virus family', 'virus genus', 'genotype of founder fish', 'mice', 'life form']"
+Biospecimen Sex,20,104956,"['gender', 'Sex', 'sex', 'Gender', 'animal sex', 'fetal sex', 'biological sex', 'female', 'SEX', 'gender source', 'sex predicted', 'InfantSex', 'gender composition', 'placental sex', 'Sex of recipient mice', 'source gender', 'biologics', 'gene', 'biological source', 'nulliparous']"
+Other,411,93670,"['visit', 'segment', 'reference', 'datatype', 'tst', 'dataset', 'roi', 'date', 'biological replicate', 'assay', 'geographical region', 'labversion', 'roi number', 'protection', 'lab', 'class', 'area', 'library prep', 'pipeline version', 'censored', 'platesimple', 'experiment_type', 'albumin', 'hematocrit', 'hemoglobin', 'model', 'bin', 'birth_place', 'method', 'adjusted household density', 'geographic location', 'field_site', 'atmosphere', 'geographic origin', 'lane.number', 'center', 'weight', 'lane', 'sort', 'recipient', 'cluster', 'immature_granulocytes_percent', 'genotype_abbreviation', 'immature_granulocytes_absolute', 'allele actual', 'well address', 'plate_location', 'allele nominal', 'match', 'smear microscopy', 'instrument model', 'supplier', 'affy_batch', 'library prep_plate', 'assigned cluster', 'probe_detection', 'title', 'filtered peaks', 'extract name', 'assay name', 'project', 'hemisphere_name', 'platelet_count', 'multisector', 'injection_roi', 'array_design', 'cluster_label', 'is_technical_replicate', 'duplicate_pair', 'material support', 'library name', 'genome build', 'label', 'bait', 'chain', 'outlier', 'date collected', 'gene_count', 'nuclei count', 'technique', 'recruiting site', 'procedure date', 'smoking start date', 'smoking amount', 'smoking stop date', 'binding density', 'cap score', 'chip antibody cat', 'negative normalization factor', 'note', 'history', 'surface area', 'link', 'who', 'nuclei_counts', 'amplification cycles', 'smoke', 'visit_date', 'mean corpuscular volume', 'job/role', 'technical replicate', 'index', 'genetic testing', 'unpublished', 'city', 'datasets', 'volume', 'geographical location', 'training.test', 'used for analysis', 'block_name', 'structure acronym', 'set', 'read length', 'duplication_rate', 'align_unique', 'exon_ratio', 'align_input', 'reads_all', 'nuclear_reads', 'library_prep_date', 'extract_date', 'repeat', 'season', 'other information', 'sorting strategy', 'escape', 'diffuse', 'hist.score', 'feeding', 'bal sampling date', 'timing', 'processing', 'library quality', 'visit number', 'pair', 'run_date', 'muscle mass', 'waist to hip ratio', 'reference genome_for_processed_files', 'fat mass', 'reference genome_for_alignment', 'region of birth', 'period', 'buffer', 'extraction date', 'draw_date', 'comment', 'LabeledExtract', 'expanded allele cag repeat count', 'factor', 'paired material support', 'input', 'further operations', 'efficacy', 'buffer_volume', 'protein exchange', 'buffer_volume_unit', 'study_origin', 'library prep. kit', 'restriction enzyme', 'classifier_mes', 'aerosol.run', 'lane.ordinal', 'notes', 'adapter', 'target gene', 'Other', 'technology', 'sofa', 'application', 'country', 'met_amplification', 'other batch', 'date of array', 'batch.date', 'fragments in clean bam', 'sensor', 'spike-in', 'other', 'admission', 'circumstances', 'target', 'geo series', 'library strategy', 'geo accession', 'Filter number', 'cortical_score', 'striatal_score', 'channel count', 'reporter', 'roi lot', 'chemistry', 'purification', 'replicate # in experiment', 'progression_free_survival_censor', 'experiment year_month', 'instance', 'integrative analysis', 'panel', 'expression', 'adapter sequence', 'mib', 'geo expression data', 'replicate / experiment', 'ClinicalInformation', 'spike-ins', 'preservation method', 'tags', 'restriction enzymes', 'structure', 'backbone', 'genetic variants', 'risk', 'immune border', 'comments', 'cag repeat size', 'library_batch', 'enrichment method', 'library prep person', 'carbon source', 'corrector', 'coo', 'angiogenesis score', 'ras score', 'cag repeats', 'cycling', 'respirations per minute', 'cag length', 'commercial source', 'topography', 'kit mutation', 'library version', 'sort strategy', 'match degree', 'collected_by', 'platform', 'biological_replicate', 'genetic specifics', 'last follow-up', 'ago protein', 'kit', 'scan method', 'to concatenate', 'total bilirubin', 'littermate', 'processing batch', 'mean.corpuscular.volume', 'histone mark', 'modality', 'temp', 'nutritional state', 'Cluster', 'markers used for sorting', 'number cag repeats', 'experimental variables', 'gel_bead_version', 'pipeline.version', 'tau_score', 'profession', 'freezer', 'labor', 'data file subset', 'data type', 'Cycle', 'paired with', 'batch number', 'number of replicates', 'water salinity', 'locale', 'asbestos-fiber count', 'method of preservation', 'tandem repeat number', 'core code', 'chip-antibody cat', 'definite analysis', 'total volume', 'genetic variants inheritance', 'twins', 'virus accession number', 'note_other', 'test', 'promoter', 'preparation method', 'line name in manuscript', 'lactate', 'los', 'creatinine', 'tobacco', 'specific primer', 'culture results', 'run', 'sort fraction', 'variant', 'clinical', 'ectopic expression', 'biological replicates', 'percent_aligned', 'technical_replicate_number', 'biological_replicate_number', 'date_death', 'decode_name', 'sorting', 'chip processing date', 'Parity', 'calcium level', 'hospital admission', 'radiology', 'sort-gate', 'sort gate', 'stitched reads', 'raw reads', 'aligned reads', 'level', 'performance', 'vascular support', 'has_pressure', 'viral titre', 'pool', 'sorting fraction', 'oxygen', 'detachment', 'primers', 'gel bead version', 'rip', 'ubi', 'measure', 'Weight', 'pooling', 'functional connectivity', 'paradigm', 'div', 'sorting probe', 'product', 'oxygenation', 'expressing', 'operator', 'insertion site distance to gene', 'replica', 'scale', 'technical replicates', 'knockdown target', 'submission date', 'company', 'drinking', 'replicate experiment', 'chip antibody manufacturer', 'salt.score', 'library label_name', 'metabolic activity', 'animals pooled', 'isolated by', 'driver gene', 'transcription factor expression level', 'cutting enzymes', 'chip antibody details', 'antigen reactivity', 'number of cag repeats', 'data presented in the manuscript', 'hit.status', 'sorting criteria', 'well diameter in um', 'molecule purification', 'clinical comments', 'digestion enzyme', 'incubation temperature', 'chip antibody manufacturers', 'bilirubin', 'ast', 'encode accession', 'alt', 'variation', 'Labeling_reference', 'Extraction_reference', 'Extraction_amount', 'zone', 'mating pair', 'ARN_quality', 'extraction batch', 'mother from', 'expression level', 'nitrogen', 'tubular shadows', 'exposed pollutants', 'cross', 'behavior', 'mean number of oocysts', 'number of half-sclerotomes', 'Bra', 'body weight', 'sampling post confirm', 'library_strategy', 'term accession number', 'term source ref', 'experiment performed in', 'vector construct', 'chip magnetic beads', 'gating', 'express', 'isolation column', 'antibody lot number', 'antibody antibody description', 'immunology', 'details', 'reactivity', 'assay type', 'clip antibody cat', 'feature type', 'domain', 'par-clip', 'data_type']"
+Biospecimen Race,10,19755,"['ethnicity', 'race', 'Race', 'Ethnicity', 'self_reported_race', 'race/ethnicity', 'ethnic group', 'Ethnic group', 'race_ethnicity', 'ancestry']"
+Treatment Dosage Regimen,63,19368,"['protocol', 'dose', 'extraction_protocol', 'chip_protocol_chromatin_amount', 'chip_protocol', 'chip_protocol_bead_type', 'chip_protocol_antibody_amount', 'chip_protocol_bead_amount', 'growth protocol', 'duration', 'immunization dose', 'protocol description', 'concentration', 'regimen', 'library protocol', 'duration of illness', 'culture duration', 'protocol number', 'stimulation protocol', 'stimulation duration', 'vaccination dose', 'infectious_dose', 'illness_duration', 'psoriasis duration', 'extract_protocol', 'duration in hours', 'extract protocol', 'viral concentration', 'study protocol', 'lung radiation dose', 'Duration of psoriasis', 'Induration', 'digestion protocol', 'labeling protocol', 'library preparation protocol', 'virus dose', 'inoculation dose', 'dietary regiment', 'duration of cultivation', 'symptom duration', 'Extraction_concentration', 'protocols', 'extraction_protocol_fragmentation', 'duration_units', 'region', 'library preparation method', 'vaccination', 'mutation', 'education', 'library preparation', 'immunization', 'vaccination route', 'vaccination boost', 'derivation', 'induction', 'inoculation', 'indication', 'virus added', 'vaccination state', 'immunization route', 'culture variation', 'schedule', 'weekly dosing']"
diff --git a/RDAS_RDOMICS/paper_materials/supplementary_files/Supp.file_6_Fine_grained_subcategories_sample_characteristics.xlsx b/RDAS_RDOMICS/paper_materials/supplementary_files/Supp.file_6_Fine_grained_subcategories_sample_characteristics.xlsx
new file mode 100644
index 0000000..77b2aad
Binary files /dev/null and b/RDAS_RDOMICS/paper_materials/supplementary_files/Supp.file_6_Fine_grained_subcategories_sample_characteristics.xlsx differ
diff --git a/RDAS_RDOMICS/paper_materials/supplementary_files/Supp.file_7_RD_GES_list.xlsx b/RDAS_RDOMICS/paper_materials/supplementary_files/Supp.file_7_RD_GES_list.xlsx
new file mode 100644
index 0000000..a7b43ff
Binary files /dev/null and b/RDAS_RDOMICS/paper_materials/supplementary_files/Supp.file_7_RD_GES_list.xlsx differ
diff --git a/RDAS_RDOMICS/paper_materials/supplementary_files/Supp.file_8_GEO_GBM_search.pdf b/RDAS_RDOMICS/paper_materials/supplementary_files/Supp.file_8_GEO_GBM_search.pdf
new file mode 100644
index 0000000..a489747
Binary files /dev/null and b/RDAS_RDOMICS/paper_materials/supplementary_files/Supp.file_8_GEO_GBM_search.pdf differ
diff --git a/RDAS_RDOMICS/paper_materials/supplementary_files/Supp.file_9_RD-OMICS_case_study.xlsx b/RDAS_RDOMICS/paper_materials/supplementary_files/Supp.file_9_RD-OMICS_case_study.xlsx
new file mode 100644
index 0000000..0b49c95
Binary files /dev/null and b/RDAS_RDOMICS/paper_materials/supplementary_files/Supp.file_9_RD-OMICS_case_study.xlsx differ
diff --git a/RDAS_RDOMICS/requirements-llm.txt b/RDAS_RDOMICS/requirements-llm.txt
new file mode 100644
index 0000000..f32c774
--- /dev/null
+++ b/RDAS_RDOMICS/requirements-llm.txt
@@ -0,0 +1,2 @@
+-r requirements.txt
+vllm
diff --git a/RDAS_RDOMICS/requirements.txt b/RDAS_RDOMICS/requirements.txt
new file mode 100644
index 0000000..a9a99fc
--- /dev/null
+++ b/RDAS_RDOMICS/requirements.txt
@@ -0,0 +1,10 @@
+beautifulsoup4
+biopython
+neo4j
+nltk
+numpy
+openpyxl
+pandas
+PyYAML
+requests
+tqdm
diff --git a/RDAS_RDOMICS/scripts/__init__.py b/RDAS_RDOMICS/scripts/__init__.py
new file mode 100644
index 0000000..196db18
--- /dev/null
+++ b/RDAS_RDOMICS/scripts/__init__.py
@@ -0,0 +1 @@
+"""RDAS_RDOMICS pipeline scripts."""
diff --git a/RDAS_RDOMICS/scripts/check_unique_comb/check_amount_of_unique_normalized_combo.py b/RDAS_RDOMICS/scripts/check_unique_comb/check_amount_of_unique_normalized_combo.py
new file mode 100644
index 0000000..963778f
--- /dev/null
+++ b/RDAS_RDOMICS/scripts/check_unique_comb/check_amount_of_unique_normalized_combo.py
@@ -0,0 +1,68 @@
+import pandas as pd
+import numpy as np
+from pathlib import Path
+import sys
+
+CURRENT_DIR = Path(__file__).resolve().parent
+SCRIPTS_DIR = CURRENT_DIR.parent
+if str(SCRIPTS_DIR) not in sys.path:
+    sys.path.insert(0, str(SCRIPTS_DIR))
+
+from utils import load_paths
+
+paths = load_paths()
+df = pd.read_csv(paths['experiment_normalization_rules'])
+
+print("=== Dataset Overview ===")
+print(f"Total rows in dataset: {len(df)}")
+print(f"Dataset shape: {df.shape}")
+print()
+
+print("=== Column Information ===")
+print("Columns in the dataset:")
+for col in df.columns:
+    print(f"  - {col}")
+print()
+
+print("=== Unique Values Analysis ===")
+print(f"Unique values in 'Omics_type_norm': {df['Omics_type_norm'].nunique()}")
+print(f"Unique values in 'Sequencing_library_norm': {df['Sequencing_library_norm'].nunique()}")
+print()
+
+print("=== Unique Combinations ===")
+# Get unique combinations of the two columns
+unique_combinations = df[['Omics_type_norm', 'Sequencing_library_norm']].drop_duplicates()
+print(f"Total unique combinations of 'Omics_type_norm' and 'Sequencing_library_norm': {len(unique_combinations)}")
+print()
+
+print("=== All Unique Combinations ===")
+print("Omics_type_norm | Sequencing_library_norm")
+print("-" * 50)
+for idx, row in unique_combinations.iterrows():
+    omics_type = row['Omics_type_norm']
+    seq_lib = row['Sequencing_library_norm']
+    # Handle NaN values
+    if pd.isna(seq_lib):
+        seq_lib = "NaN/Empty"
+    print(f"{omics_type} | {seq_lib}")
+
+print()
+print("=== Frequency of Each Combination ===")
+combination_counts = df.groupby(['Omics_type_norm', 'Sequencing_library_norm']).size().reset_index(name='count')
+combination_counts = combination_counts.sort_values('count', ascending=False)
+print("Omics_type_norm | Sequencing_library_norm | Count")
+print("-" * 60)
+for idx, row in combination_counts.iterrows():
+    omics_type = row['Omics_type_norm']
+    seq_lib = row['Sequencing_library_norm']
+    count = row['count']
+    # Handle NaN values
+    if pd.isna(seq_lib):
+        seq_lib = "NaN/Empty"
+    print(f"{omics_type} | {seq_lib} | {count}")
+
+print()
+print("=== Summary Statistics ===")
+print(f"Most common combination appears {combination_counts['count'].max()} times")
+print(f"Least common combination appears {combination_counts['count'].min()} times")
+print(f"Average frequency per combination: {combination_counts['count'].mean():.2f}")
diff --git a/RDAS_RDOMICS/scripts/check_unique_comb/check_unique_omics_type_comb.py b/RDAS_RDOMICS/scripts/check_unique_comb/check_unique_omics_type_comb.py
new file mode 100644
index 0000000..9432416
--- /dev/null
+++ b/RDAS_RDOMICS/scripts/check_unique_comb/check_unique_omics_type_comb.py
@@ -0,0 +1,25 @@
+import pandas as pd
+from pathlib import Path
+import sys
+
+CURRENT_DIR = Path(__file__).resolve().parent
+SCRIPTS_DIR = CURRENT_DIR.parent
+if str(SCRIPTS_DIR) not in sys.path:
+    sys.path.insert(0, str(SCRIPTS_DIR))
+
+from utils import load_paths
+
+paths = load_paths()
+df = pd.read_csv(f"{paths['node_csv_files']}/experiment_node.csv")
+
+# Select the relevant columns
+df_subset = df[['Omics_type', 'Sequencing_type', 'Sequencing_library']]
+
+# Get unique combinations, including rows with NaN in either column
+unique_combinations = df_subset.drop_duplicates()
+
+# Sort (optional)
+unique_combinations = unique_combinations.sort_values(by=['Omics_type', 'Sequencing_type', 'Sequencing_library'])
+
+# Save to CSV
+unique_combinations.to_csv("omics_sequencing_combinations2.csv", index=False)
diff --git a/RDAS_RDOMICS/scripts/check_unique_comb/check_unique_sample_characteristics.py b/RDAS_RDOMICS/scripts/check_unique_comb/check_unique_sample_characteristics.py
new file mode 100644
index 0000000..749ae31
--- /dev/null
+++ b/RDAS_RDOMICS/scripts/check_unique_comb/check_unique_sample_characteristics.py
@@ -0,0 +1,34 @@
+import pandas as pd
+from collections import Counter
+from pathlib import Path
+import sys
+
+CURRENT_DIR = Path(__file__).resolve().parent
+SCRIPTS_DIR = CURRENT_DIR.parent
+if str(SCRIPTS_DIR) not in sys.path:
+    sys.path.insert(0, str(SCRIPTS_DIR))
+
+from utils import load_paths
+
+paths = load_paths()
+df = pd.read_csv(f"{paths['node_csv_files']}/sample_node.csv")
+
+# Initialize a counter for keys
+key_counter = Counter()
+
+# Iterate through the 'Sample_characteristics' column
+for entry in df['Sample_characteristics'].dropna():
+    for item in entry.split(';'):
+        item = item.strip()
+        if ':' in item:
+            key = item.split(':', 1)[0].strip()
+            key_counter[key] += 1
+
+# Convert to DataFrame
+key_df = pd.DataFrame(key_counter.items(), columns=['name', 'count'])
+
+# Sort by count descending (optional)
+key_df = key_df.sort_values(by='count', ascending=False)
+
+# Save to CSV
+key_df.to_csv("sample_characteristics_key_count.csv", index=False)
diff --git a/RDAS_RDOMICS/scripts/check_unique_comb/omics_sequencing_combinations.csv b/RDAS_RDOMICS/scripts/check_unique_comb/omics_sequencing_combinations.csv
new file mode 100644
index 0000000..2b8de7f
--- /dev/null
+++ b/RDAS_RDOMICS/scripts/check_unique_comb/omics_sequencing_combinations.csv
@@ -0,0 +1,167 @@
+Omics_type,Sequencing_type
+['Epigenomics'],ATAC-seq
+['Epigenomics'],Bisulfite-Seq
+['Epigenomics'],ChIA-PET
+['Epigenomics'],ChIP-Seq
+['Epigenomics'],DNase-Hypersensitivity
+['Epigenomics'],FAIRE-seq
+['Epigenomics'],Hi-C
+['Epigenomics'],MBD-Seq
+['Epigenomics'],MNase-Seq
+['Epigenomics'],MeDIP-Seq
+['Epigenomics'],OTHER
+['Epigenomics'],RNA-Seq
+['Epigenomics'],"['', 'Bisulfite-Seq', 'ChIP-Seq', 'RNA-Seq']"
+['Epigenomics'],"['ATAC-seq', 'ChIP-Seq']"
+['Epigenomics'],"['ATAC-seq', 'OTHER', 'RNA-Seq']"
+['Epigenomics'],"['Bisulfite-Seq', 'ChIP-Seq', 'MeDIP-Seq']"
+['Epigenomics'],"['Bisulfite-Seq', 'ChIP-Seq', 'OTHER']"
+['Epigenomics'],"['Bisulfite-Seq', 'OTHER']"
+['Epigenomics'],"['ChIP-Seq', 'DNase-Hypersensitivity']"
+['Epigenomics'],"['ChIP-Seq', 'FAIRE-seq']"
+['Epigenomics'],"['ChIP-Seq', 'MNase-Seq']"
+['Epigenomics'],"['ChIP-Seq', 'MeDIP-Seq']"
+['Epigenomics'],"['ChIP-Seq', 'OTHER']"
+['Epigenomics'],"['ChIP-Seq', 'RNA-Seq']"
+['Epigenomics'],
+"['Genome sequencing and assembly, Genome sequencing, Transcriptome or Gene expression']",RNA-Seq
+"['Genome sequencing and assembly, Raw sequence reads']",RNA-Seq
+"['Genome sequencing and assembly, Raw sequence reads, Genome sequencing, Assembly']",RNA-Seq
+['Genome sequencing'],ChIP-Seq
+"['Genome sequencing, Exome, Transcriptome or Gene expression']",ATAC-seq
+"['Genome sequencing, Exome, Transcriptome or Gene expression']",RNA-Seq
+"['Genome sequencing, Exome, Transcriptome or Gene expression']","['ATAC-seq', 'RNA-Seq']"
+['Metagenome'],RNA-Seq
+['Phenotype or Genotype'],RNA-Seq
+['Phenotype or Genotype'],"['ATAC-seq', 'RNA-Seq']"
+['Proteome'],
+['Raw sequence reads'],ATAC-seq
+['Raw sequence reads'],ChIP-Seq
+['Raw sequence reads'],Hi-C
+['Raw sequence reads'],OTHER
+['Raw sequence reads'],RNA-Seq
+['Raw sequence reads'],"['ChIP-Seq', 'RIP-Seq']"
+['Raw sequence reads'],"['ChIP-Seq', 'RNA-Seq']"
+['Raw sequence reads'],"['Hi-C', 'OTHER', 'RNA-Seq']"
+['Raw sequence reads'],"['OTHER', 'RNA-Seq']"
+['Raw sequence reads'],"['RIP-Seq', 'RNA-Seq']"
+['Raw sequence reads'],
+"['Raw sequence reads, Epigenomics']","['ATAC-seq', 'ChIP-Seq', 'RNA-Seq']"
+"['Raw sequence reads, Genome sequencing, Epigenomics, Transcriptome or Gene expression, Other']","['ATAC-seq', 'ChIP-Seq']"
+"['Raw sequence reads, Genome sequencing, Transcriptome or Gene expression']",RNA-Seq
+"['Raw sequence reads, Targeted Locus (Loci), Transcriptome or Gene expression']",RNA-Seq
+"['Raw sequence reads, Transcriptome or Gene expression']",OTHER
+"['Raw sequence reads, Transcriptome or Gene expression']",RNA-Seq
+['Targeted Locus (Loci)'],RNA-Seq
+['Transcriptome or Gene expression'],ATAC-seq
+['Transcriptome or Gene expression'],Bisulfite-Seq
+['Transcriptome or Gene expression'],Hi-C
+['Transcriptome or Gene expression'],OTHER
+['Transcriptome or Gene expression'],RIP-Seq
+['Transcriptome or Gene expression'],RNA-Seq
+['Transcriptome or Gene expression'],"['', 'RNA-Seq']"
+['Transcriptome or Gene expression'],"['Bisulfite-Seq', 'RNA-Seq']"
+['Transcriptome or Gene expression'],"['OTHER', 'RNA-Seq']"
+['Transcriptome or Gene expression'],"['RIP-Seq', 'RNA-Seq', 'ncRNA-Seq']"
+['Transcriptome or Gene expression'],"['RIP-Seq', 'RNA-Seq']"
+['Transcriptome or Gene expression'],"['RNA-Seq', 'miRNA-Seq']"
+['Transcriptome or Gene expression'],"['RNA-Seq', 'ncRNA-Seq']"
+['Transcriptome or Gene expression'],"['RNA-Seq', 'ssRNA-seq']"
+['Transcriptome or Gene expression'],[]
+['Transcriptome or Gene expression'],miRNA-Seq
+['Transcriptome or Gene expression'],ncRNA-Seq
+['Transcriptome or Gene expression'],ssRNA-seq
+['Transcriptome or Gene expression'],
+['Variation'],ChIP-Seq
+['Variation'],OTHER
+['Variation'],RNA-Seq
+['Variation'],
+[],ATAC-seq
+[],Bisulfite-Seq
+[],ChIP-Seq
+[],DNase-Hypersensitivity
+[],Hi-C
+[],OTHER
+[],RIP-Seq
+[],RNA-Seq
+[],SELEX
+[],Tn-Seq
+[],"['', 'ATAC-seq', 'Bisulfite-Seq', 'ChIP-Seq', 'RNA-Seq']"
+[],"['', 'ATAC-seq']"
+[],"['', 'Bisulfite-Seq', 'RNA-Seq']"
+[],"['', 'Bisulfite-Seq']"
+[],"['', 'ChIP-Seq', 'DNase-Hypersensitivity', 'OTHER']"
+[],"['', 'ChIP-Seq', 'DNase-Hypersensitivity', 'RNA-Seq']"
+[],"['', 'ChIP-Seq', 'DNase-Hypersensitivity']"
+[],"['', 'ChIP-Seq', 'FAIRE-seq', 'RNA-Seq']"
+[],"['', 'ChIP-Seq', 'OTHER', 'RNA-Seq']"
+[],"['', 'ChIP-Seq', 'OTHER']"
+[],"['', 'ChIP-Seq', 'RNA-Seq']"
+[],"['', 'ChIP-Seq']"
+[],"['', 'DNase-Hypersensitivity']"
+[],"['', 'MeDIP-Seq']"
+[],"['', 'OTHER', 'RNA-Seq']"
+[],"['', 'OTHER']"
+[],"['', 'RNA-Seq', 'miRNA-Seq']"
+[],"['', 'RNA-Seq']"
+[],"['', 'miRNA-Seq']"
+[],"['', 'ncRNA-Seq']"
+[],"['ATAC-seq', 'Bisulfite-Seq', 'ChIP-Seq', 'OTHER', 'RNA-Seq']"
+[],"['ATAC-seq', 'Bisulfite-Seq', 'ChIP-Seq', 'RNA-Seq']"
+[],"['ATAC-seq', 'Bisulfite-Seq', 'OTHER', 'RNA-Seq']"
+[],"['ATAC-seq', 'Bisulfite-Seq', 'RNA-Seq']"
+[],"['ATAC-seq', 'ChIP-Seq', 'Hi-C', 'OTHER', 'RNA-Seq']"
+[],"['ATAC-seq', 'ChIP-Seq', 'Hi-C', 'RNA-Seq']"
+[],"['ATAC-seq', 'ChIP-Seq', 'Hi-C']"
+[],"['ATAC-seq', 'ChIP-Seq', 'MeDIP-Seq', 'OTHER', 'RNA-Seq']"
+[],"['ATAC-seq', 'ChIP-Seq', 'OTHER', 'RNA-Seq']"
+[],"['ATAC-seq', 'ChIP-Seq', 'RNA-Seq']"
+[],"['ATAC-seq', 'ChIP-Seq']"
+[],"['ATAC-seq', 'Hi-C', 'OTHER']"
+[],"['ATAC-seq', 'OTHER', 'RIP-Seq', 'RNA-Seq', 'miRNA-Seq', 'ssRNA-seq']"
+[],"['ATAC-seq', 'OTHER', 'RNA-Seq']"
+[],"['ATAC-seq', 'OTHER']"
+[],"['ATAC-seq', 'RNA-Seq', 'miRNA-Seq']"
+[],"['ATAC-seq', 'RNA-Seq']"
+[],"['Bisulfite-Seq', 'ChIP-Seq', 'Hi-C', 'OTHER', 'RNA-Seq']"
+[],"['Bisulfite-Seq', 'ChIP-Seq', 'OTHER', 'RNA-Seq']"
+[],"['Bisulfite-Seq', 'ChIP-Seq', 'OTHER']"
+[],"['Bisulfite-Seq', 'ChIP-Seq', 'RNA-Seq']"
+[],"['Bisulfite-Seq', 'ChIP-Seq']"
+[],"['Bisulfite-Seq', 'MNase-Seq', 'RNA-Seq']"
+[],"['Bisulfite-Seq', 'OTHER', 'RNA-Seq']"
+[],"['Bisulfite-Seq', 'OTHER']"
+[],"['Bisulfite-Seq', 'RNA-Seq']"
+[],"['ChIA-PET', 'ChIP-Seq', 'OTHER', 'RNA-Seq']"
+[],"['ChIP-Seq', 'Hi-C', 'OTHER', 'RIP-Seq', 'RNA-Seq']"
+[],"['ChIP-Seq', 'Hi-C', 'OTHER', 'RNA-Seq']"
+[],"['ChIP-Seq', 'Hi-C', 'RNA-Seq']"
+[],"['ChIP-Seq', 'OTHER', 'RNA-Seq', 'WGS']"
+[],"['ChIP-Seq', 'OTHER', 'RNA-Seq']"
+[],"['ChIP-Seq', 'OTHER']"
+[],"['ChIP-Seq', 'RIP-Seq', 'RNA-Seq']"
+[],"['ChIP-Seq', 'RIP-Seq']"
+[],"['ChIP-Seq', 'RNA-Seq']"
+[],"['DNase-Hypersensitivity', 'RNA-Seq']"
+[],"['FAIRE-seq', 'RNA-Seq']"
+[],"['Hi-C', 'OTHER', 'RNA-Seq']"
+[],"['Hi-C', 'OTHER']"
+[],"['Hi-C', 'RNA-Seq']"
+[],"['MNase-Seq', 'OTHER', 'RNA-Seq']"
+[],"['MeDIP-Seq', 'RNA-Seq']"
+[],"['OTHER', 'RIP-Seq', 'RNA-Seq']"
+[],"['OTHER', 'RIP-Seq']"
+[],"['OTHER', 'RNA-Seq', 'miRNA-Seq']"
+[],"['OTHER', 'RNA-Seq', 'ncRNA-Seq']"
+[],"['OTHER', 'RNA-Seq']"
+[],"['OTHER', 'ssRNA-seq']"
+[],"['RIP-Seq', 'RNA-Seq', 'ncRNA-Seq']"
+[],"['RIP-Seq', 'RNA-Seq']"
+[],"['RIP-Seq', 'ncRNA-Seq']"
+[],"['RNA-Seq', 'miRNA-Seq']"
+[],"['RNA-Seq', 'ncRNA-Seq']"
+[],"['RNA-Seq', 'ssRNA-seq']"
+[],[]
+[],ncRNA-Seq
+[],ssRNA-seq
+[],
diff --git a/RDAS_RDOMICS/scripts/check_unique_comb/omics_sequencing_combinations2.csv b/RDAS_RDOMICS/scripts/check_unique_comb/omics_sequencing_combinations2.csv
new file mode 100644
index 0000000..2741004
--- /dev/null
+++ b/RDAS_RDOMICS/scripts/check_unique_comb/omics_sequencing_combinations2.csv
@@ -0,0 +1,317 @@
+Omics_type,Sequencing_type,Sequencing_library
+['Epigenomics'],ATAC-seq,genomic DNA
+['Epigenomics'],ATAC-seq,polyA RNA
+['Epigenomics'],Bisulfite-Seq,genomic DNA
+['Epigenomics'],Bisulfite-Seq,total RNA
+['Epigenomics'],ChIA-PET,genomic DNA
+['Epigenomics'],ChIP-Seq,genomic DNA
+['Epigenomics'],DNase-Hypersensitivity,genomic DNA
+['Epigenomics'],FAIRE-seq,genomic DNA
+['Epigenomics'],Hi-C,genomic DNA
+['Epigenomics'],MBD-Seq,genomic DNA
+['Epigenomics'],MBD-Seq,other
+['Epigenomics'],MNase-Seq,genomic DNA
+['Epigenomics'],MeDIP-Seq,genomic DNA
+['Epigenomics'],OTHER,"['genomic DNA', 'other']"
+['Epigenomics'],OTHER,genomic DNA
+['Epigenomics'],OTHER,polyA RNA
+['Epigenomics'],RNA-Seq,genomic DNA
+['Epigenomics'],RNA-Seq,polyA RNA
+['Epigenomics'],RNA-Seq,total RNA
+['Epigenomics'],"['', 'Bisulfite-Seq', 'ChIP-Seq', 'RNA-Seq']","['genomic DNA', 'total RNA']"
+['Epigenomics'],"['ATAC-seq', 'ChIP-Seq']",genomic DNA
+['Epigenomics'],"['ATAC-seq', 'OTHER', 'RNA-Seq']","['genomic DNA', 'total RNA']"
+['Epigenomics'],"['Bisulfite-Seq', 'ChIP-Seq', 'MeDIP-Seq']",genomic DNA
+['Epigenomics'],"['Bisulfite-Seq', 'ChIP-Seq', 'OTHER']",genomic DNA
+['Epigenomics'],"['Bisulfite-Seq', 'OTHER']",genomic DNA
+['Epigenomics'],"['ChIP-Seq', 'DNase-Hypersensitivity']",genomic DNA
+['Epigenomics'],"['ChIP-Seq', 'FAIRE-seq']",genomic DNA
+['Epigenomics'],"['ChIP-Seq', 'MNase-Seq']",genomic DNA
+['Epigenomics'],"['ChIP-Seq', 'MeDIP-Seq']",genomic DNA
+['Epigenomics'],"['ChIP-Seq', 'OTHER']",genomic DNA
+['Epigenomics'],"['ChIP-Seq', 'RNA-Seq']","['genomic DNA', 'polyA RNA']"
+['Epigenomics'],,"['genomic DNA', 'total RNA']"
+['Epigenomics'],,genomic DNA
+['Epigenomics'],,total RNA
+"['Genome sequencing and assembly, Genome sequencing, Transcriptome or Gene expression']",RNA-Seq,polyA RNA
+"['Genome sequencing and assembly, Raw sequence reads']",RNA-Seq,polyA RNA
+"['Genome sequencing and assembly, Raw sequence reads, Genome sequencing, Assembly']",RNA-Seq,total RNA
+['Genome sequencing'],ChIP-Seq,genomic DNA
+"['Genome sequencing, Exome, Transcriptome or Gene expression']",ATAC-seq,genomic DNA
+"['Genome sequencing, Exome, Transcriptome or Gene expression']",RNA-Seq,total RNA
+"['Genome sequencing, Exome, Transcriptome or Gene expression']","['ATAC-seq', 'RNA-Seq']","['genomic DNA', 'total RNA']"
+['Metagenome'],RNA-Seq,total RNA
+['Phenotype or Genotype'],RNA-Seq,total RNA
+['Phenotype or Genotype'],"['ATAC-seq', 'RNA-Seq']","['genomic DNA', 'total RNA']"
+['Proteome'],,other
+['Proteome'],,protein
+['Raw sequence reads'],ATAC-seq,genomic DNA
+['Raw sequence reads'],ChIP-Seq,genomic DNA
+['Raw sequence reads'],Hi-C,genomic DNA
+['Raw sequence reads'],OTHER,"['polyA RNA', 'protein']"
+['Raw sequence reads'],OTHER,genomic DNA
+['Raw sequence reads'],OTHER,polyA RNA
+['Raw sequence reads'],RNA-Seq,polyA RNA
+['Raw sequence reads'],RNA-Seq,total RNA
+['Raw sequence reads'],"['ChIP-Seq', 'RIP-Seq']","['genomic DNA', 'total RNA']"
+['Raw sequence reads'],"['ChIP-Seq', 'RNA-Seq']","['genomic DNA', 'polyA RNA']"
+['Raw sequence reads'],"['Hi-C', 'OTHER', 'RNA-Seq']","['genomic DNA', 'total RNA']"
+['Raw sequence reads'],"['OTHER', 'RNA-Seq']","['polyA RNA', 'total RNA']"
+['Raw sequence reads'],"['RIP-Seq', 'RNA-Seq']","['polyA RNA', 'total RNA']"
+['Raw sequence reads'],,total RNA
+"['Raw sequence reads, Epigenomics']","['ATAC-seq', 'ChIP-Seq', 'RNA-Seq']","['genomic DNA', 'polyA RNA']"
+"['Raw sequence reads, Genome sequencing, Epigenomics, Transcriptome or Gene expression, Other']","['ATAC-seq', 'ChIP-Seq']",genomic DNA
+"['Raw sequence reads, Genome sequencing, Transcriptome or Gene expression']",RNA-Seq,total RNA
+"['Raw sequence reads, Targeted Locus (Loci), Transcriptome or Gene expression']",RNA-Seq,polyA RNA
+"['Raw sequence reads, Transcriptome or Gene expression']",OTHER,polyA RNA
+"['Raw sequence reads, Transcriptome or Gene expression']",RNA-Seq,polyA RNA
+['Targeted Locus (Loci)'],RNA-Seq,total RNA
+['Transcriptome or Gene expression'],ATAC-seq,genomic DNA
+['Transcriptome or Gene expression'],Bisulfite-Seq,genomic DNA
+['Transcriptome or Gene expression'],Hi-C,genomic DNA
+['Transcriptome or Gene expression'],OTHER,"['polyA RNA', 'protein']"
+['Transcriptome or Gene expression'],OTHER,"['polyA RNA', 'total RNA']"
+['Transcriptome or Gene expression'],OTHER,polyA RNA
+['Transcriptome or Gene expression'],OTHER,total RNA
+['Transcriptome or Gene expression'],RIP-Seq,polyA RNA
+['Transcriptome or Gene expression'],RIP-Seq,total RNA
+['Transcriptome or Gene expression'],RNA-Seq,"['cytoplasmic RNA', 'nuclear RNA']"
+['Transcriptome or Gene expression'],RNA-Seq,"['genomic DNA', 'polyA RNA']"
+['Transcriptome or Gene expression'],RNA-Seq,"['nuclear RNA', 'total RNA']"
+['Transcriptome or Gene expression'],RNA-Seq,"['other', 'polyA RNA', 'total RNA']"
+['Transcriptome or Gene expression'],RNA-Seq,"['other', 'polyA RNA']"
+['Transcriptome or Gene expression'],RNA-Seq,"['polyA RNA', 'protein', 'total RNA']"
+['Transcriptome or Gene expression'],RNA-Seq,"['polyA RNA', 'protein']"
+['Transcriptome or Gene expression'],RNA-Seq,"['polyA RNA', 'total RNA']"
+['Transcriptome or Gene expression'],RNA-Seq,"['protein', 'total RNA']"
+['Transcriptome or Gene expression'],RNA-Seq,cytoplasmic RNA
+['Transcriptome or Gene expression'],RNA-Seq,genomic DNA
+['Transcriptome or Gene expression'],RNA-Seq,nuclear RNA
+['Transcriptome or Gene expression'],RNA-Seq,polyA RNA
+['Transcriptome or Gene expression'],RNA-Seq,protein
+['Transcriptome or Gene expression'],RNA-Seq,total RNA
+['Transcriptome or Gene expression'],"['', 'RNA-Seq']",total RNA
+['Transcriptome or Gene expression'],"['Bisulfite-Seq', 'RNA-Seq']","['genomic DNA', 'polyA RNA']"
+['Transcriptome or Gene expression'],"['OTHER', 'RNA-Seq']","['other', 'total RNA']"
+['Transcriptome or Gene expression'],"['OTHER', 'RNA-Seq']","['polyA RNA', 'protein']"
+['Transcriptome or Gene expression'],"['OTHER', 'RNA-Seq']","['polyA RNA', 'total RNA']"
+['Transcriptome or Gene expression'],"['OTHER', 'RNA-Seq']","['protein', 'total RNA']"
+['Transcriptome or Gene expression'],"['OTHER', 'RNA-Seq']",total RNA
+['Transcriptome or Gene expression'],"['RIP-Seq', 'RNA-Seq', 'ncRNA-Seq']","['polyA RNA', 'total RNA']"
+['Transcriptome or Gene expression'],"['RIP-Seq', 'RNA-Seq']","['polyA RNA', 'total RNA']"
+['Transcriptome or Gene expression'],"['RIP-Seq', 'RNA-Seq']",total RNA
+['Transcriptome or Gene expression'],"['RNA-Seq', 'miRNA-Seq']","['polyA RNA', 'total RNA']"
+['Transcriptome or Gene expression'],"['RNA-Seq', 'miRNA-Seq']",total RNA
+['Transcriptome or Gene expression'],"['RNA-Seq', 'ncRNA-Seq']","['polyA RNA', 'total RNA']"
+['Transcriptome or Gene expression'],"['RNA-Seq', 'ncRNA-Seq']",total RNA
+['Transcriptome or Gene expression'],"['RNA-Seq', 'ssRNA-seq']",total RNA
+['Transcriptome or Gene expression'],[],[]
+['Transcriptome or Gene expression'],miRNA-Seq,other
+['Transcriptome or Gene expression'],miRNA-Seq,polyA RNA
+['Transcriptome or Gene expression'],miRNA-Seq,total RNA
+['Transcriptome or Gene expression'],ncRNA-Seq,"['cytoplasmic RNA', 'nuclear RNA', 'total RNA']"
+['Transcriptome or Gene expression'],ncRNA-Seq,other
+['Transcriptome or Gene expression'],ncRNA-Seq,total RNA
+['Transcriptome or Gene expression'],ssRNA-seq,polyA RNA
+['Transcriptome or Gene expression'],ssRNA-seq,total RNA
+['Transcriptome or Gene expression'],,"['cytoplasmic RNA', 'total RNA']"
+['Transcriptome or Gene expression'],,"['genomic DNA', 'total RNA']"
+['Transcriptome or Gene expression'],,"['other', 'total RNA']"
+['Transcriptome or Gene expression'],,"['polyA RNA', 'total RNA']"
+['Transcriptome or Gene expression'],,genomic DNA
+['Transcriptome or Gene expression'],,other
+['Transcriptome or Gene expression'],,polyA RNA
+['Transcriptome or Gene expression'],,total RNA
+['Variation'],ChIP-Seq,genomic DNA
+['Variation'],OTHER,"['genomic DNA', 'other']"
+['Variation'],OTHER,genomic DNA
+['Variation'],RNA-Seq,total RNA
+['Variation'],,"['genomic DNA', 'nuclear RNA']"
+['Variation'],,genomic DNA
+[],ATAC-seq,genomic DNA
+[],Bisulfite-Seq,genomic DNA
+[],ChIP-Seq,"['genomic DNA', 'polyA RNA']"
+[],ChIP-Seq,genomic DNA
+[],DNase-Hypersensitivity,genomic DNA
+[],Hi-C,genomic DNA
+[],OTHER,"['genomic DNA', 'other', 'polyA RNA']"
+[],OTHER,"['genomic DNA', 'other']"
+[],OTHER,"['genomic DNA', 'polyA RNA', 'protein']"
+[],OTHER,"['genomic DNA', 'polyA RNA']"
+[],OTHER,"['genomic DNA', 'total RNA']"
+[],OTHER,"['other', 'polyA RNA', 'protein']"
+[],OTHER,"['other', 'polyA RNA']"
+[],OTHER,"['other', 'total RNA']"
+[],OTHER,"['polyA RNA', 'protein']"
+[],OTHER,"['polyA RNA', 'total RNA']"
+[],OTHER,"['protein', 'total RNA']"
+[],OTHER,cytoplasmic RNA
+[],OTHER,genomic DNA
+[],OTHER,nuclear RNA
+[],OTHER,other
+[],OTHER,polyA RNA
+[],OTHER,protein
+[],OTHER,total RNA
+[],RIP-Seq,"['other', 'total RNA']"
+[],RIP-Seq,other
+[],RIP-Seq,polyA RNA
+[],RIP-Seq,total RNA
+[],RNA-Seq,"['cytoplasmic RNA', 'total RNA']"
+[],RNA-Seq,"['genomic DNA', 'total RNA']"
+[],RNA-Seq,"['other', 'polyA RNA', 'total RNA']"
+[],RNA-Seq,"['other', 'protein', 'total RNA']"
+[],RNA-Seq,"['polyA RNA', 'protein']"
+[],RNA-Seq,"['polyA RNA', 'total RNA']"
+[],RNA-Seq,"['protein', 'total RNA']"
+[],RNA-Seq,polyA RNA
+[],RNA-Seq,total RNA
+[],SELEX,protein
+[],Tn-Seq,genomic DNA
+[],"['', 'ATAC-seq', 'Bisulfite-Seq', 'ChIP-Seq', 'RNA-Seq']","['genomic DNA', 'polyA RNA', 'total RNA']"
+[],"['', 'ATAC-seq']",genomic DNA
+[],"['', 'Bisulfite-Seq', 'RNA-Seq']","['genomic DNA', 'total RNA']"
+[],"['', 'Bisulfite-Seq']","['genomic DNA', 'total RNA']"
+[],"['', 'Bisulfite-Seq']",genomic DNA
+[],"['', 'ChIP-Seq', 'DNase-Hypersensitivity', 'OTHER']",genomic DNA
+[],"['', 'ChIP-Seq', 'DNase-Hypersensitivity', 'RNA-Seq']","['genomic DNA', 'total RNA']"
+[],"['', 'ChIP-Seq', 'DNase-Hypersensitivity']","['genomic DNA', 'total RNA']"
+[],"['', 'ChIP-Seq', 'FAIRE-seq', 'RNA-Seq']","['genomic DNA', 'total RNA']"
+[],"['', 'ChIP-Seq', 'OTHER', 'RNA-Seq']","['genomic DNA', 'total RNA']"
+[],"['', 'ChIP-Seq', 'OTHER']","['genomic DNA', 'protein']"
+[],"['', 'ChIP-Seq', 'RNA-Seq']","['genomic DNA', 'polyA RNA', 'total RNA']"
+[],"['', 'ChIP-Seq', 'RNA-Seq']","['genomic DNA', 'polyA RNA']"
+[],"['', 'ChIP-Seq', 'RNA-Seq']","['genomic DNA', 'total RNA']"
+[],"['', 'ChIP-Seq']","['genomic DNA', 'total RNA']"
+[],"['', 'ChIP-Seq']",genomic DNA
+[],"['', 'DNase-Hypersensitivity']","['genomic DNA', 'total RNA']"
+[],"['', 'MeDIP-Seq']","['genomic DNA', 'total RNA']"
+[],"['', 'OTHER', 'RNA-Seq']","['genomic DNA', 'total RNA']"
+[],"['', 'OTHER']","['protein', 'total RNA']"
+[],"['', 'OTHER']",genomic DNA
+[],"['', 'OTHER']",total RNA
+[],"['', 'RNA-Seq', 'miRNA-Seq']","['genomic DNA', 'total RNA']"
+[],"['', 'RNA-Seq']","['genomic DNA', 'polyA RNA', 'total RNA']"
+[],"['', 'RNA-Seq']","['genomic DNA', 'polyA RNA']"
+[],"['', 'RNA-Seq']","['genomic DNA', 'total RNA']"
+[],"['', 'RNA-Seq']","['other', 'total RNA']"
+[],"['', 'RNA-Seq']","['polyA RNA', 'total RNA']"
+[],"['', 'RNA-Seq']","['protein', 'total RNA']"
+[],"['', 'RNA-Seq']",total RNA
+[],"['', 'miRNA-Seq']",total RNA
+[],"['', 'ncRNA-Seq']",total RNA
+[],"['ATAC-seq', 'Bisulfite-Seq', 'ChIP-Seq', 'OTHER', 'RNA-Seq']","['genomic DNA', 'total RNA']"
+[],"['ATAC-seq', 'Bisulfite-Seq', 'ChIP-Seq', 'RNA-Seq']","['genomic DNA', 'total RNA']"
+[],"['ATAC-seq', 'Bisulfite-Seq', 'OTHER', 'RNA-Seq']","['genomic DNA', 'total RNA']"
+[],"['ATAC-seq', 'Bisulfite-Seq', 'RNA-Seq']","['genomic DNA', 'total RNA']"
+[],"['ATAC-seq', 'Bisulfite-Seq', 'RNA-Seq']",polyA RNA
+[],"['ATAC-seq', 'ChIP-Seq', 'Hi-C', 'OTHER', 'RNA-Seq']","['genomic DNA', 'total RNA']"
+[],"['ATAC-seq', 'ChIP-Seq', 'Hi-C', 'RNA-Seq']","['genomic DNA', 'total RNA']"
+[],"['ATAC-seq', 'ChIP-Seq', 'Hi-C']",genomic DNA
+[],"['ATAC-seq', 'ChIP-Seq', 'MeDIP-Seq', 'OTHER', 'RNA-Seq']","['genomic DNA', 'polyA RNA']"
+[],"['ATAC-seq', 'ChIP-Seq', 'OTHER', 'RNA-Seq']","['genomic DNA', 'polyA RNA', 'total RNA']"
+[],"['ATAC-seq', 'ChIP-Seq', 'OTHER', 'RNA-Seq']","['genomic DNA', 'polyA RNA']"
+[],"['ATAC-seq', 'ChIP-Seq', 'OTHER', 'RNA-Seq']","['genomic DNA', 'total RNA']"
+[],"['ATAC-seq', 'ChIP-Seq', 'RNA-Seq']","['genomic DNA', 'polyA RNA']"
+[],"['ATAC-seq', 'ChIP-Seq', 'RNA-Seq']","['genomic DNA', 'total RNA']"
+[],"['ATAC-seq', 'ChIP-Seq']",genomic DNA
+[],"['ATAC-seq', 'Hi-C', 'OTHER']",genomic DNA
+[],"['ATAC-seq', 'OTHER', 'RIP-Seq', 'RNA-Seq', 'miRNA-Seq', 'ssRNA-seq']","['genomic DNA', 'other', 'polyA RNA', 'total RNA']"
+[],"['ATAC-seq', 'OTHER', 'RNA-Seq']","['genomic DNA', 'other', 'polyA RNA']"
+[],"['ATAC-seq', 'OTHER', 'RNA-Seq']","['genomic DNA', 'other', 'total RNA']"
+[],"['ATAC-seq', 'OTHER', 'RNA-Seq']","['genomic DNA', 'polyA RNA', 'total RNA']"
+[],"['ATAC-seq', 'OTHER', 'RNA-Seq']","['genomic DNA', 'polyA RNA']"
+[],"['ATAC-seq', 'OTHER', 'RNA-Seq']","['genomic DNA', 'protein', 'total RNA']"
+[],"['ATAC-seq', 'OTHER', 'RNA-Seq']","['genomic DNA', 'total RNA']"
+[],"['ATAC-seq', 'OTHER']","['genomic DNA', 'nuclear RNA']"
+[],"['ATAC-seq', 'OTHER']",genomic DNA
+[],"['ATAC-seq', 'RNA-Seq', 'miRNA-Seq']","['genomic DNA', 'polyA RNA', 'total RNA']"
+[],"['ATAC-seq', 'RNA-Seq']","['genomic DNA', 'nuclear RNA', 'total RNA']"
+[],"['ATAC-seq', 'RNA-Seq']","['genomic DNA', 'nuclear RNA']"
+[],"['ATAC-seq', 'RNA-Seq']","['genomic DNA', 'polyA RNA', 'total RNA']"
+[],"['ATAC-seq', 'RNA-Seq']","['genomic DNA', 'polyA RNA']"
+[],"['ATAC-seq', 'RNA-Seq']","['genomic DNA', 'total RNA']"
+[],"['ATAC-seq', 'RNA-Seq']","['other', 'total RNA']"
+[],"['ATAC-seq', 'RNA-Seq']",polyA RNA
+[],"['ATAC-seq', 'RNA-Seq']",total RNA
+[],"['Bisulfite-Seq', 'ChIP-Seq', 'Hi-C', 'OTHER', 'RNA-Seq']","['genomic DNA', 'polyA RNA']"
+[],"['Bisulfite-Seq', 'ChIP-Seq', 'OTHER', 'RNA-Seq']","['genomic DNA', 'total RNA']"
+[],"['Bisulfite-Seq', 'ChIP-Seq', 'OTHER']",genomic DNA
+[],"['Bisulfite-Seq', 'ChIP-Seq', 'RNA-Seq']","['genomic DNA', 'total RNA']"
+[],"['Bisulfite-Seq', 'ChIP-Seq']",genomic DNA
+[],"['Bisulfite-Seq', 'MNase-Seq', 'RNA-Seq']","['genomic DNA', 'total RNA']"
+[],"['Bisulfite-Seq', 'OTHER', 'RNA-Seq']","['genomic DNA', 'total RNA']"
+[],"['Bisulfite-Seq', 'OTHER']","['genomic DNA', 'polyA RNA']"
+[],"['Bisulfite-Seq', 'OTHER']",genomic DNA
+[],"['Bisulfite-Seq', 'RNA-Seq']","['genomic DNA', 'polyA RNA']"
+[],"['Bisulfite-Seq', 'RNA-Seq']","['genomic DNA', 'total RNA']"
+[],"['ChIA-PET', 'ChIP-Seq', 'OTHER', 'RNA-Seq']","['genomic DNA', 'polyA RNA']"
+[],"['ChIP-Seq', 'Hi-C', 'OTHER', 'RIP-Seq', 'RNA-Seq']","['genomic DNA', 'total RNA']"
+[],"['ChIP-Seq', 'Hi-C', 'OTHER', 'RNA-Seq']","['genomic DNA', 'total RNA']"
+[],"['ChIP-Seq', 'Hi-C', 'RNA-Seq']","['genomic DNA', 'total RNA']"
+[],"['ChIP-Seq', 'OTHER', 'RNA-Seq', 'WGS']","['genomic DNA', 'nuclear RNA', 'total RNA']"
+[],"['ChIP-Seq', 'OTHER', 'RNA-Seq']","['genomic DNA', 'other', 'total RNA']"
+[],"['ChIP-Seq', 'OTHER', 'RNA-Seq']","['genomic DNA', 'polyA RNA', 'total RNA']"
+[],"['ChIP-Seq', 'OTHER', 'RNA-Seq']","['genomic DNA', 'polyA RNA']"
+[],"['ChIP-Seq', 'OTHER', 'RNA-Seq']","['genomic DNA', 'total RNA']"
+[],"['ChIP-Seq', 'OTHER']","['genomic DNA', 'total RNA']"
+[],"['ChIP-Seq', 'OTHER']",genomic DNA
+[],"['ChIP-Seq', 'RIP-Seq', 'RNA-Seq']","['genomic DNA', 'polyA RNA', 'total RNA']"
+[],"['ChIP-Seq', 'RIP-Seq', 'RNA-Seq']",total RNA
+[],"['ChIP-Seq', 'RIP-Seq']","['genomic DNA', 'total RNA']"
+[],"['ChIP-Seq', 'RNA-Seq']","['genomic DNA', 'polyA RNA', 'total RNA']"
+[],"['ChIP-Seq', 'RNA-Seq']","['genomic DNA', 'polyA RNA']"
+[],"['ChIP-Seq', 'RNA-Seq']","['genomic DNA', 'total RNA']"
+[],"['ChIP-Seq', 'RNA-Seq']",total RNA
+[],"['DNase-Hypersensitivity', 'RNA-Seq']","['genomic DNA', 'total RNA']"
+[],"['FAIRE-seq', 'RNA-Seq']","['genomic DNA', 'polyA RNA']"
+[],"['Hi-C', 'OTHER', 'RNA-Seq']","['genomic DNA', 'total RNA']"
+[],"['Hi-C', 'OTHER']","['genomic DNA', 'polyA RNA']"
+[],"['Hi-C', 'RNA-Seq']","['genomic DNA', 'total RNA']"
+[],"['MNase-Seq', 'OTHER', 'RNA-Seq']","['genomic DNA', 'total RNA']"
+[],"['MeDIP-Seq', 'RNA-Seq']","['genomic DNA', 'total RNA']"
+[],"['OTHER', 'RIP-Seq', 'RNA-Seq']","['genomic DNA', 'polyA RNA', 'total RNA']"
+[],"['OTHER', 'RIP-Seq', 'RNA-Seq']",total RNA
+[],"['OTHER', 'RIP-Seq']","['genomic DNA', 'total RNA']"
+[],"['OTHER', 'RIP-Seq']",total RNA
+[],"['OTHER', 'RNA-Seq', 'miRNA-Seq']","['genomic DNA', 'polyA RNA', 'total RNA']"
+[],"['OTHER', 'RNA-Seq', 'ncRNA-Seq']",total RNA
+[],"['OTHER', 'RNA-Seq']","['cytoplasmic RNA', 'total RNA']"
+[],"['OTHER', 'RNA-Seq']","['genomic DNA', 'nuclear RNA']"
+[],"['OTHER', 'RNA-Seq']","['genomic DNA', 'other', 'polyA RNA']"
+[],"['OTHER', 'RNA-Seq']","['genomic DNA', 'polyA RNA', 'total RNA']"
+[],"['OTHER', 'RNA-Seq']","['genomic DNA', 'polyA RNA']"
+[],"['OTHER', 'RNA-Seq']","['genomic DNA', 'total RNA']"
+[],"['OTHER', 'RNA-Seq']","['nuclear RNA', 'other', 'polyA RNA']"
+[],"['OTHER', 'RNA-Seq']","['other', 'polyA RNA', 'protein']"
+[],"['OTHER', 'RNA-Seq']","['other', 'total RNA']"
+[],"['OTHER', 'RNA-Seq']","['polyA RNA', 'protein', 'total RNA']"
+[],"['OTHER', 'RNA-Seq']","['polyA RNA', 'protein']"
+[],"['OTHER', 'RNA-Seq']","['polyA RNA', 'total RNA']"
+[],"['OTHER', 'RNA-Seq']","['protein', 'total RNA']"
+[],"['OTHER', 'RNA-Seq']",polyA RNA
+[],"['OTHER', 'RNA-Seq']",total RNA
+[],"['OTHER', 'ssRNA-seq']","['polyA RNA', 'total RNA']"
+[],"['RIP-Seq', 'RNA-Seq', 'ncRNA-Seq']",total RNA
+[],"['RIP-Seq', 'RNA-Seq']","['other', 'total RNA']"
+[],"['RIP-Seq', 'RNA-Seq']","['polyA RNA', 'total RNA']"
+[],"['RIP-Seq', 'RNA-Seq']",polyA RNA
+[],"['RIP-Seq', 'RNA-Seq']",total RNA
+[],"['RIP-Seq', 'ncRNA-Seq']",total RNA
+[],"['RNA-Seq', 'miRNA-Seq']","['other', 'polyA RNA', 'total RNA']"
+[],"['RNA-Seq', 'miRNA-Seq']","['polyA RNA', 'total RNA']"
+[],"['RNA-Seq', 'miRNA-Seq']",total RNA
+[],"['RNA-Seq', 'ncRNA-Seq']","['polyA RNA', 'total RNA']"
+[],"['RNA-Seq', 'ncRNA-Seq']",total RNA
+[],"['RNA-Seq', 'ssRNA-seq']","['polyA RNA', 'total RNA']"
+[],[],[]
+[],ncRNA-Seq,total RNA
+[],ssRNA-seq,total RNA
+[],,"['genomic DNA', 'polyA RNA', 'total RNA']"
+[],,"['genomic DNA', 'total RNA']"
+[],,"['other', 'protein']"
+[],,"['other', 'total RNA']"
+[],,genomic DNA
+[],,other
+[],,polyA RNA
+[],,protein
+[],,total RNA
diff --git a/RDAS_RDOMICS/scripts/check_unique_comb/omics_sequencing_combinations2_normalization.csv b/RDAS_RDOMICS/scripts/check_unique_comb/omics_sequencing_combinations2_normalization.csv
new file mode 100644
index 0000000..d82f494
--- /dev/null
+++ b/RDAS_RDOMICS/scripts/check_unique_comb/omics_sequencing_combinations2_normalization.csv
@@ -0,0 +1,317 @@
+Omics_type,Sequencing_type,Sequencing_library,Omics_type_norm,Assay_type_norm,Sequencing_library_norm,Annotation
+['Epigenomics'],ATAC-seq,genomic DNA,Epigenomics,ATAC-seq,,"indicated by ""epigenoimcs"""
+['Epigenomics'],ATAC-seq,polyA RNA,Epigenomics,ATAC-seq,,"indicated by ""epigenoimcs"""
+['Epigenomics'],Bisulfite-Seq,genomic DNA,Epigenomics,Bisulfite-seq,,"indicated by ""epigenoimcs"""
+['Epigenomics'],Bisulfite-Seq,total RNA,Epigenomics,Bisulfite-seq,,"indicated by ""epigenoimcs"""
+['Epigenomics'],ChIA-PET,genomic DNA,Epigenomics,ChIA-PET,,"indicated by ""epigenoimcs"""
+['Epigenomics'],ChIP-Seq,genomic DNA,Epigenomics,ChIP-seq,,"indicated by ""epigenoimcs"""
+['Epigenomics'],DNase-Hypersensitivity,genomic DNA,Epigenomics,DNase-Hypersensitivity,,"indicated by ""epigenoimcs"""
+['Epigenomics'],FAIRE-seq,genomic DNA,Epigenomics,FAIRE-seq,,"indicated by ""epigenoimcs"""
+['Epigenomics'],Hi-C,genomic DNA,Epigenomics,Hi-C assay,,"indicated by ""epigenoimcs""and hi-c"
+['Epigenomics'],MBD-Seq,genomic DNA,Epigenomics,MBD-Seq,,"indicated by ""epigenoimcs"""
+['Epigenomics'],MBD-Seq,other,Epigenomics,MBD-Seq,,"indicated by ""epigenoimcs"""
+['Epigenomics'],MNase-Seq,genomic DNA,Epigenomics,MNase-Seq,,"indicated by ""epigenoimcs"""
+['Epigenomics'],MeDIP-Seq,genomic DNA,Epigenomics,MeDIP-Seq,,"indicated by ""epigenoimcs"""
+['Epigenomics'],OTHER,"['genomic DNA', 'other']",Epigenomics,Other,,"indicated by ""epigenoimcs"""
+['Epigenomics'],OTHER,genomic DNA,Epigenomics,Other,,"indicated by ""epigenoimcs"""
+['Epigenomics'],OTHER,polyA RNA,Epigenomics,Other,,"indicated by ""epigenoimcs"""
+['Epigenomics'],RNA-Seq,genomic DNA,Epigenomics,RNA-Seq,,"indicated by ""epigenoimcs"""
+['Epigenomics'],RNA-Seq,polyA RNA,Epigenomics,RNA-Seq,,"indicated by ""epigenoimcs"""
+['Epigenomics'],RNA-Seq,total RNA,Epigenomics,RNA-Seq,,"indicated by ""epigenoimcs"""
+['Epigenomics'],"['', 'Bisulfite-Seq', 'ChIP-Seq', 'RNA-Seq']","['genomic DNA', 'total RNA']",Epigenomics,Bisulfite-seq,,"indicated by ""epigenoimcs"""
+['Epigenomics'],"['ATAC-seq', 'ChIP-Seq']",genomic DNA,Epigenomics,ATAC-seq,,"indicated by ""epigenoimcs"""
+['Epigenomics'],"['ATAC-seq', 'OTHER', 'RNA-Seq']","['genomic DNA', 'total RNA']",Epigenomics,ATAC-seq,,"indicated by ""epigenoimcs"""
+['Epigenomics'],"['Bisulfite-Seq', 'ChIP-Seq', 'MeDIP-Seq']",genomic DNA,Epigenomics,Bisulfite-seq,,"indicated by ""epigenoimcs"""
+['Epigenomics'],"['Bisulfite-Seq', 'ChIP-Seq', 'OTHER']",genomic DNA,Epigenomics,Bisulfite-seq,,"indicated by ""epigenoimcs"""
+['Epigenomics'],"['Bisulfite-Seq', 'OTHER']",genomic DNA,Epigenomics,Bisulfite-seq,,"indicated by ""epigenoimcs"""
+['Epigenomics'],"['ChIP-Seq', 'DNase-Hypersensitivity']",genomic DNA,Epigenomics,ChIP-seq,,"indicated by ""epigenoimcs"""
+['Epigenomics'],"['ChIP-Seq', 'FAIRE-seq']",genomic DNA,Epigenomics,ChIP-seq,,"indicated by ""epigenoimcs"""
+['Epigenomics'],"['ChIP-Seq', 'MNase-Seq']",genomic DNA,Epigenomics,ChIP-seq,,"indicated by ""epigenoimcs"""
+['Epigenomics'],"['ChIP-Seq', 'MeDIP-Seq']",genomic DNA,Epigenomics,ChIP-seq,,"indicated by ""epigenoimcs"""
+['Epigenomics'],"['ChIP-Seq', 'OTHER']",genomic DNA,Epigenomics,ChIP-seq,,"indicated by ""epigenoimcs"""
+['Epigenomics'],"['ChIP-Seq', 'RNA-Seq']","['genomic DNA', 'polyA RNA']",Epigenomics,ChIP-seq,,"indicated by ""epigenoimcs"""
+['Epigenomics'],,"['genomic DNA', 'total RNA']",Epigenomics,Other,,"indicated by ""epigenoimcs"""
+['Epigenomics'],,genomic DNA,Epigenomics,Other,,"indicated by ""epigenoimcs"""
+['Epigenomics'],,total RNA,Epigenomics,Other,,"indicated by ""epigenoimcs"""
+"['Genome sequencing and assembly, Genome sequencing, Transcriptome or Gene expression']",RNA-Seq,polyA RNA,Transcriptomics,RNA-Seq,polyA RNA,
+"['Genome sequencing and assembly, Raw sequence reads']",RNA-Seq,polyA RNA,Transcriptomics,RNA-Seq,polyA RNA,
+"['Genome sequencing and assembly, Raw sequence reads, Genome sequencing, Assembly']",RNA-Seq,total RNA,Transcriptomics,RNA-Seq,total RNA,
+['Genome sequencing'],ChIP-Seq,genomic DNA,Epigenomics,ChIP-seq,,"indicated by ""ChIP-seq"""
+"['Genome sequencing, Exome, Transcriptome or Gene expression']",ATAC-seq,genomic DNA,Epigenomics,ATAC-seq,,"indicated by ""ATAC-seq"""
+"['Genome sequencing, Exome, Transcriptome or Gene expression']",RNA-Seq,total RNA,Transcriptomics,RNA-Seq,total RNA,
+"['Genome sequencing, Exome, Transcriptome or Gene expression']","['ATAC-seq', 'RNA-Seq']","['genomic DNA', 'total RNA']",Epigenomics,ATAC-seq,,"indicated by ""ATAC-seq"""
+['Metagenome'],RNA-Seq,total RNA,Genomics,Metagenomics ,,
+['Phenotype or Genotype'],RNA-Seq,total RNA,Transcriptomics,RNA-Seq,total RNA,
+['Phenotype or Genotype'],"['ATAC-seq', 'RNA-Seq']","['genomic DNA', 'total RNA']",Epigenomics,ATAC-seq,,"indicated by ""ATAC-seq"""
+['Proteome'],,other,Proteomics,Other,,
+['Proteome'],,protein,Proteomics,Other,,
+['Raw sequence reads'],ATAC-seq,genomic DNA,Epigenomics,ATAC-seq,,"indicated by ""ATAC-seq"""
+['Raw sequence reads'],ChIP-Seq,genomic DNA,Epigenomics,ChIP-seq,,"indicated by ""ChIP-seq"""
+['Raw sequence reads'],Hi-C,genomic DNA,Epigenomics,Hi-C assay,,"indicated by ""Hi-c"""
+['Raw sequence reads'],OTHER,"['polyA RNA', 'protein']",Transcriptomics,Other,,
+['Raw sequence reads'],OTHER,genomic DNA,Genomics,Other,,
+['Raw sequence reads'],OTHER,polyA RNA,Transcriptomics,Other,,
+['Raw sequence reads'],RNA-Seq,polyA RNA,Transcriptomics,RNA-Seq,,
+['Raw sequence reads'],RNA-Seq,total RNA,Transcriptomics,RNA-Seq,,
+['Raw sequence reads'],"['ChIP-Seq', 'RIP-Seq']","['genomic DNA', 'total RNA']",Epigenomics,ChIP-seq,,"indicated by ""ChIP-seq"""
+['Raw sequence reads'],"['ChIP-Seq', 'RNA-Seq']","['genomic DNA', 'polyA RNA']",Epigenomics,ChIP-seq,,"indicated by ""ChIP-seq"""
+['Raw sequence reads'],"['Hi-C', 'OTHER', 'RNA-Seq']","['genomic DNA', 'total RNA']",Epigenomics,Hi-C assay,,"indicated by ""Hi-c"""
+['Raw sequence reads'],"['OTHER', 'RNA-Seq']","['polyA RNA', 'total RNA']",Transcriptomics,RNA-Seq,,
+['Raw sequence reads'],"['RIP-Seq', 'RNA-Seq']","['polyA RNA', 'total RNA']",Epigenomics,RNA immunoprecipitation,,
+['Raw sequence reads'],,total RNA,Transcriptomics,Other,,
+"['Raw sequence reads, Epigenomics']","['ATAC-seq', 'ChIP-Seq', 'RNA-Seq']","['genomic DNA', 'polyA RNA']",Epigenomics,ATAC-seq,,"indicated by ""epigenoimcs"""
+"['Raw sequence reads, Genome sequencing, Epigenomics, Transcriptome or Gene expression, Other']","['ATAC-seq', 'ChIP-Seq']",genomic DNA,Epigenomics,ATAC-seq,,"indicated by ""epigenoimcs"""
+"['Raw sequence reads, Genome sequencing, Transcriptome or Gene expression']",RNA-Seq,total RNA,Transcriptomics,RNA-Seq,total RNA,
+"['Raw sequence reads, Targeted Locus (Loci), Transcriptome or Gene expression']",RNA-Seq,polyA RNA,Transcriptomics,RNA-Seq,polyA RNA,
+"['Raw sequence reads, Transcriptome or Gene expression']",OTHER,polyA RNA,Transcriptomics,Other,,
+"['Raw sequence reads, Transcriptome or Gene expression']",RNA-Seq,polyA RNA,Transcriptomics,RNA-Seq,polyA RNA,
+['Targeted Locus (Loci)'],RNA-Seq,total RNA,Transcriptomics,RNA-Seq,total RNA,
+['Transcriptome or Gene expression'],ATAC-seq,genomic DNA,Epigenomics,ATAC-seq,,"indicated by ""ATAC-seq"""
+['Transcriptome or Gene expression'],Bisulfite-Seq,genomic DNA,Epigenomics,Bisulfite-seq,,"indicated by ""bisulfite-seq"""
+['Transcriptome or Gene expression'],Hi-C,genomic DNA,Epigenomics,Hi-C assay,,"indicated by ""Hi-c"""
+['Transcriptome or Gene expression'],OTHER,"['polyA RNA', 'protein']",Transcriptomics,Other,,
+['Transcriptome or Gene expression'],OTHER,"['polyA RNA', 'total RNA']",Transcriptomics,Other,,
+['Transcriptome or Gene expression'],OTHER,polyA RNA,Transcriptomics,Other,,
+['Transcriptome or Gene expression'],OTHER,total RNA,Transcriptomics,Other,,
+['Transcriptome or Gene expression'],RIP-Seq,polyA RNA,Epigenomics,RNA immunoprecipitation,,
+['Transcriptome or Gene expression'],RIP-Seq,total RNA,Epigenomics,RNA immunoprecipitation,,
+['Transcriptome or Gene expression'],RNA-Seq,"['cytoplasmic RNA', 'nuclear RNA']",Transcriptomics,RNA-Seq,,
+['Transcriptome or Gene expression'],RNA-Seq,"['genomic DNA', 'polyA RNA']",Genomics,RNA-Seq,,
+['Transcriptome or Gene expression'],RNA-Seq,"['nuclear RNA', 'total RNA']",Transcriptomics,RNA-Seq,,
+['Transcriptome or Gene expression'],RNA-Seq,"['other', 'polyA RNA', 'total RNA']",Transcriptomics,RNA-Seq,,
+['Transcriptome or Gene expression'],RNA-Seq,"['other', 'polyA RNA']",Transcriptomics,RNA-Seq,,
+['Transcriptome or Gene expression'],RNA-Seq,"['polyA RNA', 'protein', 'total RNA']",Transcriptomics,RNA-Seq,,
+['Transcriptome or Gene expression'],RNA-Seq,"['polyA RNA', 'protein']",Transcriptomics,RNA-Seq,,
+['Transcriptome or Gene expression'],RNA-Seq,"['polyA RNA', 'total RNA']",Transcriptomics,RNA-Seq,,
+['Transcriptome or Gene expression'],RNA-Seq,"['protein', 'total RNA']",Transcriptomics,RNA-Seq,,
+['Transcriptome or Gene expression'],RNA-Seq,cytoplasmic RNA,Transcriptomics,RNA-Seq,,
+['Transcriptome or Gene expression'],RNA-Seq,genomic DNA,Genomics,RNA-Seq,,
+['Transcriptome or Gene expression'],RNA-Seq,nuclear RNA,Transcriptomics,RNA-Seq,nuclear RNA,
+['Transcriptome or Gene expression'],RNA-Seq,polyA RNA,Transcriptomics,RNA-Seq,,
+['Transcriptome or Gene expression'],RNA-Seq,protein,Transcriptomics,RNA-Seq,,
+['Transcriptome or Gene expression'],RNA-Seq,total RNA,Transcriptomics,RNA-Seq,total RNA,
+['Transcriptome or Gene expression'],"['', 'RNA-Seq']",total RNA,Transcriptomics,RNA-Seq,,
+['Transcriptome or Gene expression'],"['Bisulfite-Seq', 'RNA-Seq']","['genomic DNA', 'polyA RNA']",Epigenomics,Bisulfite-seq,,"indicated by ""bisulfite-seq"""
+['Transcriptome or Gene expression'],"['OTHER', 'RNA-Seq']","['other', 'total RNA']",Transcriptomics,RNA-Seq,,
+['Transcriptome or Gene expression'],"['OTHER', 'RNA-Seq']","['polyA RNA', 'protein']",Transcriptomics,RNA-Seq,,
+['Transcriptome or Gene expression'],"['OTHER', 'RNA-Seq']","['polyA RNA', 'total RNA']",Transcriptomics,RNA-Seq,,
+['Transcriptome or Gene expression'],"['OTHER', 'RNA-Seq']","['protein', 'total RNA']",Transcriptomics,RNA-Seq,,
+['Transcriptome or Gene expression'],"['OTHER', 'RNA-Seq']",total RNA,Transcriptomics,RNA-Seq,,
+['Transcriptome or Gene expression'],"['RIP-Seq', 'RNA-Seq', 'ncRNA-Seq']","['polyA RNA', 'total RNA']",Transcriptomics,RNA-Seq,,
+['Transcriptome or Gene expression'],"['RIP-Seq', 'RNA-Seq']","['polyA RNA', 'total RNA']",Transcriptomics,RNA-Seq,,
+['Transcriptome or Gene expression'],"['RIP-Seq', 'RNA-Seq']",total RNA,Transcriptomics,RNA-Seq,,
+['Transcriptome or Gene expression'],"['RNA-Seq', 'miRNA-Seq']","['polyA RNA', 'total RNA']",Transcriptomics,RNA-Seq,,
+['Transcriptome or Gene expression'],"['RNA-Seq', 'miRNA-Seq']",total RNA,Transcriptomics,RNA-Seq,,
+['Transcriptome or Gene expression'],"['RNA-Seq', 'ncRNA-Seq']","['polyA RNA', 'total RNA']",Transcriptomics,RNA-Seq,,
+['Transcriptome or Gene expression'],"['RNA-Seq', 'ncRNA-Seq']",total RNA,Transcriptomics,RNA-Seq,,
+['Transcriptome or Gene expression'],"['RNA-Seq', 'ssRNA-seq']",total RNA,Transcriptomics,Single cell sequencing,,
+['Transcriptome or Gene expression'],[],[],Other,Other,,
+['Transcriptome or Gene expression'],miRNA-Seq,other,Transcriptomics,RNA-Seq,miRNA-Seq,
+['Transcriptome or Gene expression'],miRNA-Seq,polyA RNA,Transcriptomics,RNA-Seq,miRNA-Seq,
+['Transcriptome or Gene expression'],miRNA-Seq,total RNA,Transcriptomics,RNA-Seq,,
+['Transcriptome or Gene expression'],ncRNA-Seq,"['cytoplasmic RNA', 'nuclear RNA', 'total RNA']",Transcriptomics,RNA-Seq,,
+['Transcriptome or Gene expression'],ncRNA-Seq,other,Transcriptomics,RNA-Seq,ncRNA-Seq,
+['Transcriptome or Gene expression'],ncRNA-Seq,total RNA,Transcriptomics,RNA-Seq,,
+['Transcriptome or Gene expression'],ssRNA-seq,polyA RNA,Transcriptomics,Single cell sequencing,,
+['Transcriptome or Gene expression'],ssRNA-seq,total RNA,Transcriptomics,Single cell sequencing,,
+['Transcriptome or Gene expression'],,"['cytoplasmic RNA', 'total RNA']",Transcriptomics,Other,,
+['Transcriptome or Gene expression'],,"['genomic DNA', 'total RNA']",Genomics,Other,,
+['Transcriptome or Gene expression'],,"['other', 'total RNA']",Transcriptomics,Other,,
+['Transcriptome or Gene expression'],,"['polyA RNA', 'total RNA']",Transcriptomics,Other,,
+['Transcriptome or Gene expression'],,genomic DNA,Genomics,Other,,
+['Transcriptome or Gene expression'],,other,Transcriptomics,Other,,
+['Transcriptome or Gene expression'],,polyA RNA,Transcriptomics,Other,,
+['Transcriptome or Gene expression'],,total RNA,Transcriptomics,Other,,
+['Variation'],ChIP-Seq,genomic DNA,Epigenomics,ChIP-seq,,"indicated by ""ChIP-seq"""
+['Variation'],OTHER,"['genomic DNA', 'other']",Genomics,Other,,
+['Variation'],OTHER,genomic DNA,Genomics,Other,,
+['Variation'],RNA-Seq,total RNA,Transcriptomics,RNA-Seq,,
+['Variation'],,"['genomic DNA', 'nuclear RNA']",Genomics,Other,,
+['Variation'],,genomic DNA,Genomics,Other,,
+[],ATAC-seq,genomic DNA,Epigenomics,ATAC-seq,,"indicated by ""ATAC-seq"""
+[],Bisulfite-Seq,genomic DNA,Epigenomics,Bisulfite-seq,,"indicated by ""bisulfite-seq"""
+[],ChIP-Seq,"['genomic DNA', 'polyA RNA']",Epigenomics,ChIP-seq,,"indicated by ""ChIP-seq"""
+[],ChIP-Seq,genomic DNA,Epigenomics,ChIP-seq,,"indicated by ""ChIP-seq"""
+[],DNase-Hypersensitivity,genomic DNA,Epigenomics,DNase-Hypersensitivity,,
+[],Hi-C,genomic DNA,Epigenomics,Hi-C assay,,"indicated by ""Hi-c"""
+[],OTHER,"['genomic DNA', 'other', 'polyA RNA']",Genomics,Other,,
+[],OTHER,"['genomic DNA', 'other']",Genomics,Other,,
+[],OTHER,"['genomic DNA', 'polyA RNA', 'protein']",Genomics,Other,,
+[],OTHER,"['genomic DNA', 'polyA RNA']",Genomics,Other,,
+[],OTHER,"['genomic DNA', 'total RNA']",Genomics,Other,,
+[],OTHER,"['other', 'polyA RNA', 'protein']",Transcriptomics,RNA-Seq,,
+[],OTHER,"['other', 'polyA RNA']",Transcriptomics,Other,,
+[],OTHER,"['other', 'total RNA']",Transcriptomics,Other,,
+[],OTHER,"['polyA RNA', 'protein']",Transcriptomics,RNA-Seq,,
+[],OTHER,"['polyA RNA', 'total RNA']",Transcriptomics,Other,,
+[],OTHER,"['protein', 'total RNA']",Transcriptomics,RNA-Seq,,
+[],OTHER,cytoplasmic RNA,Transcriptomics,Other,cytoplasmic RNA,
+[],OTHER,genomic DNA,Genomics,Other,,
+[],OTHER,nuclear RNA,Transcriptomics,Other,nuclear RNA,
+[],OTHER,other,Other,Other,,
+[],OTHER,polyA RNA,Transcriptomics,Other,,
+[],OTHER,protein,Proteomics,Other,,
+[],OTHER,total RNA,Transcriptomics,Other,,
+[],RIP-Seq,"['other', 'total RNA']",Epigenomics,RNA immunoprecipitation,,
+[],RIP-Seq,other,Epigenomics,RNA immunoprecipitation,,
+[],RIP-Seq,polyA RNA,Epigenomics,RNA immunoprecipitation,,
+[],RIP-Seq,total RNA,Epigenomics,RNA immunoprecipitation,,
+[],RNA-Seq,"['cytoplasmic RNA', 'total RNA']",Transcriptomics,RNA-Seq,,
+[],RNA-Seq,"['genomic DNA', 'total RNA']",Genomics,RNA-Seq,,
+[],RNA-Seq,"['other', 'polyA RNA', 'total RNA']",Transcriptomics,RNA-Seq,,
+[],RNA-Seq,"['other', 'protein', 'total RNA']",Transcriptomics,RNA-Seq,,
+[],RNA-Seq,"['polyA RNA', 'protein']",Transcriptomics,RNA-Seq,,
+[],RNA-Seq,"['polyA RNA', 'total RNA']",Transcriptomics,RNA-Seq,,
+[],RNA-Seq,"['protein', 'total RNA']",Transcriptomics,RNA-Seq,,
+[],RNA-Seq,polyA RNA,Transcriptomics,RNA-Seq,,
+[],RNA-Seq,total RNA,Transcriptomics,RNA-Seq,,
+[],SELEX,protein,Proteomics,SELEX,,
+[],Tn-Seq,genomic DNA,Genomics,Tn-Seq,,
+[],"['', 'ATAC-seq', 'Bisulfite-Seq', 'ChIP-Seq', 'RNA-Seq']","['genomic DNA', 'polyA RNA', 'total RNA']",Epigenomics,ATAC-seq,,"indicated by ""ATAC-seq"""
+[],"['', 'ATAC-seq']",genomic DNA,Epigenomics,ATAC-seq,,"indicated by ""ATAC-seq"""
+[],"['', 'Bisulfite-Seq', 'RNA-Seq']","['genomic DNA', 'total RNA']",Epigenomics,Bisulfite-seq,,"indicated by ""bisulfite-seq"""
+[],"['', 'Bisulfite-Seq']","['genomic DNA', 'total RNA']",Epigenomics,Bisulfite-seq,,"indicated by ""bisulfite-seq"""
+[],"['', 'Bisulfite-Seq']",genomic DNA,Epigenomics,Bisulfite-seq,,"indicated by ""bisulfite-seq"""
+[],"['', 'ChIP-Seq', 'DNase-Hypersensitivity', 'OTHER']",genomic DNA,Epigenomics,ChIP-seq,,"indicated by ""ChIP-seq"""
+[],"['', 'ChIP-Seq', 'DNase-Hypersensitivity', 'RNA-Seq']","['genomic DNA', 'total RNA']",Epigenomics,ChIP-seq,,"indicated by ""ChIP-seq"""
+[],"['', 'ChIP-Seq', 'DNase-Hypersensitivity']","['genomic DNA', 'total RNA']",Epigenomics,ChIP-seq,,"indicated by ""ChIP-seq"""
+[],"['', 'ChIP-Seq', 'FAIRE-seq', 'RNA-Seq']","['genomic DNA', 'total RNA']",Epigenomics,ChIP-seq,,"indicated by ""ChIP-seq"""
+[],"['', 'ChIP-Seq', 'OTHER', 'RNA-Seq']","['genomic DNA', 'total RNA']",Epigenomics,ChIP-seq,,"indicated by ""ChIP-seq"""
+[],"['', 'ChIP-Seq', 'OTHER']","['genomic DNA', 'protein']",Epigenomics,ChIP-seq,,"indicated by ""ChIP-seq"""
+[],"['', 'ChIP-Seq', 'RNA-Seq']","['genomic DNA', 'polyA RNA', 'total RNA']",Epigenomics,ChIP-seq,,"indicated by ""ChIP-seq"""
+[],"['', 'ChIP-Seq', 'RNA-Seq']","['genomic DNA', 'polyA RNA']",Epigenomics,ChIP-seq,,"indicated by ""ChIP-seq"""
+[],"['', 'ChIP-Seq', 'RNA-Seq']","['genomic DNA', 'total RNA']",Epigenomics,ChIP-seq,,"indicated by ""ChIP-seq"""
+[],"['', 'ChIP-Seq']","['genomic DNA', 'total RNA']",Epigenomics,ChIP-seq,,"indicated by ""ChIP-seq"""
+[],"['', 'ChIP-Seq']",genomic DNA,Epigenomics,ChIP-seq,,"indicated by ""ChIP-seq"""
+[],"['', 'DNase-Hypersensitivity']","['genomic DNA', 'total RNA']",Epigenomics,DNase-Hypersensitivity,,
+[],"['', 'MeDIP-Seq']","['genomic DNA', 'total RNA']",Epigenomics,MeDIP-Seq,,
+[],"['', 'OTHER', 'RNA-Seq']","['genomic DNA', 'total RNA']",Genomics,RNA-Seq,,
+[],"['', 'OTHER']","['protein', 'total RNA']",Transcriptomics,RNA-Seq,,
+[],"['', 'OTHER']",genomic DNA,Genomics,Other,,
+[],"['', 'OTHER']",total RNA,Transcriptomics,RNA-Seq,,
+[],"['', 'RNA-Seq', 'miRNA-Seq']","['genomic DNA', 'total RNA']",Genomics,RNA-Seq,,
+[],"['', 'RNA-Seq']","['genomic DNA', 'polyA RNA', 'total RNA']",Genomics,RNA-Seq,,
+[],"['', 'RNA-Seq']","['genomic DNA', 'polyA RNA']",Genomics,RNA-Seq,,
+[],"['', 'RNA-Seq']","['genomic DNA', 'total RNA']",Genomics,RNA-Seq,,
+[],"['', 'RNA-Seq']","['other', 'total RNA']",Transcriptomics,RNA-Seq,,
+[],"['', 'RNA-Seq']","['polyA RNA', 'total RNA']",Transcriptomics,RNA-Seq,,
+[],"['', 'RNA-Seq']","['protein', 'total RNA']",Transcriptomics,RNA-Seq,,
+[],"['', 'RNA-Seq']",total RNA,Transcriptomics,RNA-Seq,,
+[],"['', 'miRNA-Seq']",total RNA,Transcriptomics,RNA-Seq,,
+[],"['', 'ncRNA-Seq']",total RNA,Transcriptomics,RNA-Seq,,
+[],"['ATAC-seq', 'Bisulfite-Seq', 'ChIP-Seq', 'OTHER', 'RNA-Seq']","['genomic DNA', 'total RNA']",Epigenomics,ATAC-seq,,"indicated by ""ATAC-seq"""
+[],"['ATAC-seq', 'Bisulfite-Seq', 'ChIP-Seq', 'RNA-Seq']","['genomic DNA', 'total RNA']",Epigenomics,ATAC-seq,,"indicated by ""ATAC-seq"""
+[],"['ATAC-seq', 'Bisulfite-Seq', 'OTHER', 'RNA-Seq']","['genomic DNA', 'total RNA']",Epigenomics,ATAC-seq,,"indicated by ""ATAC-seq"""
+[],"['ATAC-seq', 'Bisulfite-Seq', 'RNA-Seq']","['genomic DNA', 'total RNA']",Epigenomics,ATAC-seq,,"indicated by ""ATAC-seq"""
+[],"['ATAC-seq', 'Bisulfite-Seq', 'RNA-Seq']",polyA RNA,Epigenomics,ATAC-seq,,"indicated by ""ATAC-seq"""
+[],"['ATAC-seq', 'ChIP-Seq', 'Hi-C', 'OTHER', 'RNA-Seq']","['genomic DNA', 'total RNA']",Epigenomics,ATAC-seq,,"indicated by ""ATAC-seq"""
+[],"['ATAC-seq', 'ChIP-Seq', 'Hi-C', 'RNA-Seq']","['genomic DNA', 'total RNA']",Epigenomics,ATAC-seq,,"indicated by ""ATAC-seq"""
+[],"['ATAC-seq', 'ChIP-Seq', 'Hi-C']",genomic DNA,Epigenomics,ATAC-seq,,"indicated by ""ATAC-seq"""
+[],"['ATAC-seq', 'ChIP-Seq', 'MeDIP-Seq', 'OTHER', 'RNA-Seq']","['genomic DNA', 'polyA RNA']",Epigenomics,ATAC-seq,,"indicated by ""ATAC-seq"""
+[],"['ATAC-seq', 'ChIP-Seq', 'OTHER', 'RNA-Seq']","['genomic DNA', 'polyA RNA', 'total RNA']",Epigenomics,ATAC-seq,,"indicated by ""ATAC-seq"""
+[],"['ATAC-seq', 'ChIP-Seq', 'OTHER', 'RNA-Seq']","['genomic DNA', 'polyA RNA']",Epigenomics,ATAC-seq,,"indicated by ""ATAC-seq"""
+[],"['ATAC-seq', 'ChIP-Seq', 'OTHER', 'RNA-Seq']","['genomic DNA', 'total RNA']",Epigenomics,ATAC-seq,,"indicated by ""ATAC-seq"""
+[],"['ATAC-seq', 'ChIP-Seq', 'RNA-Seq']","['genomic DNA', 'polyA RNA']",Epigenomics,ATAC-seq,,"indicated by ""ATAC-seq"""
+[],"['ATAC-seq', 'ChIP-Seq', 'RNA-Seq']","['genomic DNA', 'total RNA']",Epigenomics,ATAC-seq,,"indicated by ""ATAC-seq"""
+[],"['ATAC-seq', 'ChIP-Seq']",genomic DNA,Epigenomics,ATAC-seq,,"indicated by ""ATAC-seq"""
+[],"['ATAC-seq', 'Hi-C', 'OTHER']",genomic DNA,Epigenomics,ATAC-seq,,"indicated by ""ATAC-seq"""
+[],"['ATAC-seq', 'OTHER', 'RIP-Seq', 'RNA-Seq', 'miRNA-Seq', 'ssRNA-seq']","['genomic DNA', 'other', 'polyA RNA', 'total RNA']",Epigenomics,ATAC-seq,,"indicated by ""ATAC-seq"""
+[],"['ATAC-seq', 'OTHER', 'RNA-Seq']","['genomic DNA', 'other', 'polyA RNA']",Epigenomics,ATAC-seq,,"indicated by ""ATAC-seq"""
+[],"['ATAC-seq', 'OTHER', 'RNA-Seq']","['genomic DNA', 'other', 'total RNA']",Epigenomics,ATAC-seq,,"indicated by ""ATAC-seq"""
+[],"['ATAC-seq', 'OTHER', 'RNA-Seq']","['genomic DNA', 'polyA RNA', 'total RNA']",Epigenomics,ATAC-seq,,"indicated by ""ATAC-seq"""
+[],"['ATAC-seq', 'OTHER', 'RNA-Seq']","['genomic DNA', 'polyA RNA']",Epigenomics,ATAC-seq,,"indicated by ""ATAC-seq"""
+[],"['ATAC-seq', 'OTHER', 'RNA-Seq']","['genomic DNA', 'protein', 'total RNA']",Epigenomics,ATAC-seq,,"indicated by ""ATAC-seq"""
+[],"['ATAC-seq', 'OTHER', 'RNA-Seq']","['genomic DNA', 'total RNA']",Epigenomics,ATAC-seq,,"indicated by ""ATAC-seq"""
+[],"['ATAC-seq', 'OTHER']","['genomic DNA', 'nuclear RNA']",Epigenomics,ATAC-seq,,"indicated by ""ATAC-seq"""
+[],"['ATAC-seq', 'OTHER']",genomic DNA,Epigenomics,ATAC-seq,,"indicated by ""ATAC-seq"""
+[],"['ATAC-seq', 'RNA-Seq', 'miRNA-Seq']","['genomic DNA', 'polyA RNA', 'total RNA']",Epigenomics,ATAC-seq,,"indicated by ""ATAC-seq"""
+[],"['ATAC-seq', 'RNA-Seq']","['genomic DNA', 'nuclear RNA', 'total RNA']",Epigenomics,ATAC-seq,,"indicated by ""ATAC-seq"""
+[],"['ATAC-seq', 'RNA-Seq']","['genomic DNA', 'nuclear RNA']",Epigenomics,ATAC-seq,,"indicated by ""ATAC-seq"""
+[],"['ATAC-seq', 'RNA-Seq']","['genomic DNA', 'polyA RNA', 'total RNA']",Epigenomics,ATAC-seq,,"indicated by ""ATAC-seq"""
+[],"['ATAC-seq', 'RNA-Seq']","['genomic DNA', 'polyA RNA']",Epigenomics,ATAC-seq,,"indicated by ""ATAC-seq"""
+[],"['ATAC-seq', 'RNA-Seq']","['genomic DNA', 'total RNA']",Epigenomics,ATAC-seq,,"indicated by ""ATAC-seq"""
+[],"['ATAC-seq', 'RNA-Seq']","['other', 'total RNA']",Epigenomics,ATAC-seq,,"indicated by ""ATAC-seq"""
+[],"['ATAC-seq', 'RNA-Seq']",polyA RNA,Epigenomics,ATAC-seq,,"indicated by ""ATAC-seq"""
+[],"['ATAC-seq', 'RNA-Seq']",total RNA,Epigenomics,ATAC-seq,,"indicated by ""ATAC-seq"""
+[],"['Bisulfite-Seq', 'ChIP-Seq', 'Hi-C', 'OTHER', 'RNA-Seq']","['genomic DNA', 'polyA RNA']",Epigenomics,Bisulfite-seq,,"indicated by ""bisulfite-seq"""
+[],"['Bisulfite-Seq', 'ChIP-Seq', 'OTHER', 'RNA-Seq']","['genomic DNA', 'total RNA']",Epigenomics,Bisulfite-seq,,"indicated by ""bisulfite-seq"""
+[],"['Bisulfite-Seq', 'ChIP-Seq', 'OTHER']",genomic DNA,Epigenomics,Bisulfite-seq,,"indicated by ""bisulfite-seq"""
+[],"['Bisulfite-Seq', 'ChIP-Seq', 'RNA-Seq']","['genomic DNA', 'total RNA']",Epigenomics,Bisulfite-seq,,"indicated by ""bisulfite-seq"""
+[],"['Bisulfite-Seq', 'ChIP-Seq']",genomic DNA,Epigenomics,Bisulfite-seq,,"indicated by ""bisulfite-seq"""
+[],"['Bisulfite-Seq', 'MNase-Seq', 'RNA-Seq']","['genomic DNA', 'total RNA']",Epigenomics,Bisulfite-seq,,"indicated by ""bisulfite-seq"""
+[],"['Bisulfite-Seq', 'OTHER', 'RNA-Seq']","['genomic DNA', 'total RNA']",Epigenomics,Bisulfite-seq,,"indicated by ""bisulfite-seq"""
+[],"['Bisulfite-Seq', 'OTHER']","['genomic DNA', 'polyA RNA']",Epigenomics,Bisulfite-seq,,"indicated by ""bisulfite-seq"""
+[],"['Bisulfite-Seq', 'OTHER']",genomic DNA,Epigenomics,Bisulfite-seq,,"indicated by ""bisulfite-seq"""
+[],"['Bisulfite-Seq', 'RNA-Seq']","['genomic DNA', 'polyA RNA']",Epigenomics,Bisulfite-seq,,"indicated by ""bisulfite-seq"""
+[],"['Bisulfite-Seq', 'RNA-Seq']","['genomic DNA', 'total RNA']",Epigenomics,Bisulfite-seq,,"indicated by ""bisulfite-seq"""
+[],"['ChIA-PET', 'ChIP-Seq', 'OTHER', 'RNA-Seq']","['genomic DNA', 'polyA RNA']",Epigenomics,ChIP-seq,,"indicated by ""ChIP-seq"""
+[],"['ChIP-Seq', 'Hi-C', 'OTHER', 'RIP-Seq', 'RNA-Seq']","['genomic DNA', 'total RNA']",Epigenomics,ChIP-seq,,"indicated by ""ChIP-seq"""
+[],"['ChIP-Seq', 'Hi-C', 'OTHER', 'RNA-Seq']","['genomic DNA', 'total RNA']",Epigenomics,ChIP-seq,,"indicated by ""ChIP-seq"""
+[],"['ChIP-Seq', 'Hi-C', 'RNA-Seq']","['genomic DNA', 'total RNA']",Epigenomics,ChIP-seq,,"indicated by ""ChIP-seq"""
+[],"['ChIP-Seq', 'OTHER', 'RNA-Seq', 'WGS']","['genomic DNA', 'nuclear RNA', 'total RNA']",Epigenomics,ChIP-seq,,"indicated by ""ChIP-seq"""
+[],"['ChIP-Seq', 'OTHER', 'RNA-Seq']","['genomic DNA', 'other', 'total RNA']",Epigenomics,ChIP-seq,,"indicated by ""ChIP-seq"""
+[],"['ChIP-Seq', 'OTHER', 'RNA-Seq']","['genomic DNA', 'polyA RNA', 'total RNA']",Epigenomics,ChIP-seq,,"indicated by ""ChIP-seq"""
+[],"['ChIP-Seq', 'OTHER', 'RNA-Seq']","['genomic DNA', 'polyA RNA']",Epigenomics,ChIP-seq,,"indicated by ""ChIP-seq"""
+[],"['ChIP-Seq', 'OTHER', 'RNA-Seq']","['genomic DNA', 'total RNA']",Epigenomics,ChIP-seq,,"indicated by ""ChIP-seq"""
+[],"['ChIP-Seq', 'OTHER']","['genomic DNA', 'total RNA']",Epigenomics,ChIP-seq,,"indicated by ""ChIP-seq"""
+[],"['ChIP-Seq', 'OTHER']",genomic DNA,Epigenomics,ChIP-seq,,"indicated by ""ChIP-seq"""
+[],"['ChIP-Seq', 'RIP-Seq', 'RNA-Seq']","['genomic DNA', 'polyA RNA', 'total RNA']",Epigenomics,ChIP-seq,,"indicated by ""ChIP-seq"""
+[],"['ChIP-Seq', 'RIP-Seq', 'RNA-Seq']",total RNA,Epigenomics,ChIP-seq,,"indicated by ""ChIP-seq"""
+[],"['ChIP-Seq', 'RIP-Seq']","['genomic DNA', 'total RNA']",Epigenomics,ChIP-seq,,"indicated by ""ChIP-seq"""
+[],"['ChIP-Seq', 'RNA-Seq']","['genomic DNA', 'polyA RNA', 'total RNA']",Epigenomics,ChIP-seq,,"indicated by ""ChIP-seq"""
+[],"['ChIP-Seq', 'RNA-Seq']","['genomic DNA', 'polyA RNA']",Epigenomics,ChIP-seq,,"indicated by ""ChIP-seq"""
+[],"['ChIP-Seq', 'RNA-Seq']","['genomic DNA', 'total RNA']",Epigenomics,ChIP-seq,,"indicated by ""ChIP-seq"""
+[],"['ChIP-Seq', 'RNA-Seq']",total RNA,Epigenomics,ChIP-seq,,"indicated by ""ChIP-seq"""
+[],"['DNase-Hypersensitivity', 'RNA-Seq']","['genomic DNA', 'total RNA']",Epigenomics,DNase-Hypersensitivity,,
+[],"['FAIRE-seq', 'RNA-Seq']","['genomic DNA', 'polyA RNA']",Epigenomics,FAIRE-seq,,
+[],"['Hi-C', 'OTHER', 'RNA-Seq']","['genomic DNA', 'total RNA']",Epigenomics,Hi-C assay,,"indicated by ""Hi-c"""
+[],"['Hi-C', 'OTHER']","['genomic DNA', 'polyA RNA']",Epigenomics,Hi-C assay,,"indicated by ""Hi-c"""
+[],"['Hi-C', 'RNA-Seq']","['genomic DNA', 'total RNA']",Epigenomics,Hi-C assay,,"indicated by ""Hi-c"""
+[],"['MNase-Seq', 'OTHER', 'RNA-Seq']","['genomic DNA', 'total RNA']",Epigenomics,MNase-Seq,,
+[],"['MeDIP-Seq', 'RNA-Seq']","['genomic DNA', 'total RNA']",Epigenomics,MeDIP-Seq,,
+[],"['OTHER', 'RIP-Seq', 'RNA-Seq']","['genomic DNA', 'polyA RNA', 'total RNA']",Epigenomics,RNA immunoprecipitation,,
+[],"['OTHER', 'RIP-Seq', 'RNA-Seq']",total RNA,Transcriptomics,RNA-Seq,,
+[],"['OTHER', 'RIP-Seq']","['genomic DNA', 'total RNA']",Epigenomics,RNA immunoprecipitation,,
+[],"['OTHER', 'RIP-Seq']",total RNA,Epigenomics,RNA immunoprecipitation,,
+[],"['OTHER', 'RNA-Seq', 'miRNA-Seq']","['genomic DNA', 'polyA RNA', 'total RNA']",Genomics,RNA-Seq,,
+[],"['OTHER', 'RNA-Seq', 'ncRNA-Seq']",total RNA,Transcriptomics,RNA-Seq,,
+[],"['OTHER', 'RNA-Seq']","['cytoplasmic RNA', 'total RNA']",Transcriptomics,RNA-Seq,,
+[],"['OTHER', 'RNA-Seq']","['genomic DNA', 'nuclear RNA']",Genomics,RNA-Seq,,
+[],"['OTHER', 'RNA-Seq']","['genomic DNA', 'other', 'polyA RNA']",Genomics,RNA-Seq,,
+[],"['OTHER', 'RNA-Seq']","['genomic DNA', 'polyA RNA', 'total RNA']",Transcriptomics,RNA-Seq,,
+[],"['OTHER', 'RNA-Seq']","['genomic DNA', 'polyA RNA']",Genomics,RNA-Seq,,
+[],"['OTHER', 'RNA-Seq']","['genomic DNA', 'total RNA']",Genomics,RNA-Seq,,
+[],"['OTHER', 'RNA-Seq']","['nuclear RNA', 'other', 'polyA RNA']",Transcriptomics,RNA-Seq,,
+[],"['OTHER', 'RNA-Seq']","['other', 'polyA RNA', 'protein']",Transcriptomics,RNA-Seq,,
+[],"['OTHER', 'RNA-Seq']","['other', 'total RNA']",Transcriptomics,RNA-Seq,,
+[],"['OTHER', 'RNA-Seq']","['polyA RNA', 'protein', 'total RNA']",Transcriptomics,RNA-Seq,,
+[],"['OTHER', 'RNA-Seq']","['polyA RNA', 'protein']",Transcriptomics,RNA-Seq,,
+[],"['OTHER', 'RNA-Seq']","['polyA RNA', 'total RNA']",Transcriptomics,RNA-Seq,,
+[],"['OTHER', 'RNA-Seq']","['protein', 'total RNA']",Transcriptomics,RNA-Seq,,
+[],"['OTHER', 'RNA-Seq']",polyA RNA,Transcriptomics,RNA-Seq,,
+[],"['OTHER', 'RNA-Seq']",total RNA,Transcriptomics,RNA-Seq,,
+[],"['OTHER', 'ssRNA-seq']","['polyA RNA', 'total RNA']",Transcriptomics,Single cell sequencing,,
+[],"['RIP-Seq', 'RNA-Seq', 'ncRNA-Seq']",total RNA,Epigenomics,RNA immunoprecipitation,,
+[],"['RIP-Seq', 'RNA-Seq']","['other', 'total RNA']",Epigenomics,RNA immunoprecipitation,,
+[],"['RIP-Seq', 'RNA-Seq']","['polyA RNA', 'total RNA']",Epigenomics,RNA immunoprecipitation,,
+[],"['RIP-Seq', 'RNA-Seq']",polyA RNA,Epigenomics,RNA immunoprecipitation,,
+[],"['RIP-Seq', 'RNA-Seq']",total RNA,Epigenomics,RNA immunoprecipitation,,
+[],"['RIP-Seq', 'ncRNA-Seq']",total RNA,Epigenomics,RNA immunoprecipitation,,
+[],"['RNA-Seq', 'miRNA-Seq']","['other', 'polyA RNA', 'total RNA']",Transcriptomics,RNA-Seq,,
+[],"['RNA-Seq', 'miRNA-Seq']","['polyA RNA', 'total RNA']",Transcriptomics,RNA-Seq,,
+[],"['RNA-Seq', 'miRNA-Seq']",total RNA,Transcriptomics,RNA-Seq,,
+[],"['RNA-Seq', 'ncRNA-Seq']","['polyA RNA', 'total RNA']",Transcriptomics,RNA-Seq,,
+[],"['RNA-Seq', 'ncRNA-Seq']",total RNA,Transcriptomics,RNA-Seq,,
+[],"['RNA-Seq', 'ssRNA-seq']","['polyA RNA', 'total RNA']",Transcriptomics,Single cell sequencing,,
+[],[],[],Other,Other,,
+[],ncRNA-Seq,total RNA,Transcriptomics,RNA-Seq,,
+[],ssRNA-seq,total RNA,Transcriptomics,Single cell sequencing,,
+[],,"['genomic DNA', 'polyA RNA', 'total RNA']",Genomics,Other,,
+[],,"['genomic DNA', 'total RNA']",Genomics,Other,,
+[],,"['other', 'protein']",Proteomics,Other,,
+[],,"['other', 'total RNA']",Transcriptomics,Other,,
+[],,genomic DNA,Genomics,Other,,
+[],,other,Transcriptomics,Other,,
+[],,polyA RNA,Transcriptomics,Other,,
+[],,protein,Proteomics,Other,,
+[],,total RNA,Transcriptomics,Other,,
diff --git a/RDAS_RDOMICS/scripts/config/paths.yaml b/RDAS_RDOMICS/scripts/config/paths.yaml
new file mode 100644
index 0000000..8bf8870
--- /dev/null
+++ b/RDAS_RDOMICS/scripts/config/paths.yaml
@@ -0,0 +1,31 @@
+paths:
+  disease_list_combined_file: "scripts/data/final_disease_list_combined_file.xlsx"
+  disease_list_combined_with_count: "scripts/data/final_combined_disease_list_with_series_count.xlsx"
+
+  geo_matrix_files: "scripts/data/geo_matrix_files"
+  geo_table_template: "scripts/data/table_template.xlsx"
+  geo_final_tables: "scripts/data/geo_final_tables"
+  gse_ids_csv: "scripts/data/gard_to_gse.json"
+
+  geo_final_tables_testing: "scripts/data/geo_final_tables_testing"
+  node_csv_files: "scripts/data/node_csv_files"
+  node_json_files: "scripts/data/node_json_files"
+  experiment_normalization_rules: "scripts/check_unique_comb/omics_sequencing_combinations2_normalization.csv"
+  experiment_node_normalized: "scripts/data/node_csv_files/experiment_node_normalized.csv"
+
+  sample_characteristics_output_dir: "scripts/sample_characteristics_harmonization/sample_characteristics_harmonization_output"
+  sample_characteristics_cleaned_sample_node: "scripts/sample_characteristics_harmonization/sample_characteristics_harmonization_output/1_sample_node_chars_removed.csv"
+  sample_characteristics_key_count_cleaned: "scripts/sample_characteristics_harmonization/sample_characteristics_harmonization_output/1_sample_characteristics_key_count_chars_removed.csv"
+  sample_characteristics_key_count_rule_based: "scripts/sample_characteristics_harmonization/sample_characteristics_harmonization_output/2_sample_characteristics_key_count_chars_removed_rule_based_cleaned.csv"
+  sample_characteristics_key_count_english_only: "scripts/sample_characteristics_harmonization/sample_characteristics_harmonization_output/3_sample_characteristics_key_count_english_only.csv"
+  sample_characteristics_removed_non_english: "scripts/sample_characteristics_harmonization/sample_characteristics_harmonization_output/3_removed_non_english_labels.txt"
+  sample_characteristics_vocabulary: "scripts/sample_characteristics_harmonization/sample_characteristics_harmonization_output/4_sample_characteristics_vocabulary_fixed.csv"
+  sample_characteristics_clustered: "scripts/sample_characteristics_harmonization/sample_characteristics_harmonization_output/4_llm_clustered_sample_characteristics.csv"
+  sample_characteristics_confidence_report: "scripts/sample_characteristics_harmonization/sample_characteristics_harmonization_output/clustering_confidence_report.csv"
+  sample_characteristics_subclustered_generated: "scripts/sample_characteristics_harmonization/sample_characteristics_harmonization_output/5_subclustered_sample_characteristics_v1.csv"
+  sample_characteristics_subclustered_final: "scripts/sample_characteristics_harmonization/sample_characteristics_harmonization_output/5_subclustered_sample_characteristics_v2_expert_consolidated.csv"
+  sample_properties_by_subcategory: "scripts/sample_characteristics_harmonization/sample_characteristics_harmonization_output/sample_properties_by_subcategory.csv"
+  sample_import_resume_file: "scripts/sample_characteristics_harmonization/sample_characteristics_harmonization_output/sample_import_resume.json"
+
+settings:
+  llm_model_path: ""
diff --git a/RDAS_RDOMICS/scripts/data/final_disease_list_combined_file.xlsx b/RDAS_RDOMICS/scripts/data/final_disease_list_combined_file.xlsx
new file mode 100644
index 0000000..6866b37
Binary files /dev/null and b/RDAS_RDOMICS/scripts/data/final_disease_list_combined_file.xlsx differ
diff --git a/RDAS_RDOMICS/scripts/data/gard_to_gse.json b/RDAS_RDOMICS/scripts/data/gard_to_gse.json
new file mode 100644
index 0000000..f6875be
--- /dev/null
+++ b/RDAS_RDOMICS/scripts/data/gard_to_gse.json
@@ -0,0 +1,17984 @@
+{
+    "GARD:0004647": [
+        "GSE47603",
+        "GSE174299",
+        "GSE158560"
+    ],
+    "GARD:0017933": [
+        "GSE280136",
+        "GSE52980",
+        "GSE67097"
+    ],
+    "GARD:0024276": [
+        "GSE139825",
+        "GSE84076",
+        "GSE32447",
+        "GSE71066",
+        "GSE148862",
+        "GSE266563",
+        "GSE179417",
+        "GSE267006",
+        "GSE142069",
+        "GSE141192",
+        "GSE83456",
+        "GSE273691",
+        "GSE19491",
+        "GSE45386",
+        "GSE148036",
+        "GSE148861",
+        "GSE76873",
+        "GSE171961",
+        "GSE69581",
+        "GSE25435",
+        "GSE19435",
+        "GSE54992",
+        "GSE174443",
+        "GSE176255",
+        "GSE174566",
+        "GSE57736",
+        "GSE39219",
+        "GSE107731",
+        "GSE68206",
+        "GSE229020",
+        "GSE31348",
+        "GSE29628",
+        "GSE44848",
+        "GSE100288",
+        "GSE19442",
+        "GSE200151",
+        "GSE160039",
+        "GSE57124",
+        "GSE19443",
+        "GSE169541",
+        "GSE15977",
+        "GSE193979",
+        "GSE54442",
+        "GSE261175",
+        "GSE32619",
+        "GSE119143",
+        "GSE67589",
+        "GSE141205",
+        "GSE19444",
+        "GSE252118",
+        "GSE198877",
+        "GSE93316",
+        "GSE34608",
+        "GSE153340",
+        "GSE3837",
+        "GSE203037",
+        "GSE190024",
+        "GSE57101",
+        "GSE179816",
+        "GSE139598",
+        "GSE29190",
+        "GSE27992",
+        "GSE138580",
+        "GSE19439",
+        "GSE181143",
+        "GSE151764",
+        "GSE89552",
+        "GSE158767",
+        "GSE143619",
+        "GSE20050",
+        "GSE133249",
+        "GSE118469",
+        "GSE77885",
+        "GSE153326",
+        "GSE77884",
+        "GSE48027",
+        "GSE236853",
+        "GSE79362",
+        "GSE74687",
+        "GSE49947",
+        "GSE149758",
+        "GSE168247",
+        "GSE107917",
+        "GSE266562",
+        "GSE211633",
+        "GSE193777",
+        "GSE116542",
+        "GSE256184",
+        "GSE100105",
+        "GSE36238",
+        "GSE102272",
+        "GSE141848",
+        "GSE193978"
+    ],
+    "GARD:0007058": [
+        "GSE45536",
+        "GSE76809",
+        "GSE6520",
+        "GSE214088",
+        "GSE247804",
+        "GSE166861",
+        "GSE4385",
+        "GSE45537",
+        "GSE175866",
+        "GSE181957",
+        "GSE168312",
+        "GSE256420",
+        "GSE76886",
+        "GSE71995",
+        "GSE71998",
+        "GSE43469",
+        "GSE24403",
+        "GSE153011",
+        "GSE115503",
+        "GSE195452",
+        "GSE157538",
+        "GSE226331",
+        "GSE132771",
+        "GSE11130",
+        "GSE163973",
+        "GSE146478",
+        "GSE134310",
+        "GSE226760",
+        "GSE196637",
+        "GSE137276",
+        "GSE187002",
+        "GSE24410",
+        "GSE76885",
+        "GSE132869",
+        "GSE261205",
+        "GSE138669",
+        "GSE4445",
+        "GSE22356",
+        "GSE269610",
+        "GSE27165",
+        "GSE71999",
+        "GSE239592",
+        "GSE83501",
+        "GSE9285",
+        "GSE83505",
+        "GSE3886",
+        "GSE3887",
+        "GSE182300",
+        "GSE160536",
+        "GSE254716",
+        "GSE226375",
+        "GSE194380",
+        "GSE2710",
+        "GSE202649",
+        "GSE34827",
+        "GSE234987",
+        "GSE104174",
+        "GSE131793",
+        "GSE55427",
+        "GSE195581",
+        "GSE17914",
+        "GSE128169",
+        "GSE150592",
+        "GSE33463",
+        "GSE249279",
+        "GSE262558",
+        "GSE182301",
+        "GSE181228",
+        "GSE1724",
+        "GSE191223",
+        "GSE71991",
+        "GSE226374",
+        "GSE153880",
+        "GSE75173",
+        "GSE47616",
+        "GSE20055",
+        "GSE166863",
+        "GSE121659",
+        "GSE195583",
+        "GSE32245",
+        "GSE175379",
+        "GSE186961",
+        "GSE40839",
+        "GSE45535",
+        "GSE58613",
+        "GSE24409",
+        "GSE2052",
+        "GSE240009",
+        "GSE16031",
+        "GSE12493",
+        "GSE99702",
+        "GSE41744",
+        "GSE264508",
+        "GSE182302",
+        "GSE163199",
+        "GSE86984",
+        "GSE165117",
+        "GSE130953",
+        "GSE108918",
+        "GSE144625",
+        "GSE45536",
+        "GSE76809",
+        "GSE6520",
+        "GSE214088",
+        "GSE247804",
+        "GSE166861",
+        "GSE4385",
+        "GSE45537",
+        "GSE175866",
+        "GSE181957",
+        "GSE168312",
+        "GSE256420",
+        "GSE76886",
+        "GSE71995",
+        "GSE71998",
+        "GSE43469",
+        "GSE24403",
+        "GSE153011",
+        "GSE115503",
+        "GSE195452",
+        "GSE157538",
+        "GSE226331",
+        "GSE132771",
+        "GSE11130",
+        "GSE163973",
+        "GSE146478",
+        "GSE134310",
+        "GSE226760",
+        "GSE196637",
+        "GSE137276",
+        "GSE187002",
+        "GSE24410",
+        "GSE76885",
+        "GSE132869",
+        "GSE261205",
+        "GSE138669",
+        "GSE4445",
+        "GSE22356",
+        "GSE269610",
+        "GSE27165",
+        "GSE71999",
+        "GSE239592",
+        "GSE83501",
+        "GSE9285",
+        "GSE83505",
+        "GSE3886",
+        "GSE3887",
+        "GSE182300",
+        "GSE160536",
+        "GSE254716",
+        "GSE226375",
+        "GSE194380",
+        "GSE2710",
+        "GSE202649",
+        "GSE34827",
+        "GSE234987",
+        "GSE104174",
+        "GSE131793",
+        "GSE55427",
+        "GSE195581",
+        "GSE17914",
+        "GSE128169",
+        "GSE150592",
+        "GSE33463",
+        "GSE249279",
+        "GSE262558",
+        "GSE182301",
+        "GSE181228",
+        "GSE1724",
+        "GSE191223",
+        "GSE71991",
+        "GSE226374",
+        "GSE153880",
+        "GSE75173",
+        "GSE47616",
+        "GSE20055",
+        "GSE166863",
+        "GSE121659",
+        "GSE195583",
+        "GSE32245",
+        "GSE175379",
+        "GSE186961",
+        "GSE40839",
+        "GSE45535",
+        "GSE58613",
+        "GSE24409",
+        "GSE2052",
+        "GSE240009",
+        "GSE16031",
+        "GSE12493",
+        "GSE99702",
+        "GSE41744",
+        "GSE264508",
+        "GSE182302",
+        "GSE163199",
+        "GSE86984",
+        "GSE165117",
+        "GSE130953",
+        "GSE108918",
+        "GSE144625"
+    ],
+    "GARD:0009615": [
+        "GSE174694",
+        "GSE224528",
+        "GSE63425",
+        "GSE237441",
+        "GSE198891",
+        "GSE196830",
+        "GSE196829",
+        "GSE236367",
+        "GSE5180",
+        "GSE201752",
+        "GSE224526",
+        "GSE201753",
+        "GSE224527",
+        "GSE201754"
+    ],
+    "GARD:0008614": [
+        "GSE244401",
+        "GSE17078",
+        "GSE110936",
+        "GSE11060",
+        "GSE148529",
+        "GSE113544",
+        "GSE117613",
+        "GSE105035",
+        "GSE212603",
+        "GSE22367",
+        "GSE42383",
+        "GSE74977",
+        "GSE179359",
+        "GSE180869",
+        "GSE200676",
+        "GSE235633",
+        "GSE46471",
+        "GSE107775",
+        "GSE224834",
+        "GSE139912",
+        "GSE111356",
+        "GSE284318",
+        "GSE6479",
+        "GSE232221",
+        "GSE113503",
+        "GSE38528",
+        "GSE188695",
+        "GSE277176",
+        "GSE118357",
+        "GSE252686",
+        "GSE86418",
+        "GSE221182",
+        "GSE228819",
+        "GSE218231",
+        "GSE10002",
+        "GSE133181",
+        "GSE179360",
+        "GSE163912",
+        "GSE77207",
+        "GSE97671",
+        "GSE144413",
+        "GSE22368",
+        "GSE109257",
+        "GSE223911",
+        "GSE263200",
+        "GSE180860",
+        "GSE248671",
+        "GSE205876",
+        "GSE179363",
+        "GSE284319",
+        "GSE35007",
+        "GSE179364",
+        "GSE11524",
+        "GSE9877",
+        "GSE284394",
+        "GSE194064",
+        "GSE240446",
+        "GSE118358",
+        "GSE255403",
+        "GSE130935",
+        "GSE121992",
+        "GSE229212",
+        "GSE115687",
+        "GSE102881",
+        "GSE13284",
+        "GSE168532",
+        "GSE144476",
+        "GSE131809",
+        "GSE42382",
+        "GSE41573",
+        "GSE114709",
+        "GSE275063",
+        "GSE218232",
+        "GSE53441",
+        "GSE22366",
+        "GSE84635",
+        "GSE84633",
+        "GSE256494",
+        "GSE275157",
+        "GSE248760",
+        "GSE13283",
+        "GSE180998",
+        "GSE72999",
+        "GSE6578",
+        "GSE211942",
+        "GSE25014",
+        "GSE163144",
+        "GSE150056",
+        "GSE32035",
+        "GSE254951",
+        "GSE22162",
+        "GSE159373",
+        "GSE31757",
+        "GSE1849",
+        "GSE180999",
+        "GSE41575",
+        "GSE111860",
+        "GSE96060",
+        "GSE275158",
+        "GSE11507",
+        "GSE225966",
+        "GSE181000",
+        "GSE42384",
+        "GSE84634",
+        "GSE179362",
+        "GSE41574",
+        "GSE103445",
+        "GSE11372",
+        "GSE252778",
+        "GSE277175",
+        "GSE84632",
+        "GSE180855",
+        "GSE89373",
+        "GSE35102",
+        "GSE16728",
+        "GSE200675",
+        "GSE274340",
+        "GSE131387",
+        "GSE150341",
+        "GSE244401",
+        "GSE17078",
+        "GSE110936",
+        "GSE11060",
+        "GSE148529",
+        "GSE113544",
+        "GSE117613",
+        "GSE105035",
+        "GSE212603",
+        "GSE22367",
+        "GSE42383",
+        "GSE74977",
+        "GSE179359",
+        "GSE180869",
+        "GSE200676",
+        "GSE235633",
+        "GSE46471",
+        "GSE107775",
+        "GSE224834",
+        "GSE139912",
+        "GSE111356",
+        "GSE284318",
+        "GSE6479",
+        "GSE232221",
+        "GSE113503",
+        "GSE38528",
+        "GSE188695",
+        "GSE277176",
+        "GSE118357",
+        "GSE252686",
+        "GSE86418",
+        "GSE221182",
+        "GSE228819",
+        "GSE218231",
+        "GSE10002",
+        "GSE133181",
+        "GSE179360",
+        "GSE163912",
+        "GSE77207",
+        "GSE97671",
+        "GSE144413",
+        "GSE22368",
+        "GSE109257",
+        "GSE223911",
+        "GSE263200",
+        "GSE180860",
+        "GSE248671",
+        "GSE205876",
+        "GSE179363",
+        "GSE284319",
+        "GSE35007",
+        "GSE179364",
+        "GSE11524",
+        "GSE9877",
+        "GSE284394",
+        "GSE194064",
+        "GSE240446",
+        "GSE118358",
+        "GSE255403",
+        "GSE130935",
+        "GSE121992",
+        "GSE229212",
+        "GSE115687",
+        "GSE102881",
+        "GSE13284",
+        "GSE168532",
+        "GSE144476",
+        "GSE131809",
+        "GSE42382",
+        "GSE41573",
+        "GSE114709",
+        "GSE275063",
+        "GSE218232",
+        "GSE53441",
+        "GSE22366",
+        "GSE84635",
+        "GSE84633",
+        "GSE256494",
+        "GSE275157",
+        "GSE248760",
+        "GSE13283",
+        "GSE180998",
+        "GSE72999",
+        "GSE6578",
+        "GSE211942",
+        "GSE25014",
+        "GSE163144",
+        "GSE150056",
+        "GSE32035",
+        "GSE254951",
+        "GSE22162",
+        "GSE159373",
+        "GSE31757",
+        "GSE1849",
+        "GSE180999",
+        "GSE41575",
+        "GSE111860",
+        "GSE96060",
+        "GSE275158",
+        "GSE11507",
+        "GSE225966",
+        "GSE181000",
+        "GSE42384",
+        "GSE84634",
+        "GSE179362",
+        "GSE41574",
+        "GSE103445",
+        "GSE11372",
+        "GSE252778",
+        "GSE277175",
+        "GSE84632",
+        "GSE180855",
+        "GSE89373",
+        "GSE35102",
+        "GSE16728",
+        "GSE200675",
+        "GSE274340",
+        "GSE131387",
+        "GSE150341"
+    ],
+    "GARD:0007122": [
+        "GSE128357",
+        "GSE873",
+        "GSE182038",
+        "GSE103812",
+        "GSE103974",
+        "GSE215237",
+        "GSE11967",
+        "GSE92593",
+        "GSE263220",
+        "GSE112696",
+        "GSE11465",
+        "GSE85452",
+        "GSE131703",
+        "GSE227835",
+        "GSE154573",
+        "GSE85647",
+        "GSE85649",
+        "GSE167914",
+        "GSE233180",
+        "GSE111870"
+    ],
+    "GARD:0016928": [
+        "GSE47603",
+        "GSE174299",
+        "GSE158560",
+        "GSE174299",
+        "GSE158560"
+    ],
+    "GARD:0020951": [
+        "GSE67644",
+        "GSE252552",
+        "GSE268545",
+        "GSE9604",
+        "GSE20561",
+        "GSE202835",
+        "GSE206696",
+        "GSE242364",
+        "GSE4182",
+        "GSE25983",
+        "GSE246181",
+        "GSE232218",
+        "GSE121867",
+        "GSE81846",
+        "GSE28834",
+        "GSE164178",
+        "GSE69502",
+        "GSE77049",
+        "GSE33111",
+        "GSE169582",
+        "GSE169350",
+        "GSE81846",
+        "GSE28834",
+        "GSE206696",
+        "GSE101141"
+    ],
+    "GARD:0021879": [
+        "GSE29497",
+        "GSE152676"
+    ],
+    "GARD:0006233": [
+        "GSE129168",
+        "GSE98551",
+        "GSE28306",
+        "GSE620",
+        "GSE198534",
+        "GSE154803",
+        "GSE221966",
+        "GSE139038",
+        "GSE159056",
+        "GSE40445",
+        "GSE239869",
+        "GSE76347",
+        "GSE198718",
+        "GSE197189",
+        "GSE61243",
+        "GSE240500",
+        "GSE264019",
+        "GSE28152",
+        "GSE191060",
+        "GSE30568",
+        "GSE12245",
+        "GSE219733",
+        "GSE220854",
+        "GSE51086",
+        "GSE162693",
+        "GSE35711",
+        "GSE18265",
+        "GSE25129",
+        "GSE154806",
+        "GSE188904",
+        "GSE5715",
+        "GSE219789",
+        "GSE118567",
+        "GSE36174",
+        "GSE187762",
+        "GSE7177",
+        "GSE25130",
+        "GSE132106",
+        "GSE214434",
+        "GSE6122",
+        "GSE145360",
+        "GSE127696",
+        "GSE85976",
+        "GSE85857",
+        "GSE19621",
+        "GSE21704",
+        "GSE116753",
+        "GSE769",
+        "GSE154802",
+        "GSE191041",
+        "GSE177444",
+        "GSE220658",
+        "GSE139078",
+        "GSE10406",
+        "GSE172232",
+        "GSE134702",
+        "GSE104587",
+        "GSE237630",
+        "GSE81573",
+        "GSE9234",
+        "GSE126646",
+        "GSE154023",
+        "GSE35713",
+        "GSE15139",
+        "GSE124926",
+        "GSE110177",
+        "GSE41926",
+        "GSE234785",
+        "GSE75168",
+        "GSE7860",
+        "GSE77665",
+        "GSE142610",
+        "GSE102469",
+        "GSE252557",
+        "GSE2109",
+        "GSE10304",
+        "GSE110415",
+        "GSE125704",
+        "GSE10592",
+        "GSE219541",
+        "GSE4513",
+        "GSE107176",
+        "GSE102472",
+        "GSE165718",
+        "GSE15568",
+        "GSE166165",
+        "GSE38956",
+        "GSE20206",
+        "GSE51003",
+        "GSE111467",
+        "GSE198717",
+        "GSE48777",
+        "GSE202676",
+        "GSE163095",
+        "GSE10362",
+        "GSE136858",
+        "GSE202024",
+        "GSE195909",
+        "GSE244214",
+        "GSE237629",
+        "GSE158947",
+        "GSE52179",
+        "GSE128765",
+        "GSE209496",
+        "GSE233733",
+        "GSE7545",
+        "GSE186918",
+        "GSE101829",
+        "GSE26482",
+        "GSE167100",
+        "GSE12738",
+        "GSE48585",
+        "GSE132547",
+        "GSE7704",
+        "GSE131862",
+        "GSE107793",
+        "GSE9488",
+        "GSE239870",
+        "GSE83773",
+        "GSE3100",
+        "GSE235679",
+        "GSE284214",
+        "GSE52180",
+        "GSE219758",
+        "GSE70442",
+        "GSE128861",
+        "GSE55000",
+        "GSE8408",
+        "GSE198716",
+        "GSE241801",
+        "GSE186919",
+        "GSE126736",
+        "GSE42623",
+        "GSE246353",
+        "GSE67698",
+        "GSE35391",
+        "GSE221413",
+        "GSE123405",
+        "GSE141536",
+        "GSE141535",
+        "GSE60690",
+        "GSE162547",
+        "GSE71010",
+        "GSE6741",
+        "GSE187825",
+        "GSE165265",
+        "GSE31227",
+        "GSE234839",
+        "GSE197184",
+        "GSE163740",
+        "GSE153698",
+        "GSE210497",
+        "GSE110044",
+        "GSE57083",
+        "GSE71799",
+        "GSE170052",
+        "GSE68534",
+        "GSE165716",
+        "GSE237406",
+        "GSE50605",
+        "GSE209495",
+        "GSE21071",
+        "GSE100521",
+        "GSE75996",
+        "GSE74445",
+        "GSE203558",
+        "GSE276816",
+        "GSE154751",
+        "GSE177079",
+        "GSE4512",
+        "GSE33319",
+        "GSE9621",
+        "GSE119019",
+        "GSE185556",
+        "GSE136371",
+        "GSE31260",
+        "GSE22430",
+        "GSE167066",
+        "GSE55146",
+        "GSE29360",
+        "GSE150674",
+        "GSE153898",
+        "GSE80798",
+        "GSE208971",
+        "GSE128912",
+        "GSE98393",
+        "GSE185849",
+        "GSE154804",
+        "GSE205849",
+        "GSE121347",
+        "GSE198719",
+        "GSE107794",
+        "GSE245059",
+        "GSE74444",
+        "GSE183898",
+        "GSE53543",
+        "GSE108846",
+        "GSE2958",
+        "GSE101641",
+        "GSE209016",
+        "GSE94726",
+        "GSE193782",
+        "GSE203559",
+        "GSE13252",
+        "GSE25945",
+        "GSE53991",
+        "GSE18594",
+        "GSE119022",
+        "GSE152145",
+        "GSE15491",
+        "GSE102436",
+        "GSE39843",
+        "GSE247298",
+        "GSE71862",
+        "GSE246379",
+        "GSE182347",
+        "GSE61245",
+        "GSE25128",
+        "GSE19431",
+        "GSE165717",
+        "GSE200342",
+        "GSE261943",
+        "GSE197187",
+        "GSE6746",
+        "GSE2395",
+        "GSE188809",
+        "GSE135119",
+        "GSE121243",
+        "GSE107846",
+        "GSE77772",
+        "GSE209174",
+        "GSE70909",
+        "GSE26238",
+        "GSE51002",
+        "GSE17945",
+        "GSE131084",
+        "GSE263022",
+        "GSE110445",
+        "GSE8083",
+        "GSE209462",
+        "GSE264021",
+        "GSE102580",
+        "GSE103354",
+        "GSE171532",
+        "GSE150211",
+        "GSE268718",
+        "GSE129281",
+        "GSE237632",
+        "GSE42668",
+        "GSE78914",
+        "GSE154905",
+        "GSE136857",
+        "GSE285099",
+        "GSE25481",
+        "GSE176121",
+        "GSE148076",
+        "GSE71880",
+        "GSE74365",
+        "GSE74709",
+        "GSE159708",
+        "GSE765",
+        "GSE110935",
+        "GSE111754",
+        "GSE104329",
+        "GSE67006",
+        "GSE220853",
+        "GSE191061",
+        "GSE141537",
+        "GSE1469",
+        "GSE47173",
+        "GSE224547",
+        "GSE128723",
+        "GSE100287",
+        "GSE151264",
+        "GSE173073",
+        "GSE30439",
+        "GSE76095",
+        "GSE172916",
+        "GSE19115",
+        "GSE139662",
+        "GSE38267",
+        "GSE140405",
+        "GSE133495",
+        "GSE27594",
+        "GSE78175",
+        "GSE2430",
+        "GSE255619",
+        "GSE7178",
+        "GSE209154",
+        "GSE154805",
+        "GSE219907",
+        "GSE10030",
+        "GSE130159",
+        "GSE7179",
+        "GSE186920",
+        "GSE66634",
+        "GSE219794",
+        "GSE194288",
+        "GSE124548",
+        "GSE3090",
+        "GSE61244",
+        "GSE162562",
+        "GSE98552",
+        "GSE208489",
+        "GSE138716",
+        "GSE172550",
+        "GSE4485",
+        "GSE148963",
+        "GSE49061",
+        "GSE220852",
+        "GSE154807",
+        "GSE35394",
+        "GSE208460",
+        "GSE7957",
+        "GSE268909",
+        "GSE59800",
+        "GSE237631",
+        "GSE36647",
+        "GSE130226",
+        "GSE117885",
+        "GSE21966",
+        "GSE75169",
+        "GSE217102",
+        "GSE62970",
+        "GSE65935",
+        "GSE72821",
+        "GSE923",
+        "GSE182958",
+        "GSE36906",
+        "GSE139943",
+        "GSE75334",
+        "GSE217122",
+        "GSE101993",
+        "GSE18327",
+        "GSE42667",
+        "GSE35248",
+        "GSE174168",
+        "GSE30402",
+        "GSE5560",
+        "GSE110288",
+        "GSE99862",
+        "GSE95510",
+        "GSE142246",
+        "GSE97006",
+        "GSE33275",
+        "GSE172649",
+        "GSE182956",
+        "GSE69377",
+        "GSE219563",
+        "GSE205161",
+        "GSE232805",
+        "GSE72769",
+        "GSE233654",
+        "GSE264022",
+        "GSE110289",
+        "GSE81114",
+        "GSE238000"
+    ],
+    "GARD:0002356": [
+        "GSE78872",
+        "GSE67447",
+        "GSE236880",
+        "GSE40970",
+        "GSE14582",
+        "GSE178893",
+        "GSE171424",
+        "GSE40971",
+        "GSE16455",
+        "GSE132365",
+        "GSE54919",
+        "GSE4385",
+        "GSE41856",
+        "GSE157801",
+        "GSE65135",
+        "GSE56311",
+        "GSE155228",
+        "GSE23647",
+        "GSE39577",
+        "GSE218716",
+        "GSE120316",
+        "GSE105095",
+        "GSE41315",
+        "GSE152068",
+        "GSE142335",
+        "GSE31110",
+        "GSE3646",
+        "GSE12195",
+        "GSE26294",
+        "GSE80103",
+        "GSE218715",
+        "GSE130918",
+        "GSE16131",
+        "GSE270555",
+        "GSE56884",
+        "GSE231523",
+        "GSE41855",
+        "GSE68895",
+        "GSE125394",
+        "GSE67388",
+        "GSE159303",
+        "GSE182436",
+        "GSE37088",
+        "GSE12393",
+        "GSE73924",
+        "GSE48548",
+        "GSE28314",
+        "GSE124192",
+        "GSE138036",
+        "GSE86622",
+        "GSE67385",
+        "GSE272403",
+        "GSE135491",
+        "GSE3647",
+        "GSE252344",
+        "GSE152642",
+        "GSE67450",
+        "GSE81184",
+        "GSE27928",
+        "GSE114791",
+        "GSE68950",
+        "GSE86621",
+        "GSE156644",
+        "GSE132929",
+        "GSE67455",
+        "GSE35426",
+        "GSE107367",
+        "GSE154834",
+        "GSE154830",
+        "GSE152215",
+        "GSE158438",
+        "GSE84072",
+        "GSE120315",
+        "GSE273153",
+        "GSE41851",
+        "GSE8918",
+        "GSE166577",
+        "GSE165007",
+        "GSE22604",
+        "GSE252416",
+        "GSE22470",
+        "GSE243919",
+        "GSE15229",
+        "GSE52562",
+        "GSE255548",
+        "GSE42525",
+        "GSE93261",
+        "GSE142336",
+        "GSE208031",
+        "GSE278481",
+        "GSE148070",
+        "GSE68928",
+        "GSE54303",
+        "GSE182434",
+        "GSE6337",
+        "GSE62241",
+        "GSE220255",
+        "GSE254589",
+        "GSE54740",
+        "GSE23293",
+        "GSE37022",
+        "GSE261745",
+        "GSE103944",
+        "GSE16024",
+        "GSE9327",
+        "GSE60",
+        "GSE32232",
+        "GSE35424",
+        "GSE48047",
+        "GSE261746",
+        "GSE125393",
+        "GSE273154",
+        "GSE93985",
+        "GSE29493",
+        "GSE93984",
+        "GSE120124",
+        "GSE58718",
+        "GSE148656",
+        "GSE42977",
+        "GSE28090",
+        "GSE138032",
+        "GSE138033",
+        "GSE22082",
+        "GSE81183",
+        "GSE3887",
+        "GSE3458",
+        "GSE145841",
+        "GSE126247",
+        "GSE54920",
+        "GSE13029",
+        "GSE262093",
+        "GSE66384",
+        "GSE32436",
+        "GSE21554",
+        "GSE62245",
+        "GSE14214",
+        "GSE52561",
+        "GSE114492",
+        "GSE131618",
+        "GSE89869",
+        "GSE4351",
+        "GSE252642",
+        "GSE24183",
+        "GSE145848",
+        "GSE66166",
+        "GSE22208",
+        "GSE51359",
+        "GSE261917",
+        "GSE238258",
+        "GSE29165",
+        "GSE67417",
+        "GSE68307",
+        "GSE11635",
+        "GSE32231",
+        "GSE237987",
+        "GSE32233",
+        "GSE262094",
+        "GSE127462",
+        "GSE55267",
+        "GSE53820",
+        "GSE273152",
+        "GSE147125",
+        "GSE233953",
+        "GSE38816",
+        "GSE18736",
+        "GSE89688",
+        "GSE50973",
+        "GSE270480",
+        "GSE20019",
+        "GSE2350",
+        "GSE7425",
+        "GSE41239",
+        "GSE22898",
+        "GSE152386",
+        "GSE254591",
+        "GSE85233",
+        "GSE57083",
+        "GSE80263",
+        "GSE142334",
+        "GSE252687",
+        "GSE35331",
+        "GSE32018",
+        "GSE145846",
+        "GSE62246",
+        "GSE54916",
+        "GSE239433",
+        "GSE203610",
+        "GSE154831",
+        "GSE88799",
+        "GSE254594",
+        "GSE67763",
+        "GSE68092",
+        "GSE65134",
+        "GSE42637",
+        "GSE183030",
+        "GSE111052",
+        "GSE119214",
+        "GSE242756",
+        "GSE67494",
+        "GSE218717",
+        "GSE58613",
+        "GSE156640",
+        "GSE69255",
+        "GSE222532",
+        "GSE254595",
+        "GSE86613",
+        "GSE61912",
+        "GSE254593",
+        "GSE118707",
+        "GSE40641",
+        "GSE216645",
+        "GSE147033",
+        "GSE68308",
+        "GSE3211",
+        "GSE12453",
+        "GSE74102",
+        "GSE254588",
+        "GSE256457",
+        "GSE147211",
+        "GSE173820",
+        "GSE145842",
+        "GSE115795",
+        "GSE70479",
+        "GSE40989",
+        "GSE2109",
+        "GSE54158",
+        "GSE66714",
+        "GSE78872",
+        "GSE67447",
+        "GSE236880",
+        "GSE40970",
+        "GSE14582",
+        "GSE178893",
+        "GSE171424",
+        "GSE40971",
+        "GSE16455",
+        "GSE132365",
+        "GSE54919",
+        "GSE4385",
+        "GSE41856",
+        "GSE157801",
+        "GSE65135",
+        "GSE56311",
+        "GSE155228",
+        "GSE23647",
+        "GSE39577",
+        "GSE218716",
+        "GSE120316",
+        "GSE105095",
+        "GSE41315",
+        "GSE152068",
+        "GSE142335",
+        "GSE31110",
+        "GSE3646",
+        "GSE12195",
+        "GSE26294",
+        "GSE80103",
+        "GSE218715",
+        "GSE130918",
+        "GSE16131",
+        "GSE270555",
+        "GSE56884",
+        "GSE231523",
+        "GSE41855",
+        "GSE68895",
+        "GSE125394",
+        "GSE67388",
+        "GSE159303",
+        "GSE182436",
+        "GSE37088",
+        "GSE12393",
+        "GSE73924",
+        "GSE48548",
+        "GSE28314",
+        "GSE124192",
+        "GSE138036",
+        "GSE86622",
+        "GSE67385",
+        "GSE272403",
+        "GSE135491",
+        "GSE3647",
+        "GSE252344",
+        "GSE152642",
+        "GSE67450",
+        "GSE81184",
+        "GSE27928",
+        "GSE114791",
+        "GSE68950",
+        "GSE86621",
+        "GSE156644",
+        "GSE132929",
+        "GSE67455",
+        "GSE35426",
+        "GSE107367",
+        "GSE154834",
+        "GSE154830",
+        "GSE152215",
+        "GSE158438",
+        "GSE84072",
+        "GSE120315",
+        "GSE273153",
+        "GSE41851",
+        "GSE8918",
+        "GSE166577",
+        "GSE165007",
+        "GSE22604",
+        "GSE252416",
+        "GSE22470",
+        "GSE243919",
+        "GSE15229",
+        "GSE52562",
+        "GSE255548",
+        "GSE42525",
+        "GSE93261",
+        "GSE142336",
+        "GSE208031",
+        "GSE278481",
+        "GSE148070",
+        "GSE68928",
+        "GSE54303",
+        "GSE182434",
+        "GSE6337",
+        "GSE62241",
+        "GSE220255",
+        "GSE254589",
+        "GSE54740",
+        "GSE23293",
+        "GSE37022",
+        "GSE261745",
+        "GSE103944",
+        "GSE16024",
+        "GSE9327",
+        "GSE60",
+        "GSE32232",
+        "GSE35424",
+        "GSE48047",
+        "GSE261746",
+        "GSE125393",
+        "GSE273154",
+        "GSE93985",
+        "GSE29493",
+        "GSE93984",
+        "GSE120124",
+        "GSE58718",
+        "GSE148656",
+        "GSE42977",
+        "GSE28090",
+        "GSE138032",
+        "GSE138033",
+        "GSE22082",
+        "GSE81183",
+        "GSE3887",
+        "GSE3458",
+        "GSE145841",
+        "GSE126247",
+        "GSE54920",
+        "GSE13029",
+        "GSE262093",
+        "GSE66384",
+        "GSE32436",
+        "GSE21554",
+        "GSE62245",
+        "GSE14214",
+        "GSE52561",
+        "GSE114492",
+        "GSE131618",
+        "GSE89869",
+        "GSE4351",
+        "GSE252642",
+        "GSE24183",
+        "GSE145848",
+        "GSE66166",
+        "GSE22208",
+        "GSE51359",
+        "GSE261917",
+        "GSE238258",
+        "GSE29165",
+        "GSE67417",
+        "GSE68307",
+        "GSE11635",
+        "GSE32231",
+        "GSE237987",
+        "GSE32233",
+        "GSE262094",
+        "GSE127462",
+        "GSE55267",
+        "GSE53820",
+        "GSE273152",
+        "GSE147125",
+        "GSE233953",
+        "GSE38816",
+        "GSE18736",
+        "GSE89688",
+        "GSE50973",
+        "GSE270480",
+        "GSE20019",
+        "GSE2350",
+        "GSE7425",
+        "GSE41239",
+        "GSE22898",
+        "GSE152386",
+        "GSE254591",
+        "GSE85233",
+        "GSE57083",
+        "GSE80263",
+        "GSE142334",
+        "GSE252687",
+        "GSE35331",
+        "GSE32018",
+        "GSE145846",
+        "GSE62246",
+        "GSE54916",
+        "GSE239433",
+        "GSE203610",
+        "GSE154831",
+        "GSE88799",
+        "GSE254594",
+        "GSE67763",
+        "GSE68092",
+        "GSE65134",
+        "GSE42637",
+        "GSE183030",
+        "GSE111052",
+        "GSE119214",
+        "GSE242756",
+        "GSE67494",
+        "GSE218717",
+        "GSE58613",
+        "GSE156640",
+        "GSE69255",
+        "GSE222532",
+        "GSE254595",
+        "GSE86613",
+        "GSE61912",
+        "GSE254593",
+        "GSE118707",
+        "GSE40641",
+        "GSE216645",
+        "GSE147033",
+        "GSE68308",
+        "GSE3211",
+        "GSE12453",
+        "GSE74102",
+        "GSE254588",
+        "GSE256457",
+        "GSE147211",
+        "GSE173820",
+        "GSE145842",
+        "GSE115795",
+        "GSE70479",
+        "GSE40989",
+        "GSE2109",
+        "GSE54158",
+        "GSE66714"
+    ],
+    "GARD:0020333": [
+        "GSE69327",
+        "GSE178833",
+        "GSE200443",
+        "GSE99240"
+    ],
+    "GARD:0006102": [
+        "GSE252646",
+        "GSE180498",
+        "GSE252647"
+    ],
+    "GARD:0005699": [
+        "GSE48775",
+        "GSE209591",
+        "GSE167217",
+        "GSE74235",
+        "GSE130033",
+        "GSE84003",
+        "GSE185581",
+        "GSE88803"
+    ],
+    "GARD:0004386": [
+        "GSE247615",
+        "GSE8006",
+        "GSE199686",
+        "GSE67718",
+        "GSE255275",
+        "GSE167239",
+        "GSE232453",
+        "GSE255176",
+        "GSE159562",
+        "GSE67716",
+        "GSE232225",
+        "GSE112229",
+        "GSE162533",
+        "GSE18607",
+        "GSE87158",
+        "GSE226536",
+        "GSE24343",
+        "GSE232454",
+        "GSE47460",
+        "GSE156843",
+        "GSE67717",
+        "GSE27835",
+        "GSE67721",
+        "GSE232357",
+        "GSE67720",
+        "GSE20149",
+        "GSE199684",
+        "GSE11005",
+        "GSE232355",
+        "GSE255235",
+        "GSE157627",
+        "GSE199685",
+        "GSE80975",
+        "GSE225246",
+        "GSE230598",
+        "GSE136100",
+        "GSE79079",
+        "GSE51750"
+    ],
+    "GARD:0005728": [
+        "GSE16180",
+        "GSE102862",
+        "GSE20209"
+    ],
+    "GARD:0016642": [
+        "GSE282021",
+        "GSE69421",
+        "GSE263557",
+        "GSE156469",
+        "GSE122334",
+        "GSE157566",
+        "GSE196645",
+        "GSE249722",
+        "GSE215315",
+        "GSE108563",
+        "GSE95038",
+        "GSE99957",
+        "GSE245375",
+        "GSE13743",
+        "GSE168114",
+        "GSE283413",
+        "GSE157280",
+        "GSE61201",
+        "GSE205842",
+        "GSE253360",
+        "GSE154660",
+        "GSE197775",
+        "GSE228838",
+        "GSE11310",
+        "GSE157959",
+        "GSE255545",
+        "GSE95811",
+        "GSE182679",
+        "GSE83552",
+        "GSE196541",
+        "GSE165606",
+        "GSE44368",
+        "GSE38798",
+        "GSE245360",
+        "GSE161343",
+        "GSE65045",
+        "GSE108564",
+        "GSE71995",
+        "GSE200083",
+        "GSE71998",
+        "GSE26769",
+        "GSE214529",
+        "GSE108562",
+        "GSE223368",
+        "GSE278747",
+        "GSE252139",
+        "GSE16210",
+        "GSE23508",
+        "GSE24403",
+        "GSE247452",
+        "GSE267178",
+        "GSE215068",
+        "GSE140724",
+        "GSE195452",
+        "GSE121796",
+        "GSE234733",
+        "GSE252425",
+        "GSE165605",
+        "GSE157538",
+        "GSE65043",
+        "GSE102228",
+        "GSE172169",
+        "GSE99644",
+        "GSE128704",
+        "GSE232000",
+        "GSE230082",
+        "GSE182678",
+        "GSE228645",
+        "GSE214506",
+        "GSE157981",
+        "GSE164262",
+        "GSE214788",
+        "GSE212137",
+        "GSE74306",
+        "GSE158259",
+        "GSE168116",
+        "GSE145527",
+        "GSE111512",
+        "GSE112269",
+        "GSE155250",
+        "GSE120904",
+        "GSE92841",
+        "GSE140483",
+        "GSE54616",
+        "GSE143788",
+        "GSE87386",
+        "GSE219227",
+        "GSE116070",
+        "GSE7888",
+        "GSE65670",
+        "GSE215164",
+        "GSE79083",
+        "GSE180544",
+        "GSE54017",
+        "GSE74203",
+        "GSE17928",
+        "GSE197477",
+        "GSE179441",
+        "GSE232002",
+        "GSE205375",
+        "GSE227929",
+        "GSE73723",
+        "GSE193475",
+        "GSE56495",
+        "GSE72893",
+        "GSE83257",
+        "GSE83260",
+        "GSE17922",
+        "GSE10513",
+        "GSE10512",
+        "GSE223800",
+        "GSE227828",
+        "GSE148087",
+        "GSE200520",
+        "GSE229043",
+        "GSE222916",
+        "GSE192453",
+        "GSE110124",
+        "GSE182502",
+        "GSE165607",
+        "GSE207485",
+        "GSE240196",
+        "GSE183886",
+        "GSE180808",
+        "GSE227064",
+        "GSE149138",
+        "GSE229733",
+        "GSE81397",
+        "GSE83743",
+        "GSE31702",
+        "GSE269610",
+        "GSE83076",
+        "GSE7510",
+        "GSE163730",
+        "GSE138439",
+        "GSE161160",
+        "GSE75023",
+        "GSE212135",
+        "GSE190796",
+        "GSE159031",
+        "GSE151204",
+        "GSE124426",
+        "GSE175603",
+        "GSE150735",
+        "GSE255298",
+        "GSE231999",
+        "GSE183884",
+        "GSE108694",
+        "GSE183212",
+        "GSE112244",
+        "GSE100791",
+        "GSE218343",
+        "GSE230788",
+        "GSE10572",
+        "GSE17995",
+        "GSE141663",
+        "GSE276126",
+        "GSE39250",
+        "GSE182612",
+        "GSE174214",
+        "GSE36832",
+        "GSE103569",
+        "GSE83258",
+        "GSE182610",
+        "GSE119313",
+        "GSE164425",
+        "GSE284173",
+        "GSE110435",
+        "GSE60674",
+        "GSE70931",
+        "GSE249316",
+        "GSE196540",
+        "GSE101552",
+        "GSE50900",
+        "GSE202887",
+        "GSE243364",
+        "GSE230200",
+        "GSE223797",
+        "GSE260477",
+        "GSE73809",
+        "GSE48662",
+        "GSE230286",
+        "GSE23332",
+        "GSE230274",
+        "GSE210364",
+        "GSE190268",
+        "GSE255031",
+        "GSE182025",
+        "GSE159418",
+        "GSE64713",
+        "GSE203167",
+        "GSE235755",
+        "GSE183883",
+        "GSE23604",
+        "GSE150773",
+        "GSE134662",
+        "GSE225159",
+        "GSE153591",
+        "GSE76340",
+        "GSE141415",
+        "GSE17914",
+        "GSE270430",
+        "GSE192590",
+        "GSE59731",
+        "GSE17068",
+        "GSE22045",
+        "GSE214625",
+        "GSE141414",
+        "GSE73810",
+        "GSE279879",
+        "GSE223798",
+        "GSE175602",
+        "GSE113815",
+        "GSE252964",
+        "GSE212129",
+        "GSE93155",
+        "GSE78755",
+        "GSE135998",
+        "GSE4624",
+        "GSE190855",
+        "GSE159419",
+        "GSE126518",
+        "GSE75118",
+        "GSE223390",
+        "GSE84251",
+        "GSE9791",
+        "GSE166585",
+        "GSE229389",
+        "GSE232001",
+        "GSE71991",
+        "GSE142483",
+        "GSE223796",
+        "GSE227285",
+        "GSE262974",
+        "GSE225756",
+        "GSE223814",
+        "GSE200142",
+        "GSE252379",
+        "GSE10044",
+        "GSE58613",
+        "GSE226432",
+        "GSE24409",
+        "GSE164500",
+        "GSE215166",
+        "GSE185327",
+        "GSE230285",
+        "GSE84119",
+        "GSE21885",
+        "GSE184963",
+        "GSE234357",
+        "GSE216645",
+        "GSE75344",
+        "GSE269828",
+        "GSE175604",
+        "GSE285617",
+        "GSE236264",
+        "GSE138785",
+        "GSE147371",
+        "GSE282021",
+        "GSE69421",
+        "GSE263557",
+        "GSE156469",
+        "GSE122334",
+        "GSE157566",
+        "GSE196645",
+        "GSE249722",
+        "GSE215315",
+        "GSE108563",
+        "GSE95038",
+        "GSE99957",
+        "GSE245375",
+        "GSE13743",
+        "GSE168114",
+        "GSE283413",
+        "GSE157280",
+        "GSE61201",
+        "GSE205842",
+        "GSE253360",
+        "GSE154660",
+        "GSE197775",
+        "GSE228838",
+        "GSE11310",
+        "GSE157959",
+        "GSE255545",
+        "GSE95811",
+        "GSE182679",
+        "GSE83552",
+        "GSE196541",
+        "GSE165606",
+        "GSE44368",
+        "GSE38798",
+        "GSE245360",
+        "GSE161343",
+        "GSE65045",
+        "GSE108564",
+        "GSE71995",
+        "GSE200083",
+        "GSE71998",
+        "GSE26769",
+        "GSE214529",
+        "GSE108562",
+        "GSE223368",
+        "GSE278747",
+        "GSE252139",
+        "GSE16210",
+        "GSE23508",
+        "GSE24403",
+        "GSE247452",
+        "GSE267178",
+        "GSE215068",
+        "GSE140724",
+        "GSE195452",
+        "GSE121796",
+        "GSE234733",
+        "GSE252425",
+        "GSE165605",
+        "GSE157538",
+        "GSE65043",
+        "GSE102228",
+        "GSE172169",
+        "GSE99644",
+        "GSE128704",
+        "GSE232000",
+        "GSE230082",
+        "GSE182678",
+        "GSE228645",
+        "GSE214506",
+        "GSE157981",
+        "GSE164262",
+        "GSE214788",
+        "GSE212137",
+        "GSE74306",
+        "GSE158259",
+        "GSE168116",
+        "GSE145527",
+        "GSE111512",
+        "GSE112269",
+        "GSE155250",
+        "GSE120904",
+        "GSE92841",
+        "GSE140483",
+        "GSE54616",
+        "GSE143788",
+        "GSE87386",
+        "GSE219227",
+        "GSE116070",
+        "GSE7888",
+        "GSE65670",
+        "GSE215164",
+        "GSE79083",
+        "GSE180544",
+        "GSE54017",
+        "GSE74203",
+        "GSE17928",
+        "GSE197477",
+        "GSE179441",
+        "GSE232002",
+        "GSE205375",
+        "GSE227929",
+        "GSE73723",
+        "GSE193475",
+        "GSE56495",
+        "GSE72893",
+        "GSE83257",
+        "GSE83260",
+        "GSE17922",
+        "GSE10513",
+        "GSE10512",
+        "GSE223800",
+        "GSE227828",
+        "GSE148087",
+        "GSE200520",
+        "GSE229043",
+        "GSE222916",
+        "GSE192453",
+        "GSE110124",
+        "GSE182502",
+        "GSE165607",
+        "GSE207485",
+        "GSE240196",
+        "GSE183886",
+        "GSE180808",
+        "GSE227064",
+        "GSE149138",
+        "GSE229733",
+        "GSE81397",
+        "GSE83743",
+        "GSE31702",
+        "GSE269610",
+        "GSE83076",
+        "GSE7510",
+        "GSE163730",
+        "GSE138439",
+        "GSE161160",
+        "GSE75023",
+        "GSE212135",
+        "GSE190796",
+        "GSE159031",
+        "GSE151204",
+        "GSE124426",
+        "GSE175603",
+        "GSE150735",
+        "GSE255298",
+        "GSE231999",
+        "GSE183884",
+        "GSE108694",
+        "GSE183212",
+        "GSE112244",
+        "GSE100791",
+        "GSE218343",
+        "GSE230788",
+        "GSE10572",
+        "GSE17995",
+        "GSE141663",
+        "GSE276126",
+        "GSE39250",
+        "GSE182612",
+        "GSE174214",
+        "GSE36832",
+        "GSE103569",
+        "GSE83258",
+        "GSE182610",
+        "GSE119313",
+        "GSE164425",
+        "GSE284173",
+        "GSE110435",
+        "GSE60674",
+        "GSE70931",
+        "GSE249316",
+        "GSE196540",
+        "GSE101552",
+        "GSE50900",
+        "GSE202887",
+        "GSE243364",
+        "GSE230200",
+        "GSE223797",
+        "GSE260477",
+        "GSE73809",
+        "GSE48662",
+        "GSE230286",
+        "GSE23332",
+        "GSE230274",
+        "GSE210364",
+        "GSE190268",
+        "GSE255031",
+        "GSE182025",
+        "GSE159418",
+        "GSE64713",
+        "GSE203167",
+        "GSE235755",
+        "GSE183883",
+        "GSE23604",
+        "GSE150773",
+        "GSE134662",
+        "GSE225159",
+        "GSE153591",
+        "GSE76340",
+        "GSE141415",
+        "GSE17914",
+        "GSE270430",
+        "GSE192590",
+        "GSE59731",
+        "GSE17068",
+        "GSE22045",
+        "GSE214625",
+        "GSE141414",
+        "GSE73810",
+        "GSE279879",
+        "GSE223798",
+        "GSE175602",
+        "GSE113815",
+        "GSE252964",
+        "GSE212129",
+        "GSE93155",
+        "GSE78755",
+        "GSE135998",
+        "GSE4624",
+        "GSE190855",
+        "GSE159419",
+        "GSE126518",
+        "GSE75118",
+        "GSE223390",
+        "GSE84251",
+        "GSE9791",
+        "GSE166585",
+        "GSE229389",
+        "GSE232001",
+        "GSE71991",
+        "GSE142483",
+        "GSE223796",
+        "GSE227285",
+        "GSE262974",
+        "GSE225756",
+        "GSE223814",
+        "GSE200142",
+        "GSE252379",
+        "GSE10044",
+        "GSE58613",
+        "GSE226432",
+        "GSE24409",
+        "GSE164500",
+        "GSE215166",
+        "GSE185327",
+        "GSE230285",
+        "GSE84119",
+        "GSE21885",
+        "GSE184963",
+        "GSE234357",
+        "GSE216645",
+        "GSE75344",
+        "GSE269828",
+        "GSE175604",
+        "GSE285617",
+        "GSE236264",
+        "GSE138785",
+        "GSE147371"
+    ],
+    "GARD:0009525": [
+        "GSE241547",
+        "GSE71417",
+        "GSE18064",
+        "GSE179468",
+        "GSE52581",
+        "GSE274766",
+        "GSE21407",
+        "GSE121301",
+        "GSE146594",
+        "GSE274767",
+        "GSE196011",
+        "GSE40379",
+        "GSE242551",
+        "GSE132336",
+        "GSE200881",
+        "GSE178277",
+        "GSE102481",
+        "GSE186067",
+        "GSE33899",
+        "GSE142339",
+        "GSE85364",
+        "GSE52582",
+        "GSE43031",
+        "GSE146594",
+        "GSE178277",
+        "GSE274767",
+        "GSE40379",
+        "GSE85364",
+        "GSE179468",
+        "GSE274766",
+        "GSE163151"
+    ],
+    "GARD:0007425": [
+        "GSE95772",
+        "GSE125977",
+        "GSE221091",
+        "GSE100150",
+        "GSE181180",
+        "GSE243339",
+        "GSE94535",
+        "GSE5370",
+        "GSE155281",
+        "GSE133378",
+        "GSE39454",
+        "GSE11971",
+        "GSE1551",
+        "GSE100152",
+        "GSE46239",
+        "GSE32245",
+        "GSE11083",
+        "GSE142807",
+        "GSE128314",
+        "GSE493",
+        "GSE193276",
+        "GSE3112",
+        "GSE26852",
+        "GSE227124",
+        "GSE66845",
+        "GSE2044",
+        "GSE3307",
+        "GSE95735",
+        "GSE49062",
+        "GSE19033",
+        "GSE143323",
+        "GSE9397",
+        "GSE190684",
+        "GSE48280",
+        "GSE198794",
+        "GSE128470",
+        "GSE280931"
+    ],
+    "GARD:0006682": [
+        "GSE254100",
+        "GSE126327",
+        "GSE54838",
+        "GSE201945",
+        "GSE196017",
+        "GSE244940",
+        "GSE186802",
+        "GSE8696",
+        "GSE4623",
+        "GSE127896",
+        "GSE73191",
+        "GSE29551",
+        "GSE16985",
+        "GSE287750",
+        "GSE77246",
+        "GSE156404",
+        "GSE189420",
+        "GSE271767",
+        "GSE198497",
+        "GSE174251",
+        "GSE126408",
+        "GSE203332",
+        "GSE133063",
+        "GSE30016",
+        "GSE130677",
+        "GSE113233",
+        "GSE142241",
+        "GSE86268",
+        "GSE249900",
+        "GSE121867",
+        "GSE219228",
+        "GSE218143",
+        "GSE192946",
+        "GSE110226",
+        "GSE73190",
+        "GSE212672",
+        "GSE229749",
+        "GSE183715",
+        "GSE185438",
+        "GSE241018",
+        "GSE167559",
+        "GSE182718",
+        "GSE85080",
+        "GSE199649",
+        "GSE212236",
+        "GSE59612",
+        "GSE271764",
+        "GSE84241",
+        "GSE207546",
+        "GSE240627",
+        "GSE37098"
+    ],
+    "GARD:0007459": [
+        "GSE186333",
+        "GSE84178",
+        "GSE93171",
+        "GSE186399",
+        "GSE79850",
+        "GSE60753",
+        "GSE179993",
+        "GSE180288",
+        "GSE11907",
+        "GSE76162",
+        "GSE206364",
+        "GSE62408",
+        "GSE241014",
+        "GSE79094",
+        "GSE119600",
+        "GSE246059",
+        "GSE67504",
+        "GSE138888",
+        "GSE246060",
+        "GSE251872",
+        "GSE223894",
+        "GSE159676",
+        "GSE167116",
+        "GSE109182",
+        "GSE199065",
+        "GSE11908",
+        "GSE202676",
+        "GSE76161",
+        "GSE84954",
+        "GSE140249",
+        "GSE184066",
+        "GSE93170",
+        "GSE180289",
+        "GSE113707",
+        "GSE245661",
+        "GSE246061",
+        "GSE215278",
+        "GSE154548"
+    ],
+    "GARD:0002734": [
+        "GSE100849",
+        "GSE34011",
+        "GSE34010",
+        "GSE166586",
+        "GSE240712"
+    ],
+    "GARD:0024456": [
+        "GSE122903",
+        "GSE21619",
+        "GSE98952",
+        "GSE96823",
+        "GSE96822",
+        "GSE98951",
+        "GSE179407",
+        "GSE96861",
+        "GSE122905",
+        "GSE98954",
+        "GSE29161",
+        "GSE62390",
+        "GSE88803",
+        "GSE98953",
+        "GSE122904",
+        "GSE96862",
+        "GSE167914",
+        "GSE240319",
+        "GSE240320"
+    ],
+    "GARD:0010413": [
+        "GSE165956",
+        "GSE244998",
+        "GSE151949",
+        "GSE189153",
+        "GSE210217",
+        "GSE165417",
+        "GSE141281",
+        "GSE74452",
+        "GSE73579",
+        "GSE11500",
+        "GSE72554",
+        "GSE202681",
+        "GSE110057",
+        "GSE128522",
+        "GSE164564",
+        "GSE137945",
+        "GSE141279",
+        "GSE141741",
+        "GSE185948",
+        "GSE133530",
+        "GSE142664",
+        "GSE2673",
+        "GSE128524",
+        "GSE149739",
+        "GSE215875",
+        "GSE165418",
+        "GSE179947",
+        "GSE100812",
+        "GSE134720",
+        "GSE134721",
+        "GSE7869",
+        "GSE244450",
+        "GSE165416",
+        "GSE101811",
+        "GSE108864",
+        "GSE86508",
+        "GSE183512",
+        "GSE9167",
+        "GSE131277",
+        "GSE151951",
+        "GSE141739",
+        "GSE173694",
+        "GSE146714",
+        "GSE78808",
+        "GSE244997",
+        "GSE173695",
+        "GSE86507",
+        "GSE148840",
+        "GSE75578",
+        "GSE128521",
+        "GSE237528",
+        "GSE173693",
+        "GSE257535",
+        "GSE141280",
+        "GSE141740",
+        "GSE252716",
+        "GSE35831",
+        "GSE151950",
+        "GSE110786",
+        "GSE183510",
+        "GSE32586",
+        "GSE202065",
+        "GSE24352",
+        "GSE183511",
+        "GSE13452",
+        "GSE74453",
+        "GSE235269",
+        "GSE74451",
+        "GSE270531",
+        "GSE286070",
+        "GSE141355",
+        "GSE225495"
+    ],
+    "GARD:0021853": [
+        "GSE54426"
+    ],
+    "GARD:0019727": [
+        "GSE47603"
+    ],
+    "GARD:0010522": [
+        "GSE49704",
+        "GSE185143",
+        "GSE134384",
+        "GSE221970",
+        "GSE236903",
+        "GSE157061",
+        "GSE236904",
+        "GSE236902",
+        "GSE231966",
+        "GSE207853",
+        "GSE100019"
+    ],
+    "GARD:0007880": [
+        "GSE105149",
+        "GSE18885",
+        "GSE203432",
+        "GSE119136",
+        "GSE86884",
+        "GSE144302",
+        "GSE184898",
+        "GSE58331"
+    ],
+    "GARD:0018900": [
+        "GSE198331",
+        "GSE48634",
+        "GSE268790",
+        "GSE185101",
+        "GSE192819",
+        "GSE94648",
+        "GSE25275",
+        "GSE235236",
+        "GSE154014",
+        "GSE126124",
+        "GSE164918",
+        "GSE105074"
+    ],
+    "GARD:0010768": [
+        "GSE67933",
+        "GSE145102"
+    ],
+    "GARD:0019876": [
+        "GSE66987",
+        "GSE5563"
+    ],
+    "GARD:0019913": [
+        "GSE242232",
+        "GSE133028",
+        "GSE246608",
+        "GSE235277",
+        "GSE235276",
+        "GSE98784",
+        "GSE150598"
+    ],
+    "GARD:0002027": [
+        "GSE154725",
+        "GSE99590",
+        "GSE154726",
+        "GSE154728",
+        "GSE249875",
+        "GSE249876",
+        "GSE249877",
+        "GSE249994"
+    ],
+    "GARD:0016529": [
+        "GSE185818",
+        "GSE131559",
+        "GSE42437",
+        "GSE227589",
+        "GSE21251",
+        "GSE120331",
+        "GSE22404",
+        "GSE13996",
+        "GSE132348",
+        "GSE125651",
+        "GSE184662",
+        "GSE29545",
+        "GSE23647",
+        "GSE211445",
+        "GSE120538",
+        "GSE86845",
+        "GSE86068",
+        "GSE208543",
+        "GSE15264",
+        "GSE153517",
+        "GSE4109",
+        "GSE120330",
+        "GSE147387",
+        "GSE54157",
+        "GSE8388",
+        "GSE211443",
+        "GSE14879",
+        "GSE25986",
+        "GSE227013",
+        "GSE111052",
+        "GSE26101",
+        "GSE206130",
+        "GSE211444",
+        "GSE245920",
+        "GSE120329",
+        "GSE42441",
+        "GSE189927",
+        "GSE147116",
+        "GSE134511",
+        "GSE213461",
+        "GSE21586",
+        "GSE23591",
+        "GSE22208",
+        "GSE102693",
+        "GSE211441",
+        "GSE218703",
+        "GSE28079",
+        "GSE2657",
+        "GSE21253",
+        "GSE21252",
+        "GSE211913",
+        "GSE44244",
+        "GSE212902",
+        "GSE40160",
+        "GSE12453",
+        "GSE21254",
+        "GSE115191",
+        "GSE44551",
+        "GSE20011",
+        "GSE244989",
+        "GSE120328",
+        "GSE74983",
+        "GSE181063",
+        "GSE45264",
+        "GSE42440",
+        "GSE212326"
+    ],
+    "GARD:0025912": [
+        "GSE97372",
+        "GSE99590",
+        "GSE201686",
+        "GSE89180",
+        "GSE273219",
+        "GSE273221",
+        "GSE249875",
+        "GSE154729",
+        "GSE30960",
+        "GSE283266",
+        "GSE250291",
+        "GSE141278",
+        "GSE30190",
+        "GSE98839",
+        "GSE3064",
+        "GSE141244",
+        "GSE166712",
+        "GSE199836",
+        "GSE273220",
+        "GSE147633",
+        "GSE250293",
+        "GSE141277",
+        "GSE120440",
+        "GSE185476",
+        "GSE245093",
+        "GSE208353",
+        "GSE264536",
+        "GSE184957",
+        "GSE43771",
+        "GSE41157",
+        "GSE29985",
+        "GSE250295",
+        "GSE154726",
+        "GSE184959",
+        "GSE154728",
+        "GSE184958",
+        "GSE120635",
+        "GSE249876",
+        "GSE249994",
+        "GSE19419",
+        "GSE249877",
+        "GSE154725"
+    ],
+    "GARD:0020510": [
+        "GSE65270",
+        "GSE246987",
+        "GSE50788",
+        "GSE242085",
+        "GSE71997",
+        "GSE81266",
+        "GSE84779",
+        "GSE242086",
+        "GSE162335",
+        "GSE242087"
+    ],
+    "GARD:0005693": [
+        "GSE137634",
+        "GSE20881",
+        "GSE142049",
+        "GSE100648",
+        "GSE175364",
+        "GSE137594",
+        "GSE4579",
+        "GSE137593",
+        "GSE141934",
+        "GSE119404",
+        "GSE137634",
+        "GSE142049",
+        "GSE100648",
+        "GSE175364",
+        "GSE137594",
+        "GSE4579",
+        "GSE137593",
+        "GSE141934",
+        "GSE119404"
+    ],
+    "GARD:0003247": [
+        "GSE213346",
+        "GSE70666",
+        "GSE38616",
+        "GSE213349",
+        "GSE280583",
+        "GSE101619",
+        "GSE68407",
+        "GSE220609",
+        "GSE38617",
+        "GSE68406",
+        "GSE52130",
+        "GSE213345",
+        "GSE70664",
+        "GSE280584",
+        "GSE254542",
+        "GSE206391",
+        "GSE70665",
+        "GSE211630",
+        "GSE186075",
+        "GSE130403",
+        "GSE131567",
+        "GSE38615",
+        "GSE193351",
+        "GSE63741",
+        "GSE101618",
+        "GSE255248",
+        "GSE157538",
+        "GSE68408",
+        "GSE58121",
+        "GSE204663",
+        "GSE280220",
+        "GSE11905",
+        "GSE59131",
+        "GSE123781"
+    ],
+    "GARD:0007079": [
+        "GSE32040",
+        "GSE171999",
+        "GSE6613",
+        "GSE129531",
+        "GSE209944",
+        "GSE199724",
+        "GSE159812",
+        "GSE199715",
+        "GSE189525",
+        "GSE247259",
+        "GSE32041",
+        "GSE133357",
+        "GSE197153",
+        "GSE149632",
+        "GSE134472",
+        "GSE241198",
+        "GSE199258",
+        "GSE51781",
+        "GSE143157",
+        "GSE32037",
+        "GSE107582",
+        "GSE32039",
+        "GSE34287"
+    ],
+    "GARD:0008204": [
+        "GSE220100",
+        "GSE243002",
+        "GSE102114",
+        "GSE220100"
+    ],
+    "GARD:0006591": [
+        "GSE118157",
+        "GSE60910",
+        "GSE12629",
+        "GSE12510",
+        "GSE242919",
+        "GSE254503",
+        "GSE259214",
+        "GSE65581",
+        "GSE85051",
+        "GSE138331",
+        "GSE139993",
+        "GSE99619",
+        "GSE106436",
+        "GSE140078",
+        "GSE159492",
+        "GSE124663",
+        "GSE138332",
+        "GSE138330",
+        "GSE253521",
+        "GSE190760",
+        "GSE140079",
+        "GSE230495",
+        "GSE229621",
+        "GSE140295",
+        "GSE242926",
+        "GSE242805",
+        "GSE60909",
+        "GSE15809",
+        "GSE118157",
+        "GSE60910",
+        "GSE12629",
+        "GSE12510",
+        "GSE242919",
+        "GSE254503",
+        "GSE259214",
+        "GSE65581",
+        "GSE85051",
+        "GSE138331",
+        "GSE139993",
+        "GSE99619",
+        "GSE106436",
+        "GSE140078",
+        "GSE159492",
+        "GSE124663",
+        "GSE138332",
+        "GSE138330",
+        "GSE253521",
+        "GSE190760",
+        "GSE140079",
+        "GSE230495",
+        "GSE229621",
+        "GSE140295",
+        "GSE242926",
+        "GSE242805",
+        "GSE60909",
+        "GSE15809"
+    ],
+    "GARD:0007866": [
+        "GSE18447",
+        "GSE232451",
+        "GSE140913",
+        "GSE144601",
+        "GSE173577",
+        "GSE263046",
+        "GSE122774",
+        "GSE122775",
+        "GSE95085",
+        "GSE181985",
+        "GSE218046",
+        "GSE282216",
+        "GSE148249",
+        "GSE122773",
+        "GSE65831",
+        "GSE122776",
+        "GSE1482",
+        "GSE166080",
+        "GSE37607",
+        "GSE213787",
+        "GSE140986",
+        "GSE275047",
+        "GSE149946",
+        "GSE262030",
+        "GSE92647",
+        "GSE14038",
+        "GSE135189",
+        "GSE280335",
+        "GSE213786",
+        "GSE140987",
+        "GSE115890",
+        "GSE232766",
+        "GSE122999",
+        "GSE5675",
+        "GSE275048",
+        "GSE102345",
+        "GSE16041",
+        "GSE283902",
+        "GSE29343",
+        "GSE18448",
+        "GSE231603",
+        "GSE18445",
+        "GSE246610",
+        "GSE218493",
+        "GSE232707",
+        "GSE24328",
+        "GSE117322",
+        "GSE235594",
+        "GSE66743",
+        "GSE40212",
+        "GSE19730",
+        "GSE277520",
+        "GSE39764",
+        "GSE18444",
+        "GSE60082",
+        "GSE198656",
+        "GSE239561",
+        "GSE203647",
+        "GSE64869",
+        "GSE41747",
+        "GSE122730",
+        "GSE201668",
+        "GSE196652",
+        "GSE18447",
+        "GSE232451",
+        "GSE140913",
+        "GSE144601",
+        "GSE173577",
+        "GSE263046",
+        "GSE122774",
+        "GSE122775",
+        "GSE95085",
+        "GSE181985",
+        "GSE218046",
+        "GSE282216",
+        "GSE148249",
+        "GSE122773",
+        "GSE65831",
+        "GSE122776",
+        "GSE1482",
+        "GSE166080",
+        "GSE37607",
+        "GSE213787",
+        "GSE140986",
+        "GSE275047",
+        "GSE149946",
+        "GSE262030",
+        "GSE92647",
+        "GSE14038",
+        "GSE135189",
+        "GSE280335",
+        "GSE213786",
+        "GSE140987",
+        "GSE115890",
+        "GSE232766",
+        "GSE122999",
+        "GSE5675",
+        "GSE275048",
+        "GSE102345",
+        "GSE16041",
+        "GSE283902",
+        "GSE29343",
+        "GSE18448",
+        "GSE231603",
+        "GSE18445",
+        "GSE246610",
+        "GSE218493",
+        "GSE232707",
+        "GSE24328",
+        "GSE117322",
+        "GSE235594",
+        "GSE66743",
+        "GSE40212",
+        "GSE19730",
+        "GSE277520",
+        "GSE39764",
+        "GSE18444",
+        "GSE60082",
+        "GSE198656",
+        "GSE239561",
+        "GSE203647",
+        "GSE64869",
+        "GSE41747",
+        "GSE122730",
+        "GSE201668",
+        "GSE196652"
+    ],
+    "GARD:0009237": [
+        "GSE282769",
+        "GSE236941",
+        "GSE124016",
+        "GSE205621",
+        "GSE235094",
+        "GSE222249",
+        "GSE225517",
+        "GSE217556",
+        "GSE227648",
+        "GSE214664",
+        "GSE249308",
+        "GSE182745",
+        "GSE158261",
+        "GSE166489",
+        "GSE176269",
+        "GSE160033",
+        "GSE151879",
+        "GSE173590",
+        "GSE246452",
+        "GSE215262",
+        "GSE216020",
+        "GSE182994",
+        "GSE233732",
+        "GSE162039",
+        "GSE234486",
+        "GSE223139",
+        "GSE228594",
+        "GSE218934",
+        "GSE198882",
+        "GSE210676",
+        "GSE149036",
+        "GSE159372",
+        "GSE206101",
+        "GSE184288",
+        "GSE173835",
+        "GSE277027",
+        "GSE206147",
+        "GSE161777",
+        "GSE193264",
+        "GSE56192",
+        "GSE156761",
+        "GSE196464",
+        "GSE209800",
+        "GSE90624",
+        "GSE195673",
+        "GSE246312",
+        "GSE210476",
+        "GSE247916",
+        "GSE260604",
+        "GSE182264",
+        "GSE245922",
+        "GSE184330",
+        "GSE169687",
+        "GSE220046",
+        "GSE221319",
+        "GSE151878",
+        "GSE165193",
+        "GSE180578",
+        "GSE230080",
+        "GSE216048",
+        "GSE1739",
+        "GSE225349",
+        "GSE171668",
+        "GSE248556",
+        "GSE148816",
+        "GSE149973",
+        "GSE184569",
+        "GSE224464",
+        "GSE36971",
+        "GSE190036",
+        "GSE262439",
+        "GSE193722",
+        "GSE284042",
+        "GSE268196",
+        "GSE247910",
+        "GSE234939",
+        "GSE165747",
+        "GSE231529",
+        "GSE159212",
+        "GSE182299",
+        "GSE281135",
+        "GSE269423",
+        "GSE169159",
+        "GSE183714",
+        "GSE190672",
+        "GSE163624",
+        "GSE254309",
+        "GSE235131",
+        "GSE156544",
+        "GSE186460",
+        "GSE167341",
+        "GSE166651",
+        "GSE272713",
+        "GSE227585",
+        "GSE183356",
+        "GSE186267",
+        "GSE186621",
+        "GSE157490",
+        "GSE287123",
+        "GSE247186",
+        "GSE163632",
+        "GSE186672",
+        "GSE155106",
+        "GSE267622",
+        "GSE162615",
+        "GSE212861",
+        "GSE234805",
+        "GSE222764",
+        "GSE179184",
+        "GSE217796",
+        "GSE157036",
+        "GSE201390",
+        "GSE50848",
+        "GSE93283",
+        "GSE243732",
+        "GSE208337",
+        "GSE160034",
+        "GSE175779",
+        "GSE230398",
+        "GSE263657",
+        "GSE231416",
+        "GSE247445",
+        "GSE249432",
+        "GSE247904",
+        "GSE239372",
+        "GSE162113",
+        "GSE150819",
+        "GSE199498",
+        "GSE78915",
+        "GSE252877",
+        "GSE246819",
+        "GSE159272",
+        "GSE261002",
+        "GSE64660",
+        "GSE222252",
+        "GSE264683",
+        "GSE205014",
+        "GSE210497",
+        "GSE235130",
+        "GSE164332",
+        "GSE233894",
+        "GSE154784",
+        "GSE196113",
+        "GSE224710",
+        "GSE186794",
+        "GSE184401",
+        "GSE156755",
+        "GSE50000",
+        "GSE210058",
+        "GSE221799",
+        "GSE171690",
+        "GSE193732",
+        "GSE124979",
+        "GSE242722",
+        "GSE201391",
+        "GSE182562",
+        "GSE210695",
+        "GSE226702",
+        "GSE230656",
+        "GSE200132",
+        "GSE252444",
+        "GSE208612",
+        "GSE249304",
+        "GSE239587",
+        "GSE154104",
+        "GSE225382",
+        "GSE199743",
+        "GSE247912",
+        "GSE235133",
+        "GSE177543",
+        "GSE158052",
+        "GSE151327",
+        "GSE147194",
+        "GSE261996",
+        "GSE154769",
+        "GSE274784",
+        "GSE233230",
+        "GSE161615",
+        "GSE252508",
+        "GSE197665",
+        "GSE233943",
+        "GSE223612",
+        "GSE225722",
+        "GSE159213",
+        "GSE233046",
+        "GSE222872",
+        "GSE202965",
+        "GSE189920",
+        "GSE212119",
+        "GSE247806",
+        "GSE248773",
+        "GSE179131",
+        "GSE159522",
+        "GSE162736",
+        "GSE224063",
+        "GSE164485",
+        "GSE182394",
+        "GSE212410",
+        "GSE84081",
+        "GSE244173",
+        "GSE223476",
+        "GSE52405",
+        "GSE216357",
+        "GSE49263",
+        "GSE158752",
+        "GSE249998",
+        "GSE160163",
+        "GSE206023",
+        "GSE174621",
+        "GSE264189",
+        "GSE191089",
+        "GSE202262",
+        "GSE154564",
+        "GSE241292",
+        "GSE215802",
+        "GSE198899",
+        "GSE169241",
+        "GSE162494",
+        "GSE154782",
+        "GSE255644",
+        "GSE189015",
+        "GSE261262",
+        "GSE190895",
+        "GSE180118",
+        "GSE274266",
+        "GSE234487",
+        "GSE239646",
+        "GSE176169",
+        "GSE183850",
+        "GSE167075",
+        "GSE211741",
+        "GSE165005",
+        "GSE155536",
+        "GSE263817",
+        "GSE196988",
+        "GSE153218",
+        "GSE183507",
+        "GSE174745",
+        "GSE199001",
+        "GSE165532",
+        "GSE210271",
+        "GSE184287",
+        "GSE188429",
+        "GSE172471",
+        "GSE154936",
+        "GSE206263",
+        "GSE276876",
+        "GSE249581",
+        "GSE274964",
+        "GSE157057",
+        "GSE199286",
+        "GSE153851",
+        "GSE36969",
+        "GSE226820",
+        "GSE178699",
+        "GSE209974",
+        "GSE154761",
+        "GSE210675",
+        "GSE223690",
+        "GSE247908",
+        "GSE182297",
+        "GSE160232",
+        "GSE157526",
+        "GSE210228",
+        "GSE237132",
+        "GSE223236",
+        "GSE206134",
+        "GSE210660",
+        "GSE159812",
+        "GSE211934",
+        "GSE252959",
+        "GSE236842",
+        "GSE163838",
+        "GSE169158",
+        "GSE235050",
+        "GSE245040",
+        "GSE206635",
+        "GSE235153",
+        "GSE163530",
+        "GSE201894",
+        "GSE162618",
+        "GSE237121",
+        "GSE184390",
+        "GSE180795",
+        "GSE159787",
+        "GSE150847",
+        "GSE44274",
+        "GSE164380",
+        "GSE175666",
+        "GSE215865",
+        "GSE183716",
+        "GSE47962",
+        "GSE157103",
+        "GSE149601",
+        "GSE202967",
+        "GSE23955",
+        "GSE271754",
+        "GSE222381",
+        "GSE210231",
+        "GSE166766",
+        "GSE193639",
+        "GSE177027",
+        "GSE191080",
+        "GSE162323",
+        "GSE165373",
+        "GSE162612",
+        "GSE217099",
+        "GSE211378",
+        "GSE154171",
+        "GSE252448",
+        "GSE251849",
+        "GSE186627",
+        "GSE171037",
+        "GSE215441",
+        "GSE201266",
+        "GSE167400",
+        "GSE161262",
+        "GSE208440",
+        "GSE186020",
+        "GSE211240",
+        "GSE217429",
+        "GSE208565",
+        "GSE163959",
+        "GSE163317",
+        "GSE182742",
+        "GSE241891",
+        "GSE194061",
+        "GSE189731",
+        "GSE227282",
+        "GSE249987",
+        "GSE232623",
+        "GSE205244",
+        "GSE201269",
+        "GSE157486",
+        "GSE207840",
+        "GSE209676",
+        "GSE162911",
+        "GSE267009",
+        "GSE202998",
+        "GSE193169",
+        "GSE268640",
+        "GSE250024",
+        "GSE164571",
+        "GSE236563",
+        "GSE241893",
+        "GSE202964",
+        "GSE234484",
+        "GSE158298",
+        "GSE165190",
+        "GSE255601",
+        "GSE207077",
+        "GSE163623",
+        "GSE157344",
+        "GSE164379",
+        "GSE168400",
+        "GSE186623",
+        "GSE235437",
+        "GSE189613",
+        "GSE218644",
+        "GSE202553",
+        "GSE223056",
+        "GSE181866",
+        "GSE236318",
+        "GSE159191",
+        "GSE234008",
+        "GSE152641",
+        "GSE200562",
+        "GSE179949",
+        "GSE181877",
+        "GSE231409",
+        "GSE246128",
+        "GSE165080",
+        "GSE193724",
+        "GSE224290",
+        "GSE173086",
+        "GSE22581",
+        "GSE195894",
+        "GSE199272",
+        "GSE203081",
+        "GSE248989",
+        "GSE196989",
+        "GSE179709",
+        "GSE206677",
+        "GSE270518",
+        "GSE247903",
+        "GSE200422",
+        "GSE181827",
+        "GSE171052",
+        "GSE261313",
+        "GSE253235",
+        "GSE208034",
+        "GSE201921",
+        "GSE176393",
+        "GSE161810",
+        "GSE203064",
+        "GSE177477",
+        "GSE196893",
+        "GSE205099",
+        "GSE11704",
+        "GSE171430",
+        "GSE223213",
+        "GSE180622",
+        "GSE237741",
+        "GSE173317",
+        "GSE248984",
+        "GSE189199",
+        "GSE279405",
+        "GSE186167",
+        "GSE180632",
+        "GSE166703",
+        "GSE168998",
+        "GSE172920",
+        "GSE227529",
+        "GSE180063",
+        "GSE269780",
+        "GSE252876",
+        "GSE160036",
+        "GSE153277",
+        "GSE197521",
+        "GSE244484",
+        "GSE161665",
+        "GSE160230",
+        "GSE206510",
+        "GSE227530",
+        "GSE151973",
+        "GSE186799",
+        "GSE250023",
+        "GSE182849",
+        "GSE224028",
+        "GSE178157",
+        "GSE153684",
+        "GSE235164",
+        "GSE5972",
+        "GSE167334",
+        "GSE186624",
+        "GSE171742",
+        "GSE167421",
+        "GSE241888",
+        "GSE270479",
+        "GSE270321",
+        "GSE168098",
+        "GSE148729",
+        "GSE250025",
+        "GSE222487",
+        "GSE247807",
+        "GSE241385",
+        "GSE189619",
+        "GSE162317",
+        "GSE222548",
+        "GSE273241",
+        "GSE183300",
+        "GSE249303",
+        "GSE193990",
+        "GSE168388",
+        "GSE223140",
+        "GSE157034",
+        "GSE243426",
+        "GSE247907",
+        "GSE236942",
+        "GSE179325",
+        "GSE197962",
+        "GSE235435",
+        "GSE148815",
+        "GSE247808",
+        "GSE196802",
+        "GSE216529",
+        "GSE214564",
+        "GSE188382",
+        "GSE17400",
+        "GSE149907",
+        "GSE190674",
+        "GSE190165",
+        "GSE210059",
+        "GSE151346",
+        "GSE161934",
+        "GSE159585",
+        "GSE172923",
+        "GSE228112",
+        "GSE254256",
+        "GSE163426",
+        "GSE227562",
+        "GSE244297",
+        "GSE175900",
+        "GSE186650",
+        "GSE178399",
+        "GSE253698",
+        "GSE208533",
+        "GSE247914",
+        "GSE196649",
+        "GSE158930",
+        "GSE190913",
+        "GSE151880",
+        "GSE191232",
+        "GSE182920",
+        "GSE201268",
+        "GSE152439",
+        "GSE201156",
+        "GSE236876",
+        "GSE149689",
+        "GSE247488",
+        "GSE239585",
+        "GSE239631",
+        "GSE156063",
+        "GSE210229",
+        "GSE158030",
+        "GSE161731",
+        "GSE160032",
+        "GSE154998",
+        "GSE167000",
+        "GSE228507",
+        "GSE161881",
+        "GSE186628",
+        "GSE195871",
+        "GSE208575",
+        "GSE166424",
+        "GSE68820",
+        "GSE274933",
+        "GSE180365",
+        "GSE176201",
+        "GSE200274",
+        "GSE169599",
+        "GSE232627",
+        "GSE199130",
+        "GSE189263",
+        "GSE193708",
+        "GSE185488",
+        "GSE267639",
+        "GSE174786",
+        "GSE200596",
+        "GSE151803",
+        "GSE217370",
+        "GSE225564",
+        "GSE244965",
+        "GSE241039",
+        "GSE243733",
+        "GSE216488",
+        "GSE181238",
+        "GSE271808",
+        "GSE239588",
+        "GSE239787",
+        "GSE205620",
+        "GSE167029",
+        "GSE232423",
+        "GSE215814",
+        "GSE546",
+        "GSE261278",
+        "GSE222765",
+        "GSE239450",
+        "GSE235150",
+        "GSE179923",
+        "GSE208240",
+        "GSE268812",
+        "GSE235136",
+        "GSE210223",
+        "GSE158835",
+        "GSE160031",
+        "GSE182826",
+        "GSE247809",
+        "GSE284624",
+        "GSE245466",
+        "GSE167747",
+        "GSE158050",
+        "GSE270367",
+        "GSE271988",
+        "GSE197258",
+        "GSE227971",
+        "GSE155900",
+        "GSE254647",
+        "GSE167402",
+        "GSE188477",
+        "GSE247915",
+        "GSE171620",
+        "GSE50855",
+        "GSE251973",
+        "GSE156760",
+        "GSE159788",
+        "GSE176405",
+        "GSE201534",
+        "GSE247909",
+        "GSE177541",
+        "GSE190350",
+        "GSE158038",
+        "GSE186475",
+        "GSE158297",
+        "GSE264701",
+        "GSE227116",
+        "GSE219037",
+        "GSE224615",
+        "GSE237092",
+        "GSE147903",
+        "GSE235132",
+        "GSE190747",
+        "GSE56677",
+        "GSE152586",
+        "GSE266967",
+        "GSE282488",
+        "GSE173707",
+        "GSE195870",
+        "GSE209615",
+        "GSE222326",
+        "GSE162208",
+        "GSE237059",
+        "GSE172241",
+        "GSE47963",
+        "GSE197204",
+        "GSE195541",
+        "GSE189990",
+        "GSE167749",
+        "GSE50878",
+        "GSE264679",
+        "GSE162835",
+        "GSE159513",
+        "GSE146074",
+        "GSE176233",
+        "GSE160631",
+        "GSE196455",
+        "GSE177545",
+        "GSE235986",
+        "GSE239835",
+        "GSE159717",
+        "GSE180594",
+        "GSE183999",
+        "GSE165025",
+        "GSE216049",
+        "GSE184949",
+        "GSE239595",
+        "GSE155986",
+        "GSE274026",
+        "GSE229187",
+        "GSE236562",
+        "GSE171370",
+        "GSE235262",
+        "GSE162562",
+        "GSE240108",
+        "GSE189900",
+        "GSE209985",
+        "GSE158036",
+        "GSE201463",
+        "GSE287567",
+        "GSE240694",
+        "GSE253948",
+        "GSE184536",
+        "GSE229570",
+        "GSE173507",
+        "GSE40827",
+        "GSE190193",
+        "GSE261920",
+        "GSE161263",
+        "GSE228111",
+        "GSE229622",
+        "GSE244820",
+        "GSE37827",
+        "GSE171080",
+        "GSE202095",
+        "GSE193288",
+        "GSE252446",
+        "GSE158948",
+        "GSE190004",
+        "GSE168215",
+        "GSE216644",
+        "GSE161663",
+        "GSE244483",
+        "GSE161200",
+        "GSE229459",
+        "GSE163151",
+        "GSE244486",
+        "GSE221510",
+        "GSE222431",
+        "GSE237122",
+        "GSE176442",
+        "GSE148697",
+        "GSE173186",
+        "GSE254516",
+        "GSE173418",
+        "GSE162316",
+        "GSE192472",
+        "GSE166990",
+        "GSE159576",
+        "GSE156598",
+        "GSE198592",
+        "GSE197976",
+        "GSE224198",
+        "GSE184173",
+        "GSE235135",
+        "GSE226758",
+        "GSE211851",
+        "GSE7779",
+        "GSE234236",
+        "GSE274686",
+        "GSE183408",
+        "GSE274938",
+        "GSE19137",
+        "GSE259276",
+        "GSE230130",
+        "GSE217504",
+        "GSE153940",
+        "GSE162131",
+        "GSE252878",
+        "GSE227649",
+        "GSE173488",
+        "GSE235159",
+        "GSE194378",
+        "GSE183579",
+        "GSE223885",
+        "GSE171009",
+        "GSE207015",
+        "GSE182475",
+        "GSE167030",
+        "GSE263469",
+        "GSE194062",
+        "GSE159785",
+        "GSE181032",
+        "GSE189792",
+        "GSE148696",
+        "GSE217181",
+        "GSE157058",
+        "GSE154770",
+        "GSE160876",
+        "GSE202963",
+        "GSE241133",
+        "GSE227942",
+        "GSE164565",
+        "GSE158877",
+        "GSE153931",
+        "GSE252445",
+        "GSE214516",
+        "GSE195542",
+        "GSE180389",
+        "GSE225942",
+        "GSE226959",
+        "GSE240903",
+        "GSE218165",
+        "GSE235626",
+        "GSE277947",
+        "GSE172054",
+        "GSE274932",
+        "GSE161916",
+        "GSE249313",
+        "GSE171010",
+        "GSE235436",
+        "GSE210661",
+        "GSE212584",
+        "GSE239818",
+        "GSE202869",
+        "GSE210272",
+        "GSE160824",
+        "GSE177025",
+        "GSE203401",
+        "GSE174398",
+        "GSE249111",
+        "GSE225474",
+        "GSE193555",
+        "GSE208320",
+        "GSE247406",
+        "GSE158374",
+        "GSE188945",
+        "GSE162492",
+        "GSE235433",
+        "GSE157859",
+        "GSE162495",
+        "GSE172274",
+        "GSE276775",
+        "GSE273371",
+        "GSE172114",
+        "GSE155974",
+        "GSE192702",
+        "GSE274586",
+        "GSE253847",
+        "GSE150962",
+        "GSE181422",
+        "GSE203229",
+        "GSE196938",
+        "GSE150148",
+        "GSE173310",
+        "GSE228504",
+        "GSE155249",
+        "GSE212041",
+        "GSE250155",
+        "GSE147507",
+        "GSE233642",
+        "GSE171828",
+        "GSE239643",
+        "GSE155733",
+        "GSE159584",
+        "GSE231910",
+        "GSE215915",
+        "GSE193879",
+        "GSE227647",
+        "GSE157424",
+        "GSE222489",
+        "GSE148113",
+        "GSE203166",
+        "GSE186360",
+        "GSE189887",
+        "GSE167336",
+        "GSE247913",
+        "GSE213313",
+        "GSE203001",
+        "GSE192890",
+        "GSE148829",
+        "GSE203030",
+        "GSE201267",
+        "GSE245876",
+        "GSE218033",
+        "GSE162569",
+        "GSE247917",
+        "GSE156005",
+        "GSE246866",
+        "GSE253635",
+        "GSE201535",
+        "GSE151513",
+        "GSE239452",
+        "GSE171382",
+        "GSE233557",
+        "GSE267021",
+        "GSE164013",
+        "GSE232168",
+        "GSE222760",
+        "GSE246535",
+        "GSE205369",
+        "GSE203065",
+        "GSE228446",
+        "GSE161381",
+        "GSE167028",
+        "GSE180563",
+        "GSE189794",
+        "GSE209537",
+        "GSE241849",
+        "GSE166160",
+        "GSE230022",
+        "GSE267642",
+        "GSE155286",
+        "GSE200074",
+        "GSE171130",
+        "GSE190680",
+        "GSE142503",
+        "GSE171711",
+        "GSE160864",
+        "GSE185471",
+        "GSE158034",
+        "GSE205402",
+        "GSE209550",
+        "GSE162629",
+        "GSE211972",
+        "GSE196987",
+        "GSE47961",
+        "GSE196456",
+        "GSE106850",
+        "GSE59185",
+        "GSE182572",
+        "GSE164073",
+        "GSE166411",
+        "GSE223142",
+        "GSE246242",
+        "GSE214694",
+        "GSE231528",
+        "GSE243731",
+        "GSE190432",
+        "GSE165200",
+        "GSE165340",
+        "GSE232616",
+        "GSE215906",
+        "GSE228779",
+        "GSE181046",
+        "GSE186625",
+        "GSE164784",
+        "GSE47960",
+        "GSE282879",
+        "GSE155454",
+        "GSE158127",
+        "GSE262861",
+        "GSE228268",
+        "GSE222002",
+        "GSE165477",
+        "GSE206265",
+        "GSE188792",
+        "GSE157055",
+        "GSE178942",
+        "GSE247906",
+        "GSE216974",
+        "GSE163698",
+        "GSE185432",
+        "GSE167310",
+        "GSE276544",
+        "GSE209616",
+        "GSE249500",
+        "GSE162899",
+        "GSE224955",
+        "GSE202296",
+        "GSE147975",
+        "GSE176080",
+        "GSE165182",
+        "GSE155717",
+        "GSE162318",
+        "GSE162247",
+        "GSE172118",
+        "GSE21318",
+        "GSE195939",
+        "GSE227528",
+        "GSE184610",
+        "GSE207665",
+        "GSE182569",
+        "GSE241135",
+        "GSE166190",
+        "GSE199816",
+        "GSE248489",
+        "GSE229424",
+        "GSE193834",
+        "GSE52920",
+        "GSE246178",
+        "GSE174843",
+        "GSE232226",
+        "GSE150392",
+        "GSE163676",
+        "GSE150316",
+        "GSE186201",
+        "GSE165955",
+        "GSE282247",
+        "GSE161383",
+        "GSE178333",
+        "GSE260625",
+        "GSE168797",
+        "GSE260817",
+        "GSE206283",
+        "GSE267226",
+        "GSE227280",
+        "GSE252056",
+        "GSE159519",
+        "GSE247911",
+        "GSE193330",
+        "GSE253234",
+        "GSE254984",
+        "GSE159593",
+        "GSE160435",
+        "GSE239893",
+        "GSE33266",
+        "GSE158484",
+        "GSE169504",
+        "GSE167480",
+        "GSE206264",
+        "GSE182883",
+        "GSE157059",
+        "GSE171488",
+        "GSE205429",
+        "GSE222987",
+        "GSE233059",
+        "GSE209806",
+        "GSE220190",
+        "GSE156754",
+        "GSE167403",
+        "GSE211061",
+        "GSE152522",
+        "GSE207981",
+        "GSE211394",
+        "GSE254993",
+        "GSE253876",
+        "GSE185602",
+        "GSE180595",
+        "GSE178967",
+        "GSE220682",
+        "GSE174382",
+        "GSE217863",
+        "GSE161664",
+        "GSE196820",
+        "GSE30743",
+        "GSE33818",
+        "GSE275240",
+        "GSE268810",
+        "GSE236800",
+        "GSE182183",
+        "GSE174072",
+        "GSE247094",
+        "GSE287550",
+        "GSE169399",
+        "GSE244714",
+        "GSE206996",
+        "GSE180984",
+        "GSE204696",
+        "GSE261966",
+        "GSE189039",
+        "GSE193022",
+        "GSE216851",
+        "GSE26477",
+        "GSE152075",
+        "GSE49262",
+        "GSE230092",
+        "GSE180557",
+        "GSE166209",
+        "GSE56193",
+        "GSE267645",
+        "GSE196488",
+        "GSE161264",
+        "GSE162040",
+        "GSE248086",
+        "GSE202182",
+        "GSE261311",
+        "GSE156701",
+        "GSE148881",
+        "GSE247370",
+        "GSE166253",
+        "GSE189086",
+        "GSE149687",
+        "GSE162491",
+        "GSE154613",
+        "GSE179251",
+        "GSE185406",
+        "GSE164547",
+        "GSE190659",
+        "GSE166281",
+        "GSE178491",
+        "GSE268369",
+        "GSE208116",
+        "GSE193839",
+        "GSE231673",
+        "GSE166778",
+        "GSE190673",
+        "GSE173946",
+        "GSE163547",
+        "GSE283001",
+        "GSE217918",
+        "GSE236939",
+        "GSE217483",
+        "GSE189259",
+        "GSE208587",
+        "GSE254409",
+        "GSE161089",
+        "GSE276765",
+        "GSE188678",
+        "GSE162619",
+        "GSE184715",
+        "GSE155222",
+        "GSE157852",
+        "GSE199668",
+        "GSE191088",
+        "GSE283152",
+        "GSE149878",
+        "GSE231415",
+        "GSE168739",
+        "GSE225603",
+        "GSE56189",
+        "GSE201790",
+        "GSE228236",
+        "GSE209750",
+        "GSE223646",
+        "GSE234242",
+        "GSE284552",
+        "GSE163529",
+        "GSE239451",
+        "GSE222251",
+        "GSE155113",
+        "GSE163668",
+        "GSE210061",
+        "GSE163688",
+        "GSE169503",
+        "GSE158037",
+        "GSE214663",
+        "GSE225602",
+        "GSE201533",
+        "GSE271679",
+        "GSE154311",
+        "GSE154244",
+        "GSE173498",
+        "GSE209797",
+        "GSE200896",
+        "GSE182917",
+        "GSE167202",
+        "GSE167528",
+        "GSE166530",
+        "GSE157789",
+        "GSE30589",
+        "GSE198864",
+        "GSE40824",
+        "GSE203220",
+        "GSE193122",
+        "GSE248778",
+        "GSE201212",
+        "GSE164386",
+        "GSE173567",
+        "GSE40840",
+        "GSE216486",
+        "GSE201530",
+        "GSE158069",
+        "GSE171995",
+        "GSE165890",
+        "GSE197255",
+        "GSE159556",
+        "GSE167131",
+        "GSE201471",
+        "GSE215433",
+        "GSE193723",
+        "GSE201626",
+        "GSE246985",
+        "GSE271482",
+        "GSE168095",
+        "GSE248775",
+        "GSE247902",
+        "GSE158055",
+        "GSE255211",
+        "GSE164533",
+        "GSE195721",
+        "GSE39568",
+        "GSE195540",
+        "GSE195796",
+        "GSE174399",
+        "GSE161382",
+        "GSE184932",
+        "GSE214555",
+        "GSE241843",
+        "GSE198281",
+        "GSE167319",
+        "GSE274265",
+        "GSE274550",
+        "GSE283771",
+        "GSE180523",
+        "GSE240766",
+        "GSE212003",
+        "GSE196980",
+        "GSE149312",
+        "GSE240940",
+        "GSE171008",
+        "GSE180908",
+        "GSE45042",
+        "GSE227211",
+        "GSE160231",
+        "GSE254179",
+        "GSE274267",
+        "GSE189791",
+        "GSE235978",
+        "GSE242397",
+        "GSE182738",
+        "GSE171524",
+        "GSE205487",
+        "GSE212411",
+        "GSE174635",
+        "GSE218401",
+        "GSE242775",
+        "GSE153984",
+        "GSE283190",
+        "GSE228320",
+        "GSE248875",
+        "GSE249570",
+        "GSE161917",
+        "GSE169370",
+        "GSE221316",
+        "GSE184806",
+        "GSE147863",
+        "GSE21802",
+        "GSE153970",
+        "GSE171703",
+        "GSE233522",
+        "GSE159214",
+        "GSE253857",
+        "GSE186622",
+        "GSE33267",
+        "GSE235232",
+        "GSE272381",
+        "GSE148360",
+        "GSE213998",
+        "GSE185557",
+        "GSE243217",
+        "GSE180391",
+        "GSE162038",
+        "GSE161915",
+        "GSE253474",
+        "GSE159201",
+        "GSE206455",
+        "GSE213192",
+        "GSE173568",
+        "GSE244485",
+        "GSE154662",
+        "GSE213997",
+        "GSE148817",
+        "GSE247805",
+        "GSE216484",
+        "GSE185657",
+        "GSE224951",
+        "GSE266907",
+        "GSE266968",
+        "GSE219086",
+        "GSE179156",
+        "GSE179277",
+        "GSE173508",
+        "GSE270045",
+        "GSE243268",
+        "GSE210694",
+        "GSE178331",
+        "GSE156988",
+        "GSE177537",
+        "GSE164948",
+        "GSE239449",
+        "GSE243218",
+        "GSE207151",
+        "GSE213759",
+        "GSE187420",
+        "GSE176480",
+        "GSE219098",
+        "GSE198722",
+        "GSE210664",
+        "GSE180417",
+        "GSE184150",
+        "GSE156759",
+        "GSE154783",
+        "GSE234720",
+        "GSE265975",
+        "GSE172921",
+        "GSE231711",
+        "GSE154430",
+        "GSE189514",
+        "GSE243734",
+        "GSE272645",
+        "GSE212866",
+        "GSE231530",
+        "GSE150708",
+        "GSE269769",
+        "GSE171390",
+        "GSE200561",
+        "GSE163774",
+        "GSE184657",
+        "GSE210227",
+        "GSE261967",
+        "GSE152060",
+        "GSE236601",
+        "GSE233548",
+        "GSE161281",
+        "GSE190496",
+        "GSE181005",
+        "GSE253542",
+        "GSE241890",
+        "GSE253845",
+        "GSE176224",
+        "GSE51387",
+        "GSE217200",
+        "GSE236841",
+        "GSE171381",
+        "GSE244322",
+        "GSE235938",
+        "GSE227080",
+        "GSE180390",
+        "GSE253385",
+        "GSE181787",
+        "GSE178757",
+        "GSE208076",
+        "GSE214247",
+        "GSE235134",
+        "GSE236294",
+        "GSE220077",
+        "GSE224131",
+        "GSE186213",
+        "GSE151161",
+        "GSE183280",
+        "GSE181002",
+        "GSE229135",
+        "GSE205619",
+        "GSE198449",
+        "GSE232117",
+        "GSE155223",
+        "GSE214150",
+        "GSE155897",
+        "GSE236651",
+        "GSE166397",
+        "GSE199545",
+        "GSE247905",
+        "GSE184289",
+        "GSE247901",
+        "GSE211812",
+        "GSE212865",
+        "GSE155241",
+        "GSE230227",
+        "GSE211562",
+        "GSE206266",
+        "GSE225165",
+        "GSE267228",
+        "GSE212191",
+        "GSE235162",
+        "GSE154768",
+        "GSE161988",
+        "GSE202966",
+        "GSE178246",
+        "GSE272840",
+        "GSE273994",
+        "GSE260583",
+        "GSE21319",
+        "GSE174682",
+        "GSE175996",
+        "GSE221320",
+        "GSE155518",
+        "GSE244488",
+        "GSE260763",
+        "GSE155363",
+        "GSE159316",
+        "GSE160668",
+        "GSE252396",
+        "GSE189706",
+        "GSE162086",
+        "GSE184447",
+        "GSE212701",
+        "GSE195879",
+        "GSE216811",
+        "GSE250377",
+        "GSE237131",
+        "GSE151764",
+        "GSE210659",
+        "GSE199922",
+        "GSE190839",
+        "GSE220076",
+        "GSE279753",
+        "GSE207923",
+        "GSE183621",
+        "GSE19398",
+        "GSE224845",
+        "GSE36016",
+        "GSE157032",
+        "GSE225601",
+        "GSE230301",
+        "GSE227846",
+        "GSE184678",
+        "GSE150728",
+        "GSE198096",
+        "GSE51386"
+    ],
+    "GARD:0020568": [
+        "GSE44275",
+        "GSE261205",
+        "GSE20881"
+    ],
+    "GARD:0016535": [
+        "GSE206227",
+        "GSE199284",
+        "GSE186845",
+        "GSE145903",
+        "GSE227776",
+        "GSE479",
+        "GSE110964",
+        "GSE223807",
+        "GSE190720",
+        "GSE261874",
+        "GSE182081",
+        "GSE249352",
+        "GSE82083",
+        "GSE128101",
+        "GSE174251",
+        "GSE110965",
+        "GSE153534",
+        "GSE152389",
+        "GSE8759",
+        "GSE189091",
+        "GSE78833",
+        "GSE82079",
+        "GSE104365",
+        "GSE182101",
+        "GSE137681",
+        "GSE110966",
+        "GSE199283",
+        "GSE109797",
+        "GSE109722",
+        "GSE1852",
+        "GSE128481",
+        "GSE199282"
+    ],
+    "GARD:0009749": [
+        "GSE32268",
+        "GSE262896",
+        "GSE247955",
+        "GSE141435",
+        "GSE123281",
+        "GSE57431",
+        "GSE66148",
+        "GSE72391",
+        "GSE275956",
+        "GSE80149",
+        "GSE221853",
+        "GSE130500",
+        "GSE34918",
+        "GSE17043",
+        "GSE200196",
+        "GSE70245",
+        "GSE232763",
+        "GSE210521",
+        "GSE142101",
+        "GSE972",
+        "GSE195590",
+        "GSE182632",
+        "GSE188241",
+        "GSE165589",
+        "GSE147821",
+        "GSE63592",
+        "GSE153614",
+        "GSE137241",
+        "GSE196321",
+        "GSE75125",
+        "GSE150007",
+        "GSE135471",
+        "GSE181287",
+        "GSE152752",
+        "GSE161130",
+        "GSE145551",
+        "GSE129114",
+        "GSE30596",
+        "GSE166460",
+        "GSE281763",
+        "GSE128191",
+        "GSE44299",
+        "GSE139409",
+        "GSE11788",
+        "GSE42519",
+        "GSE164110",
+        "GSE34920",
+        "GSE246248",
+        "GSE197786",
+        "GSE246603",
+        "GSE180183",
+        "GSE111327",
+        "GSE220081",
+        "GSE228339",
+        "GSE230319",
+        "GSE173284",
+        "GSE30167",
+        "GSE203116",
+        "GSE121324",
+        "GSE45226",
+        "GSE229148",
+        "GSE53679",
+        "GSE105016",
+        "GSE205213",
+        "GSE215795",
+        "GSE89437",
+        "GSE44727",
+        "GSE202440",
+        "GSE267008",
+        "GSE161126",
+        "GSE242700",
+        "GSE202057",
+        "GSE199441",
+        "GSE202442",
+        "GSE77207",
+        "GSE65050",
+        "GSE232762",
+        "GSE205212",
+        "GSE192640",
+        "GSE102123",
+        "GSE45223",
+        "GSE138619",
+        "GSE66851",
+        "GSE8759",
+        "GSE78268",
+        "GSE270155",
+        "GSE256464",
+        "GSE228342",
+        "GSE250526",
+        "GSE94082",
+        "GSE216674",
+        "GSE150006",
+        "GSE81430",
+        "GSE195573",
+        "GSE202238",
+        "GSE202055",
+        "GSE81072",
+        "GSE165344",
+        "GSE185279",
+        "GSE61273",
+        "GSE85620",
+        "GSE272480",
+        "GSE39918",
+        "GSE107843",
+        "GSE151850",
+        "GSE275132",
+        "GSE281769",
+        "GSE137721",
+        "GSE181577",
+        "GSE19698",
+        "GSE63040",
+        "GSE9285",
+        "GSE12007",
+        "GSE15969",
+        "GSE125124",
+        "GSE62123",
+        "GSE63428",
+        "GSE201257",
+        "GSE115353",
+        "GSE89420",
+        "GSE137614",
+        "GSE18043",
+        "GSE23954",
+        "GSE212225",
+        "GSE252061",
+        "GSE230316",
+        "GSE96631",
+        "GSE237713",
+        "GSE145327",
+        "GSE107053",
+        "GSE264211",
+        "GSE180196",
+        "GSE74701",
+        "GSE82095",
+        "GSE202441",
+        "GSE32386",
+        "GSE243840",
+        "GSE236673",
+        "GSE151700",
+        "GSE230317",
+        "GSE214632",
+        "GSE14421",
+        "GSE175809",
+        "GSE147270",
+        "GSE140150",
+        "GSE130079",
+        "GSE166603",
+        "GSE22092",
+        "GSE56999",
+        "GSE184359",
+        "GSE184364",
+        "GSE175808",
+        "GSE103240",
+        "GSE99317",
+        "GSE68044",
+        "GSE241522",
+        "GSE180194",
+        "GSE68052",
+        "GSE42589",
+        "GSE136449",
+        "GSE228343",
+        "GSE137240",
+        "GSE80151",
+        "GSE144366",
+        "GSE24598",
+        "GSE57430",
+        "GSE68546",
+        "GSE261846",
+        "GSE253235",
+        "GSE101655",
+        "GSE34303",
+        "GSE180999",
+        "GSE197927",
+        "GSE89188",
+        "GSE230303",
+        "GSE181562",
+        "GSE202058",
+        "GSE95815",
+        "GSE59125",
+        "GSE205900",
+        "GSE219149",
+        "GSE121427",
+        "GSE11149",
+        "GSE161176",
+        "GSE104849",
+        "GSE81282",
+        "GSE64556",
+        "GSE180519",
+        "GSE126089",
+        "GSE62680",
+        "GSE250528",
+        "GSE65049",
+        "GSE263087",
+        "GSE50251",
+        "GSE241256",
+        "GSE246805",
+        "GSE149688",
+        "GSE109432",
+        "GSE76806",
+        "GSE104420",
+        "GSE221188",
+        "GSE168131",
+        "GSE80153",
+        "GSE221031",
+        "GSE138538",
+        "GSE143912",
+        "GSE218217",
+        "GSE108518",
+        "GSE87641",
+        "GSE61823",
+        "GSE23709",
+        "GSE21539",
+        "GSE183307",
+        "GSE260990",
+        "GSE217214",
+        "GSE42572",
+        "GSE51034",
+        "GSE215960",
+        "GSE152755",
+        "GSE52220",
+        "GSE202195",
+        "GSE192906",
+        "GSE216759",
+        "GSE26980",
+        "GSE52357",
+        "GSE161510",
+        "GSE221330",
+        "GSE263169",
+        "GSE87750",
+        "GSE27159",
+        "GSE68047",
+        "GSE274407",
+        "GSE210015",
+        "GSE51297",
+        "GSE21511",
+        "GSE184622",
+        "GSE108199",
+        "GSE70237",
+        "GSE163768",
+        "GSE189381",
+        "GSE228194",
+        "GSE19664",
+        "GSE232516",
+        "GSE204731",
+        "GSE199440",
+        "GSE213132",
+        "GSE246806",
+        "GSE127469",
+        "GSE163757",
+        "GSE125711",
+        "GSE117304",
+        "GSE219153",
+        "GSE232432",
+        "GSE265932",
+        "GSE113074",
+        "GSE8066",
+        "GSE212234",
+        "GSE47919",
+        "GSE104950",
+        "GSE76809",
+        "GSE114961",
+        "GSE61674",
+        "GSE178823",
+        "GSE263168",
+        "GSE182783",
+        "GSE277165",
+        "GSE83317",
+        "GSE89436",
+        "GSE68045",
+        "GSE103822",
+        "GSE34904",
+        "GSE95780",
+        "GSE168303",
+        "GSE25256",
+        "GSE216125",
+        "GSE67338",
+        "GSE177489",
+        "GSE57001",
+        "GSE32339",
+        "GSE223901",
+        "GSE89670",
+        "GSE175767",
+        "GSE111753",
+        "GSE205903",
+        "GSE174708",
+        "GSE67073",
+        "GSE63895",
+        "GSE35506",
+        "GSE66850",
+        "GSE119962",
+        "GSE75355",
+        "GSE230315",
+        "GSE115149",
+        "GSE261828",
+        "GSE100907",
+        "GSE7007",
+        "GSE143911",
+        "GSE107516",
+        "GSE205904",
+        "GSE93134",
+        "GSE77114",
+        "GSE149369",
+        "GSE272868",
+        "GSE180546",
+        "GSE192645",
+        "GSE241499",
+        "GSE143910",
+        "GSE80130",
+        "GSE94914",
+        "GSE2295",
+        "GSE80335",
+        "GSE244473",
+        "GSE134532",
+        "GSE39346",
+        "GSE64513",
+        "GSE172069",
+        "GSE232163",
+        "GSE141106",
+        "GSE242157",
+        "GSE208184",
+        "GSE152599",
+        "GSE109137",
+        "GSE194430",
+        "GSE84666",
+        "GSE44297",
+        "GSE112072",
+        "GSE13002",
+        "GSE149884",
+        "GSE35148",
+        "GSE263091",
+        "GSE148699",
+        "GSE198561",
+        "GSE230350",
+        "GSE41121",
+        "GSE57518",
+        "GSE222639",
+        "GSE108517",
+        "GSE77272",
+        "GSE45491",
+        "GSE17312",
+        "GSE250450",
+        "GSE53203",
+        "GSE202196",
+        "GSE211906",
+        "GSE216492",
+        "GSE175095",
+        "GSE234616",
+        "GSE92764",
+        "GSE91377",
+        "GSE142309",
+        "GSE139859",
+        "GSE72985",
+        "GSE143395",
+        "GSE243834",
+        "GSE223900",
+        "GSE225890",
+        "GSE169654",
+        "GSE283071",
+        "GSE80334",
+        "GSE185119",
+        "GSE211660",
+        "GSE186198",
+        "GSE184227",
+        "GSE121131",
+        "GSE143913",
+        "GSE239305",
+        "GSE150709",
+        "GSE57505",
+        "GSE126087",
+        "GSE206745",
+        "GSE9451",
+        "GSE83327",
+        "GSE241903",
+        "GSE178805",
+        "GSE278072",
+        "GSE237881",
+        "GSE217212",
+        "GSE282770",
+        "GSE224158",
+        "GSE142752",
+        "GSE69108",
+        "GSE205902",
+        "GSE46561",
+        "GSE250247",
+        "GSE122714",
+        "GSE67555",
+        "GSE206903",
+        "GSE201378",
+        "GSE133014",
+        "GSE210139",
+        "GSE190462",
+        "GSE223104",
+        "GSE195519",
+        "GSE109267",
+        "GSE92763",
+        "GSE29742",
+        "GSE120409",
+        "GSE46591",
+        "GSE102553",
+        "GSE47407",
+        "GSE46387",
+        "GSE162035",
+        "GSE140247",
+        "GSE14340",
+        "GSE226566",
+        "GSE113297",
+        "GSE127269",
+        "GSE62117",
+        "GSE246672",
+        "GSE161531",
+        "GSE232560",
+        "GSE195730",
+        "GSE124075",
+        "GSE177517",
+        "GSE80663",
+        "GSE216138",
+        "GSE182402",
+        "GSE67786",
+        "GSE217298",
+        "GSE11482",
+        "GSE18690",
+        "GSE180998",
+        "GSE105145",
+        "GSE85636",
+        "GSE66032",
+        "GSE144311",
+        "GSE50643",
+        "GSE80662",
+        "GSE45968",
+        "GSE178364",
+        "GSE73355",
+        "GSE80150",
+        "GSE201511",
+        "GSE60313",
+        "GSE214996",
+        "GSE139273",
+        "GSE234071",
+        "GSE162044",
+        "GSE41122",
+        "GSE198491",
+        "GSE183319",
+        "GSE114894",
+        "GSE21517",
+        "GSE228340",
+        "GSE89910",
+        "GSE94521",
+        "GSE211902",
+        "GSE28875",
+        "GSE172742",
+        "GSE62816",
+        "GSE27176",
+        "GSE275825",
+        "GSE141107",
+        "GSE123142",
+        "GSE252573",
+        "GSE276561",
+        "GSE165590",
+        "GSE81717",
+        "GSE10934",
+        "GSE181000",
+        "GSE103849",
+        "GSE168179",
+        "GSE56430",
+        "GSE37189",
+        "GSE211903",
+        "GSE174949",
+        "GSE239434",
+        "GSE237970",
+        "GSE120434",
+        "GSE262095",
+        "GSE111153",
+        "GSE64752",
+        "GSE198297",
+        "GSE215109",
+        "GSE145306",
+        "GSE253865",
+        "GSE54720",
+        "GSE164327",
+        "GSE249075",
+        "GSE11029",
+        "GSE135237",
+        "GSE104141",
+        "GSE121507",
+        "GSE200674",
+        "GSE179986",
+        "GSE108521",
+        "GSE255577",
+        "GSE99551",
+        "GSE131737",
+        "GSE52358",
+        "GSE178969",
+        "GSE230176",
+        "GSE70751",
+        "GSE33767",
+        "GSE196592",
+        "GSE222213",
+        "GSE73180",
+        "GSE266652",
+        "GSE149860",
+        "GSE178434",
+        "GSE223132",
+        "GSE162889",
+        "GSE116173",
+        "GSE29634",
+        "GSE186696",
+        "GSE206048",
+        "GSE168200",
+        "GSE22989",
+        "GSE199439",
+        "GSE223750",
+        "GSE169529",
+        "GSE116140",
+        "GSE62247",
+        "GSE236680",
+        "GSE162973",
+        "GSE4680",
+        "GSE45893",
+        "GSE6460",
+        "GSE286314",
+        "GSE6868",
+        "GSE140319",
+        "GSE53678",
+        "GSE206008",
+        "GSE153121",
+        "GSE2841",
+        "GSE165303",
+        "GSE187102",
+        "GSE89435",
+        "GSE137219",
+        "GSE229532",
+        "GSE120678",
+        "GSE119537",
+        "GSE121526",
+        "GSE80393",
+        "GSE242826",
+        "GSE81026",
+        "GSE72268",
+        "GSE41123",
+        "GSE75356",
+        "GSE77363",
+        "GSE68898",
+        "GSE125141",
+        "GSE84430",
+        "GSE80689",
+        "GSE246769",
+        "GSE213382",
+        "GSE268988",
+        "GSE34502",
+        "GSE151649",
+        "GSE109686",
+        "GSE202059",
+        "GSE263778",
+        "GSE41179",
+        "GSE183309",
+        "GSE18477",
+        "GSE23530",
+        "GSE80165",
+        "GSE217197",
+        "GSE125143",
+        "GSE61510",
+        "GSE137462",
+        "GSE211899",
+        "GSE169322",
+        "GSE211901",
+        "GSE165588",
+        "GSE202671",
+        "GSE9339",
+        "GSE188163",
+        "GSE137975",
+        "GSE195589",
+        "GSE117754",
+        "GSE223614",
+        "GSE263086",
+        "GSE42548",
+        "GSE245175",
+        "GSE169280",
+        "GSE178834",
+        "GSE176731",
+        "GSE110872",
+        "GSE100538",
+        "GSE57810",
+        "GSE24730",
+        "GSE166625",
+        "GSE121329",
+        "GSE53677",
+        "GSE9894",
+        "GSE42254",
+        "GSE262042",
+        "GSE250527",
+        "GSE199158",
+        "GSE132857",
+        "GSE133141",
+        "GSE176055",
+        "GSE104163",
+        "GSE60394",
+        "GSE1588",
+        "GSE121429",
+        "GSE30716",
+        "GSE212793",
+        "GSE197631",
+        "GSE235864",
+        "GSE14391",
+        "GSE72815",
+        "GSE11979",
+        "GSE179984",
+        "GSE250387",
+        "GSE131136",
+        "GSE124312",
+        "GSE206197",
+        "GSE230318",
+        "GSE119534",
+        "GSE252428",
+        "GSE104473",
+        "GSE210251",
+        "GSE108943",
+        "GSE149072",
+        "GSE111766",
+        "GSE185255",
+        "GSE157575",
+        "GSE80152",
+        "GSE54719",
+        "GSE58474",
+        "GSE38381",
+        "GSE78002",
+        "GSE69311",
+        "GSE141664",
+        "GSE45159",
+        "GSE68776",
+        "GSE223615",
+        "GSE67087",
+        "GSE246807",
+        "GSE211904",
+        "GSE100905",
+        "GSE69110",
+        "GSE28874",
+        "GSE117305",
+        "GSE188990",
+        "GSE250009",
+        "GSE124579",
+        "GSE99382",
+        "GSE127245",
+        "GSE114464",
+        "GSE119498",
+        "GSE50059",
+        "GSE205901",
+        "GSE156031",
+        "GSE115348",
+        "GSE189544",
+        "GSE131293",
+        "GSE78003",
+        "GSE141439",
+        "GSE163961",
+        "GSE205214",
+        "GSE156146",
+        "GSE80509",
+        "GSE186707",
+        "GSE90683",
+        "GSE180187",
+        "GSE163826",
+        "GSE176965",
+        "GSE96629",
+        "GSE58916",
+        "GSE77513",
+        "GSE216136",
+        "GSE211478",
+        "GSE131793",
+        "GSE85621",
+        "GSE16249",
+        "GSE163771",
+        "GSE95814",
+        "GSE80288",
+        "GSE261227",
+        "GSE67124",
+        "GSE178784",
+        "GSE161281",
+        "GSE146809",
+        "GSE89434",
+        "GSE19465",
+        "GSE261603",
+        "GSE216760",
+        "GSE163907",
+        "GSE17448",
+        "GSE175114",
+        "GSE284063",
+        "GSE35218",
+        "GSE238166",
+        "GSE182721",
+        "GSE161579",
+        "GSE261358",
+        "GSE168133",
+        "GSE69109",
+        "GSE221190",
+        "GSE79928",
+        "GSE226565",
+        "GSE20399",
+        "GSE19617",
+        "GSE126880",
+        "GSE173696",
+        "GSE192676",
+        "GSE34208",
+        "GSE5658",
+        "GSE125140",
+        "GSE99636",
+        "GSE278071",
+        "GSE236674",
+        "GSE206128",
+        "GSE193097",
+        "GSE198492",
+        "GSE10360",
+        "GSE240190",
+        "GSE46791",
+        "GSE131155",
+        "GSE193815",
+        "GSE212226",
+        "GSE108506",
+        "GSE113736",
+        "GSE95812",
+        "GSE8368",
+        "GSE205436",
+        "GSE127795",
+        "GSE213728",
+        "GSE106219",
+        "GSE228341",
+        "GSE133009",
+        "GSE135851",
+        "GSE102542",
+        "GSE124073",
+        "GSE108515",
+        "GSE175647",
+        "GSE1822",
+        "GSE154483",
+        "GSE106676",
+        "GSE120936",
+        "GSE183305",
+        "GSE46150",
+        "GSE39540",
+        "GSE202056",
+        "GSE55964",
+        "GSE134768",
+        "GSE129801",
+        "GSE117844",
+        "GSE208250",
+        "GSE150582",
+        "GSE108230",
+        "GSE184363",
+        "GSE202198",
+        "GSE183308",
+        "GSE127260",
+        "GSE38066",
+        "GSE202197",
+        "GSE140193",
+        "GSE126088",
+        "GSE30419",
+        "GSE157356",
+        "GSE161120",
+        "GSE108918",
+        "GSE80107",
+        "GSE44257",
+        "GSE61206",
+        "GSE215977",
+        "GSE169516",
+        "GSE181561",
+        "GSE172029",
+        "GSE160312",
+        "GSE219151",
+        "GSE57064",
+        "GSE262468",
+        "GSE250370",
+        "GSE19987",
+        "GSE92333",
+        "GSE44537",
+        "GSE222566",
+        "GSE120200",
+        "GSE68636",
+        "GSE220475",
+        "GSE198493",
+        "GSE115140",
+        "GSE121318",
+        "GSE99933",
+        "GSE46792",
+        "GSE252615",
+        "GSE205446",
+        "GSE50487",
+        "GSE255684",
+        "GSE137227",
+        "GSE100998",
+        "GSE185394",
+        "GSE261486",
+        "GSE185669",
+        "GSE136057",
+        "GSE254500",
+        "GSE235280",
+        "GSE11028",
+        "GSE55173",
+        "GSE205448",
+        "GSE103402",
+        "GSE100793",
+        "GSE92765",
+        "GSE120920",
+        "GSE36474",
+        "GSE193007",
+        "GSE39191",
+        "GSE164108",
+        "GSE57003",
+        "GSE282901",
+        "GSE57125",
+        "GSE243072",
+        "GSE176101",
+        "GSE68040",
+        "GSE278511",
+        "GSE255060",
+        "GSE229531",
+        "GSE214099",
+        "GSE140636",
+        "GSE75352",
+        "GSE44295",
+        "GSE279710",
+        "GSE125145",
+        "GSE196544",
+        "GSE246685",
+        "GSE14038",
+        "GSE221125",
+        "GSE61695",
+        "GSE176634",
+        "GSE190305",
+        "GSE125480",
+        "GSE79988",
+        "GSE12274",
+        "GSE13129",
+        "GSE196386",
+        "GSE222212",
+        "GSE225530",
+        "GSE32308",
+        "GSE78890",
+        "GSE154972",
+        "GSE178687",
+        "GSE11027",
+        "GSE217199",
+        "GSE217757",
+        "GSE121044",
+        "GSE28199",
+        "GSE28876",
+        "GSE34912",
+        "GSE63058",
+        "GSE200689",
+        "GSE166262",
+        "GSE103748",
+        "GSE52456",
+        "GSE108221",
+        "GSE174572",
+        "GSE168399",
+        "GSE125707",
+        "GSE182329",
+        "GSE101661",
+        "GSE80252",
+        "GSE198562",
+        "GSE135832",
+        "GSE183306",
+        "GSE61755",
+        "GSE207592",
+        "GSE58476",
+        "GSE68039",
+        "GSE42678",
+        "GSE72322",
+        "GSE274096",
+        "GSE223616",
+        "GSE161565",
+        "GSE275013",
+        "GSE213390",
+        "GSE85598",
+        "GSE226568",
+        "GSE56957",
+        "GSE185592",
+        "GSE83400",
+        "GSE68101",
+        "GSE55967",
+        "GSE216920",
+        "GSE125142",
+        "GSE75748",
+        "GSE228335",
+        "GSE90711",
+        "GSE10454",
+        "GSE262111",
+        "GSE52227",
+        "GSE118682",
+        "GSE186770",
+        "GSE107968",
+        "GSE222042",
+        "GSE170335",
+        "GSE263085",
+        "GSE175811",
+        "GSE155691",
+        "GSE101909",
+        "GSE77364",
+        "GSE31205",
+        "GSE198231",
+        "GSE172066",
+        "GSE64000",
+        "GSE95813",
+        "GSE211664",
+        "GSE243814",
+        "GSE165826",
+        "GSE116110",
+        "GSE208369",
+        "GSE223103",
+        "GSE11356",
+        "GSE161143",
+        "GSE102552",
+        "GSE252592",
+        "GSE139168",
+        "GSE126457",
+        "GSE106325",
+        "GSE44296",
+        "GSE258835",
+        "GSE75351",
+        "GSE242228",
+        "GSE173251",
+        "GSE162238",
+        "GSE131688",
+        "GSE261748",
+        "GSE211900",
+        "GSE142337",
+        "GSE190002",
+        "GSE200486",
+        "GSE136448",
+        "GSE125710",
+        "GSE76807",
+        "GSE263084",
+        "GSE186199",
+        "GSE218625",
+        "GSE70353",
+        "GSE97851",
+        "GSE75354",
+        "GSE146481",
+        "GSE261360",
+        "GSE163960",
+        "GSE25501",
+        "GSE130526",
+        "GSE123686",
+        "GSE172059",
+        "GSE145048",
+        "GSE121428",
+        "GSE235534",
+        "GSE138905",
+        "GSE183002",
+        "GSE86212",
+        "GSE152906",
+        "GSE125709",
+        "GSE155690",
+        "GSE101746",
+        "GSE255790",
+        "GSE121527",
+        "GSE166246",
+        "GSE197513",
+        "GSE224197",
+        "GSE174446",
+        "GSE149855",
+        "GSE172028",
+        "GSE187115",
+        "GSE270493",
+        "GSE151628",
+        "GSE52852",
+        "GSE67429",
+        "GSE121331",
+        "GSE35560",
+        "GSE11030",
+        "GSE255059",
+        "GSE136046",
+        "GSE84428",
+        "GSE220680",
+        "GSE178804",
+        "GSE174571",
+        "GSE129547",
+        "GSE127268",
+        "GSE75353",
+        "GSE95004",
+        "GSE109136",
+        "GSE87781",
+        "GSE144442",
+        "GSE141108",
+        "GSE130082",
+        "GSE138596",
+        "GSE155773",
+        "GSE71958",
+        "GSE63896",
+        "GSE198494",
+        "GSE252046",
+        "GSE166458",
+        "GSE61825",
+        "GSE154332"
+    ],
+    "GARD:0025139": [
+        "GSE32268",
+        "GSE262896",
+        "GSE247955",
+        "GSE141435",
+        "GSE123281",
+        "GSE57431",
+        "GSE66148",
+        "GSE72391",
+        "GSE275956",
+        "GSE80149",
+        "GSE221853",
+        "GSE130500",
+        "GSE34918",
+        "GSE17043",
+        "GSE200196",
+        "GSE70245",
+        "GSE232763",
+        "GSE210521",
+        "GSE142101",
+        "GSE972",
+        "GSE195590",
+        "GSE182632",
+        "GSE188241",
+        "GSE165589",
+        "GSE147821",
+        "GSE63592",
+        "GSE153614",
+        "GSE137241",
+        "GSE196321",
+        "GSE75125",
+        "GSE150007",
+        "GSE135471",
+        "GSE181287",
+        "GSE152752",
+        "GSE161130",
+        "GSE145551",
+        "GSE129114",
+        "GSE30596",
+        "GSE166460",
+        "GSE281763",
+        "GSE128191",
+        "GSE44299",
+        "GSE139409",
+        "GSE11788",
+        "GSE42519",
+        "GSE164110",
+        "GSE34920",
+        "GSE246248",
+        "GSE197786",
+        "GSE246603",
+        "GSE180183",
+        "GSE111327",
+        "GSE220081",
+        "GSE228339",
+        "GSE230319",
+        "GSE173284",
+        "GSE30167",
+        "GSE203116",
+        "GSE121324",
+        "GSE45226",
+        "GSE229148",
+        "GSE53679",
+        "GSE105016",
+        "GSE205213",
+        "GSE215795",
+        "GSE89437",
+        "GSE44727",
+        "GSE202440",
+        "GSE267008",
+        "GSE161126",
+        "GSE242700",
+        "GSE202057",
+        "GSE199441",
+        "GSE202442",
+        "GSE77207",
+        "GSE65050",
+        "GSE232762",
+        "GSE205212",
+        "GSE192640",
+        "GSE102123",
+        "GSE45223",
+        "GSE138619",
+        "GSE66851",
+        "GSE8759",
+        "GSE78268",
+        "GSE270155",
+        "GSE256464",
+        "GSE228342",
+        "GSE250526",
+        "GSE94082",
+        "GSE216674",
+        "GSE150006",
+        "GSE81430",
+        "GSE195573",
+        "GSE202238",
+        "GSE202055",
+        "GSE165344",
+        "GSE185279",
+        "GSE61273",
+        "GSE85620",
+        "GSE272480",
+        "GSE39918",
+        "GSE107843",
+        "GSE151850",
+        "GSE275132",
+        "GSE281769",
+        "GSE137721",
+        "GSE181577",
+        "GSE19698",
+        "GSE63040",
+        "GSE9285",
+        "GSE12007",
+        "GSE15969",
+        "GSE125124",
+        "GSE62123",
+        "GSE63428",
+        "GSE201257",
+        "GSE115353",
+        "GSE89420",
+        "GSE137614",
+        "GSE18043",
+        "GSE23954",
+        "GSE212225",
+        "GSE252061",
+        "GSE230316",
+        "GSE96631",
+        "GSE237713",
+        "GSE145327",
+        "GSE107053",
+        "GSE264211",
+        "GSE180196",
+        "GSE74701",
+        "GSE82095",
+        "GSE202441",
+        "GSE32386",
+        "GSE243840",
+        "GSE236673",
+        "GSE151700",
+        "GSE230317",
+        "GSE214632",
+        "GSE14421",
+        "GSE175809",
+        "GSE147270",
+        "GSE140150",
+        "GSE130079",
+        "GSE166603",
+        "GSE22092",
+        "GSE56999",
+        "GSE184359",
+        "GSE184364",
+        "GSE175808",
+        "GSE103240",
+        "GSE99317",
+        "GSE68044",
+        "GSE241522",
+        "GSE180194",
+        "GSE68052",
+        "GSE42589",
+        "GSE136449",
+        "GSE228343",
+        "GSE137240",
+        "GSE80151",
+        "GSE144366",
+        "GSE24598",
+        "GSE57430",
+        "GSE68546",
+        "GSE261846",
+        "GSE253235",
+        "GSE101655",
+        "GSE34303",
+        "GSE180999",
+        "GSE197927",
+        "GSE89188",
+        "GSE230303",
+        "GSE181562",
+        "GSE202058",
+        "GSE95815",
+        "GSE59125",
+        "GSE205900",
+        "GSE219149",
+        "GSE121427",
+        "GSE11149",
+        "GSE161176",
+        "GSE104849",
+        "GSE81282",
+        "GSE64556",
+        "GSE180519",
+        "GSE126089",
+        "GSE62680",
+        "GSE250528",
+        "GSE65049",
+        "GSE263087",
+        "GSE50251",
+        "GSE241256",
+        "GSE246805",
+        "GSE149688",
+        "GSE109432",
+        "GSE76806",
+        "GSE104420",
+        "GSE221188",
+        "GSE168131",
+        "GSE80153",
+        "GSE221031",
+        "GSE138538",
+        "GSE143912",
+        "GSE218217",
+        "GSE108518",
+        "GSE87641",
+        "GSE61823",
+        "GSE23709",
+        "GSE21539",
+        "GSE183307",
+        "GSE260990",
+        "GSE217214",
+        "GSE42572",
+        "GSE51034",
+        "GSE215960",
+        "GSE152755",
+        "GSE52220",
+        "GSE202195",
+        "GSE192906",
+        "GSE216759",
+        "GSE26980",
+        "GSE52357",
+        "GSE161510",
+        "GSE221330",
+        "GSE263169",
+        "GSE87750",
+        "GSE27159",
+        "GSE68047",
+        "GSE274407",
+        "GSE210015",
+        "GSE51297",
+        "GSE21511",
+        "GSE184622",
+        "GSE108199",
+        "GSE70237",
+        "GSE163768",
+        "GSE189381",
+        "GSE228194",
+        "GSE19664",
+        "GSE232516",
+        "GSE204731",
+        "GSE199440",
+        "GSE213132",
+        "GSE246806",
+        "GSE127469",
+        "GSE163757",
+        "GSE125711",
+        "GSE117304",
+        "GSE219153",
+        "GSE232432",
+        "GSE265932",
+        "GSE113074",
+        "GSE8066",
+        "GSE212234",
+        "GSE47919",
+        "GSE104950",
+        "GSE76809",
+        "GSE114961",
+        "GSE61674",
+        "GSE178823",
+        "GSE263168",
+        "GSE182783",
+        "GSE277165",
+        "GSE83317",
+        "GSE89436",
+        "GSE68045",
+        "GSE103822",
+        "GSE34904",
+        "GSE95780",
+        "GSE168303",
+        "GSE25256",
+        "GSE216125",
+        "GSE67338",
+        "GSE177489",
+        "GSE57001",
+        "GSE32339",
+        "GSE223901",
+        "GSE89670",
+        "GSE175767",
+        "GSE111753",
+        "GSE205903",
+        "GSE174708",
+        "GSE67073",
+        "GSE63895",
+        "GSE35506",
+        "GSE66850",
+        "GSE119962",
+        "GSE75355",
+        "GSE230315",
+        "GSE115149",
+        "GSE261828",
+        "GSE100907",
+        "GSE7007",
+        "GSE143911",
+        "GSE107516",
+        "GSE205904",
+        "GSE93134",
+        "GSE77114",
+        "GSE149369",
+        "GSE272868",
+        "GSE180546",
+        "GSE192645",
+        "GSE241499",
+        "GSE143910",
+        "GSE80130",
+        "GSE94914",
+        "GSE2295",
+        "GSE80335",
+        "GSE244473",
+        "GSE134532",
+        "GSE39346",
+        "GSE64513",
+        "GSE172069",
+        "GSE232163",
+        "GSE141106",
+        "GSE242157",
+        "GSE208184",
+        "GSE152599",
+        "GSE109137",
+        "GSE194430",
+        "GSE84666",
+        "GSE44297",
+        "GSE112072",
+        "GSE13002",
+        "GSE149884",
+        "GSE35148",
+        "GSE263091",
+        "GSE148699",
+        "GSE198561",
+        "GSE230350",
+        "GSE41121",
+        "GSE57518",
+        "GSE222639",
+        "GSE108517",
+        "GSE77272",
+        "GSE45491",
+        "GSE17312",
+        "GSE250450",
+        "GSE53203",
+        "GSE202196",
+        "GSE211906",
+        "GSE216492",
+        "GSE175095",
+        "GSE234616",
+        "GSE92764",
+        "GSE91377",
+        "GSE142309",
+        "GSE139859",
+        "GSE72985",
+        "GSE143395",
+        "GSE243834",
+        "GSE223900",
+        "GSE225890",
+        "GSE169654",
+        "GSE283071",
+        "GSE80334",
+        "GSE185119",
+        "GSE211660",
+        "GSE184227",
+        "GSE121131",
+        "GSE143913",
+        "GSE239305",
+        "GSE150709",
+        "GSE57505",
+        "GSE126087",
+        "GSE206745",
+        "GSE9451",
+        "GSE83327",
+        "GSE241903",
+        "GSE178805",
+        "GSE278072",
+        "GSE237881",
+        "GSE217212",
+        "GSE282770",
+        "GSE224158",
+        "GSE142752",
+        "GSE69108",
+        "GSE205902",
+        "GSE46561",
+        "GSE250247",
+        "GSE122714",
+        "GSE67555",
+        "GSE206903",
+        "GSE201378",
+        "GSE133014",
+        "GSE210139",
+        "GSE190462",
+        "GSE223104",
+        "GSE195519",
+        "GSE109267",
+        "GSE92763",
+        "GSE29742",
+        "GSE120409",
+        "GSE46591",
+        "GSE102553",
+        "GSE47407",
+        "GSE46387",
+        "GSE162035",
+        "GSE140247",
+        "GSE14340",
+        "GSE226566",
+        "GSE113297",
+        "GSE127269",
+        "GSE62117",
+        "GSE246672",
+        "GSE161531",
+        "GSE232560",
+        "GSE195730",
+        "GSE177517",
+        "GSE80663",
+        "GSE216138",
+        "GSE182402",
+        "GSE67786",
+        "GSE217298",
+        "GSE11482",
+        "GSE18690",
+        "GSE180998",
+        "GSE105145",
+        "GSE85636",
+        "GSE66032",
+        "GSE144311",
+        "GSE50643",
+        "GSE80662",
+        "GSE45968",
+        "GSE178364",
+        "GSE73355",
+        "GSE80150",
+        "GSE201511",
+        "GSE60313",
+        "GSE214996",
+        "GSE139273",
+        "GSE234071",
+        "GSE162044",
+        "GSE41122",
+        "GSE198491",
+        "GSE183319",
+        "GSE114894",
+        "GSE21517",
+        "GSE228340",
+        "GSE89910",
+        "GSE94521",
+        "GSE211902",
+        "GSE28875",
+        "GSE172742",
+        "GSE62816",
+        "GSE27176",
+        "GSE275825",
+        "GSE141107",
+        "GSE123142",
+        "GSE252573",
+        "GSE276561",
+        "GSE165590",
+        "GSE81717",
+        "GSE10934",
+        "GSE181000",
+        "GSE103849",
+        "GSE168179",
+        "GSE56430",
+        "GSE37189",
+        "GSE211903",
+        "GSE174949",
+        "GSE239434",
+        "GSE237970",
+        "GSE120434",
+        "GSE262095",
+        "GSE111153",
+        "GSE64752",
+        "GSE198297",
+        "GSE215109",
+        "GSE145306",
+        "GSE253865",
+        "GSE54720",
+        "GSE164327",
+        "GSE249075",
+        "GSE11029",
+        "GSE135237",
+        "GSE104141",
+        "GSE121507",
+        "GSE200674",
+        "GSE179986",
+        "GSE108521",
+        "GSE255577",
+        "GSE99551",
+        "GSE131737",
+        "GSE52358",
+        "GSE178969",
+        "GSE230176",
+        "GSE70751",
+        "GSE33767",
+        "GSE196592",
+        "GSE222213",
+        "GSE73180",
+        "GSE266652",
+        "GSE149860",
+        "GSE178434",
+        "GSE223132",
+        "GSE162889",
+        "GSE116173",
+        "GSE29634",
+        "GSE186696",
+        "GSE206048",
+        "GSE168200",
+        "GSE22989",
+        "GSE199439",
+        "GSE223750",
+        "GSE169529",
+        "GSE116140",
+        "GSE62247",
+        "GSE236680",
+        "GSE162973",
+        "GSE4680",
+        "GSE45893",
+        "GSE6460",
+        "GSE286314",
+        "GSE6868",
+        "GSE140319",
+        "GSE53678",
+        "GSE206008",
+        "GSE153121",
+        "GSE2841",
+        "GSE165303",
+        "GSE187102",
+        "GSE89435",
+        "GSE137219",
+        "GSE229532",
+        "GSE120678",
+        "GSE119537",
+        "GSE121526",
+        "GSE80393",
+        "GSE242826",
+        "GSE81026",
+        "GSE72268",
+        "GSE41123",
+        "GSE75356",
+        "GSE77363",
+        "GSE68898",
+        "GSE125141",
+        "GSE84430",
+        "GSE80689",
+        "GSE246769",
+        "GSE213382",
+        "GSE268988",
+        "GSE34502",
+        "GSE151649",
+        "GSE109686",
+        "GSE202059",
+        "GSE263778",
+        "GSE41179",
+        "GSE183309",
+        "GSE18477",
+        "GSE23530",
+        "GSE80165",
+        "GSE217197",
+        "GSE125143",
+        "GSE61510",
+        "GSE137462",
+        "GSE211899",
+        "GSE169322",
+        "GSE211901",
+        "GSE165588",
+        "GSE202671",
+        "GSE9339",
+        "GSE188163",
+        "GSE137975",
+        "GSE195589",
+        "GSE117754",
+        "GSE223614",
+        "GSE263086",
+        "GSE42548",
+        "GSE245175",
+        "GSE169280",
+        "GSE178834",
+        "GSE176731",
+        "GSE110872",
+        "GSE100538",
+        "GSE57810",
+        "GSE24730",
+        "GSE166625",
+        "GSE121329",
+        "GSE53677",
+        "GSE9894",
+        "GSE42254",
+        "GSE262042",
+        "GSE250527",
+        "GSE199158",
+        "GSE132857",
+        "GSE133141",
+        "GSE176055",
+        "GSE104163",
+        "GSE60394",
+        "GSE1588",
+        "GSE121429",
+        "GSE30716",
+        "GSE212793",
+        "GSE197631",
+        "GSE235864",
+        "GSE14391",
+        "GSE72815",
+        "GSE11979",
+        "GSE179984",
+        "GSE250387",
+        "GSE131136",
+        "GSE124312",
+        "GSE206197",
+        "GSE230318",
+        "GSE119534",
+        "GSE252428",
+        "GSE104473",
+        "GSE210251",
+        "GSE108943",
+        "GSE149072",
+        "GSE111766",
+        "GSE185255",
+        "GSE157575",
+        "GSE80152",
+        "GSE54719",
+        "GSE58474",
+        "GSE38381",
+        "GSE78002",
+        "GSE69311",
+        "GSE141664",
+        "GSE45159",
+        "GSE68776",
+        "GSE223615",
+        "GSE67087",
+        "GSE246807",
+        "GSE211904",
+        "GSE100905",
+        "GSE69110",
+        "GSE28874",
+        "GSE117305",
+        "GSE188990",
+        "GSE250009",
+        "GSE124579",
+        "GSE99382",
+        "GSE127245",
+        "GSE114464",
+        "GSE119498",
+        "GSE50059",
+        "GSE205901",
+        "GSE156031",
+        "GSE115348",
+        "GSE189544",
+        "GSE131293",
+        "GSE78003",
+        "GSE141439",
+        "GSE163961",
+        "GSE205214",
+        "GSE156146",
+        "GSE80509",
+        "GSE186707",
+        "GSE90683",
+        "GSE180187",
+        "GSE163826",
+        "GSE176965",
+        "GSE96629",
+        "GSE58916",
+        "GSE77513",
+        "GSE216136",
+        "GSE211478",
+        "GSE131793",
+        "GSE85621",
+        "GSE16249",
+        "GSE163771",
+        "GSE95814",
+        "GSE80288",
+        "GSE261227",
+        "GSE67124",
+        "GSE178784",
+        "GSE161281",
+        "GSE146809",
+        "GSE89434",
+        "GSE19465",
+        "GSE261603",
+        "GSE216760",
+        "GSE163907",
+        "GSE17448",
+        "GSE175114",
+        "GSE284063",
+        "GSE35218",
+        "GSE238166",
+        "GSE182721",
+        "GSE161579",
+        "GSE261358",
+        "GSE168133",
+        "GSE69109",
+        "GSE221190",
+        "GSE79928",
+        "GSE226565",
+        "GSE20399",
+        "GSE126880",
+        "GSE173696",
+        "GSE192676",
+        "GSE34208",
+        "GSE5658",
+        "GSE125140",
+        "GSE99636",
+        "GSE278071",
+        "GSE236674",
+        "GSE206128",
+        "GSE193097",
+        "GSE198492",
+        "GSE10360",
+        "GSE240190",
+        "GSE46791",
+        "GSE131155",
+        "GSE193815",
+        "GSE212226",
+        "GSE108506",
+        "GSE113736",
+        "GSE95812",
+        "GSE8368",
+        "GSE205436",
+        "GSE127795",
+        "GSE213728",
+        "GSE106219",
+        "GSE228341",
+        "GSE133009",
+        "GSE135851",
+        "GSE102542",
+        "GSE108515",
+        "GSE175647",
+        "GSE1822",
+        "GSE154483",
+        "GSE106676",
+        "GSE120936",
+        "GSE183305",
+        "GSE46150",
+        "GSE39540",
+        "GSE202056",
+        "GSE55964",
+        "GSE134768",
+        "GSE129801",
+        "GSE117844",
+        "GSE208250",
+        "GSE150582",
+        "GSE108230",
+        "GSE184363",
+        "GSE202198",
+        "GSE183308",
+        "GSE127260",
+        "GSE38066",
+        "GSE202197",
+        "GSE140193",
+        "GSE126088",
+        "GSE30419",
+        "GSE157356",
+        "GSE161120",
+        "GSE108918",
+        "GSE80107",
+        "GSE44257",
+        "GSE61206",
+        "GSE215977",
+        "GSE169516",
+        "GSE181561",
+        "GSE172029",
+        "GSE160312",
+        "GSE219151",
+        "GSE57064",
+        "GSE262468",
+        "GSE250370",
+        "GSE19987",
+        "GSE92333",
+        "GSE44537",
+        "GSE222566",
+        "GSE120200",
+        "GSE68636",
+        "GSE220475",
+        "GSE198493",
+        "GSE115140",
+        "GSE121318",
+        "GSE99933",
+        "GSE46792",
+        "GSE252615",
+        "GSE205446",
+        "GSE50487",
+        "GSE255684",
+        "GSE137227",
+        "GSE100998",
+        "GSE185394",
+        "GSE261486",
+        "GSE185669",
+        "GSE136057",
+        "GSE254500",
+        "GSE235280",
+        "GSE11028",
+        "GSE55173",
+        "GSE205448",
+        "GSE103402",
+        "GSE100793",
+        "GSE92765",
+        "GSE120920",
+        "GSE36474",
+        "GSE193007",
+        "GSE39191",
+        "GSE164108",
+        "GSE57003",
+        "GSE282901",
+        "GSE57125",
+        "GSE243072",
+        "GSE176101",
+        "GSE68040",
+        "GSE278511",
+        "GSE255060",
+        "GSE229531",
+        "GSE214099",
+        "GSE140636",
+        "GSE75352",
+        "GSE44295",
+        "GSE279710",
+        "GSE125145",
+        "GSE196544",
+        "GSE246685",
+        "GSE14038",
+        "GSE221125",
+        "GSE61695",
+        "GSE176634",
+        "GSE190305",
+        "GSE125480",
+        "GSE79988",
+        "GSE12274",
+        "GSE13129",
+        "GSE196386",
+        "GSE222212",
+        "GSE225530",
+        "GSE32308",
+        "GSE78890",
+        "GSE154972",
+        "GSE178687",
+        "GSE11027",
+        "GSE217199",
+        "GSE217757",
+        "GSE121044",
+        "GSE28199",
+        "GSE28876",
+        "GSE34912",
+        "GSE63058",
+        "GSE200689",
+        "GSE166262",
+        "GSE103748",
+        "GSE52456",
+        "GSE108221",
+        "GSE174572",
+        "GSE168399",
+        "GSE125707",
+        "GSE182329",
+        "GSE101661",
+        "GSE80252",
+        "GSE198562",
+        "GSE135832",
+        "GSE183306",
+        "GSE61755",
+        "GSE207592",
+        "GSE58476",
+        "GSE68039",
+        "GSE42678",
+        "GSE72322",
+        "GSE274096",
+        "GSE223616",
+        "GSE161565",
+        "GSE275013",
+        "GSE213390",
+        "GSE85598",
+        "GSE226568",
+        "GSE56957",
+        "GSE185592",
+        "GSE83400",
+        "GSE68101",
+        "GSE55967",
+        "GSE216920",
+        "GSE125142",
+        "GSE75748",
+        "GSE228335",
+        "GSE90711",
+        "GSE10454",
+        "GSE262111",
+        "GSE52227",
+        "GSE118682",
+        "GSE186770",
+        "GSE107968",
+        "GSE222042",
+        "GSE170335",
+        "GSE263085",
+        "GSE175811",
+        "GSE155691",
+        "GSE101909",
+        "GSE77364",
+        "GSE31205",
+        "GSE198231",
+        "GSE172066",
+        "GSE64000",
+        "GSE95813",
+        "GSE211664",
+        "GSE243814",
+        "GSE165826",
+        "GSE116110",
+        "GSE208369",
+        "GSE223103",
+        "GSE11356",
+        "GSE161143",
+        "GSE102552",
+        "GSE252592",
+        "GSE139168",
+        "GSE126457",
+        "GSE106325",
+        "GSE44296",
+        "GSE258835",
+        "GSE75351",
+        "GSE242228",
+        "GSE173251",
+        "GSE162238",
+        "GSE131688",
+        "GSE261748",
+        "GSE211900",
+        "GSE142337",
+        "GSE190002",
+        "GSE125710",
+        "GSE136448",
+        "GSE76807",
+        "GSE263084",
+        "GSE218625",
+        "GSE70353",
+        "GSE97851",
+        "GSE75354",
+        "GSE146481",
+        "GSE261360",
+        "GSE163960",
+        "GSE25501",
+        "GSE130526",
+        "GSE123686",
+        "GSE172059",
+        "GSE145048",
+        "GSE121428",
+        "GSE235534",
+        "GSE138905",
+        "GSE183002",
+        "GSE86212",
+        "GSE152906",
+        "GSE125709",
+        "GSE155690",
+        "GSE101746",
+        "GSE255790",
+        "GSE121527",
+        "GSE166246",
+        "GSE197513",
+        "GSE224197",
+        "GSE174446",
+        "GSE149855",
+        "GSE172028",
+        "GSE187115",
+        "GSE270493",
+        "GSE151628",
+        "GSE52852",
+        "GSE67429",
+        "GSE121331",
+        "GSE35560",
+        "GSE11030",
+        "GSE255059",
+        "GSE136046",
+        "GSE84428",
+        "GSE220680",
+        "GSE178804",
+        "GSE174571",
+        "GSE129547",
+        "GSE127268",
+        "GSE75353",
+        "GSE95004",
+        "GSE109136",
+        "GSE87781",
+        "GSE144442",
+        "GSE141108",
+        "GSE130082",
+        "GSE138596",
+        "GSE155773",
+        "GSE71958",
+        "GSE63896",
+        "GSE198494",
+        "GSE252046",
+        "GSE166458",
+        "GSE61825",
+        "GSE154332"
+    ],
+    "GARD:0007827": [
+        "GSE266564",
+        "GSE189996",
+        "GSE139825",
+        "GSE164590",
+        "GSE34922",
+        "GSE118482",
+        "GSE196816",
+        "GSE190850",
+        "GSE225820",
+        "GSE8829",
+        "GSE210691",
+        "GSE148171",
+        "GSE183469",
+        "GSE180658",
+        "GSE73654",
+        "GSE121705",
+        "GSE72328",
+        "GSE148862",
+        "GSE103147",
+        "GSE45675",
+        "GSE55979",
+        "GSE52819",
+        "GSE52020",
+        "GSE7588",
+        "GSE166114",
+        "GSE34919",
+        "GSE267006",
+        "GSE157657",
+        "GSE99374",
+        "GSE162620",
+        "GSE17587",
+        "GSE64167",
+        "GSE44825",
+        "GSE141362",
+        "GSE107104",
+        "GSE235800",
+        "GSE248244",
+        "GSE196833",
+        "GSE108188",
+        "GSE137793",
+        "GSE269733",
+        "GSE239869",
+        "GSE164460",
+        "GSE238102",
+        "GSE64335",
+        "GSE45386",
+        "GSE19491",
+        "GSE34622",
+        "GSE12381",
+        "GSE12302",
+        "GSE66933",
+        "GSE273016",
+        "GSE148861",
+        "GSE128626",
+        "GSE183165",
+        "GSE180792",
+        "GSE168467",
+        "GSE77711",
+        "GSE37191",
+        "GSE222001",
+        "GSE151636",
+        "GSE25435",
+        "GSE171759",
+        "GSE264592",
+        "GSE119585",
+        "GSE116859",
+        "GSE114949",
+        "GSE108844",
+        "GSE92495",
+        "GSE145770",
+        "GSE222013",
+        "GSE216654",
+        "GSE39163",
+        "GSE203032",
+        "GSE218660",
+        "GSE229680",
+        "GSE57948",
+        "GSE271119",
+        "GSE74323",
+        "GSE48237",
+        "GSE56153",
+        "GSE216503",
+        "GSE135592",
+        "GSE39219",
+        "GSE196192",
+        "GSE167232",
+        "GSE166546",
+        "GSE118508",
+        "GSE14826",
+        "GSE32718",
+        "GSE126837",
+        "GSE215456",
+        "GSE158807",
+        "GSE44848",
+        "GSE166271",
+        "GSE64177",
+        "GSE52551",
+        "GSE47672",
+        "GSE36344",
+        "GSE237259",
+        "GSE9776",
+        "GSE16146",
+        "GSE115892",
+        "GSE210088",
+        "GSE102664",
+        "GSE131174",
+        "GSE84344",
+        "GSE143996",
+        "GSE30950",
+        "GSE271061",
+        "GSE102677",
+        "GSE35231",
+        "GSE184172",
+        "GSE48164",
+        "GSE2561",
+        "GSE149645",
+        "GSE9331",
+        "GSE205290",
+        "GSE119225",
+        "GSE50050",
+        "GSE205600",
+        "GSE6112",
+        "GSE241072",
+        "GSE212203",
+        "GSE165673",
+        "GSE94438",
+        "GSE252417",
+        "GSE23498",
+        "GSE10391",
+        "GSE116411",
+        "GSE151050",
+        "GSE132790",
+        "GSE146227",
+        "GSE227436",
+        "GSE116830",
+        "GSE89391",
+        "GSE98750",
+        "GSE67589",
+        "GSE59774",
+        "GSE57028",
+        "GSE27984",
+        "GSE147689",
+        "GSE42825",
+        "GSE132461",
+        "GSE72435",
+        "GSE144330",
+        "GSE160357",
+        "GSE203261",
+        "GSE102816",
+        "GSE19838",
+        "GSE262613",
+        "GSE162760",
+        "GSE48132",
+        "GSE211992",
+        "GSE134186",
+        "GSE115495",
+        "GSE162725",
+        "GSE121398",
+        "GSE5815",
+        "GSE90839",
+        "GSE19444",
+        "GSE23429",
+        "GSE17424",
+        "GSE176423",
+        "GSE93316",
+        "GSE54444",
+        "GSE110355",
+        "GSE192537",
+        "GSE106611",
+        "GSE248986",
+        "GSE74282",
+        "GSE243659",
+        "GSE182239",
+        "GSE112483",
+        "GSE31734",
+        "GSE11095",
+        "GSE11519",
+        "GSE216603",
+        "GSE128627",
+        "GSE166557",
+        "GSE138398",
+        "GSE85905",
+        "GSE140113",
+        "GSE16250",
+        "GSE116861",
+        "GSE235293",
+        "GSE287288",
+        "GSE63548",
+        "GSE3837",
+        "GSE144317",
+        "GSE64133",
+        "GSE64134",
+        "GSE9946",
+        "GSE37840",
+        "GSE166501",
+        "GSE150030",
+        "GSE100097",
+        "GSE14840",
+        "GSE121793",
+        "GSE245836",
+        "GSE143627",
+        "GSE264715",
+        "GSE197408",
+        "GSE122377",
+        "GSE269919",
+        "GSE179552",
+        "GSE70478",
+        "GSE119571",
+        "GSE33309",
+        "GSE228998",
+        "GSE64142",
+        "GSE89830",
+        "GSE134574",
+        "GSE31769",
+        "GSE237582",
+        "GSE161712",
+        "GSE193950",
+        "GSE181143",
+        "GSE280580",
+        "GSE103276",
+        "GSE121049",
+        "GSE199649",
+        "GSE98821",
+        "GSE193395",
+        "GSE218065",
+        "GSE64173",
+        "GSE141207",
+        "GSE255435",
+        "GSE216023",
+        "GSE129830",
+        "GSE65036",
+        "GSE163531",
+        "GSE172041",
+        "GSE23014",
+        "GSE19148",
+        "GSE263891",
+        "GSE210689",
+        "GSE95773",
+        "GSE50159",
+        "GSE108363",
+        "GSE49188",
+        "GSE21113",
+        "GSE99456",
+        "GSE77885",
+        "GSE218270",
+        "GSE156136",
+        "GSE6083",
+        "GSE271206",
+        "GSE222063",
+        "GSE153326",
+        "GSE143764",
+        "GSE98182",
+        "GSE89089",
+        "GSE276053",
+        "GSE235263",
+        "GSE229446",
+        "GSE222247",
+        "GSE57572",
+        "GSE150657",
+        "GSE39941",
+        "GSE79362",
+        "GSE32645",
+        "GSE32076",
+        "GSE200639",
+        "GSE192504",
+        "GSE176139",
+        "GSE253828",
+        "GSE211666",
+        "GSE213340",
+        "GSE43337",
+        "GSE24035",
+        "GSE132300",
+        "GSE62942",
+        "GSE237039",
+        "GSE166805",
+        "GSE67670",
+        "GSE51029",
+        "GSE168247",
+        "GSE107917",
+        "GSE266562",
+        "GSE193777",
+        "GSE78233",
+        "GSE118021",
+        "GSE99712",
+        "GSE140943",
+        "GSE249605",
+        "GSE85037",
+        "GSE70812",
+        "GSE41582",
+        "GSE218892",
+        "GSE248728",
+        "GSE211191",
+        "GSE152218",
+        "GSE158465",
+        "GSE256252",
+        "GSE102678",
+        "GSE118084",
+        "GSE41088",
+        "GSE32157",
+        "GSE94007",
+        "GSE268196",
+        "GSE197222",
+        "GSE169202",
+        "GSE15335",
+        "GSE243269",
+        "GSE165705",
+        "GSE3408",
+        "GSE118350",
+        "GSE102574",
+        "GSE96639",
+        "GSE33058",
+        "GSE29166",
+        "GSE76703",
+        "GSE163902",
+        "GSE260585",
+        "GSE150171",
+        "GSE230738",
+        "GSE151633",
+        "GSE180161",
+        "GSE129035",
+        "GSE11518",
+        "GSE271126",
+        "GSE46268",
+        "GSE117435",
+        "GSE67445",
+        "GSE185372",
+        "GSE119105",
+        "GSE266563",
+        "GSE64183",
+        "GSE273911",
+        "GSE179417",
+        "GSE132932",
+        "GSE112104",
+        "GSE112482",
+        "GSE64045",
+        "GSE234093",
+        "GSE182215",
+        "GSE213342",
+        "GSE190523",
+        "GSE131590",
+        "GSE89403",
+        "GSE243661",
+        "GSE199263",
+        "GSE189123",
+        "GSE231628",
+        "GSE149443",
+        "GSE246736",
+        "GSE137093",
+        "GSE116405",
+        "GSE165709",
+        "GSE99098",
+        "GSE86141",
+        "GSE64135",
+        "GSE29536",
+        "GSE365",
+        "GSE76873",
+        "GSE15976",
+        "GSE113051",
+        "GSE19433",
+        "GSE243750",
+        "GSE30264",
+        "GSE106135",
+        "GSE118018",
+        "GSE8827",
+        "GSE60376",
+        "GSE89106",
+        "GSE222412",
+        "GSE207580",
+        "GSE119107",
+        "GSE242343",
+        "GSE168513",
+        "GSE111194",
+        "GSE23074",
+        "GSE68350",
+        "GSE110508",
+        "GSE199000",
+        "GSE131031",
+        "GSE119494",
+        "GSE92740",
+        "GSE70765",
+        "GSE57275",
+        "GSE19237",
+        "GSE16618",
+        "GSE11199",
+        "GSE188945",
+        "GSE165871",
+        "GSE47863",
+        "GSE57736",
+        "GSE121292",
+        "GSE101963",
+        "GSE168473",
+        "GSE148731",
+        "GSE180561",
+        "GSE88801",
+        "GSE137518",
+        "GSE119158",
+        "GSE66408",
+        "GSE139871",
+        "GSE244230",
+        "GSE67843",
+        "GSE229020",
+        "GSE117330",
+        "GSE189942",
+        "GSE268977",
+        "GSE198557",
+        "GSE29628",
+        "GSE188322",
+        "GSE107521",
+        "GSE245950",
+        "GSE183787",
+        "GSE263497",
+        "GSE139507",
+        "GSE193527",
+        "GSE156135",
+        "GSE125287",
+        "GSE247649",
+        "GSE240200",
+        "GSE230753",
+        "GSE108067",
+        "GSE14005",
+        "GSE201201",
+        "GSE267774",
+        "GSE211981",
+        "GSE124341",
+        "GSE7871",
+        "GSE21114",
+        "GSE160039",
+        "GSE124120",
+        "GSE151991",
+        "GSE51707",
+        "GSE50210",
+        "GSE50160",
+        "GSE206485",
+        "GSE67427",
+        "GSE112998",
+        "GSE270105",
+        "GSE228114",
+        "GSE3999",
+        "GSE30722",
+        "GSE139646",
+        "GSE54442",
+        "GSE162729",
+        "GSE181156",
+        "GSE174552",
+        "GSE21590",
+        "GSE140156",
+        "GSE211977",
+        "GSE239870",
+        "GSE141656",
+        "GSE42832",
+        "GSE113683",
+        "GSE97958",
+        "GSE8786",
+        "GSE97559",
+        "GSE156137",
+        "GSE255475",
+        "GSE141205",
+        "GSE69379",
+        "GSE18794",
+        "GSE11315",
+        "GSE175579",
+        "GSE104599",
+        "GSE179403",
+        "GSE13780",
+        "GSE30273",
+        "GSE205292",
+        "GSE237792",
+        "GSE124415",
+        "GSE189297",
+        "GSE158208",
+        "GSE86494",
+        "GSE118196",
+        "GSE199069",
+        "GSE64181",
+        "GSE75847",
+        "GSE153340",
+        "GSE122837",
+        "GSE271124",
+        "GSE111192",
+        "GSE22098",
+        "GSE154627",
+        "GSE69680",
+        "GSE220147",
+        "GSE83397",
+        "GSE15164",
+        "GSE203037",
+        "GSE276937",
+        "GSE45439",
+        "GSE62506",
+        "GSE175661",
+        "GSE179816",
+        "GSE98599",
+        "GSE168486",
+        "GSE235564",
+        "GSE98458",
+        "GSE221413",
+        "GSE29190",
+        "GSE106462",
+        "GSE78894",
+        "GSE260838",
+        "GSE111193",
+        "GSE66883",
+        "GSE50835",
+        "GSE246347",
+        "GSE74050",
+        "GSE165708",
+        "GSE214729",
+        "GSE47163",
+        "GSE138580",
+        "GSE13670",
+        "GSE41401",
+        "GSE21932",
+        "GSE23590",
+        "GSE137421",
+        "GSE22854",
+        "GSE173378",
+        "GSE212202",
+        "GSE56179",
+        "GSE55863",
+        "GSE281697",
+        "GSE222081",
+        "GSE180348",
+        "GSE268366",
+        "GSE122083",
+        "GSE115292",
+        "GSE148829",
+        "GSE84152",
+        "GSE72745",
+        "GSE100596",
+        "GSE15608",
+        "GSE7870",
+        "GSE201641",
+        "GSE158767",
+        "GSE198998",
+        "GSE143619",
+        "GSE226474",
+        "GSE90858",
+        "GSE122427",
+        "GSE150815",
+        "GSE113050",
+        "GSE63917",
+        "GSE67035",
+        "GSE19774",
+        "GSE20050",
+        "GSE118288",
+        "GSE11549",
+        "GSE192483",
+        "GSE57263",
+        "GSE146228",
+        "GSE11096",
+        "GSE66578",
+        "GSE129270",
+        "GSE227653",
+        "GSE196357",
+        "GSE53254",
+        "GSE15328",
+        "GSE246201",
+        "GSE152295",
+        "GSE33094",
+        "GSE8664",
+        "GSE197113",
+        "GSE165581",
+        "GSE122619",
+        "GSE271425",
+        "GSE20716",
+        "GSE25534",
+        "GSE21963",
+        "GSE89389",
+        "GSE166159",
+        "GSE16626",
+        "GSE218354",
+        "GSE35484",
+        "GSE188586",
+        "GSE126718",
+        "GSE17640",
+        "GSE134564",
+        "GSE58411",
+        "GSE166806",
+        "GSE107485",
+        "GSE51085",
+        "GSE284505",
+        "GSE18652",
+        "GSE54289",
+        "GSE76566",
+        "GSE140944",
+        "GSE100105",
+        "GSE64852",
+        "GSE40917",
+        "GSE102440",
+        "GSE269547",
+        "GSE184241",
+        "GSE33752",
+        "GSE74196",
+        "GSE161829",
+        "GSE26305",
+        "GSE184292",
+        "GSE14316",
+        "GSE135952",
+        "GSE42826",
+        "GSE178188",
+        "GSE100897",
+        "GSE108393",
+        "GSE32237",
+        "GSE141848",
+        "GSE118867",
+        "GSE24045",
+        "GSE236053",
+        "GSE212586",
+        "GSE15539",
+        "GSE103188",
+        "GSE40846",
+        "GSE165232",
+        "GSE107992",
+        "GSE20917",
+        "GSE221544",
+        "GSE118866",
+        "GSE165703",
+        "GSE213943",
+        "GSE71066",
+        "GSE95181",
+        "GSE34588",
+        "GSE3201",
+        "GSE139511",
+        "GSE6889",
+        "GSE116769",
+        "GSE110276",
+        "GSE114192",
+        "GSE123267",
+        "GSE83812",
+        "GSE224055",
+        "GSE159982",
+        "GSE83379",
+        "GSE32249",
+        "GSE179376",
+        "GSE224043",
+        "GSE210690",
+        "GSE154320",
+        "GSE83456",
+        "GSE141679",
+        "GSE79732",
+        "GSE10336",
+        "GSE263029",
+        "GSE119573",
+        "GSE126286",
+        "GSE59184",
+        "GSE119106",
+        "GSE98598",
+        "GSE40845",
+        "GSE168659",
+        "GSE148036",
+        "GSE56561",
+        "GSE68805",
+        "GSE107791",
+        "GSE219072",
+        "GSE37973",
+        "GSE83271",
+        "GSE23508",
+        "GSE23713",
+        "GSE17835",
+        "GSE39939",
+        "GSE89529",
+        "GSE166137",
+        "GSE235754",
+        "GSE281239",
+        "GSE165671",
+        "GSE107995",
+        "GSE232827",
+        "GSE84554",
+        "GSE34624",
+        "GSE65517",
+        "GSE154169",
+        "GSE216652",
+        "GSE117563",
+        "GSE128412",
+        "GSE100280",
+        "GSE116353",
+        "GSE62025",
+        "GSE203662",
+        "GSE24968",
+        "GSE146127",
+        "GSE25508",
+        "GSE131043",
+        "GSE180517",
+        "GSE174566",
+        "GSE39940",
+        "GSE76499",
+        "GSE47486",
+        "GSE18575",
+        "GSE79731",
+        "GSE100440",
+        "GSE129285",
+        "GSE42606",
+        "GSE59063",
+        "GSE56736",
+        "GSE37823",
+        "GSE110325",
+        "GSE131990",
+        "GSE17191",
+        "GSE104211",
+        "GSE243658",
+        "GSE213850",
+        "GSE245205",
+        "GSE107790",
+        "GSE134565",
+        "GSE159048",
+        "GSE113054",
+        "GSE68856",
+        "GSE30721",
+        "GSE19442",
+        "GSE4231",
+        "GSE72330",
+        "GSE40862",
+        "GSE200151",
+        "GSE249824",
+        "GSE147690",
+        "GSE98792",
+        "GSE78706",
+        "GSE64427",
+        "GSE17706",
+        "GSE273018",
+        "GSE211974",
+        "GSE171540",
+        "GSE287753",
+        "GSE107994",
+        "GSE57124",
+        "GSE7963",
+        "GSE114911",
+        "GSE35362",
+        "GSE19443",
+        "GSE360",
+        "GSE169541",
+        "GSE263880",
+        "GSE57868",
+        "GSE8732",
+        "GSE165514",
+        "GSE162164",
+        "GSE54241",
+        "GSE106953",
+        "GSE269918",
+        "GSE165913",
+        "GSE194262",
+        "GSE261175",
+        "GSE32619",
+        "GSE117428",
+        "GSE43645",
+        "GSE70718",
+        "GSE251760",
+        "GSE36341",
+        "GSE114045",
+        "GSE15642",
+        "GSE79733",
+        "GSE223999",
+        "GSE46281",
+        "GSE179437",
+        "GSE83188",
+        "GSE218775",
+        "GSE116014",
+        "GSE42831",
+        "GSE41055",
+        "GSE107991",
+        "GSE83677",
+        "GSE58883",
+        "GSE262379",
+        "GSE119753",
+        "GSE43700",
+        "GSE190909",
+        "GSE244194",
+        "GSE136322",
+        "GSE6750",
+        "GSE186318",
+        "GSE178919",
+        "GSE46432",
+        "GSE36686",
+        "GSE269009",
+        "GSE13246",
+        "GSE12297",
+        "GSE34608",
+        "GSE100915",
+        "GSE58230",
+        "GSE8921",
+        "GSE280578",
+        "GSE235799",
+        "GSE236156",
+        "GSE70200",
+        "GSE49186",
+        "GSE243657",
+        "GSE54630",
+        "GSE8639",
+        "GSE139598",
+        "GSE201410",
+        "GSE198997",
+        "GSE213343",
+        "GSE52338",
+        "GSE167650",
+        "GSE83554",
+        "GSE48130",
+        "GSE118091",
+        "GSE62147",
+        "GSE260461",
+        "GSE211113",
+        "GSE133803",
+        "GSE101805",
+        "GSE8857",
+        "GSE270571",
+        "GSE25505",
+        "GSE64548",
+        "GSE27992",
+        "GSE190522",
+        "GSE31368",
+        "GSE18073",
+        "GSE7962",
+        "GSE61531",
+        "GSE53640",
+        "GSE7539",
+        "GSE12382",
+        "GSE224027",
+        "GSE147345",
+        "GSE101048",
+        "GSE19439",
+        "GSE166850",
+        "GSE255071",
+        "GSE110564",
+        "GSE17234",
+        "GSE5977",
+        "GSE198999",
+        "GSE35080",
+        "GSE8830",
+        "GSE134550",
+        "GSE243031",
+        "GSE232922",
+        "GSE214237",
+        "GSE233364",
+        "GSE133249",
+        "GSE116399",
+        "GSE114371",
+        "GSE64175",
+        "GSE270136",
+        "GSE249575",
+        "GSE236027",
+        "GSE164287",
+        "GSE132354",
+        "GSE167439",
+        "GSE151884",
+        "GSE3552",
+        "GSE81746",
+        "GSE137857",
+        "GSE180505",
+        "GSE236853",
+        "GSE225792",
+        "GSE106461",
+        "GSE139035",
+        "GSE48027",
+        "GSE64065",
+        "GSE74687",
+        "GSE159983",
+        "GSE145647",
+        "GSE161190",
+        "GSE17232",
+        "GSE255724",
+        "GSE36345",
+        "GSE193092",
+        "GSE149758",
+        "GSE145714",
+        "GSE93091",
+        "GSE158769",
+        "GSE37250",
+        "GSE13998",
+        "GSE156196",
+        "GSE211633",
+        "GSE29731",
+        "GSE21111",
+        "GSE255074",
+        "GSE47640",
+        "GSE156422",
+        "GSE263882",
+        "GSE182669",
+        "GSE214266",
+        "GSE213034",
+        "GSE136098",
+        "GSE242285",
+        "GSE98589",
+        "GSE81926",
+        "GSE77848",
+        "GSE35149",
+        "GSE68337",
+        "GSE102459",
+        "GSE31314",
+        "GSE199730",
+        "GSE211141",
+        "GSE84445",
+        "GSE59086",
+        "GSE193978",
+        "GSE40941",
+        "GSE185900",
+        "GSE34151",
+        "GSE42830",
+        "GSE107646",
+        "GSE23731",
+        "GSE224470",
+        "GSE12364",
+        "GSE269917",
+        "GSE124688",
+        "GSE189627",
+        "GSE190875",
+        "GSE83814",
+        "GSE147964",
+        "GSE84076",
+        "GSE58466",
+        "GSE212205",
+        "GSE37392",
+        "GSE32447",
+        "GSE62152",
+        "GSE19052",
+        "GSE33359",
+        "GSE235563",
+        "GSE172150",
+        "GSE118097",
+        "GSE263892",
+        "GSE99373",
+        "GSE36343",
+        "GSE98456",
+        "GSE53143",
+        "GSE42827",
+        "GSE196961",
+        "GSE218873",
+        "GSE249096",
+        "GSE122058",
+        "GSE255565",
+        "GSE142069",
+        "GSE271079",
+        "GSE273015",
+        "GSE120725",
+        "GSE141192",
+        "GSE159046",
+        "GSE175812",
+        "GSE55647",
+        "GSE16811",
+        "GSE83892",
+        "GSE228259",
+        "GSE64182",
+        "GSE273691",
+        "GSE210687",
+        "GSE107831",
+        "GSE8689",
+        "GSE195959",
+        "GSE248720",
+        "GSE226503",
+        "GSE70291",
+        "GSE54239",
+        "GSE45811",
+        "GSE103092",
+        "GSE148900",
+        "GSE171961",
+        "GSE142756",
+        "GSE69581",
+        "GSE152532",
+        "GSE163901",
+        "GSE122485",
+        "GSE19435",
+        "GSE10198",
+        "GSE62423",
+        "GSE98457",
+        "GSE236963",
+        "GSE228113",
+        "GSE6209",
+        "GSE54992",
+        "GSE265840",
+        "GSE15977",
+        "GSE174443",
+        "GSE104263",
+        "GSE261737",
+        "GSE176255",
+        "GSE166622",
+        "GSE173225",
+        "GSE98461",
+        "GSE140945",
+        "GSE99625",
+        "GSE225679",
+        "GSE243663",
+        "GSE154673",
+        "GSE166804",
+        "GSE42293",
+        "GSE224469",
+        "GSE146881",
+        "GSE182749",
+        "GSE107731",
+        "GSE137092",
+        "GSE129833",
+        "GSE147691",
+        "GSE207244",
+        "GSE68206",
+        "GSE183440",
+        "GSE55183",
+        "GSE178190",
+        "GSE227058",
+        "GSE132931",
+        "GSE115322",
+        "GSE271125",
+        "GSE54421",
+        "GSE40719",
+        "GSE31348",
+        "GSE243818",
+        "GSE163292",
+        "GSE98550",
+        "GSE18909",
+        "GSE211976",
+        "GSE100288",
+        "GSE151718",
+        "GSE196844",
+        "GSE120139",
+        "GSE54240",
+        "GSE241092",
+        "GSE220711",
+        "GSE29507",
+        "GSE42834",
+        "GSE160767",
+        "GSE111459",
+        "GSE179966",
+        "GSE72459",
+        "GSE102633",
+        "GSE145648",
+        "GSE47673",
+        "GSE43182",
+        "GSE218157",
+        "GSE106464",
+        "GSE49187",
+        "GSE28623",
+        "GSE223863",
+        "GSE267063",
+        "GSE273017",
+        "GSE131708",
+        "GSE73877",
+        "GSE123294",
+        "GSE101705",
+        "GSE14782",
+        "GSE249102",
+        "GSE193979",
+        "GSE154341",
+        "GSE116732",
+        "GSE162200",
+        "GSE250589",
+        "GSE118994",
+        "GSE123993",
+        "GSE118869",
+        "GSE64132",
+        "GSE139327",
+        "GSE119143",
+        "GSE194017",
+        "GSE94116",
+        "GSE97298",
+        "GSE86184",
+        "GSE13978",
+        "GSE58810",
+        "GSE188319",
+        "GSE173560",
+        "GSE157671",
+        "GSE107792",
+        "GSE103551",
+        "GSE118008",
+        "GSE133750",
+        "GSE72329",
+        "GSE132283",
+        "GSE80817",
+        "GSE276988",
+        "GSE18023",
+        "GSE227851",
+        "GSE97530",
+        "GSE157084",
+        "GSE108731",
+        "GSE42151",
+        "GSE12379",
+        "GSE252118",
+        "GSE116406",
+        "GSE244235",
+        "GSE198877",
+        "GSE43749",
+        "GSE264267",
+        "GSE115155",
+        "GSE139896",
+        "GSE224467",
+        "GSE227049",
+        "GSE159080",
+        "GSE55817",
+        "GSE36998",
+        "GSE234115",
+        "GSE126355",
+        "GSE263496",
+        "GSE190024",
+        "GSE116394",
+        "GSE58314",
+        "GSE57101",
+        "GSE120552",
+        "GSE51037",
+        "GSE49951",
+        "GSE17477",
+        "GSE115546",
+        "GSE94907",
+        "GSE23947",
+        "GSE182591",
+        "GSE49760",
+        "GSE43466",
+        "GSE97835",
+        "GSE171775",
+        "GSE107387",
+        "GSE71200",
+        "GSE61618",
+        "GSE277003",
+        "GSE104287",
+        "GSE32236",
+        "GSE50834",
+        "GSE244851",
+        "GSE206607",
+        "GSE122737",
+        "GSE10897",
+        "GSE243660",
+        "GSE190433",
+        "GSE8839",
+        "GSE178186",
+        "GSE198064",
+        "GSE30299",
+        "GSE278812",
+        "GSE85357",
+        "GSE15540",
+        "GSE156134",
+        "GSE249460",
+        "GSE77556",
+        "GSE226075",
+        "GSE123132",
+        "GSE151764",
+        "GSE89552",
+        "GSE164156",
+        "GSE61579",
+        "GSE146260",
+        "GSE118100",
+        "GSE93362",
+        "GSE21112",
+        "GSE240372",
+        "GSE213893",
+        "GSE197742",
+        "GSE127263",
+        "GSE143731",
+        "GSE205280",
+        "GSE116733",
+        "GSE116731",
+        "GSE107993",
+        "GSE56559",
+        "GSE133145",
+        "GSE118469",
+        "GSE87801",
+        "GSE93036",
+        "GSE46212",
+        "GSE1642",
+        "GSE141931",
+        "GSE107882",
+        "GSE255073",
+        "GSE116357",
+        "GSE232691",
+        "GSE183912",
+        "GSE77884",
+        "GSE143500",
+        "GSE12380",
+        "GSE203118",
+        "GSE53843",
+        "GSE144514",
+        "GSE134566",
+        "GSE168519",
+        "GSE98597",
+        "GSE122787",
+        "GSE49947",
+        "GSE168458",
+        "GSE119572",
+        "GSE165259",
+        "GSE81913",
+        "GSE141513",
+        "GSE31732",
+        "GSE7461",
+        "GSE64179",
+        "GSE59725",
+        "GSE27882",
+        "GSE116542",
+        "GSE166677",
+        "GSE256184",
+        "GSE188320",
+        "GSE99710",
+        "GSE271121",
+        "GSE144127",
+        "GSE205161",
+        "GSE47834",
+        "GSE18426",
+        "GSE15511",
+        "GSE250112",
+        "GSE36238",
+        "GSE107123",
+        "GSE42273",
+        "GSE276178",
+        "GSE160184",
+        "GSE206304",
+        "GSE287968",
+        "GSE168198",
+        "GSE248407",
+        "GSE102272",
+        "GSE107884",
+        "GSE62525",
+        "GSE34623",
+        "GSE119582",
+        "GSE129835",
+        "GSE98600",
+        "GSE11696",
+        "GSE174526",
+        "GSE12835",
+        "GSE128199",
+        "GSE126614"
+    ],
+    "GARD:0020599": [
+        "GSE92500"
+    ],
+    "GARD:0006485": [
+        "GSE69009",
+        "GSE13314",
+        "GSE35278",
+        "GSE155177",
+        "GSE34015",
+        "GSE39577",
+        "GSE150417",
+        "GSE25527",
+        "GSE18616",
+        "GSE23877",
+        "GSE36311",
+        "GSE25637",
+        "GSE215792",
+        "GSE49356",
+        "GSE54303",
+        "GSE171059",
+        "GSE3237",
+        "GSE151360",
+        "GSE148112",
+        "GSE25550",
+        "GSE53115",
+        "GSE16024",
+        "GSE25636",
+        "GSE24881",
+        "GSE25638",
+        "GSE48047",
+        "GSE25639",
+        "GSE18736",
+        "GSE24485",
+        "GSE29493",
+        "GSE69009",
+        "GSE3648",
+        "GSE13314",
+        "GSE35278",
+        "GSE155177",
+        "GSE221273",
+        "GSE34015",
+        "GSE39577",
+        "GSE150417",
+        "GSE25527",
+        "GSE18616",
+        "GSE23877",
+        "GSE36311",
+        "GSE25637",
+        "GSE215792",
+        "GSE266548",
+        "GSE49356",
+        "GSE54303",
+        "GSE111052",
+        "GSE171059",
+        "GSE3237",
+        "GSE151360",
+        "GSE148112",
+        "GSE25550",
+        "GSE53115",
+        "GSE16024",
+        "GSE25636",
+        "GSE24881",
+        "GSE25638",
+        "GSE48047",
+        "GSE25639",
+        "GSE18736",
+        "GSE24485",
+        "GSE40931"
+    ],
+    "GARD:0019039": [
+        "GSE180706",
+        "GSE120242",
+        "GSE218252",
+        "GSE119462",
+        "GSE33503",
+        "GSE19880",
+        "GSE3624",
+        "GSE246108",
+        "GSE253232",
+        "GSE202067",
+        "GSE73579",
+        "GSE25496",
+        "GSE186489",
+        "GSE106718",
+        "GSE104499",
+        "GSE156853",
+        "GSE176351",
+        "GSE33500"
+    ],
+    "GARD:0007360": [
+        "GSE64486"
+    ],
+    "GARD:0005994": [
+        "GSE102246",
+        "GSE27162"
+    ],
+    "GARD:0025873": [
+        "GSE41789",
+        "GSE147242",
+        "GSE174196",
+        "GSE147241",
+        "GSE273235",
+        "GSE236049",
+        "GSE14431",
+        "GSE85359",
+        "GSE65402",
+        "GSE202586"
+    ],
+    "GARD:0018819": [
+        "GSE212242",
+        "GSE280498",
+        "GSE15297",
+        "GSE212238",
+        "GSE212239",
+        "GSE11223",
+        "GSE212241"
+    ],
+    "GARD:0000871": [
+        "GSE117221",
+        "GSE229212",
+        "GSE160602",
+        "GSE52637",
+        "GSE115687",
+        "GSE94351",
+        "GSE110936",
+        "GSE92620",
+        "GSE13284",
+        "GSE131809",
+        "GSE252157",
+        "GSE160603",
+        "GSE118357",
+        "GSE24901",
+        "GSE71396",
+        "GSE158839",
+        "GSE218232",
+        "GSE214558",
+        "GSE111860",
+        "GSE260900",
+        "GSE228819",
+        "GSE226078",
+        "GSE218231",
+        "GSE36618",
+        "GSE30220",
+        "GSE10002",
+        "GSE196682",
+        "GSE133181",
+        "GSE4240",
+        "GSE160601",
+        "GSE260901",
+        "GSE93971",
+        "GSE152338",
+        "GSE93973",
+        "GSE25925",
+        "GSE241141",
+        "GSE34125",
+        "GSE13283",
+        "GSE97671",
+        "GSE252159",
+        "GSE241765",
+        "GSE103445",
+        "GSE69319",
+        "GSE56088",
+        "GSE252161",
+        "GSE252160",
+        "GSE214557",
+        "GSE68587",
+        "GSE70219",
+        "GSE57992",
+        "GSE122524",
+        "GSE22109",
+        "GSE7847",
+        "GSE62431",
+        "GSE133589",
+        "GSE206098",
+        "GSE96060",
+        "GSE194064",
+        "GSE118358",
+        "GSE113503",
+        "GSE6808",
+        "GSE214556",
+        "GSE62430",
+        "GSE168116",
+        "GSE121992",
+        "GSE228570",
+        "GSE36312"
+    ],
+    "GARD:0019591": [
+        "GSE181063"
+    ],
+    "GARD:0006267": [
+        "GSE242232",
+        "GSE133028",
+        "GSE246608",
+        "GSE235277",
+        "GSE235276",
+        "GSE98784",
+        "GSE150598"
+    ],
+    "GARD:0024273": [
+        "GSE24358",
+        "GSE261443",
+        "GSE138708",
+        "GSE83227",
+        "GSE44077",
+        "GSE196303"
+    ],
+    "GARD:0024190": [
+        "GSE247574",
+        "GSE211485",
+        "GSE108055",
+        "GSE211486",
+        "GSE211483",
+        "GSE211482"
+    ],
+    "GARD:0022992": [
+        "GSE9800",
+        "GSE205734"
+    ],
+    "GARD:0021868": [
+        "GSE243981",
+        "GSE37468",
+        "GSE11507",
+        "GSE66231",
+        "GSE179993",
+        "GSE11907",
+        "GSE177044",
+        "GSE118373",
+        "GSE69948",
+        "GSE18759",
+        "GSE4603",
+        "GSE206364",
+        "GSE130563",
+        "GSE87898",
+        "GSE79094",
+        "GSE230568",
+        "GSE119600",
+        "GSE261205",
+        "GSE72602",
+        "GSE213165",
+        "GSE168758",
+        "GSE159676",
+        "GSE230524",
+        "GSE72593",
+        "GSE259311",
+        "GSE245620",
+        "GSE144521",
+        "GSE117593",
+        "GSE104876",
+        "GSE11908",
+        "GSE132168",
+        "GSE217968",
+        "GSE240429",
+        "GSE84954",
+        "GSE247128",
+        "GSE228596",
+        "GSE166087",
+        "GSE72600",
+        "GSE213388",
+        "GSE239283",
+        "GSE180289",
+        "GSE37559",
+        "GSE268905",
+        "GSE104873",
+        "GSE230569",
+        "GSE243977"
+    ],
+    "GARD:0024444": [
+        "GSE169146",
+        "GSE32887",
+        "GSE192456",
+        "GSE169149",
+        "GSE192460",
+        "GSE169147",
+        "GSE169148",
+        "GSE39606"
+    ],
+    "GARD:0006218": [
+        "GSE208333",
+        "GSE147109",
+        "GSE17338",
+        "GSE226656",
+        "GSE66510",
+        "GSE271485",
+        "GSE21178",
+        "GSE29675",
+        "GSE78824",
+        "GSE135039",
+        "GSE126313",
+        "GSE94091",
+        "GSE16692",
+        "GSE64871",
+        "GSE53912",
+        "GSE153947",
+        "GSE61550",
+        "GSE237320",
+        "GSE162914",
+        "GSE153134",
+        "GSE112636",
+        "GSE96543",
+        "GSE108649",
+        "GSE188965",
+        "GSE150802",
+        "GSE226651",
+        "GSE59583",
+        "GSE21176",
+        "GSE235148",
+        "GSE183184",
+        "GSE60398",
+        "GSE136832",
+        "GSE93699",
+        "GSE43189",
+        "GSE45027",
+        "GSE73203",
+        "GSE83594",
+        "GSE146235",
+        "GSE108534",
+        "GSE57720",
+        "GSE206758",
+        "GSE55337",
+        "GSE112668",
+        "GSE21192",
+        "GSE24927",
+        "GSE146233",
+        "GSE30154",
+        "GSE277848",
+        "GSE36181",
+        "GSE142374",
+        "GSE109582",
+        "GSE248987",
+        "GSE255160",
+        "GSE206508",
+        "GSE52645",
+        "GSE260932",
+        "GSE126977",
+        "GSE36183",
+        "GSE65088",
+        "GSE233612",
+        "GSE146435",
+        "GSE152784",
+        "GSE118549",
+        "GSE111400",
+        "GSE223548",
+        "GSE95128",
+        "GSE23948",
+        "GSE153693",
+        "GSE36184",
+        "GSE86345",
+        "GSE133695",
+        "GSE121183",
+        "GSE108059",
+        "GSE226637",
+        "GSE168814",
+        "GSE110120",
+        "GSE110723",
+        "GSE263806",
+        "GSE165294",
+        "GSE69532",
+        "GSE76063",
+        "GSE74217",
+        "GSE138083",
+        "GSE36182",
+        "GSE208163",
+        "GSE241788",
+        "GSE23929",
+        "GSE126314",
+        "GSE52520",
+        "GSE48595",
+        "GSE21484",
+        "GSE215311",
+        "GSE37875",
+        "GSE74218",
+        "GSE80357",
+        "GSE80230",
+        "GSE53348",
+        "GSE217345",
+        "GSE118543",
+        "GSE116040",
+        "GSE93701",
+        "GSE57287",
+        "GSE10075",
+        "GSE101749",
+        "GSE80474",
+        "GSE32228",
+        "GSE11390",
+        "GSE233619",
+        "GSE183183",
+        "GSE118759",
+        "GSE214001",
+        "GSE195824",
+        "GSE57217",
+        "GSE10073",
+        "GSE125281",
+        "GSE111975",
+        "GSE32075",
+        "GSE242109",
+        "GSE43370",
+        "GSE146234",
+        "GSE31911",
+        "GSE253846",
+        "GSE196267",
+        "GSE136879",
+        "GSE13834",
+        "GSE93700",
+        "GSE229703",
+        "GSE41211",
+        "GSE244094",
+        "GSE10104",
+        "GSE6226",
+        "GSE133840",
+        "GSE110122",
+        "GSE8688",
+        "GSE159601",
+        "GSE171092",
+        "GSE29671",
+        "GSE130375",
+        "GSE52523",
+        "GSE35241",
+        "GSE260902",
+        "GSE121420",
+        "GSE69361",
+        "GSE27660",
+        "GSE28673",
+        "GSE18282",
+        "GSE203483",
+        "GSE69528",
+        "GSE133067",
+        "GSE74298",
+        "GSE133125",
+        "GSE30156",
+        "GSE46829",
+        "GSE10750",
+        "GSE66509",
+        "GSE128009",
+        "GSE122765",
+        "GSE51573",
+        "GSE104198",
+        "GSE35105",
+        "GSE5341",
+        "GSE17052",
+        "GSE147378",
+        "GSE124734",
+        "GSE44978",
+        "GSE43363",
+        "GSE226255",
+        "GSE35067",
+        "GSE45688",
+        "GSE243519",
+        "GSE269512",
+        "GSE277849",
+        "GSE182879",
+        "GSE135038",
+        "GSE110121",
+        "GSE66508",
+        "GSE93005",
+        "GSE222564",
+        "GSE162851",
+        "GSE28592",
+        "GSE135040",
+        "GSE129227",
+        "GSE122785",
+        "GSE238170",
+        "GSE26925",
+        "GSE232437",
+        "GSE29627",
+        "GSE135566",
+        "GSE216963",
+        "GSE173209",
+        "GSE160397",
+        "GSE32049",
+        "GSE22988",
+        "GSE183182",
+        "GSE217187",
+        "GSE40303",
+        "GSE134684",
+        "GSE17887",
+        "GSE131891",
+        "GSE74219",
+        "GSE153497",
+        "GSE41066",
+        "GSE21177",
+        "GSE137248",
+        "GSE46692",
+        "GSE117227",
+        "GSE36977",
+        "GSE171937",
+        "GSE198875",
+        "GSE115570",
+        "GSE245849",
+        "GSE126312",
+        "GSE133026"
+    ],
+    "GARD:0020204": [
+        "GSE102073",
+        "GSE29156",
+        "GSE191301",
+        "GSE10971",
+        "GSE102085",
+        "GSE53963",
+        "GSE213699",
+        "GSE7180",
+        "GSE28720",
+        "GSE147995",
+        "GSE73614",
+        "GSE241221",
+        "GSE101976",
+        "GSE28721",
+        "GSE102094",
+        "GSE212890",
+        "GSE148005",
+        "GSE12040",
+        "GSE172016",
+        "GSE102073",
+        "GSE29156",
+        "GSE191301",
+        "GSE10971",
+        "GSE102085",
+        "GSE53963",
+        "GSE213699",
+        "GSE7180",
+        "GSE28720",
+        "GSE147995",
+        "GSE73614",
+        "GSE241221",
+        "GSE101976",
+        "GSE28721",
+        "GSE102094",
+        "GSE212890",
+        "GSE148005",
+        "GSE12040",
+        "GSE172016"
+    ],
+    "GARD:0016829": [
+        "GSE261274",
+        "GSE56981",
+        "GSE192767",
+        "GSE84352",
+        "GSE125040",
+        "GSE167546",
+        "GSE184927",
+        "GSE159873",
+        "GSE108432",
+        "GSE84354",
+        "GSE195572",
+        "GSE445",
+        "GSE159872",
+        "GSE108430",
+        "GSE159871",
+        "GSE184925",
+        "GSE174593",
+        "GSE84353",
+        "GSE60514",
+        "GSE22028",
+        "GSE159874",
+        "GSE261563",
+        "GSE184915",
+        "GSE35339",
+        "GSE103460",
+        "GSE197988",
+        "GSE96060",
+        "GSE261274",
+        "GSE56981",
+        "GSE192767",
+        "GSE84352",
+        "GSE125040",
+        "GSE167546",
+        "GSE184927",
+        "GSE159873",
+        "GSE108432",
+        "GSE84354",
+        "GSE195572",
+        "GSE445",
+        "GSE159872",
+        "GSE108430",
+        "GSE159871",
+        "GSE184925",
+        "GSE174593",
+        "GSE84353",
+        "GSE60514",
+        "GSE22028",
+        "GSE159874",
+        "GSE261563",
+        "GSE184915",
+        "GSE35339",
+        "GSE103460",
+        "GSE197988",
+        "GSE96060"
+    ],
+    "GARD:0012820": [
+        "GSE237767",
+        "GSE36381",
+        "GSE240486",
+        "GSE26450",
+        "GSE60971",
+        "GSE267857",
+        "GSE263420",
+        "GSE143688",
+        "GSE161084",
+        "GSE109426",
+        "GSE114729",
+        "GSE150851",
+        "GSE117468",
+        "GSE41662",
+        "GSE41905",
+        "GSE14905",
+        "GSE151278",
+        "GSE176279",
+        "GSE253440",
+        "GSE154818",
+        "GSE50099",
+        "GSE85967",
+        "GSE102725",
+        "GSE229198",
+        "GSE137510",
+        "GSE212126",
+        "GSE150672",
+        "GSE204832",
+        "GSE54884",
+        "GSE239719",
+        "GSE84204",
+        "GSE137906",
+        "GSE50598",
+        "GSE280220",
+        "GSE85034",
+        "GSE248679",
+        "GSE68923",
+        "GSE262954",
+        "GSE235570",
+        "GSE145304",
+        "GSE68750",
+        "GSE79704",
+        "GSE73894",
+        "GSE39500",
+        "GSE67853",
+        "GSE59384",
+        "GSE74761",
+        "GSE233000",
+        "GSE261036",
+        "GSE102641",
+        "GSE57405",
+        "GSE35582",
+        "GSE126017",
+        "GSE217552",
+        "GSE81106",
+        "GSE225475",
+        "GSE248626",
+        "GSE122624",
+        "GSE231728",
+        "GSE86315",
+        "GSE71829",
+        "GSE57225",
+        "GSE203029",
+        "GSE34756",
+        "GSE74697",
+        "GSE131663",
+        "GSE186117",
+        "GSE189889",
+        "GSE123492",
+        "GSE188954",
+        "GSE183134",
+        "GSE149622",
+        "GSE179731",
+        "GSE39743",
+        "GSE206147",
+        "GSE228982",
+        "GSE53795",
+        "GSE80430",
+        "GSE249936",
+        "GSE153469",
+        "GSE18686",
+        "GSE248680",
+        "GSE155538",
+        "GSE92472",
+        "GSE53431",
+        "GSE230842",
+        "GSE282510",
+        "GSE275154",
+        "GSE63080",
+        "GSE217060",
+        "GSE89725",
+        "GSE142552",
+        "GSE115797",
+        "GSE268744",
+        "GSE11308",
+        "GSE175732",
+        "GSE57383",
+        "GSE136434",
+        "GSE129176",
+        "GSE169375",
+        "GSE145054",
+        "GSE145126",
+        "GSE9211",
+        "GSE185764",
+        "GSE237771",
+        "GSE7216",
+        "GSE119207",
+        "GSE129373",
+        "GSE237552",
+        "GSE104603",
+        "GSE167914",
+        "GSE160310",
+        "GSE38039",
+        "GSE57173",
+        "GSE254707",
+        "GSE11306",
+        "GSE231815",
+        "GSE47944",
+        "GSE138089",
+        "GSE43580",
+        "GSE161350",
+        "GSE42632",
+        "GSE103489",
+        "GSE68939",
+        "GSE101877",
+        "GSE179632",
+        "GSE78057",
+        "GSE52471",
+        "GSE63315",
+        "GSE32407",
+        "GSE250390",
+        "GSE200493",
+        "GSE193128",
+        "GSE50614",
+        "GSE137634",
+        "GSE121315",
+        "GSE31408",
+        "GSE31652",
+        "GSE197056",
+        "GSE109182",
+        "GSE63343",
+        "GSE218745",
+        "GSE173651",
+        "GSE137593",
+        "GSE175438",
+        "GSE83582",
+        "GSE161500",
+        "GSE21635",
+        "GSE106992",
+        "GSE31835",
+        "GSE253791",
+        "GSE202011",
+        "GSE69371",
+        "GSE224783",
+        "GSE183820",
+        "GSE203415",
+        "GSE145127",
+        "GSE46889",
+        "GSE218977",
+        "GSE267132",
+        "GSE68937",
+        "GSE173706",
+        "GSE32620",
+        "GSE17334",
+        "GSE237556",
+        "GSE26952",
+        "GSE47607",
+        "GSE184609",
+        "GSE137594",
+        "GSE226452",
+        "GSE239722",
+        "GSE270251",
+        "GSE189094",
+        "GSE220116",
+        "GSE202352",
+        "GSE131670",
+        "GSE21637",
+        "GSE207390",
+        "GSE268695",
+        "GSE74876",
+        "GSE160308",
+        "GSE193920",
+        "GSE96957",
+        "GSE63980",
+        "GSE267066",
+        "GSE6601",
+        "GSE30768",
+        "GSE160306",
+        "GSE181748",
+        "GSE58033",
+        "GSE161076",
+        "GSE25733",
+        "GSE138209",
+        "GSE162183",
+        "GSE21634",
+        "GSE106087",
+        "GSE147339",
+        "GSE228421",
+        "GSE80429",
+        "GSE261205",
+        "GSE115103",
+        "GSE178228",
+        "GSE161683",
+        "GSE150805",
+        "GSE142517",
+        "GSE63361",
+        "GSE18948",
+        "GSE11307",
+        "GSE151835",
+        "GSE193101",
+        "GSE194315",
+        "GSE209981",
+        "GSE77719",
+        "GSE18123",
+        "GSE268745",
+        "GSE179800",
+        "GSE12875",
+        "GSE74528",
+        "GSE216914",
+        "GSE219008",
+        "GSE13355",
+        "GSE62408",
+        "GSE192867",
+        "GSE221648",
+        "GSE186713",
+        "GSE189095",
+        "GSE160904",
+        "GSE24767",
+        "GSE201676",
+        "GSE25400",
+        "GSE155702",
+        "GSE193350",
+        "GSE30355",
+        "GSE228953",
+        "GSE175471",
+        "GSE42305",
+        "GSE234831",
+        "GSE226244",
+        "GSE162274",
+        "GSE146149",
+        "GSE173387",
+        "GSE251736",
+        "GSE41664",
+        "GSE248121",
+        "GSE223799",
+        "GSE142582",
+        "GSE41745",
+        "GSE53552",
+        "GSE123787",
+        "GSE237690",
+        "GSE282511",
+        "GSE67762",
+        "GSE188763",
+        "GSE47751",
+        "GSE205959",
+        "GSE153007",
+        "GSE141384",
+        "GSE248221",
+        "GSE168640",
+        "GSE123086",
+        "GSE186063",
+        "GSE126066",
+        "GSE47598",
+        "GSE213528",
+        "GSE189751",
+        "GSE27887",
+        "GSE55515",
+        "GSE69365",
+        "GSE72246",
+        "GSE186724",
+        "GSE137220",
+        "GSE30999",
+        "GSE26866",
+        "GSE163700",
+        "GSE233280",
+        "GSE174763",
+        "GSE154968",
+        "GSE181994",
+        "GSE144312",
+        "GSE57376",
+        "GSE214836",
+        "GSE150361",
+        "GSE81944",
+        "GSE167248",
+        "GSE208671",
+        "GSE215333",
+        "GSE16161",
+        "GSE105035",
+        "GSE201397",
+        "GSE189096",
+        "GSE34248",
+        "GSE23113",
+        "GSE61741",
+        "GSE223468",
+        "GSE107871",
+        "GSE248678",
+        "GSE123088",
+        "GSE75343",
+        "GSE255248",
+        "GSE144850",
+        "GSE141934",
+        "GSE220813",
+        "GSE86139",
+        "GSE190867",
+        "GSE268273",
+        "GSE216519",
+        "GSE51440",
+        "GSE277246",
+        "GSE185858",
+        "GSE108640",
+        "GSE252029",
+        "GSE272325",
+        "GSE21694",
+        "GSE185857",
+        "GSE139341",
+        "GSE138084",
+        "GSE249613",
+        "GSE232568",
+        "GSE269610",
+        "GSE162051",
+        "GSE123786",
+        "GSE121212",
+        "GSE55201",
+        "GSE36700",
+        "GSE161906",
+        "GSE42634",
+        "GSE164579",
+        "GSE40033",
+        "GSE250242",
+        "GSE183047",
+        "GSE85891",
+        "GSE183547",
+        "GSE214837",
+        "GSE93423",
+        "GSE142510",
+        "GSE282992",
+        "GSE228972",
+        "GSE110658",
+        "GSE61281",
+        "GSE151193",
+        "GSE83645",
+        "GSE263428",
+        "GSE159457",
+        "GSE230512",
+        "GSE215124",
+        "GSE70277",
+        "GSE6549",
+        "GSE256275",
+        "GSE66511",
+        "GSE200977",
+        "GSE50400",
+        "GSE188919",
+        "GSE241033",
+        "GSE214835",
+        "GSE10080",
+        "GSE230511",
+        "GSE237555",
+        "GSE201827",
+        "GSE171676",
+        "GSE166388",
+        "GSE82140",
+        "GSE6710",
+        "GSE93698",
+        "GSE63079",
+        "GSE41663",
+        "GSE164580",
+        "GSE70275",
+        "GSE4828",
+        "GSE68924",
+        "GSE17335",
+        "GSE69370",
+        "GSE4747",
+        "GSE102190",
+        "GSE39267",
+        "GSE117239",
+        "GSE48586",
+        "GSE17333",
+        "GSE69372",
+        "GSE272361",
+        "GSE100648",
+        "GSE266043",
+        "GSE160932",
+        "GSE36287",
+        "GSE164400",
+        "GSE123785",
+        "GSE36387",
+        "GSE269981",
+        "GSE185856",
+        "GSE115293",
+        "GSE180418",
+        "GSE17336",
+        "GSE228938",
+        "GSE78023",
+        "GSE178197",
+        "GSE164438",
+        "GSE198805",
+        "GSE162998",
+        "GSE165781",
+        "GSE80427",
+        "GSE157932",
+        "GSE9120",
+        "GSE159704",
+        "GSE70276",
+        "GSE72396",
+        "GSE5515",
+        "GSE136757",
+        "GSE107264",
+        "GSE11903",
+        "GSE145305",
+        "GSE80428",
+        "GSE200376",
+        "GSE2737",
+        "GSE149880",
+        "GSE175473",
+        "GSE182283",
+        "GSE119762",
+        "GSE69366",
+        "GSE58297",
+        "GSE158112",
+        "GSE100774",
+        "GSE42633",
+        "GSE72193",
+        "GSE47965",
+        "GSE104509",
+        "GSE108743",
+        "GSE57012",
+        "GSE154200",
+        "GSE80047",
+        "GSE17337",
+        "GSE171170",
+        "GSE6932",
+        "GSE248548",
+        "GSE228629",
+        "GSE107375",
+        "GSE235032",
+        "GSE237610",
+        "GSE248917",
+        "GSE200836",
+        "GSE146264",
+        "GSE181318",
+        "GSE117769",
+        "GSE142049",
+        "GSE205501",
+        "GSE151177",
+        "GSE188905",
+        "GSE2631",
+        "GSE107265",
+        "GSE181089",
+        "GSE183732",
+        "GSE210037",
+        "GSE175364",
+        "GSE141804",
+        "GSE176509",
+        "GSE205748",
+        "GSE107266",
+        "GSE60804",
+        "GSE255890",
+        "GSE167057",
+        "GSE40263",
+        "GSE235950",
+        "GSE72212",
+        "GSE189361",
+        "GSE220586",
+        "GSE162926",
+        "GSE44579",
+        "GSE27628",
+        "GSE67785",
+        "GSE236694",
+        "GSE101077",
+        "GSE184500",
+        "GSE183608",
+        "GSE235635",
+        "GSE169376",
+        "GSE65309",
+        "GSE70327",
+        "GSE58749",
+        "GSE81881",
+        "GSE57939",
+        "GSE63684",
+        "GSE52361",
+        "GSE136431",
+        "GSE222043",
+        "GSE137221",
+        "GSE69600",
+        "GSE182740",
+        "GSE277039",
+        "GSE137218",
+        "GSE78097",
+        "GSE158448",
+        "GSE153648",
+        "GSE260584",
+        "GSE120464",
+        "GSE152637",
+        "GSE69967",
+        "GSE54456",
+        "GSE90450",
+        "GSE12722",
+        "GSE63741",
+        "GSE41261",
+        "GSE175474",
+        "GSE239720",
+        "GSE228385",
+        "GSE205499",
+        "GSE114286",
+        "GSE243689",
+        "GSE58121",
+        "GSE86451",
+        "GSE171012",
+        "GSE182244",
+        "GSE251967",
+        "GSE57386",
+        "GSE39266",
+        "GSE75890",
+        "GSE160906",
+        "GSE28729",
+        "GSE117405",
+        "GSE20264",
+        "GSE31037",
+        "GSE196431",
+        "GSE109248",
+        "GSE206391",
+        "GSE103038",
+        "GSE229605",
+        "GSE253346",
+        "GSE161406",
+        "GSE247463",
+        "GSE32245",
+        "GSE236695",
+        "GSE239533",
+        "GSE50790",
+        "GSE206311",
+        "GSE165021",
+        "GSE205960",
+        "GSE266075",
+        "GSE52648",
+        "GSE102274",
+        "GSE101177",
+        "GSE247047",
+        "GSE79642",
+        "GSE175470"
+    ],
+    "GARD:0006969": [
+        "GSE239482",
+        "GSE81552",
+        "GSE23849",
+        "GSE178893",
+        "GSE171424",
+        "GSE217579",
+        "GSE16455",
+        "GSE116873",
+        "GSE182687",
+        "GSE95291",
+        "GSE116870",
+        "GSE71102",
+        "GSE39577",
+        "GSE268228",
+        "GSE34602",
+        "GSE273299",
+        "GSE30189",
+        "GSE190599",
+        "GSE22264",
+        "GSE42935",
+        "GSE32230",
+        "GSE18820",
+        "GSE141333",
+        "GSE122513",
+        "GSE182689",
+        "GSE52146",
+        "GSE243395",
+        "GSE189927",
+        "GSE141334",
+        "GSE123518",
+        "GSE66514",
+        "GSE227976",
+        "GSE53309",
+        "GSE144095",
+        "GSE229517",
+        "GSE138127",
+        "GSE52434",
+        "GSE175568",
+        "GSE194360",
+        "GSE126726",
+        "GSE240555",
+        "GSE10793",
+        "GSE114791",
+        "GSE116868",
+        "GSE132929",
+        "GSE35426",
+        "GSE16412",
+        "GSE93291",
+        "GSE4176",
+        "GSE46846",
+        "GSE116869",
+        "GSE14003",
+        "GSE116876",
+        "GSE21452",
+        "GSE60327",
+        "GSE13331",
+        "GSE8918",
+        "GSE186942",
+        "GSE52149",
+        "GSE15229",
+        "GSE52214",
+        "GSE56495",
+        "GSE89615",
+        "GSE22905",
+        "GSE54303",
+        "GSE214725",
+        "GSE144106",
+        "GSE268224",
+        "GSE141335",
+        "GSE16435",
+        "GSE108111",
+        "GSE42854",
+        "GSE42917",
+        "GSE36138",
+        "GSE273294",
+        "GSE116872",
+        "GSE110134",
+        "GSE52435",
+        "GSE208679",
+        "GSE194362",
+        "GSE268225",
+        "GSE16024",
+        "GSE240725",
+        "GSE9327",
+        "GSE80563",
+        "GSE184031",
+        "GSE35424",
+        "GSE31814",
+        "GSE123449",
+        "GSE99501",
+        "GSE52148",
+        "GSE86322",
+        "GSE223150",
+        "GSE116810",
+        "GSE108651",
+        "GSE57128",
+        "GSE116871",
+        "GSE29493",
+        "GSE120124",
+        "GSE173869",
+        "GSE42549",
+        "GSE77788",
+        "GSE70651",
+        "GSE66299",
+        "GSE34763",
+        "GSE55405",
+        "GSE16413",
+        "GSE116129",
+        "GSE10258",
+        "GSE220936",
+        "GSE19243",
+        "GSE36139",
+        "GSE20915",
+        "GSE21554",
+        "GSE162234",
+        "GSE240726",
+        "GSE97541",
+        "GSE124931",
+        "GSE54169",
+        "GSE45717",
+        "GSE6728",
+        "GSE190600",
+        "GSE38145",
+        "GSE186938",
+        "GSE46969",
+        "GSE11635",
+        "GSE70927",
+        "GSE94328",
+        "GSE36133",
+        "GSE36000",
+        "GSE159808",
+        "GSE141539",
+        "GSE173872",
+        "GSE279602",
+        "GSE60023",
+        "GSE95292",
+        "GSE25613",
+        "GSE146851",
+        "GSE2109",
+        "GSE18736",
+        "GSE140184",
+        "GSE147484",
+        "GSE70926",
+        "GSE2350",
+        "GSE182688",
+        "GSE122739",
+        "GSE118301",
+        "GSE16411",
+        "GSE22898",
+        "GSE190587",
+        "GSE116867",
+        "GSE68091",
+        "GSE194363",
+        "GSE116875",
+        "GSE25621",
+        "GSE32018",
+        "GSE186941",
+        "GSE52892",
+        "GSE116874",
+        "GSE122510",
+        "GSE42637",
+        "GSE183030",
+        "GSE89447",
+        "GSE111052",
+        "GSE171059",
+        "GSE59810",
+        "GSE36808",
+        "GSE58165",
+        "GSE160742",
+        "GSE141336",
+        "GSE58613",
+        "GSE122509",
+        "GSE273297",
+        "GSE216645",
+        "GSE70910",
+        "GSE98268",
+        "GSE116132",
+        "GSE173353",
+        "GSE268226",
+        "GSE199257",
+        "GSE268227",
+        "GSE116097",
+        "GSE106092",
+        "GSE70479"
+    ],
+    "GARD:0000848": [
+        "GSE61399",
+        "GSE198616",
+        "GSE145191",
+        "GSE70403",
+        "GSE198533",
+        "GSE185919",
+        "GSE205867",
+        "GSE17114",
+        "GSE225904",
+        "GSE95078",
+        "GSE165254",
+        "GSE209567",
+        "GSE61399",
+        "GSE198616",
+        "GSE145191",
+        "GSE70403",
+        "GSE198533",
+        "GSE185919",
+        "GSE205867",
+        "GSE17114",
+        "GSE225904",
+        "GSE95078",
+        "GSE165254",
+        "GSE209567"
+    ],
+    "GARD:0002092": [
+        "GSE55726",
+        "GSE8966",
+        "GSE29109",
+        "GSE56339",
+        "GSE6230"
+    ],
+    "GARD:0007700": [
+        "GSE13727",
+        "GSE12829",
+        "GSE273720",
+        "GSE13726"
+    ],
+    "GARD:0010263": [
+        "GSE54948",
+        "GSE88873",
+        "GSE22091",
+        "GSE240957",
+        "GSE66247",
+        "GSE52576",
+        "GSE18701",
+        "GSE281755",
+        "GSE67413",
+        "GSE138864",
+        "GSE125592",
+        "GSE18642",
+        "GSE252907",
+        "GSE122872",
+        "GSE252906",
+        "GSE186009",
+        "GSE52578",
+        "GSE64244",
+        "GSE50783",
+        "GSE15314",
+        "GSE14",
+        "GSE67412",
+        "GSE226394",
+        "GSE123065",
+        "GSE18663",
+        "GSE138250",
+        "GSE12713",
+        "GSE65881",
+        "GSE252905",
+        "GSE141906",
+        "GSE153211",
+        "GSE117672"
+    ],
+    "GARD:0005972": [
+        "GSE74375",
+        "GSE112235",
+        "GSE242232",
+        "GSE278382",
+        "GSE280619",
+        "GSE182644",
+        "GSE77361",
+        "GSE278926",
+        "GSE280220",
+        "GSE280620",
+        "GSE263026",
+        "GSE126956"
+    ],
+    "GARD:0007413": [
+        "GSE233949",
+        "GSE221725",
+        "GSE10569",
+        "GSE55576",
+        "GSE52489",
+        "GSE62",
+        "GSE108995",
+        "GSE52324",
+        "GSE44721",
+        "GSE10566",
+        "GSE69433",
+        "GSE16191",
+        "GSE260461",
+        "GSE146890",
+        "GSE76967",
+        "GSE243750",
+        "GSE107375",
+        "GSE178932",
+        "GSE144218"
+    ],
+    "GARD:0008598": [
+        "GSE45901",
+        "GSE8167",
+        "GSE68606",
+        "GSE47913",
+        "GSE241927",
+        "GSE162115",
+        "GSE69465",
+        "GSE85589",
+        "GSE2553",
+        "GSE156680",
+        "GSE17743",
+        "GSE77839",
+        "GSE80305",
+        "GSE13861",
+        "GSE50890",
+        "GSE17018",
+        "GSE68740",
+        "GSE31741",
+        "GSE182451",
+        "GSE73346",
+        "GSE247209",
+        "GSE29357",
+        "GSE153717",
+        "GSE131481",
+        "GSE171496",
+        "GSE113217",
+        "GSE40021",
+        "GSE53021",
+        "GSE197763",
+        "GSE60744",
+        "GSE71120",
+        "GSE22852",
+        "GSE247170",
+        "GSE182453",
+        "GSE172153",
+        "GSE112",
+        "GSE80443",
+        "GSE93963",
+        "GSE92345",
+        "GSE37586",
+        "GSE64762",
+        "GSE51697",
+        "GSE19396",
+        "GSE241924",
+        "GSE119558",
+        "GSE15966",
+        "GSE21315",
+        "GSE241925",
+        "GSE159702",
+        "GSE4305",
+        "GSE68743",
+        "GSE173682",
+        "GSE22905",
+        "GSE161226",
+        "GSE110823",
+        "GSE147303",
+        "GSE26942",
+        "GSE21124",
+        "GSE51698",
+        "GSE206257",
+        "GSE171495",
+        "GSE102054",
+        "GSE113215",
+        "GSE212854",
+        "GSE13808",
+        "GSE206793",
+        "GSE113207",
+        "GSE95863",
+        "GSE107447",
+        "GSE151323",
+        "GSE172154",
+        "GSE5336",
+        "GSE118896",
+        "GSE215402",
+        "GSE241926",
+        "GSE106623",
+        "GSE27399",
+        "GSE54734",
+        "GSE68742",
+        "GSE68860",
+        "GSE46928",
+        "GSE19399",
+        "GSE11940",
+        "GSE8164",
+        "GSE95861",
+        "GSE50894",
+        "GSE136755",
+        "GSE87902",
+        "GSE30416",
+        "GSE3443",
+        "GSE75479",
+        "GSE52323",
+        "GSE36087",
+        "GSE194259",
+        "GSE85613",
+        "GSE50891",
+        "GSE3930",
+        "GSE34387",
+        "GSE32064",
+        "GSE56670",
+        "GSE234092",
+        "GSE40080",
+        "GSE71119",
+        "GSE22185",
+        "GSE171499",
+        "GSE188700",
+        "GSE106624",
+        "GSE52666",
+        "GSE60853",
+        "GSE220511",
+        "GSE20708",
+        "GSE6988",
+        "GSE2719",
+        "GSE22433",
+        "GSE28866",
+        "GSE89051",
+        "GSE89673",
+        "GSE95862",
+        "GSE47911",
+        "GSE59841",
+        "GSE106626",
+        "GSE2069",
+        "GSE40018",
+        "GSE143547",
+        "GSE55521",
+        "GSE156715",
+        "GSE225978",
+        "GSE225819",
+        "GSE11942",
+        "GSE64608",
+        "GSE153750",
+        "GSE254762",
+        "GSE97581",
+        "GSE4303",
+        "GSE20709",
+        "GSE28469",
+        "GSE14755",
+        "GSE22441",
+        "GSE31802",
+        "GSE282434",
+        "GSE172152",
+        "GSE47912",
+        "GSE20710",
+        "GSE26899",
+        "GSE171498",
+        "GSE93077",
+        "GSE71121",
+        "GSE183635",
+        "GSE155800",
+        "GSE4001",
+        "GSE132542",
+        "GSE63159",
+        "GSE95864",
+        "GSE52252",
+        "GSE64609",
+        "GSE2109",
+        "GSE213777",
+        "GSE12931",
+        "GSE14541",
+        "GSE21123",
+        "GSE63453",
+        "GSE45901",
+        "GSE8167",
+        "GSE68606",
+        "GSE47913",
+        "GSE241927",
+        "GSE162115",
+        "GSE69465",
+        "GSE85589",
+        "GSE2553",
+        "GSE156680",
+        "GSE17743",
+        "GSE77839",
+        "GSE80305",
+        "GSE13861",
+        "GSE50890",
+        "GSE17018",
+        "GSE68740",
+        "GSE31741",
+        "GSE182451",
+        "GSE73346",
+        "GSE247209",
+        "GSE29357",
+        "GSE153717",
+        "GSE131481",
+        "GSE171496",
+        "GSE113217",
+        "GSE40021",
+        "GSE53021",
+        "GSE197763",
+        "GSE60744",
+        "GSE71120",
+        "GSE22852",
+        "GSE247170",
+        "GSE182453",
+        "GSE172153",
+        "GSE112",
+        "GSE80443",
+        "GSE93963",
+        "GSE92345",
+        "GSE37586",
+        "GSE64762",
+        "GSE51697",
+        "GSE19396",
+        "GSE241924",
+        "GSE119558",
+        "GSE15966",
+        "GSE21315",
+        "GSE241925",
+        "GSE159702",
+        "GSE4305",
+        "GSE68743",
+        "GSE173682",
+        "GSE22905",
+        "GSE161226",
+        "GSE110823",
+        "GSE147303",
+        "GSE26942",
+        "GSE21124",
+        "GSE51698",
+        "GSE206257",
+        "GSE171495",
+        "GSE102054",
+        "GSE113215",
+        "GSE212854",
+        "GSE13808",
+        "GSE206793",
+        "GSE113207",
+        "GSE95863",
+        "GSE107447",
+        "GSE151323",
+        "GSE172154",
+        "GSE5336",
+        "GSE118896",
+        "GSE215402",
+        "GSE241926",
+        "GSE106623",
+        "GSE27399",
+        "GSE54734",
+        "GSE68742",
+        "GSE68860",
+        "GSE46928",
+        "GSE19399",
+        "GSE11940",
+        "GSE8164",
+        "GSE95861",
+        "GSE50894",
+        "GSE136755",
+        "GSE87902",
+        "GSE30416",
+        "GSE3443",
+        "GSE75479",
+        "GSE52323",
+        "GSE36087",
+        "GSE194259",
+        "GSE85613",
+        "GSE50891",
+        "GSE3930",
+        "GSE34387",
+        "GSE32064",
+        "GSE56670",
+        "GSE234092",
+        "GSE40080",
+        "GSE71119",
+        "GSE22185",
+        "GSE171499",
+        "GSE188700",
+        "GSE106624",
+        "GSE52666",
+        "GSE60853",
+        "GSE220511",
+        "GSE20708",
+        "GSE6988",
+        "GSE2719",
+        "GSE22433",
+        "GSE28866",
+        "GSE89051",
+        "GSE89673",
+        "GSE95862",
+        "GSE47911",
+        "GSE59841",
+        "GSE106626",
+        "GSE2069",
+        "GSE40018",
+        "GSE143547",
+        "GSE55521",
+        "GSE156715",
+        "GSE225978",
+        "GSE225819",
+        "GSE11942",
+        "GSE64608",
+        "GSE153750",
+        "GSE254762",
+        "GSE97581",
+        "GSE4303",
+        "GSE20709",
+        "GSE28469",
+        "GSE14755",
+        "GSE22441",
+        "GSE31802",
+        "GSE282434",
+        "GSE172152",
+        "GSE47912",
+        "GSE20710",
+        "GSE26899",
+        "GSE171498",
+        "GSE93077",
+        "GSE71121",
+        "GSE183635",
+        "GSE155800",
+        "GSE4001",
+        "GSE132542",
+        "GSE63159",
+        "GSE95864",
+        "GSE52252",
+        "GSE64609",
+        "GSE2109",
+        "GSE213777",
+        "GSE12931",
+        "GSE14541",
+        "GSE21123",
+        "GSE63453"
+    ],
+    "GARD:0022419": [
+        "GSE26490",
+        "GSE23032",
+        "GSE50536",
+        "GSE154179",
+        "GSE73873",
+        "GSE241094",
+        "GSE195758",
+        "GSE50962",
+        "GSE151162",
+        "GSE50965",
+        "GSE80214",
+        "GSE26473",
+        "GSE5551",
+        "GSE98743",
+        "GSE119956",
+        "GSE50964",
+        "GSE50696",
+        "GSE50961",
+        "GSE79390",
+        "GSE157182",
+        "GSE23029",
+        "GSE54012",
+        "GSE280989",
+        "GSE123805",
+        "GSE56258",
+        "GSE50963",
+        "GSE50651"
+    ],
+    "GARD:0024237": [
+        "GSE26490",
+        "GSE23032",
+        "GSE200758",
+        "GSE50536",
+        "GSE205648",
+        "GSE19200",
+        "GSE125876",
+        "GSE119251",
+        "GSE50680",
+        "GSE14830",
+        "GSE154179",
+        "GSE61962",
+        "GSE94068",
+        "GSE41966",
+        "GSE73873",
+        "GSE132461",
+        "GSE241094",
+        "GSE119250",
+        "GSE27232",
+        "GSE92600",
+        "GSE152295",
+        "GSE207487",
+        "GSE60085",
+        "GSE166114",
+        "GSE50962",
+        "GSE151162",
+        "GSE110091",
+        "GSE50965",
+        "GSE42905",
+        "GSE196713",
+        "GSE80214",
+        "GSE51185",
+        "GSE270694",
+        "GSE135803",
+        "GSE141830",
+        "GSE26473",
+        "GSE19196",
+        "GSE5551",
+        "GSE98743",
+        "GSE87029",
+        "GSE119956",
+        "GSE50964",
+        "GSE50696",
+        "GSE185936",
+        "GSE50961",
+        "GSE79390",
+        "GSE125559",
+        "GSE69508",
+        "GSE13323",
+        "GSE19451",
+        "GSE12796",
+        "GSE157182",
+        "GSE63622",
+        "GSE23029",
+        "GSE89184",
+        "GSE135386",
+        "GSE13147",
+        "GSE54012",
+        "GSE280989",
+        "GSE123805",
+        "GSE56258",
+        "GSE50963",
+        "GSE61535",
+        "GSE281108",
+        "GSE272232",
+        "GSE190376",
+        "GSE50651",
+        "GSE159109",
+        "GSE26491"
+    ],
+    "GARD:0024215": [
+        "GSE178821",
+        "GSE53292",
+        "GSE96066",
+        "GSE77316",
+        "GSE154910",
+        "GSE32485",
+        "GSE107625",
+        "GSE221454",
+        "GSE7000",
+        "GSE166390",
+        "GSE180255",
+        "GSE145378",
+        "GSE222860",
+        "GSE241768",
+        "GSE235142",
+        "GSE268112",
+        "GSE130442",
+        "GSE35858",
+        "GSE39124",
+        "GSE56959",
+        "GSE172481",
+        "GSE198699",
+        "GSE126110",
+        "GSE159126",
+        "GSE44127",
+        "GSE29874",
+        "GSE119150",
+        "GSE23215",
+        "GSE132050",
+        "GSE113087",
+        "GSE12515",
+        "GSE3877",
+        "GSE180668",
+        "GSE1124",
+        "GSE4324",
+        "GSE144970",
+        "GSE21689",
+        "GSE172366",
+        "GSE55644",
+        "GSE168657",
+        "GSE244804",
+        "GSE119854",
+        "GSE145855",
+        "GSE59632",
+        "GSE45165",
+        "GSE65116",
+        "GSE132796",
+        "GSE22861",
+        "GSE43125",
+        "GSE34621",
+        "GSE145731",
+        "GSE35860",
+        "GSE114718",
+        "GSE72580",
+        "GSE162304",
+        "GSE133241",
+        "GSE213194",
+        "GSE100561",
+        "GSE125460",
+        "GSE159124",
+        "GSE4552",
+        "GSE104101",
+        "GSE116156",
+        "GSE199423",
+        "GSE90864",
+        "GSE59097",
+        "GSE255403",
+        "GSE59773",
+        "GSE169028",
+        "GSE231838",
+        "GSE152608",
+        "GSE264687",
+        "GSE162760",
+        "GSE157753",
+        "GSE81393",
+        "GSE709",
+        "GSE85205",
+        "GSE18323",
+        "GSE192930",
+        "GSE186820",
+        "GSE50957",
+        "GSE110970",
+        "GSE33796",
+        "GSE16259",
+        "GSE181179",
+        "GSE159532",
+        "GSE243215",
+        "GSE80466",
+        "GSE149727",
+        "GSE189196",
+        "GSE154651",
+        "GSE100562",
+        "GSE208155",
+        "GSE163144",
+        "GSE198603",
+        "GSE143900",
+        "GSE32200",
+        "GSE180257",
+        "GSE9853",
+        "GSE5418",
+        "GSE202876",
+        "GSE85478",
+        "GSE34878",
+        "GSE119849",
+        "GSE18037",
+        "GSE103874",
+        "GSE69629",
+        "GSE34806",
+        "GSE153778",
+        "GSE90878",
+        "GSE188659",
+        "GSE193761",
+        "GSE65036",
+        "GSE179055",
+        "GSE35949",
+        "GSE239405",
+        "GSE77165",
+        "GSE94916",
+        "GSE190342",
+        "GSE119853",
+        "GSE75795",
+        "GSE150479",
+        "GSE75137",
+        "GSE142527",
+        "GSE244805",
+        "GSE160923",
+        "GSE157967",
+        "GSE120076",
+        "GSE99486",
+        "GSE17866",
+        "GSE273785",
+        "GSE44921",
+        "GSE150484",
+        "GSE74820",
+        "GSE198586",
+        "GSE23867",
+        "GSE210629",
+        "GSE33836",
+        "GSE156791",
+        "GSE103259",
+        "GSE192757",
+        "GSE149772",
+        "GSE120448",
+        "GSE149894",
+        "GSE18780",
+        "GSE267362",
+        "GSE212754",
+        "GSE62133",
+        "GSE180985",
+        "GSE135002",
+        "GSE58402",
+        "GSE31274",
+        "GSE95534",
+        "GSE99679",
+        "GSE172450",
+        "GSE97158",
+        "GSE64931",
+        "GSE210624",
+        "GSE180256",
+        "GSE136169",
+        "GSE230169",
+        "GSE18831",
+        "GSE116219",
+        "GSE169520",
+        "GSE52166",
+        "GSE6019",
+        "GSE189034",
+        "GSE137044",
+        "GSE270553",
+        "GSE142275",
+        "GSE101484",
+        "GSE149393",
+        "GSE7814",
+        "GSE244528",
+        "GSE120488",
+        "GSE119852",
+        "GSE46471",
+        "GSE150478",
+        "GSE143899",
+        "GSE54775",
+        "GSE153600",
+        "GSE47349",
+        "GSE14964",
+        "GSE119944",
+        "GSE133651",
+        "GSE176156",
+        "GSE142276",
+        "GSE35936",
+        "GSE30974",
+        "GSE125566",
+        "GSE33002",
+        "GSE64690",
+        "GSE230206",
+        "GSE33605",
+        "GSE190750",
+        "GSE81818",
+        "GSE157611",
+        "GSE116341",
+        "GSE235824",
+        "GSE18075",
+        "GSE156102",
+        "GSE137043",
+        "GSE149728",
+        "GSE210943",
+        "GSE252334",
+        "GSE119851",
+        "GSE252686",
+        "GSE75593",
+        "GSE12727",
+        "GSE57551",
+        "GSE285041",
+        "GSE67470",
+        "GSE136008",
+        "GSE33834",
+        "GSE107672",
+        "GSE7586",
+        "GSE150546",
+        "GSE59098",
+        "GSE144413",
+        "GSE13014",
+        "GSE220039",
+        "GSE151116",
+        "GSE226145",
+        "GSE32007",
+        "GSE234253",
+        "GSE240202",
+        "GSE69628",
+        "GSE38707",
+        "GSE13578",
+        "GSE180258",
+        "GSE234970",
+        "GSE149865",
+        "GSE119151",
+        "GSE33835",
+        "GSE159127",
+        "GSE228947",
+        "GSE199239",
+        "GSE225556",
+        "GSE251974",
+        "GSE66669",
+        "GSE156410",
+        "GSE123391",
+        "GSE51329",
+        "GSE77398",
+        "GSE254652",
+        "GSE199368",
+        "GSE99223",
+        "GSE5672",
+        "GSE197916",
+        "GSE212753",
+        "GSE23865",
+        "GSE286478",
+        "GSE71518",
+        "GSE14524",
+        "GSE210625",
+        "GSE198585",
+        "GSE64702",
+        "GSE273781",
+        "GSE210628",
+        "GSE233713",
+        "GSE24903",
+        "GSE226020",
+        "GSE189345",
+        "GSE126381",
+        "GSE116025",
+        "GSE233703",
+        "GSE278246",
+        "GSE106462",
+        "GSE100692",
+        "GSE9808",
+        "GSE233739",
+        "GSE116021",
+        "GSE72448",
+        "GSE54806",
+        "GSE68757",
+        "GSE151557",
+        "GSE63260",
+        "GSE233472",
+        "GSE116024",
+        "GSE81196",
+        "GSE64887",
+        "GSE227873",
+        "GSE150268",
+        "GSE63611",
+        "GSE275092",
+        "GSE207610",
+        "GSE23982",
+        "GSE83331",
+        "GSE103507",
+        "GSE144965",
+        "GSE130278",
+        "GSE271070",
+        "GSE217930",
+        "GSE9152",
+        "GSE161959",
+        "GSE145634",
+        "GSE255062",
+        "GSE114094",
+        "GSE241313",
+        "GSE133238",
+        "GSE87373",
+        "GSE199419",
+        "GSE189197",
+        "GSE120728",
+        "GSE108478",
+        "GSE235286",
+        "GSE141761",
+        "GSE79135",
+        "GSE133236",
+        "GSE226021",
+        "GSE86082",
+        "GSE71637",
+        "GSE64493",
+        "GSE121312",
+        "GSE212052",
+        "GSE80634",
+        "GSE64338",
+        "GSE44128",
+        "GSE76537",
+        "GSE132643",
+        "GSE224162",
+        "GSE226630",
+        "GSE56329",
+        "GSE159045",
+        "GSE119848",
+        "GSE253397",
+        "GSE22585",
+        "GSE119855",
+        "GSE109599",
+        "GSE129397",
+        "GSE117613",
+        "GSE111066",
+        "GSE49690",
+        "GSE132625",
+        "GSE141155",
+        "GSE114096",
+        "GSE67469",
+        "GSE151189",
+        "GSE208131",
+        "GSE33811",
+        "GSE199569",
+        "GSE196126",
+        "GSE103862",
+        "GSE144976",
+        "GSE132647",
+        "GSE237217",
+        "GSE211439",
+        "GSE242856",
+        "GSE35859",
+        "GSE102909",
+        "GSE41496",
+        "GSE239600",
+        "GSE190519",
+        "GSE133654",
+        "GSE80015",
+        "GSE268018",
+        "GSE93631",
+        "GSE104330",
+        "GSE179860",
+        "GSE67184",
+        "GSE141758",
+        "GSE234872",
+        "GSE114076",
+        "GSE28701",
+        "GSE79702",
+        "GSE106238",
+        "GSE81391",
+        "GSE65928",
+        "GSE84030",
+        "GSE123839",
+        "GSE267413",
+        "GSE103012",
+        "GSE205515",
+        "GSE163965",
+        "GSE224160",
+        "GSE77809",
+        "GSE202214",
+        "GSE213186",
+        "GSE94901",
+        "GSE275671",
+        "GSE143898",
+        "GSE128115",
+        "GSE72058",
+        "GSE50199",
+        "GSE33764",
+        "GSE116619",
+        "GSE66185",
+        "GSE149729",
+        "GSE228097",
+        "GSE226628",
+        "GSE120990",
+        "GSE8125",
+        "GSE233471",
+        "GSE138499",
+        "GSE72446",
+        "GSE72579",
+        "GSE24849",
+        "GSE117307",
+        "GSE249806",
+        "GSE255891",
+        "GSE205012",
+        "GSE66188",
+        "GSE242548",
+        "GSE159516",
+        "GSE19756",
+        "GSE197159",
+        "GSE134268",
+        "GSE197458",
+        "GSE33333",
+        "GSE133240",
+        "GSE144599",
+        "GSE19157",
+        "GSE169027",
+        "GSE59258",
+        "GSE149773",
+        "GSE164070",
+        "GSE136076",
+        "GSE33269",
+        "GSE230850",
+        "GSE25878",
+        "GSE144476",
+        "GSE65032",
+        "GSE129133",
+        "GSE152536",
+        "GSE224161",
+        "GSE133652",
+        "GSE115906",
+        "GSE65577",
+        "GSE212142",
+        "GSE11763",
+        "GSE15221",
+        "GSE109586",
+        "GSE111110",
+        "GSE9497",
+        "GSE133237",
+        "GSE108034",
+        "GSE149392",
+        "GSE198588",
+        "GSE61536",
+        "GSE72695",
+        "GSE72578",
+        "GSE35732",
+        "GSE69931",
+        "GSE110201",
+        "GSE64548",
+        "GSE137042",
+        "GSE86308",
+        "GSE106463",
+        "GSE116149",
+        "GSE54253",
+        "GSE159125",
+        "GSE24416",
+        "GSE197409",
+        "GSE114095",
+        "GSE9868",
+        "GSE31686",
+        "GSE244803",
+        "GSE255053",
+        "GSE149774",
+        "GSE144971",
+        "GSE191025",
+        "GSE195649",
+        "GSE113718",
+        "GSE226629",
+        "GSE198587",
+        "GSE116026",
+        "GSE270631",
+        "GSE151754",
+        "GSE177479",
+        "GSE215426",
+        "GSE106461",
+        "GSE29535",
+        "GSE199366",
+        "GSE120729",
+        "GSE181725",
+        "GSE226027",
+        "GSE5267",
+        "GSE98993",
+        "GSE62364",
+        "GSE209877",
+        "GSE30564",
+        "GSE234587",
+        "GSE141653",
+        "GSE150047",
+        "GSE68982",
+        "GSE102288",
+        "GSE120727",
+        "GSE33797",
+        "GSE153026",
+        "GSE152924",
+        "GSE243024",
+        "GSE102459",
+        "GSE94316",
+        "GSE6785",
+        "GSE139990",
+        "GSE3414",
+        "GSE127079",
+        "GSE26941",
+        "GSE164175",
+        "GSE239393",
+        "GSE133239",
+        "GSE147643",
+        "GSE274341",
+        "GSE148125",
+        "GSE210626",
+        "GSE197459",
+        "GSE13592",
+        "GSE62136",
+        "GSE157454",
+        "GSE69627",
+        "GSE142069",
+        "GSE119856",
+        "GSE34404",
+        "GSE228948",
+        "GSE186984",
+        "GSE17029",
+        "GSE153775",
+        "GSE12249",
+        "GSE89292",
+        "GSE107375",
+        "GSE85248",
+        "GSE226631",
+        "GSE13251",
+        "GSE8099",
+        "GSE2878",
+        "GSE111333",
+        "GSE182536",
+        "GSE92289",
+        "GSE188985",
+        "GSE77807",
+        "GSE77499",
+        "GSE221211",
+        "GSE17919",
+        "GSE157966",
+        "GSE183744",
+        "GSE14967",
+        "GSE144826",
+        "GSE89555",
+        "GSE144743",
+        "GSE117656",
+        "GSE98992",
+        "GSE234585",
+        "GSE48089",
+        "GSE9724",
+        "GSE44831",
+        "GSE192756",
+        "GSE24086",
+        "GSE45172",
+        "GSE104223",
+        "GSE255057",
+        "GSE63369",
+        "GSE55265",
+        "GSE86254",
+        "GSE163432",
+        "GSE74819",
+        "GSE105126",
+        "GSE25879",
+        "GSE27937",
+        "GSE218998",
+        "GSE59844",
+        "GSE241467",
+        "GSE215359",
+        "GSE166258",
+        "GSE106464",
+        "GSE62132",
+        "GSE25433",
+        "GSE39485",
+        "GSE52859",
+        "GSE94274",
+        "GSE141759",
+        "GSE253390",
+        "GSE55843",
+        "GSE93545",
+        "GSE168974",
+        "GSE157709",
+        "GSE215427",
+        "GSE278976",
+        "GSE113582",
+        "GSE58340",
+        "GSE103042",
+        "GSE57439",
+        "GSE64688",
+        "GSE267361",
+        "GSE157457",
+        "GSE120658",
+        "GSE266399",
+        "GSE144486",
+        "GSE157456",
+        "GSE157420",
+        "GSE78771",
+        "GSE72447",
+        "GSE268068",
+        "GSE103036",
+        "GSE115155",
+        "GSE4582",
+        "GSE91188",
+        "GSE211626",
+        "GSE116306",
+        "GSE13560",
+        "GSE69188",
+        "GSE208560",
+        "GSE34877",
+        "GSE48514",
+        "GSE51739",
+        "GSE103401",
+        "GSE35083",
+        "GSE240643",
+        "GSE16463",
+        "GSE133653",
+        "GSE25642",
+        "GSE23565",
+        "GSE59015",
+        "GSE225340",
+        "GSE164459",
+        "GSE75295",
+        "GSE53176",
+        "GSE41567",
+        "GSE228461",
+        "GSE5555",
+        "GSE208757",
+        "GSE183526",
+        "GSE198287",
+        "GSE103034",
+        "GSE141760",
+        "GSE83667",
+        "GSE111593",
+        "GSE160924",
+        "GSE8784",
+        "GSE174791",
+        "GSE148655",
+        "GSE285040",
+        "GSE104114",
+        "GSE143901",
+        "GSE6356",
+        "GSE162550",
+        "GSE2369",
+        "GSE162535",
+        "GSE41873",
+        "GSE175931",
+        "GSE186109",
+        "GSE32211",
+        "GSE93664",
+        "GSE9861",
+        "GSE17603",
+        "GSE210627",
+        "GSE211599",
+        "GSE191332",
+        "GSE102695",
+        "GSE81197",
+        "GSE119650",
+        "GSE233473",
+        "GSE154317",
+        "GSE135005",
+        "GSE119152",
+        "GSE222586",
+        "GSE94273",
+        "GSE110994",
+        "GSE168817",
+        "GSE119850",
+        "GSE135822",
+        "GSE2900",
+        "GSE245735",
+        "GSE214535",
+        "GSE136046",
+        "GSE190497",
+        "GSE19468",
+        "GSE2265",
+        "GSE210010",
+        "GSE78689",
+        "GSE227672",
+        "GSE33385",
+        "GSE169752",
+        "GSE68667",
+        "GSE24579",
+        "GSE123495",
+        "GSE117538",
+        "GSE234586",
+        "GSE8789",
+        "GSE212894",
+        "GSE66189",
+        "GSE33795",
+        "GSE85263",
+        "GSE189151",
+        "GSE244806"
+    ],
+    "GARD:0010280": [
+        "GSE12578",
+        "GSE174340"
+    ],
+    "GARD:0008692": [
+        "GSE124842",
+        "GSE260585",
+        "GSE60847",
+        "GSE223836",
+        "GSE164312",
+        "GSE10235",
+        "GSE195627",
+        "GSE233583",
+        "GSE153118",
+        "GSE74833",
+        "GSE5168",
+        "GSE271603",
+        "GSE164702",
+        "GSE183625",
+        "GSE149443",
+        "GSE164460",
+        "GSE172513",
+        "GSE68805",
+        "GSE107791",
+        "GSE33995",
+        "GSE188162",
+        "GSE183165",
+        "GSE223137",
+        "GSE233855",
+        "GSE210776",
+        "GSE37191",
+        "GSE167545",
+        "GSE28574",
+        "GSE137180",
+        "GSE226083",
+        "GSE79702",
+        "GSE233572",
+        "GSE180561",
+        "GSE195625",
+        "GSE51341",
+        "GSE28642",
+        "GSE173557",
+        "GSE188322",
+        "GSE252959",
+        "GSE37074",
+        "GSE230753",
+        "GSE107790",
+        "GSE154920",
+        "GSE40869",
+        "GSE39017",
+        "GSE112619",
+        "GSE188161",
+        "GSE98155",
+        "GSE121764",
+        "GSE181046",
+        "GSE106464",
+        "GSE62088",
+        "GSE241920",
+        "GSE137027",
+        "GSE205290",
+        "GSE268598",
+        "GSE205600",
+        "GSE75107",
+        "GSE11288",
+        "GSE250589",
+        "GSE166179",
+        "GSE75108",
+        "GSE70210",
+        "GSE137980",
+        "GSE53294",
+        "GSE151701",
+        "GSE112620",
+        "GSE144218",
+        "GSE188319",
+        "GSE107792",
+        "GSE49847",
+        "GSE256410",
+        "GSE254863",
+        "GSE137801",
+        "GSE238120",
+        "GSE205292",
+        "GSE111256",
+        "GSE157084",
+        "GSE185427",
+        "GSE83602",
+        "GSE113891",
+        "GSE86494",
+        "GSE186318",
+        "GSE8092",
+        "GSE8802",
+        "GSE227049",
+        "GSE164643",
+        "GSE236540",
+        "GSE280578",
+        "GSE164263",
+        "GSE213739",
+        "GSE144317",
+        "GSE195626",
+        "GSE211925",
+        "GSE126289",
+        "GSE106462",
+        "GSE171510",
+        "GSE212531",
+        "GSE44873",
+        "GSE188687",
+        "GSE15841",
+        "GSE278812",
+        "GSE83604",
+        "GSE173378",
+        "GSE51075",
+        "GSE49385",
+        "GSE280580",
+        "GSE167914",
+        "GSE227394",
+        "GSE154175",
+        "GSE152683",
+        "GSE193240",
+        "GSE213893",
+        "GSE253318",
+        "GSE205280",
+        "GSE181924",
+        "GSE51336",
+        "GSE182807",
+        "GSE193238",
+        "GSE222063",
+        "GSE101753",
+        "GSE143500",
+        "GSE145049",
+        "GSE106461",
+        "GSE113382",
+        "GSE5017",
+        "GSE253857",
+        "GSE166159",
+        "GSE165259",
+        "GSE120661",
+        "GSE47900",
+        "GSE7461",
+        "GSE59725",
+        "GSE156196",
+        "GSE169144",
+        "GSE208093",
+        "GSE249605",
+        "GSE188320",
+        "GSE144540",
+        "GSE7807",
+        "GSE213034",
+        "GSE83603",
+        "GSE98589",
+        "GSE167202",
+        "GSE113973",
+        "GSE77754",
+        "GSE59697",
+        "GSE51334",
+        "GSE251784",
+        "GSE75105",
+        "GSE231873",
+        "GSE8906",
+        "GSE39524",
+        "GSE29579",
+        "GSE75438",
+        "GSE133283"
+    ],
+    "GARD:0021716": [
+        "GSE249240",
+        "GSE98342",
+        "GSE143466",
+        "GSE112118",
+        "GSE81345",
+        "GSE98383",
+        "GSE109824",
+        "GSE68631",
+        "GSE246985",
+        "GSE241849",
+        "GSE107170",
+        "GSE270625"
+    ],
+    "GARD:0007468": [
+        "GSE45639",
+        "GSE7819",
+        "GSE264236"
+    ],
+    "GARD:0018705": [
+        "GSE32268",
+        "GSE262896",
+        "GSE247955",
+        "GSE213991",
+        "GSE141435",
+        "GSE123281",
+        "GSE57431",
+        "GSE66148",
+        "GSE275956",
+        "GSE72391",
+        "GSE80149",
+        "GSE6520",
+        "GSE99999",
+        "GSE221853",
+        "GSE21547",
+        "GSE130500",
+        "GSE175866",
+        "GSE59787",
+        "GSE34918",
+        "GSE17043",
+        "GSE200196",
+        "GSE70245",
+        "GSE232763",
+        "GSE210521",
+        "GSE142101",
+        "GSE972",
+        "GSE195590",
+        "GSE182632",
+        "GSE188241",
+        "GSE212100",
+        "GSE44998",
+        "GSE165589",
+        "GSE147821",
+        "GSE63592",
+        "GSE153614",
+        "GSE137241",
+        "GSE196321",
+        "GSE75125",
+        "GSE150007",
+        "GSE135471",
+        "GSE181287",
+        "GSE152752",
+        "GSE161130",
+        "GSE145551",
+        "GSE142663",
+        "GSE129114",
+        "GSE30596",
+        "GSE224884",
+        "GSE166460",
+        "GSE115503",
+        "GSE281763",
+        "GSE195452",
+        "GSE128191",
+        "GSE117931",
+        "GSE44299",
+        "GSE139409",
+        "GSE11788",
+        "GSE42519",
+        "GSE164110",
+        "GSE34920",
+        "GSE246248",
+        "GSE197786",
+        "GSE261579",
+        "GSE163973",
+        "GSE156980",
+        "GSE246603",
+        "GSE180183",
+        "GSE111327",
+        "GSE44999",
+        "GSE255492",
+        "GSE151469",
+        "GSE220081",
+        "GSE228339",
+        "GSE230319",
+        "GSE196637",
+        "GSE173284",
+        "GSE203116",
+        "GSE30167",
+        "GSE121324",
+        "GSE45226",
+        "GSE229148",
+        "GSE187002",
+        "GSE53679",
+        "GSE105016",
+        "GSE205213",
+        "GSE215795",
+        "GSE89437",
+        "GSE130313",
+        "GSE44727",
+        "GSE156173",
+        "GSE202440",
+        "GSE267008",
+        "GSE161126",
+        "GSE242700",
+        "GSE202057",
+        "GSE212109",
+        "GSE199441",
+        "GSE202442",
+        "GSE77207",
+        "GSE232762",
+        "GSE205212",
+        "GSE192640",
+        "GSE102123",
+        "GSE65050",
+        "GSE138619",
+        "GSE66851",
+        "GSE44996",
+        "GSE20055",
+        "GSE78268",
+        "GSE270155",
+        "GSE256464",
+        "GSE228342",
+        "GSE250526",
+        "GSE94082",
+        "GSE216674",
+        "GSE150006",
+        "GSE81430",
+        "GSE195573",
+        "GSE97248",
+        "GSE202238",
+        "GSE83501",
+        "GSE202055",
+        "GSE81072",
+        "GSE224849",
+        "GSE165344",
+        "GSE185279",
+        "GSE61273",
+        "GSE85620",
+        "GSE272480",
+        "GSE39918",
+        "GSE211230",
+        "GSE107843",
+        "GSE151850",
+        "GSE275132",
+        "GSE281769",
+        "GSE137721",
+        "GSE181577",
+        "GSE19698",
+        "GSE63040",
+        "GSE9285",
+        "GSE12007",
+        "GSE15969",
+        "GSE125124",
+        "GSE79387",
+        "GSE62123",
+        "GSE201257",
+        "GSE115353",
+        "GSE89420",
+        "GSE137614",
+        "GSE196071",
+        "GSE63428",
+        "GSE18043",
+        "GSE23954",
+        "GSE212225",
+        "GSE252061",
+        "GSE230316",
+        "GSE174580",
+        "GSE83505",
+        "GSE96631",
+        "GSE3887",
+        "GSE237713",
+        "GSE160536",
+        "GSE145327",
+        "GSE107053",
+        "GSE76808",
+        "GSE264211",
+        "GSE180196",
+        "GSE74701",
+        "GSE82095",
+        "GSE186197",
+        "GSE202441",
+        "GSE32386",
+        "GSE243840",
+        "GSE48149",
+        "GSE236673",
+        "GSE151700",
+        "GSE230317",
+        "GSE155687",
+        "GSE194380",
+        "GSE214632",
+        "GSE100250",
+        "GSE255031",
+        "GSE14421",
+        "GSE175809",
+        "GSE147270",
+        "GSE140150",
+        "GSE130079",
+        "GSE100867",
+        "GSE166603",
+        "GSE22092",
+        "GSE56999",
+        "GSE184359",
+        "GSE184364",
+        "GSE175808",
+        "GSE103240",
+        "GSE99317",
+        "GSE68044",
+        "GSE241522",
+        "GSE180194",
+        "GSE68052",
+        "GSE42589",
+        "GSE136449",
+        "GSE228343",
+        "GSE137240",
+        "GSE80151",
+        "GSE144366",
+        "GSE24598",
+        "GSE57430",
+        "GSE68546",
+        "GSE261846",
+        "GSE253235",
+        "GSE101655",
+        "GSE34303",
+        "GSE180999",
+        "GSE197927",
+        "GSE89188",
+        "GSE230303",
+        "GSE181562",
+        "GSE202058",
+        "GSE95815",
+        "GSE59125",
+        "GSE205900",
+        "GSE219149",
+        "GSE121427",
+        "GSE11149",
+        "GSE249279",
+        "GSE161176",
+        "GSE104849",
+        "GSE115201",
+        "GSE81282",
+        "GSE64556",
+        "GSE180519",
+        "GSE126089",
+        "GSE62680",
+        "GSE250528",
+        "GSE207424",
+        "GSE61728",
+        "GSE65049",
+        "GSE263087",
+        "GSE50251",
+        "GSE241256",
+        "GSE246805",
+        "GSE267348",
+        "GSE149688",
+        "GSE109432",
+        "GSE217067",
+        "GSE104420",
+        "GSE221188",
+        "GSE153880",
+        "GSE168131",
+        "GSE221031",
+        "GSE80153",
+        "GSE138538",
+        "GSE143912",
+        "GSE218217",
+        "GSE108518",
+        "GSE87641",
+        "GSE75173",
+        "GSE61823",
+        "GSE23709",
+        "GSE21539",
+        "GSE183307",
+        "GSE166863",
+        "GSE260990",
+        "GSE110177",
+        "GSE217214",
+        "GSE42572",
+        "GSE8759",
+        "GSE51034",
+        "GSE215960",
+        "GSE186961",
+        "GSE152755",
+        "GSE106358",
+        "GSE40839",
+        "GSE52220",
+        "GSE202195",
+        "GSE192906",
+        "GSE216759",
+        "GSE26980",
+        "GSE24409",
+        "GSE52357",
+        "GSE32413",
+        "GSE161510",
+        "GSE221330",
+        "GSE263169",
+        "GSE87750",
+        "GSE27159",
+        "GSE68047",
+        "GSE274407",
+        "GSE210015",
+        "GSE264508",
+        "GSE51297",
+        "GSE184622",
+        "GSE108199",
+        "GSE70237",
+        "GSE163768",
+        "GSE21511",
+        "GSE189381",
+        "GSE228194",
+        "GSE19664",
+        "GSE232516",
+        "GSE204731",
+        "GSE199440",
+        "GSE213132",
+        "GSE246806",
+        "GSE127469",
+        "GSE163757",
+        "GSE125711",
+        "GSE117304",
+        "GSE219153",
+        "GSE232432",
+        "GSE265932",
+        "GSE113074",
+        "GSE45536",
+        "GSE8066",
+        "GSE212234",
+        "GSE47919",
+        "GSE104950",
+        "GSE76809",
+        "GSE114961",
+        "GSE61674",
+        "GSE174598",
+        "GSE178823",
+        "GSE263168",
+        "GSE182783",
+        "GSE277165",
+        "GSE166861",
+        "GSE83317",
+        "GSE89436",
+        "GSE103822",
+        "GSE68045",
+        "GSE95780",
+        "GSE34904",
+        "GSE168303",
+        "GSE25256",
+        "GSE216125",
+        "GSE67338",
+        "GSE177489",
+        "GSE57001",
+        "GSE32339",
+        "GSE223901",
+        "GSE89670",
+        "GSE175767",
+        "GSE111753",
+        "GSE205903",
+        "GSE209635",
+        "GSE168312",
+        "GSE174708",
+        "GSE67073",
+        "GSE63895",
+        "GSE35506",
+        "GSE256420",
+        "GSE66850",
+        "GSE119962",
+        "GSE75355",
+        "GSE230315",
+        "GSE115149",
+        "GSE261828",
+        "GSE100907",
+        "GSE7007",
+        "GSE143911",
+        "GSE107516",
+        "GSE205904",
+        "GSE93134",
+        "GSE77114",
+        "GSE252139",
+        "GSE149369",
+        "GSE272868",
+        "GSE180546",
+        "GSE192645",
+        "GSE241499",
+        "GSE143910",
+        "GSE80130",
+        "GSE94914",
+        "GSE24403",
+        "GSE2295",
+        "GSE136732",
+        "GSE80335",
+        "GSE244473",
+        "GSE134532",
+        "GSE157538",
+        "GSE64513",
+        "GSE231691",
+        "GSE232163",
+        "GSE172069",
+        "GSE141106",
+        "GSE39346",
+        "GSE242157",
+        "GSE208184",
+        "GSE152599",
+        "GSE109137",
+        "GSE194430",
+        "GSE84666",
+        "GSE44297",
+        "GSE112072",
+        "GSE13002",
+        "GSE149884",
+        "GSE33581",
+        "GSE35148",
+        "GSE263091",
+        "GSE148699",
+        "GSE198561",
+        "GSE230350",
+        "GSE121825",
+        "GSE57518",
+        "GSE222639",
+        "GSE108517",
+        "GSE77272",
+        "GSE41121",
+        "GSE45491",
+        "GSE250450",
+        "GSE53203",
+        "GSE17312",
+        "GSE202196",
+        "GSE211906",
+        "GSE216492",
+        "GSE175095",
+        "GSE234616",
+        "GSE92764",
+        "GSE91377",
+        "GSE142309",
+        "GSE139859",
+        "GSE72985",
+        "GSE143395",
+        "GSE196007",
+        "GSE24410",
+        "GSE81293",
+        "GSE243834",
+        "GSE223900",
+        "GSE225890",
+        "GSE169654",
+        "GSE283071",
+        "GSE80334",
+        "GSE185119",
+        "GSE211660",
+        "GSE186198",
+        "GSE184227",
+        "GSE121131",
+        "GSE261205",
+        "GSE143913",
+        "GSE239305",
+        "GSE150709",
+        "GSE57505",
+        "GSE126087",
+        "GSE206745",
+        "GSE125362",
+        "GSE4445",
+        "GSE9451",
+        "GSE83327",
+        "GSE59785",
+        "GSE23741",
+        "GSE241903",
+        "GSE122305",
+        "GSE178805",
+        "GSE278072",
+        "GSE237881",
+        "GSE217212",
+        "GSE282770",
+        "GSE224158",
+        "GSE142752",
+        "GSE69108",
+        "GSE205902",
+        "GSE46561",
+        "GSE250247",
+        "GSE122714",
+        "GSE67555",
+        "GSE206903",
+        "GSE136731",
+        "GSE201378",
+        "GSE133014",
+        "GSE210139",
+        "GSE190462",
+        "GSE223104",
+        "GSE195519",
+        "GSE109267",
+        "GSE92763",
+        "GSE29742",
+        "GSE120409",
+        "GSE46591",
+        "GSE102553",
+        "GSE47407",
+        "GSE46387",
+        "GSE162035",
+        "GSE140247",
+        "GSE14340",
+        "GSE226566",
+        "GSE113297",
+        "GSE127269",
+        "GSE62117",
+        "GSE246672",
+        "GSE181549",
+        "GSE161531",
+        "GSE232560",
+        "GSE195730",
+        "GSE124075",
+        "GSE177517",
+        "GSE80663",
+        "GSE216138",
+        "GSE182402",
+        "GSE202649",
+        "GSE217298",
+        "GSE67786",
+        "GSE11482",
+        "GSE18690",
+        "GSE180998",
+        "GSE105145",
+        "GSE85636",
+        "GSE104174",
+        "GSE144311",
+        "GSE66032",
+        "GSE119939",
+        "GSE80662",
+        "GSE50643",
+        "GSE55427",
+        "GSE178364",
+        "GSE45968",
+        "GSE73355",
+        "GSE76806",
+        "GSE80150",
+        "GSE201511",
+        "GSE71991",
+        "GSE60313",
+        "GSE214996",
+        "GSE139273",
+        "GSE234071",
+        "GSE162044",
+        "GSE41122",
+        "GSE17914",
+        "GSE198491",
+        "GSE183319",
+        "GSE114894",
+        "GSE34142",
+        "GSE21517",
+        "GSE228340",
+        "GSE128169",
+        "GSE269954",
+        "GSE150592",
+        "GSE89910",
+        "GSE94521",
+        "GSE211902",
+        "GSE28875",
+        "GSE184356",
+        "GSE172742",
+        "GSE62816",
+        "GSE27176",
+        "GSE275825",
+        "GSE163740",
+        "GSE141107",
+        "GSE33463",
+        "GSE262558",
+        "GSE252573",
+        "GSE276561",
+        "GSE123142",
+        "GSE165590",
+        "GSE81717",
+        "GSE10934",
+        "GSE181000",
+        "GSE68698",
+        "GSE103849",
+        "GSE168179",
+        "GSE56430",
+        "GSE37189",
+        "GSE211903",
+        "GSE174949",
+        "GSE137472",
+        "GSE146088",
+        "GSE239434",
+        "GSE226374",
+        "GSE237970",
+        "GSE120434",
+        "GSE262095",
+        "GSE111153",
+        "GSE64752",
+        "GSE282652",
+        "GSE248221",
+        "GSE198297",
+        "GSE215109",
+        "GSE145306",
+        "GSE146092",
+        "GSE253865",
+        "GSE54720",
+        "GSE199581",
+        "GSE164327",
+        "GSE249075",
+        "GSE11029",
+        "GSE135237",
+        "GSE104141",
+        "GSE121507",
+        "GSE200674",
+        "GSE179986",
+        "GSE108521",
+        "GSE255577",
+        "GSE99551",
+        "GSE45535",
+        "GSE2052",
+        "GSE131737",
+        "GSE52358",
+        "GSE178969",
+        "GSE210395",
+        "GSE230176",
+        "GSE70751",
+        "GSE33767",
+        "GSE222213",
+        "GSE196592",
+        "GSE73180",
+        "GSE266652",
+        "GSE149860",
+        "GSE178434",
+        "GSE182302",
+        "GSE223132",
+        "GSE162889",
+        "GSE116173",
+        "GSE29634",
+        "GSE186696",
+        "GSE206048",
+        "GSE168200",
+        "GSE22989",
+        "GSE199439",
+        "GSE115487",
+        "GSE223750",
+        "GSE169529",
+        "GSE116140",
+        "GSE62247",
+        "GSE95065",
+        "GSE153898",
+        "GSE236680",
+        "GSE162973",
+        "GSE122334",
+        "GSE4680",
+        "GSE45893",
+        "GSE6460",
+        "GSE286314",
+        "GSE247804",
+        "GSE6868",
+        "GSE140319",
+        "GSE53678",
+        "GSE206008",
+        "GSE45537",
+        "GSE153121",
+        "GSE2841",
+        "GSE165303",
+        "GSE187102",
+        "GSE89435",
+        "GSE137219",
+        "GSE229532",
+        "GSE120678",
+        "GSE119537",
+        "GSE121526",
+        "GSE80393",
+        "GSE242826",
+        "GSE81026",
+        "GSE72268",
+        "GSE41123",
+        "GSE75356",
+        "GSE77363",
+        "GSE68898",
+        "GSE125141",
+        "GSE84430",
+        "GSE80689",
+        "GSE210394",
+        "GSE246769",
+        "GSE213382",
+        "GSE268988",
+        "GSE34502",
+        "GSE76886",
+        "GSE151649",
+        "GSE109686",
+        "GSE202059",
+        "GSE71995",
+        "GSE222552",
+        "GSE263778",
+        "GSE157840",
+        "GSE183309",
+        "GSE162966",
+        "GSE71998",
+        "GSE41179",
+        "GSE18477",
+        "GSE28094",
+        "GSE23530",
+        "GSE80165",
+        "GSE217197",
+        "GSE125143",
+        "GSE61510",
+        "GSE137462",
+        "GSE211899",
+        "GSE169322",
+        "GSE211901",
+        "GSE165588",
+        "GSE202671",
+        "GSE9339",
+        "GSE188163",
+        "GSE137975",
+        "GSE195589",
+        "GSE117754",
+        "GSE223614",
+        "GSE263086",
+        "GSE226331",
+        "GSE42548",
+        "GSE245175",
+        "GSE11130",
+        "GSE169280",
+        "GSE178834",
+        "GSE176731",
+        "GSE110872",
+        "GSE100538",
+        "GSE57810",
+        "GSE24730",
+        "GSE166625",
+        "GSE121329",
+        "GSE124070",
+        "GSE53677",
+        "GSE9894",
+        "GSE134310",
+        "GSE42254",
+        "GSE262042",
+        "GSE250527",
+        "GSE199158",
+        "GSE132857",
+        "GSE133141",
+        "GSE176055",
+        "GSE104163",
+        "GSE60394",
+        "GSE1588",
+        "GSE137276",
+        "GSE121429",
+        "GSE30716",
+        "GSE212793",
+        "GSE197631",
+        "GSE235864",
+        "GSE14391",
+        "GSE72815",
+        "GSE11979",
+        "GSE179984",
+        "GSE250387",
+        "GSE131136",
+        "GSE124312",
+        "GSE206197",
+        "GSE230318",
+        "GSE119534",
+        "GSE252428",
+        "GSE104473",
+        "GSE210251",
+        "GSE108943",
+        "GSE149072",
+        "GSE111766",
+        "GSE185255",
+        "GSE157575",
+        "GSE138669",
+        "GSE80152",
+        "GSE54719",
+        "GSE58474",
+        "GSE38381",
+        "GSE78002",
+        "GSE269610",
+        "GSE69311",
+        "GSE141664",
+        "GSE45159",
+        "GSE68776",
+        "GSE27165",
+        "GSE223615",
+        "GSE239592",
+        "GSE67087",
+        "GSE246807",
+        "GSE179153",
+        "GSE211904",
+        "GSE100905",
+        "GSE69110",
+        "GSE28874",
+        "GSE117305",
+        "GSE94340",
+        "GSE188990",
+        "GSE250009",
+        "GSE124579",
+        "GSE99382",
+        "GSE127245",
+        "GSE114464",
+        "GSE119498",
+        "GSE50059",
+        "GSE205901",
+        "GSE156031",
+        "GSE115348",
+        "GSE189544",
+        "GSE131293",
+        "GSE78003",
+        "GSE3886",
+        "GSE254716",
+        "GSE264187",
+        "GSE163961",
+        "GSE205214",
+        "GSE226375",
+        "GSE178299",
+        "GSE141439",
+        "GSE156146",
+        "GSE80509",
+        "GSE186707",
+        "GSE90683",
+        "GSE45223",
+        "GSE180187",
+        "GSE163826",
+        "GSE176965",
+        "GSE2710",
+        "GSE96629",
+        "GSE58916",
+        "GSE77513",
+        "GSE34827",
+        "GSE216136",
+        "GSE211478",
+        "GSE131793",
+        "GSE85621",
+        "GSE16249",
+        "GSE163771",
+        "GSE95814",
+        "GSE80288",
+        "GSE261227",
+        "GSE67124",
+        "GSE178784",
+        "GSE161281",
+        "GSE195581",
+        "GSE146809",
+        "GSE89434",
+        "GSE19465",
+        "GSE261603",
+        "GSE216760",
+        "GSE163907",
+        "GSE17448",
+        "GSE175114",
+        "GSE284063",
+        "GSE35218",
+        "GSE238166",
+        "GSE182721",
+        "GSE207423",
+        "GSE93698",
+        "GSE171532",
+        "GSE161579",
+        "GSE261358",
+        "GSE168133",
+        "GSE69109",
+        "GSE226376",
+        "GSE221190",
+        "GSE102864",
+        "GSE79928",
+        "GSE226565",
+        "GSE20399",
+        "GSE19617",
+        "GSE126880",
+        "GSE44997",
+        "GSE173696",
+        "GSE192676",
+        "GSE34208",
+        "GSE5658",
+        "GSE125140",
+        "GSE99636",
+        "GSE278071",
+        "GSE236674",
+        "GSE206128",
+        "GSE253089",
+        "GSE193097",
+        "GSE198492",
+        "GSE117929",
+        "GSE10360",
+        "GSE240190",
+        "GSE46791",
+        "GSE131155",
+        "GSE193815",
+        "GSE212226",
+        "GSE108506",
+        "GSE113736",
+        "GSE95812",
+        "GSE8368",
+        "GSE205436",
+        "GSE127795",
+        "GSE213728",
+        "GSE106219",
+        "GSE228341",
+        "GSE121659",
+        "GSE133009",
+        "GSE135851",
+        "GSE4385",
+        "GSE102542",
+        "GSE124073",
+        "GSE231693",
+        "GSE244781",
+        "GSE175647",
+        "GSE108515",
+        "GSE1822",
+        "GSE154483",
+        "GSE106676",
+        "GSE120936",
+        "GSE58613",
+        "GSE183305",
+        "GSE240009",
+        "GSE46150",
+        "GSE39540",
+        "GSE202056",
+        "GSE55964",
+        "GSE134768",
+        "GSE129801",
+        "GSE117844",
+        "GSE208250",
+        "GSE150582",
+        "GSE12493",
+        "GSE268765",
+        "GSE41744",
+        "GSE108230",
+        "GSE184363",
+        "GSE264288",
+        "GSE202198",
+        "GSE183308",
+        "GSE163199",
+        "GSE127260",
+        "GSE38066",
+        "GSE202197",
+        "GSE140193",
+        "GSE126088",
+        "GSE30419",
+        "GSE157356",
+        "GSE161120",
+        "GSE130953",
+        "GSE109350",
+        "GSE108918",
+        "GSE68101",
+        "GSE80107",
+        "GSE44257",
+        "GSE231694",
+        "GSE61206",
+        "GSE215977",
+        "GSE169516",
+        "GSE181561",
+        "GSE172029",
+        "GSE160312",
+        "GSE219151",
+        "GSE57064",
+        "GSE262468",
+        "GSE214088",
+        "GSE250370",
+        "GSE19987",
+        "GSE92333",
+        "GSE44537",
+        "GSE181957",
+        "GSE222566",
+        "GSE120200",
+        "GSE68636",
+        "GSE220475",
+        "GSE198493",
+        "GSE115140",
+        "GSE121318",
+        "GSE99933",
+        "GSE46792",
+        "GSE45485",
+        "GSE252615",
+        "GSE205446",
+        "GSE50487",
+        "GSE255684",
+        "GSE137227",
+        "GSE100998",
+        "GSE185394",
+        "GSE261486",
+        "GSE185669",
+        "GSE159354",
+        "GSE255493",
+        "GSE136057",
+        "GSE254500",
+        "GSE235280",
+        "GSE11028",
+        "GSE55173",
+        "GSE43469",
+        "GSE205448",
+        "GSE153011",
+        "GSE196070",
+        "GSE103402",
+        "GSE100793",
+        "GSE130955",
+        "GSE252425",
+        "GSE92765",
+        "GSE156310",
+        "GSE213614",
+        "GSE120920",
+        "GSE132771",
+        "GSE36474",
+        "GSE282697",
+        "GSE193007",
+        "GSE39191",
+        "GSE164108",
+        "GSE57003",
+        "GSE282901",
+        "GSE57125",
+        "GSE146478",
+        "GSE81292",
+        "GSE243072",
+        "GSE226760",
+        "GSE176101",
+        "GSE215841",
+        "GSE68040",
+        "GSE278511",
+        "GSE255060",
+        "GSE229531",
+        "GSE214099",
+        "GSE207425",
+        "GSE140636",
+        "GSE75352",
+        "GSE279710",
+        "GSE125145",
+        "GSE44295",
+        "GSE76885",
+        "GSE196544",
+        "GSE246685",
+        "GSE132869",
+        "GSE14038",
+        "GSE221125",
+        "GSE61695",
+        "GSE176634",
+        "GSE190305",
+        "GSE125480",
+        "GSE56308",
+        "GSE79988",
+        "GSE12274",
+        "GSE13129",
+        "GSE222916",
+        "GSE196386",
+        "GSE222212",
+        "GSE225530",
+        "GSE32308",
+        "GSE73674",
+        "GSE78890",
+        "GSE22356",
+        "GSE154972",
+        "GSE66634",
+        "GSE178687",
+        "GSE11027",
+        "GSE117928",
+        "GSE217199",
+        "GSE217757",
+        "GSE121044",
+        "GSE28199",
+        "GSE71999",
+        "GSE28876",
+        "GSE34912",
+        "GSE63058",
+        "GSE200689",
+        "GSE166262",
+        "GSE103748",
+        "GSE58095",
+        "GSE52456",
+        "GSE108221",
+        "GSE174572",
+        "GSE273556",
+        "GSE146093",
+        "GSE168399",
+        "GSE115488",
+        "GSE125707",
+        "GSE182329",
+        "GSE101661",
+        "GSE80252",
+        "GSE198562",
+        "GSE135832",
+        "GSE183306",
+        "GSE61755",
+        "GSE100212",
+        "GSE207592",
+        "GSE139334",
+        "GSE68039",
+        "GSE55036",
+        "GSE58476",
+        "GSE42678",
+        "GSE72322",
+        "GSE274096",
+        "GSE223616",
+        "GSE161565",
+        "GSE275013",
+        "GSE213390",
+        "GSE85598",
+        "GSE226568",
+        "GSE56957",
+        "GSE185592",
+        "GSE83400",
+        "GSE182300",
+        "GSE81294",
+        "GSE55967",
+        "GSE216920",
+        "GSE125142",
+        "GSE75748",
+        "GSE228335",
+        "GSE90711",
+        "GSE10454",
+        "GSE262111",
+        "GSE63903",
+        "GSE52227",
+        "GSE118682",
+        "GSE186770",
+        "GSE107968",
+        "GSE222042",
+        "GSE170335",
+        "GSE263085",
+        "GSE175811",
+        "GSE234987",
+        "GSE155691",
+        "GSE101909",
+        "GSE77364",
+        "GSE31205",
+        "GSE198231",
+        "GSE172066",
+        "GSE64000",
+        "GSE47162",
+        "GSE95813",
+        "GSE211664",
+        "GSE243814",
+        "GSE192985",
+        "GSE165826",
+        "GSE116110",
+        "GSE208369",
+        "GSE223103",
+        "GSE11356",
+        "GSE161143",
+        "GSE102552",
+        "GSE252592",
+        "GSE139168",
+        "GSE126457",
+        "GSE106325",
+        "GSE65405",
+        "GSE65336",
+        "GSE44296",
+        "GSE258835",
+        "GSE75351",
+        "GSE242228",
+        "GSE173251",
+        "GSE162238",
+        "GSE131688",
+        "GSE261748",
+        "GSE211900",
+        "GSE142337",
+        "GSE190002",
+        "GSE200486",
+        "GSE136448",
+        "GSE125710",
+        "GSE76807",
+        "GSE263084",
+        "GSE186199",
+        "GSE182301",
+        "GSE218625",
+        "GSE162550",
+        "GSE97851",
+        "GSE181228",
+        "GSE70353",
+        "GSE75354",
+        "GSE146481",
+        "GSE1724",
+        "GSE261360",
+        "GSE191223",
+        "GSE163960",
+        "GSE25501",
+        "GSE249550",
+        "GSE130526",
+        "GSE123686",
+        "GSE172059",
+        "GSE145048",
+        "GSE121428",
+        "GSE231692",
+        "GSE235534",
+        "GSE138905",
+        "GSE183002",
+        "GSE47616",
+        "GSE86212",
+        "GSE152906",
+        "GSE125709",
+        "GSE155690",
+        "GSE195583",
+        "GSE101746",
+        "GSE255790",
+        "GSE121527",
+        "GSE166246",
+        "GSE197513",
+        "GSE224197",
+        "GSE174446",
+        "GSE149855",
+        "GSE172028",
+        "GSE66321",
+        "GSE187115",
+        "GSE175379",
+        "GSE270493",
+        "GSE32245",
+        "GSE151628",
+        "GSE52852",
+        "GSE67429",
+        "GSE121331",
+        "GSE35560",
+        "GSE16031",
+        "GSE11030",
+        "GSE255059",
+        "GSE136046",
+        "GSE84428",
+        "GSE220680",
+        "GSE178804",
+        "GSE174571",
+        "GSE210396",
+        "GSE129547",
+        "GSE127268",
+        "GSE95004",
+        "GSE75353",
+        "GSE99702",
+        "GSE109136",
+        "GSE86984",
+        "GSE87781",
+        "GSE144442",
+        "GSE141108",
+        "GSE130082",
+        "GSE165117",
+        "GSE138596",
+        "GSE155773",
+        "GSE71958",
+        "GSE63896",
+        "GSE198494",
+        "GSE252046",
+        "GSE166458",
+        "GSE61825",
+        "GSE154332",
+        "GSE144625"
+    ],
+    "GARD:0005575": [
+        "GSE89991",
+        "GSE174043",
+        "GSE285295",
+        "GSE285289",
+        "GSE285285",
+        "GSE285284",
+        "GSE106210",
+        "GSE102992",
+        "GSE277484",
+        "GSE81541",
+        "GSE43575",
+        "GSE41759",
+        "GSE285305",
+        "GSE269225",
+        "GSE285300",
+        "GSE249891",
+        "GSE56136",
+        "GSE190334",
+        "GSE285306",
+        "GSE25028",
+        "GSE285302",
+        "GSE190336",
+        "GSE145159",
+        "GSE103249",
+        "GSE178687",
+        "GSE243185",
+        "GSE285293",
+        "GSE139524",
+        "GSE38541",
+        "GSE232183",
+        "GSE190337",
+        "GSE117283",
+        "GSE152288",
+        "GSE250009",
+        "GSE120624",
+        "GSE14984",
+        "GSE22188"
+    ],
+    "GARD:0005786": [
+        "GSE281064",
+        "GSE77685",
+        "GSE160402",
+        "GSE125654",
+        "GSE187775",
+        "GSE76220",
+        "GSE86223",
+        "GSE121825",
+        "GSE189988",
+        "GSE18632",
+        "GSE139900",
+        "GSE242978",
+        "GSE215657",
+        "GSE99843",
+        "GSE287862",
+        "GSE106803",
+        "GSE234243",
+        "GSE198767",
+        "GSE187352",
+        "GSE218865",
+        "GSE106443",
+        "GSE96047",
+        "GSE21450",
+        "GSE250633",
+        "GSE97106",
+        "GSE76698",
+        "GSE51685",
+        "GSE272626",
+        "GSE122647",
+        "GSE120374",
+        "GSE200530",
+        "GSE163560",
+        "GSE3307",
+        "GSE39644",
+        "GSE289053",
+        "GSE40328",
+        "GSE122640",
+        "GSE122069",
+        "GSE166615",
+        "GSE136409",
+        "GSE114510",
+        "GSE142654",
+        "GSE209696",
+        "GSE68502",
+        "GSE102902",
+        "GSE187713",
+        "GSE69450",
+        "GSE61321",
+        "GSE77700",
+        "GSE116622",
+        "GSE271011",
+        "GSE52917",
+        "GSE77681",
+        "GSE102562",
+        "GSE2039",
+        "GSE49657",
+        "GSE9397",
+        "GSE101768",
+        "GSE27371",
+        "GSE263117",
+        "GSE833",
+        "GSE226291",
+        "GSE130763",
+        "GSE68605",
+        "GSE283702",
+        "GSE118336",
+        "GSE132972",
+        "GSE226753",
+        "GSE233588",
+        "GSE242473",
+        "GSE290436",
+        "GSE98289",
+        "GSE56500",
+        "GSE271030",
+        "GSE235312",
+        "GSE172484",
+        "GSE187703",
+        "GSE261848",
+        "GSE68607",
+        "GSE115262",
+        "GSE224580",
+        "GSE34113",
+        "GSE209424",
+        "GSE218226",
+        "GSE208897",
+        "GSE147607",
+        "GSE12525",
+        "GSE200037",
+        "GSE153577",
+        "GSE1060",
+        "GSE276214",
+        "GSE77703",
+        "GSE61324",
+        "GSE156222",
+        "GSE253372",
+        "GSE174841",
+        "GSE218863",
+        "GSE291052",
+        "GSE124834",
+        "GSE122261",
+        "GSE73379",
+        "GSE126801",
+        "GSE187737",
+        "GSE246397",
+        "GSE86038",
+        "GSE117873",
+        "GSE101067",
+        "GSE249071",
+        "GSE223747",
+        "GSE239901",
+        "GSE251940",
+        "GSE121789",
+        "GSE224582",
+        "GSE64582",
+        "GSE86462",
+        "GSE52935",
+        "GSE242475",
+        "GSE187462",
+        "GSE111106",
+        "GSE95842",
+        "GSE145675",
+        "GSE166307",
+        "GSE113579",
+        "GSE205718",
+        "GSE142730",
+        "GSE143680",
+        "GSE158264",
+        "GSE52670",
+        "GSE101686",
+        "GSE28253",
+        "GSE125125",
+        "GSE10953",
+        "GSE86224",
+        "GSE199197",
+        "GSE281403",
+        "GSE173524",
+        "GSE147784",
+        "GSE118620",
+        "GSE147288",
+        "GSE16361",
+        "GSE80974",
+        "GSE182718",
+        "GSE133047",
+        "GSE90913",
+        "GSE3343",
+        "GSE187767",
+        "GSE86218",
+        "GSE40438",
+        "GSE134994",
+        "GSE245303",
+        "GSE54409",
+        "GSE242766",
+        "GSE196843",
+        "GSE115259",
+        "GSE290437",
+        "GSE219884",
+        "GSE151997",
+        "GSE187543",
+        "GSE215424",
+        "GSE249484",
+        "GSE148604",
+        "GSE250455",
+        "GSE157467",
+        "GSE242360",
+        "GSE52668",
+        "GSE49023",
+        "GSE272624",
+        "GSE78730",
+        "GSE212761",
+        "GSE145676",
+        "GSE268371",
+        "GSE263048",
+        "GSE112676",
+        "GSE60424",
+        "GSE212422",
+        "GSE7441",
+        "GSE135349",
+        "GSE196021",
+        "GSE216294",
+        "GSE113924",
+        "GSE157714",
+        "GSE234246",
+        "GSE273052",
+        "GSE242472",
+        "GSE148097",
+        "GSE155700",
+        "GSE219278",
+        "GSE212630",
+        "GSE153960",
+        "GSE39642",
+        "GSE18920",
+        "GSE212133",
+        "GSE256070",
+        "GSE166712",
+        "GSE3305",
+        "GSE235448",
+        "GSE245520",
+        "GSE203580",
+        "GSE251822",
+        "GSE125653",
+        "GSE40649",
+        "GSE143570",
+        "GSE189470",
+        "GSE52946",
+        "GSE128165",
+        "GSE187929",
+        "GSE242474",
+        "GSE209201",
+        "GSE261875",
+        "GSE242770",
+        "GSE290441",
+        "GSE186757",
+        "GSE187695",
+        "GSE56926",
+        "GSE188054",
+        "GSE52671",
+        "GSE187612",
+        "GSE26276",
+        "GSE291695",
+        "GSE233881",
+        "GSE50178",
+        "GSE86043",
+        "GSE125655",
+        "GSE157185",
+        "GSE126541",
+        "GSE252050",
+        "GSE189525",
+        "GSE264018",
+        "GSE40710",
+        "GSE143558",
+        "GSE188133",
+        "GSE51741",
+        "GSE93939",
+        "GSE139384",
+        "GSE135611",
+        "GSE101687",
+        "GSE37640",
+        "GSE112931",
+        "GSE161680",
+        "GSE232929",
+        "GSE116613",
+        "GSE188159",
+        "GSE282665",
+        "GSE224138",
+        "GSE52803",
+        "GSE52937",
+        "GSE215679",
+        "GSE244263",
+        "GSE215689",
+        "GSE4390",
+        "GSE230064",
+        "GSE118347",
+        "GSE61320",
+        "GSE7251",
+        "GSE156413",
+        "GSE52959",
+        "GSE77704",
+        "GSE255022",
+        "GSE69166",
+        "GSE187594",
+        "GSE239403",
+        "GSE234783",
+        "GSE4595",
+        "GSE252683",
+        "GSE77101",
+        "GSE85554",
+        "GSE52898",
+        "GSE221381",
+        "GSE26070",
+        "GSE248404",
+        "GSE213844",
+        "GSE203578",
+        "GSE173838",
+        "GSE103607",
+        "GSE264012",
+        "GSE171714",
+        "GSE16360",
+        "GSE40652",
+        "GSE187264",
+        "GSE19332",
+        "GSE37148",
+        "GSE252875",
+        "GSE187876",
+        "GSE213125",
+        "GSE67196",
+        "GSE219279",
+        "GSE218864",
+        "GSE152983",
+        "GSE150397",
+        "GSE100505",
+        "GSE219759",
+        "GSE128647",
+        "GSE214718",
+        "GSE22482",
+        "GSE65973",
+        "GSE80093",
+        "GSE271039",
+        "GSE20894",
+        "GSE164674",
+        "GSE234245",
+        "GSE144640",
+        "GSE161199",
+        "GSE219280",
+        "GSE292832",
+        "GSE220705",
+        "GSE139144",
+        "GSE77699",
+        "GSE187084",
+        "GSE252793",
+        "GSE261670",
+        "GSE103225",
+        "GSE244021",
+        "GSE200474",
+        "GSE110492",
+        "GSE187508",
+        "GSE232587",
+        "GSE135075",
+        "GSE212134",
+        "GSE162028",
+        "GSE180410",
+        "GSE86040",
+        "GSE189417",
+        "GSE212131",
+        "GSE124439",
+        "GSE112680",
+        "GSE148901",
+        "GSE219408",
+        "GSE138592",
+        "GSE206330",
+        "GSE102903",
+        "GSE160193",
+        "GSE52202",
+        "GSE179819",
+        "GSE187829",
+        "GSE68608",
+        "GSE217625",
+        "GSE2400",
+        "GSE293662",
+        "GSE269925",
+        "GSE100829",
+        "GSE193962",
+        "GSE221077",
+        "GSE109177",
+        "GSE51684",
+        "GSE224578",
+        "GSE133323",
+        "GSE260532",
+        "GSE156202",
+        "GSE147544",
+        "GSE55507",
+        "GSE107375",
+        "GSE43879",
+        "GSE219951",
+        "GSE187463",
+        "GSE101046",
+        "GSE187622",
+        "GSE262674",
+        "GSE143566",
+        "GSE122648",
+        "GSE244306",
+        "GSE171992",
+        "GSE40651",
+        "GSE112681",
+        "GSE100188",
+        "GSE215569",
+        "GSE156542",
+        "GSE183483",
+        "GSE153712",
+        "GSE187790",
+        "GSE234297",
+        "GSE242209",
+        "GSE95810",
+        "GSE162943",
+        "GSE39643",
+        "GSE125652",
+        "GSE290359",
+        "GSE73492",
+        "GSE52936",
+        "GSE52673",
+        "GSE151826",
+        "GSE157713",
+        "GSE168491",
+        "GSE112629",
+        "GSE164675",
+        "GSE223834",
+        "GSE115130",
+        "GSE254208",
+        "GSE142504",
+        "GSE125424",
+        "GSE160133",
+        "GSE187257",
+        "GSE212423",
+        "GSE214017",
+        "GSE126542",
+        "GSE203579",
+        "GSE111148",
+        "GSE86041",
+        "GSE27201",
+        "GSE101688",
+        "GSE105811",
+        "GSE287769",
+        "GSE188037",
+        "GSE80735",
+        "GSE56808",
+        "GSE19519",
+        "GSE192755",
+        "GSE187580",
+        "GSE101391",
+        "GSE106386",
+        "GSE56503",
+        "GSE174332",
+        "GSE43294",
+        "GSE254209",
+        "GSE183204",
+        "GSE167557",
+        "GSE188100",
+        "GSE101590",
+        "GSE77720",
+        "GSE268090",
+        "GSE27218",
+        "GSE87385",
+        "GSE248515",
+        "GSE6483",
+        "GSE86227",
+        "GSE145214",
+        "GSE101097",
+        "GSE95659",
+        "GSE184484",
+        "GSE215364",
+        "GSE130604",
+        "GSE21993",
+        "GSE229095",
+        "GSE246462",
+        "GSE143573",
+        "GSE260913",
+        "GSE226699",
+        "GSE7950",
+        "GSE259432",
+        "GSE111434",
+        "GSE42091",
+        "GSE122649",
+        "GSE230127",
+        "GSE271156",
+        "GSE98288",
+        "GSE94888",
+        "GSE101591",
+        "GSE196022",
+        "GSE213091",
+        "GSE219201",
+        "GSE215363",
+        "GSE239611",
+        "GSE33855",
+        "GSE123172",
+        "GSE83484",
+        "GSE7493",
+        "GSE64583",
+        "GSE219277",
+        "GSE83226",
+        "GSE275999",
+        "GSE52672",
+        "GSE187630",
+        "GSE178693",
+        "GSE225648",
+        "GSE212424",
+        "GSE102563",
+        "GSE111031",
+        "GSE146141",
+        "GSE61322",
+        "GSE121519",
+        "GSE196219",
+        "GSE254069",
+        "GSE43308",
+        "GSE26927",
+        "GSE94379",
+        "GSE115310",
+        "GSE80315",
+        "GSE77702",
+        "GSE239419",
+        "GSE244751",
+        "GSE68501",
+        "GSE196739",
+        "GSE50642",
+        "GSE102564",
+        "GSE134995",
+        "GSE168714",
+        "GSE121069",
+        "GSE181180",
+        "GSE224581",
+        "GSE143161",
+        "GSE80004",
+        "GSE43366"
+    ],
+    "GARD:0012860": [
+        "GSE101",
+        "GSE7110",
+        "GSE44717",
+        "GSE37947",
+        "GSE9676",
+        "GSE103",
+        "GSE46651",
+        "GSE43010",
+        "GSE61321",
+        "GSE104",
+        "GSE73379",
+        "GSE145676",
+        "GSE6032",
+        "GSE61324",
+        "GSE145675",
+        "GSE8731",
+        "GSE61322",
+        "GSE178841",
+        "GSE61400",
+        "GSE61320",
+        "GSE135349",
+        "GSE6032",
+        "GSE7110",
+        "GSE101",
+        "GSE44717",
+        "GSE46651",
+        "GSE43010",
+        "GSE37947",
+        "GSE9676",
+        "GSE103",
+        "GSE8731",
+        "GSE104"
+    ],
+    "GARD:0004694": [
+        "GSE106802",
+        "GSE104169"
+    ],
+    "GARD:0010792": [
+        "GSE185644",
+        "GSE260461",
+        "GSE266485",
+        "GSE199194",
+        "GSE243750",
+        "GSE110226"
+    ],
+    "GARD:0010453": [
+        "GSE279803"
+    ],
+    "GARD:0007193": [
+        "GSE138346",
+        "GSE108524",
+        "GSE228630",
+        "GSE54934",
+        "GSE141801",
+        "GSE61528",
+        "GSE167560",
+        "GSE56598",
+        "GSE70742",
+        "GSE219136",
+        "GSE56596",
+        "GSE180338",
+        "GSE138347",
+        "GSE115359",
+        "GSE186107",
+        "GSE138344",
+        "GSE40187",
+        "GSE56597",
+        "GSE125408",
+        "GSE17792",
+        "GSE232528",
+        "GSE219135"
+    ],
+    "GARD:0010587": [
+        "GSE65368"
+    ],
+    "GARD:0001049": [
+        "GSE204803",
+        "GSE242794",
+        "GSE124500"
+    ],
+    "GARD:0009232": [
+        "GSE42936"
+    ],
+    "GARD:0006677": [
+        "GSE3621",
+        "GSE244970",
+        "GSE149900",
+        "GSE278354",
+        "GSE97100",
+        "GSE108398",
+        "GSE180294",
+        "GSE98738",
+        "GSE3248",
+        "GSE225790",
+        "GSE34721",
+        "GSE245631",
+        "GSE65775",
+        "GSE19677",
+        "GSE157076",
+        "GSE144559",
+        "GSE73655",
+        "GSE48960",
+        "GSE114755",
+        "GSE96099",
+        "GSE167104",
+        "GSE28685",
+        "GSE214108",
+        "GSE38001",
+        "GSE144493",
+        "GSE64977",
+        "GSE184255",
+        "GSE3634",
+        "GSE97353",
+        "GSE273501",
+        "GSE67761",
+        "GSE22267",
+        "GSE241430",
+        "GSE109416",
+        "GSE58996",
+        "GSE65769",
+        "GSE38218",
+        "GSE110226",
+        "GSE142603",
+        "GSE112657",
+        "GSE12651",
+        "GSE78928",
+        "GSE166695",
+        "GSE59572",
+        "GSE220662",
+        "GSE239312",
+        "GSE188559",
+        "GSE242195",
+        "GSE228254",
+        "GSE2872",
+        "GSE199837",
+        "GSE281847",
+        "GSE78274",
+        "GSE114756",
+        "GSE38000",
+        "GSE185476",
+        "GSE67829",
+        "GSE230640",
+        "GSE267802",
+        "GSE270728",
+        "GSE43429",
+        "GSE33000",
+        "GSE169386",
+        "GSE171099",
+        "GSE201694",
+        "GSE157083",
+        "GSE80093",
+        "GSE42107",
+        "GSE150748",
+        "GSE108395",
+        "GSE84055",
+        "GSE65771",
+        "GSE183652",
+        "GSE210996",
+        "GSE141856",
+        "GSE180236",
+        "GSE217469",
+        "GSE76593",
+        "GSE126869",
+        "GSE245510",
+        "GSE143355",
+        "GSE144699",
+        "GSE61405",
+        "GSE79666",
+        "GSE48104",
+        "GSE145879",
+        "GSE73508",
+        "GSE196021",
+        "GSE214973",
+        "GSE144477",
+        "GSE73503",
+        "GSE170998",
+        "GSE135589",
+        "GSE59570",
+        "GSE271852",
+        "GSE140118",
+        "GSE165658",
+        "GSE214110",
+        "GSE65772",
+        "GSE9330",
+        "GSE78791",
+        "GSE73507",
+        "GSE95344",
+        "GSE162349",
+        "GSE146674",
+        "GSE135057",
+        "GSE37517",
+        "GSE199005",
+        "GSE79711",
+        "GSE113928",
+        "GSE124664",
+        "GSE233387",
+        "GSE19780",
+        "GSE88775",
+        "GSE78273",
+        "GSE225789",
+        "GSE264218",
+        "GSE104552",
+        "GSE78272",
+        "GSE206322",
+        "GSE233408",
+        "GSE10581",
+        "GSE72778",
+        "GSE194242",
+        "GSE76738",
+        "GSE11139",
+        "GSE167630",
+        "GSE121757",
+        "GSE112655",
+        "GSE51799",
+        "GSE196022",
+        "GSE173546",
+        "GSE25232",
+        "GSE77194",
+        "GSE43430",
+        "GSE272903",
+        "GSE10202",
+        "GSE109871",
+        "GSE188561",
+        "GSE71816",
+        "GSE180928",
+        "GSE44854",
+        "GSE130570",
+        "GSE107259",
+        "GSE18551",
+        "GSE104091",
+        "GSE154181",
+        "GSE194243",
+        "GSE44855",
+        "GSE233385",
+        "GSE220847",
+        "GSE111622",
+        "GSE154128",
+        "GSE32192",
+        "GSE43431",
+        "GSE129473",
+        "GSE76752",
+        "GSE189647",
+        "GSE78270",
+        "GSE1767",
+        "GSE105158",
+        "GSE188558",
+        "GSE88920",
+        "GSE31560",
+        "GSE40377",
+        "GSE241325",
+        "GSE112379",
+        "GSE173731",
+        "GSE194416",
+        "GSE153791",
+        "GSE54443",
+        "GSE44306",
+        "GSE116267",
+        "GSE165317",
+        "GSE113930",
+        "GSE126914",
+        "GSE77558",
+        "GSE233914",
+        "GSE9803",
+        "GSE1751",
+        "GSE270727",
+        "GSE201692",
+        "GSE152058",
+        "GSE84058",
+        "GSE175657",
+        "GSE67733",
+        "GSE138525",
+        "GSE227729",
+        "GSE181180",
+        "GSE109534",
+        "GSE147004",
+        "GSE40695",
+        "GSE68952",
+        "GSE19291",
+        "GSE107613",
+        "GSE64810",
+        "GSE160586",
+        "GSE148185",
+        "GSE146673",
+        "GSE272271",
+        "GSE9038",
+        "GSE278893",
+        "GSE62210",
+        "GSE146917",
+        "GSE63675",
+        "GSE136158",
+        "GSE84013",
+        "GSE270472",
+        "GSE66769",
+        "GSE85126",
+        "GSE112654",
+        "GSE73505",
+        "GSE170997",
+        "GSE261670",
+        "GSE139847",
+        "GSE24250",
+        "GSE92905",
+        "GSE279460",
+        "GSE195633",
+        "GSE127821",
+        "GSE9760",
+        "GSE211891",
+        "GSE29751",
+        "GSE214743",
+        "GSE276407",
+        "GSE175658",
+        "GSE182866",
+        "GSE166567",
+        "GSE194241",
+        "GSE146399",
+        "GSE11358",
+        "GSE36233",
+        "GSE95843",
+        "GSE89505",
+        "GSE229839",
+        "GSE215217",
+        "GSE95602",
+        "GSE29647",
+        "GSE95842",
+        "GSE209893",
+        "GSE39586",
+        "GSE147003",
+        "GSE147002",
+        "GSE159940",
+        "GSE169405",
+        "GSE162812",
+        "GSE105041",
+        "GSE80004",
+        "GSE150174",
+        "GSE273082",
+        "GSE251684",
+        "GSE95343",
+        "GSE78792",
+        "GSE27588",
+        "GSE115522",
+        "GSE19676",
+        "GSE102750",
+        "GSE59571",
+        "GSE281069",
+        "GSE65774",
+        "GSE156236",
+        "GSE187445",
+        "GSE76753",
+        "GSE9375",
+        "GSE106161",
+        "GSE78793",
+        "GSE103345",
+        "GSE153827",
+        "GSE175618",
+        "GSE144518",
+        "GSE28232",
+        "GSE26001",
+        "GSE140117",
+        "GSE10190",
+        "GSE143475",
+        "GSE65770",
+        "GSE65773",
+        "GSE263368",
+        "GSE146675",
+        "GSE109872",
+        "GSE90068",
+        "GSE47500",
+        "GSE78790",
+        "GSE233895",
+        "GSE95342",
+        "GSE181370",
+        "GSE129141",
+        "GSE21237",
+        "GSE124846",
+        "GSE150747",
+        "GSE70249",
+        "GSE8762",
+        "GSE7958",
+        "GSE29681",
+        "GSE270473",
+        "GSE172379",
+        "GSE12481",
+        "GSE169388",
+        "GSE74201",
+        "GSE189988",
+        "GSE103341",
+        "GSE223847",
+        "GSE857",
+        "GSE3583",
+        "GSE193573",
+        "GSE26317",
+        "GSE26927",
+        "GSE5786",
+        "GSE175656",
+        "GSE148440",
+        "GSE25925",
+        "GSE198927",
+        "GSE109873",
+        "GSE157099",
+        "GSE70656",
+        "GSE225788",
+        "GSE144684",
+        "GSE113929",
+        "GSE148176",
+        "GSE216520",
+        "GSE18644",
+        "GSE116266",
+        "GSE267435",
+        "GSE272134",
+        "GSE242197",
+        "GSE98739",
+        "GSE242506",
+        "GSE38219",
+        "GSE59051",
+        "GSE201691",
+        "GSE79064",
+        "GSE81367",
+        "GSE10263",
+        "GSE127820",
+        "GSE162813",
+        "GSE160967",
+        "GSE93767",
+        "GSE48963",
+        "GSE65776",
+        "GSE48962",
+        "GSE34201",
+        "GSE165663",
+        "GSE248873",
+        "GSE73468",
+        "GSE242198",
+        "GSE165667",
+        "GSE9025",
+        "GSE270729",
+        "GSE37547",
+        "GSE71191",
+        "GSE97101",
+        "GSE214109",
+        "GSE70209",
+        "GSE129143",
+        "GSE269068",
+        "GSE154131",
+        "GSE152443",
+        "GSE73743",
+        "GSE71220",
+        "GSE154141",
+        "GSE9804",
+        "GSE84056",
+        "GSE112656",
+        "GSE49392",
+        "GSE220224",
+        "GSE139884",
+        "GSE43432",
+        "GSE204833",
+        "GSE108396"
+    ],
+    "GARD:0010510": [
+        "GSE3621",
+        "GSE244970",
+        "GSE149900",
+        "GSE278354",
+        "GSE97100",
+        "GSE108398",
+        "GSE180294",
+        "GSE98738",
+        "GSE3248",
+        "GSE225790",
+        "GSE34721",
+        "GSE245631",
+        "GSE65775",
+        "GSE19677",
+        "GSE157076",
+        "GSE144559",
+        "GSE73655",
+        "GSE48960",
+        "GSE114755",
+        "GSE96099",
+        "GSE167104",
+        "GSE28685",
+        "GSE214108",
+        "GSE38001",
+        "GSE144493",
+        "GSE64977",
+        "GSE184255",
+        "GSE3634",
+        "GSE97353",
+        "GSE273501",
+        "GSE67761",
+        "GSE22267",
+        "GSE241430",
+        "GSE109416",
+        "GSE58996",
+        "GSE65769",
+        "GSE38218",
+        "GSE110226",
+        "GSE142603",
+        "GSE112657",
+        "GSE12651",
+        "GSE78928",
+        "GSE166695",
+        "GSE59572",
+        "GSE220662",
+        "GSE239312",
+        "GSE188559",
+        "GSE242195",
+        "GSE228254",
+        "GSE2872",
+        "GSE199837",
+        "GSE281847",
+        "GSE78274",
+        "GSE114756",
+        "GSE38000",
+        "GSE185476",
+        "GSE67829",
+        "GSE230640",
+        "GSE267802",
+        "GSE270728",
+        "GSE43429",
+        "GSE33000",
+        "GSE169386",
+        "GSE171099",
+        "GSE201694",
+        "GSE157083",
+        "GSE80093",
+        "GSE42107",
+        "GSE150748",
+        "GSE108395",
+        "GSE84055",
+        "GSE65771",
+        "GSE183652",
+        "GSE210996",
+        "GSE141856",
+        "GSE180236",
+        "GSE217469",
+        "GSE76593",
+        "GSE126869",
+        "GSE245510",
+        "GSE143355",
+        "GSE144699",
+        "GSE61405",
+        "GSE79666",
+        "GSE48104",
+        "GSE145879",
+        "GSE73508",
+        "GSE196021",
+        "GSE214973",
+        "GSE144477",
+        "GSE73503",
+        "GSE170998",
+        "GSE135589",
+        "GSE59570",
+        "GSE271852",
+        "GSE140118",
+        "GSE165658",
+        "GSE214110",
+        "GSE65772",
+        "GSE9330",
+        "GSE78791",
+        "GSE73507",
+        "GSE95344",
+        "GSE162349",
+        "GSE146674",
+        "GSE135057",
+        "GSE37517",
+        "GSE199005",
+        "GSE79711",
+        "GSE113928",
+        "GSE124664",
+        "GSE233387",
+        "GSE19780",
+        "GSE88775",
+        "GSE78273",
+        "GSE225789",
+        "GSE264218",
+        "GSE104552",
+        "GSE78272",
+        "GSE206322",
+        "GSE233408",
+        "GSE10581",
+        "GSE72778",
+        "GSE194242",
+        "GSE76738",
+        "GSE11139",
+        "GSE167630",
+        "GSE121757",
+        "GSE112655",
+        "GSE51799",
+        "GSE196022",
+        "GSE173546",
+        "GSE25232",
+        "GSE77194",
+        "GSE43430",
+        "GSE272903",
+        "GSE10202",
+        "GSE109871",
+        "GSE188561",
+        "GSE71816",
+        "GSE180928",
+        "GSE44854",
+        "GSE130570",
+        "GSE107259",
+        "GSE18551",
+        "GSE104091",
+        "GSE154181",
+        "GSE194243",
+        "GSE44855",
+        "GSE233385",
+        "GSE220847",
+        "GSE111622",
+        "GSE154128",
+        "GSE32192",
+        "GSE43431",
+        "GSE129473",
+        "GSE76752",
+        "GSE189647",
+        "GSE78270",
+        "GSE1767",
+        "GSE105158",
+        "GSE188558",
+        "GSE88920",
+        "GSE31560",
+        "GSE40377",
+        "GSE241325",
+        "GSE112379",
+        "GSE173731",
+        "GSE194416",
+        "GSE153791",
+        "GSE54443",
+        "GSE44306",
+        "GSE116267",
+        "GSE165317",
+        "GSE113930",
+        "GSE126914",
+        "GSE77558",
+        "GSE233914",
+        "GSE9803",
+        "GSE1751",
+        "GSE270727",
+        "GSE201692",
+        "GSE152058",
+        "GSE84058",
+        "GSE175657",
+        "GSE67733",
+        "GSE138525",
+        "GSE227729",
+        "GSE181180",
+        "GSE109534",
+        "GSE147004",
+        "GSE40695",
+        "GSE68952",
+        "GSE19291",
+        "GSE107613",
+        "GSE64810",
+        "GSE160586",
+        "GSE148185",
+        "GSE146673",
+        "GSE272271",
+        "GSE9038",
+        "GSE278893",
+        "GSE62210",
+        "GSE146917",
+        "GSE63675",
+        "GSE136158",
+        "GSE84013",
+        "GSE270472",
+        "GSE66769",
+        "GSE85126",
+        "GSE112654",
+        "GSE73505",
+        "GSE170997",
+        "GSE261670",
+        "GSE139847",
+        "GSE24250",
+        "GSE92905",
+        "GSE279460",
+        "GSE195633",
+        "GSE127821",
+        "GSE9760",
+        "GSE211891",
+        "GSE29751",
+        "GSE214743",
+        "GSE276407",
+        "GSE175658",
+        "GSE182866",
+        "GSE166567",
+        "GSE194241",
+        "GSE146399",
+        "GSE11358",
+        "GSE36233",
+        "GSE95843",
+        "GSE89505",
+        "GSE229839",
+        "GSE215217",
+        "GSE95602",
+        "GSE29647",
+        "GSE95842",
+        "GSE209893",
+        "GSE39586",
+        "GSE147003",
+        "GSE147002",
+        "GSE159940",
+        "GSE169405",
+        "GSE162812",
+        "GSE105041",
+        "GSE80004",
+        "GSE150174",
+        "GSE273082",
+        "GSE251684",
+        "GSE95343",
+        "GSE78792",
+        "GSE27588",
+        "GSE115522",
+        "GSE19676",
+        "GSE102750",
+        "GSE59571",
+        "GSE281069",
+        "GSE65774",
+        "GSE156236",
+        "GSE187445",
+        "GSE76753",
+        "GSE9375",
+        "GSE106161",
+        "GSE78793",
+        "GSE103345",
+        "GSE153827",
+        "GSE175618",
+        "GSE144518",
+        "GSE28232",
+        "GSE26001",
+        "GSE140117",
+        "GSE10190",
+        "GSE143475",
+        "GSE65770",
+        "GSE65773",
+        "GSE263368",
+        "GSE146675",
+        "GSE109872",
+        "GSE90068",
+        "GSE47500",
+        "GSE78790",
+        "GSE233895",
+        "GSE95342",
+        "GSE181370",
+        "GSE129141",
+        "GSE21237",
+        "GSE124846",
+        "GSE150747",
+        "GSE70249",
+        "GSE8762",
+        "GSE7958",
+        "GSE29681",
+        "GSE270473",
+        "GSE172379",
+        "GSE12481",
+        "GSE169388",
+        "GSE74201",
+        "GSE189988",
+        "GSE103341",
+        "GSE223847",
+        "GSE857",
+        "GSE3583",
+        "GSE193573",
+        "GSE26317",
+        "GSE26927",
+        "GSE5786",
+        "GSE175656",
+        "GSE148440",
+        "GSE25925",
+        "GSE198927",
+        "GSE109873",
+        "GSE157099",
+        "GSE70656",
+        "GSE225788",
+        "GSE144684",
+        "GSE113929",
+        "GSE148176",
+        "GSE216520",
+        "GSE18644",
+        "GSE116266",
+        "GSE267435",
+        "GSE272134",
+        "GSE242197",
+        "GSE98739",
+        "GSE242506",
+        "GSE38219",
+        "GSE59051",
+        "GSE201691",
+        "GSE79064",
+        "GSE81367",
+        "GSE10263",
+        "GSE127820",
+        "GSE162813",
+        "GSE160967",
+        "GSE93767",
+        "GSE48963",
+        "GSE65776",
+        "GSE48962",
+        "GSE34201",
+        "GSE165663",
+        "GSE248873",
+        "GSE73468",
+        "GSE242198",
+        "GSE165667",
+        "GSE9025",
+        "GSE270729",
+        "GSE37547",
+        "GSE71191",
+        "GSE97101",
+        "GSE214109",
+        "GSE70209",
+        "GSE129143",
+        "GSE269068",
+        "GSE154131",
+        "GSE152443",
+        "GSE73743",
+        "GSE71220",
+        "GSE154141",
+        "GSE9804",
+        "GSE84056",
+        "GSE112656",
+        "GSE49392",
+        "GSE220224",
+        "GSE139884",
+        "GSE43432",
+        "GSE204833",
+        "GSE108396"
+    ],
+    "GARD:0002162": [
+        "GSE6275",
+        "GSE7624",
+        "GSE85023",
+        "GSE18123",
+        "GSE198756",
+        "GSE7486"
+    ],
+    "GARD:0002491": [
+        "GSE82009",
+        "GSE176539",
+        "GSE113149",
+        "GSE276177",
+        "GSE7427",
+        "GSE103274",
+        "GSE158097",
+        "GSE245853",
+        "GSE51395",
+        "GSE161534",
+        "GSE24100",
+        "GSE153680",
+        "GSE182169",
+        "GSE163185",
+        "GSE77307",
+        "GSE195848",
+        "GSE168115",
+        "GSE72927",
+        "GSE168037",
+        "GSE139533",
+        "GSE246895",
+        "GSE151852",
+        "GSE120066",
+        "GSE50227",
+        "GSE140819",
+        "GSE239651",
+        "GSE171227",
+        "GSE117126",
+        "GSE41875",
+        "GSE183910",
+        "GSE117905",
+        "GSE85539",
+        "GSE77475",
+        "GSE244301",
+        "GSE273013",
+        "GSE107559",
+        "GSE2727",
+        "GSE36900",
+        "GSE200902",
+        "GSE255502",
+        "GSE41470",
+        "GSE50047",
+        "GSE227098",
+        "GSE9171",
+        "GSE159702",
+        "GSE245800",
+        "GSE32482",
+        "GSE116545",
+        "GSE53220",
+        "GSE214466",
+        "GSE7181",
+        "GSE158549",
+        "GSE50173",
+        "GSE265971",
+        "GSE244666",
+        "GSE245043",
+        "GSE195680",
+        "GSE197762",
+        "GSE42400",
+        "GSE143189",
+        "GSE263685",
+        "GSE86574",
+        "GSE117832",
+        "GSE139238",
+        "GSE163071",
+        "GSE127989",
+        "GSE134973",
+        "GSE89201",
+        "GSE113361",
+        "GSE119776",
+        "GSE198439",
+        "GSE75592",
+        "GSE50923",
+        "GSE169286",
+        "GSE86202",
+        "GSE95386",
+        "GSE244893",
+        "GSE1128",
+        "GSE255581",
+        "GSE159738",
+        "GSE211272",
+        "GSE152575",
+        "GSE240676",
+        "GSE244579",
+        "GSE8315",
+        "GSE213308",
+        "GSE58646",
+        "GSE273250",
+        "GSE14079",
+        "GSE75254",
+        "GSE182685",
+        "GSE99181",
+        "GSE198855",
+        "GSE241396",
+        "GSE112734",
+        "GSE68030",
+        "GSE95392",
+        "GSE112241",
+        "GSE71116",
+        "GSE112648",
+        "GSE236568",
+        "GSE174308",
+        "GSE211462",
+        "GSE39292",
+        "GSE101148",
+        "GSE76652",
+        "GSE30034",
+        "GSE37120",
+        "GSE35453",
+        "GSE63536",
+        "GSE117258",
+        "GSE263588",
+        "GSE133471",
+        "GSE108343",
+        "GSE163021",
+        "GSE42355",
+        "GSE54077",
+        "GSE215240",
+        "GSE79671",
+        "GSE205590",
+        "GSE236082",
+        "GSE11233",
+        "GSE100351",
+        "GSE185861",
+        "GSE150604",
+        "GSE159880",
+        "GSE85697",
+        "GSE10758",
+        "GSE106804",
+        "GSE107047",
+        "GSE18804",
+        "GSE182697",
+        "GSE222520",
+        "GSE238199",
+        "GSE186442",
+        "GSE155839",
+        "GSE241284",
+        "GSE146197",
+        "GSE192710",
+        "GSE42401",
+        "GSE79896",
+        "GSE53800",
+        "GSE15309",
+        "GSE10007",
+        "GSE205512",
+        "GSE79302",
+        "GSE112651",
+        "GSE74561",
+        "GSE185873",
+        "GSE103659",
+        "GSE20633",
+        "GSE87535",
+        "GSE29458",
+        "GSE155834",
+        "GSE201975",
+        "GSE263890",
+        "GSE40265",
+        "GSE140297",
+        "GSE20306",
+        "GSE216888",
+        "GSE109569",
+        "GSE112462",
+        "GSE140002",
+        "GSE272737",
+        "GSE34824",
+        "GSE62731",
+        "GSE184472",
+        "GSE271448",
+        "GSE152160",
+        "GSE201977",
+        "GSE211554",
+        "GSE225191",
+        "GSE124769",
+        "GSE10922",
+        "GSE61388",
+        "GSE154958",
+        "GSE58401",
+        "GSE38815",
+        "GSE85024",
+        "GSE28618",
+        "GSE156663",
+        "GSE162831",
+        "GSE161573",
+        "GSE45301",
+        "GSE181366",
+        "GSE162783",
+        "GSE21045",
+        "GSE253152",
+        "GSE121721",
+        "GSE138622",
+        "GSE64637",
+        "GSE102244",
+        "GSE190953",
+        "GSE1902",
+        "GSE193957",
+        "GSE153982",
+        "GSE61078",
+        "GSE129908",
+        "GSE17047",
+        "GSE103455",
+        "GSE13276",
+        "GSE138618",
+        "GSE249637",
+        "GSE230389",
+        "GSE100623",
+        "GSE145559",
+        "GSE180895",
+        "GSE168039",
+        "GSE96088",
+        "GSE72477",
+        "GSE143755",
+        "GSE12836",
+        "GSE165390",
+        "GSE43674",
+        "GSE63387",
+        "GSE7426",
+        "GSE68995",
+        "GSE101980",
+        "GSE138794",
+        "GSE118960",
+        "GSE271707",
+        "GSE213592",
+        "GSE206225",
+        "GSE102136",
+        "GSE74571",
+        "GSE184696",
+        "GSE35239",
+        "GSE206357",
+        "GSE165386",
+        "GSE242790",
+        "GSE190504",
+        "GSE99361",
+        "GSE97071",
+        "GSE249636",
+        "GSE283576",
+        "GSE110890",
+        "GSE246154",
+        "GSE216626",
+        "GSE7696",
+        "GSE221971",
+        "GSE126212",
+        "GSE19112",
+        "GSE72204",
+        "GSE110130",
+        "GSE161523",
+        "GSE261440",
+        "GSE163120",
+        "GSE137310",
+        "GSE241227",
+        "GSE129877",
+        "GSE273621",
+        "GSE134974",
+        "GSE154133",
+        "GSE238071",
+        "GSE203154",
+        "GSE61706",
+        "GSE46016",
+        "GSE232725",
+        "GSE4536",
+        "GSE133095",
+        "GSE46531",
+        "GSE235438",
+        "GSE40328",
+        "GSE119755",
+        "GSE64661",
+        "GSE260701",
+        "GSE68850",
+        "GSE224090",
+        "GSE19846",
+        "GSE244868",
+        "GSE279073",
+        "GSE221580",
+        "GSE143843",
+        "GSE277014",
+        "GSE133470",
+        "GSE13214",
+        "GSE213307",
+        "GSE130220",
+        "GSE9177",
+        "GSE181378",
+        "GSE51301",
+        "GSE116621",
+        "GSE61705",
+        "GSE121810",
+        "GSE229600",
+        "GSE183221",
+        "GSE114867",
+        "GSE79889",
+        "GSE245635",
+        "GSE266154",
+        "GSE261190",
+        "GSE232469",
+        "GSE111676",
+        "GSE125243",
+        "GSE159747",
+        "GSE32883",
+        "GSE108848",
+        "GSE37475",
+        "GSE276176",
+        "GSE142827",
+        "GSE208074",
+        "GSE2485",
+        "GSE214967",
+        "GSE249155",
+        "GSE37956",
+        "GSE144623",
+        "GSE137808",
+        "GSE214252",
+        "GSE229673",
+        "GSE39747",
+        "GSE45185",
+        "GSE165389",
+        "GSE35603",
+        "GSE120627",
+        "GSE245919",
+        "GSE73127",
+        "GSE102294",
+        "GSE150612",
+        "GSE162931",
+        "GSE51146",
+        "GSE162631",
+        "GSE127895",
+        "GSE94693",
+        "GSE70175",
+        "GSE181379",
+        "GSE215365",
+        "GSE118683",
+        "GSE8692",
+        "GSE12657",
+        "GSE32876",
+        "GSE133479",
+        "GSE233640",
+        "GSE154043",
+        "GSE253222",
+        "GSE128195",
+        "GSE46538",
+        "GSE261187",
+        "GSE53042",
+        "GSE207288",
+        "GSE88320",
+        "GSE283387",
+        "GSE183211",
+        "GSE155808",
+        "GSE57872",
+        "GSE114438",
+        "GSE274633",
+        "GSE75789",
+        "GSE119468",
+        "GSE136829",
+        "GSE75910",
+        "GSE205591",
+        "GSE56937",
+        "GSE115459",
+        "GSE12694",
+        "GSE46688",
+        "GSE247800",
+        "GSE199407",
+        "GSE141961",
+        "GSE236478",
+        "GSE24716",
+        "GSE26344",
+        "GSE60274",
+        "GSE21570",
+        "GSE167300",
+        "GSE251908",
+        "GSE253400",
+        "GSE74610",
+        "GSE22385",
+        "GSE188393",
+        "GSE8569",
+        "GSE194329",
+        "GSE72217",
+        "GSE49808",
+        "GSE181146",
+        "GSE13021",
+        "GSE98366",
+        "GSE222560",
+        "GSE83511",
+        "GSE233304",
+        "GSE259378",
+        "GSE60921",
+        "GSE208697",
+        "GSE49412",
+        "GSE116531",
+        "GSE52319",
+        "GSE145374",
+        "GSE234832",
+        "GSE29384",
+        "GSE36245",
+        "GSE156902",
+        "GSE74520",
+        "GSE276299",
+        "GSE163108",
+        "GSE231555",
+        "GSE85033",
+        "GSE18890",
+        "GSE26676",
+        "GSE183773",
+        "GSE164352",
+        "GSE162986",
+        "GSE86519",
+        "GSE64411",
+        "GSE114574",
+        "GSE166111",
+        "GSE202484",
+        "GSE31545",
+        "GSE178471",
+        "GSE40770",
+        "GSE72219",
+        "GSE123755",
+        "GSE173279",
+        "GSE30291",
+        "GSE129972",
+        "GSE263832",
+        "GSE119586",
+        "GSE83756",
+        "GSE192823",
+        "GSE137454",
+        "GSE48433",
+        "GSE261471",
+        "GSE16805",
+        "GSE197990",
+        "GSE122920",
+        "GSE149009",
+        "GSE133509",
+        "GSE113261",
+        "GSE205538",
+        "GSE117423",
+        "GSE240490",
+        "GSE245624",
+        "GSE260700",
+        "GSE147382",
+        "GSE247884",
+        "GSE81287",
+        "GSE134470",
+        "GSE261132",
+        "GSE108957",
+        "GSE122486",
+        "GSE102924",
+        "GSE221949",
+        "GSE87411",
+        "GSE28860",
+        "GSE71538",
+        "GSE46226",
+        "GSE44151",
+        "GSE196067",
+        "GSE36354",
+        "GSE13030",
+        "GSE30563",
+        "GSE72203",
+        "GSE246936",
+        "GSE171872",
+        "GSE240492",
+        "GSE150676",
+        "GSE126073",
+        "GSE30472",
+        "GSE188739",
+        "GSE14819",
+        "GSE224941",
+        "GSE194220",
+        "GSE104783",
+        "GSE149334",
+        "GSE135306",
+        "GSE136330",
+        "GSE112735",
+        "GSE106810",
+        "GSE199033",
+        "GSE241037",
+        "GSE77530",
+        "GSE90598",
+        "GSE99183",
+        "GSE14",
+        "GSE126840",
+        "GSE33328",
+        "GSE111571",
+        "GSE110066",
+        "GSE179004",
+        "GSE60704",
+        "GSE151155",
+        "GSE73573",
+        "GSE189650",
+        "GSE184698",
+        "GSE239610",
+        "GSE42656",
+        "GSE121719",
+        "GSE189781",
+        "GSE165595",
+        "GSE79877",
+        "GSE153746",
+        "GSE154337",
+        "GSE122807",
+        "GSE232173",
+        "GSE165937",
+        "GSE63534",
+        "GSE226765",
+        "GSE180621",
+        "GSE233867",
+        "GSE151352",
+        "GSE103228",
+        "GSE154042",
+        "GSE89398",
+        "GSE14889",
+        "GSE225210",
+        "GSE77998",
+        "GSE67633",
+        "GSE42618",
+        "GSE65910",
+        "GSE217366",
+        "GSE207726",
+        "GSE179667",
+        "GSE51336",
+        "GSE1989",
+        "GSE152612",
+        "GSE78895",
+        "GSE239847",
+        "GSE187418",
+        "GSE156820",
+        "GSE163655",
+        "GSE189517",
+        "GSE40833",
+        "GSE62714",
+        "GSE277015",
+        "GSE208323",
+        "GSE48079",
+        "GSE24557",
+        "GSE163401",
+        "GSE270493",
+        "GSE226293",
+        "GSE147595",
+        "GSE115840",
+        "GSE213554",
+        "GSE138077",
+        "GSE91391",
+        "GSE179087",
+        "GSE243575",
+        "GSE95216",
+        "GSE7233",
+        "GSE25272",
+        "GSE228497",
+        "GSE153908",
+        "GSE146698",
+        "GSE163400",
+        "GSE75906",
+        "GSE262708",
+        "GSE21143",
+        "GSE254874",
+        "GSE123760",
+        "GSE161437",
+        "GSE26313",
+        "GSE43911",
+        "GSE226172",
+        "GSE32293",
+        "GSE152861",
+        "GSE85297",
+        "GSE279423",
+        "GSE95106",
+        "GSE212086",
+        "GSE273464",
+        "GSE104653",
+        "GSE58922",
+        "GSE81465",
+        "GSE270855",
+        "GSE14824",
+        "GSE184695",
+        "GSE233532",
+        "GSE122832",
+        "GSE36278",
+        "GSE154060",
+        "GSE118093",
+        "GSE19114",
+        "GSE244497",
+        "GSE147352",
+        "GSE107560",
+        "GSE103963",
+        "GSE157779",
+        "GSE215123",
+        "GSE128654",
+        "GSE151680",
+        "GSE196141",
+        "GSE179649",
+        "GSE87615",
+        "GSE253407",
+        "GSE206551",
+        "GSE201976",
+        "GSE256491",
+        "GSE234125",
+        "GSE87515",
+        "GSE164104",
+        "GSE245855",
+        "GSE217348",
+        "GSE75189",
+        "GSE28271",
+        "GSE156821",
+        "GSE271928",
+        "GSE240119",
+        "GSE65878",
+        "GSE121422",
+        "GSE228512",
+        "GSE42577",
+        "GSE4290",
+        "GSE109867",
+        "GSE1991",
+        "GSE261684",
+        "GSE103366",
+        "GSE149910",
+        "GSE55363",
+        "GSE56517",
+        "GSE44099",
+        "GSE91016",
+        "GSE199364",
+        "GSE110866",
+        "GSE163906",
+        "GSE93850",
+        "GSE128555",
+        "GSE134404",
+        "GSE116520",
+        "GSE65911",
+        "GSE15209",
+        "GSE78025",
+        "GSE282325",
+        "GSE25411",
+        "GSE158284",
+        "GSE30700",
+        "GSE79338",
+        "GSE98128",
+        "GSE178147",
+        "GSE174617",
+        "GSE127273",
+        "GSE72732",
+        "GSE69081",
+        "GSE110424",
+        "GSE22772",
+        "GSE59967",
+        "GSE249657",
+        "GSE196175",
+        "GSE53124",
+        "GSE110867",
+        "GSE61002",
+        "GSE140272",
+        "GSE63537",
+        "GSE9200",
+        "GSE158803",
+        "GSE262598",
+        "GSE75443",
+        "GSE96911",
+        "GSE222515",
+        "GSE199862",
+        "GSE7428",
+        "GSE61852",
+        "GSE222971",
+        "GSE159000",
+        "GSE44842",
+        "GSE268426",
+        "GSE242044",
+        "GSE95680",
+        "GSE229409",
+        "GSE79878",
+        "GSE235207",
+        "GSE192874",
+        "GSE4217",
+        "GSE218041",
+        "GSE235672",
+        "GSE246697",
+        "GSE161175",
+        "GSE239379",
+        "GSE137830",
+        "GSE123821",
+        "GSE138092",
+        "GSE17381",
+        "GSE24717",
+        "GSE202371",
+        "GSE76184",
+        "GSE24558",
+        "GSE79735",
+        "GSE90459",
+        "GSE35917",
+        "GSE266141",
+        "GSE89456",
+        "GSE199031",
+        "GSE133041",
+        "GSE196695",
+        "GSE39413",
+        "GSE141946",
+        "GSE193745",
+        "GSE72538",
+        "GSE58298",
+        "GSE58525",
+        "GSE207046",
+        "GSE178236",
+        "GSE143609",
+        "GSE32466",
+        "GSE225964",
+        "GSE142825",
+        "GSE109330",
+        "GSE255535",
+        "GSE71224",
+        "GSE197062",
+        "GSE132172",
+        "GSE61445",
+        "GSE100146",
+        "GSE15805",
+        "GSE18150",
+        "GSE134711",
+        "GSE131660",
+        "GSE30800",
+        "GSE98824",
+        "GSE203260",
+        "GSE139380",
+        "GSE6109",
+        "GSE131402",
+        "GSE42670",
+        "GSE19720",
+        "GSE36337",
+        "GSE90603",
+        "GSE54142",
+        "GSE185474",
+        "GSE153679",
+        "GSE156194",
+        "GSE65576",
+        "GSE14507",
+        "GSE199376",
+        "GSE75147",
+        "GSE88106",
+        "GSE75589",
+        "GSE256493",
+        "GSE266130",
+        "GSE36947",
+        "GSE4817",
+        "GSE217031",
+        "GSE198522",
+        "GSE138662",
+        "GSE108998",
+        "GSE198547",
+        "GSE49822",
+        "GSE72269",
+        "GSE195640",
+        "GSE92460",
+        "GSE33213",
+        "GSE197728",
+        "GSE263756",
+        "GSE142719",
+        "GSE169418",
+        "GSE185955",
+        "GSE159889",
+        "GSE148686",
+        "GSE35454",
+        "GSE183004",
+        "GSE108089",
+        "GSE233971",
+        "GSE241247",
+        "GSE14805",
+        "GSE181650",
+        "GSE188771",
+        "GSE138535",
+        "GSE268342",
+        "GSE122871",
+        "GSE74052",
+        "GSE128961",
+        "GSE68994",
+        "GSE268118",
+        "GSE39221",
+        "GSE9635",
+        "GSE256490",
+        "GSE193178",
+        "GSE281549",
+        "GSE276102",
+        "GSE129976",
+        "GSE14821",
+        "GSE185420",
+        "GSE55362",
+        "GSE188772",
+        "GSE233380",
+        "GSE181274",
+        "GSE178337",
+        "GSE12689",
+        "GSE137879",
+        "GSE98797",
+        "GSE226976",
+        "GSE142210",
+        "GSE58923",
+        "GSE61079",
+        "GSE139136",
+        "GSE92322",
+        "GSE266144",
+        "GSE247890",
+        "GSE89409",
+        "GSE148685",
+        "GSE208696",
+        "GSE129671",
+        "GSE94874",
+        "GSE42631",
+        "GSE193729",
+        "GSE150614",
+        "GSE236486",
+        "GSE212941",
+        "GSE110869",
+        "GSE171287",
+        "GSE29738",
+        "GSE46014",
+        "GSE201657",
+        "GSE181145",
+        "GSE49416",
+        "GSE178623",
+        "GSE190950",
+        "GSE186392",
+        "GSE212171",
+        "GSE151547",
+        "GSE158700",
+        "GSE46599",
+        "GSE73120",
+        "GSE241039",
+        "GSE108749",
+        "GSE115509",
+        "GSE273274",
+        "GSE129974",
+        "GSE214907",
+        "GSE168004",
+        "GSE273012",
+        "GSE150680",
+        "GSE39144",
+        "GSE200146",
+        "GSE56750",
+        "GSE51413",
+        "GSE188226",
+        "GSE11848",
+        "GSE68950",
+        "GSE28026",
+        "GSE134567",
+        "GSE182670",
+        "GSE274546",
+        "GSE174470",
+        "GSE84010",
+        "GSE45874",
+        "GSE145644",
+        "GSE68661",
+        "GSE188924",
+        "GSE45307",
+        "GSE280761",
+        "GSE186443",
+        "GSE46190",
+        "GSE81314",
+        "GSE229866",
+        "GSE145932",
+        "GSE217515",
+        "GSE28040",
+        "GSE26283",
+        "GSE108098",
+        "GSE54004",
+        "GSE150956",
+        "GSE274460",
+        "GSE217511",
+        "GSE112736",
+        "GSE47997",
+        "GSE118791",
+        "GSE271170",
+        "GSE72202",
+        "GSE163186",
+        "GSE45117",
+        "GSE119592",
+        "GSE52581",
+        "GSE238010",
+        "GSE149485",
+        "GSE240418",
+        "GSE152858",
+        "GSE135062",
+        "GSE233868",
+        "GSE208616",
+        "GSE108658",
+        "GSE188227",
+        "GSE223063",
+        "GSE211725",
+        "GSE6042",
+        "GSE117838",
+        "GSE132825",
+        "GSE104267",
+        "GSE232040",
+        "GSE175862",
+        "GSE195567",
+        "GSE196320",
+        "GSE231577",
+        "GSE107601",
+        "GSE14878",
+        "GSE344",
+        "GSE226990",
+        "GSE14820",
+        "GSE141944",
+        "GSE229940",
+        "GSE75003",
+        "GSE66177",
+        "GSE154367",
+        "GSE21336",
+        "GSE148542",
+        "GSE9885",
+        "GSE32692",
+        "GSE22692",
+        "GSE155994",
+        "GSE139417",
+        "GSE90886",
+        "GSE68029",
+        "GSE23806",
+        "GSE25630",
+        "GSE81473",
+        "GSE62212",
+        "GSE58924",
+        "GSE92483",
+        "GSE111627",
+        "GSE65526",
+        "GSE186440",
+        "GSE186047",
+        "GSE117543",
+        "GSE159739",
+        "GSE185463",
+        "GSE146358",
+        "GSE140441",
+        "GSE285543",
+        "GSE137934",
+        "GSE18798",
+        "GSE196694",
+        "GSE130324",
+        "GSE60706",
+        "GSE1923",
+        "GSE19678",
+        "GSE267458",
+        "GSE32465",
+        "GSE134045",
+        "GSE31262",
+        "GSE34989",
+        "GSE222666",
+        "GSE61704",
+        "GSE273252",
+        "GSE18892",
+        "GSE188958",
+        "GSE38330",
+        "GSE118684",
+        "GSE106557",
+        "GSE109399",
+        "GSE107932",
+        "GSE47620",
+        "GSE51411",
+        "GSE101799",
+        "GSE60507",
+        "GSE97347",
+        "GSE185758",
+        "GSE40699",
+        "GSE96682",
+        "GSE87617",
+        "GSE161574",
+        "GSE184398",
+        "GSE271072",
+        "GSE24084",
+        "GSE32286",
+        "GSE249656",
+        "GSE42657",
+        "GSE5949",
+        "GSE193179",
+        "GSE229419",
+        "GSE33362",
+        "GSE105773",
+        "GSE10547",
+        "GSE191021",
+        "GSE151414",
+        "GSE197879",
+        "GSE255850",
+        "GSE181314",
+        "GSE17227",
+        "GSE80821",
+        "GSE136751",
+        "GSE97350",
+        "GSE129978",
+        "GSE195682",
+        "GSE41685",
+        "GSE106545",
+        "GSE207725",
+        "GSE214965",
+        "GSE29796",
+        "GSE4328",
+        "GSE149303",
+        "GSE63319",
+        "GSE231595",
+        "GSE78666",
+        "GSE273251",
+        "GSE100736",
+        "GSE58399",
+        "GSE224942",
+        "GSE52009",
+        "GSE126503",
+        "GSE94808",
+        "GSE267976",
+        "GSE278988",
+        "GSE20723",
+        "GSE188547",
+        "GSE76959",
+        "GSE278136",
+        "GSE102886",
+        "GSE77626",
+        "GSE91392",
+        "GSE254145",
+        "GSE107040",
+        "GSE285544",
+        "GSE73625",
+        "GSE217029",
+        "GSE271073",
+        "GSE139414",
+        "GSE51062",
+        "GSE190129",
+        "GSE282886",
+        "GSE141383",
+        "GSE197508",
+        "GSE278456",
+        "GSE113510",
+        "GSE198438",
+        "GSE213309",
+        "GSE126658",
+        "GSE14581",
+        "GSE107530",
+        "GSE62367",
+        "GSE79122",
+        "GSE137287",
+        "GSE116488",
+        "GSE243221",
+        "GSE218331",
+        "GSE229672",
+        "GSE143263",
+        "GSE72201",
+        "GSE5107",
+        "GSE68424",
+        "GSE149989",
+        "GSE273589",
+        "GSE197543",
+        "GSE163020",
+        "GSE155247",
+        "GSE183606",
+        "GSE137809",
+        "GSE236243",
+        "GSE155835",
+        "GSE279771",
+        "GSE66388",
+        "GSE122283",
+        "GSE104554",
+        "GSE93204",
+        "GSE18894",
+        "GSE242352",
+        "GSE178260",
+        "GSE42420",
+        "GSE218042",
+        "GSE114534",
+        "GSE79897",
+        "GSE214968",
+        "GSE130105",
+        "GSE231503",
+        "GSE142828",
+        "GSE196339",
+        "GSE95027",
+        "GSE251900",
+        "GSE121601",
+        "GSE268158",
+        "GSE73895",
+        "GSE137902",
+        "GSE221950",
+        "GSE203177",
+        "GSE262707",
+        "GSE240675",
+        "GSE129977",
+        "GSE245762",
+        "GSE241147",
+        "GSE3185",
+        "GSE210654",
+        "GSE46028",
+        "GSE13598",
+        "GSE35186",
+        "GSE204944",
+        "GSE207760",
+        "GSE134783",
+        "GSE206984",
+        "GSE249154",
+        "GSE244894",
+        "GSE138114",
+        "GSE53227",
+        "GSE222421",
+        "GSE107859",
+        "GSE246262",
+        "GSE211147",
+        "GSE224692",
+        "GSE98693",
+        "GSE244332",
+        "GSE83301",
+        "GSE51332",
+        "GSE94349",
+        "GSE286477",
+        "GSE70231",
+        "GSE186319",
+        "GSE30016",
+        "GSE163409",
+        "GSE282334",
+        "GSE205519",
+        "GSE131744",
+        "GSE175864",
+        "GSE243465",
+        "GSE180466",
+        "GSE30448",
+        "GSE99180",
+        "GSE209777",
+        "GSE171497",
+        "GSE19113",
+        "GSE21514",
+        "GSE242326",
+        "GSE270857",
+        "GSE232486",
+        "GSE68343",
+        "GSE68800",
+        "GSE236569",
+        "GSE37634",
+        "GSE285545",
+        "GSE266971",
+        "GSE64230",
+        "GSE207002",
+        "GSE130093",
+        "GSE50161",
+        "GSE244869",
+        "GSE50478",
+        "GSE84132",
+        "GSE142693",
+        "GSE226740",
+        "GSE160437",
+        "GSE197761",
+        "GSE144399",
+        "GSE196418",
+        "GSE77053",
+        "GSE214832",
+        "GSE148673",
+        "GSE181035",
+        "GSE150631",
+        "GSE131956",
+        "GSE233869",
+        "GSE185695",
+        "GSE76018",
+        "GSE102193",
+        "GSE106142",
+        "GSE103790",
+        "GSE19612",
+        "GSE19693",
+        "GSE266969",
+        "GSE214140",
+        "GSE147454",
+        "GSE245263",
+        "GSE253080",
+        "GSE235911",
+        "GSE87619",
+        "GSE164717",
+        "GSE14818",
+        "GSE229964",
+        "GSE254873",
+        "GSE63532",
+        "GSE89745",
+        "GSE26002",
+        "GSE261472",
+        "GSE185954",
+        "GSE224104",
+        "GSE36426",
+        "GSE182295",
+        "GSE243455",
+        "GSE234284",
+        "GSE137796",
+        "GSE181144",
+        "GSE59484",
+        "GSE196707",
+        "GSE140145",
+        "GSE147391",
+        "GSE113824",
+        "GSE77043",
+        "GSE126168",
+        "GSE106143",
+        "GSE175700",
+        "GSE249544",
+        "GSE41980",
+        "GSE271618",
+        "GSE282194",
+        "GSE6014",
+        "GSE2109",
+        "GSE243682",
+        "GSE58400",
+        "GSE230825",
+        "GSE276841",
+        "GSE114915",
+        "GSE36619",
+        "GSE108474",
+        "GSE206604",
+        "GSE185759",
+        "GSE4412",
+        "GSE84707",
+        "GSE41467",
+        "GSE161352",
+        "GSE226202",
+        "GSE182281",
+        "GSE165238",
+        "GSE35811",
+        "GSE163504",
+        "GSE162976",
+        "GSE213046",
+        "GSE180896",
+        "GSE13041",
+        "GSE179115",
+        "GSE32100",
+        "GSE104273",
+        "GSE63035",
+        "GSE56573",
+        "GSE205514",
+        "GSE80968",
+        "GSE240516",
+        "GSE234912",
+        "GSE76786",
+        "GSE206241",
+        "GSE243501",
+        "GSE247977",
+        "GSE130949",
+        "GSE185956",
+        "GSE179110",
+        "GSE8537",
+        "GSE200162",
+        "GSE139416",
+        "GSE199689",
+        "GSE248703",
+        "GSE141947",
+        "GSE77452",
+        "GSE145897",
+        "GSE137489",
+        "GSE22866",
+        "GSE138328",
+        "GSE151137",
+        "GSE15170",
+        "GSE36940",
+        "GSE76422",
+        "GSE251777",
+        "GSE93143",
+        "GSE279426",
+        "GSE199379",
+        "GSE60867",
+        "GSE59678",
+        "GSE36782",
+        "GSE19870",
+        "GSE184890",
+        "GSE29442",
+        "GSE226757",
+        "GSE239486",
+        "GSE270481",
+        "GSE85615",
+        "GSE88771",
+        "GSE62153",
+        "GSE137048",
+        "GSE109340",
+        "GSE186057",
+        "GSE163656",
+        "GSE87618",
+        "GSE62381",
+        "GSE53228",
+        "GSE51441",
+        "GSE248420",
+        "GSE190154",
+        "GSE75945",
+        "GSE266620",
+        "GSE217035",
+        "GSE178621",
+        "GSE156678",
+        "GSE62211",
+        "GSE208617",
+        "GSE89239",
+        "GSE165037",
+        "GSE186945",
+        "GSE218081",
+        "GSE157424",
+        "GSE228500",
+        "GSE121718",
+        "GSE45161",
+        "GSE206675",
+        "GSE273275",
+        "GSE215401",
+        "GSE199185",
+        "GSE121716",
+        "GSE36901",
+        "GSE182220",
+        "GSE122586",
+        "GSE253362",
+        "GSE229482",
+        "GSE98377",
+        "GSE165624",
+        "GSE234762",
+        "GSE236494",
+        "GSE202200",
+        "GSE22927",
+        "GSE133285",
+        "GSE189577",
+        "GSE173280",
+        "GSE162833",
+        "GSE85087",
+        "GSE145409",
+        "GSE32970",
+        "GSE266619",
+        "GSE108862",
+        "GSE276103",
+        "GSE153907",
+        "GSE86518",
+        "GSE129438",
+        "GSE57083",
+        "GSE210717",
+        "GSE229136",
+        "GSE3521",
+        "GSE154795",
+        "GSE251878",
+        "GSE109628",
+        "GSE230453",
+        "GSE131879",
+        "GSE230661",
+        "GSE235100",
+        "GSE38814",
+        "GSE285535",
+        "GSE141013",
+        "GSE147275",
+        "GSE222522",
+        "GSE158741",
+        "GSE92462",
+        "GSE131400",
+        "GSE212325",
+        "GSE240193",
+        "GSE152071",
+        "GSE33442",
+        "GSE218860",
+        "GSE181315",
+        "GSE101291",
+        "GSE231994",
+        "GSE139142",
+        "GSE266884",
+        "GSE8852",
+        "GSE145646",
+        "GSE199110",
+        "GSE254875",
+        "GSE29288",
+        "GSE179882",
+        "GSE55361",
+        "GSE130119",
+        "GSE223064",
+        "GSE264275",
+        "GSE145558",
+        "GSE157647",
+        "GSE244878",
+        "GSE208773",
+        "GSE54047",
+        "GSE162444",
+        "GSE83537",
+        "GSE247650",
+        "GSE93054",
+        "GSE86624",
+        "GSE54967",
+        "GSE52580",
+        "GSE222518",
+        "GSE27931",
+        "GSE11100",
+        "GSE7516",
+        "GSE242225",
+        "GSE237183",
+        "GSE173645",
+        "GSE234127",
+        "GSE252870",
+        "GSE163715",
+        "GSE248704",
+        "GSE196591",
+        "GSE14806",
+        "GSE160887",
+        "GSE214966",
+        "GSE148803",
+        "GSE278450",
+        "GSE186302",
+        "GSE77751",
+        "GSE27671",
+        "GSE255501",
+        "GSE225967",
+        "GSE225973",
+        "GSE266147",
+        "GSE219288",
+        "GSE2221",
+        "GSE54791",
+        "GSE79438",
+        "GSE47945",
+        "GSE200574",
+        "GSE195683",
+        "GSE192678",
+        "GSE153794",
+        "GSE89400",
+        "GSE70038",
+        "GSE277301",
+        "GSE89623",
+        "GSE90176",
+        "GSE249653",
+        "GSE75300",
+        "GSE60184",
+        "GSE234262",
+        "GSE113370",
+        "GSE52230",
+        "GSE19363",
+        "GSE68368",
+        "GSE195506",
+        "GSE244825",
+        "GSE81934",
+        "GSE152862",
+        "GSE284766",
+        "GSE229965",
+        "GSE137900",
+        "GSE103961",
+        "GSE235913",
+        "GSE261191",
+        "GSE129047",
+        "GSE274090",
+        "GSE123444",
+        "GSE217152",
+        "GSE127274",
+        "GSE265904",
+        "GSE48568",
+        "GSE13808",
+        "GSE229671",
+        "GSE40051",
+        "GSE245688",
+        "GSE60866",
+        "GSE104291",
+        "GSE275293",
+        "GSE165286",
+        "GSE144610",
+        "GSE280951",
+        "GSE215873",
+        "GSE159605",
+        "GSE232434",
+        "GSE124145",
+        "GSE143798",
+        "GSE116298",
+        "GSE90426",
+        "GSE26576",
+        "GSE133040",
+        "GSE63712",
+        "GSE89501",
+        "GSE56715",
+        "GSE75244",
+        "GSE50412",
+        "GSE51281",
+        "GSE221714",
+        "GSE125905",
+        "GSE159607",
+        "GSE132118",
+        "GSE41230",
+        "GSE98127",
+        "GSE241276",
+        "GSE44561",
+        "GSE205513",
+        "GSE166696",
+        "GSE84465",
+        "GSE69104",
+        "GSE230826",
+        "GSE140449",
+        "GSE248352",
+        "GSE207426",
+        "GSE67089",
+        "GSE122808",
+        "GSE207821",
+        "GSE222895",
+        "GSE28220",
+        "GSE63853",
+        "GSE254168",
+        "GSE180209",
+        "GSE190930",
+        "GSE72951",
+        "GSE138942",
+        "GSE240377",
+        "GSE234473",
+        "GSE103224",
+        "GSE121857",
+        "GSE51481",
+        "GSE161436",
+        "GSE131837",
+        "GSE196533",
+        "GSE209865",
+        "GSE224082",
+        "GSE149921",
+        "GSE63037",
+        "GSE111247",
+        "GSE184643",
+        "GSE266145",
+        "GSE99537",
+        "GSE138475",
+        "GSE179147",
+        "GSE155052",
+        "GSE148842",
+        "GSE171758",
+        "GSE196706",
+        "GSE145128",
+        "GSE117632",
+        "GSE54660",
+        "GSE45899",
+        "GSE42402",
+        "GSE150673",
+        "GSE247886",
+        "GSE189605",
+        "GSE181649",
+        "GSE229420",
+        "GSE43452",
+        "GSE186207",
+        "GSE121722",
+        "GSE119688",
+        "GSE137210",
+        "GSE272370",
+        "GSE83294",
+        "GSE136089",
+        "GSE35500",
+        "GSE268563",
+        "GSE270465",
+        "GSE154041",
+        "GSE30626",
+        "GSE243130",
+        "GSE262760",
+        "GSE18883",
+        "GSE119081",
+        "GSE147147",
+        "GSE163019",
+        "GSE189541",
+        "GSE57091",
+        "GSE209772",
+        "GSE155300",
+        "GSE98692",
+        "GSE73270",
+        "GSE28214",
+        "GSE31133",
+        "GSE148740",
+        "GSE137733",
+        "GSE148292",
+        "GSE214248",
+        "GSE242328",
+        "GSE234126",
+        "GSE234124",
+        "GSE191126",
+        "GSE4218",
+        "GSE90604",
+        "GSE58345",
+        "GSE126550",
+        "GSE54792",
+        "GSE133116",
+        "GSE58530",
+        "GSE213876",
+        "GSE278511",
+        "GSE48865",
+        "GSE229416",
+        "GSE230393",
+        "GSE91014",
+        "GSE180889",
+        "GSE147526",
+        "GSE128541",
+        "GSE261618",
+        "GSE118792",
+        "GSE150395",
+        "GSE98126",
+        "GSE151506",
+        "GSE25965",
+        "GSE247299",
+        "GSE122488",
+        "GSE16666",
+        "GSE122679",
+        "GSE283049",
+        "GSE60705",
+        "GSE145510",
+        "GSE119102",
+        "GSE10774",
+        "GSE241149",
+        "GSE141241",
+        "GSE235676",
+        "GSE12737",
+        "GSE232050",
+        "GSE242231",
+        "GSE139233",
+        "GSE158016",
+        "GSE100775",
+        "GSE83300",
+        "GSE37985",
+        "GSE208634",
+        "GSE138890",
+        "GSE5082",
+        "GSE148467",
+        "GSE77487",
+        "GSE49377",
+        "GSE217344",
+        "GSE118092",
+        "GSE175863",
+        "GSE72955",
+        "GSE79772",
+        "GSE21026",
+        "GSE12305",
+        "GSE230824",
+        "GSE209807",
+        "GSE72218",
+        "GSE25632",
+        "GSE78703",
+        "GSE38008",
+        "GSE104296",
+        "GSE164105",
+        "GSE83130",
+        "GSE46686",
+        "GSE92459",
+        "GSE61710",
+        "GSE76146",
+        "GSE114222",
+        "GSE72476",
+        "GSE226468",
+        "GSE194222",
+        "GSE103559",
+        "GSE186341",
+        "GSE276838",
+        "GSE226726",
+        "GSE18166",
+        "GSE180464",
+        "GSE49009",
+        "GSE200647",
+        "GSE173784",
+        "GSE119711",
+        "GSE7344",
+        "GSE9385",
+        "GSE108013",
+        "GSE108088",
+        "GSE90547",
+        "GSE54162",
+        "GSE145933",
+        "GSE277539",
+        "GSE274966",
+        "GSE27144",
+        "GSE13470",
+        "GSE162643",
+        "GSE53229",
+        "GSE14822",
+        "GSE149845",
+        "GSE228785",
+        "GSE12350",
+        "GSE126253",
+        "GSE136644",
+        "GSE133211",
+        "GSE99045",
+        "GSE124877",
+        "GSE223280",
+        "GSE185029",
+        "GSE63296",
+        "GSE111806",
+        "GSE213269",
+        "GSE113961",
+        "GSE145699",
+        "GSE180981",
+        "GSE217347",
+        "GSE161438",
+        "GSE262681",
+        "GSE103229",
+        "GSE229962",
+        "GSE1993",
+        "GSE112650",
+        "GSE264713",
+        "GSE222481",
+        "GSE51253",
+        "GSE22821",
+        "GSE94765",
+        "GSE188773",
+        "GSE25631",
+        "GSE74187",
+        "GSE86511",
+        "GSE97349",
+        "GSE112810",
+        "GSE55712",
+        "GSE108870",
+        "GSE223607",
+        "GSE237053",
+        "GSE4058",
+        "GSE72209",
+        "GSE131502",
+        "GSE121092",
+        "GSE47809",
+        "GSE25012",
+        "GSE173146",
+        "GSE237779",
+        "GSE154789",
+        "GSE40776",
+        "GSE61335",
+        "GSE36902",
+        "GSE99171",
+        "GSE195896",
+        "GSE97632",
+        "GSE68928",
+        "GSE95164",
+        "GSE128255",
+        "GSE176187",
+        "GSE137901",
+        "GSE42669",
+        "GSE112902",
+        "GSE264186",
+        "GSE117448",
+        "GSE271379",
+        "GSE186736",
+        "GSE222192",
+        "GSE166351",
+        "GSE224727",
+        "GSE238012",
+        "GSE232504",
+        "GSE139448",
+        "GSE116012",
+        "GSE134676",
+        "GSE5720",
+        "GSE19578",
+        "GSE144204",
+        "GSE45265",
+        "GSE68086",
+        "GSE49224",
+        "GSE270109",
+        "GSE34152",
+        "GSE225869",
+        "GSE206170",
+        "GSE128536",
+        "GSE163949",
+        "GSE65626",
+        "GSE166877",
+        "GSE158020",
+        "GSE89399",
+        "GSE106159",
+        "GSE146463",
+        "GSE157910",
+        "GSE14804",
+        "GSE227059",
+        "GSE158740",
+        "GSE67986",
+        "GSE113474",
+        "GSE114456",
+        "GSE7806",
+        "GSE225975",
+        "GSE99385",
+        "GSE184859",
+        "GSE72468",
+        "GSE44728",
+        "GSE80639",
+        "GSE135349",
+        "GSE200031",
+        "GSE269962",
+        "GSE123519",
+        "GSE29682",
+        "GSE266143",
+        "GSE171500",
+        "GSE223297",
+        "GSE119774",
+        "GSE201960",
+        "GSE130857",
+        "GSE92458",
+        "GSE174634",
+        "GSE155985",
+        "GSE8049",
+        "GSE121332",
+        "GSE18015",
+        "GSE133117",
+        "GSE26082",
+        "GSE185269",
+        "GSE226647",
+        "GSE165926",
+        "GSE118793",
+        "GSE280891",
+        "GSE99175",
+        "GSE171163",
+        "GSE35191",
+        "GSE174177",
+        "GSE237673",
+        "GSE113512",
+        "GSE182373",
+        "GSE210736",
+        "GSE107558",
+        "GSE227721",
+        "GSE186332",
+        "GSE178114",
+        "GSE11778",
+        "GSE155809",
+        "GSE79478",
+        "GSE46015",
+        "GSE178113",
+        "GSE135210",
+        "GSE80399",
+        "GSE274548",
+        "GSE226700",
+        "GSE212616",
+        "GSE73199",
+        "GSE91393",
+        "GSE155836",
+        "GSE109982",
+        "GSE148739",
+        "GSE145557",
+        "GSE166418",
+        "GSE211148",
+        "GSE138060",
+        "GSE112645",
+        "GSE129142",
+        "GSE111231",
+        "GSE63533",
+        "GSE249282",
+        "GSE158175",
+        "GSE277823",
+        "GSE59612",
+        "GSE52582",
+        "GSE53014",
+        "GSE143887",
+        "GSE225971",
+        "GSE174295",
+        "GSE62802",
+        "GSE179356",
+        "GSE137453",
+        "GSE92612",
+        "GSE159416",
+        "GSE27584",
+        "GSE58277",
+        "GSE35158",
+        "GSE121723",
+        "GSE276101",
+        "GSE264695",
+        "GSE241281",
+        "GSE202764",
+        "GSE86237",
+        "GSE193884",
+        "GSE242966",
+        "GSE156522",
+        "GSE229966",
+        "GSE84134",
+        "GSE215420",
+        "GSE207753",
+        "GSE63535",
+        "GSE147329",
+        "GSE49810",
+        "GSE158550",
+        "GSE212067",
+        "GSE36247",
+        "GSE64667",
+        "GSE183772",
+        "GSE49162",
+        "GSE142119",
+        "GSE148196",
+        "GSE32283",
+        "GSE226292",
+        "GSE104806",
+        "GSE108958",
+        "GSE108742",
+        "GSE175851",
+        "GSE120793",
+        "GSE42515",
+        "GSE26068",
+        "GSE195681",
+        "GSE115397",
+        "GSE35444",
+        "GSE264374",
+        "GSE184567",
+        "GSE193525",
+        "GSE118790",
+        "GSE23935",
+        "GSE80137",
+        "GSE60806",
+        "GSE218668",
+        "GSE148779",
+        "GSE190816",
+        "GSE130407",
+        "GSE82183",
+        "GSE124727",
+        "GSE143495",
+        "GSE68936",
+        "GSE83626",
+        "GSE13991",
+        "GSE122994",
+        "GSE178371",
+        "GSE229967",
+        "GSE159896",
+        "GSE248634",
+        "GSE224149",
+        "GSE56113",
+        "GSE182942",
+        "GSE246708",
+        "GSE240822",
+        "GSE173278",
+        "GSE95157",
+        "GSE168038",
+        "GSE122498",
+        "GSE134972",
+        "GSE266210",
+        "GSE242570",
+        "GSE223065",
+        "GSE148949",
+        "GSE74557",
+        "GSE53733",
+        "GSE150630",
+        "GSE81043",
+        "GSE136974",
+        "GSE241273",
+        "GSE132554",
+        "GSE138737",
+        "GSE212246",
+        "GSE50924",
+        "GSE40698",
+        "GSE7330",
+        "GSE141945",
+        "GSE245488",
+        "GSE39242",
+        "GSE4717",
+        "GSE121655",
+        "GSE123414",
+        "GSE44841",
+        "GSE193495",
+        "GSE254461",
+        "GSE199032",
+        "GSE206917",
+        "GSE220083",
+        "GSE243865",
+        "GSE103227",
+        "GSE199030",
+        "GSE277282",
+        "GSE64072",
+        "GSE176578",
+        "GSE261188",
+        "GSE79734",
+        "GSE248471",
+        "GSE245854",
+        "GSE106482",
+        "GSE196490",
+        "GSE82139",
+        "GSE211724",
+        "GSE37737",
+        "GSE44931",
+        "GSE182374",
+        "GSE237103",
+        "GSE86348",
+        "GSE15191",
+        "GSE243132",
+        "GSE190804",
+        "GSE74084",
+        "GSE117599",
+        "GSE110868",
+        "GSE74516",
+        "GSE93991",
+        "GSE167746",
+        "GSE259262",
+        "GSE203074",
+        "GSE125587",
+        "GSE77030",
+        "GSE60818",
+        "GSE73262",
+        "GSE198523",
+        "GSE161528",
+        "GSE129476",
+        "GSE52419",
+        "GSE99979",
+        "GSE98330",
+        "GSE160875",
+        "GSE182375",
+        "GSE119637",
+        "GSE119834",
+        "GSE45394",
+        "GSE113816",
+        "GSE230770",
+        "GSE19728",
+        "GSE131928",
+        "GSE72475",
+        "GSE126892",
+        "GSE221376",
+        "GSE20018",
+        "GSE218043",
+        "GSE32374",
+        "GSE255754",
+        "GSE38589",
+        "GSE19422",
+        "GSE236661",
+        "GSE184451",
+        "GSE24446",
+        "GSE168040",
+        "GSE23839",
+        "GSE61281",
+        "GSE22891",
+        "GSE56316",
+        "GSE43289",
+        "GSE56752",
+        "GSE228008",
+        "GSE100013",
+        "GSE201557",
+        "GSE110767",
+        "GSE157608",
+        "GSE122809",
+        "GSE57978",
+        "GSE236570",
+        "GSE145556",
+        "GSE130648",
+        "GSE112240",
+        "GSE93680",
+        "GSE36201",
+        "GSE288052",
+        "GSE245634",
+        "GSE29692",
+        "GSE178458",
+        "GSE158742",
+        "GSE225775",
+        "GSE259352",
+        "GSE159851",
+        "GSE41824",
+        "GSE31586",
+        "GSE138113",
+        "GSE120647",
+        "GSE163853",
+        "GSE207452",
+        "GSE52363",
+        "GSE111260",
+        "GSE266621",
+        "GSE174554",
+        "GSE263766",
+        "GSE159456",
+        "GSE193180",
+        "GSE74754",
+        "GSE83344",
+        "GSE235648",
+        "GSE121717",
+        "GSE86213",
+        "GSE147342",
+        "GSE15824",
+        "GSE64965",
+        "GSE205062",
+        "GSE227722",
+        "GSE59116",
+        "GSE116414",
+        "GSE272042",
+        "GSE10221",
+        "GSE146440",
+        "GSE15134",
+        "GSE156739",
+        "GSE135437",
+        "GSE57488",
+        "GSE118983",
+        "GSE177549",
+        "GSE98849",
+        "GSE217346",
+        "GSE152147",
+        "GSE240343",
+        "GSE155807",
+        "GSE150986",
+        "GSE199143",
+        "GSE109398",
+        "GSE234128",
+        "GSE202362",
+        "GSE2223",
+        "GSE102505",
+        "GSE208698",
+        "GSE107581",
+        "GSE44713",
+        "GSE252489",
+        "GSE247079",
+        "GSE66200",
+        "GSE32335",
+        "GSE24072",
+        "GSE245303",
+        "GSE39223",
+        "GSE3254",
+        "GSE136738",
+        "GSE49161",
+        "GSE256492",
+        "GSE135408",
+        "GSE226721",
+        "GSE199375",
+        "GSE201639",
+        "GSE179924",
+        "GSE255536",
+        "GSE282324",
+        "GSE188228",
+        "GSE166979",
+        "GSE214006",
+        "GSE27523",
+        "GSE183776",
+        "GSE149366",
+        "GSE4482",
+        "GSE143842",
+        "GSE106775",
+        "GSE30730",
+        "GSE74304",
+        "GSE249289",
+        "GSE160417",
+        "GSE158551",
+        "GSE30043",
+        "GSE42658",
+        "GSE32662",
+        "GSE195813",
+        "GSE14823",
+        "GSE51822",
+        "GSE100675",
+        "GSE68071",
+        "GSE277011",
+        "GSE250617",
+        "GSE200062",
+        "GSE173801",
+        "GSE44843",
+        "GSE266140",
+        "GSE139250",
+        "GSE213013",
+        "GSE139139",
+        "GSE145940",
+        "GSE51663",
+        "GSE10878",
+        "GSE16119",
+        "GSE95289",
+        "GSE215239",
+        "GSE26328",
+        "GSE182282",
+        "GSE163044",
+        "GSE125255",
+        "GSE156819",
+        "GSE200341",
+        "GSE58921",
+        "GSE201553",
+        "GSE35493",
+        "GSE112733",
+        "GSE117544",
+        "GSE111462",
+        "GSE79876",
+        "GSE128547",
+        "GSE110152",
+        "GSE20736",
+        "GSE63694",
+        "GSE117685",
+        "GSE73243",
+        "GSE274910",
+        "GSE139415",
+        "GSE22867",
+        "GSE200984",
+        "GSE121720",
+        "GSE139826",
+        "GSE123344",
+        "GSE194221",
+        "GSE138236",
+        "GSE71769",
+        "GSE92375",
+        "GSE138620",
+        "GSE18899",
+        "GSE80338",
+        "GSE143934",
+        "GSE157488",
+        "GSE73556",
+        "GSE108085",
+        "GSE229210",
+        "GSE121998",
+        "GSE237936",
+        "GSE111458",
+        "GSE125621",
+        "GSE273171",
+        "GSE40299",
+        "GSE149324",
+        "GSE190638",
+        "GSE14945",
+        "GSE195684",
+        "GSE161572",
+        "GSE145645",
+        "GSE243836",
+        "GSE15116",
+        "GSE33912",
+        "GSE179439",
+        "GSE208618",
+        "GSE33483",
+        "GSE50756",
+        "GSE81879",
+        "GSE58218",
+        "GSE60530",
+        "GSE100398",
+        "GSE181372",
+        "GSE159609",
+        "GSE200348",
+        "GSE31126",
+        "GSE162429",
+        "GSE165391",
+        "GSE32474",
+        "GSE155434",
+        "GSE131399",
+        "GSE248995",
+        "GSE217349",
+        "GSE150615",
+        "GSE53504",
+        "GSE26196",
+        "GSE180465",
+        "GSE185569",
+        "GSE163833",
+        "GSE179077",
+        "GSE220909",
+        "GSE246295",
+        "GSE161440",
+        "GSE139018",
+        "GSE240704",
+        "GSE108476",
+        "GSE81353",
+        "GSE82009",
+        "GSE176539",
+        "GSE113149",
+        "GSE276177",
+        "GSE7427",
+        "GSE103274",
+        "GSE158097",
+        "GSE245853",
+        "GSE51395",
+        "GSE161534",
+        "GSE24100",
+        "GSE153680",
+        "GSE182169",
+        "GSE163185",
+        "GSE77307",
+        "GSE195848",
+        "GSE168115",
+        "GSE72927",
+        "GSE168037",
+        "GSE139533",
+        "GSE246895",
+        "GSE151852",
+        "GSE120066",
+        "GSE50227",
+        "GSE140819",
+        "GSE239651",
+        "GSE171227",
+        "GSE117126",
+        "GSE41875",
+        "GSE183910",
+        "GSE117905",
+        "GSE85539",
+        "GSE77475",
+        "GSE244301",
+        "GSE273013",
+        "GSE107559",
+        "GSE2727",
+        "GSE36900",
+        "GSE200902",
+        "GSE255502",
+        "GSE41470",
+        "GSE50047",
+        "GSE227098",
+        "GSE9171",
+        "GSE159702",
+        "GSE245800",
+        "GSE32482",
+        "GSE116545",
+        "GSE53220",
+        "GSE214466",
+        "GSE7181",
+        "GSE158549",
+        "GSE50173",
+        "GSE265971",
+        "GSE244666",
+        "GSE245043",
+        "GSE195680",
+        "GSE197762",
+        "GSE42400",
+        "GSE143189",
+        "GSE263685",
+        "GSE86574",
+        "GSE117832",
+        "GSE139238",
+        "GSE163071",
+        "GSE127989",
+        "GSE134973",
+        "GSE89201",
+        "GSE113361",
+        "GSE119776",
+        "GSE198439",
+        "GSE75592",
+        "GSE50923",
+        "GSE169286",
+        "GSE86202",
+        "GSE95386",
+        "GSE244893",
+        "GSE1128",
+        "GSE255581",
+        "GSE159738",
+        "GSE211272",
+        "GSE152575",
+        "GSE240676",
+        "GSE244579",
+        "GSE8315",
+        "GSE213308",
+        "GSE58646",
+        "GSE273250",
+        "GSE14079",
+        "GSE75254",
+        "GSE182685",
+        "GSE99181",
+        "GSE198855",
+        "GSE241396",
+        "GSE112734",
+        "GSE68030",
+        "GSE95392",
+        "GSE112241",
+        "GSE71116",
+        "GSE112648",
+        "GSE236568",
+        "GSE174308",
+        "GSE211462",
+        "GSE39292",
+        "GSE101148",
+        "GSE76652",
+        "GSE30034",
+        "GSE37120",
+        "GSE35453",
+        "GSE63536",
+        "GSE117258",
+        "GSE263588",
+        "GSE133471",
+        "GSE108343",
+        "GSE163021",
+        "GSE42355",
+        "GSE54077",
+        "GSE215240",
+        "GSE79671",
+        "GSE205590",
+        "GSE236082",
+        "GSE11233",
+        "GSE100351",
+        "GSE185861",
+        "GSE150604",
+        "GSE159880",
+        "GSE85697",
+        "GSE10758",
+        "GSE106804",
+        "GSE107047",
+        "GSE18804",
+        "GSE182697",
+        "GSE222520",
+        "GSE238199",
+        "GSE186442",
+        "GSE155839",
+        "GSE241284",
+        "GSE146197",
+        "GSE192710",
+        "GSE42401",
+        "GSE79896",
+        "GSE53800",
+        "GSE15309",
+        "GSE10007",
+        "GSE205512",
+        "GSE79302",
+        "GSE112651",
+        "GSE74561",
+        "GSE185873",
+        "GSE103659",
+        "GSE20633",
+        "GSE87535",
+        "GSE29458",
+        "GSE155834",
+        "GSE201975",
+        "GSE263890",
+        "GSE40265",
+        "GSE140297",
+        "GSE20306",
+        "GSE216888",
+        "GSE109569",
+        "GSE112462",
+        "GSE140002",
+        "GSE272737",
+        "GSE34824",
+        "GSE62731",
+        "GSE184472",
+        "GSE271448",
+        "GSE152160",
+        "GSE201977",
+        "GSE211554",
+        "GSE225191",
+        "GSE124769",
+        "GSE10922",
+        "GSE61388",
+        "GSE154958",
+        "GSE58401",
+        "GSE38815",
+        "GSE85024",
+        "GSE28618",
+        "GSE156663",
+        "GSE162831",
+        "GSE161573",
+        "GSE45301",
+        "GSE181366",
+        "GSE162783",
+        "GSE21045",
+        "GSE253152",
+        "GSE121721",
+        "GSE138622",
+        "GSE64637",
+        "GSE102244",
+        "GSE190953",
+        "GSE1902",
+        "GSE193957",
+        "GSE153982",
+        "GSE61078",
+        "GSE129908",
+        "GSE17047",
+        "GSE103455",
+        "GSE13276",
+        "GSE138618",
+        "GSE249637",
+        "GSE230389",
+        "GSE100623",
+        "GSE145559",
+        "GSE180895",
+        "GSE168039",
+        "GSE96088",
+        "GSE72477",
+        "GSE143755",
+        "GSE12836",
+        "GSE165390",
+        "GSE43674",
+        "GSE63387",
+        "GSE7426",
+        "GSE68995",
+        "GSE101980",
+        "GSE138794",
+        "GSE118960",
+        "GSE271707",
+        "GSE213592",
+        "GSE206225",
+        "GSE102136",
+        "GSE74571",
+        "GSE184696",
+        "GSE35239",
+        "GSE206357",
+        "GSE165386",
+        "GSE242790",
+        "GSE190504",
+        "GSE99361",
+        "GSE97071",
+        "GSE249636",
+        "GSE283576",
+        "GSE110890",
+        "GSE246154",
+        "GSE216626",
+        "GSE7696",
+        "GSE221971",
+        "GSE126212",
+        "GSE19112",
+        "GSE72204",
+        "GSE110130",
+        "GSE161523",
+        "GSE261440",
+        "GSE163120",
+        "GSE137310",
+        "GSE241227",
+        "GSE129877",
+        "GSE273621",
+        "GSE134974",
+        "GSE154133",
+        "GSE238071",
+        "GSE203154",
+        "GSE61706",
+        "GSE46016",
+        "GSE232725",
+        "GSE4536",
+        "GSE133095",
+        "GSE46531",
+        "GSE235438",
+        "GSE40328",
+        "GSE119755",
+        "GSE64661",
+        "GSE260701",
+        "GSE68850",
+        "GSE224090",
+        "GSE19846",
+        "GSE244868",
+        "GSE279073",
+        "GSE221580",
+        "GSE143843",
+        "GSE277014",
+        "GSE133470",
+        "GSE13214",
+        "GSE213307",
+        "GSE130220",
+        "GSE9177",
+        "GSE181378",
+        "GSE51301",
+        "GSE116621",
+        "GSE61705",
+        "GSE121810",
+        "GSE229600",
+        "GSE183221",
+        "GSE114867",
+        "GSE79889",
+        "GSE245635",
+        "GSE266154",
+        "GSE261190",
+        "GSE232469",
+        "GSE111676",
+        "GSE125243",
+        "GSE159747",
+        "GSE32883",
+        "GSE108848",
+        "GSE37475",
+        "GSE276176",
+        "GSE142827",
+        "GSE208074",
+        "GSE2485",
+        "GSE214967",
+        "GSE249155",
+        "GSE37956",
+        "GSE144623",
+        "GSE137808",
+        "GSE214252",
+        "GSE229673",
+        "GSE39747",
+        "GSE45185",
+        "GSE165389",
+        "GSE35603",
+        "GSE120627",
+        "GSE245919",
+        "GSE73127",
+        "GSE102294",
+        "GSE150612",
+        "GSE162931",
+        "GSE51146",
+        "GSE162631",
+        "GSE127895",
+        "GSE94693",
+        "GSE70175",
+        "GSE181379",
+        "GSE215365",
+        "GSE118683",
+        "GSE8692",
+        "GSE12657",
+        "GSE32876",
+        "GSE133479",
+        "GSE233640",
+        "GSE154043",
+        "GSE253222",
+        "GSE128195",
+        "GSE46538",
+        "GSE261187",
+        "GSE53042",
+        "GSE207288",
+        "GSE88320",
+        "GSE283387",
+        "GSE183211",
+        "GSE155808",
+        "GSE57872",
+        "GSE114438",
+        "GSE274633",
+        "GSE75789",
+        "GSE119468",
+        "GSE136829",
+        "GSE75910",
+        "GSE205591",
+        "GSE56937",
+        "GSE115459",
+        "GSE12694",
+        "GSE46688",
+        "GSE247800",
+        "GSE199407",
+        "GSE141961",
+        "GSE236478",
+        "GSE24716",
+        "GSE26344",
+        "GSE60274",
+        "GSE21570",
+        "GSE167300",
+        "GSE251908",
+        "GSE253400",
+        "GSE74610",
+        "GSE22385",
+        "GSE188393",
+        "GSE8569",
+        "GSE194329",
+        "GSE72217",
+        "GSE49808",
+        "GSE181146",
+        "GSE13021",
+        "GSE98366",
+        "GSE222560",
+        "GSE83511",
+        "GSE233304",
+        "GSE259378",
+        "GSE60921",
+        "GSE208697",
+        "GSE49412",
+        "GSE116531",
+        "GSE52319",
+        "GSE145374",
+        "GSE234832",
+        "GSE29384",
+        "GSE36245",
+        "GSE156902",
+        "GSE74520",
+        "GSE276299",
+        "GSE163108",
+        "GSE231555",
+        "GSE85033",
+        "GSE18890",
+        "GSE26676",
+        "GSE183773",
+        "GSE164352",
+        "GSE162986",
+        "GSE86519",
+        "GSE64411",
+        "GSE114574",
+        "GSE166111",
+        "GSE202484",
+        "GSE31545",
+        "GSE178471",
+        "GSE40770",
+        "GSE72219",
+        "GSE123755",
+        "GSE173279",
+        "GSE30291",
+        "GSE129972",
+        "GSE263832",
+        "GSE119586",
+        "GSE83756",
+        "GSE192823",
+        "GSE137454",
+        "GSE48433",
+        "GSE261471",
+        "GSE16805",
+        "GSE197990",
+        "GSE122920",
+        "GSE149009",
+        "GSE133509",
+        "GSE113261",
+        "GSE205538",
+        "GSE117423",
+        "GSE240490",
+        "GSE245624",
+        "GSE260700",
+        "GSE147382",
+        "GSE247884",
+        "GSE81287",
+        "GSE134470",
+        "GSE261132",
+        "GSE108957",
+        "GSE122486",
+        "GSE102924",
+        "GSE221949",
+        "GSE87411",
+        "GSE28860",
+        "GSE71538",
+        "GSE46226",
+        "GSE44151",
+        "GSE196067",
+        "GSE36354",
+        "GSE13030",
+        "GSE30563",
+        "GSE72203",
+        "GSE246936",
+        "GSE171872",
+        "GSE240492",
+        "GSE150676",
+        "GSE126073",
+        "GSE30472",
+        "GSE188739",
+        "GSE14819",
+        "GSE224941",
+        "GSE194220",
+        "GSE104783",
+        "GSE149334",
+        "GSE135306",
+        "GSE136330",
+        "GSE112735",
+        "GSE106810",
+        "GSE199033",
+        "GSE241037",
+        "GSE77530",
+        "GSE90598",
+        "GSE99183",
+        "GSE14",
+        "GSE126840",
+        "GSE33328",
+        "GSE111571",
+        "GSE110066",
+        "GSE179004",
+        "GSE60704",
+        "GSE151155",
+        "GSE73573",
+        "GSE189650",
+        "GSE184698",
+        "GSE239610",
+        "GSE42656",
+        "GSE121719",
+        "GSE189781",
+        "GSE165595",
+        "GSE79877",
+        "GSE153746",
+        "GSE154337",
+        "GSE122807",
+        "GSE232173",
+        "GSE165937",
+        "GSE63534",
+        "GSE226765",
+        "GSE180621",
+        "GSE233867",
+        "GSE151352",
+        "GSE103228",
+        "GSE154042",
+        "GSE89398",
+        "GSE14889",
+        "GSE225210",
+        "GSE77998",
+        "GSE67633",
+        "GSE42618",
+        "GSE65910",
+        "GSE217366",
+        "GSE207726",
+        "GSE179667",
+        "GSE51336",
+        "GSE1989",
+        "GSE152612",
+        "GSE78895",
+        "GSE239847",
+        "GSE187418",
+        "GSE156820",
+        "GSE163655",
+        "GSE189517",
+        "GSE40833",
+        "GSE62714",
+        "GSE277015",
+        "GSE208323",
+        "GSE48079",
+        "GSE24557",
+        "GSE163401",
+        "GSE270493",
+        "GSE226293",
+        "GSE147595",
+        "GSE115840",
+        "GSE213554",
+        "GSE138077",
+        "GSE91391",
+        "GSE179087",
+        "GSE243575",
+        "GSE95216",
+        "GSE7233",
+        "GSE25272",
+        "GSE228497",
+        "GSE153908",
+        "GSE146698",
+        "GSE163400",
+        "GSE75906",
+        "GSE262708",
+        "GSE21143",
+        "GSE254874",
+        "GSE123760",
+        "GSE161437",
+        "GSE26313",
+        "GSE43911",
+        "GSE226172",
+        "GSE32293",
+        "GSE152861",
+        "GSE85297",
+        "GSE279423",
+        "GSE95106",
+        "GSE212086",
+        "GSE273464",
+        "GSE104653",
+        "GSE58922",
+        "GSE81465",
+        "GSE270855",
+        "GSE14824",
+        "GSE184695",
+        "GSE233532",
+        "GSE122832",
+        "GSE36278",
+        "GSE154060",
+        "GSE118093",
+        "GSE19114",
+        "GSE244497",
+        "GSE147352",
+        "GSE107560",
+        "GSE103963",
+        "GSE157779",
+        "GSE215123",
+        "GSE128654",
+        "GSE151680",
+        "GSE196141",
+        "GSE179649",
+        "GSE87615",
+        "GSE253407",
+        "GSE206551",
+        "GSE201976",
+        "GSE256491",
+        "GSE234125",
+        "GSE87515",
+        "GSE164104",
+        "GSE245855",
+        "GSE217348",
+        "GSE75189",
+        "GSE28271",
+        "GSE156821",
+        "GSE271928",
+        "GSE240119",
+        "GSE65878",
+        "GSE121422",
+        "GSE228512",
+        "GSE42577",
+        "GSE4290",
+        "GSE109867",
+        "GSE1991",
+        "GSE261684",
+        "GSE103366",
+        "GSE149910",
+        "GSE55363",
+        "GSE56517",
+        "GSE44099",
+        "GSE91016",
+        "GSE199364",
+        "GSE110866",
+        "GSE163906",
+        "GSE93850",
+        "GSE128555",
+        "GSE134404",
+        "GSE116520",
+        "GSE65911",
+        "GSE15209",
+        "GSE78025",
+        "GSE282325",
+        "GSE25411",
+        "GSE158284",
+        "GSE30700",
+        "GSE79338",
+        "GSE98128",
+        "GSE178147",
+        "GSE174617",
+        "GSE127273",
+        "GSE72732",
+        "GSE69081",
+        "GSE110424",
+        "GSE22772",
+        "GSE59967",
+        "GSE249657",
+        "GSE196175",
+        "GSE53124",
+        "GSE110867",
+        "GSE61002",
+        "GSE140272",
+        "GSE63537",
+        "GSE9200",
+        "GSE158803",
+        "GSE262598",
+        "GSE75443",
+        "GSE96911",
+        "GSE222515",
+        "GSE199862",
+        "GSE7428",
+        "GSE61852",
+        "GSE222971",
+        "GSE159000",
+        "GSE44842",
+        "GSE268426",
+        "GSE242044",
+        "GSE95680",
+        "GSE229409",
+        "GSE79878",
+        "GSE235207",
+        "GSE192874",
+        "GSE4217",
+        "GSE218041",
+        "GSE235672",
+        "GSE246697",
+        "GSE161175",
+        "GSE239379",
+        "GSE137830",
+        "GSE123821",
+        "GSE138092",
+        "GSE17381",
+        "GSE24717",
+        "GSE202371",
+        "GSE76184",
+        "GSE24558",
+        "GSE79735",
+        "GSE90459",
+        "GSE35917",
+        "GSE266141",
+        "GSE89456",
+        "GSE199031",
+        "GSE133041",
+        "GSE196695",
+        "GSE39413",
+        "GSE141946",
+        "GSE193745",
+        "GSE72538",
+        "GSE58298",
+        "GSE58525",
+        "GSE207046",
+        "GSE178236",
+        "GSE143609",
+        "GSE32466",
+        "GSE225964",
+        "GSE142825",
+        "GSE109330",
+        "GSE255535",
+        "GSE71224",
+        "GSE197062",
+        "GSE132172",
+        "GSE61445",
+        "GSE100146",
+        "GSE15805",
+        "GSE18150",
+        "GSE134711",
+        "GSE131660",
+        "GSE30800",
+        "GSE98824",
+        "GSE203260",
+        "GSE139380",
+        "GSE6109",
+        "GSE131402",
+        "GSE42670",
+        "GSE19720",
+        "GSE36337",
+        "GSE90603",
+        "GSE54142",
+        "GSE185474",
+        "GSE153679",
+        "GSE156194",
+        "GSE65576",
+        "GSE14507",
+        "GSE199376",
+        "GSE75147",
+        "GSE88106",
+        "GSE75589",
+        "GSE256493",
+        "GSE266130",
+        "GSE36947",
+        "GSE4817",
+        "GSE217031",
+        "GSE198522",
+        "GSE138662",
+        "GSE108998",
+        "GSE198547",
+        "GSE49822",
+        "GSE72269",
+        "GSE195640",
+        "GSE92460",
+        "GSE33213",
+        "GSE197728",
+        "GSE263756",
+        "GSE142719",
+        "GSE169418",
+        "GSE185955",
+        "GSE159889",
+        "GSE148686",
+        "GSE35454",
+        "GSE183004",
+        "GSE108089",
+        "GSE233971",
+        "GSE241247",
+        "GSE14805",
+        "GSE181650",
+        "GSE188771",
+        "GSE138535",
+        "GSE268342",
+        "GSE122871",
+        "GSE74052",
+        "GSE128961",
+        "GSE68994",
+        "GSE268118",
+        "GSE39221",
+        "GSE9635",
+        "GSE256490",
+        "GSE193178",
+        "GSE281549",
+        "GSE276102",
+        "GSE129976",
+        "GSE14821",
+        "GSE185420",
+        "GSE55362",
+        "GSE188772",
+        "GSE233380",
+        "GSE181274",
+        "GSE178337",
+        "GSE12689",
+        "GSE137879",
+        "GSE98797",
+        "GSE226976",
+        "GSE142210",
+        "GSE58923",
+        "GSE61079",
+        "GSE139136",
+        "GSE92322",
+        "GSE266144",
+        "GSE247890",
+        "GSE89409",
+        "GSE148685",
+        "GSE208696",
+        "GSE129671",
+        "GSE94874",
+        "GSE42631",
+        "GSE193729",
+        "GSE150614",
+        "GSE236486",
+        "GSE212941",
+        "GSE110869",
+        "GSE171287",
+        "GSE29738",
+        "GSE46014",
+        "GSE201657",
+        "GSE181145",
+        "GSE49416",
+        "GSE178623",
+        "GSE190950",
+        "GSE186392",
+        "GSE212171",
+        "GSE151547",
+        "GSE158700",
+        "GSE46599",
+        "GSE73120",
+        "GSE241039",
+        "GSE108749",
+        "GSE115509",
+        "GSE273274",
+        "GSE129974",
+        "GSE214907",
+        "GSE168004",
+        "GSE273012",
+        "GSE150680",
+        "GSE39144",
+        "GSE200146",
+        "GSE56750",
+        "GSE51413",
+        "GSE188226",
+        "GSE11848",
+        "GSE68950",
+        "GSE28026",
+        "GSE134567",
+        "GSE182670",
+        "GSE274546",
+        "GSE174470",
+        "GSE84010",
+        "GSE45874",
+        "GSE145644",
+        "GSE68661",
+        "GSE188924",
+        "GSE45307",
+        "GSE280761",
+        "GSE186443",
+        "GSE46190",
+        "GSE81314",
+        "GSE229866",
+        "GSE145932",
+        "GSE217515",
+        "GSE28040",
+        "GSE26283",
+        "GSE108098",
+        "GSE54004",
+        "GSE150956",
+        "GSE274460",
+        "GSE217511",
+        "GSE112736",
+        "GSE47997",
+        "GSE118791",
+        "GSE271170",
+        "GSE72202",
+        "GSE163186",
+        "GSE45117",
+        "GSE119592",
+        "GSE52581",
+        "GSE238010",
+        "GSE149485",
+        "GSE240418",
+        "GSE152858",
+        "GSE135062",
+        "GSE233868",
+        "GSE208616",
+        "GSE108658",
+        "GSE188227",
+        "GSE223063",
+        "GSE211725",
+        "GSE6042",
+        "GSE117838",
+        "GSE132825",
+        "GSE104267",
+        "GSE232040",
+        "GSE175862",
+        "GSE195567",
+        "GSE196320",
+        "GSE231577",
+        "GSE107601",
+        "GSE14878",
+        "GSE344",
+        "GSE226990",
+        "GSE14820",
+        "GSE141944",
+        "GSE229940",
+        "GSE75003",
+        "GSE66177",
+        "GSE154367",
+        "GSE21336",
+        "GSE148542",
+        "GSE9885",
+        "GSE32692",
+        "GSE22692",
+        "GSE155994",
+        "GSE139417",
+        "GSE90886",
+        "GSE68029",
+        "GSE23806",
+        "GSE25630",
+        "GSE81473",
+        "GSE62212",
+        "GSE58924",
+        "GSE92483",
+        "GSE111627",
+        "GSE65526",
+        "GSE186440",
+        "GSE186047",
+        "GSE117543",
+        "GSE159739",
+        "GSE185463",
+        "GSE146358",
+        "GSE140441",
+        "GSE285543",
+        "GSE137934",
+        "GSE18798",
+        "GSE196694",
+        "GSE130324",
+        "GSE60706",
+        "GSE1923",
+        "GSE19678",
+        "GSE267458",
+        "GSE32465",
+        "GSE134045",
+        "GSE31262",
+        "GSE34989",
+        "GSE61704",
+        "GSE273252",
+        "GSE18892",
+        "GSE188958",
+        "GSE38330",
+        "GSE118684",
+        "GSE106557",
+        "GSE109399",
+        "GSE107932",
+        "GSE47620",
+        "GSE51411",
+        "GSE101799",
+        "GSE60507",
+        "GSE97347",
+        "GSE185758",
+        "GSE40699",
+        "GSE96682",
+        "GSE87617",
+        "GSE161574",
+        "GSE184398",
+        "GSE271072",
+        "GSE24084",
+        "GSE32286",
+        "GSE249656",
+        "GSE42657",
+        "GSE5949",
+        "GSE193179",
+        "GSE229419",
+        "GSE33362",
+        "GSE105773",
+        "GSE10547",
+        "GSE191021",
+        "GSE151414",
+        "GSE197879",
+        "GSE255850",
+        "GSE181314",
+        "GSE17227",
+        "GSE80821",
+        "GSE136751",
+        "GSE97350",
+        "GSE129978",
+        "GSE195682",
+        "GSE41685",
+        "GSE106545",
+        "GSE207725",
+        "GSE214965",
+        "GSE29796",
+        "GSE4328",
+        "GSE149303",
+        "GSE63319",
+        "GSE231595",
+        "GSE78666",
+        "GSE273251",
+        "GSE100736",
+        "GSE58399",
+        "GSE224942",
+        "GSE52009",
+        "GSE126503",
+        "GSE94808",
+        "GSE267976",
+        "GSE278988",
+        "GSE20723",
+        "GSE188547",
+        "GSE76959",
+        "GSE278136",
+        "GSE102886",
+        "GSE77626",
+        "GSE91392",
+        "GSE254145",
+        "GSE107040",
+        "GSE285544",
+        "GSE73625",
+        "GSE217029",
+        "GSE271073",
+        "GSE139414",
+        "GSE51062",
+        "GSE190129",
+        "GSE282886",
+        "GSE141383",
+        "GSE197508",
+        "GSE278456",
+        "GSE113510",
+        "GSE198438",
+        "GSE213309",
+        "GSE126658",
+        "GSE14581",
+        "GSE107530",
+        "GSE62367",
+        "GSE79122",
+        "GSE137287",
+        "GSE116488",
+        "GSE243221",
+        "GSE218331",
+        "GSE229672",
+        "GSE143263",
+        "GSE72201",
+        "GSE5107",
+        "GSE68424",
+        "GSE149989",
+        "GSE273589",
+        "GSE197543",
+        "GSE163020",
+        "GSE155247",
+        "GSE183606",
+        "GSE137809",
+        "GSE236243",
+        "GSE155835",
+        "GSE279771",
+        "GSE66388",
+        "GSE122283",
+        "GSE104554",
+        "GSE93204",
+        "GSE18894",
+        "GSE242352",
+        "GSE178260",
+        "GSE42420",
+        "GSE218042",
+        "GSE114534",
+        "GSE79897",
+        "GSE214968",
+        "GSE130105",
+        "GSE231503",
+        "GSE142828",
+        "GSE196339",
+        "GSE95027",
+        "GSE251900",
+        "GSE121601",
+        "GSE268158",
+        "GSE73895",
+        "GSE137902",
+        "GSE221950",
+        "GSE203177",
+        "GSE262707",
+        "GSE240675",
+        "GSE129977",
+        "GSE245762",
+        "GSE241147",
+        "GSE3185",
+        "GSE210654",
+        "GSE46028",
+        "GSE13598",
+        "GSE35186",
+        "GSE204944",
+        "GSE207760",
+        "GSE134783",
+        "GSE206984",
+        "GSE249154",
+        "GSE244894",
+        "GSE138114",
+        "GSE53227",
+        "GSE222421",
+        "GSE107859",
+        "GSE246262",
+        "GSE211147",
+        "GSE224692",
+        "GSE98693",
+        "GSE244332",
+        "GSE83301",
+        "GSE51332",
+        "GSE94349",
+        "GSE286477",
+        "GSE70231",
+        "GSE186319",
+        "GSE30016",
+        "GSE163409",
+        "GSE282334",
+        "GSE205519",
+        "GSE131744",
+        "GSE175864",
+        "GSE243465",
+        "GSE180466",
+        "GSE30448",
+        "GSE99180",
+        "GSE209777",
+        "GSE171497",
+        "GSE19113",
+        "GSE21514",
+        "GSE242326",
+        "GSE270857",
+        "GSE232486",
+        "GSE68343",
+        "GSE68800",
+        "GSE236569",
+        "GSE37634",
+        "GSE285545",
+        "GSE266971",
+        "GSE64230",
+        "GSE207002",
+        "GSE130093",
+        "GSE50161",
+        "GSE244869",
+        "GSE50478",
+        "GSE84132",
+        "GSE142693",
+        "GSE226740",
+        "GSE160437",
+        "GSE197761",
+        "GSE144399",
+        "GSE196418",
+        "GSE77053",
+        "GSE214832",
+        "GSE148673",
+        "GSE181035",
+        "GSE150631",
+        "GSE131956",
+        "GSE233869",
+        "GSE185695",
+        "GSE76018",
+        "GSE102193",
+        "GSE106142",
+        "GSE103790",
+        "GSE19612",
+        "GSE19693",
+        "GSE266969",
+        "GSE214140",
+        "GSE147454",
+        "GSE245263",
+        "GSE253080",
+        "GSE235911",
+        "GSE87619",
+        "GSE164717",
+        "GSE14818",
+        "GSE229964",
+        "GSE254873",
+        "GSE63532",
+        "GSE89745",
+        "GSE26002",
+        "GSE261472",
+        "GSE185954",
+        "GSE224104",
+        "GSE36426",
+        "GSE182295",
+        "GSE243455",
+        "GSE234284",
+        "GSE137796",
+        "GSE181144",
+        "GSE59484",
+        "GSE196707",
+        "GSE140145",
+        "GSE147391",
+        "GSE113824",
+        "GSE77043",
+        "GSE126168",
+        "GSE106143",
+        "GSE175700",
+        "GSE249544",
+        "GSE41980",
+        "GSE271618",
+        "GSE282194",
+        "GSE6014",
+        "GSE2109",
+        "GSE243682",
+        "GSE58400",
+        "GSE230825",
+        "GSE276841",
+        "GSE114915",
+        "GSE36619",
+        "GSE108474",
+        "GSE206604",
+        "GSE185759",
+        "GSE4412",
+        "GSE84707",
+        "GSE41467",
+        "GSE161352",
+        "GSE226202",
+        "GSE182281",
+        "GSE165238",
+        "GSE35811",
+        "GSE163504",
+        "GSE162976",
+        "GSE213046",
+        "GSE180896",
+        "GSE13041",
+        "GSE179115",
+        "GSE32100",
+        "GSE104273",
+        "GSE63035",
+        "GSE56573",
+        "GSE205514",
+        "GSE80968",
+        "GSE240516",
+        "GSE234912",
+        "GSE76786",
+        "GSE206241",
+        "GSE243501",
+        "GSE247977",
+        "GSE130949",
+        "GSE185956",
+        "GSE179110",
+        "GSE8537",
+        "GSE200162",
+        "GSE139416",
+        "GSE199689",
+        "GSE248703",
+        "GSE141947",
+        "GSE77452",
+        "GSE145897",
+        "GSE137489",
+        "GSE22866",
+        "GSE138328",
+        "GSE151137",
+        "GSE15170",
+        "GSE36940",
+        "GSE76422",
+        "GSE251777",
+        "GSE93143",
+        "GSE279426",
+        "GSE199379",
+        "GSE60867",
+        "GSE59678",
+        "GSE36782",
+        "GSE19870",
+        "GSE184890",
+        "GSE29442",
+        "GSE226757",
+        "GSE239486",
+        "GSE270481",
+        "GSE85615",
+        "GSE88771",
+        "GSE62153",
+        "GSE137048",
+        "GSE109340",
+        "GSE186057",
+        "GSE163656",
+        "GSE87618",
+        "GSE62381",
+        "GSE53228",
+        "GSE51441",
+        "GSE248420",
+        "GSE190154",
+        "GSE75945",
+        "GSE266620",
+        "GSE217035",
+        "GSE178621",
+        "GSE156678",
+        "GSE62211",
+        "GSE208617",
+        "GSE89239",
+        "GSE165037",
+        "GSE186945",
+        "GSE218081",
+        "GSE157424",
+        "GSE228500",
+        "GSE121718",
+        "GSE45161",
+        "GSE206675",
+        "GSE273275",
+        "GSE215401",
+        "GSE199185",
+        "GSE121716",
+        "GSE36901",
+        "GSE182220",
+        "GSE122586",
+        "GSE253362",
+        "GSE229482",
+        "GSE98377",
+        "GSE165624",
+        "GSE234762",
+        "GSE236494",
+        "GSE202200",
+        "GSE22927",
+        "GSE133285",
+        "GSE189577",
+        "GSE173280",
+        "GSE162833",
+        "GSE85087",
+        "GSE145409",
+        "GSE32970",
+        "GSE266619",
+        "GSE108862",
+        "GSE276103",
+        "GSE153907",
+        "GSE86518",
+        "GSE129438",
+        "GSE57083",
+        "GSE210717",
+        "GSE229136",
+        "GSE3521",
+        "GSE154795",
+        "GSE251878",
+        "GSE109628",
+        "GSE230453",
+        "GSE131879",
+        "GSE230661",
+        "GSE235100",
+        "GSE38814",
+        "GSE285535",
+        "GSE141013",
+        "GSE147275",
+        "GSE222522",
+        "GSE158741",
+        "GSE92462",
+        "GSE131400",
+        "GSE212325",
+        "GSE240193",
+        "GSE152071",
+        "GSE33442",
+        "GSE218860",
+        "GSE181315",
+        "GSE101291",
+        "GSE231994",
+        "GSE139142",
+        "GSE266884",
+        "GSE8852",
+        "GSE145646",
+        "GSE199110",
+        "GSE254875",
+        "GSE29288",
+        "GSE179882",
+        "GSE55361",
+        "GSE130119",
+        "GSE223064",
+        "GSE264275",
+        "GSE145558",
+        "GSE157647",
+        "GSE244878",
+        "GSE208773",
+        "GSE54047",
+        "GSE162444",
+        "GSE83537",
+        "GSE247650",
+        "GSE93054",
+        "GSE86624",
+        "GSE54967",
+        "GSE52580",
+        "GSE222518",
+        "GSE27931",
+        "GSE11100",
+        "GSE7516",
+        "GSE242225",
+        "GSE237183",
+        "GSE173645",
+        "GSE234127",
+        "GSE252870",
+        "GSE163715",
+        "GSE248704",
+        "GSE196591",
+        "GSE14806",
+        "GSE160887",
+        "GSE214966",
+        "GSE148803",
+        "GSE278450",
+        "GSE186302",
+        "GSE77751",
+        "GSE27671",
+        "GSE255501",
+        "GSE225967",
+        "GSE225973",
+        "GSE266147",
+        "GSE219288",
+        "GSE2221",
+        "GSE54791",
+        "GSE79438",
+        "GSE47945",
+        "GSE200574",
+        "GSE195683",
+        "GSE192678",
+        "GSE153794",
+        "GSE89400",
+        "GSE70038",
+        "GSE277301",
+        "GSE89623",
+        "GSE90176",
+        "GSE249653",
+        "GSE75300",
+        "GSE60184",
+        "GSE234262",
+        "GSE113370",
+        "GSE52230",
+        "GSE19363",
+        "GSE68368",
+        "GSE195506",
+        "GSE244825",
+        "GSE81934",
+        "GSE152862",
+        "GSE284766",
+        "GSE229965",
+        "GSE137900",
+        "GSE103961",
+        "GSE235913",
+        "GSE261191",
+        "GSE129047",
+        "GSE274090",
+        "GSE123444",
+        "GSE217152",
+        "GSE127274",
+        "GSE265904",
+        "GSE48568",
+        "GSE13808",
+        "GSE229671",
+        "GSE40051",
+        "GSE245688",
+        "GSE60866",
+        "GSE104291",
+        "GSE275293",
+        "GSE165286",
+        "GSE144610",
+        "GSE280951",
+        "GSE215873",
+        "GSE159605",
+        "GSE232434",
+        "GSE124145",
+        "GSE143798",
+        "GSE116298",
+        "GSE90426",
+        "GSE26576",
+        "GSE133040",
+        "GSE63712",
+        "GSE89501",
+        "GSE56715",
+        "GSE75244",
+        "GSE50412",
+        "GSE51281",
+        "GSE221714",
+        "GSE125905",
+        "GSE159607",
+        "GSE132118",
+        "GSE41230",
+        "GSE98127",
+        "GSE241276",
+        "GSE44561",
+        "GSE205513",
+        "GSE166696",
+        "GSE84465",
+        "GSE69104",
+        "GSE230826",
+        "GSE140449",
+        "GSE248352",
+        "GSE207426",
+        "GSE67089",
+        "GSE122808",
+        "GSE207821",
+        "GSE222895",
+        "GSE28220",
+        "GSE63853",
+        "GSE254168",
+        "GSE180209",
+        "GSE190930",
+        "GSE72951",
+        "GSE138942",
+        "GSE240377",
+        "GSE234473",
+        "GSE103224",
+        "GSE121857",
+        "GSE51481",
+        "GSE161436",
+        "GSE131837",
+        "GSE196533",
+        "GSE209865",
+        "GSE224082",
+        "GSE149921",
+        "GSE63037",
+        "GSE111247",
+        "GSE184643",
+        "GSE266145",
+        "GSE99537",
+        "GSE138475",
+        "GSE179147",
+        "GSE155052",
+        "GSE148842",
+        "GSE171758",
+        "GSE196706",
+        "GSE145128",
+        "GSE117632",
+        "GSE54660",
+        "GSE45899",
+        "GSE42402",
+        "GSE150673",
+        "GSE247886",
+        "GSE189605",
+        "GSE181649",
+        "GSE229420",
+        "GSE43452",
+        "GSE186207",
+        "GSE121722",
+        "GSE119688",
+        "GSE137210",
+        "GSE272370",
+        "GSE83294",
+        "GSE136089",
+        "GSE35500",
+        "GSE268563",
+        "GSE270465",
+        "GSE154041",
+        "GSE30626",
+        "GSE243130",
+        "GSE262760",
+        "GSE18883",
+        "GSE119081",
+        "GSE147147",
+        "GSE163019",
+        "GSE189541",
+        "GSE57091",
+        "GSE209772",
+        "GSE155300",
+        "GSE98692",
+        "GSE73270",
+        "GSE28214",
+        "GSE31133",
+        "GSE148740",
+        "GSE137733",
+        "GSE148292",
+        "GSE214248",
+        "GSE242328",
+        "GSE234126",
+        "GSE234124",
+        "GSE191126",
+        "GSE4218",
+        "GSE90604",
+        "GSE58345",
+        "GSE126550",
+        "GSE54792",
+        "GSE133116",
+        "GSE58530",
+        "GSE213876",
+        "GSE278511",
+        "GSE48865",
+        "GSE229416",
+        "GSE230393",
+        "GSE91014",
+        "GSE180889",
+        "GSE147526",
+        "GSE128541",
+        "GSE261618",
+        "GSE118792",
+        "GSE150395",
+        "GSE98126",
+        "GSE151506",
+        "GSE25965",
+        "GSE247299",
+        "GSE122488",
+        "GSE16666",
+        "GSE122679",
+        "GSE283049",
+        "GSE60705",
+        "GSE145510",
+        "GSE119102",
+        "GSE10774",
+        "GSE241149",
+        "GSE141241",
+        "GSE235676",
+        "GSE12737",
+        "GSE232050",
+        "GSE242231",
+        "GSE139233",
+        "GSE158016",
+        "GSE100775",
+        "GSE83300",
+        "GSE37985",
+        "GSE208634",
+        "GSE138890",
+        "GSE5082",
+        "GSE148467",
+        "GSE77487",
+        "GSE49377",
+        "GSE217344",
+        "GSE118092",
+        "GSE175863",
+        "GSE72955",
+        "GSE79772",
+        "GSE21026",
+        "GSE12305",
+        "GSE230824",
+        "GSE209807",
+        "GSE72218",
+        "GSE25632",
+        "GSE78703",
+        "GSE38008",
+        "GSE104296",
+        "GSE164105",
+        "GSE83130",
+        "GSE46686",
+        "GSE92459",
+        "GSE61710",
+        "GSE76146",
+        "GSE114222",
+        "GSE72476",
+        "GSE226468",
+        "GSE194222",
+        "GSE103559",
+        "GSE186341",
+        "GSE276838",
+        "GSE226726",
+        "GSE18166",
+        "GSE180464",
+        "GSE49009",
+        "GSE200647",
+        "GSE173784",
+        "GSE119711",
+        "GSE7344",
+        "GSE9385",
+        "GSE108013",
+        "GSE108088",
+        "GSE90547",
+        "GSE54162",
+        "GSE145933",
+        "GSE277539",
+        "GSE274966",
+        "GSE27144",
+        "GSE13470",
+        "GSE162643",
+        "GSE53229",
+        "GSE14822",
+        "GSE149845",
+        "GSE228785",
+        "GSE12350",
+        "GSE126253",
+        "GSE136644",
+        "GSE133211",
+        "GSE99045",
+        "GSE124877",
+        "GSE223280",
+        "GSE185029",
+        "GSE63296",
+        "GSE111806",
+        "GSE213269",
+        "GSE113961",
+        "GSE145699",
+        "GSE180981",
+        "GSE217347",
+        "GSE161438",
+        "GSE262681",
+        "GSE103229",
+        "GSE229962",
+        "GSE1993",
+        "GSE112650",
+        "GSE264713",
+        "GSE222481",
+        "GSE51253",
+        "GSE22821",
+        "GSE94765",
+        "GSE188773",
+        "GSE25631",
+        "GSE74187",
+        "GSE86511",
+        "GSE97349",
+        "GSE112810",
+        "GSE55712",
+        "GSE108870",
+        "GSE223607",
+        "GSE237053",
+        "GSE4058",
+        "GSE72209",
+        "GSE131502",
+        "GSE121092",
+        "GSE47809",
+        "GSE25012",
+        "GSE173146",
+        "GSE237779",
+        "GSE154789",
+        "GSE40776",
+        "GSE61335",
+        "GSE36902",
+        "GSE99171",
+        "GSE195896",
+        "GSE97632",
+        "GSE68928",
+        "GSE95164",
+        "GSE128255",
+        "GSE176187",
+        "GSE137901",
+        "GSE42669",
+        "GSE112902",
+        "GSE264186",
+        "GSE117448",
+        "GSE271379",
+        "GSE186736",
+        "GSE222192",
+        "GSE166351",
+        "GSE224727",
+        "GSE238012",
+        "GSE232504",
+        "GSE139448",
+        "GSE116012",
+        "GSE134676",
+        "GSE5720",
+        "GSE19578",
+        "GSE144204",
+        "GSE45265",
+        "GSE68086",
+        "GSE49224",
+        "GSE270109",
+        "GSE34152",
+        "GSE225869",
+        "GSE206170",
+        "GSE128536",
+        "GSE163949",
+        "GSE65626",
+        "GSE166877",
+        "GSE158020",
+        "GSE89399",
+        "GSE106159",
+        "GSE146463",
+        "GSE157910",
+        "GSE14804",
+        "GSE227059",
+        "GSE158740",
+        "GSE67986",
+        "GSE113474",
+        "GSE114456",
+        "GSE7806",
+        "GSE225975",
+        "GSE99385",
+        "GSE184859",
+        "GSE72468",
+        "GSE44728",
+        "GSE80639",
+        "GSE135349",
+        "GSE200031",
+        "GSE269962",
+        "GSE123519",
+        "GSE29682",
+        "GSE266143",
+        "GSE171500",
+        "GSE223297",
+        "GSE119774",
+        "GSE201960",
+        "GSE130857",
+        "GSE92458",
+        "GSE174634",
+        "GSE155985",
+        "GSE8049",
+        "GSE121332",
+        "GSE18015",
+        "GSE133117",
+        "GSE26082",
+        "GSE185269",
+        "GSE226647",
+        "GSE165926",
+        "GSE118793",
+        "GSE280891",
+        "GSE99175",
+        "GSE171163",
+        "GSE35191",
+        "GSE174177",
+        "GSE237673",
+        "GSE113512",
+        "GSE182373",
+        "GSE210736",
+        "GSE107558",
+        "GSE227721",
+        "GSE186332",
+        "GSE178114",
+        "GSE11778",
+        "GSE155809",
+        "GSE79478",
+        "GSE46015",
+        "GSE178113",
+        "GSE135210",
+        "GSE80399",
+        "GSE274548",
+        "GSE226700",
+        "GSE212616",
+        "GSE73199",
+        "GSE91393",
+        "GSE155836",
+        "GSE109982",
+        "GSE148739",
+        "GSE145557",
+        "GSE166418",
+        "GSE211148",
+        "GSE138060",
+        "GSE112645",
+        "GSE129142",
+        "GSE111231",
+        "GSE63533",
+        "GSE249282",
+        "GSE158175",
+        "GSE277823",
+        "GSE59612",
+        "GSE52582",
+        "GSE53014",
+        "GSE143887",
+        "GSE225971",
+        "GSE174295",
+        "GSE62802",
+        "GSE179356",
+        "GSE137453",
+        "GSE92612",
+        "GSE159416",
+        "GSE27584",
+        "GSE58277",
+        "GSE35158",
+        "GSE121723",
+        "GSE276101",
+        "GSE264695",
+        "GSE241281",
+        "GSE202764",
+        "GSE86237",
+        "GSE193884",
+        "GSE242966",
+        "GSE156522",
+        "GSE229966",
+        "GSE84134",
+        "GSE215420",
+        "GSE207753",
+        "GSE63535",
+        "GSE147329",
+        "GSE49810",
+        "GSE158550",
+        "GSE212067",
+        "GSE36247",
+        "GSE64667",
+        "GSE183772",
+        "GSE49162",
+        "GSE142119",
+        "GSE148196",
+        "GSE32283",
+        "GSE226292",
+        "GSE104806",
+        "GSE108958",
+        "GSE108742",
+        "GSE175851",
+        "GSE120793",
+        "GSE42515",
+        "GSE26068",
+        "GSE195681",
+        "GSE115397",
+        "GSE35444",
+        "GSE264374",
+        "GSE184567",
+        "GSE193525",
+        "GSE118790",
+        "GSE23935",
+        "GSE80137",
+        "GSE60806",
+        "GSE218668",
+        "GSE148779",
+        "GSE190816",
+        "GSE130407",
+        "GSE82183",
+        "GSE124727",
+        "GSE143495",
+        "GSE68936",
+        "GSE83626",
+        "GSE13991",
+        "GSE122994",
+        "GSE178371",
+        "GSE229967",
+        "GSE159896",
+        "GSE248634",
+        "GSE224149",
+        "GSE56113",
+        "GSE182942",
+        "GSE246708",
+        "GSE240822",
+        "GSE173278",
+        "GSE95157",
+        "GSE168038",
+        "GSE122498",
+        "GSE134972",
+        "GSE266210",
+        "GSE242570",
+        "GSE223065",
+        "GSE148949",
+        "GSE74557",
+        "GSE53733",
+        "GSE150630",
+        "GSE81043",
+        "GSE136974",
+        "GSE241273",
+        "GSE132554",
+        "GSE138737",
+        "GSE212246",
+        "GSE50924",
+        "GSE40698",
+        "GSE7330",
+        "GSE141945",
+        "GSE245488",
+        "GSE39242",
+        "GSE4717",
+        "GSE121655",
+        "GSE123414",
+        "GSE44841",
+        "GSE193495",
+        "GSE254461",
+        "GSE199032",
+        "GSE206917",
+        "GSE220083",
+        "GSE243865",
+        "GSE103227",
+        "GSE199030",
+        "GSE277282",
+        "GSE64072",
+        "GSE176578",
+        "GSE261188",
+        "GSE79734",
+        "GSE248471",
+        "GSE245854",
+        "GSE106482",
+        "GSE196490",
+        "GSE82139",
+        "GSE211724",
+        "GSE37737",
+        "GSE44931",
+        "GSE182374",
+        "GSE237103",
+        "GSE86348",
+        "GSE15191",
+        "GSE243132",
+        "GSE190804",
+        "GSE74084",
+        "GSE117599",
+        "GSE110868",
+        "GSE74516",
+        "GSE93991",
+        "GSE167746",
+        "GSE259262",
+        "GSE203074",
+        "GSE125587",
+        "GSE77030",
+        "GSE60818",
+        "GSE73262",
+        "GSE198523",
+        "GSE161528",
+        "GSE129476",
+        "GSE52419",
+        "GSE99979",
+        "GSE98330",
+        "GSE160875",
+        "GSE182375",
+        "GSE119637",
+        "GSE119834",
+        "GSE45394",
+        "GSE113816",
+        "GSE230770",
+        "GSE19728",
+        "GSE131928",
+        "GSE72475",
+        "GSE126892",
+        "GSE221376",
+        "GSE20018",
+        "GSE218043",
+        "GSE32374",
+        "GSE255754",
+        "GSE38589",
+        "GSE19422",
+        "GSE236661",
+        "GSE184451",
+        "GSE24446",
+        "GSE168040",
+        "GSE23839",
+        "GSE61281",
+        "GSE22891",
+        "GSE56316",
+        "GSE43289",
+        "GSE56752",
+        "GSE228008",
+        "GSE100013",
+        "GSE201557",
+        "GSE110767",
+        "GSE157608",
+        "GSE122809",
+        "GSE57978",
+        "GSE236570",
+        "GSE145556",
+        "GSE130648",
+        "GSE112240",
+        "GSE93680",
+        "GSE36201",
+        "GSE288052",
+        "GSE245634",
+        "GSE29692",
+        "GSE178458",
+        "GSE158742",
+        "GSE225775",
+        "GSE259352",
+        "GSE159851",
+        "GSE41824",
+        "GSE31586",
+        "GSE138113",
+        "GSE120647",
+        "GSE163853",
+        "GSE207452",
+        "GSE52363",
+        "GSE111260",
+        "GSE266621",
+        "GSE174554",
+        "GSE263766",
+        "GSE159456",
+        "GSE193180",
+        "GSE74754",
+        "GSE83344",
+        "GSE235648",
+        "GSE121717",
+        "GSE86213",
+        "GSE147342",
+        "GSE15824",
+        "GSE64965",
+        "GSE205062",
+        "GSE227722",
+        "GSE59116",
+        "GSE116414",
+        "GSE272042",
+        "GSE10221",
+        "GSE146440",
+        "GSE15134",
+        "GSE156739",
+        "GSE135437",
+        "GSE57488",
+        "GSE118983",
+        "GSE177549",
+        "GSE98849",
+        "GSE217346",
+        "GSE152147",
+        "GSE240343",
+        "GSE155807",
+        "GSE150986",
+        "GSE199143",
+        "GSE109398",
+        "GSE234128",
+        "GSE202362",
+        "GSE2223",
+        "GSE102505",
+        "GSE208698",
+        "GSE107581",
+        "GSE44713",
+        "GSE252489",
+        "GSE247079",
+        "GSE66200",
+        "GSE32335",
+        "GSE24072",
+        "GSE245303",
+        "GSE39223",
+        "GSE3254",
+        "GSE136738",
+        "GSE49161",
+        "GSE256492",
+        "GSE135408",
+        "GSE226721",
+        "GSE199375",
+        "GSE201639",
+        "GSE179924",
+        "GSE255536",
+        "GSE282324",
+        "GSE188228",
+        "GSE166979",
+        "GSE214006",
+        "GSE27523",
+        "GSE183776",
+        "GSE149366",
+        "GSE4482",
+        "GSE143842",
+        "GSE106775",
+        "GSE30730",
+        "GSE74304",
+        "GSE249289",
+        "GSE160417",
+        "GSE158551",
+        "GSE30043",
+        "GSE42658",
+        "GSE32662",
+        "GSE195813",
+        "GSE14823",
+        "GSE51822",
+        "GSE100675",
+        "GSE68071",
+        "GSE277011",
+        "GSE250617",
+        "GSE200062",
+        "GSE173801",
+        "GSE44843",
+        "GSE266140",
+        "GSE139250",
+        "GSE213013",
+        "GSE139139",
+        "GSE145940",
+        "GSE51663",
+        "GSE10878",
+        "GSE16119",
+        "GSE95289",
+        "GSE215239",
+        "GSE26328",
+        "GSE182282",
+        "GSE163044",
+        "GSE125255",
+        "GSE156819",
+        "GSE200341",
+        "GSE58921",
+        "GSE201553",
+        "GSE35493",
+        "GSE112733",
+        "GSE117544",
+        "GSE111462",
+        "GSE79876",
+        "GSE128547",
+        "GSE110152",
+        "GSE20736",
+        "GSE63694",
+        "GSE117685",
+        "GSE73243",
+        "GSE274910",
+        "GSE139415",
+        "GSE22867",
+        "GSE200984",
+        "GSE121720",
+        "GSE139826",
+        "GSE123344",
+        "GSE194221",
+        "GSE138236",
+        "GSE71769",
+        "GSE92375",
+        "GSE138620",
+        "GSE18899",
+        "GSE80338",
+        "GSE143934",
+        "GSE157488",
+        "GSE73556",
+        "GSE108085",
+        "GSE229210",
+        "GSE121998",
+        "GSE237936",
+        "GSE111458",
+        "GSE125621",
+        "GSE273171",
+        "GSE40299",
+        "GSE149324",
+        "GSE190638",
+        "GSE14945",
+        "GSE195684",
+        "GSE161572",
+        "GSE145645",
+        "GSE243836",
+        "GSE15116",
+        "GSE33912",
+        "GSE179439",
+        "GSE208618",
+        "GSE33483",
+        "GSE50756",
+        "GSE81879",
+        "GSE58218",
+        "GSE60530",
+        "GSE100398",
+        "GSE181372",
+        "GSE159609",
+        "GSE200348",
+        "GSE31126",
+        "GSE162429",
+        "GSE165391",
+        "GSE32474",
+        "GSE155434",
+        "GSE131399",
+        "GSE248995",
+        "GSE217349",
+        "GSE150615",
+        "GSE53504",
+        "GSE26196",
+        "GSE180465",
+        "GSE185569",
+        "GSE163833",
+        "GSE179077",
+        "GSE220909",
+        "GSE246295",
+        "GSE161440",
+        "GSE139018",
+        "GSE240704",
+        "GSE108476",
+        "GSE81353"
+    ],
+    "GARD:0007471": [
+        "GSE32040",
+        "GSE153960",
+        "GSE140830",
+        "GSE93885",
+        "GSE6613",
+        "GSE163855",
+        "GSE32041",
+        "GSE115606",
+        "GSE53740",
+        "GSE255902",
+        "GSE186921",
+        "GSE32037",
+        "GSE207099",
+        "GSE163150",
+        "GSE32039",
+        "GSE34287",
+        "GSE46131",
+        "GSE75704",
+        "GSE255904"
+    ],
+    "GARD:0000017": [
+        "GSE260461",
+        "GSE190502",
+        "GSE174251",
+        "GSE243750",
+        "GSE19727"
+    ],
+    "GARD:0008207": [
+        "GSE278579",
+        "GSE255906",
+        "GSE68956",
+        "GSE35499",
+        "GSE255911",
+        "GSE133801",
+        "GSE255907",
+        "GSE73801",
+        "GSE215240",
+        "GSE255908",
+        "GSE276299",
+        "GSE255909",
+        "GSE255905",
+        "GSE99961",
+        "GSE14087",
+        "GSE108089",
+        "GSE12370",
+        "GSE180868",
+        "GSE99994",
+        "GSE255912",
+        "GSE255910",
+        "GSE124537",
+        "GSE198855",
+        "GSE255913",
+        "GSE255914",
+        "GSE108088",
+        "GSE178388",
+        "GSE14295",
+        "GSE19404"
+    ],
+    "GARD:0010009": [
+        "GSE189367",
+        "GSE189742",
+        "GSE189741"
+    ],
+    "GARD:0007716": [
+        "GSE3621",
+        "GSE244970",
+        "GSE149900",
+        "GSE278354",
+        "GSE97100",
+        "GSE108398",
+        "GSE180294",
+        "GSE98738",
+        "GSE3248",
+        "GSE225790",
+        "GSE34721",
+        "GSE245631",
+        "GSE65775",
+        "GSE19677",
+        "GSE157076",
+        "GSE144559",
+        "GSE73655",
+        "GSE48960",
+        "GSE114755",
+        "GSE96099",
+        "GSE167104",
+        "GSE28685",
+        "GSE214108",
+        "GSE38001",
+        "GSE144493",
+        "GSE64977",
+        "GSE184255",
+        "GSE3634",
+        "GSE97353",
+        "GSE273501",
+        "GSE67761",
+        "GSE22267",
+        "GSE241430",
+        "GSE109416",
+        "GSE58996",
+        "GSE65769",
+        "GSE38218",
+        "GSE110226",
+        "GSE142603",
+        "GSE112657",
+        "GSE12651",
+        "GSE78928",
+        "GSE166695",
+        "GSE59572",
+        "GSE220662",
+        "GSE239312",
+        "GSE188559",
+        "GSE242195",
+        "GSE228254",
+        "GSE2872",
+        "GSE199837",
+        "GSE281847",
+        "GSE78274",
+        "GSE114756",
+        "GSE38000",
+        "GSE185476",
+        "GSE67829",
+        "GSE230640",
+        "GSE267802",
+        "GSE270728",
+        "GSE43429",
+        "GSE33000",
+        "GSE169386",
+        "GSE171099",
+        "GSE201694",
+        "GSE157083",
+        "GSE80093",
+        "GSE42107",
+        "GSE150748",
+        "GSE108395",
+        "GSE84055",
+        "GSE65771",
+        "GSE183652",
+        "GSE210996",
+        "GSE141856",
+        "GSE180236",
+        "GSE217469",
+        "GSE76593",
+        "GSE126869",
+        "GSE245510",
+        "GSE143355",
+        "GSE144699",
+        "GSE61405",
+        "GSE79666",
+        "GSE48104",
+        "GSE145879",
+        "GSE73508",
+        "GSE196021",
+        "GSE214973",
+        "GSE144477",
+        "GSE73503",
+        "GSE170998",
+        "GSE135589",
+        "GSE59570",
+        "GSE271852",
+        "GSE140118",
+        "GSE165658",
+        "GSE214110",
+        "GSE65772",
+        "GSE9330",
+        "GSE78791",
+        "GSE73507",
+        "GSE95344",
+        "GSE162349",
+        "GSE146674",
+        "GSE135057",
+        "GSE37517",
+        "GSE199005",
+        "GSE79711",
+        "GSE113928",
+        "GSE124664",
+        "GSE233387",
+        "GSE19780",
+        "GSE88775",
+        "GSE78273",
+        "GSE225789",
+        "GSE264218",
+        "GSE104552",
+        "GSE78272",
+        "GSE206322",
+        "GSE233408",
+        "GSE10581",
+        "GSE72778",
+        "GSE194242",
+        "GSE76738",
+        "GSE11139",
+        "GSE167630",
+        "GSE121757",
+        "GSE112655",
+        "GSE51799",
+        "GSE196022",
+        "GSE173546",
+        "GSE25232",
+        "GSE77194",
+        "GSE43430",
+        "GSE272903",
+        "GSE10202",
+        "GSE109871",
+        "GSE188561",
+        "GSE71816",
+        "GSE180928",
+        "GSE44854",
+        "GSE130570",
+        "GSE107259",
+        "GSE18551",
+        "GSE104091",
+        "GSE154181",
+        "GSE194243",
+        "GSE44855",
+        "GSE233385",
+        "GSE220847",
+        "GSE111622",
+        "GSE154128",
+        "GSE32192",
+        "GSE43431",
+        "GSE129473",
+        "GSE76752",
+        "GSE189647",
+        "GSE78270",
+        "GSE1767",
+        "GSE105158",
+        "GSE188558",
+        "GSE88920",
+        "GSE31560",
+        "GSE40377",
+        "GSE241325",
+        "GSE112379",
+        "GSE173731",
+        "GSE194416",
+        "GSE153791",
+        "GSE54443",
+        "GSE44306",
+        "GSE116267",
+        "GSE165317",
+        "GSE113930",
+        "GSE126914",
+        "GSE77558",
+        "GSE233914",
+        "GSE9803",
+        "GSE1751",
+        "GSE270727",
+        "GSE201692",
+        "GSE152058",
+        "GSE84058",
+        "GSE175657",
+        "GSE67733",
+        "GSE138525",
+        "GSE227729",
+        "GSE181180",
+        "GSE109534",
+        "GSE147004",
+        "GSE40695",
+        "GSE68952",
+        "GSE19291",
+        "GSE107613",
+        "GSE64810",
+        "GSE160586",
+        "GSE148185",
+        "GSE146673",
+        "GSE272271",
+        "GSE9038",
+        "GSE278893",
+        "GSE62210",
+        "GSE146917",
+        "GSE63675",
+        "GSE136158",
+        "GSE84013",
+        "GSE270472",
+        "GSE66769",
+        "GSE85126",
+        "GSE112654",
+        "GSE73505",
+        "GSE170997",
+        "GSE261670",
+        "GSE139847",
+        "GSE24250",
+        "GSE92905",
+        "GSE279460",
+        "GSE195633",
+        "GSE127821",
+        "GSE9760",
+        "GSE211891",
+        "GSE29751",
+        "GSE214743",
+        "GSE276407",
+        "GSE175658",
+        "GSE182866",
+        "GSE166567",
+        "GSE194241",
+        "GSE146399",
+        "GSE11358",
+        "GSE36233",
+        "GSE95843",
+        "GSE89505",
+        "GSE229839",
+        "GSE215217",
+        "GSE95602",
+        "GSE29647",
+        "GSE95842",
+        "GSE209893",
+        "GSE39586",
+        "GSE147003",
+        "GSE147002",
+        "GSE159940",
+        "GSE169405",
+        "GSE162812",
+        "GSE105041",
+        "GSE80004",
+        "GSE150174",
+        "GSE273082",
+        "GSE251684",
+        "GSE95343",
+        "GSE78792",
+        "GSE27588",
+        "GSE115522",
+        "GSE19676",
+        "GSE102750",
+        "GSE59571",
+        "GSE281069",
+        "GSE65774",
+        "GSE156236",
+        "GSE187445",
+        "GSE76753",
+        "GSE9375",
+        "GSE106161",
+        "GSE78793",
+        "GSE103345",
+        "GSE153827",
+        "GSE175618",
+        "GSE144518",
+        "GSE28232",
+        "GSE26001",
+        "GSE140117",
+        "GSE10190",
+        "GSE143475",
+        "GSE65770",
+        "GSE65773",
+        "GSE263368",
+        "GSE146675",
+        "GSE109872",
+        "GSE90068",
+        "GSE47500",
+        "GSE78790",
+        "GSE233895",
+        "GSE95342",
+        "GSE181370",
+        "GSE129141",
+        "GSE21237",
+        "GSE124846",
+        "GSE150747",
+        "GSE70249",
+        "GSE8762",
+        "GSE7958",
+        "GSE29681",
+        "GSE270473",
+        "GSE172379",
+        "GSE12481",
+        "GSE169388",
+        "GSE74201",
+        "GSE189988",
+        "GSE103341",
+        "GSE223847",
+        "GSE857",
+        "GSE3583",
+        "GSE193573",
+        "GSE26317",
+        "GSE26927",
+        "GSE5786",
+        "GSE175656",
+        "GSE148440",
+        "GSE25925",
+        "GSE198927",
+        "GSE109873",
+        "GSE157099",
+        "GSE70656",
+        "GSE225788",
+        "GSE144684",
+        "GSE113929",
+        "GSE148176",
+        "GSE216520",
+        "GSE18644",
+        "GSE116266",
+        "GSE267435",
+        "GSE272134",
+        "GSE242197",
+        "GSE98739",
+        "GSE242506",
+        "GSE38219",
+        "GSE59051",
+        "GSE201691",
+        "GSE79064",
+        "GSE81367",
+        "GSE10263",
+        "GSE127820",
+        "GSE162813",
+        "GSE160967",
+        "GSE93767",
+        "GSE48963",
+        "GSE65776",
+        "GSE48962",
+        "GSE34201",
+        "GSE165663",
+        "GSE248873",
+        "GSE73468",
+        "GSE242198",
+        "GSE165667",
+        "GSE9025",
+        "GSE270729",
+        "GSE37547",
+        "GSE71191",
+        "GSE97101",
+        "GSE214109",
+        "GSE70209",
+        "GSE129143",
+        "GSE269068",
+        "GSE154131",
+        "GSE152443",
+        "GSE73743",
+        "GSE71220",
+        "GSE154141",
+        "GSE9804",
+        "GSE84056",
+        "GSE112656",
+        "GSE49392",
+        "GSE220224",
+        "GSE139884",
+        "GSE43432",
+        "GSE204833",
+        "GSE108396"
+    ],
+    "GARD:0008703": [
+        "GSE213907",
+        "GSE264121",
+        "GSE169486",
+        "GSE99030",
+        "GSE79189",
+        "GSE230077",
+        "GSE23076",
+        "GSE164140",
+        "GSE214901"
+    ],
+    "GARD:0000943": [
+        "GSE163915",
+        "GSE206118",
+        "GSE58149"
+    ],
+    "GARD:0002170": [
+        "GSE217726",
+        "GSE124507",
+        "GSE208672",
+        "GSE6771",
+        "GSE163296",
+        "GSE25453",
+        "GSE99455",
+        "GSE75458",
+        "GSE275302",
+        "GSE127871",
+        "GSE138100",
+        "GSE241219",
+        "GSE227239",
+        "GSE133930",
+        "GSE128300",
+        "GSE234941",
+        "GSE114700",
+        "GSE109233",
+        "GSE107375",
+        "GSE197015",
+        "GSE205661",
+        "GSE134697",
+        "GSE27166",
+        "GSE22897",
+        "GSE73878",
+        "GSE79129",
+        "GSE128299",
+        "GSE114874",
+        "GSE214901",
+        "GSE190451",
+        "GSE1831",
+        "GSE214317",
+        "GSE68430",
+        "GSE133929",
+        "GSE41320",
+        "GSE22899",
+        "GSE27015",
+        "GSE268714",
+        "GSE209793",
+        "GSE156374",
+        "GSE241756",
+        "GSE27268",
+        "GSE52443",
+        "GSE234937",
+        "GSE268715",
+        "GSE153669",
+        "GSE96067",
+        "GSE269625",
+        "GSE211696",
+        "GSE213393",
+        "GSE137473",
+        "GSE28674",
+        "GSE22894",
+        "GSE186334",
+        "GSE233890",
+        "GSE133554",
+        "GSE234940",
+        "GSE22896",
+        "GSE49849",
+        "GSE252323",
+        "GSE6773",
+        "GSE216877",
+        "GSE226815",
+        "GSE214355",
+        "GSE49851",
+        "GSE81024",
+        "GSE63808",
+        "GSE234942",
+        "GSE230828",
+        "GSE123000",
+        "GSE256068",
+        "GSE49850",
+        "GSE114701",
+        "GSE245228",
+        "GSE96721",
+        "GSE202101",
+        "GSE94744",
+        "GSE94108",
+        "GSE79131",
+        "GSE255223",
+        "GSE224494",
+        "GSE114697",
+        "GSE22994",
+        "GSE57585",
+        "GSE153976",
+        "GSE6834",
+        "GSE140658",
+        "GSE140393",
+        "GSE190452",
+        "GSE210670",
+        "GSE1834",
+        "GSE71058",
+        "GSE66762",
+        "GSE274303",
+        "GSE114847"
+    ],
+    "GARD:0007826": [
+        "GSE23650",
+        "GSE212622",
+        "GSE122858",
+        "GSE168394",
+        "GSE23885",
+        "GSE143456",
+        "GSE210600",
+        "GSE24435",
+        "GSE261736",
+        "GSE225147",
+        "GSE200642",
+        "GSE222784",
+        "GSE193394",
+        "GSE229436",
+        "GSE18065",
+        "GSE147734",
+        "GSE8369",
+        "GSE165290",
+        "GSE18075"
+    ],
+    "GARD:0010641": [
+        "GSE108085",
+        "GSE209865",
+        "GSE35499",
+        "GSE110066",
+        "GSE108089",
+        "GSE152653",
+        "GSE215240",
+        "GSE108088"
+    ],
+    "GARD:0006919": [
+        "GSE119699",
+        "GSE128204",
+        "GSE119562",
+        "GSE53454",
+        "GSE43974",
+        "GSE94964",
+        "GSE14951",
+        "GSE43327",
+        "GSE86494",
+        "GSE127242",
+        "GSE127003",
+        "GSE226829",
+        "GSE43580",
+        "GSE233533",
+        "GSE77968",
+        "GSE119748",
+        "GSE9861",
+        "GSE144431",
+        "GSE6604",
+        "GSE109841",
+        "GSE21497",
+        "GSE166712",
+        "GSE6919",
+        "GSE87175",
+        "GSE135851",
+        "GSE67978",
+        "GSE74198",
+        "GSE119650",
+        "GSE133383",
+        "GSE112619",
+        "GSE12280",
+        "GSE118182",
+        "GSE8775",
+        "GSE119696",
+        "GSE31103",
+        "GSE189539",
+        "GSE132058",
+        "GSE242270",
+        "GSE5104",
+        "GSE17978",
+        "GSE178635",
+        "GSE127055",
+        "GSE107677",
+        "GSE276531",
+        "GSE78148",
+        "GSE30718",
+        "GSE29113",
+        "GSE138091",
+        "GSE78150",
+        "GSE14700",
+        "GSE92696",
+        "GSE89120",
+        "GSE209552",
+        "GSE50221",
+        "GSE16483",
+        "GSE229413",
+        "GSE246128",
+        "GSE163256",
+        "GSE22624",
+        "GSE18995",
+        "GSE10419",
+        "GSE14839",
+        "GSE135456",
+        "GSE23649",
+        "GSE22531",
+        "GSE174409",
+        "GSE119195",
+        "GSE57691",
+        "GSE47472",
+        "GSE112620",
+        "GSE245976",
+        "GSE218788",
+        "GSE156322"
+    ],
+    "GARD:0006797": [
+        "GSE237915",
+        "GSE57330",
+        "GSE39740",
+        "GSE57647",
+        "GSE154002",
+        "GSE42942",
+        "GSE267173",
+        "GSE9524",
+        "GSE221680",
+        "GSE115167",
+        "GSE52324",
+        "GSE53784",
+        "GSE158247",
+        "GSE94789",
+        "GSE57410",
+        "GSE148029",
+        "GSE20135",
+        "GSE44721"
+    ],
+    "GARD:0006332": [
+        "GSE274566",
+        "GSE264306",
+        "GSE81393",
+        "GSE273331",
+        "GSE81391",
+        "GSE280993",
+        "GSE52659",
+        "GSE136342",
+        "GSE115167",
+        "GSE142595",
+        "GSE275201",
+        "GSE277300",
+        "GSE255795",
+        "GSE213725",
+        "GSE94789",
+        "GSE57410",
+        "GSE21407",
+        "GSE106752",
+        "GSE277431",
+        "GSE180956",
+        "GSE267173",
+        "GSE9524",
+        "GSE273334",
+        "GSE233197",
+        "GSE52324",
+        "GSE64387",
+        "GSE85300",
+        "GSE277947",
+        "GSE20135",
+        "GSE44721",
+        "GSE16451",
+        "GSE237915",
+        "GSE57330",
+        "GSE39740",
+        "GSE51399",
+        "GSE207136",
+        "GSE42942",
+        "GSE273336",
+        "GSE221680",
+        "GSE96550",
+        "GSE158247",
+        "GSE79530",
+        "GSE10120",
+        "GSE233195",
+        "GSE148029",
+        "GSE57307",
+        "GSE91074",
+        "GSE57647",
+        "GSE154002",
+        "GSE145815",
+        "GSE7647",
+        "GSE233196",
+        "GSE226098",
+        "GSE53784",
+        "GSE232775",
+        "GSE175823",
+        "GSE131434",
+        "GSE39100",
+        "GSE220562",
+        "GSE115729"
+    ],
+    "GARD:0005250": [
+        "GSE190493",
+        "GSE39151"
+    ],
+    "GARD:0012768": [
+        "GSE145581"
+    ],
+    "GARD:0009369": [
+        "GSE278579",
+        "GSE255906",
+        "GSE68956",
+        "GSE35499",
+        "GSE255911",
+        "GSE133801",
+        "GSE255907",
+        "GSE73801",
+        "GSE215240",
+        "GSE255908",
+        "GSE276299",
+        "GSE255909",
+        "GSE255905",
+        "GSE99961",
+        "GSE14087",
+        "GSE108089",
+        "GSE12370",
+        "GSE180868",
+        "GSE99994",
+        "GSE255912",
+        "GSE255910",
+        "GSE124537",
+        "GSE198855",
+        "GSE255913",
+        "GSE255914",
+        "GSE108088",
+        "GSE178388",
+        "GSE14295",
+        "GSE19404",
+        "GSE278579",
+        "GSE255906",
+        "GSE68956",
+        "GSE35499",
+        "GSE255911",
+        "GSE133801",
+        "GSE255907",
+        "GSE73801",
+        "GSE215240",
+        "GSE255908",
+        "GSE276299",
+        "GSE255909",
+        "GSE255905",
+        "GSE99961",
+        "GSE14087",
+        "GSE108089",
+        "GSE12370",
+        "GSE180868",
+        "GSE99994",
+        "GSE255912",
+        "GSE255910",
+        "GSE124537",
+        "GSE198855",
+        "GSE255913",
+        "GSE255914",
+        "GSE108088",
+        "GSE178388",
+        "GSE14295",
+        "GSE19404",
+        "GSE278579",
+        "GSE255906",
+        "GSE68956",
+        "GSE35499",
+        "GSE255911",
+        "GSE133801",
+        "GSE255907",
+        "GSE73801",
+        "GSE215240",
+        "GSE255908",
+        "GSE276299",
+        "GSE255909",
+        "GSE255905",
+        "GSE99961",
+        "GSE14087",
+        "GSE108089",
+        "GSE12370",
+        "GSE180868",
+        "GSE99994",
+        "GSE255912",
+        "GSE255910",
+        "GSE124537",
+        "GSE198855",
+        "GSE255913",
+        "GSE255914",
+        "GSE108088",
+        "GSE178388",
+        "GSE14295",
+        "GSE19404"
+    ],
+    "GARD:0005216": [
+        "GSE180956",
+        "GSE264306",
+        "GSE273331",
+        "GSE273336",
+        "GSE280993",
+        "GSE273334",
+        "GSE52324",
+        "GSE64387",
+        "GSE232775",
+        "GSE175823",
+        "GSE85300",
+        "GSE39100"
+    ],
+    "GARD:0006851": [
+        "GSE154573"
+    ],
+    "GARD:0010949": [
+        "GSE223613",
+        "GSE133989",
+        "GSE226929",
+        "GSE242159",
+        "GSE153540",
+        "GSE233440",
+        "GSE119668",
+        "GSE142248",
+        "GSE282892",
+        "GSE245519",
+        "GSE54124",
+        "GSE75475",
+        "GSE205881"
+    ],
+    "GARD:0006956": [
+        "GSE87629",
+        "GSE12651",
+        "GSE124571",
+        "GSE160208",
+        "GSE90977",
+        "GSE140069",
+        "GSE156994",
+        "GSE62699",
+        "GSE38205",
+        "GSE57233",
+        "GSE30643",
+        "GSE198063",
+        "GSE207251"
+    ],
+    "GARD:0004561": [
+        "GSE223582",
+        "GSE232343",
+        "GSE163005",
+        "GSE37830",
+        "GSE37664",
+        "GSE232814",
+        "GSE247134",
+        "GSE171398",
+        "GSE138266",
+        "GSE37826"
+    ],
+    "GARD:0008232": [
+        "GSE198855",
+        "GSE209865",
+        "GSE148216",
+        "GSE138092",
+        "GSE215240",
+        "GSE109102",
+        "GSE197378"
+    ],
+    "GARD:0005758": [
+        "GSE225718",
+        "GSE85839",
+        "GSE34309",
+        "GSE108012",
+        "GSE276153",
+        "GSE237635",
+        "GSE85804",
+        "GSE34308",
+        "GSE60542",
+        "GSE78218",
+        "GSE217140",
+        "GSE135834",
+        "GSE117647",
+        "GSE245235",
+        "GSE225718",
+        "GSE85839",
+        "GSE34309",
+        "GSE108012",
+        "GSE276153",
+        "GSE237635",
+        "GSE85804",
+        "GSE34308",
+        "GSE60542",
+        "GSE78218",
+        "GSE217140",
+        "GSE135834",
+        "GSE117647",
+        "GSE245235"
+    ],
+    "GARD:0007516": [
+        "GSE148221",
+        "GSE26271",
+        "GSE26270",
+        "GSE284262",
+        "GSE49217",
+        "GSE35684",
+        "GSE115746",
+        "GSE136455",
+        "GSE119636",
+        "GSE149107",
+        "GSE38970",
+        "GSE152728",
+        "GSE107285",
+        "GSE214895",
+        "GSE196051",
+        "GSE115865",
+        "GSE38975",
+        "GSE277578",
+        "GSE167176",
+        "GSE44721",
+        "GSE205990",
+        "GSE107277",
+        "GSE79108",
+        "GSE214386",
+        "GSE248365",
+        "GSE151892",
+        "GSE133230",
+        "GSE30577",
+        "GSE261613",
+        "GSE261436",
+        "GSE150858",
+        "GSE196771",
+        "GSE138164",
+        "GSE35706",
+        "GSE178583",
+        "GSE149994",
+        "GSE35707",
+        "GSE26269",
+        "GSE151894",
+        "GSE181363",
+        "GSE121888",
+        "GSE231664",
+        "GSE151890",
+        "GSE50045"
+    ],
+    "GARD:0007312": [
+        "GSE250292",
+        "GSE206395",
+        "GSE138294",
+        "GSE163128",
+        "GSE195622",
+        "GSE190729",
+        "GSE130042",
+        "GSE121158",
+        "GSE130041"
+    ],
+    "GARD:0008194": [
+        "GSE260929",
+        "GSE232005",
+        "GSE266860",
+        "GSE84086"
+    ],
+    "GARD:0007805": [
+        "GSE186505",
+        "GSE256472",
+        "GSE233838",
+        "GSE162284",
+        "GSE216965"
+    ],
+    "GARD:0005839": [
+        "GSE266860"
+    ]
+}
\ No newline at end of file
diff --git a/RDAS_RDOMICS/scripts/data/table_template.xlsx b/RDAS_RDOMICS/scripts/data/table_template.xlsx
new file mode 100644
index 0000000..5c2eb9a
Binary files /dev/null and b/RDAS_RDOMICS/scripts/data/table_template.xlsx differ
diff --git a/RDAS_RDOMICS/scripts/main.py b/RDAS_RDOMICS/scripts/main.py
new file mode 100644
index 0000000..acc52e7
--- /dev/null
+++ b/RDAS_RDOMICS/scripts/main.py
@@ -0,0 +1,164 @@
+import argparse
+import logging
+import os
+
+os.makedirs("logs", exist_ok=True)
+logging.basicConfig(filename=os.path.join("logs", "pipeline.log"), level=logging.INFO)
+
+def _load_pipeline_modules():
+    if __package__:
+        from . import (
+            step1_search_geo,
+            step2_download_matrix_optional as step2_download_matrix,
+            step3_download_gse_number,
+            step4_extract_to_table,
+            step5_generate_node_mappings,
+            step6_import_to_neo4j,
+            step7_experiment_normalization,
+            step7_1_import_normalized_experiment_properties,
+        )
+        from .utils import load_paths
+    else:
+        import step1_search_geo
+        import step2_download_matrix_optional as step2_download_matrix
+        import step3_download_gse_number
+        import step4_extract_to_table
+        import step5_generate_node_mappings
+        import step6_import_to_neo4j
+        import step7_experiment_normalization
+        import step7_1_import_normalized_experiment_properties
+        from utils import load_paths
+
+    return (
+        step1_search_geo,
+        step2_download_matrix,
+        step3_download_gse_number,
+        step4_extract_to_table,
+        step5_generate_node_mappings,
+        step6_import_to_neo4j,
+        step7_experiment_normalization,
+        step7_1_import_normalized_experiment_properties,
+        load_paths,
+    )
+
+
+def main(args):
+    (
+        step1_search_geo,
+        step2_download_matrix,
+        step3_download_gse_number,
+        step4_extract_to_table,
+        step5_generate_node_mappings,
+        step6_import_to_neo4j,
+        step7_experiment_normalization,
+        step7_1_import_normalized_experiment_properties,
+        load_paths,
+    ) = _load_pipeline_modules()
+    paths = load_paths(args.config)
+    
+    try:
+        logging.info("Starting GEO data pipeline")
+
+        if args.step1_search_geo:
+            step1_search_geo.process_disease_file(
+                input_file=paths["disease_list_combined_file"],
+                output_file=paths["disease_list_combined_with_count"],
+                batch_size=args.batch_size,
+            )
+            logging.info("Step 1 completed: Series count updated.")
+        
+        if args.step2_download_matrix:
+            step2_download_matrix.process_diseases_and_download_matrix(
+                input_file=paths["disease_list_combined_with_count"],
+                output_dir=paths["geo_matrix_files"],
+            )
+            logging.info("Step 2 completed: Matrix files downloaded.")
+
+        if args.step3_download_gse_number:
+            step3_download_gse_number.record_gse_number(
+                input_file=paths["disease_list_combined_with_count"],
+                output_file=paths["gse_ids_csv"],
+            )
+            logging.info("Step3 completed: GSE IDS recorded.")
+
+        if args.step4_extract_to_table:
+            step4_extract_to_table.extract_to_table(
+                input_file=paths["gse_ids_csv"],
+                table_template=paths["geo_table_template"],
+                disease_name_list = paths["disease_list_combined_with_count"],
+                output_dir=paths["geo_final_tables"]
+            )
+            logging.info("Step4 completed: Extracted to tables.")
+
+        if args.step5_generate_node_mappings:
+            step5_generate_node_mappings.process_all_nodes(
+                input_path=paths["geo_final_tables"],
+                output_path=paths["node_csv_files"]
+            )
+
+        if args.step6_import_to_neo4j:
+            step6_import_to_neo4j.process_import(
+                csv_path=paths["node_csv_files"],
+                json_path=paths["node_json_files"]
+            )
+
+        if args.step7_experiment_normalization:
+            step7_experiment_normalization.normalize_experiment_data(args.config)
+
+        if args.step7_1_import_normalized_experiment_properties:
+            step7_1_import_normalized_experiment_properties.import_normalized_properties(args.config)
+
+    except Exception as e:
+        logging.error(f"Pipeline failed: {e}")
+        raise
+
+    logging.info("GEO Extration pipeline completed successfully.")
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser(description="GEO Data Pipeline")
+    parser.add_argument(
+        "--step1-search-geo", action="store_true", help="Run Step1: Search GEO datasets with count."
+    )
+    parser.add_argument(
+        "--step2-download-matrix", action="store_true", help="Run Step2: Download matrix files."
+    )
+    parser.add_argument(
+        "--step3-download-gse-number", action="store_true", help="Run Step3: Record GSE numbers."
+    )
+    parser.add_argument(
+        "--step4-extract-to-table", action="store_true", help="Run Step4: Extracted to tables."
+    )
+    parser.add_argument(
+        "--step5-generate-node-mappings", action="store_true", help="Run Step5: Generate nodes and mapping relationships csv files."
+    ) 
+    parser.add_argument(
+        "--step6-import-to-neo4j", action="store_true", help="Run Step6: Import nodes and mapping relationships to neo4j db."
+    ) 
+    parser.add_argument(
+        "--step7-experiment-normalization", action="store_true", help="Run Step7: Normalize experiment node properties."
+    )
+    parser.add_argument(
+        "--step7-1-import-normalized-experiment-properties",
+        action="store_true",
+        help="Run Step7.1: Import normalized experiment properties into the graph database."
+    )
+    
+    # Also need to add the batch size as an argument in the parser
+    parser.add_argument("--batch-size", type=int, default=32, help="Batch size for processing.")
+    parser.add_argument("--config", help="Optional path to a YAML file with input/output paths.")
+
+    parser.add_argument("--all", action="store_true", help="Run all steps sequentially.")
+
+    args = parser.parse_args()
+
+    # If --all is specified, set all other arguments to True
+    if args.all:
+        #args.step1_search_geo = True
+        #args.step2_download_matrix = True
+        args.step3_download_gse_number = True
+        args.step4_extract_to_table = True
+        args.step5_generate_node_mappings = True
+        args.step6_import_to_neo4j = True
+        args.step7_experiment_normalization = True
+        args.step7_1_import_normalized_experiment_properties = True
+    main(args)
diff --git a/RDAS_RDOMICS/scripts/sample_characteristics_harmonization/1_clean_sample_characteristics_chars.py b/RDAS_RDOMICS/scripts/sample_characteristics_harmonization/1_clean_sample_characteristics_chars.py
new file mode 100644
index 0000000..3fdfaf4
--- /dev/null
+++ b/RDAS_RDOMICS/scripts/sample_characteristics_harmonization/1_clean_sample_characteristics_chars.py
@@ -0,0 +1,169 @@
+import pandas as pd
+import re
+from collections import Counter
+from pathlib import Path
+import sys
+from tqdm import tqdm
+
+CURRENT_DIR = Path(__file__).resolve().parent
+SCRIPTS_DIR = CURRENT_DIR.parent
+if str(SCRIPTS_DIR) not in sys.path:
+    sys.path.insert(0, str(SCRIPTS_DIR))
+
+from utils import ensure_parent_dir, load_paths
+
+def clean_label(label):
+    """
+    Remove special characters from the beginning and end of a label.
+    Keep only alphanumeric characters and spaces, plus some common scientific notation.
+    """
+    if not isinstance(label, str):
+        return str(label)
+    
+    # Remove leading and trailing special characters
+    # Keep letters, numbers, spaces, and some common scientific characters in the middle
+    cleaned = label.strip()
+    
+    # Remove leading special characters (except alphanumeric and space)
+    cleaned = re.sub(r'^[^\w\s]+', '', cleaned)
+    
+    # Remove trailing special characters (except alphanumeric and space)  
+    cleaned = re.sub(r'[^\w\s]+$', '', cleaned)
+    
+    # Clean up any remaining unwanted characters but preserve important ones
+    # Remove quotes, brackets, etc. but keep hyphens, underscores in the middle
+    cleaned = re.sub(r'^["\'\[\]{}()<>]+', '', cleaned)
+    cleaned = re.sub(r'["\'\[\]{}()<>]+$', '', cleaned)
+    
+    # Remove leading/trailing percentage, caret, etc.
+    cleaned = re.sub(r'^[%^#@!&*+=|\\/:;,\.]+', '', cleaned)
+    cleaned = re.sub(r'[%^#@!&*+=|\\/:;,\.]+$', '', cleaned)
+    
+    # Final trim
+    cleaned = cleaned.strip()
+    
+    return cleaned
+
+def clean_sample_characteristics():
+    """
+    Clean special characters from sample characteristics labels and regenerate files.
+    """
+    paths = load_paths()
+    input_file = f"{paths['node_csv_files']}/sample_node.csv"
+    output_file = paths["sample_characteristics_cleaned_sample_node"]
+    
+    print(f"Loading sample node data from: {input_file}")
+    df = pd.read_csv(input_file)
+    
+    print(f"Original dataset: {len(df)} samples")
+    
+    # Track changes for reporting
+    changes_made = 0
+    examples_before_after = []
+    
+    # Process each row's Sample_characteristics with progress bar
+    for idx, row in tqdm(df.iterrows(), total=len(df), desc="Processing samples"):
+        if pd.isna(row['Sample_characteristics']):
+            continue
+            
+        characteristics = row['Sample_characteristics']
+        cleaned_pairs = []
+        
+        # Split by semicolon to get individual key:value pairs
+        for item in characteristics.split(';'):
+            item = item.strip()
+            if ':' in item:
+                # Split on first colon to separate key and value
+                key, value = item.split(':', 1)
+                original_key = key.strip()
+                cleaned_key = clean_label(original_key)
+                
+                # Track examples of changes
+                if original_key != cleaned_key and len(examples_before_after) < 20:
+                    examples_before_after.append((original_key, cleaned_key))
+                    changes_made += 1
+                elif original_key != cleaned_key:
+                    changes_made += 1
+                
+                # Reconstruct the key:value pair
+                cleaned_pairs.append(f"{cleaned_key}:{value.strip()}")
+            else:
+                # If no colon, keep as is
+                cleaned_pairs.append(item)
+        
+        # Update the row with cleaned characteristics
+        df.loc[idx, 'Sample_characteristics'] = '; '.join(cleaned_pairs)
+    
+    # Save the cleaned sample node file
+    ensure_parent_dir(output_file)
+    df.to_csv(output_file, index=False)
+    print(f"Cleaned sample node data saved to: {output_file}")
+    
+    # Show examples of changes made
+    print(f"\nChanges made: {changes_made} labels cleaned")
+    print(f"\nExamples of cleaning (before -> after):")
+    for before, after in examples_before_after:
+        print(f"  '{before}' -> '{after}'")
+    
+    return df
+
+def generate_cleaned_key_counts(sample_df):
+    """
+    Generate key counts from the cleaned sample characteristics.
+    """
+    print("\nGenerating key counts from cleaned data...")
+    
+    # Initialize a counter for keys
+    key_counter = Counter()
+    
+    # Iterate through the cleaned 'Sample_characteristics' column with progress bar
+    for entry in tqdm(sample_df['Sample_characteristics'].dropna(), desc="Counting keys"):
+        for item in entry.split(';'):
+            item = item.strip()
+            if ':' in item:
+                key = item.split(':', 1)[0].strip()
+                # Additional cleaning in case some special chars remain
+                key = clean_label(key)
+                if key:  # Only count non-empty keys
+                    key_counter[key] += 1
+    
+    # Convert to DataFrame
+    key_df = pd.DataFrame(key_counter.items(), columns=['name', 'count'])
+    
+    # Sort by count descending
+    key_df = key_df.sort_values(by='count', ascending=False)
+    
+    paths = load_paths()
+    output_file = paths["sample_characteristics_key_count_cleaned"]
+    ensure_parent_dir(output_file)
+    key_df.to_csv(output_file, index=False)
+    
+    print(f"Key counts saved to: {output_file}")
+    print(f"Total unique keys: {len(key_df)}")
+    
+    # Show top 20 most frequent keys
+    print(f"\nTop 20 most frequent keys after cleaning:")
+    for i, (_, row) in enumerate(key_df.head(20).iterrows()):
+        print(f"{i+1:2d}. {row['name']} (count: {row['count']})")
+    
+    return key_df
+
+def main():
+    """
+    Main function to clean sample characteristics and regenerate key counts.
+    """
+    print("=== Cleaning Sample Characteristics Labels ===")
+    
+    # Step 1: Clean the sample characteristics in the sample_node.csv
+    cleaned_sample_df = clean_sample_characteristics()
+    
+    # Step 2: Generate new key counts from cleaned data
+    key_counts_df = generate_cleaned_key_counts(cleaned_sample_df)
+    
+    print("\n=== Cleaning Complete ===")
+    print("Files generated:")
+    print("1. sample_node_chars_removed.csv - Sample node data with cleaned characteristic labels")
+    print("2. sample_characteristics_key_count_chars_removed.csv - Key frequency counts from cleaned labels")
+
+if __name__ == "__main__":
+    main() 
diff --git a/RDAS_RDOMICS/scripts/sample_characteristics_harmonization/2_rule_based_sample_label_cleaning.py b/RDAS_RDOMICS/scripts/sample_characteristics_harmonization/2_rule_based_sample_label_cleaning.py
new file mode 100644
index 0000000..7285574
--- /dev/null
+++ b/RDAS_RDOMICS/scripts/sample_characteristics_harmonization/2_rule_based_sample_label_cleaning.py
@@ -0,0 +1,120 @@
+import pandas as pd
+import re
+from pathlib import Path
+import sys
+
+CURRENT_DIR = Path(__file__).resolve().parent
+SCRIPTS_DIR = CURRENT_DIR.parent
+if str(SCRIPTS_DIR) not in sys.path:
+    sys.path.insert(0, str(SCRIPTS_DIR))
+
+from utils import ensure_parent_dir, load_paths
+
+def is_meaningful_label(label):
+    """
+    Check if a label is meaningful and worth keeping for clustering.
+    Returns True if the label should be kept, False if it should be filtered out.
+    """
+    # Convert to string and strip whitespace
+    label = str(label).strip()
+    
+    # Filter out empty or very short labels
+    if len(label) < 2:
+        return False
+    
+    # Filter out labels that are too long (likely to be descriptions rather than categories)
+    if len(label) > 100:
+        return False
+    
+    # Filter out labels with unmatched parentheses or brackets
+    if label.count('(') != label.count(')') or label.count('[') != label.count(']'):
+        return False
+    
+    # Filter out labels that are mostly numbers
+    if re.match(r'^[\d\.\-\+\s]+$', label):
+        return False
+    
+    # Filter out labels that are mostly special characters
+    special_char_ratio = len(re.findall(r'[^a-zA-Z0-9\s]', label)) / len(label)
+    if special_char_ratio > 0.5:
+        return False
+    
+    # Filter out labels that look like file paths or URLs
+    if '/' in label and len(label.split('/')) > 2:
+        return False
+    if 'http' in label.lower() or 'www.' in label.lower():
+        return False
+    
+    # Filter out labels that are just punctuation or symbols
+    if re.match(r'^[^\w\s]+$', label):
+        return False
+    
+    # Filter out labels that start or end with special characters (except common ones)
+    if re.match(r'^[^\w\s]', label) or re.search(r'[^\w\s]$', label):
+        # Allow labels ending with common abbreviations like pH, %, etc.
+        if not re.search(r'(ph|%|\w)$', label.lower()):
+            return False
+    
+    # Filter out labels that look like gene constructs or technical identifiers
+    # Examples: "Tg(-7.2sox10", "ST22 (H37Rv ideR"
+    if re.search(r'^[A-Z]{1,5}\d+\s*\(', label) or re.search(r'Tg\(', label):
+        return False
+    
+    # Filter out labels that are mostly uppercase and look like codes
+    if len(label) > 5 and label.isupper() and re.search(r'\d', label):
+        return False
+    
+    # Filter out labels with excessive underscores or dashes
+    underscore_ratio = label.count('_') / len(label)
+    dash_ratio = label.count('-') / len(label)
+    if underscore_ratio > 0.3 or dash_ratio > 0.3:
+        return False
+    
+    return True
+
+def clean_sample_labels(input_file, output_file):
+    """
+    Clean the sample characteristics labels by removing non-meaningful terms.
+    """
+    # Load the data
+    df = pd.read_csv(input_file)
+    
+    print(f"Original dataset: {len(df)} labels")
+    
+    # Apply filtering
+    df['is_meaningful'] = df['name'].apply(is_meaningful_label)
+    
+    # Show some examples of filtered out labels
+    filtered_out = df[~df['is_meaningful']]['name'].head(20).tolist()
+    print(f"\nExamples of filtered out labels:")
+    for label in filtered_out:
+        print(f"  '{label}'")
+    
+    # Keep only meaningful labels
+    cleaned_df = df[df['is_meaningful']].copy()
+    cleaned_df = cleaned_df.drop('is_meaningful', axis=1)
+    
+    # Sort by count (descending) to see most common terms first
+    cleaned_df = cleaned_df.sort_values('count', ascending=False)
+    
+    print(f"\nCleaned dataset: {len(cleaned_df)} labels")
+    print(f"Removed: {len(df) - len(cleaned_df)} labels ({(len(df) - len(cleaned_df))/len(df)*100:.1f}%)")
+    
+    # Save cleaned data
+    cleaned_df.to_csv(output_file, index=False)
+    print(f"Cleaned data saved to: {output_file}")
+    
+    # Show top 20 most frequent cleaned labels
+    print(f"\nTop 20 most frequent cleaned labels:")
+    for i, (_, row) in enumerate(cleaned_df.head(20).iterrows()):
+        print(f"{i+1:2d}. {row['name']} (count: {row['count']})")
+    
+    return cleaned_df
+
+if __name__ == "__main__":
+    paths = load_paths()
+    input_file = paths["sample_characteristics_key_count_cleaned"]
+    output_file = paths["sample_characteristics_key_count_rule_based"]
+    ensure_parent_dir(output_file)
+    
+    cleaned_df = clean_sample_labels(input_file, output_file) 
diff --git a/RDAS_RDOMICS/scripts/sample_characteristics_harmonization/3_filter_out_non_words_label.py b/RDAS_RDOMICS/scripts/sample_characteristics_harmonization/3_filter_out_non_words_label.py
new file mode 100644
index 0000000..2e4789f
--- /dev/null
+++ b/RDAS_RDOMICS/scripts/sample_characteristics_harmonization/3_filter_out_non_words_label.py
@@ -0,0 +1,286 @@
+"""
+Sample Characteristics Label Filtering Script
+
+This script filters sample characteristic labels to retain only those that contain
+standard English words from the NLTK English words corpus.
+
+PURPOSE:
+--------
+After cleaning special characters and applying rule-based filtering, many labels may still 
+contain non-English words, random strings, or irrelevant terms. This script uses a strict
+English-only approach to filter out all non-English terms, including scientific 
+abbreviations and biomedical terminology.
+
+METHODOLOGY:
+-----------
+1. English Dictionary Matching:
+   - Uses NLTK's words corpus to identify standard English words
+   - Handles common suffixes (plurals, -ing, -ed, etc.)
+   - Recognizes compound words and variations
+
+2. Compound Term Analysis:
+   - For multi-word labels, analyzes each component separately
+   - Keeps labels ONLY if ALL words are standard English words (100% requirement)
+   - Handles various separators (spaces, hyphens, underscores, slashes, periods)
+   - Rejects any label containing even one non-English word
+
+INPUT:
+------
+- sample_characteristics_key_count_chars_removed_rule_based_cleaned.csv
+  Contains cleaned sample characteristic labels with their frequency counts
+
+OUTPUT:
+-------
+- 3_sample_characteristics_key_count_english_only.csv
+  Filtered labels containing only standard English words
+  
+- 3removed_non_english_labels.txt
+  List of labels that were filtered out for manual review
+
+EXAMPLE LABELS KEPT:
+-------------------
+- "tissue" (English word)
+- "cell type" (English words)
+- "patient diagnosis" (English words)
+- "sample name" (English words)
+- "treatment group" (English words)
+
+EXAMPLE LABELS REMOVED:
+----------------------
+- "DNA methylation" (DNA is not in English dictionary)
+- "TP53 mutation" (TP53 is not in English dictionary)
+- "covid status" (covid is not in English dictionary)
+- Random character strings
+- Non-English language terms
+- Scientific abbreviations
+
+DEPENDENCIES:
+------------
+- nltk (for English words corpus)
+- pandas (for data processing)
+- tqdm (for progress bars)
+
+AUTHOR: Biomedical Data Processing Pipeline
+DATE: 2024
+"""
+
+import pandas as pd
+import nltk
+from nltk.corpus import words
+import re
+from tqdm import tqdm
+import string
+import warnings
+from pathlib import Path
+import sys
+warnings.filterwarnings('ignore')
+
+CURRENT_DIR = Path(__file__).resolve().parent
+SCRIPTS_DIR = CURRENT_DIR.parent
+if str(SCRIPTS_DIR) not in sys.path:
+    sys.path.insert(0, str(SCRIPTS_DIR))
+
+from utils import ensure_parent_dir, load_paths
+
+# Download required NLTK data
+try:
+    nltk.data.find('corpora/words')
+except LookupError:
+    print("Downloading NLTK words corpus...")
+    nltk.download('words')
+
+def is_english_word(word):
+    """
+    Check if a word is in the English dictionary.
+    """
+    if not word or len(word) < 2:
+        return False
+    
+    # Get NLTK English words
+    english_words = set(words.words())
+    
+    # Add some common words that might not be in NLTK dictionary
+    supplementary_words = {
+        'ethnicity', 'clinical', 'info', 'timepoint', 'dataset', 'barcode',
+        'id', 'type', 'state', 'part', 'point', 'version', 'batch', 'cell'
+    }
+    english_words.update(supplementary_words)
+    
+    # Convert to lowercase for comparison
+    word_lower = word.lower()
+    
+    # Direct match in NLTK words corpus
+    if word_lower in english_words:
+        return True
+    
+    # Handle plurals (simple case)
+    if word_lower.endswith('s') and word_lower[:-1] in english_words:
+        return True
+    
+    # Handle common English suffixes
+    common_suffixes = ['ing', 'ed', 'er', 'est', 'ly', 'tion', 'sion', 'ment', 'ness', 'able', 'ible']
+    for suffix in common_suffixes:
+        if word_lower.endswith(suffix):
+            root = word_lower[:-len(suffix)]
+            if len(root) > 2 and root in english_words:
+                return True
+    
+    return False
+
+def split_compound_words(text):
+    """
+    Split compound words and camelCase words into individual components.
+    """
+    # First handle camelCase (like "cellType" -> "cell Type")
+    text = re.sub(r'([a-z])([A-Z])', r'\1 \2', text)
+    
+    # Handle common compound patterns by inserting spaces
+    # This is a simple approach for the most common patterns
+    patterns = [
+        (r'subject(id|ID)', r'subject \1'),
+        (r'patient(id|ID)', r'patient \1'),
+        (r'sample(id|ID)', r'sample \1'),
+        (r'cell(type|Type)', r'cell \1'),
+        (r'tissue(type|Type)', r'tissue \1'),
+        (r'disease(state|State)', r'disease \1'),
+        (r'organism(part|Part)', r'organism \1'),
+        (r'time(point|Point)', r'time \1'),
+        (r'data(type|Type)', r'data \1'),
+        (r'bio(material|Material)', r'bio \1'),
+        (r'lab(version|Version)', r'lab \1'),
+        (r'treatment(short|Short)', r'treatment \1'),
+        (r'control(id|ID)', r'control \1'),
+        (r'plate(simple|Simple)', r'plate \1'),
+        (r'software(version|Version)', r'software \1'),
+        (r'sequencing(batch|Batch)', r'sequencing \1'),
+        (r'flow(cell|Cell)', r'flow \1'),
+    ]
+    
+    for pattern, replacement in patterns:
+        text = re.sub(pattern, replacement, text, flags=re.IGNORECASE)
+    
+    return text
+
+def should_keep_label(label):
+    """
+    Determine if a label should be kept based on English words only.
+    ALL words in the label must be standard English dictionary words.
+    """
+    if not label or not isinstance(label, str):
+        return False
+    
+    # Clean the label
+    label = label.strip()
+    if len(label) < 2:
+        return False
+    
+    # Split compound words first
+    label = split_compound_words(label)
+    
+    # Split into words (handling spaces, hyphens, underscores, slashes, and periods)
+    words_in_label = re.split(r'[\s\-_/\.]+', label.lower())
+    words_in_label = [w.strip(string.punctuation) for w in words_in_label if w.strip(string.punctuation)]
+    
+    if not words_in_label:
+        return False
+    
+    # ALL words must be English dictionary words
+    for word in words_in_label:
+        if not is_english_word(word):
+            return False  # If any word is not English, reject the entire label
+    
+    # If we get here, all words were English
+    return True
+
+def filter_non_english_labels():
+    """
+    Filter out labels that don't contain only English words.
+    """
+    paths = load_paths()
+    input_file = paths["sample_characteristics_key_count_rule_based"]
+    output_file = paths["sample_characteristics_key_count_english_only"]
+    
+    print(f"Loading cleaned labels from: {input_file}")
+    df = pd.read_csv(input_file)
+    
+    print(f"Original dataset: {len(df)} labels")
+    
+    # Filter labels
+    filtered_labels = []
+    removed_labels = []
+    
+    print("Filtering labels to keep only English dictionary words...")
+    for _, row in tqdm(df.iterrows(), total=len(df), desc="Processing labels"):
+        label = row['name']
+        if should_keep_label(label):
+            filtered_labels.append(row)
+        else:
+            removed_labels.append(label)
+    
+    # Create filtered DataFrame
+    filtered_df = pd.DataFrame(filtered_labels)
+    
+    # Sort by count descending
+    if not filtered_df.empty:
+        filtered_df = filtered_df.sort_values(by='count', ascending=False).reset_index(drop=True)
+    
+    # Save filtered results
+    ensure_parent_dir(output_file)
+    filtered_df.to_csv(output_file, index=False)
+    
+    print(f"\nFiltering complete!")
+    print(f"Labels kept: {len(filtered_df)}")
+    print(f"Labels removed: {len(removed_labels)}")
+    print(f"Retention rate: {len(filtered_df)/len(df)*100:.1f}%")
+    print(f"Filtered data saved to: {output_file}")
+    
+    # Show examples of removed labels
+    print(f"\nExamples of removed labels (first 20):")
+    for i, label in enumerate(removed_labels[:20]):
+        print(f"  {i+1:2d}. '{label}'")
+    
+    if len(removed_labels) > 20:
+        print(f"  ... and {len(removed_labels) - 20} more")
+    
+    # Show top 20 kept labels
+    print(f"\nTop 20 most frequent kept labels:")
+    for i, (_, row) in enumerate(filtered_df.head(20).iterrows()):
+        print(f"  {i+1:2d}. {row['name']} (count: {row['count']})")
+    
+    return filtered_df, removed_labels
+
+def save_removed_labels(removed_labels):
+    """
+    Save the list of removed labels for review.
+    """
+    output_file = load_paths()["sample_characteristics_removed_non_english"]
+    
+    ensure_parent_dir(output_file)
+    with open(output_file, 'w') as f:
+        f.write("Labels removed as non-English:\n")
+        f.write("=" * 40 + "\n\n")
+        for i, label in enumerate(removed_labels, 1):
+            f.write(f"{i:4d}. {label}\n")
+    
+    print(f"Removed labels saved to: {output_file}")
+
+def main():
+    """
+    Main function to filter out non-English labels.
+    """
+    print("=== Filtering Non-English Labels ===")
+    print("Using English dictionary only - strict filtering...")
+    
+    # Filter the labels
+    filtered_df, removed_labels = filter_non_english_labels()
+    
+    # Save removed labels for review
+    save_removed_labels(removed_labels)
+    
+    print("\n=== Filtering Complete ===")
+    print("Files generated:")
+    print("1. 3_sample_characteristics_key_count_english_only.csv - English words only")
+    print("2. 3removed_non_english_labels.txt - List of removed labels for review")
+
+if __name__ == "__main__":
+    main()
diff --git a/RDAS_RDOMICS/scripts/sample_characteristics_harmonization/4_llm_clustering_enhanced.py b/RDAS_RDOMICS/scripts/sample_characteristics_harmonization/4_llm_clustering_enhanced.py
new file mode 100644
index 0000000..51e9d28
--- /dev/null
+++ b/RDAS_RDOMICS/scripts/sample_characteristics_harmonization/4_llm_clustering_enhanced.py
@@ -0,0 +1,664 @@
+#!/usr/bin/env python3
+"""
+LLM-based Sample Characteristics Clustering with Confidence Scoring
+
+This script clusters biomedical sample labels into predefined categories using:
+1. Keyword-based pre-filtering for obvious matches
+2. Similarity-based matching for related terms  
+3. LLM-based categorization for complex cases
+4. Confidence scoring for all categorizations
+
+INPUT FILES:
+-----------
+1. 3_sample_characteristics_key_count_english_only.csv - Labels to be clustered
+2. sample_characteristics_vocabulary_fixed.csv - Target categories with definitions
+
+OUTPUT:
+-------
+clustered_sample_characteristics.csv - Final categorization results
+clustering_confidence_report.csv - Detailed confidence analysis
+"""
+
+import pandas as pd
+import json
+import numpy as np
+from typing import List, Dict, Set, Tuple
+import os
+import sys
+from pathlib import Path
+from collections import defaultdict
+from difflib import SequenceMatcher
+import re
+import time
+
+CURRENT_DIR = Path(__file__).resolve().parent
+SCRIPTS_DIR = CURRENT_DIR.parent
+if str(SCRIPTS_DIR) not in sys.path:
+    sys.path.insert(0, str(SCRIPTS_DIR))
+
+from utils import ensure_parent_dir, load_paths, load_settings
+
+# Import vLLM for local LLM inference
+try:
+    from vllm import LLM, SamplingParams
+    VLLM_AVAILABLE = True
+except ImportError:
+    print("Warning: vLLM not available. Please install vLLM.")
+    VLLM_AVAILABLE = False
+    sys.exit(1)
+
+
+def initialize_llm(model_path: str):
+    """Initialize the Llama3 model using vLLM."""
+    try:
+        print("Initializing Llama3 model...")
+        llm = LLM(
+            model=model_path,
+            tensor_parallel_size=4,
+            gpu_memory_utilization=0.95,
+            max_model_len=8192
+        )
+        
+        sampling_params = SamplingParams(
+            temperature=0.02,  # Very low temperature for consistent results
+            max_tokens=4096,
+            top_p=0.9,
+            stop=["</s>", "\n\n\n"]
+        )
+        
+        print("✓ Llama3 model initialized successfully")
+        return llm, sampling_params
+        
+    except Exception as e:
+        print(f"✗ Error initializing LLM: {e}")
+        return None, None
+
+
+def calculate_similarity(text1: str, text2: str) -> float:
+    """Calculate similarity between two text strings."""
+    return SequenceMatcher(None, text1.lower(), text2.lower()).ratio()
+
+
+def load_input_data(labels_file: str, vocab_file: str) -> Tuple[List[Tuple[str, int]], Dict[str, Dict]]:
+    """Load labels and vocabulary data."""
+    
+    print(f"Loading labels from {labels_file}...")
+    labels_df = pd.read_csv(labels_file)
+    labels_with_counts = [(row['name'], row['count']) for _, row in labels_df.iterrows()]
+    print(f"✓ Loaded {len(labels_with_counts)} labels")
+    
+    print(f"Loading vocabulary from {vocab_file}...")
+    vocab_df = pd.read_csv(vocab_file)
+    
+    categories = {}
+    for _, row in vocab_df.iterrows():
+        category_name = row['standarized_term']
+        categories[category_name] = {
+            'synonyms': row['synonym'] if pd.notna(row['synonym']) else '',
+            'examples': row['Example_entrys'] if pd.notna(row['Example_entrys']) else '',
+            'definition': row['Definition'] if pd.notna(row['Definition']) else ''
+        }
+    
+    print(f"✓ Loaded {len(categories)} categories")
+    
+    return labels_with_counts, categories
+
+
+def keyword_based_categorization(labels_with_counts: List[Tuple[str, int]], 
+                                categories: Dict[str, Dict]) -> Tuple[Dict[str, List[Dict]], List[Tuple[str, int]]]:
+    """Pre-categorize labels using enhanced keyword matching."""
+    
+    print("Starting keyword-based categorization...")
+    
+    # Enhanced keyword mappings based on categories
+    keyword_mappings = {
+        'External_sample_id': {
+            'exact_matches': ['patient_id', 'sample_id', 'donor_id', 'subject_id', 'patient id', 'sample id', 'donor id', 'subject id'],
+            'keywords': ['patient', 'id', 'sample', 'donor', 'subject', 'barcode', 'participant', 'individual', 'controlid', 'patientid', 'subjectid', 'sampleid'],
+            'patterns': [r'.*id$', r'.*_id$', r'patient.*', r'subject.*', r'donor.*']
+        },
+        'Biospecimen Organism': {
+            'exact_matches': ['species', 'organism', 'strain'],
+            'keywords': ['mouse', 'human', 'homo sapiens', 'mus musculus', 'host', 'background strain', 'mouse strain'],
+            'patterns': [r'.*strain.*', r'.*organism.*']
+        },
+        'Biospecimen Type': {
+            'exact_matches': ['tissue', 'cell', 'blood', 'serum', 'organ', 'cell type', 'celltype', 'tissue type'],
+            'keywords': ['lymphocyte', 'monocyte', 'macrophage', 'stem cell', 'biopsy', 'specimen', 'sample type', 'fluid', 'brain tissue', 'liver tissue'],
+            'patterns': [r'.*tissue.*', r'.*cell.*', r'.*blood.*']
+        },
+        'Biospecimen Age': {
+            'exact_matches': ['age', 'day', 'week', 'month', 'year', 'time'],
+            'keywords': ['developmental stage', 'passage', 'age in', 'donor age', 'patient age', 'time point', 'timepoint'],
+            'patterns': [r'.*age.*', r'.*day.*', r'.*time.*', r'.*stage.*']
+        },
+        'Biospecimen Sex': {
+            'exact_matches': ['sex', 'gender', 'male', 'female'],
+            'keywords': ['donor sex', 'patient gender', 'cell sex', 'animal sex'],
+            'patterns': [r'.*sex.*', r'.*gender.*']
+        },
+        'Biospecimen Race': {
+            'exact_matches': ['race', 'ethnicity'],
+            'keywords': ['caucasian', 'asian', 'hispanic', 'ethnicity', 'donor race', 'donor ethnicity'],
+            'patterns': [r'.*race.*', r'.*ethnicity.*', r'.*ethnic.*']
+        },
+        'Biospecimen Disease Condition': {
+            'exact_matches': ['disease', 'condition', 'diagnosis', 'cancer', 'tumor', 'infection'],
+            'keywords': ['disease state', 'disease status', 'clinical diagnosis', 'pathology', 'tumor type', 'cancer status', 'clinical condition'],
+            'patterns': [r'.*disease.*', r'.*tumor.*', r'.*cancer.*', r'.*diagnosis.*', r'.*condition.*']
+        },
+        'Treatment': {
+            'exact_matches': ['treatment', 'drug', 'therapy', 'medication', 'group', 'control', 'placebo'],
+            'keywords': ['drug treatment', 'therapy', 'intervention', 'compound', 'chemical', 'vaccine', 'antibody treatment', 'chemotherapy'],
+            'patterns': [r'.*treatment.*', r'.*drug.*', r'.*therapy.*', r'.*group.*']
+        },
+        'Treatment Dosage Regimen': {
+            'exact_matches': ['dose', 'dosage', 'concentration', 'duration'],
+            'keywords': ['treatment dose', 'drug dose', 'treatment duration', 'protocol', 'regimen', 'drug concentration'],
+            'patterns': [r'.*dose.*', r'.*dosage.*', r'.*concentration.*', r'.*duration.*']
+        }
+    }
+    
+    keyword_categorizations = defaultdict(list)
+    remaining_labels = []
+    
+    for label, count in labels_with_counts:
+        label_lower = label.lower().strip()
+        best_category = None
+        confidence = 'LOW'
+        matched_term = None
+        match_type = None
+        
+        # Check each category
+        for category, mapping in keyword_mappings.items():
+            
+            # Check exact matches first (highest confidence)
+            for exact_match in mapping['exact_matches']:
+                if exact_match.lower() == label_lower or exact_match.lower() in label_lower.split():
+                    best_category = category
+                    confidence = 'HIGH'
+                    matched_term = exact_match
+                    match_type = 'exact_match'
+                    break
+            
+            if best_category:
+                break
+            
+            # Check keyword matches (medium confidence)
+            for keyword in mapping['keywords']:
+                if keyword.lower() in label_lower:
+                    best_category = category
+                    confidence = 'MEDIUM'
+                    matched_term = keyword
+                    match_type = 'keyword'
+                    break
+            
+            if best_category:
+                break
+            
+            # Check pattern matches (lower confidence)
+            for pattern in mapping['patterns']:
+                if re.search(pattern, label_lower):
+                    if confidence != 'MEDIUM':  # Don't override higher confidence
+                        best_category = category
+                        confidence = 'MEDIUM' if 'id' in pattern or 'age' in pattern else 'LOW'
+                        matched_term = pattern
+                        match_type = 'pattern'
+                    break
+        
+        if best_category:
+            keyword_categorizations[best_category].append({
+                'label': label,
+                'count': count,
+                'matched_term': matched_term,
+                'match_type': match_type,
+                'confidence': confidence
+            })
+        else:
+            remaining_labels.append((label, count))
+    
+    total_processed = sum(len(results) for results in keyword_categorizations.values())
+    print(f"✓ Keyword categorization completed:")
+    print(f"  - {total_processed} labels categorized by keywords")
+    print(f"  - {len(remaining_labels)} labels remaining")
+    
+    return dict(keyword_categorizations), remaining_labels
+
+
+def similarity_based_categorization(remaining_labels: List[Tuple[str, int]], 
+                                   keyword_results: Dict[str, List[Dict]], 
+                                   threshold: float = 0.75) -> Tuple[Dict[str, List[Dict]], List[Tuple[str, int]]]:
+    """Categorize remaining labels using similarity to already categorized labels."""
+    
+    print(f"Starting similarity-based categorization with threshold {threshold}...")
+    
+    # Build reference terms from keyword results
+    reference_terms = {}
+    for category, results in keyword_results.items():
+        reference_terms[category] = [result['label'].lower() for result in results]
+    
+    similarity_categorizations = defaultdict(list)
+    final_remaining = []
+    
+    for label, count in remaining_labels:
+        best_match = None
+        best_score = 0
+        best_category = None
+        
+        for category, category_labels in reference_terms.items():
+            for ref_label in category_labels:
+                similarity = calculate_similarity(label, ref_label)
+                
+                if similarity > best_score and similarity >= threshold:
+                    best_score = similarity
+                    best_match = ref_label
+                    best_category = category
+        
+        if best_match:
+            similarity_categorizations[best_category].append({
+                'label': label,
+                'count': count,
+                'similar_to': best_match,
+                'similarity_score': best_score,
+                'confidence': 'HIGH' if best_score >= 0.9 else 'MEDIUM'
+            })
+        else:
+            final_remaining.append((label, count))
+    
+    total_processed = sum(len(results) for results in similarity_categorizations.values())
+    print(f"✓ Similarity categorization completed:")
+    print(f"  - {total_processed} labels categorized by similarity")
+    print(f"  - {len(final_remaining)} labels remaining for LLM")
+    
+    return dict(similarity_categorizations), final_remaining
+
+
+def create_clustering_prompt(labels_batch: List[Tuple[str, int]], 
+                           categories: Dict[str, Dict]) -> str:
+    """Create a clustering prompt for the LLM."""
+    
+    # Format category information
+    category_info = "AVAILABLE CATEGORIES:\n"
+    for i, (cat_name, cat_data) in enumerate(categories.items(), 1):
+        category_info += f"{i}. {cat_name}\n"
+        
+        if cat_data.get('definition'):
+            category_info += f"   Definition: {cat_data['definition'][:200]}...\n"
+        
+        if cat_data.get('synonyms'):
+            synonyms = cat_data['synonyms'][:300]  # Limit length
+            category_info += f"   Synonyms: {synonyms}...\n"
+        
+        category_info += "\n"
+    
+    # Format labels to categorize (show counts too for context)
+    labels_text = ""
+    for i, (label, count) in enumerate(labels_batch, 1):
+        labels_text += f"{i}. \"{label}\" (count: {count})\n"
+    
+    prompt = f"""You are an expert biomedical data curator. Categorize these biomedical sample characteristic labels into the most appropriate predefined categories.
+
+{category_info}
+
+LABELS TO CATEGORIZE:
+{labels_text}
+
+INSTRUCTIONS:
+- Assign each label to the MOST APPROPRIATE category above
+- Consider the label's semantic meaning and biological context
+- Use "Other" only if no category fits well
+- Higher count labels are more important to categorize correctly
+
+OUTPUT FORMAT - Respond with ONLY valid JSON:
+{{
+    "categorizations": [
+        {{"label": "example_label", "category": "Biospecimen Type", "confidence": "HIGH", "reasoning": "Brief explanation"}},
+        {{"label": "another_label", "category": "Treatment", "confidence": "MEDIUM", "reasoning": "Brief explanation"}}
+    ]
+}}
+
+JSON:"""
+    
+    return prompt
+
+
+def extract_json_from_llm_response(response_text: str) -> Dict:
+    """Extract JSON from LLM response with error handling."""
+    
+    # Try to find JSON object
+    if '{' in response_text and '}' in response_text:
+        start_idx = response_text.find('{')
+        end_idx = response_text.rfind('}') + 1
+        json_str = response_text[start_idx:end_idx]
+        
+        try:
+            result = json.loads(json_str)
+            if 'categorizations' in result and isinstance(result['categorizations'], list):
+                return result
+        except json.JSONDecodeError:
+            pass
+    
+    # Look for JSON after "JSON:" marker
+    if "JSON:" in response_text:
+        json_part = response_text.split("JSON:")[-1].strip()
+        if '{' in json_part and '}' in json_part:
+            start_idx = json_part.find('{')
+            end_idx = json_part.rfind('}') + 1
+            json_str = json_part[start_idx:end_idx]
+            
+            try:
+                result = json.loads(json_str)
+                if 'categorizations' in result and isinstance(result['categorizations'], list):
+                    return result
+            except json.JSONDecodeError:
+                pass
+    
+    return None
+
+
+def llm_categorization(labels_batch: List[Tuple[str, int]], 
+                      categories: Dict[str, Dict], 
+                      llm, sampling_params, 
+                      retry_count: int = 0) -> Dict:
+    """LLM-based categorization with retry logic."""
+    
+    prompt = create_clustering_prompt(labels_batch, categories)
+    
+    try:
+        outputs = llm.generate([prompt], sampling_params)
+        response_text = outputs[0].outputs[0].text.strip()
+        
+        print(f"LLM Response preview: {response_text[:150]}...")
+        
+        result = extract_json_from_llm_response(response_text)
+        
+        if result:
+            # Validate and clean results
+            valid_categories = list(categories.keys())
+            for cat_result in result['categorizations']:
+                if 'confidence' not in cat_result:
+                    cat_result['confidence'] = 'MEDIUM'
+                if cat_result['category'] not in valid_categories:
+                    cat_result['category'] = 'Other'
+                    cat_result['confidence'] = 'LOW'
+            
+            print(f"✓ Successfully categorized {len(result['categorizations'])} labels")
+            return result
+        else:
+            print("✗ No valid JSON found in LLM response")
+            
+            # Retry with smaller batch
+            if retry_count == 0 and len(labels_batch) > 3:
+                print(f"Retrying with smaller batch...")
+                mid = len(labels_batch) // 2
+                batch1 = labels_batch[:mid]
+                batch2 = labels_batch[mid:]
+                
+                result1 = llm_categorization(batch1, categories, llm, sampling_params, retry_count + 1)
+                result2 = llm_categorization(batch2, categories, llm, sampling_params, retry_count + 1)
+                
+                if result1 and result2:
+                    combined_result = {
+                        'categorizations': result1['categorizations'] + result2['categorizations']
+                    }
+                    return combined_result
+            
+            return None
+            
+    except Exception as e:
+        print(f"✗ Error in LLM categorization: {e}")
+        return None
+
+
+def combine_all_results(keyword_results: Dict, similarity_results: Dict, 
+                       llm_results: Dict, categories: Dict) -> Tuple[Dict, List]:
+    """Combine results from all categorization methods."""
+    
+    final_results = {}
+    confidence_report = []
+    
+    # Initialize categories
+    for category in categories.keys():
+        final_results[category] = []
+    
+    # Process keyword results
+    for category, results in keyword_results.items():
+        for result in results:
+            final_results[category].append(result['label'])
+            confidence_report.append({
+                'label': result['label'],
+                'count': result['count'],
+                'category': category,
+                'method': 'keyword',
+                'confidence': result['confidence'],
+                'details': f"{result['match_type']}: {result['matched_term']}"
+            })
+    
+    # Process similarity results
+    for category, results in similarity_results.items():
+        for result in results:
+            final_results[category].append(result['label'])
+            confidence_report.append({
+                'label': result['label'],
+                'count': result['count'],
+                'category': category,
+                'method': 'similarity',
+                'confidence': result['confidence'],
+                'details': f"Similar to: {result['similar_to']} (score: {result['similarity_score']:.3f})"
+            })
+    
+    # Process LLM results
+    for category, results in llm_results.items():
+        for result in results:
+            final_results[category].append(result['label'])
+            confidence_report.append({
+                'label': result['label'],
+                'count': result.get('count', 0),
+                'category': category,
+                'method': 'llm',
+                'confidence': result.get('confidence', 'MEDIUM'),
+                'details': result.get('reasoning', 'LLM categorization')
+            })
+    
+    return final_results, confidence_report
+
+
+def save_results(final_results: Dict, confidence_report: List, 
+                output_file: str, confidence_file: str):
+    """Save clustering results."""
+    
+    # Save final categorization results
+    output_data = []
+    for category, labels_list in final_results.items():
+        # Calculate total count for this category
+        total_count = 0
+        for report in confidence_report:
+            if report['category'] == category:
+                total_count += report.get('count', 0)
+        
+        output_data.append({
+            'standardized_term': category,
+            'label_count': len(labels_list),
+            'total_occurrence_count': total_count,
+            'labels': str(labels_list)
+        })
+    
+    output_df = pd.DataFrame(output_data)
+    output_df = output_df.sort_values('total_occurrence_count', ascending=False)
+    output_df.to_csv(output_file, index=False)
+    
+    # Save confidence report
+    confidence_df = pd.DataFrame(confidence_report)
+    confidence_df = confidence_df.sort_values(['category', 'count'], ascending=[True, False])
+    confidence_df.to_csv(confidence_file, index=False)
+    
+    print(f"✓ Results saved to {output_file}")
+    print(f"✓ Confidence report saved to {confidence_file}")
+
+
+def print_summary(final_results: Dict, confidence_report: List):
+    """Print clustering summary."""
+    
+    print("\n=== CLUSTERING SUMMARY ===")
+    total_labels = sum(len(labels) for labels in final_results.values())
+    total_occurrences = sum(report.get('count', 0) for report in confidence_report)
+    
+    print(f"Total labels clustered: {total_labels}")
+    print(f"Total label occurrences: {total_occurrences:,}")
+    
+    # Category summary
+    print(f"\nCATEGORY BREAKDOWN:")
+    category_stats = []
+    for category, labels_list in final_results.items():
+        cat_count = sum(report.get('count', 0) for report in confidence_report 
+                       if report['category'] == category)
+        category_stats.append((category, len(labels_list), cat_count))
+    
+    category_stats.sort(key=lambda x: x[2], reverse=True)  # Sort by occurrence count
+    
+    for category, label_count, occurrence_count in category_stats:
+        percentage = (occurrence_count / total_occurrences * 100) if total_occurrences > 0 else 0
+        print(f"  {category}: {label_count} labels ({occurrence_count:,} occurrences, {percentage:.1f}%)")
+    
+    # Confidence analysis
+    confidence_counts = {'HIGH': 0, 'MEDIUM': 0, 'LOW': 0}
+    method_counts = {'keyword': 0, 'similarity': 0, 'llm': 0}
+    
+    for report in confidence_report:
+        confidence_counts[report['confidence']] += 1
+        method_counts[report['method']] += 1
+    
+    print(f"\nCONFIDENCE ANALYSIS:")
+    for confidence, count in confidence_counts.items():
+        percentage = (count / total_labels * 100) if total_labels > 0 else 0
+        print(f"  {confidence}: {count} labels ({percentage:.1f}%)")
+    
+    print(f"\nMETHOD ANALYSIS:")
+    for method, count in method_counts.items():
+        percentage = (count / total_labels * 100) if total_labels > 0 else 0
+        print(f"  {method.title()}: {count} labels ({percentage:.1f}%)")
+
+
+def main():
+    """Main execution function."""
+    print("=== LLM-based Sample Characteristics Clustering ===")
+
+    paths = load_paths()
+    settings = load_settings()
+    labels_file = paths["sample_characteristics_key_count_english_only"]
+    vocab_file = paths["sample_characteristics_vocabulary"]
+    output_file = paths["sample_characteristics_clustered"]
+    confidence_file = paths["sample_characteristics_confidence_report"]
+    model_path = os.environ.get("RDAS_LLM_MODEL_PATH") or settings.get("llm_model_path")
+    
+    # Check input files
+    if not os.path.exists(labels_file):
+        print(f"✗ Labels file not found: {labels_file}")
+        return
+    
+    if not os.path.exists(vocab_file):
+        print(f"✗ Vocabulary file not found: {vocab_file}")
+        return
+    
+    try:
+        # Load data
+        print(f"\nLoading input data...")
+        labels_with_counts, categories = load_input_data(labels_file, vocab_file)
+        
+        # Stage 1: Keyword-based categorization
+        print(f"\n=== STAGE 1: KEYWORD-BASED CATEGORIZATION ===")
+        keyword_results, remaining_after_keywords = keyword_based_categorization(
+            labels_with_counts, categories
+        )
+        
+        # Stage 2: Similarity-based categorization
+        print(f"\n=== STAGE 2: SIMILARITY-BASED CATEGORIZATION ===")
+        similarity_results, remaining_after_similarity = similarity_based_categorization(
+            remaining_after_keywords, keyword_results, threshold=0.75
+        )
+        
+        # Stage 3: LLM-based categorization
+        print(f"\n=== STAGE 3: LLM-BASED CATEGORIZATION ===")
+        llm_results = defaultdict(list)
+        
+        if remaining_after_similarity:
+            print(f"Processing {len(remaining_after_similarity)} labels with LLM...")
+            
+            if not VLLM_AVAILABLE:
+                print("✗ vLLM not available")
+                return
+
+            if not model_path:
+                print("✗ No LLM model path configured. Set RDAS_LLM_MODEL_PATH or settings.llm_model_path.")
+                return
+
+            llm, sampling_params = initialize_llm(model_path)
+            if llm is None:
+                print("✗ Failed to initialize LLM")
+                return
+            
+            # Sort by count (descending) for better LLM performance on important labels
+            remaining_after_similarity.sort(key=lambda x: x[1], reverse=True)
+            
+            # Process in small batches
+            batch_size = 8
+            
+            for i in range(0, len(remaining_after_similarity), batch_size):
+                batch = remaining_after_similarity[i:i+batch_size]
+                batch_num = i // batch_size + 1
+                total_batches = (len(remaining_after_similarity) + batch_size - 1) // batch_size
+                
+                print(f"Processing LLM batch {batch_num}/{total_batches} ({len(batch)} labels)...")
+                
+                llm_result = llm_categorization(batch, categories, llm, sampling_params)
+                
+                if llm_result and 'categorizations' in llm_result:
+                    for cat_result in llm_result['categorizations']:
+                        # Find original count
+                        original_count = next((count for label, count in batch 
+                                             if label == cat_result['label']), 0)
+                        cat_result['count'] = original_count
+                        
+                        category = cat_result['category']
+                        llm_results[category].append(cat_result)
+                    
+                    print(f"✓ Batch {batch_num} processed successfully")
+                else:
+                    print(f"✗ Batch {batch_num} failed, adding to Other")
+                    for label, count in batch:
+                        llm_results['Other'].append({
+                            'label': label,
+                            'count': count,
+                            'confidence': 'LOW',
+                            'reasoning': 'LLM processing failed'
+                        })
+                
+                # Small delay between batches
+                time.sleep(1)
+        else:
+            print("✓ No labels remaining for LLM processing")
+        
+        # Combine all results
+        print(f"\n=== COMBINING RESULTS ===")
+        final_results, confidence_report = combine_all_results(
+            keyword_results, similarity_results, llm_results, categories
+        )
+        
+        # Save results
+        ensure_parent_dir(output_file)
+        ensure_parent_dir(confidence_file)
+        save_results(final_results, confidence_report, output_file, confidence_file)
+        
+        # Print summary
+        print_summary(final_results, confidence_report)
+        
+        print(f"\n✓ Clustering completed successfully!")
+        
+    except Exception as e:
+        print(f"✗ Error during clustering: {e}")
+        import traceback
+        traceback.print_exc()
+
+
+if __name__ == "__main__":
+    main() 
diff --git a/RDAS_RDOMICS/scripts/sample_characteristics_harmonization/5_llm_subclustering.py b/RDAS_RDOMICS/scripts/sample_characteristics_harmonization/5_llm_subclustering.py
new file mode 100644
index 0000000..a975181
--- /dev/null
+++ b/RDAS_RDOMICS/scripts/sample_characteristics_harmonization/5_llm_subclustering.py
@@ -0,0 +1,889 @@
+#!/usr/bin/env python3
+"""
+LLM-based Sub-clustering within Sample Characteristic Categories
+
+This script takes the clustered results from step 4 and further sub-clusters 
+the labels within each major category into more specific sub-categories.
+
+INPUT FILES:
+-----------
+1. clustered_sample_characteristics.csv - Main categories from step 4
+
+OUTPUT:
+-------
+Configured subclustering output CSV - Sub-categories results
+"""
+
+import pandas as pd
+import json
+import numpy as np
+from typing import List, Dict, Set, Tuple
+import os
+import sys
+from pathlib import Path
+from collections import defaultdict, Counter
+import re
+import time
+import ast
+from difflib import SequenceMatcher
+
+CURRENT_DIR = Path(__file__).resolve().parent
+SCRIPTS_DIR = CURRENT_DIR.parent
+if str(SCRIPTS_DIR) not in sys.path:
+    sys.path.insert(0, str(SCRIPTS_DIR))
+
+from utils import ensure_parent_dir, load_paths, load_settings
+
+# Import vLLM for local LLM inference
+try:
+    from vllm import LLM, SamplingParams
+    VLLM_AVAILABLE = True
+except ImportError:
+    print("Warning: vLLM not available. Please install vLLM.")
+    VLLM_AVAILABLE = False
+    sys.exit(1)
+
+
+# ------------------------- Data Loading Helpers -------------------------
+
+def initialize_llm(model_path: str):
+    """Initialize the Llama3 model using vLLM."""
+    try:
+        print("Initializing Llama3 model for sub-clustering...")
+        llm = LLM(
+            model=model_path,
+            tensor_parallel_size=4,
+            gpu_memory_utilization=0.95,
+            max_model_len=8192
+        )
+        
+        sampling_params = SamplingParams(
+            temperature=0.02,  # Very low temperature for consistent results
+            max_tokens=4096,
+            top_p=0.9,
+            stop=["</s>", "\n\n\n"]
+        )
+        
+        print("✓ Llama3 model initialized successfully")
+        return llm, sampling_params
+        
+    except Exception as e:
+        print(f"✗ Error initializing LLM: {e}")
+        return None, None
+
+
+def load_clustered_data(clustered_file: str) -> Dict[str, List[str]]:
+    """Load clustered data and extract labels for each category."""
+    
+    print(f"Loading clustered data from {clustered_file}...")
+    clustered_df = pd.read_csv(clustered_file)
+    
+    # Process clustered data
+    categories_data = {}
+    for _, row in clustered_df.iterrows():
+        category = row['standardized_term']
+        
+        # Parse labels list from string representation
+        try:
+            labels_list = ast.literal_eval(row['labels'])
+        except:
+            # Fallback parsing if ast fails
+            labels_str = row['labels'].strip("[]'\"")
+            labels_list = [label.strip().strip("'\"") for label in labels_str.split("', '")]
+        
+        categories_data[category] = labels_list
+    
+    print(f"✓ Loaded data for {len(categories_data)} categories from clustered file")
+    
+    return categories_data
+
+
+# ------------------------- LLM Prompting -------------------------
+
+def create_subclustering_prompt(category_name: str, labels_batch: List[str], 
+                               max_subcategories: int = 8) -> str:
+    """Create a sub-clustering prompt for the LLM."""
+    
+    # Format labels for display
+    labels_text = ""
+    for i, label in enumerate(labels_batch, 1):
+        labels_text += f"{i}. \"{label}\"\n"
+    
+    prompt = f"""You are an expert biomedical data curator. Your task is to sub-cluster these "{category_name}" labels into more specific, meaningful sub-categories.
+
+LABELS TO SUB-CLUSTER:
+{labels_text}
+
+INSTRUCTIONS:
+- Create EXACTLY {max_subcategories} or fewer meaningful sub-categories that best organize these labels
+- Each sub-category should represent a coherent biological or technical concept
+- Sub-category names should be concise, descriptive, and not include the main category name
+- Prefer broader categories that can accommodate multiple related labels
+- Avoid creating sub-categories with only 1-2 labels - merge them into broader categories
+- IMPORTANT: Assign EVERY label to one of your named sub-categories. Do NOT output an "Other" sub-category.
+
+OUTPUT FORMAT - Respond with ONLY valid JSON (no explanations):
+{{
+    "subcategories": [
+        {{
+            "name": "Sub-category Name 1",
+            "labels": ["label1", "label2", "label3"]
+        }},
+        {{
+            "name": "Sub-category Name 2", 
+            "labels": ["label4", "label5", "label6"]
+        }}
+    ]
+}}
+
+JSON:"""
+    
+    return prompt
+
+
+def extract_json_from_response(response_text: str) -> Dict:
+    """Extract JSON from LLM response with robust error handling and sanitization."""
+    raw = response_text.strip()
+
+    def try_load(s: str) -> Dict:
+        try:
+            obj = json.loads(s)
+            if isinstance(obj, dict) and 'subcategories' in obj and isinstance(obj['subcategories'], list):
+                return obj
+        except Exception:
+            pass
+        return None
+
+    # 1) Remove code fences if present
+    if raw.startswith('```'):
+        raw = raw.strip('`')
+        # Remove possible leading language tag like json
+        if raw.startswith('json'):
+            raw = raw[4:]
+    raw = raw.strip()
+
+    # 2) Extract the most outer JSON object
+    if '{' in raw and '}' in raw:
+        start_idx = raw.find('{')
+        end_idx = raw.rfind('}') + 1
+        candidate = raw[start_idx:end_idx]
+        result = try_load(candidate)
+        if result:
+            return result
+
+    # 3) If prefixed with JSON: marker, try that part specifically
+    if 'JSON:' in raw:
+        json_part = raw.split('JSON:')[-1].strip()
+        if '{' in json_part and '}' in json_part:
+            start_idx = json_part.find('{')
+            end_idx = json_part.rfind('}') + 1
+            candidate = json_part[start_idx:end_idx]
+            result = try_load(candidate)
+            if result:
+                return result
+
+    # 4) Sanitization: remove trailing commas before ] or }
+    sanitized = re.sub(r',\s*([}\]])', r'\1', raw)
+    if '{' in sanitized and '}' in sanitized:
+        start_idx = sanitized.find('{')
+        end_idx = sanitized.rfind('}') + 1
+        candidate = sanitized[start_idx:end_idx]
+        result = try_load(candidate)
+        if result:
+            return result
+
+    # 5) Last resort: attempt Python literal eval after converting JSON booleans/null
+    pyish = raw.replace('true', 'True').replace('false', 'False').replace('null', 'None')
+    if '{' in pyish and '}' in pyish:
+        start_idx = pyish.find('{')
+        end_idx = pyish.rfind('}') + 1
+        candidate = pyish[start_idx:end_idx]
+        try:
+            obj = ast.literal_eval(candidate)
+            if isinstance(obj, dict) and 'subcategories' in obj and isinstance(obj['subcategories'], list):
+                return obj
+        except Exception:
+            pass
+
+    return None
+
+
+# ------------------------- LLM Subclustering -------------------------
+
+def create_reassignment_prompt(category_name: str, existing_subcats: List[Dict], leftovers: List[str]) -> str:
+    """Prompt that asks the LLM to assign leftover labels to one of the existing subcategory names."""
+    names = [sc['name'] for sc in existing_subcats]
+    # Build small examples for each subcategory to guide assignment
+    examples_text = ""
+    for sc in existing_subcats:
+        sample_labels = sc['labels'][:5]
+        examples_text += f"- {sc['name']}: {sample_labels}\n"
+    leftovers_text = "\n".join([f"- {l}" for l in leftovers])
+    prompt = f"""You are assisting with finalizing sub-categories for the main category "{category_name}".
+We already have the following sub-categories:
+{names}
+
+EXAMPLES (few labels assigned to each sub-category):
+{examples_text}
+
+Please assign EACH of the following leftover labels to ONE of the existing sub-category names above.
+Return ONLY valid JSON with this format (no explanations):
+{{
+  "assignments": [
+    {{"label": "leftover_label_1", "subcategory": "One of {names}"}},
+    {{"label": "leftover_label_2", "subcategory": "One of {names}"}}
+  ]
+}}
+
+LEFTOVER LABELS:
+{leftovers_text}
+
+JSON:"""
+    return prompt
+
+
+def llm_reassign_leftovers(category_name: str, existing_subcats: List[Dict], leftovers: List[str], llm, sampling_params) -> Dict[str, str]:
+    """Ask the LLM to map each leftover label to one of the existing subcategory names."""
+    if not leftovers:
+        return {}
+    prompt = create_reassignment_prompt(category_name, existing_subcats, leftovers)
+    try:
+        outputs = llm.generate([prompt], sampling_params)
+        response_text = outputs[0].outputs[0].text.strip()
+        # Extract simple JSON
+        try:
+            data = json.loads(response_text[response_text.find('{'):response_text.rfind('}')+1])
+        except Exception:
+            data = None
+        mapping: Dict[str, str] = {}
+        if data and isinstance(data.get('assignments'), list):
+            valid_names = {sc['name'] for sc in existing_subcats}
+            for item in data['assignments']:
+                label = item.get('label')
+                subcat = item.get('subcategory')
+                if label in leftovers and subcat in valid_names:
+                    mapping[label] = subcat
+        return mapping
+    except Exception as e:
+        print(f"✗ Error in leftover reassignment: {e}")
+        return {}
+
+
+def heuristic_reassign_leftovers(existing_subcats: List[Dict], leftovers: List[str]) -> Dict[str, str]:
+    """Heuristic fallback: assign each leftover to the most similar existing subcategory (name or labels)."""
+    mapping: Dict[str, str] = {}
+    for label in leftovers:
+        best_name = None
+        best_score = -1.0
+        for sc in existing_subcats:
+            # Compare to subcategory name
+            score = SequenceMatcher(None, label.lower(), sc['name'].lower()).ratio()
+            # Also compare to a few labels in the subcategory
+            for ex in sc['labels'][:5]:
+                score = max(score, SequenceMatcher(None, label.lower(), ex.lower()).ratio())
+            if score > best_score:
+                best_score = score
+                best_name = sc['name']
+        if best_name is not None:
+            mapping[label] = best_name
+    return mapping
+
+
+def llm_subclustering(category_name: str, labels_batch: List[str], 
+                     llm, sampling_params, max_subcategories: int = 8, retry_depth: int = 0) -> Dict:
+    """Perform LLM-based sub-clustering with retry logic (smaller batches on failure)."""
+    
+    prompt = create_subclustering_prompt(category_name, labels_batch, max_subcategories)
+    
+    try:
+        outputs = llm.generate([prompt], sampling_params)
+        response_text = outputs[0].outputs[0].text.strip()
+        
+        print(f"LLM Response preview: {response_text[:200]}...")
+        
+        result = extract_json_from_response(response_text)
+        
+        if result and 'subcategories' in result:
+            # Validate subcategories
+            valid_subcategories = []
+            all_input_labels = set(labels_batch)
+            assigned_labels = set()
+            
+            for subcat in result['subcategories']:
+                if 'name' in subcat and 'labels' in subcat:
+                    # Filter to only include labels that were in the input
+                    clean_labels = [label for label in subcat['labels'] if label in all_input_labels]
+                    if clean_labels:
+                        # De-duplicate labels within subcategory
+                        seen_local = set()
+                        deduped = []
+                        for l in clean_labels:
+                            if l not in seen_local:
+                                seen_local.add(l)
+                                deduped.append(l)
+                        assigned_labels.update(deduped)
+                        valid_subcategories.append({'name': subcat['name'], 'labels': deduped})
+            
+            # Handle any unassigned labels by asking LLM to reassign to existing subcategories
+            unassigned = [l for l in labels_batch if l not in assigned_labels]
+            if unassigned:
+                mapping = llm_reassign_leftovers(category_name, valid_subcategories, unassigned, llm, sampling_params)
+                # Fallback heuristic if needed
+                if not mapping or len(mapping) < len(unassigned):
+                    remaining = [l for l in unassigned if l not in mapping]
+                    heuristic_map = heuristic_reassign_leftovers(valid_subcategories, remaining)
+                    mapping.update(heuristic_map)
+                # Apply mapping
+                name_to_idx = {sc['name']: i for i, sc in enumerate(valid_subcategories)}
+                for label, subname in mapping.items():
+                    idx = name_to_idx.get(subname)
+                    if idx is not None:
+                        valid_subcategories[idx]['labels'].append(label)
+                        assigned_labels.add(label)
+            
+            # Final safety: any still-unassigned go to best-matching existing
+            still_unassigned = [l for l in labels_batch if l not in assigned_labels]
+            if still_unassigned and valid_subcategories:
+                heuristic_map = heuristic_reassign_leftovers(valid_subcategories, still_unassigned)
+                name_to_idx = {sc['name']: i for i, sc in enumerate(valid_subcategories)}
+                for label, subname in heuristic_map.items():
+                    idx = name_to_idx.get(subname)
+                    if idx is not None:
+                        valid_subcategories[idx]['labels'].append(label)
+                        assigned_labels.add(label)
+            
+            print(f"✓ Successfully created {len(valid_subcategories)} subcategories")
+            return {'subcategories': valid_subcategories}
+        
+        else:
+            print("✗ No valid JSON found in LLM response")
+            # Retry by splitting into smaller batches once
+            if retry_depth == 0 and len(labels_batch) > 20:
+                mid = len(labels_batch) // 2
+                left = llm_subclustering(category_name, labels_batch[:mid], llm, sampling_params, max_subcategories=max_subcategories, retry_depth=1)
+                right = llm_subclustering(category_name, labels_batch[mid:], llm, sampling_params, max_subcategories=max_subcategories, retry_depth=1)
+                combined: List[Dict] = []
+                for part in [left, right]:
+                    if part and 'subcategories' in part:
+                        combined.extend(part['subcategories'])
+                if combined:
+                    return {'subcategories': combined}
+            # Fallback: single bucket
+            return {'subcategories': [{'name': 'Cluster 1', 'labels': labels_batch}]}
+            
+    except Exception as e:
+        print(f"✗ Error in LLM subclustering: {e}")
+        # Fallback: single bucket
+        return {'subcategories': [{'name': 'Cluster 1', 'labels': labels_batch}]}
+
+
+def create_final_merge_prompt(category_name: str, labels: List[str], target_count: int = 8) -> str:
+    """Create a prompt for final LLM-based consolidation into representative subcategories."""
+    labels_text = "\n".join([f"- {label}" for label in labels])
+    prompt = f"""You are an expert biomedical data curator. Given the full set of labels for the main category "{category_name}", cluster them into at most {target_count} representative sub-categories.
+
+REQUIREMENTS:
+- Use concise, descriptive names that a human curator would recognize
+- Assign every label to exactly one sub-category
+- Avoid creating sub-categories with only 1-2 labels unless absolutely necessary
+- Do NOT output an "Other" sub-category
+- Output ONLY valid JSON, no explanations
+
+LABELS:
+{labels_text}
+
+OUTPUT JSON FORMAT:
+{{
+  "subcategories": [
+    {{"name": "Representative Name 1", "labels": ["..."]}} ,
+    {{"name": "Representative Name 2", "labels": ["..."]}}
+  ]
+}}
+
+JSON:"""
+    return prompt
+
+
+def llm_final_merge(category_name: str, labels: List[str], llm, sampling_params, target_count: int = 8) -> List[Dict]:
+    """Use the LLM to produce the final consolidated subcategories (name + labels only), with retry."""
+    prompt = create_final_merge_prompt(category_name, labels, target_count)
+    try:
+        outputs = llm.generate([prompt], sampling_params)
+        response_text = outputs[0].outputs[0].text.strip()
+        print(f"Final merge LLM response preview: {response_text[:200]}...")
+        result = extract_json_from_response(response_text)
+        if not (result and 'subcategories' in result):
+            # Retry once with smaller target (to encourage grouping)
+            prompt2 = create_final_merge_prompt(category_name, labels, max(4, target_count - 2))
+            outputs = llm.generate([prompt2], sampling_params)
+            response_text = outputs[0].outputs[0].text.strip()
+            result = extract_json_from_response(response_text)
+        if result and 'subcategories' in result:
+            final_subcats = []
+            input_set = set(labels)
+            seen_labels = set()
+            for subcat in result['subcategories']:
+                if 'name' not in subcat or 'labels' not in subcat:
+                    continue
+                clean_labels = [l for l in subcat['labels'] if l in input_set and l not in seen_labels]
+                if clean_labels:
+                    seen_labels.update(clean_labels)
+                    final_subcats.append({'name': subcat['name'], 'labels': clean_labels})
+            # Reassign any missed labels to existing final subcategories
+            missed = [l for l in labels if l not in seen_labels]
+            if missed and final_subcats:
+                mapping = llm_reassign_leftovers(category_name, final_subcats, missed, llm, sampling_params)
+                remaining = [l for l in missed if l not in mapping]
+                if remaining:
+                    heuristic_map = heuristic_reassign_leftovers(final_subcats, remaining)
+                    mapping.update(heuristic_map)
+                name_to_idx = {sc['name']: i for i, sc in enumerate(final_subcats)}
+                for label, subname in mapping.items():
+                    idx = name_to_idx.get(subname)
+                    if idx is not None:
+                        final_subcats[idx]['labels'].append(label)
+                        seen_labels.add(label)
+            if not final_subcats:
+                final_subcats = [{'name': 'Cluster 1', 'labels': labels}]
+            return final_subcats
+        # Fallback
+        return [{'name': 'Cluster 1', 'labels': labels}]
+    except Exception as e:
+        print(f"✗ Error in final LLM merge: {e}")
+        return [{'name': 'Cluster 1', 'labels': labels}]
+
+
+def create_subcat_merge_prompt(category_name: str, subcats: List[Dict], target_count: int = 8) -> str:
+    """Prompt to merge existing subcategories into up to target_count higher-level groups.
+    Returns mapping from subcategory names to merged group names.
+    """
+    examples = []
+    for sc in subcats:
+        sample = sc['labels'][:4]
+        examples.append(f"- {sc['name']}: {sample}")
+    examples_text = "\n".join(examples)
+    subcat_names = ", ".join([sc['name'] for sc in subcats])
+    prompt = f"""
+You are an expert biomedical data curator. Merge the existing sub-categories for the main category "{category_name}" into at most {target_count} coherent, human-readable groups.
+
+REQUIREMENTS:
+- Use concise, descriptive group names that do not include the main category name
+- Assign EVERY sub-category to exactly ONE group
+- Do NOT create an "Other" group
+- Output ONLY valid JSON enclosed in a single ```json fenced block
+
+EXISTING SUB-CATEGORIES:
+{subcat_names}
+
+EXAMPLES (few labels per sub-category to guide grouping):
+{examples_text}
+
+OUTPUT JSON FORMAT:
+```json
+{{
+  "groups": [
+    {{"name": "Group Name 1", "subcategories": ["subcat name a", "subcat name b"]}},
+    {{"name": "Group Name 2", "subcategories": ["subcat name c"]}}
+  ]
+}}
+```
+"""
+    return prompt
+
+
+def extract_json_block(response_text: str) -> str:
+    """Extract the content inside a ```json ... ``` block if present; else return raw."""
+    m = re.search(r"```json\s*(\{[\s\S]*?\})\s*```", response_text)
+    if m:
+        return m.group(1)
+    return response_text
+
+
+def llm_merge_subcategories(category_name: str, subcats: List[Dict], llm, sampling_params, target_count: int = 8) -> List[Dict]:
+    """Merge existing subcategories into at most target_count groups using the LLM.
+    Returns list of merged subcategories with aggregated labels.
+    """
+    if not subcats:
+        return []
+    prompt = create_subcat_merge_prompt(category_name, subcats, target_count)
+    try:
+        outputs = llm.generate([prompt], sampling_params)
+        text = outputs[0].outputs[0].text.strip()
+        json_str = extract_json_block(text)
+        data = extract_json_from_response(json_str) or extract_json_from_response(text)
+        merged = []
+        if data and isinstance(data.get('groups'), list):
+            name_to_labels: Dict[str, List[str]] = {}
+            # Map subcat name -> labels
+            subcat_lookup = {sc['name']: sc['labels'] for sc in subcats}
+            for grp in data['groups']:
+                gname = grp.get('name')
+                sc_names = grp.get('subcategories', [])
+                if not gname or not sc_names:
+                    continue
+                labels_accum: List[str] = []
+                for scn in sc_names:
+                    labels_accum.extend(subcat_lookup.get(scn, []))
+                # Deduplicate labels
+                seen = set()
+                deduped = []
+                for l in labels_accum:
+                    if l not in seen:
+                        seen.add(l)
+                        deduped.append(l)
+                if deduped:
+                    merged.append({"name": gname, "labels": deduped})
+        return merged
+    except Exception as e:
+        print(f"✗ Error in llm_merge_subcategories: {e}")
+        return []
+
+
+def heuristic_merge_subcategories(subcats: List[Dict], target_count: int = 8) -> List[Dict]:
+    """Heuristic fallback: merge subcategories by name similarity until <= target_count groups."""
+    if len(subcats) <= target_count:
+        return subcats
+    groups: List[List[Dict]] = []
+    for sc in subcats:
+        placed = False
+        for g in groups:
+            # Compare to first name in group
+            ref = g[0]['name']
+            score = SequenceMatcher(None, sc['name'].lower(), ref.lower()).ratio()
+            if score >= 0.45:
+                g.append(sc)
+                placed = True
+                break
+        if not placed:
+            groups.append([sc])
+    # If still many groups, merge smallest by name similarity
+    while len(groups) > target_count:
+        groups.sort(key=lambda x: sum(len(s['labels']) for s in x))
+        g1 = groups.pop(0)
+        # Merge into most similar group
+        best_idx, best_score = 0, -1.0
+        for i, g in enumerate(groups):
+            score = SequenceMatcher(None, g1[0]['name'].lower(), g[0]['name'].lower()).ratio()
+            if score > best_score:
+                best_score, best_idx = score, i
+        groups[best_idx].extend(g1)
+    # Build merged
+    merged: List[Dict] = []
+    for g in groups:
+        all_labels: List[str] = []
+        names: List[str] = []
+        for sc in g:
+            all_labels.extend(sc['labels'])
+            names.append(sc['name'])
+        seen = set()
+        deduped = []
+        for l in all_labels:
+            if l not in seen:
+                seen.add(l)
+                deduped.append(l)
+        merged_name = max(names, key=len)
+        merged.append({"name": merged_name, "labels": deduped})
+    return merged
+
+def create_naming_prompt(category_name: str, subcats: List[Dict]) -> str:
+    """Create a prompt to assign concise, descriptive names to each subcategory based on its labels."""
+    entries = []
+    for sc in subcats:
+        sample = sc['labels'][:12]
+        entries.append(f"- {sc['name']}: {sample}")
+    entries_text = "\n".join(entries)
+    prompt = f"""
+You are an expert biomedical data curator. For the main category "{category_name}", assign a concise, descriptive name to EACH sub-category below based on its example labels.
+
+REQUIREMENTS:
+- Provide meaningful names that do NOT include the main category name
+- Keep names short and human-readable
+- Output ONLY valid JSON enclosed in a single ```json fenced block
+
+SUB-CATEGORIES WITH EXAMPLE LABELS:
+{entries_text}
+
+OUTPUT JSON FORMAT:
+```json
+{{
+  "names": [
+    {{"old": "existing subcat name", "new": "Concise descriptive name"}}
+  ]
+}}
+```
+"""
+    return prompt
+
+
+def llm_name_subcategories(category_name: str, subcats: List[Dict], llm, sampling_params) -> List[Dict]:
+    """Rename generic subcategory names using LLM suggestions; fallback keeps original."""
+    if not subcats:
+        return subcats
+    prompt = create_naming_prompt(category_name, subcats)
+    try:
+        outputs = llm.generate([prompt], sampling_params)
+        text = outputs[0].outputs[0].text.strip()
+        json_str = extract_json_block(text)
+        data = None
+        try:
+            data = json.loads(json_str)
+        except Exception:
+            try:
+                data = json.loads(text[text.find('{'):text.rfind('}')+1])
+            except Exception:
+                data = None
+        mapping: Dict[str, str] = {}
+        if data and isinstance(data.get('names'), list):
+            for item in data['names']:
+                old = item.get('old')
+                new = item.get('new')
+                if old and new:
+                    mapping[old] = new
+        # Apply mapping to any generic names
+        renamed: List[Dict] = []
+        for sc in subcats:
+            old = sc['name']
+            if old in mapping:
+                renamed.append({"name": mapping[old], "labels": sc['labels']})
+            else:
+                renamed.append(sc)
+        return renamed
+    except Exception as e:
+        print(f"✗ Error in llm_name_subcategories: {e}")
+        return subcats
+
+
+def needs_naming(subcats: List[Dict]) -> bool:
+    for sc in subcats:
+        n = sc['name'].lower()
+        if n.startswith('chunk') or n.startswith('cluster'):
+            return True
+    return False
+
+# Apply naming after pipelines where appropriate
+# 1) After hierarchical merge fallback
+# (modify process_category_in_batches to call naming if generic names persist)
+
+# Wire hierarchical merge into the batch pipeline
+
+def base_process_category_in_batches(category_name: str, labels: List[str], 
+                                    llm, sampling_params, batch_size: int = 100) -> List[Dict]:
+    """Original batching + final-merge pipeline."""
+    if len(labels) <= batch_size:
+        # Small category - process as single batch directly to target_count
+        result = llm_subclustering(category_name, labels, llm, sampling_params, max_subcategories=8)
+        return result['subcategories'] if result else [{'name': 'Cluster 1', 'labels': labels}]
+    
+    print(f"Processing {category_name} in batches (total labels: {len(labels)})")
+    
+    all_subcategories = []
+    batch_num = 0
+    
+    for i in range(0, len(labels), batch_size):
+        batch = labels[i:i+batch_size]
+        batch_num += 1
+        
+        print(f"  Processing batch {batch_num} ({len(batch)} labels)...")
+        
+        result = llm_subclustering(category_name, batch, llm, sampling_params, max_subcategories=6)
+        
+        if result and 'subcategories' in result:
+            all_subcategories.extend(result['subcategories'])
+        
+        # Small delay between batches
+        time.sleep(1)
+    
+    # Final LLM-based consolidation: use the full label list to produce <= target_count groups
+    unique_labels = []
+    seen = set()
+    for subcat in all_subcategories:
+        for l in subcat['labels']:
+            if l not in seen:
+                seen.add(l)
+                unique_labels.append(l)
+    
+    final_subcategories = llm_final_merge(category_name, unique_labels, llm, sampling_params, target_count=8)
+    return final_subcategories
+
+
+def process_category_in_batches(category_name: str, labels: List[str], 
+                               llm, sampling_params, batch_size: int = 100) -> List[Dict]:
+    """Wrapper that uses the base pipeline and, if it collapses to one cluster, attempts hierarchical merging."""
+    prelim = base_process_category_in_batches(category_name, labels, llm, sampling_params, batch_size)
+    if not prelim:
+        return []
+    # If the result is a single generic cluster, attempt hierarchical merge using pseudo-subcategories
+    if len(prelim) == 1 and prelim[0]['name'].lower().startswith('cluster'):
+        print("Result collapsed to a single cluster; attempting hierarchical merge of subcategories...")
+        # Create pseudo-subcategories by chunking labels deterministically
+        pseudo_subcats: List[Dict] = []
+        chunk = max(30, min(100, len(labels)//6 or 30))
+        for i in range(0, len(labels), chunk):
+            pseudo_subcats.append({"name": f"Chunk {i//chunk+1}", "labels": labels[i:i+chunk]})
+        # Try LLM-based merge of pseudo subcats
+        merged = llm_merge_subcategories(category_name, pseudo_subcats, llm, sampling_params, target_count=8)
+        if merged:
+            # Name the merged groups if needed
+            if needs_naming(merged):
+                merged = llm_name_subcategories(category_name, merged, llm, sampling_params)
+            return merged
+        # Heuristic fallback
+        merged = heuristic_merge_subcategories(pseudo_subcats, target_count=8)
+        if needs_naming(merged):
+            merged = llm_name_subcategories(category_name, merged, llm, sampling_params)
+        return merged
+    # Name prelim if contains generic placeholders
+    if needs_naming(prelim):
+        prelim = llm_name_subcategories(category_name, prelim, llm, sampling_params)
+    return prelim
+
+
+# ------------------------- Saving / Summary -------------------------
+
+def save_category_results(category_name: str, subcategories: List[Dict], 
+                         output_file: str, append: bool = True):
+    """Save results for a single category incrementally (name + labels only)."""
+    
+    print(f"Saving results for '{category_name}' to file {output_file}...")
+    
+    # Prepare data for this category
+    output_data = []
+    
+    for subcat in subcategories:
+        output_data.append({
+            'main_category': category_name,
+            'subcategory': subcat['name'],
+            'labels': str(subcat['labels'])
+        })
+    
+    # Create DataFrame
+    output_df = pd.DataFrame(output_data)
+    
+    # Write to file (append mode if file exists)
+    write_header = not (append and os.path.exists(output_file))
+    output_df.to_csv(output_file, mode='a' if append else 'w', 
+                     header=write_header, index=False)
+    
+    print(f"✓ Saved {len(subcategories)} subcategories for '{category_name}'")
+    print(f"  - {len(output_data)} rows added to {output_file}")
+
+
+# ------------------------- Main -------------------------
+
+def print_category_summary(category_name: str, subcategories: List[Dict]):
+    """Print summary for a single category."""
+    
+    total_labels = sum(len(subcat['labels']) for subcat in subcategories)
+    
+    print(f"\n--- {category_name} Summary ---")
+    print(f"Sub-categories created: {len(subcategories)}")
+    print(f"Total labels: {total_labels}")
+    
+    for i, subcat in enumerate(subcategories, 1):
+        print(f"  {i}. {subcat['name']}: {len(subcat['labels'])} labels")
+
+
+def main():
+    """Main execution function."""
+    print("=== LLM-based Sub-clustering within Categories ===")
+
+    paths = load_paths()
+    settings = load_settings()
+    clustered_file = paths["sample_characteristics_clustered"]
+    output_file = paths["sample_characteristics_subclustered_generated"]
+    model_path = os.environ.get("RDAS_LLM_MODEL_PATH") or settings.get("llm_model_path")
+    
+    # Check input file
+    if not os.path.exists(clustered_file):
+        print(f"✗ Input file not found: {clustered_file}")
+        return
+    
+    try:
+        # Reset output file at start to avoid resume/skip behavior
+        if os.path.exists(output_file):
+            os.remove(output_file)
+            print(f"Reset output file: {output_file}")
+        
+        # Load data
+        print(f"\nLoading input data...")
+        categories_data = load_clustered_data(clustered_file)
+        
+        # Initialize LLM
+        if not VLLM_AVAILABLE:
+            print("✗ vLLM not available")
+            return
+
+        if not model_path:
+            print("✗ No LLM model path configured. Set RDAS_LLM_MODEL_PATH or settings.llm_model_path.")
+            return
+
+        llm, sampling_params = initialize_llm(model_path)
+        if llm is None:
+            print("✗ Failed to initialize LLM")
+            return
+        
+        print(f"\n=== PROCESSING CATEGORIES ===")
+        
+        processed_count = 0
+        skipped_count = 0
+        target_categories = list(categories_data.keys())
+        total_categories = len(target_categories)
+        
+        for idx, category_name in enumerate(target_categories, start=1):
+            labels = categories_data.get(category_name, [])
+            
+            print(f"\n[{idx}/{total_categories}] Processing '{category_name}':")
+            print(f"  Labels: {len(labels):,}")
+            
+            # Process even if small or empty
+            if not labels:
+                print("  No labels found for this category; writing empty result entry is skipped")
+                skipped_count += 1
+                continue
+            
+            # Process category
+            subcategories = process_category_in_batches(
+                category_name, labels, llm, sampling_params, batch_size=100
+            )
+            
+            if not subcategories:
+                # Fallback: single cluster
+                subcategories = [{'name': 'Cluster 1', 'labels': labels}]
+            
+            # Save results immediately
+            ensure_parent_dir(output_file)
+            save_category_results(
+                category_name, subcategories, output_file, 
+                append=(processed_count > 0)
+            )
+            
+            # Print category summary
+            print_category_summary(category_name, subcategories)
+            
+            processed_count += 1
+            print(f"✓ Completed {processed_count} categories, {skipped_count} skipped")
+            
+            # Small delay between categories
+            time.sleep(1)
+        
+        # Final summary
+        print(f"\n=== FINAL SUMMARY ===")
+        print(f"Categories processed: {processed_count}")
+        print(f"Categories skipped (no labels): {skipped_count}")
+        print(f"Total target categories: {total_categories}")
+        
+        if processed_count > 0:
+            print(f"\n✓ Sub-clustering completed successfully!")
+            print(f"Results saved to:")
+            print(f"  - {output_file}")
+        else:
+            print(f"\n⚠ No categories were processed")
+        
+    except Exception as e:
+        print(f"✗ Error during sub-clustering: {e}")
+        import traceback
+        traceback.print_exc()
+
+
+if __name__ == "__main__":
+    main() 
diff --git a/RDAS_RDOMICS/scripts/sample_characteristics_harmonization/6_prepare_sample_properties.py b/RDAS_RDOMICS/scripts/sample_characteristics_harmonization/6_prepare_sample_properties.py
new file mode 100644
index 0000000..9b2faaf
--- /dev/null
+++ b/RDAS_RDOMICS/scripts/sample_characteristics_harmonization/6_prepare_sample_properties.py
@@ -0,0 +1,214 @@
+#!/usr/bin/env python3
+"""
+Prepare Sample Properties by Subcategory
+
+This script reads:
+- the configured final subclustering file (subcategory -> labels mapping)
+- sample_node.csv from the pipeline outputs (contains Sample_id and Sample_characteristics)
+
+It outputs:
+- sample_properties_by_subcategory.csv with columns:
+  [Sample_id] + [one column per subcategory name], where each cell contains the
+  value(s) from Sample_characteristics whose key belongs to that subcategory.
+
+Notes:
+- Keys in Sample_characteristics are matched case-insensitively against the
+  'labels' lists from the subclustering file
+- If multiple keys map to the same subcategory for a sample, their values are
+  joined by " | "
+- If duplicate subcategory names exist across main categories, they are
+  disambiguated by appending " (main_category)" to the column name
+- Spaces in subcategory column names are replaced with underscores for DB compatibility
+"""
+
+import pandas as pd
+import ast
+import os
+import re
+from typing import Dict, List, Tuple
+from pathlib import Path
+import sys
+
+CURRENT_DIR = Path(__file__).resolve().parent
+SCRIPTS_DIR = CURRENT_DIR.parent
+if str(SCRIPTS_DIR) not in sys.path:
+    sys.path.insert(0, str(SCRIPTS_DIR))
+
+from utils import ensure_parent_dir, load_paths
+
+
+def normalize_label(s: str) -> str:
+    if s is None:
+        return ""
+    s = str(s).strip().lower()
+    # Replace underscores/hyphens with space
+    s = s.replace("_", " ").replace("-", " ")
+    # Collapse multiple spaces
+    s = re.sub(r"\s+", " ", s)
+    return s
+
+
+def sanitize_key(name: str) -> str:
+    """Replace spaces with underscores in property keys."""
+    return str(name).replace(" ", "_")
+
+
+def load_label_to_subcategory_map(subcluster_path: str) -> Tuple[Dict[str, str], Dict[str, str], List[str]]:
+    """Load mapping from label -> subcategory; also main_category per subcategory; return full subcategory list.
+    Returns:
+      label_to_subcat: normalized_label -> subcategory
+      subcat_to_main: subcategory -> main_category (first occurrence)
+      subcat_list: ordered list of (possibly disambiguated and sanitized) subcategory column names
+    """
+    if not os.path.exists(subcluster_path):
+        raise FileNotFoundError(f"Subcluster file not found: {subcluster_path}")
+
+    df = pd.read_csv(subcluster_path)
+
+    label_to_subcat: Dict[str, str] = {}
+    subcat_to_main: Dict[str, str] = {}
+
+    # Collect subcategories per main category; detect duplicates for disambiguation
+    subcat_counts: Dict[str, int] = {}
+    rows: List[Tuple[str, str, List[str]]] = []
+
+    for _, row in df.iterrows():
+        main_cat = str(row['main_category'])
+        subcat = str(row['subcategory'])
+        try:
+            labels = ast.literal_eval(row['labels']) if isinstance(row['labels'], str) else []
+        except Exception:
+            labels = []
+        rows.append((main_cat, subcat, labels))
+        subcat_counts[subcat] = subcat_counts.get(subcat, 0) + 1
+
+    # Build mapping; record main category for subcategory
+    for main_cat, subcat, labels in rows:
+        if subcat not in subcat_to_main:
+            subcat_to_main[subcat] = main_cat
+        for lab in labels:
+            nlab = normalize_label(lab)
+            if nlab and nlab not in label_to_subcat:
+                label_to_subcat[nlab] = subcat
+
+    # Build final subcategory column list; disambiguate duplicates by appending main category
+    subcat_list: List[str] = []
+    used_cols: Dict[str, int] = {}
+    for main_cat, subcat, _ in rows:
+        col_name = subcat
+        if subcat_counts.get(subcat, 0) > 1:
+            # Disambiguate
+            col_name = f"{subcat} ({main_cat})"
+        col_name = sanitize_key(col_name)
+        if col_name not in used_cols:
+            used_cols[col_name] = 1
+            subcat_list.append(col_name)
+
+    return label_to_subcat, subcat_to_main, subcat_list
+
+
+def parse_sample_characteristics(cell: str) -> List[Tuple[str, str]]:
+    """Parse a Sample_characteristics string into list of (key, value)."""
+    if not isinstance(cell, str) or not cell.strip():
+        return []
+    parts = [p.strip() for p in cell.split(';') if p.strip()]
+    kvs: List[Tuple[str, str]] = []
+    for p in parts:
+        if ':' in p:
+            k, v = p.split(':', 1)
+            k = k.strip()
+            v = v.strip()
+            if k:
+                kvs.append((k, v))
+    return kvs
+
+
+def main():
+    print("=== Preparing Sample Properties by Subcategory ===")
+    paths = load_paths()
+    subcluster_file = paths["sample_characteristics_subclustered_final"]
+    sample_node_file = f"{paths['node_csv_files']}/sample_node.csv"
+    output_file = paths["sample_properties_by_subcategory"]
+
+    # Load mappings
+    label_to_subcat, subcat_to_main, subcat_list = load_label_to_subcategory_map(subcluster_file)
+    print(f"✓ Loaded {len(label_to_subcat)} labels mapped to {len(subcat_list)} subcategories")
+
+    # Load sample_node.csv
+    if not os.path.exists(sample_node_file):
+        raise FileNotFoundError(f"Sample node file not found: {sample_node_file}")
+
+    sdf = pd.read_csv(sample_node_file)
+    if 'Sample_id' not in sdf.columns:
+        raise ValueError("'Sample_id' column not found in sample_node.csv")
+    if 'Sample_characteristics' not in sdf.columns:
+        raise ValueError("'Sample_characteristics' column not found in sample_node.csv")
+
+    # Prepare output rows
+    output_rows: List[Dict[str, str]] = []
+
+    # Build a mapping from original subcategory to sanitized column name (accounting for disambiguation)
+    subcat_to_col: Dict[str, str] = {}
+    subcluster_df = pd.read_csv(subcluster_file)
+    # Precompute duplicates
+    subcat_series = subcluster_df['subcategory'].astype(str)
+    dup_mask = subcat_series.duplicated(keep=False)
+    dup_names = set(subcat_series[dup_mask])
+
+    for _, row in subcluster_df.iterrows():
+        main_cat = str(row['main_category'])
+        subcat = str(row['subcategory'])
+        col_name = subcat
+        if subcat in dup_names:
+            col_name = f"{subcat} ({main_cat})"
+        col_name = sanitize_key(col_name)
+        if subcat not in subcat_to_col:
+            subcat_to_col[subcat] = col_name
+
+    for _, row in sdf.iterrows():
+        sample_id = row['Sample_id']
+        scell = row['Sample_characteristics']
+        kvs = parse_sample_characteristics(scell)
+
+        # Initialize all subcategory cells empty
+        out_row: Dict[str, str] = {col: '' for col in subcat_list}
+        out_row['Sample_id'] = sample_id
+
+        # Aggregate values per subcategory
+        agg: Dict[str, List[str]] = {}
+        for k, v in kvs:
+            nk = normalize_label(k)
+            subcat = label_to_subcat.get(nk)
+            if not subcat:
+                continue
+            col_name = subcat_to_col.get(subcat, sanitize_key(subcat))
+            agg.setdefault(col_name, []).append(v)
+
+        # Assign aggregated values
+        for col_name, vals in agg.items():
+            # Deduplicate while preserving order
+            seen = set()
+            deduped = []
+            for val in vals:
+                if val not in seen:
+                    seen.add(val)
+                    deduped.append(val)
+            out_row[col_name] = ' | '.join(deduped)
+
+        output_rows.append(out_row)
+
+    # Create output DataFrame with columns order: Sample_id + subcat_list
+    out_df = pd.DataFrame(output_rows)
+    # Ensure all columns exist
+    for col in ['Sample_id'] + subcat_list:
+        if col not in out_df.columns:
+            out_df[col] = ''
+    out_df = out_df[['Sample_id'] + subcat_list]
+
+    ensure_parent_dir(output_file)
+    out_df.to_csv(output_file, index=False)
+    print(f"✓ Wrote {len(out_df)} rows to {output_file}")
+
+
+if __name__ == "__main__":
+    main()
diff --git a/RDAS_RDOMICS/scripts/sample_characteristics_harmonization/7_import_to_sample_node.py b/RDAS_RDOMICS/scripts/sample_characteristics_harmonization/7_import_to_sample_node.py
new file mode 100644
index 0000000..e915a38
--- /dev/null
+++ b/RDAS_RDOMICS/scripts/sample_characteristics_harmonization/7_import_to_sample_node.py
@@ -0,0 +1,232 @@
+#!/usr/bin/env python3
+"""
+Import Sample subcategory properties into Memgraph Sample nodes.
+
+For each row, updates the corresponding (Sample {Sample_id}) node by setting
+only the non-empty properties present in that row. Empty cells are ignored.
+"""
+
+import os
+import sys
+import json
+import time
+import pandas as pd
+from neo4j import GraphDatabase
+from typing import Dict, Any, List, Optional
+import re
+import argparse
+from pathlib import Path
+
+CURRENT_DIR = Path(__file__).resolve().parent
+SCRIPTS_DIR = CURRENT_DIR.parent
+if str(SCRIPTS_DIR) not in sys.path:
+    sys.path.insert(0, str(SCRIPTS_DIR))
+
+# Toggle: when False, use property names as-is (user guarantees safety)
+# Set STRICT_CYPHER_ESCAPING=True to enable backtick-quoting for property keys.
+STRICT_CYPHER_ESCAPING = False
+
+from utils import ensure_parent_dir, load_paths
+
+
+def _sanitize_param_name(key: str) -> str:
+    """Create a Cypher-safe parameter name for a given property key."""
+    safe = re.sub(r"[^A-Za-z0-9_]", "_", str(key))
+    if not safe or not (safe[0].isalpha() or safe[0] == "_"):
+        safe = f"p_{safe}"
+    return f"prop_{safe}"
+
+
+def _quote_property(key: str) -> str:
+    """Quote a property key with backticks for Cypher/openCypher."""
+    return f"`{str(key).replace('`', '``')}`"
+
+
+def _param_name_for_key(key: str) -> str:
+    # Always sanitize parameter names; Cypher param identifiers cannot contain hyphens/parentheses, etc.
+    return _sanitize_param_name(key)
+
+
+def _property_for_key(key: str) -> str:
+    if STRICT_CYPHER_ESCAPING:
+        return _quote_property(key)
+    # Auto-quote only when key is not a valid unquoted identifier
+    # Valid: starts with letter or underscore, followed by letters/digits/underscore
+    if re.match(r"^[A-Za-z_][A-Za-z0-9_]*$", str(key)):
+        return str(key)
+    return _quote_property(key)
+
+
+def build_set_clause(props: Dict[str, Any]) -> (str, Dict[str, Any]):
+    """Build a Cypher SET clause and parameter dict for given property dict.
+    Returns (set_clause_string, params_dict)
+    Example: ({'A': 'x', 'B': 'y'}) -> ("SET s.A = $A, s.B = $B", {'A': 'x', 'B': 'y'})
+    """
+    assignments: List[str] = []
+    params: Dict[str, Any] = {}
+    for key, value in props.items():
+        param_key = _param_name_for_key(key)
+        assignments.append(f"s.{_property_for_key(key)} = ${param_key}")
+        params[param_key] = value
+    set_clause = "SET " + ", ".join(assignments)
+    return set_clause, params
+
+
+def _load_resume(resume_file: Optional[str]) -> Optional[Dict[str, Any]]:
+    if not resume_file:
+        return None
+    try:
+        if os.path.exists(resume_file):
+            with open(resume_file, "r") as f:
+                return json.load(f)
+    except Exception:
+        return None
+    return None
+
+
+def _save_resume(resume_file: Optional[str], state: Dict[str, Any]) -> None:
+    if not resume_file:
+        return
+    tmp_path = f"{resume_file}.tmp"
+    with open(tmp_path, "w") as f:
+        json.dump(state, f)
+        f.flush()
+        os.fsync(f.fileno())
+    os.replace(tmp_path, resume_file)
+
+
+def import_sample_properties(config_path: str | None = None,
+                             resume_file: Optional[str] = None,
+                             start_index: int = 0,
+                             batch_size: int = 500,
+                             reset_resume: bool = False) -> None:
+    neo4j_uri = os.environ.get("NEO4J_URI")
+    neo4j_user = os.environ.get("NEO4J_USER")
+    neo4j_password = os.environ.get("NEO4J_PASSWORD")
+    if not all([neo4j_uri, neo4j_user, neo4j_password]):
+        raise ValueError("Set NEO4J_URI, NEO4J_USER, and NEO4J_PASSWORD before running this step.")
+
+    paths = load_paths(config_path)
+    input_csv = paths["sample_properties_by_subcategory"]
+    resume_file = resume_file or paths["sample_import_resume_file"]
+
+    if not os.path.exists(input_csv):
+        raise FileNotFoundError(f"Input CSV not found: {input_csv}")
+
+    print("Reading sample properties from CSV...", flush=True)
+    df = pd.read_csv(input_csv, low_memory=False)
+
+    if 'Sample_id' not in df.columns:
+        raise ValueError("Input CSV must contain 'Sample_id' column")
+
+    # Columns to consider as properties (exclude Sample_id)
+    prop_columns = [c for c in df.columns if c != 'Sample_id']
+    print(f"Found {len(prop_columns)} property columns to import", flush=True)
+
+    total_rows = len(df)
+
+    # Initialize or load resume state
+    resume_state = None if reset_resume else _load_resume(resume_file)
+    if resume_state and resume_state.get("input_csv") == input_csv and resume_state.get("total_rows") == total_rows:
+        start_index = max(start_index, int(resume_state.get("next_index", 0)))
+        print(f"Resuming from row index {start_index} based on resume file: {resume_file}", flush=True)
+    else:
+        if resume_file and not reset_resume:
+            if resume_state is not None:
+                print("Resume file present but does not match current job. Starting from beginning.", flush=True)
+        # Save initial resume state
+        ensure_parent_dir(resume_file)
+        _save_resume(resume_file, {"input_csv": input_csv, "total_rows": total_rows, "next_index": start_index, "updated_nodes": 0, "updated_props_total": 0, "skipped_rows": 0, "last_update_ts": time.time()})
+
+    print("Connecting to Memgraph database...", flush=True)
+    driver = GraphDatabase.driver(neo4j_uri, auth=(neo4j_user, neo4j_password))
+
+    updated_nodes = int((resume_state or {}).get("updated_nodes", 0))
+    updated_props_total = int((resume_state or {}).get("updated_props_total", 0))
+    skipped_rows = int((resume_state or {}).get("skipped_rows", 0))
+
+    with driver.session() as session:
+        for start in range(start_index, total_rows, batch_size):
+            end = min(start + batch_size, total_rows)
+            batch = df.iloc[start:end]
+            batch_updates = 0
+            batch_props = 0
+
+            for _, row in batch.iterrows():
+                sample_id = row['Sample_id']
+                # Collect non-empty properties
+                props: Dict[str, Any] = {}
+                for col in prop_columns:
+                    val = row[col]
+                    # Treat NaN or empty string as missing
+                    if pd.isna(val):
+                        continue
+                    sval = str(val).strip()
+                    if not sval:
+                        continue
+                    props[col] = sval
+
+                if not props:
+                    skipped_rows += 1
+                    continue
+
+                set_clause, params = build_set_clause(props)
+                params['sample_id'] = sample_id
+
+                query = f"""
+                MATCH (s:Sample {{Sample_id: $sample_id}})
+                {set_clause}
+                RETURN count(s) as updated
+                """
+                result = session.run(query, **params)
+                updated = result.single()["updated"]
+                if updated:
+                    batch_updates += 1
+                    batch_props += len(props)
+
+            updated_nodes += batch_updates
+            updated_props_total += batch_props
+            # Progress output per batch
+            print(f"Processed rows {start+1}-{end}: updated {batch_updates} nodes, set {batch_props} properties", flush=True)
+
+            # Save resume checkpoint at end of each batch
+            _save_resume(resume_file, {
+                "input_csv": input_csv,
+                "total_rows": total_rows,
+                "next_index": end,
+                "updated_nodes": updated_nodes,
+                "updated_props_total": updated_props_total,
+                "skipped_rows": skipped_rows,
+                "last_update_ts": time.time(),
+            })
+
+    driver.close()
+    print(f"Import complete. Updated {updated_nodes} Sample nodes. Total properties set: {updated_props_total}. Skipped rows (no properties): {skipped_rows}.", flush=True)
+
+    # Mark completion and remove resume file
+    if resume_file and os.path.exists(resume_file):
+        try:
+            os.remove(resume_file)
+        except Exception:
+            pass
+
+
+def _parse_args() -> argparse.Namespace:
+    parser = argparse.ArgumentParser(description="Import sample subcategory properties into Memgraph with resume support.")
+    parser.add_argument("--config", help="Optional path to a YAML config file.")
+    parser.add_argument("--resume_file", type=str, help="Path to resume checkpoint file.")
+    parser.add_argument("--start_index", type=int, default=0, help="Row index to start processing from (overrides resume if higher).")
+    parser.add_argument("--batch_size", type=int, default=500, help="Number of rows per batch.")
+    parser.add_argument("--reset_resume", action="store_true", help="Ignore existing resume file and start fresh.")
+    return parser.parse_args()
+
+
+if __name__ == "__main__":
+    args = _parse_args()
+    import_sample_properties(
+        config_path=args.config,
+        resume_file=args.resume_file,
+        start_index=args.start_index,
+        batch_size=args.batch_size,
+        reset_resume=args.reset_resume,
+    )
diff --git a/RDAS_RDOMICS/scripts/sample_characteristics_harmonization/run_import_sample_properties.sh b/RDAS_RDOMICS/scripts/sample_characteristics_harmonization/run_import_sample_properties.sh
new file mode 100644
index 0000000..74016e1
--- /dev/null
+++ b/RDAS_RDOMICS/scripts/sample_characteristics_harmonization/run_import_sample_properties.sh
@@ -0,0 +1,57 @@
+#!/bin/bash
+
+#SBATCH --job-name=import_sample_props
+#SBATCH --output=scripts/sample_characteristics_harmonization/logs/import_sample_props_%j.out
+#SBATCH --error=scripts/sample_characteristics_harmonization/logs/import_sample_props_%j.out
+#SBATCH --nodes=1
+#SBATCH --ntasks=1
+#SBATCH --cpus-per-task=2
+#SBATCH --mem=8G
+#SBATCH --time=2-00:00:00
+
+# Adjust the SBATCH resource lines above for your cluster if needed.
+echo "=== Importing Sample Properties into Memgraph ==="
+echo "Date: $(date)"
+echo "SLURM Job ID: $SLURM_JOB_ID"
+echo "Running on node: $(hostname)"
+
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+REPO_ROOT="$(cd "${SCRIPT_DIR}/../.." && pwd)"
+OUTPUT_DIR="${RDAS_HARM_OUTPUT_DIR:-${SCRIPT_DIR}/sample_characteristics_harmonization_output}"
+LOG_DIR="${SCRIPT_DIR}/logs"
+INPUT_CSV="${RDAS_SAMPLE_PROPERTIES_FILE:-${OUTPUT_DIR}/sample_properties_by_subcategory.csv}"
+RESUME_FILE="${RDAS_RESUME_FILE:-${OUTPUT_DIR}/sample_import_resume.json}"
+CONDA_ENV_NAME="${RDAS_IMPORT_CONDA_ENV:-socialnetwork310}"
+
+mkdir -p "${LOG_DIR}" "${OUTPUT_DIR}"
+
+echo "Logs will stream to: ${LOG_DIR}/import_sample_props_${SLURM_JOB_ID}.out"
+echo "You can follow progress with: tail -f ${LOG_DIR}/import_sample_props_${SLURM_JOB_ID}.out &"
+
+# Activate environment
+source ~/anaconda3/etc/profile.d/conda.sh
+conda activate "${CONDA_ENV_NAME}"
+
+cd "${REPO_ROOT}"
+
+# Check input
+if [ ! -f "${INPUT_CSV}" ]; then
+  echo "Error: input CSV not found: ${INPUT_CSV}"
+  exit 1
+fi
+
+echo "Starting import script..."
+echo "Conda env: ${CONDA_ENV_NAME}"
+echo "Expected env vars: NEO4J_URI, NEO4J_USER, NEO4J_PASSWORD"
+PYTHONUNBUFFERED=1 python -u "${SCRIPT_DIR}/7_import_to_sample_node.py" --resume_file "$RESUME_FILE"
+
+if [ $? -eq 0 ]; then
+  echo "\n✓ Import completed successfully!"
+else
+  echo "✗ Import failed with exit code $?"
+  echo "If interrupted, you can resume automatically using the resume file: $RESUME_FILE"
+  exit 1
+fi
+
+echo "\n=== Import Complete ==="
+echo "Date: $(date)" 
diff --git a/RDAS_RDOMICS/scripts/sample_characteristics_harmonization/run_llm_clustering.sh b/RDAS_RDOMICS/scripts/sample_characteristics_harmonization/run_llm_clustering.sh
new file mode 100644
index 0000000..c768441
--- /dev/null
+++ b/RDAS_RDOMICS/scripts/sample_characteristics_harmonization/run_llm_clustering.sh
@@ -0,0 +1,151 @@
+#!/bin/bash
+#SBATCH --job-name=llm_clustering
+#SBATCH --partition=extended_gpu
+#SBATCH --nodes=1
+#SBATCH --ntasks=32
+#SBATCH --gres=gpu:4
+#SBATCH --mem-per-cpu=8G
+#SBATCH --time=5-00:00:00
+#SBATCH -o scripts/sample_characteristics_harmonization/logs/llm_clustering_%j.out
+#SBATCH -e scripts/sample_characteristics_harmonization/logs/llm_clustering_%j.out
+
+# Adjust the SBATCH resource lines above for your cluster if needed.
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+REPO_ROOT="$(cd "${SCRIPT_DIR}/../.." && pwd)"
+OUTPUT_DIR="${RDAS_HARM_OUTPUT_DIR:-${SCRIPT_DIR}/sample_characteristics_harmonization_output}"
+LOG_DIR="${SCRIPT_DIR}/logs"
+CONDA_ENV_NAME="${RDAS_LLM_CONDA_ENV:-step4-expertise}"
+
+mkdir -p "${LOG_DIR}" "${OUTPUT_DIR}"
+cd "${REPO_ROOT}"
+
+# Activate environment
+source ~/anaconda3/etc/profile.d/conda.sh
+conda activate "${CONDA_ENV_NAME}"
+
+# Set CUDA environment variables for vLLM
+export CUDA_VISIBLE_DEVICES=0,1,2,3
+export VLLM_USE_MODELSCOPE=False
+
+# Print job information
+echo "=== LLM-based Sample Characteristics Clustering ==="
+echo "Job ID: $SLURM_JOB_ID"
+echo "Node: $SLURM_NODELIST"
+echo "Start time: $(date)"
+echo "Working directory: ${REPO_ROOT}"
+
+# Check Python and vLLM installation
+echo "Python version: $(python --version)"
+echo "vLLM check:"
+python -c "import vllm; print(f'vLLM version: {vllm.__version__}')" 2>/dev/null || echo "vLLM not available"
+echo "Conda env: ${CONDA_ENV_NAME}"
+
+# Check input files
+echo ""
+echo "Checking input files:"
+LABELS_FILE="${RDAS_LABELS_FILE:-${OUTPUT_DIR}/3_sample_characteristics_key_count_english_only.csv}"
+VOCAB_FILE="${RDAS_VOCAB_FILE:-${OUTPUT_DIR}/4_sample_characteristics_vocabulary_fixed.csv}"
+CLUSTERED_FILE="${RDAS_CLUSTERED_FILE:-${OUTPUT_DIR}/4_llm_clustered_sample_characteristics.csv}"
+CONFIDENCE_FILE="${RDAS_CONFIDENCE_FILE:-${OUTPUT_DIR}/clustering_confidence_report.csv}"
+
+if [ -f "${LABELS_FILE}" ]; then
+    echo "✓ Labels file found: ${LABELS_FILE}"
+    echo "  Total labels: $(($(wc -l < "${LABELS_FILE}") - 1))"
+    echo "  File size: $(du -h "${LABELS_FILE}" | cut -f1)"
+else
+    echo "✗ Labels file missing: ${LABELS_FILE}"
+    exit 1
+fi
+
+if [ -f "${VOCAB_FILE}" ]; then
+    echo "✓ Vocabulary file found: ${VOCAB_FILE}"
+    echo "  Categories: $(($(wc -l < "${VOCAB_FILE}") - 1))"
+else
+    echo "✗ Vocabulary file missing: ${VOCAB_FILE}"
+    exit 1
+fi
+
+# Show top labels by count
+echo ""
+echo "Top 10 labels by occurrence count:"
+tail -n +2 "${LABELS_FILE}" | sort -t',' -k2 -nr | head -10 | nl
+
+# Show available categories
+echo ""
+echo "Available categories for clustering:"
+tail -n +2 "${VOCAB_FILE}" | cut -d',' -f1 | nl
+
+echo ""
+echo "Starting clustering process..."
+echo "Model path: ${RDAS_LLM_MODEL_PATH:-configured in scripts/config/paths.yaml}"
+echo "Features: Multi-stage processing (Keyword → Similarity → LLM)"
+echo "Expected outputs: ${CLUSTERED_FILE}, ${CONFIDENCE_FILE}"
+echo "============================================"
+
+# Run the clustering script
+python "${SCRIPT_DIR}/4_llm_clustering_enhanced.py"
+
+# Check exit status
+if [ $? -eq 0 ]; then
+    echo "============================================"
+    echo "✓ Clustering completed successfully!"
+    echo "End time: $(date)"
+    
+    # Display output file info
+    if [ -f "${CLUSTERED_FILE}" ]; then
+        echo ""
+        echo "✓ Main output file created: ${CLUSTERED_FILE}"
+        echo "  Lines: $(wc -l < "${CLUSTERED_FILE}")"
+        echo ""
+        echo "Clustering results by category:"
+        echo "Category | Label Count | Total Occurrences"
+        echo "---------|-------------|------------------"
+        tail -n +2 "${CLUSTERED_FILE}" | while IFS=',' read -r category label_count total_count labels; do
+            printf "%-20s | %8s | %15s\n" "$category" "$label_count" "$total_count"
+        done
+    else
+        echo "⚠ Warning: Main output file not found"
+    fi
+    
+    if [ -f "${CONFIDENCE_FILE}" ]; then
+        echo ""
+        echo "✓ Confidence report created: ${CONFIDENCE_FILE}"
+        echo "  Total entries: $(($(wc -l < "${CONFIDENCE_FILE}") - 1))"
+        echo ""
+        echo "Confidence distribution:"
+        tail -n +2 "${CONFIDENCE_FILE}" | cut -d',' -f5 | sort | uniq -c | sort -nr | while read count conf; do
+            echo "  $conf: $count labels"
+        done
+        echo ""
+        echo "Method distribution:"
+        tail -n +2 "${CONFIDENCE_FILE}" | cut -d',' -f4 | sort | uniq -c | sort -nr | while read count method; do
+            echo "  $method: $count labels"
+        done
+        
+        # Show top clustered labels by occurrence
+        echo ""
+        echo "Top 10 clustered labels by occurrence count:"
+        tail -n +2 "${CONFIDENCE_FILE}" | sort -t',' -k3 -nr | head -10 | cut -d',' -f2,3,4,5 | nl
+    else
+        echo "⚠ Warning: Confidence report not found"
+    fi
+    
+    echo ""
+    echo "=== CLUSTERING SUMMARY ==="
+    echo "• Multi-stage processing reduces LLM workload"
+    echo "• Confidence scoring for quality assessment"
+    echo "• Preserves original occurrence counts"
+    echo "• Comprehensive reporting for analysis"
+    echo ""
+    echo "Files created:"
+    echo "  - ${CLUSTERED_FILE} (main results)"
+    echo "  - ${CONFIDENCE_FILE} (detailed analysis)"
+    
+else
+    echo "✗ Clustering failed with exit code $?"
+    echo "End time: $(date)"
+    echo ""
+    echo "Check the log file for detailed error information:"
+    echo "  ${LOG_DIR}/llm_clustering_${SLURM_JOB_ID}.out"
+    exit 1
+fi 
diff --git a/RDAS_RDOMICS/scripts/sample_characteristics_harmonization/run_prepare_sample_properties.sh b/RDAS_RDOMICS/scripts/sample_characteristics_harmonization/run_prepare_sample_properties.sh
new file mode 100644
index 0000000..80281d5
--- /dev/null
+++ b/RDAS_RDOMICS/scripts/sample_characteristics_harmonization/run_prepare_sample_properties.sh
@@ -0,0 +1,67 @@
+#!/bin/bash
+
+#SBATCH --job-name=prepare_properties
+#SBATCH --output=scripts/sample_characteristics_harmonization/logs/prepare_properties_%j.out
+#SBATCH --error=scripts/sample_characteristics_harmonization/logs/prepare_properties_%j.out
+#SBATCH --nodes=1
+#SBATCH --ntasks=1
+#SBATCH --cpus-per-task=4
+#SBATCH --mem=16G
+#SBATCH --time=02:00:00
+
+# Adjust the SBATCH resource lines above for your cluster if needed.
+echo "=== Preparing Sample Properties by Subcategory ==="
+echo "Date: $(date)"
+echo "SLURM Job ID: $SLURM_JOB_ID"
+echo "Running on node: $(hostname)"
+
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+REPO_ROOT="$(cd "${SCRIPT_DIR}/../.." && pwd)"
+OUTPUT_DIR="${RDAS_HARM_OUTPUT_DIR:-${SCRIPT_DIR}/sample_characteristics_harmonization_output}"
+LOG_DIR="${SCRIPT_DIR}/logs"
+SUBCLUSTER_FILE="${RDAS_SUBCLUSTER_FILE:-${OUTPUT_DIR}/5_subclustered_sample_characteristics_v2_expert_consolidated.csv}"
+SAMPLE_NODE_FILE="${RDAS_SAMPLE_NODE_FILE:-${REPO_ROOT}/scripts/data/node_csv_files/sample_node.csv}"
+SAMPLE_PROPERTIES_FILE="${RDAS_SAMPLE_PROPERTIES_FILE:-${OUTPUT_DIR}/sample_properties_by_subcategory.csv}"
+CONDA_ENV_NAME="${RDAS_PREP_CONDA_ENV:-step4-expertise}"
+
+mkdir -p "${LOG_DIR}" "${OUTPUT_DIR}"
+
+# Activate environment
+source ~/anaconda3/etc/profile.d/conda.sh
+conda activate "${CONDA_ENV_NAME}"
+
+cd "${REPO_ROOT}"
+
+# Check inputs
+echo "Checking input files..."
+if [ ! -f "${SUBCLUSTER_FILE}" ]; then
+  echo "Error: subcluster file not found: ${SUBCLUSTER_FILE}"
+  exit 1
+fi
+if [ ! -f "${SAMPLE_NODE_FILE}" ]; then
+  echo "Error: sample_node.csv not found: ${SAMPLE_NODE_FILE}"
+  exit 1
+fi
+
+echo "Conda env: ${CONDA_ENV_NAME}"
+echo "Inputs found. Running preparation script..."
+python "${SCRIPT_DIR}/6_prepare_sample_properties.py"
+
+if [ $? -eq 0 ]; then
+  echo "\n✓ Sample properties preparation completed successfully!"
+  if [ -f "${SAMPLE_PROPERTIES_FILE}" ]; then
+    echo "Output file: ${SAMPLE_PROPERTIES_FILE}"
+    echo "Rows: $(tail -n +2 "${SAMPLE_PROPERTIES_FILE}" | wc -l)"
+    echo "Columns: $(head -n 1 "${SAMPLE_PROPERTIES_FILE}" | awk -F"," '{print NF}')"
+    echo "\nPreview of columns:"
+    head -n 1 "${SAMPLE_PROPERTIES_FILE}" | tr ',' '\n' | nl | sed -n '1,30p'
+  else
+    echo "Warning: Output file not found after run."
+  fi
+else
+  echo "✗ Preparation failed with exit code $?"
+  exit 1
+fi
+
+echo "\n=== Preparation Complete ==="
+echo "Date: $(date)"
diff --git a/RDAS_RDOMICS/scripts/sample_characteristics_harmonization/run_subclustering.sh b/RDAS_RDOMICS/scripts/sample_characteristics_harmonization/run_subclustering.sh
new file mode 100644
index 0000000..abb6bfe
--- /dev/null
+++ b/RDAS_RDOMICS/scripts/sample_characteristics_harmonization/run_subclustering.sh
@@ -0,0 +1,79 @@
+#!/bin/bash
+
+#SBATCH --job-name=subclustering
+#SBATCH --output=scripts/sample_characteristics_harmonization/logs/subclustering_%j.out
+#SBATCH --error=scripts/sample_characteristics_harmonization/logs/subclustering_%j.out
+#SBATCH --partition=extended_gpu
+#SBATCH --gres=gpu:4
+#SBATCH --nodes=1
+#SBATCH --ntasks-per-node=1
+#SBATCH --cpus-per-task=16
+#SBATCH --mem=200G
+#SBATCH --time=2-00:00:00
+
+# Adjust the SBATCH resource lines above for your cluster if needed.
+echo "=== Starting LLM Sub-clustering Process ==="
+echo "Date: $(date)"
+echo "SLURM Job ID: $SLURM_JOB_ID"
+echo "Running on node: $(hostname)"
+
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+REPO_ROOT="$(cd "${SCRIPT_DIR}/../.." && pwd)"
+OUTPUT_DIR="${RDAS_HARM_OUTPUT_DIR:-${SCRIPT_DIR}/sample_characteristics_harmonization_output}"
+LOG_DIR="${SCRIPT_DIR}/logs"
+CLUSTERED_FILE="${RDAS_CLUSTERED_FILE:-${OUTPUT_DIR}/4_llm_clustered_sample_characteristics.csv}"
+SUBCLUSTERED_FILE="${RDAS_SUBCLUSTERED_FILE:-${OUTPUT_DIR}/5_subclustered_sample_characteristics_v1.csv}"
+CONDA_ENV_NAME="${RDAS_LLM_CONDA_ENV:-step4-expertise}"
+
+mkdir -p "${LOG_DIR}" "${OUTPUT_DIR}"
+
+source ~/anaconda3/etc/profile.d/conda.sh
+conda activate "${CONDA_ENV_NAME}"
+# Check GPU availability
+echo "GPU Information:"
+nvidia-smi
+
+# Set environment variables
+export CUDA_VISIBLE_DEVICES=0,1,2,3
+export VLLM_WORKER_MULTIPROC_METHOD=spawn
+
+cd "${REPO_ROOT}"
+
+# Check input files exist
+echo "Checking input files..."
+if [ ! -f "${CLUSTERED_FILE}" ]; then
+    echo "Error: clustered file not found: ${CLUSTERED_FILE}"
+    exit 1
+fi
+
+echo "Conda env: ${CONDA_ENV_NAME}"
+echo "Input files found. Starting sub-clustering..."
+
+# Run the sub-clustering script
+python "${SCRIPT_DIR}/5_llm_subclustering.py"
+
+# Check if successful
+if [ $? -eq 0 ]; then
+    echo "✓ Sub-clustering completed successfully!"
+    
+    # Show output files
+    echo ""
+    echo "Output file created:"
+    ls -la "${SUBCLUSTERED_FILE}" 2>/dev/null || echo "Output file not found"
+    
+    # Show summary statistics
+    if [ -f "${SUBCLUSTERED_FILE}" ]; then
+        echo ""
+        echo "Summary statistics:"
+        echo "Total sub-categories: $(tail -n +2 "${SUBCLUSTERED_FILE}" | wc -l)"
+        echo "Main categories processed: $(tail -n +2 "${SUBCLUSTERED_FILE}" | cut -d',' -f1 | sort -u | wc -l)"
+    fi
+    
+else
+    echo "✗ Sub-clustering failed with exit code $?"
+    exit 1
+fi
+
+echo ""
+echo "=== Sub-clustering Process Complete ==="
+echo "Date: $(date)" 
diff --git a/RDAS_RDOMICS/scripts/sample_characteristics_harmonization/sample_characteristics_harmonization_output/2_sample_characteristics_key_count_chars_removed_rule_based_cleaned.csv b/RDAS_RDOMICS/scripts/sample_characteristics_harmonization/sample_characteristics_harmonization_output/2_sample_characteristics_key_count_chars_removed_rule_based_cleaned.csv
new file mode 100644
index 0000000..c4edc7b
--- /dev/null
+++ b/RDAS_RDOMICS/scripts/sample_characteristics_harmonization/sample_characteristics_harmonization_output/2_sample_characteristics_key_count_chars_removed_rule_based_cleaned.csv
@@ -0,0 +1,4975 @@
+name,count
+tissue,157196
+cell type,97260
+age,73415
+treatment,71874
+gender,53178
+Sex,47903
+genotype,46776
+strain,41490
+cell line,40278
+disease state,31657
+time,17068
+disease,14111
+time point,12459
+group,11700
+diagnosis,11647
+condition,10956
+ethnicity,10118
+sample type,10037
+batch,9770
+timepoint,9424
+patient id,8310
+infection,8270
+individual,8008
+race,7888
+genotype/variation,6816
+subject id,6726
+replicate,5824
+donor,5515
+subject,5499
+chip antibody,5153
+developmental stage,5106
+disease status,4806
+antibody,4446
+Stage,4189
+patient,4121
+day,3722
+clinical info,3680
+visit,3653
+histology,3618
+agent,3539
+vaccine,3535
+plate,3492
+tissue type,3471
+subject status,3306
+protocol,3271
+bmi,3259
+tumor type,3082
+cohort,3031
+region,2915
+age in years,2898
+molecule subtype,2882
+housing condition,2815
+sample id,2694
+subjectid,2672
+site,2620
+smoking status,2577
+sample,2422
+segment,2380
+stimulation,2378
+strain background,2334
+location,2284
+organismpart,2192
+pasi,2192
+diseasestate,2186
+sample group,2179
+clinical diagnosis,2111
+organism part,2102
+celltype,2035
+phenotype,1959
+pathologic status,1940
+histologic diagnosis,1936
+tissue anatomic site,1936
+grade,1888
+type,1856
+mouse id,1755
+donor id,1737
+experiment,1725
+hiv status,1705
+slide no,1700
+psa-psoriatic arthritis,1700
+cell description,1693
+reference,1682
+source,1670
+participant id,1666
+Age,1662
+cell sex,1656
+controlid,1655
+molecule type,1618
+datatype description,1606
+datatype,1603
+tumor grade,1602
+sex,1601
+library type,1600
+tst,1588
+passage,1586
+cell,1531
+tcga subtype,1529
+molecule,1522
+dataset,1520
+mgmt status,1518
+collection_method,1517
+cell organism,1508
+well,1500
+Tissue,1499
+segment type,1492
+dose,1480
+roi,1459
+strain/background,1449
+deduplicatedreads,1447
+trimmedreads,1447
+sequencingsaturation,1447
+alignedreads,1447
+rawreads,1447
+stitchedreads,1447
+roi x coordinate,1444
+roi y coordinate,1444
+virus,1436
+surgical status,1417
+phillips subtype,1417
+infection status,1402
+tumor location,1401
+date,1400
+tumor stage,1390
+infection states,1389
+biological replicate,1375
+kps,1369
+hb,1364
+donor_id,1361
+outcome,1324
+tag,1317
+rin,1300
+biomaterial_type,1293
+mouse strain,1292
+culture,1264
+animal,1261
+antibody vendorid,1258
+antibody vendorname,1245
+patientid,1239
+mmse,1234
+batch id,1213
+tissue source,1209
+individual id,1208
+assay,1202
+antibody targetdescription,1200
+clinical status,1187
+geographical region,1182
+labversion,1180
+roi number,1177
+Gender,1172
+protection,1172
+lab,1170
+barcode,1156
+patient_id,1152
+disease group,1144
+corticosteroids,1140
+antibody antibodydescription,1138
+passages,1138
+class,1132
+labexpid,1110
+treatment description,1095
+temperature,1094
+tissue/cell type,1069
+final diagnosis,1067
+isolate,1067
+status,1055
+area,1053
+material,1047
+library prep,1030
+animal id,1019
+primary site,1010
+fraction,1003
+cell subtype,1002
+patient diagnosis,1001
+enrollment batch,1000
+covid-19 status,1000
+enrollment date t0,1000
+bc run_id,1000
+pipeline version,1000
+censored,1000
+biocollection id,1000
+provider,1000
+parity,998
+lab description,997
+background strain,997
+subtype,994
+cdna synthesis,993
+treatmentshort,992
+pasi.baseline,992
+platesimple,992
+pasi75.response,992
+pasi.week4,992
+pasi.week12,992
+biomaterial_provider,987
+patient gender,977
+extraction_protocol,970
+experiment_type,970
+moi,969
+medium,949
+tuberculin skin test,938
+drug treatment,934
+albumin,923
+treated with,920
+m. tuberculosis culture,911
+country of serum collection,911
+bcg scar or history,911
+acid fast bacilli (afb) smear microscopy,911
+previous history of active tb,911
+organ failure,910
+infected with,898
+development stage,897
+culture result,894
+hematocrit,883
+tb status,881
+survival_yr,876
+site_onset,876
+age_onset,876
+cell_type,875
+clone,871
+hemoglobin,865
+model,861
+bin,855
+qft,854
+cell line id,847
+idh status,842
+sampleID,841
+metastasis,840
+age description,839
+extraction_protocol_sonication_cycles,838
+extraction_protocol_type_of_sonicator,838
+cancer status,837
+donor_ethnicity,835
+donor_health_status,835
+donor_age,835
+donor_sex,835
+mouse model,822
+birth_place,813
+severity score,811
+method,810
+cell subset,806
+chip_protocol,804
+geographic location,804
+chip_protocol_chromatin_amount,804
+adjusted household density,804
+infant's sex,804
+disease stage,804
+delivery,804
+agricultural animals,804
+companion animals,804
+mother's age,804
+bmi code,804
+time post-partum,804
+softwareversion,795
+treatment group,792
+rpa,791
+hours post infection,779
+wbc,779
+tissue preparation,779
+treatment time,775
+disease severity,774
+morphology,764
+control,757
+fev1 % predicted,753
+neutrophils,749
+stress,744
+tissue of origin,744
+participant,742
+study,741
+infection protocol,740
+stimulus,736
+control description,731
+background,730
+patient viral load,726
+case number,726
+cell karyotype,726
+histology subtype1,722
+patient group,721
+cell lineage,713
+idh1 status,709
+chip_antibody_catalog,708
+sample source,708
+chip_antibody_provider,708
+sample alias,707
+sample common name,707
+os,703
+chip_antibody_lot,696
+sequencing_batch,685
+genetic background,683
+chip_protocol_bead_type,680
+chip_antibody,680
+chip_protocol_antibody_amount,680
+chip_protocol_bead_amount,680
+first_diagnosis,678
+working_diagnosis,678
+smoker,670
+field_site,669
+response,667
+irradiated,667
+hospitalized,665
+tissue_type,661
+atmosphere,661
+tumor grading,658
+treatment duration,657
+os_status,656
+growth protocol,654
+sample collection site,652
+fev1 %_predicted,648
+chest x-ray,644
+age group,642
+flowcell,640
+Race,638
+strain description,638
+infection time,635
+year,633
+transduction,629
+transfection,629
+severity,619
+epithelial,618
+ploidy,616
+first vaccination,614
+second vaccination,614
+geographic origin,610
+patient sample id,610
+pathology,605
+subgroup,601
+sample.id,597
+nanostring_id,597
+cartridgeid,597
+lane.number,597
+generlf,597
+fovcount,597
+bindingdensity,597
+fovcounted,597
+scannerid,597
+stageposition,597
+patient age,597
+systemapf,597
+center,596
+brain region,595
+crp,593
+ID,584
+illness,574
+passage_if_expanded,572
+selection,567
+weight,567
+lane,566
+qpcr plasmodium species,562
+naturally exposed or unexposed to plasmodium sp. parasites,562
+p53 mutation,560
+cftr genotype,560
+growth phase,558
+igra,557
+selection marker,554
+doubling time,553
+sars-cov-2 pcr,552
+sars-cov-2 rpm,552
+dnamage,551
+case,551
+Ethnicity,547
+Illness,546
+sorted cells,546
+infectious agent,546
+sort,542
+covid_status,538
+host,536
+pid,536
+groups,535
+recipient,534
+collection time point,533
+pmd_min,531
+duration,530
+disease duration,527
+cluster,527
+treg donor,527
+pcr2 cy. no,527
+origin,525
+nhl subtype,524
+slide,522
+donor age,518
+originating cell line,515
+facs sorting,512
+molecular subgroup,509
+biomaterial,508
+per lymphosstained,507
+disease_category,507
+resistance,506
+ChIP,506
+cell population,505
+sample_code,503
+organ/tissue,503
+previousdiagnosisoftb,501
+meconium ileus surrogate variable 21,500
+persistent ps aer status,500
+b_symptoms,500
+age_at_diagnosis,500
+meconium ileus surrogate variable 22,500
+patient classification at first sample,500
+meconium ileus surrogate variable 16,500
+meconium ileus surrogate variable 20,500
+meconium ileus surrogate variable 18,500
+meconium ileus surrogate variable 17,500
+age of onset of persistent ps aer or censored age,500
+meconium ileus surrogate variable 15,500
+sample_pre_active_treatment,500
+tss enrichment,500
+meconium ileus status,500
+genotype pc1,500
+filtered peaks,500
+meconium ileus surrogate variable 13,500
+genotype pc2,500
+genotype pc3,500
+genotype pc4,500
+genotype pc5,500
+genotype pc6,500
+genotype pc7,500
+consortium lung phenotype surrogate variable,500
+meconium ileus surrogate variable 1,500
+meconium ileus surrogate variable 14,500
+xpert,500
+meconium ileus surrogate variable 12,500
+conf_combine_unc,500
+quantiferon test,500
+t-spot. tb test,500
+discharged_to,500
+days_in_hospital,500
+immunization dose,500
+title,500
+dosanjh,500
+ed_disposition,500
+age of enrollment,500
+meconium ileus surrogate variable 23,500
+os_followup_y,500
+conf_entropy,500
+conf_combine_gcb,500
+meconium ileus surrogate variable 11,500
+conf_combine_abc,500
+pred_combine,500
+microdissection,500
+reagent,500
+probe_detection,500
+qc_fail,500
+case_diagnostic_subtype_icdo3,500
+diagnostic_group,500
+timetonegativity,500
+mgit,500
+meconium ileus surrogate variable 3,500
+tgrv,500
+meconium ileus surrogate variable 2,500
+days since first sample,500
+meconium ileus surrogate variable 4,500
+totfa,500
+p_il1ra,500
+whr,500
+in vivo passage,500
+sequencingbatch,500
+external id,500
+passedqc,500
+cancer site,500
+disease staging,500
+p_crp,500
+waist_circumference,500
+hip_circumference,500
+ffmass,500
+p_adipon,500
+meconium ileus surrogate variable 5,500
+matsuda,500
+extract name,500
+source_organism,500
+p_proi0,500
+systbp,500
+fsc.w.x,500
+assay name,500
+b_ghba1c,500
+diastbp,500
+sample_name,500
+fsc.h.x,500
+chest x-ray description,500
+gfr,500
+p_ffa0,500
+percent.ercc,500
+nfeature rna,500
+meconium ileus surrogate variable 6,500
+meconium ileus surrogate variable 8,500
+meconium ileus surrogate variable 9,500
+frip,500
+meconium ileus surrogate variable 10,500
+treatmentresult,500
+in_pmid_32187361,500
+in_pmid_30408148,500
+meconium ileus surrogate variable 7,500
+meconium ileus surrogate variable 19,500
+p_ins0,500
+fsc.a.x,500
+s_tottg,500
+s_totalc,500
+pfam_dbd,500
+array_design,500
+s_ldlc,500
+dev_stage,500
+s_hdlc,500
+chemical compound,500
+homair,500
+vendor id,500
+p_gl0,500
+ncount rna,500
+sorted compartment,500
+covid_hosp_days,500
+seurat clusters,500
+afb smear grade,500
+acuity.max,500
+fev1/fvc,500
+platform_id_id design,500
+white_blood_cell_count,500
+cluster_label,500
+segmented_neutrophils,500
+patient category,500
+sample class,500
+nrbc_absolute,500
+malaria_status,500
+nrbc_percent,500
+days since vaccine,500
+injection_roi,500
+meth-plate,500
+surgery number,500
+multisector,500
+classification group,500
+rna-seq plate,500
+meconium ileus surrogate variable 25,500
+platelet_count,500
+injection_materials,500
+hemisphere_name,500
+dbd source organism,500
+animal replicate,500
+project,500
+sample id alt,500
+library preparation method,500
+dbd,500
+time harvest,500
+assigned cluster,500
+date hyb,500
+match,500
+allele nominal,500
+sid,500
+date_m0,500
+plate_location,500
+date_m3_5,500
+time_to_malaria,500
+clinicaldiagnosis,500
+age_at_draw,500
+well address,500
+date harvest,500
+allele actual,500
+plate id,500
+tsne cluster,500
+smear_results,500
+predicted parent celltype,500
+days_from_att,500
+genotype_abbreviation,500
+neoplastic,500
+cancersite,500
+in_covid_aki_dataset,500
+immature_granulocytes_percent,500
+culture_result,500
+connectivity_zscore,500
+predicted celltype,500
+viral_positivity,500
+volunteer id,500
+fev1% predicted,500
+age_weeks,500
+institutional tumor diagnosis,500
+blood sample id,500
+waz,500
+immature_granulocytes_absolute,500
+consortium lung phenotype,500
+timepoint biopsy,500
+patient_asymptomatic,500
+eptborptb,500
+neutrophils_absolute,500
+admitted_to_icu,500
+blood sample_id,500
+library prep_plate,500
+sampling time_point_label,500
+days since_first_sample,500
+patient classification_at_first_sample,500
+covid-19 positive,500
+crna plate,500
+affy_batch,500
+supplier,500
+cell line code,500
+disease location,500
+cosmic id,500
+cmv status,500
+risk for tb,500
+induced,500
+n1_ct,500
+haz,500
+malaria_before_m3_5,500
+hiv positive,500
+facs.date,500
+cell projection,500
+recent boostrix,500
+instrument model,500
+exp_component_name,500
+external_donor_name,500
+full_genotype,500
+facs_population_plan,500
+meconium ileus surrogate variable 26,500
+conf_combine_mhg,500
+meconium ileus surrogate variable 24,500
+smear microscopy,500
+ethnicity1,500
+basophils_absolute,500
+pcr,500
+qtf-git,500
+tspot.tb,500
+basophils_percent,500
+eosinophils_absolute,500
+eosinophils_percent,500
+monocyte_absolute,500
+monocyte_percent,500
+lymphocyte_absolute,500
+lymphocyte_percent,500
+malaria_transmission,500
+in_covid_only_dataset,500
+contributing institute,499
+pcr cq,499
+curative_intent,496
+ldh,496
+sampledate at t0,496
+firstline_regimen,496
+sequencing batch,494
+tumor,494
+who category,493
+age_at_death_years,492
+disease_duration_years,492
+thal_amyloid_phase,492
+braak_asyn_stage,492
+clinical_diagnosis,492
+dementia,492
+braak_nft_stage,492
+cerad_stage,492
+neuropathological_diagnosis,492
+amp_plate,492
+duplicate_pair,492
+protocol description,492
+failed_genotyping_qc,492
+is_technical_replicate,492
+slide_position,492
+sequencing parameters,490
+cinsarc,489
+assayed molecule,489
+material support,489
+Strain,486
+passage number,485
+sars-cov-2 positivity,484
+diagnostic_mean,484
+comorbidities,481
+pathogen,478
+population,477
+library name,476
+contributing person,476
+infected with/healthy control,476
+brainbank,475
+personid,475
+broadbrainregion,475
+postmorteminterval,475
+dnamagewindsorized,475
+caglength,475
+esr,475
+code,473
+culture condition,472
+tissue_depot,471
+hyb chamber,470
+sample name,470
+monkeyid,470
+synchroset,470
+pittid,470
+red blood cells,460
+lymphs,460
+death,460
+performance_status_ecog,459
+line,459
+white blood cells,458
+FDG avidity,458
+FDG group,458
+isolation_method,455
+timing sx,455
+research pcr,455
+sample timing,455
+vaccine doses,455
+vl copies,455
+timing dx,455
+covid cat,455
+covid,455
+skin type,452
+vital status,450
+survival_status,450
+days_from_att_categ,450
+subgroup_att,450
+progression,448
+site of infection,447
+prior treatment,445
+survival,444
+breed,443
+subject_id,442
+predicted dlco,441
+cancer type,439
+infection code,438
+genome build,438
+sample material,438
+diseasestatus,437
+specimen,434
+time.to.tb.months,434
+time.from.exposure.months,434
+ffs,433
+culture conditions,432
+label,431
+immunocompromised status,429
+concentration,427
+wt/mut,426
+derived from hesc/ipsc,426
+hd/asd,426
+disease_status,426
+bait,425
+pcr1 cy. no,422
+chain,422
+techn. replicate,422
+sample collection time,421
+parasitemia,419
+media,417
+nanopore methylation_call,415
+reference diagnosis,415
+nanopore methylation_class_family_call,415
+outlier,414
+shRNA,414
+library well,412
+num_extranodal,412
+library plate,412
+genotypic pc2,410
+gxbdataset_biirinternal,410
+genotypic pc1,410
+array,407
+condition description,405
+date collected,404
+vaccination,404
+ols,403
+sequencing lane,401
+star_genome_mapped,399
+modified rankin score at 1 year post-ich,399
+initial ich volume,399
+day of trial,399
+glasgow coma score,399
+nih stroke score,399
+1 yr gcs <4,399
+senot determined,399
+fastq_frag_count,399
+gene_count,399
+adjusted disease severity index,399
+rrna_count,399
+hrs after symptom onset,399
+techrep,399
+prct_trans_mapped,399
+trans_mapped,399
+prct_rrna,399
+prct_star_genome_mapped,399
+response_group,398
+symptomatic or asymptomatic at sample collection,397
+qpcr screening for plasmodium genus,397
+grouping,395
+platelet,394
+nuclei count,393
+day post infection,391
+non human primate individual id,390
+age at death,387
+days since vaccination,387
+vaccine side effects,387
+vaccine type,387
+age at sample drawn,387
+induction date,385
+library date,385
+tau_a1,384
+antigen,384
+tau_a2,384
+nanostring plexset set in rcc files,384
+roicoordinatey,383
+sampling timepoint,383
+loq,383
+roicoordinatex,383
+markers,382
+technique,381
+exposure,381
+sample preparation,380
+chip antibody vendor,380
+tst skin test,379
+recruiting site,379
+tspot,379
+quantiferon,379
+sample_group,377
+slide id,377
+octn2,374
+aza tolerant,374
+smoking amount,374
+smoking stop date,374
+smoking start date,374
+casenote review date,374
+aza treated,374
+last followup date,374
+ibd affected relatives,374
+nod 1007 fs,374
+igr2198,374
+igr2230,374
+dlg5 133a,374
+octn1,374
+diagnosis date,374
+nod 908,374
+blood obtained,374
+other illnesses,374
+symptoms onset date,374
+birth date,374
+procedure date,374
+indictation for procedure,374
+nod 702,374
+wcc,374
+family history,374
+current medication,374
+joint problems,374
+igr2096,374
+subject group,371
+strain/genotype,371
+ipi_score,370
+binding density,370
+cap score,369
+mouse number,369
+classification,369
+cap_d_group,369
+aoinucleicount,368
+who grade,367
+gold stage,366
+chip antibody cat,365
+pcr test for sars-cov-2,364
+qc flag - low signal,363
+year of surgery,363
+tissue structure,363
+covid-19 ish status,363
+surface area,363
+history,363
+note,363
+negative normalization factor,363
+hyb-code,363
+tissue substructure,363
+sars-cov-2 rna ish,363
+replicate description,362
+age in year,362
+link,362
+organ,361
+growth condition,359
+ssc subtype,358
+experiment group,354
+mutation,354
+previous diagnosis of tb,354
+mouse,354
+sample group_label,353
+days of differentiation,353
+treatment location,353
+age at_treatment,353
+treatment age_group,353
+preoperative karnofsky performance status,352
+who,349
+rpa class,349
+source type,345
+karnofsky performance status before starting chemo-radiotherapy,345
+nuclei_counts,345
+amplification,341
+additional conditions,340
+sars-cov-2 voc,340
+egfr_amplification,340
+sample number within subject,339
+disease symptom,339
+skin,338
+chemotherapy,337
+sirna,335
+sample collection,335
+culture type,334
+animal_id,334
+tissue id,333
+rna source,333
+total number of genomic aberrations,332
+follow up years,332
+with or without clonal heterogeneity,332
+international prognostic index,332
+dead or alive at the end of follow-up,332
+animal age,330
+x coordinate,330
+aoi surface area,330
+y coordinate,330
+antibodies/tags,329
+obtainedby,328
+seizure,328
+treatment/time point,328
+other diseases,325
+monkey id,324
+amplification cycles,324
+pasi75 response at week 12,324
+idh1 mutation status,323
+disease type,322
+parasite strain,322
+animal sex,320
+colony of_origin,320
+cell phenotype,319
+scanheight,319
+ventilation,319
+scanoffsetx,319
+scanwidth,319
+dosage,319
+slide_scanid,319
+scanoffsety,319
+lotid,319
+week,317
+osteogenesis day,317
+msc source,317
+smoke,317
+donor category,317
+hemoglobin genotype,315
+asthma,314
+abs monos by lymphos,313
+abs eosinophils,313
+per monos by lymphos,313
+visit_date,313
+timepoint_months,313
+uk_arrival_year,313
+smear_result,313
+age_at_baseline_visit,313
+per lymphocytes,313
+tb_disease_type,313
+slide name,313
+per neutrophils,313
+abs neutrophils,313
+abs lymphocytes,313
+abs monocytes,313
+per monocytes,313
+paired rna-seq,312
+hb phenotype,311
+per eosinophils,310
+development,310
+disease subtype,308
+vaccinegroup,308
+cdk4_amplification,307
+cdkn2a_b_deletion,307
+mdm4_amplification,307
+pdgfra_amplification,307
+mdm2_amplification,307
+chr20_gain,307
+chr10_loss,307
+pten_deletion,307
+chr7_gain,307
+idh2 mutation status,307
+chr19_gain,307
+mean corpuscular volume,306
+vaccine v2,305
+vaccine v1,305
+aoisurfacearea,304
+cartridgebarcode,304
+sample time,302
+trachea region,301
+education,300
+p53 Status,300
+sampletype,300
+job/role,300
+CellLine,300
+BioSourceType,300
+DiseaseState,300
+Individual,300
+TargetedCellType,300
+Prior Treatment,300
+OrganismPart,300
+InitialTimePoint,300
+cells,299
+chip-antibody,298
+OS status,297
+treatment administration route,296
+treatment frequency,296
+category,296
+diffuse at baseline sample,295
+anti-rna polymerase iii,295
+anti-centromere,295
+technical replicate,295
+experiment type,295
+MDR Function,295
+anti-topoisomerase i,295
+description,294
+mrss at baseline sample,293
+hiv,292
+age at diagnosis,291
+tnm,290
+pseudomonas aeruginosa surrogate variable 1,290
+round of sequencing,288
+treatment1,288
+pfs,287
+index,287
+platinumfreeinterval.mos,286
+pfs.mos,286
+differentiation stage,286
+path.stage,286
+surgical.outcome,286
+diagnosis.of.record,286
+recurrence,286
+diagnosis.after.path.re.review,286
+tcga_subtype_pro,286
+tcga_subtype_mes,286
+tcga_subtype_imr,286
+tcga_subtype_dif,286
+vitalstatus,286
+os.mos,286
+platinumstatus,286
+stic,286
+birth defects,285
+developmental/speech disorder,285
+ct,285
+mri,285
+neurological disorder,285
+genetic testing,285
+cerebral palsy,285
+autoimmune disorder,285
+mutational subclass,285
+study group,285
+gastrointestinal disorder,285
+psychiatric disorder,285
+medications/vitamin names,284
+allergies,284
+covid-19-related medication and anti-microbials,284
+unpublished,284
+diet,284
+sars-cov-2,284
+tcr single cell sequencing,284
+single cell sequencing platform_id,284
+covid-19 severity,284
+city,284
+datasets,284
+bcr single cell sequencing,284
+diabetes,283
+virus strain,283
+lung disease,283
+chronic diseases,282
+volume,282
+molecular.diagnosis,280
+gcb.abc.signature,280
+stimulant,280
+drug,278
+age at baseline visit,277
+library preparation,277
+geographical location,277
+aoi,277
+codeos,275
+ezh2,275
+vaccination.assignment,275
+description of day,275
+protectionstatus,275
+codeffs,275
+subject number,272
+primary.tumor,271
+tissue.type,271
+irf4.prediction,271
+used for analysis,271
+irf4.status,271
+training.test,271
+irf4.probability,271
+tumor_name,270
+gene-level raw fpkm profile  file_download_link,270
+differentiation day,270
+block_name,270
+specimen_name,270
+rna_well_id,270
+structure acronym,270
+euthanized_due_to_pulmonary_tb,268
+day_of_euthanasia,268
+h3f3a status,268
+percent_weight_loss,268
+centre,268
+lung_mtb_burden,268
+hc coded,267
+radiation administered prior to tumor resection,267
+hc,267
+chemotx administered prior to tumor resection,267
+temodar administered prior to tumor resection,267
+set,267
+genome/variation,266
+immunization,265
+sample_set,265
+visit day,265
+pmi,265
+condition/tp dx,264
+tumour type,263
+induration_mm,262
+biopsy,260
+read length,259
+donor_id_blinded,258
+experimental group,256
+regimen,256
+chemo before tp,256
+per cd16pos cd3neg,255
+per cd20,255
+normalizedsmokinghistoryinpackyears,254
+diseasestaging,254
+cns subregion,253
+per cd3stained,253
+histological diagnosis,253
+per cd8,252
+transfected with,252
+align_input,251
+library_prep_date,251
+intronic_reads,251
+nuclear_reads,251
+intergenic_reads,251
+extract_date,251
+tb,251
+mtrna_reads,251
+passqc,251
+rrna_reads,251
+reads_all,251
+bfcohort,251
+tb_binary,251
+reads_trimmed_filtered,251
+micro_ref_stndrd,251
+align_unique,251
+align_multi,251
+align_tooshort,251
+exon_ratio,251
+duplication_rate,251
+intron_exon_ratio,251
+bias53,251
+exonic_reads,251
+sample_group_granular,251
+rrna_fraction,251
+ftcount,251
+lunit_score,251
+qxr_score,251
+cad4tb_score,251
+semiquant,250
+number of malaria infections,250
+volunteer code,250
+diseas state,248
+treatment dose,248
+molecular classification,248
+who.classification.2021,245
+surgical_interval_mo,245
+codel_status,245
+age_diagnosis_years,245
+recurrent_status,245
+idh_status,245
+tcga.subtype,245
+heidelberg_meth_subtype,245
+tumor localization,243
+repeat,243
+monocytes,242
+age of onset,240
+rna-sample type,240
+donor type,240
+basename,240
+paired samples,239
+season,238
+samplename,238
+original geo accession,238
+sars-cov2_rpm,237
+other information,236
+sorting strategy,234
+escape,233
+covid-19,233
+ca19-9,232
+karnofsky index,232
+treatment arm,232
+intrinsic subtype,231
+plts,231
+diffuse,231
+patient.code,231
+fvc at baseline visit,231
+1p/19q status,228
+dx,228
+hist.score,228
+pcv,227
+blood collection tube coating,227
+genetic modification,227
+dysplasia now,226
+Tumor stage,226
+sample_type,226
+broad diagnosis,226
+tumor category,226
+behavior at diagnosis,226
+dys broad location,226
+TimeUnit,225
+serostatus,224
+bcg vaccinated,224
+sorter day,224
+lymphgen_class_myc_pmid_32187361,222
+pid_pmid_32187361,222
+hmrn_class_aic_pmid_32187361,222
+modified_hmrn_class_pmid_32187361,222
+lymphgen_class_pmid_32187361,222
+disease activity,221
+subject condition,221
+tissue subtype,220
+coriell cell line repository identifier,220
+facs purification,219
+section,219
+codon129 genotype,219
+mrc scale,219
+treatment withdrawal,217
+animalid,217
+treatment initiation,217
+cdkn2a,216
+feeding,215
+cd4 count,215
+library protocol,215
+state,214
+transgene,213
+health state,213
+subject diagnosis,213
+active ingredient,212
+bal sampling date,212
+prescription drugs,212
+mtb challenged,212
+recreational drugs,212
+cigarette smoker,212
+sexually transmitted infections,212
+art start year,212
+medical.history,212
+quantiferon tb reagent,212
+sample day,212
+baseline hiv_rna,211
+tissue region,211
+baseline cd4,211
+treatment-outcome code,211
+timing,211
+processing,210
+tissue/sample type,209
+library quality,208
+blood_group,208
+sampling_timepoint,208
+bioreplicate id,207
+stimulation condition,207
+time post-stimulation,207
+in vivo or in vitro,207
+differentiation batch,207
+hyb position on 8-plex array,207
+hybridization batch,206
+visit number,205
+pair,205
+cell types,205
+developmental_stage,204
+primary diagnosis,204
+light condition,203
+malaria strain,203
+ild subtype,203
+responder cell line,203
+1 mouse or pool of 3 mice,203
+knockout,203
+diagnosis total,202
+diagnosis splen flex,202
+lauren classification,202
+anatomic_location,202
+followup total,202
+followup splen flex,202
+followup recto sigmoid,202
+followup rectum,202
+inflammation_status,202
+diagnosis hep flex,202
+aza at present,202
+diagnosis recto sigmoid,202
+diagnosis rectum,202
+uc flare up,202
+run_date,202
+ucss,202
+calprotectin,202
+followup hep flex,202
+days_symptom_onset,201
+patient_visit,201
+patient_age,201
+pregnancy status,201
+ajcc stage,201
+olink_sample_id,201
+anatomic location,201
+lung pathology,200
+muscle mass,200
+radiation.therapy,200
+log10 body mass index,200
+log10 matsuda insulin sensitivity index,200
+waist to hip ratio,200
+log10 bioimpedance,200
+per basophils,200
+ageatsampling,200
+overall.survival..days,200
+reference genome_for_processed_files,200
+fat mass,200
+reference genome_for_alignment,200
+tumor_entity_subtype,200
+sampling time,199
+patient sex,199
+time_since_onset,198
+primed,198
+library,198
+grey/whitematter,198
+treatment protocol,197
+brain location,197
+experimental replicate,196
+cancertype,196
+nf1,196
+designphase,196
+self_reported_race,195
+cell line of origin,195
+patient code,195
+plate_number,195
+cirrhosis present,195
+chronic hypertension,194
+evlp type,194
+clinical spectrum nih classification,194
+ga,194
+growth medium,193
+number of relapses,192
+pasi75resp,192
+Gleason Grade,192
+microbiota status,192
+survival after surgery,192
+sputum_culture,191
+cdna prep,191
+case/control,191
+region of birth,191
+sputum_smear,191
+biopsy type,190
+day post treament,190
+death with metastasis,189
+infection_status,189
+vaccination route,188
+outcome related,188
+couple number,188
+chr10q_loss,188
+sars cov2_hx,188
+growth,187
+rna sample id,187
+bacterium,186
+hours,186
+period,186
+infected/uninfected,186
+sequencing run,186
+buffer,186
+extraction date,185
+draw_date,185
+comment,184
+patient subgroup,184
+LabeledExtract,183
+patient number,183
+wga,182
+rip antibody,182
+hybridization protocol,182
+antibody manufacturer,182
+dna sample,182
+stimulation time and condition,182
+cell source,181
+pfs_status,181
+neoplasia type,181
+study id,181
+day post hct,181
+mgmtstatus,181
+symptom severity,180
+Histopathological diagnostic,180
+viral shedding,180
+sample tissue,179
+tst result,179
+fetal sex,179
+tissue/cell line,179
+ntd status,179
+uhdrs tfc,178
+uhdrs tms,178
+symptomatic,178
+age at year 1,178
+egfr,178
+expanded allele cag repeat count,178
+paired microarray,177
+factor,177
+age at_diagnosis,177
+dev stage,177
+paired material support,177
+ffpe quality,177
+lineage,176
+molecular subtype,176
+mtb_strain,176
+mgmt,174
+day of differentiation,174
+input,174
+sample_id,173
+biosample encode accession,173
+atcc id,172
+diagnosis rectal,172
+followup anal perianal,172
+diagnosis colonic,172
+hours post-invasion,172
+diagnosis details,172
+followup vienna classific,172
+behavior at followup,172
+diagnosis stricture fistu,172
+Cause of death,172
+treatment response,172
+ocp,172
+diagnosis anal perianal,172
+diagnosis vienna classifi,172
+harvey bradshaw,172
+sars-cov-2 infection,172
+further operations,172
+stoma ileal,172
+followup rectal,172
+followup ileal,172
+followup colonic,172
+diagnosis oral,172
+cdai,172
+diagnosis ileal,172
+followup oral,172
+smoking,171
+volunteer,171
+diseaselocation,170
+living,170
+survival time,170
+tumorgrading,170
+hc_85_samples,170
+survival cluster,170
+preparation,169
+differentiation,169
+disease_state,169
+vaccine group,168
+genotype huntington,168
+h37rv genotype,168
+ancestry,168
+enzymatic treatment,168
+subset,168
+days since covid-19 diagnosis,168
+0 = no,168
+harmonized disease score,168
+timepoint_postchallenge,168
+overall.survival.months,168
+donorid,168
+long-covid symptoms,168
+duration of illness,168
+deceased paired biopsies,168
+log grans_nx,167
+log mtb_cfu,167
+de-identified donor,167
+grans nx,167
+pitt id,167
+total mtb_cfu,167
+dose group,167
+timeafterbcg,167
+bcg dose_log10,167
+protect outcome,167
+mahpic non human primate individual id,166
+tssue,166
+tma,166
+hypertension,165
+symptomatic or asymtomatic at sample collection,165
+qpcr screening for plasmodium,165
+efficacy,164
+lentiviral transduction,164
+days post drug,164
+relative sox9_level,163
+pre-eclampsia,163
+tnm stage,163
+biorep,163
+collection time point (#) or necropsy,162
+mechanical ventilation,162
+group description,162
+hours post invasion,162
+seisure frequency,162
+antibody catalog,161
+inhibitor treatment,161
+tissue archive method,160
+parasite stage,160
+tumor full_name,160
+strain name,160
+abo,160
+mtb culture,159
+study participant,159
+disease_group_dme,158
+disease_group,158
+post_mortem_interval,158
+post_mortem_interval_unit,158
+buffer_volume_unit,158
+ammount_cells,158
+hba1c,158
+disease_group_detailed,158
+sample_site,158
+ffs_status,158
+time-point,158
+protein exchange,158
+dme,158
+eye,158
+samplenumber,158
+other_medication,158
+spike-in cell_type,158
+spike-in cell_line,158
+buffer_volume,158
+duration_diabetis,158
+ammount_cells_unit,158
+dr_severity_score,158
+diabetes_medication,158
+fov,156
+prognosis,156
+study_origin,156
+deceased unpaired biopsies,156
+os_month,156
+days after infection,156
+k13 allele,156
+illumina_index,156
+brain bank,156
+chip antibody lot,156
+cag_repeat,156
+age_binned,156
+conversion,156
+parasitemia category,155
+malaria rd test,155
+log2 parasitemia,155
+library prep. kit,155
+genotypic pc3,155
+tissue origin,155
+overexpression 1,154
+overexpression 2,154
+dm,154
+idh1/2 genotype,153
+restriction enzyme,153
+pdgfra,152
+pten,152
+mdm4,152
+sequencing type,152
+gleason,152
+differentiation_stage,152
+differentiation_method,152
+survival status,152
+rb1,152
+classifier_mes,152
+classifier_rtk2,152
+pathology_note,152
+classifier_rtk1,152
+cdk4,152
+blood.source,151
+aerosol.run,151
+biomaterial provider,151
+antibody description,151
+p53 status,151
+sequencing.lane,151
+cage,151
+lung.cfus,151
+age.days,151
+tb.status,151
+infection.time.point.days,151
+lane.ordinal,151
+embryonic stage,150
+anemia status at baseline,150
+pf infection status,150
+sample recovery type,150
+ajcc uicc stage,150
+splice variant,150
+clinical diagnosis specimen,150
+sbv challenge gold standard,150
+sequencing date,150
+parasite density,150
+clinical diagnosis patient,150
+temp max,150
+hct,150
+sample_barcode,149
+excision year,149
+flipi_score,149
+hybridizationdate,149
+rnaextractiondate,149
+fluidigm c1 capture chip size,149
+malign,148
+slide_id,148
+"deceased donors, only left kidney included in the analysis",148
+notes,148
+hc_74_samples,148
+adapter,147
+knockdown,147
+patient's condition,147
+side,146
+"biopsy data, villus height to crypt depth",146
+transplant type,145
+total_mtb_cfu,144
+time after bcg,144
+distinct stages of tb,144
+grans_nx,144
+log_mtb_cfu,144
+vax_dose,144
+time points,144
+dose_group,144
+vax_group,144
+pitt_id,144
+qft result,144
+protect_outcome,144
+cell type_at_ko/kd,143
+pneumocystis colonization,143
+target gene,143
+tst in mm,143
+identifier,142
+cell_line,142
+Phenotype,141
+patient treatment,141
+mgmt_status,141
+psa,141
+chip target,141
+facs markers,141
+bal_smear,140
+exposure_latent,140
+smear of index case,140
+modal x-ray grade,140
+cag,140
+s. haematobium at baseline,140
+bal_culture,140
+strandedness,140
+index_case_disease_site,140
+isolate_sensitivity,140
+distance from the tumor center,140
+crebbp,138
+obtainedby description,138
+ecog,138
+ep300,138
+foxo1,138
+pasi score,138
+tissue notes,138
+card11,138
+m7-flipi score,138
+arid1a,138
+mef2b,138
+pathogens,138
+foxp1,137
+obesity,137
+tumor subgroup,137
+subjects,137
+m7_flipi,137
+modified gene-expression profiling (mgep) score,137
+previously treated for nhl,137
+fvc,137
+caseid,137
+sars-cov-2 infected,136
+treatement,136
+dna methylation subgroup,136
+Other,136
+egfr status,135
+stress exposure,135
+inflammation status,135
+sample origin,135
+family,134
+time since steroid dose,134
+host cell,134
+collectiondate,134
+cellcount,134
+responder cells,134
+cell fraction,134
+years since diagnosis,134
+culture duration,134
+components,133
+biopsy site,133
+Time,132
+donor_genotype,132
+tissue-of-origin,132
+injection_type,132
+histopathology,132
+sample collection time post infection,130
+ip antibody,130
+dnase_protocol,129
+technology,128
+skin disease,128
+pcr positivity,127
+biological sex,127
+wg signature status,127
+fibrinogen,126
+ventilator-free days,126
+icu,126
+apacheii,126
+charlson score,126
+sofa,126
+genetic class,126
+target molecule,126
+associated controlled-vocabulary terms,126
+dmax<=20cm,126
+symptom,125
+gvhd,125
+mutation_carrier_status,124
+tfc_disease_stage,124
+tfc_score,124
+sequencing pool,124
+mouse genotype/variation,124
+cag_repeats,124
+t cell subset,123
+day-post-infection,123
+phase,123
+igra test_result,123
+single intradermal_comparative_tuberculin_test_(sictt)_result,123
+interferon gamma_release_assay_(igra)_test_starting_material,123
+ifga bovine_-_ifga_avian,123
+ifga bovine,123
+line type,123
+ifga nil,123
+ifga avian,123
+Diagnosis,122
+tumor subtype,122
+time post infection,121
+protocol number,121
+anca,121
+scan id,120
+nsaids,120
+infectivity,120
+arthropathymeds,120
+pcr result,120
+sequencing provider_id,120
+batch group,120
+qc status,120
+application,120
+das score,120
+sulfasalazine,120
+leflumide,120
+enzyme,120
+plaquenil,120
+steroids,120
+othermeds,120
+country,120
+biologics,120
+ehrlichia strain,120
+rituximab,120
+met_amplification,119
+tissue processing,119
+stimulation protocol,119
+other batch,118
+bmt recipient,118
+cell part,118
+serum type,118
+day after seeding,118
+bmt donor,118
+exposed stress,118
+visitid,117
+date of array,117
+line number,117
+batch.date,116
+marrow,116
+nhl or chl,116
+subtype/fl grade,116
+array batch,116
+cell culture,116
+hospital,116
+os month,116
+culture media,116
+infection agent,116
+day of_tumor_harvest,116
+harvesting time,115
+biosample confirmed diagnosis,114
+neurosphere derivation time,113
+tert promoter status,113
+immune status,113
+isolation source,113
+previous treatments,113
+vaccine regimen,112
+fragments in clean bam,112
+idh,112
+cell line source,112
+days after positive pcr results,111
+postmortem delay,111
+omicron sublineage,111
+parasite clearance halflife upon artemisinin treatment in patient,110
+cd4+ t cell subset,110
+mouse_id,110
+causes hf,110
+sensor,110
+donor code,110
+total cholesterol,109
+type of sample,109
+t2d/ir,109
+tryglicerides,109
+fibrosis degree,109
+fasting glycemia,109
+sentrix id,108
+cell type/line,108
+day_posthct,108
+spike-in,108
+hdl-cholesterol,108
+sentrix position,108
+patient population,108
+clinical condition,108
+"culture, stage, strain, harvest timepoint, estimated developmental age",108
+ldl-cholesterol,108
+dayposthct,107
+post-mortem interval,107
+Histology,107
+adt,107
+collection time,106
+readtype description,106
+interim pet response,106
+readtype,106
+primary tissues,106
+lmr>2.1,106
+time after treatment,106
+mic,106
+other,106
+growth media,106
+crispr library,105
+variety,105
+admission,105
+pasi_total,105
+age at sampling,105
+sample age proxy,105
+prnp codon 129 genotype,105
+subjid,105
+mrc scale score,105
+chip-seq antibody,105
+race/ethnicity,105
+drug dose,105
+infection group,105
+primary/recurrent,105
+day_post_hct,105
+scar,104
+timepointunit,104
+Outcome,104
+watch and wait,104
+patient condition,104
+worm infection,104
+timecollected,104
+family id,104
+colloquialtimeofday,104
+lighttreatment,104
+female,104
+braak,103
+small rna,103
+circumstances,103
+clinical phenotype,103
+sample subseries,103
+lesion,103
+target,102
+replicate mouse,102
+ph,102
+matched pair id,102
+stimulation duration,102
+gestational age,102
+lymphoma type,102
+infected,101
+rf,101
+diagnosis at bl,101
+ml_dataset,101
+Usage number,101
+das44,101
+wellbeing,101
+Filter number,101
+pain,101
+pseudotime,101
+diagnosis at year = 1,101
+swollen joints,101
+tender joints,101
+Exposures,101
+geo series,101
+ccp2,101
+geo accession,101
+symp.dur,101
+library strategy,101
+remission,101
+Tumor size,101
+response to artemsinin,101
+replicate id,101
+cortical_score,100
+cag_adj_estimated_onset,100
+cag_adj_striatal_score,100
+average library size,100
+striatal_score,100
+estimated_onset,100
+viral load,100
+donor number,100
+serotype,100
+duration_adj_striatal_score,100
+exposure time,100
+hto,100
+channel count,100
+followup months,100
+age of psoriasis onset,100
+current status,100
+sdh status,100
+litter,99
+hemisphere,99
+hours post-treatment,99
+localization,99
+treatment time point,98
+retinopathy,97
+disease_extension,97
+microarray_batch,97
+isolate type,97
+Smoking status,97
+cdeis,97
+endoscopic_mayo_score,97
+partial cdeis,97
+ko induction_time,97
+endoscopic_activity,97
+vector,97
+case_phenotype,97
+idh1,97
+mycn status,97
+tumor status,97
+incubation conditions,96
+"5, farthest",96
+sars-cov-2 infection state,96
+biosample confirmed sub-diagnosis,96
+age at transplant,96
+time of blood draw,96
+primary disease,96
+reporter,96
+atrx,96
+days post-vaccination,96
+ribosomal rna delpetion strategy,96
+culture_conditions,96
+volunteer number,96
+viral strain,96
+developmental stage rna isolation,96
+als phenotype,96
+individual identifier,96
+transplanted organ,96
+roi lot,95
+specimen_barcode,95
+sars-cov2 status,95
+imprkrt16w12,95
+imprepi.thickness,95
+parasite line,95
+imprkrt16w12_75,95
+animal name,95
+improvementtpssatw12,95
+pasi75_w12,95
+improvementpasiatw12,95
+cell stimulation,95
+endoscopic mayo subscore,94
+mitotic index,94
+xenograft line,94
+chemistry,94
+sequencing library,94
+qrds,94
+mouse identifier,94
+neuropathological diagnosis,94
+lps treatment,93
+Condition,93
+microglia media,93
+sirna treatment,93
+traf3ip2 genotype,92
+location of onset,92
+smoker or non smoker,92
+alchool use or not,92
+other pathologies,92
+therapy used,92
+vaccination boost,92
+familial anamnesis,92
+age.at.operation,92
+transduced with,92
+exposed to,92
+tumor.in.left.right.lobe,92
+fusion transcrit,92
+multifocal,92
+cinsarc group,92
+rqi,92
+purification,92
+post-mortem interval in hours,92
+subdivision of stimulated animals based on time of epilepsy developmentepilepsy development,92
+n0,92
+lymphocyte.reaction,92
+largest.dimension.ln.metastasis..cm,92
+subdivision of stimulated animals based on epilepsy development at given time point,92
+number.of.invaded.lymph.nodes..on.total.investigated.lymph.nodes,92
+health status,92
+mutational.status,92
+subdivision of stimulated animals based on seizure number,92
+extrathyroidal.extension..where,92
+vascular.invasion,92
+histological..subtype,92
+vaccination dose,92
+ibrutnib sensitivity,92
+capsular.effraction.lnm,92
+sub-population,92
+largest.dimension..primary.tumor..cm,92
+survival characteristics,92
+patient source,91
+tumour stage,91
+tumor region,91
+biopsy number for this subject,91
+disease_stage,91
+pcr screening for sars-cov-2,90
+days post onset of symptoms,90
+rna type,90
+onset,90
+p53 ihc,90
+cell state,90
+"age, months",90
+ct_aspergilloma,89
+ct_nod_cav,89
+survival_time,89
+ctscore,89
+ct_severity,89
+disease_duration,89
+ct_extent,89
+ct_nodules,89
+ct_severe_cav,89
+ct_consolidation,89
+ct_tib,89
+tlc,89
+Status,89
+sample number,89
+grna,89
+fev1,89
+eae clinical score,89
+Patient,89
+Group,89
+idh1 mutation,89
+tlco,89
+kco,89
+replicate # in experiment,88
+unique_subject_identifier,88
+tumour location,88
+progression_free_survival,88
+cell compartment,88
+progression_free_survival_censor,88
+bacterial lysate,88
+sample collection time post virus infection,87
+disease category,87
+age of death,87
+trial arm,87
+hour post infection,87
+antibiotic treatment,87
+sequencing,86
+cell subpopulation,86
+experiment year_month,86
+virus type,86
+unsorted or sorted,86
+AGE,86
+cattle breed,85
+main comorbidities,85
+clinical type,85
+surgery,85
+clinical stage,85
+tdtomato labeling,84
+cre driver,84
+apoe4,84
+patient comorbidity,84
+passes qc checks,84
+yfp labeling,84
+mouse line abbreviation,84
+pre_alveolar macrophageplification,84
+tumor type/grade,84
+dissection,84
+input material,84
+culture method,84
+rcas vector,84
+vonsattel grade,84
+responder,84
+tissue/treatment id,84
+overexpression,84
+survival time in months,84
+host genotype,84
+instance,84
+tissue compartment,83
+alias,83
+virus infection,83
+cell line background,82
+latent tb status at blood draw,82
+experiment label,82
+infectious challenge,82
+draw day,82
+viral status,82
+average tagmented library size,82
+prophylaxis,81
+e64-treatment,81
+donor_type,81
+dissolved oxygen,81
+integrative analysis,81
+pool no,81
+3' adapter sequence,81
+healthy control,81
+cell density,81
+subclass,80
+simulation,80
+cdkn2a methylation,80
+correctedtod,80
+causeofdeath,80
+pten methylation,80
+idh mut status,80
+mannerofdeath,80
+tobaccoatod,80
+tissuestoragetime_month,80
+bloodtexicology,80
+rpf_rin,80
+exercise intensity,80
+avgph,80
+tp53 seq,80
+egfr amp,80
+p-pras40 ihc,80
+timeofdeath,80
+pten del,80
+pdgfra ihc,80
+exposure condition,80
+number of cells,80
+animal identifier,80
+control/intervention,80
+medicationsatodc,80
+rtsq30,79
+umiq30,79
+pkc file,79
+adapter sequence,79
+specimen site,79
+expression,79
+challenge,79
+folder name,79
+infectious_dose,79
+library id,79
+panel,79
+relapse time,79
+primary recurrent,79
+infected host,79
+bacterial strain,79
+fracture site,78
+cell number,78
+gfap status,78
+patient identifier,78
+mib,78
+treatment2,78
+tumour,78
+bcg state,78
+age patient,78
+viral family,78
+stage of repair process,78
+viral genus,78
+covid infection_status,77
+lentivirus,77
+karyotype,77
+culture days,77
+geo expression data,77
+biopsytime,77
+covid severity_status,77
+tissue group,77
+sentrix.id,76
+bacterial infection,76
+desease state,76
+steroids_cat,76
+averageage,76
+nasal_steroids,76
+any_immune,76
+treatment status,76
+surgery type,76
+averagebodymassindex,76
+cancer stage,76
+steroids_daily_pred_mg,76
+immune_or_nasal,76
+huntingtondiseasestatus,76
+source tissue,76
+vdi,76
+smoking_status,76
+smoking_pkyrs,76
+host strain,76
+blood island injection at 28 hpf,76
+rna population,76
+c4 = egpa,76
+replicate / experiment,75
+infection duration,75
+minimum counts per cell threshold used to remove background barcodes,75
+lesional (ls) vs. nonlesional (nl) vs. normal,75
+bvas,75
+post-mortem delay,75
+peptide,75
+preservation method,75
+genotype/varaition,75
+number of pooled individuals,75
+indrops version,75
+pool id,75
+infection state,75
+library index sequence used to demultiplex,75
+minimum reads per cell during initial processing,75
+cell lines,75
+ClinicalInformation,75
+spike-ins,75
+bone-marrow grafting type,74
+bone-marrow grafting status,74
+parental tumor subtype,74
+perturbation/epigenome editor,74
+clinical outcome,74
+sample plate,74
+growth stage,74
+lung log10cfu,74
+mouse line,74
+tp53,74
+radiation,74
+activation agent,74
+ear treatment,74
+sequeneced tissue name,73
+tb-status,73
+injected virus,73
+preliminary diagnosis,73
+Type,73
+injection site,73
+experimental status,72
+clinical indication,72
+patient identification number,72
+sentrix_id,72
+b. pertussis strain,72
+sort population,72
+transgenic line,72
+therapy,72
+tcm syndrome,72
+hd genotype,72
+batch of sequencing,72
+sentrix_position,72
+metastasis site,72
+variant type,72
+b. pertussis year of isolation,72
+vzv antigen,71
+treatment 1,71
+storage,71
+sample description,71
+compound,71
+primary tumor site,71
+gca,71
+tumor contact with subventricular zone yes/no,71
+nf1 inheritance,70
+facial dysmorphism,70
+scoliosis,70
+lisch nodules,70
+microdeletion sub-type,70
+cutaneous neurofibromas,70
+subcutaneous neurofibromas,70
+skin-fold freckling,70
+host mice strain,70
+passage of pdx,70
+tags,70
+originial tumor id,70
+plexiform neurofibromas,70
+parental origin,70
+glioma,70
+fetus,70
+rna isolation kit,70
+igm,70
+cxcl11_12,70
+learning disabilities,70
+anatomical location,70
+cxcl12,70
+donor covid_status,70
+rna extraction_protocol,70
+biological drug,70
+ackr3,70
+embryo,70
+age at initiation,70
+lesional (ls) vs. normal,69
+mrna-seq reads,69
+trasplant donor origin,69
+Genetic background,69
+Lymph node involvement,69
+ezh2 mutation,69
+Degree of differentiation,69
+dpi,69
+treatment_timeline,69
+compartment,69
+alcohol,69
+host vendor,69
+host strain/background,69
+Histological type,69
+fl grade,68
+primary_recurrent,68
+idh_mutation,68
+mouse selection,68
+structure,67
+steroid,67
+restriction enzymes,67
+day blood taken,67
+vs type,67
+ebv.status,66
+clinically_aggressive,66
+lf,66
+histological.type,66
+ann arbor stage,66
+prior_surg,66
+number of immunization boost,66
+prior_rt,66
+mnp_score,66
+mnp_classifier,66
+postop_growth_rate_percentyr,66
+backbone,66
+eor,66
+preop_growth_rate_percentyr,66
+lffp,66
+tissue status,66
+genetic variants,66
+modulation mg,66
+stabilized with,66
+sampling.time,66
+chip epitope,66
+day cfu measured,66
+size,66
+control or als,65
+derivation,65
+kit/pdgfra mutation site,65
+metastatic tumor site,65
+cell markers,65
+risk,65
+tumor histology,65
+hpi,65
+malaria infection,65
+response to eribulin,65
+treatment_duration,65
+treatment 2,65
+kit/pdgfra mutation type,65
+kit dna_extraction,65
+iPSc clone name,65
+id simple,64
+tumor localisation,64
+cag repeat size,64
+hadzi-vonsattel striatal score,64
+geo_sample_id,64
+clinical trial phase,64
+methylation_geo_id,64
+idontma,64
+id sample,64
+vector treatment,64
+severity_score,64
+roilabel,64
+fetalgender,64
+covidstatus,64
+harvest time,64
+sequencing method,64
+cnccs derived from,64
+lesion_size,64
+previous drug treatment,64
+rounds_to_cure2,64
+age at time t0 in years,64
+library_batch,64
+rounds_to_cure,64
+antibodies,64
+hadzi-vonsattel cortical score,64
+immune border,64
+lesion_label2,64
+dth,64
+roi type,64
+ki67 percentage,64
+cytology,64
+ivygap,64
+infiltration,64
+genes mutated for this sample from patient,64
+presence_of_parasites_lesion,64
+days_after_pcr,64
+with_lesion_sample,64
+lesion_label,64
+ki67,64
+parasite_numbers_lesion_qpcr,64
+lesion_disease_factor,64
+lib size,64
+lymphocyte_count,64
+total skin score,64
+serum vitamin d <15ng/ml,64
+lobe,64
+living paired biopsies,64
+dth_mm2,64
+illness_duration,64
+comments,64
+enrichment method,63
+minutes of mrna decay,63
+library prep person,63
+overall.survival.time,63
+days post infection,63
+rna sample number,63
+ref id,63
+ifih1-rs1990760,63
+genotype/strain,62
+vaccine administered,62
+surgical treatment,62
+antibody group,62
+extraintestinal manifestations,62
+other biologic medicines use,62
+azathioprine use,62
+rectal mesalazine use,62
+stool frequency,62
+life stage,62
+number of_mice,62
+carbon source,62
+glucocorticoids use,62
+oral mesalazine use,62
+date sampled,62
+sulfalazine use,62
+bleeding,62
+collection day,62
+deleted_gene,62
+time in culture,62
+aspiration site,61
+ethinicity,61
+patient_no,61
+source cell type,61
+time of sample collection,61
+tcr repertoire,61
+infection type exposure,61
+infected with sars-cov-2,61
+clinical presentation,61
+cag repeats,60
+pediatric patient,60
+tcr,60
+tissue/cell info,60
+ras score,60
+angiogenesis score,60
+p53 score,60
+egfr score,60
+sample name in supplementary file,60
+prodromal status,60
+dystonia,60
+duration of infection,60
+casegroup,60
+cartridge,60
+subject age,60
+labeling agent,60
+bru labeling time,60
+alive,60
+time between bru labeling and rna extraction,60
+rapamycin treated,60
+seks,60
+ifn type,60
+Case,60
+primary tumor,60
+rna_integrity,60
+Subsets,60
+time after bcg vaccination,60
+fvc less than 70,60
+eosinophils,60
+stimulated with b . pertussis,60
+stage,60
+pertactin genotype,60
+days after stimulation,60
+csp,60
+vector constructs,60
+corrector,60
+dyt1 mutation status,60
+pathogen exposure,60
+viral challenge,60
+agvhd developed,60
+mapped te_cell line info,60
+Grading of acute GVHD,60
+SEX,60
+patient no,60
+coo,60
+rnaextractedfrom,59
+apoe genotype,59
+covid status,59
+sorted cell_type,59
+fvc predicted,59
+sandwich type,59
+biofluid,59
+gene deletion status,58
+survival year,58
+types,58
+cells detected,58
+tissue derivation,58
+pcr status,58
+endotype,58
+malaria retinopathy,58
+respirations per minute,58
+cycling,58
+library input,58
+location of lesion,58
+experimental condition,58
+replicates,58
+local skin score,58
+mrss,58
+subtypes,58
+mouse age,57
+alternative sample name,57
+culture platform,57
+treatment outcome,57
+time after infection,57
+endpoint,57
+lesion status,57
+treatment/timepoint,57
+library-type,57
+mutation class,57
+experimental set,57
+rabbit group,57
+modifications,57
+induction,57
+patient response,57
+rabbit id,57
+sampling site,57
+tissue collection,56
+plasmid,56
+symptoms,56
+primary/metastasis,56
+fas ligand level,56
+3 = severe changes,56
+malignant tumor,56
+dlco predicted,56
+study_id,56
+lymph node number,56
+commercial source,56
+grwoth condition,56
+topography,56
+glioblastoma subtype,56
+eae scores,56
+age and disease,56
+data tissue_collection,56
+sequencing id,56
+debris removal,56
+cough,56
+developemental stage,56
+dyspnea / tachypnea,56
+publication id,56
+copd,56
+fever,56
+sars-cov-2 genomes / 10^6 rnasep copies,56
+3 = numerous,56
+3 = fibrotic,56
+cvrf,56
+i7 index,56
+cag length,56
+pfspz dose,55
+disease model,55
+Sample ID,55
+gpi,55
+exitus,55
+year of isolation,55
+Differentiation Method,55
+upper or lower extremity,55
+family_history,55
+tuchmi id,55
+volar or non-volar,55
+parental line,55
+growth pattern,55
+tuberculosis_history,55
+mdm genotype,54
+sofa score,54
+copy number gain,54
+timepoint_description,54
+laboratory strain,54
+organ system,54
+match degree,54
+sort strategy,54
+clinic status,54
+primary mutation,54
+initial tumor increase/(-)decrease,54
+gvhd stage,54
+age at blood collection,54
+perturbation,54
+perturbation class,54
+library version,54
+ribosomal rna depletion strategy,54
+mdm donor,54
+kit mutation,54
+organoid line,53
+collected_by,53
+platform,53
+thymalfasin treatment,53
+age at surgery,53
+FISH origin,53
+EBV,53
+rna sample,53
+granuloma,53
+cfu,53
+samples of different individuals pooled,53
+als mutation,53
+sample/subject id,53
+rna extraction method,52
+route administered,52
+sporozoite age,52
+psoriasis duration,52
+genetic specifics,52
+Genotype,52
+pregnancy,52
+isolation method,52
+sars-cov-2 genotype,52
+biological_replicate,52
+reason for intubation,52
+tumor size,52
+30 day mortality,52
+igg used for ip,52
+egfrviii statue,52
+hispanic ethnicity,52
+brain metastasis,52
+cross-linked,52
+lrti pathogen,52
+lrti type,52
+vehicle,51
+oxygen percentage,51
+tumor_grading,51
+infection strain,51
+day of tissue harvest,51
+last follow-up,51
+lymph node,51
+cut&tag antibody,51
+days_to_tb,51
+extract_protocol,51
+organism_status,51
+dosage 1,51
+dosage 2,51
+tumor side,51
+treatment stage,51
+organism_part,51
+clinical_history,51
+recipient strain,51
+specific heart region,51
+age/gender,51
+cerebral performance category score,50
+injury/age,50
+Mouse ID,50
+strain info,50
+health_status,50
+rna,50
+study number,50
+anti-retroviral therapy,50
+metastatic site,50
+age in_yrs,50
+biosourcetype,50
+other organ lesion,49
+ago protein,49
+mtb strain,49
+parental cell line,49
+decrease of vision,49
+mutations,49
+bar code,49
+swollen eyelid,49
+sex/age,49
+idh mutation,49
+tumor source,49
+diplopia,49
+hours_post_infection,48
+treatment category,48
+block in gpr file,48
+treatment_time,48
+facs marker,48
+subject gender,48
+treatment_duration_in_hours,48
+sample/time point,48
+slide tissue area,48
+day post-infection,48
+260/280,48
+260/230,48
+rna integrity score,48
+kit,48
+replicats,48
+stem cell,48
+onset site,48
+resistance to hiv-1 following ifn treatment,48
+alsfrs,48
+anti-jo1 status,48
+scan method,48
+group label,48
+sample prep,48
+tisuue type,48
+mosquito,48
+experiment batch,48
+batchid,48
+subbatchid,48
+librarytype,48
+sequencingrunid,48
+experimental day,48
+infection statut,48
+conditions,47
+conditioning received,47
+dissected embryo id number,47
+symptons,47
+age fracture,47
+tumorsphere,47
+syndrome,47
+cjd subtype,47
+treament,47
+treatment prior to second surgery,47
+relapse,47
+isolation,47
+sample name_2,47
+codon 129,47
+proximal sars-cov-2 nucleocapsid protein,47
+diesease status,47
+graft source,47
+title_2,47
+cell surface marker,47
+processing batch,46
+tnf,46
+bw loss in 6 months prior to surgery,46
+run id,46
+monocytes_count,46
+littermate,46
+parasite density on admission,46
+person,46
+rna label,46
+surface marker,46
+lane id,46
+mean.corpuscular.volume,46
+ethnic group,46
+BREAST,46
+developmental stage/tissue,46
+lymphocytes_count,46
+sample id cat,46
+plasma epo ria,46
+mip1-beta,46
+total bilirubin,46
+derived from,46
+parental strain,46
+biol. repl,46
+il-1b,46
+hiv screen,46
+rbc.distribution.width,46
+plasma pfhrp2,46
+lifetimechronicandoracuteatodinfectiousorinflammatorydiagnosis,46
+patient/control id,46
+mip1-alpha,46
+hb genotype,46
+mcp-1,46
+plasma ho-1,46
+ifn-gamma,46
+to concatenate,46
+rna fraction,46
+2h alt,46
+ip-10,46
+il-12 p70,46
+over-expression,46
+il-8,46
+il-6,46
+systemic sclerosis subtype,46
+il-1ra,46
+neun,46
+wbc.count,46
+neutrophils_count,46
+il-10,46
+cov-2 variant,45
+immunosuppression,45
+day 28_agvhd_response,45
+fvc %predicted,45
+type of library,45
+vaccine administration,45
+cell surface markers,45
+severity binary,45
+inoculation,45
+tissue acquisition,45
+severe_eosinophilia,45
+subject/sample source id,45
+active_disease,45
+radiation sensitivity,45
+cell line / strain,45
+major_organ_involvement,45
+differeniation stage,45
+digestives_symptoms,45
+temozolomide sensitivity,45
+host cell line,45
+patient sample,45
+tumour size,45
+days post-infection,45
+serologic response status,45
+bcl2.break,45
+bcl6.break,45
+modality,44
+relative sox9 level,44
+cell/tissue type,44
+clinical phenotype details,44
+translocation,44
+ct value,44
+sample_nhp_id,44
+time of sampling,44
+intervention group,44
+donor-nhp_id,44
+growth type,44
+receptor status,44
+total rna source,44
+vendor,44
+tumour site,44
+host organism,44
+survival group,44
+histological grade,44
+histone mark,44
+strain source,44
+IL6,43
+VCAM1,43
+condition 1,43
+differentiation status,43
+Lymphotactin,43
+Tissue Factor,43
+condition 2,43
+TGFa,43
+days ill,43
+nutritional state,43
+TNFa,43
+subject's disease state,43
+hf concentration,43
+prior chemotherapy,43
+collection date,43
+cell type neun status,43
+day of collection,43
+kg,43
+P-selectin,43
+temp,43
+maternal age,42
+Donor type,42
+experimental variables,42
+length of exposure,42
+days post exposure,42
+days post_infection,42
+IL12p70,42
+age and_strain,42
+progerin,42
+antibody treatment,42
+h. bilis infection,42
+average gic50,42
+IL15,42
+main group,42
+rnase,42
+derived from hesc or ipsc,42
+properties,42
+time post-vaccination,42
+HLA match,42
+state of culture,42
+subclone,42
+injection,42
+Conditioning,42
+IL10,42
+Followup,42
+GVHD stage Skin-Liver-Gut,42
+number cag repeats,42
+differentiation time,42
+specificity,42
+markers used for sorting,42
+Cluster,42
+age years,42
+baseline fvcpp,42
+baseline fevpp,42
+Blood drawn post BMT,42
+sample date_yyyymmdd,42
+lentiviral infection,42
+age/disease timepoint,42
+tissue subtype/brodmann area,41
+fusion,41
+er status,41
+post-treatment day,41
+Disease,41
+l. pneumophila infection,41
+cpg island methylator phenotype (cimp) subgroup,41
+her2 status,41
+pr status,41
+tumor/control,41
+anti-pd1-therapy,40
+repeated samples,40
+sample.name,40
+hemolysis score,40
+overall.survival,40
+batch_id,40
+collection,40
+oxygen flow,40
+treatments,40
+transfection experiment,40
+source cell,40
+injected lentivirus,40
+gel_bead_version,40
+sequencing_method,40
+passaged in,40
+days post-prime,40
+disease phase,40
+patient reference,40
+nicotine,40
+patient id no,40
+microenvironment,40
+percentage of tumor cells,40
+m. tuberculosis strain,40
+sample condition,40
+who class,40
+clinical.diagnosis.history,39
+dcodewk,39
+diagnosis_descriptcion,39
+amyloid,39
+braaklb,39
+pmd,39
+profession,39
+neuropathological.information,39
+wcode,39
+ab_score,39
+age at biopsy date,39
+freezer,39
+ocode,39
+specific,39
+tau_score,39
+dcodeprot,39
+immnosuppressive,39
+csf,39
+"normal individual, Tissue",39
+autopsy,39
+nbb,39
+dcode,39
+2021 classification,39
+cause.of.death,39
+qualifying condition,39
+pten.mutation,39
+egfr.mutation,39
+tp53.mutation,39
+pdgfra.amplification,39
+uniprotkb id,39
+radiation exposure,39
+cdkn2a.2g.loss,39
+lentiviral vector,39
+egfr.amplification,39
+tumor.grade,39
+days post challenge,39
+sample pool,39
+pipeline.version,39
+clofazimine treatment,39
+tisue/cell type,39
+experimental repeat,39
+idh.status,39
+construct,38
+hereditary status,38
+ighv status,38
+Virus Strain,38
+isocitrate dehydrogenase 1 status,38
+tissue type analyzed,38
+ev genotype,38
+data file subset,38
+experimental batch,38
+ev donor,38
+histological response,38
+sample_time,38
+rna subtype,38
+isogenic_group,38
+host cell type,38
+postsurgical-treatment,38
+imatinib responder,38
+cells_loaded,38
+mgmt.status,38
+nulliparous,38
+labor,38
+deliveryroute,38
+resection,38
+genomic modification,38
+pooled,38
+xenograft source,38
+meningioma type,37
+sf,37
+paired with,37
+tumor vs. normal,37
+BRCA1/2 mutation,37
+perturbation type,37
+Cycle,37
+workflow,37
+Family History,37
+Cell type,37
+antibody catalog number,37
+library_generation_pcr_number_cycles,37
+library_generation_pcr_polymerase_type,37
+library_generation_pcr_product_isolation_protocol,37
+Source,37
+library_generation_pcr_thermocycling_program,37
+donor no,37
+library_generation_pcr_primer_conc,37
+translocation status of ccnd2,37
+cdca7l expression,37
+drug concentration,37
+mating type,37
+exptl time,37
+virus-stimulation,37
+library prep kit,37
+library_generation_pcr_f_primer_sequence,37
+data type,37
+sample case,37
+library_generation_pcr_r_primer_sequence,37
+skin anatomy,36
+medicine,36
+maximal prior disease extend,36
+tw culture results,36
+time post-treatment,36
+indication,36
+viral infection,36
+primary cells,36
+conditional ly6e knock-out,36
+locale,36
+parasite,36
+disease diagnosis,36
+relation to individuals with wd,36
+ki67.score,36
+subject label,36
+irf4/mum1.expr,36
+individuals,36
+tagid,36
+l.pn infection,36
+tagseq,36
+tna extraction_method,36
+hours of infection,36
+clone id,36
+subject id/diagnosis,36
+endoscopic mayo score,36
+clinical information,36
+duration in hours,36
+inhibitor removal,36
+location type,36
+antibody catalog/vendor,36
+lc status,36
+cd10.expr,36
+myc.break,36
+batch number,36
+irf4 genotype,36
+miRNA,36
+experimental,36
+timepoint_in_hours,36
+library preperation date,36
+transl,36
+environment,36
+ln involvement,36
+Mouse model,36
+extranodal,36
+growth time mins,36
+first-line therapy,36
+day transplantation,36
+number of replicates,36
+barcoded replicate,36
+water salinity,36
+clinical group,36
+organ obtained,36
+rna-extraction date,36
+ipi,36
+sample from primary gbm diagnosis,36
+developmental stages,35
+flow cytometry cell subset proportions,35
+brodmann area,35
+biopsy vs surgical resection,35
+btic id,35
+person id,35
+nonunion type,35
+host_cell_line,35
+MALT1 Tx,35
+donation source,35
+contiguous with mpnst,35
+hours post fertilization,35
+labversion description,35
+primary vs metastatic,35
+scorad,35
+Age of Onset,35
+strain  background,35
+years of disease,35
+nf1 diagnosis,35
+Age at interview & blood sampling,35
+family history of nf1,35
+Twin Pair ID,35
+Clinical Status,35
+cre,35
+culture age,35
+experimental design,35
+pulldown,35
+TNM stage,34
+Age at time of surgery,34
+Packyears,34
+dna_preparation_adaptor_sequence,34
+untreated/treated,34
+characterstics,34
+Location of distant metastasis,34
+dna_preparation_post-ligation_fragment_size_selection,34
+Type of Surgery,34
+bisulfite_conversion_percent,34
+dna_preparation_fragment_size_range,34
+conditioned media origin,34
+treated stem cells,34
+library_generation_pcr_template_conc,34
+tandem repeat number,34
+Metastases,34
+Location tumor,34
+dna_preparation_initial_dna_qnty,34
+dna_preparation_adaptor_ligation_protocol,34
+Tumor type,34
+bisulfite_conversion_protocol,34
+eae status,34
+method of preservation,34
+Dead/Alive,34
+COPD,34
+cell tye,34
+asbestos-fiber count,34
+morphotype,34
+day of isolation,34
+FEV1,34
+body site,34
+reprogramming method,34
+disease subset,34
+time_point,34
+conditioned media type,34
+dexamethasone status,34
+Sample code,34
+Tissue type,34
+GOLD stage,34
+p53 Model,33
+gene,33
+genetic variants inheritance,33
+bedaquiline dose,33
+treatment_gefitinib,33
+alternative_name,33
+total volume,33
+infectious,33
+cell treatment,33
+srcap crispr edit,33
+h2a.z crispr edit,33
+sars-cov-2 strain,33
+definite analysis,33
+age at collection,33
+parasite isolate,33
+growth conditions,33
+time post initiation of treatment,33
+chip-antibody cat,33
+core code,33
+sputum smear status,33
+induce ifnβ,33
+gdnf-stimulated,33
+chip-antibody vendor,33
+viral infected,33
+hrs post cpgb stimulation,33
+name_in_pmid_21471286,33
+extract protocol,33
+clinical phenotypes,33
+isolate sensitivity,33
+tretment,33
+transposase,32
+disrupted gene id,32
+virus accession number,32
+animal number,32
+zygosity,32
+nhp id,32
+alzheimers status,32
+plasmodium strain,32
+cultivation,32
+twins,32
+KIT mutation,32
+plasmodium falciparum infection status,32
+infection type,32
+tb_status,32
+diffuse/limited,32
+age post-hatch,32
+uv irradiation,32
+virus taxon id,32
+water type,32
+hiv_status,32
+time after treatment (and reversal) in hours,32
+tetracycline,32
+adt/hto,31
+sgrna pool,31
+paired patient,31
+single or double infection,31
+lymphoma subtype,31
+iPS,31
+age at time of collection,31
+gbm classification,31
+antibody status,31
+study sample number,31
+chl subtype,31
+treatment before challenge,31
+maternal health status,31
+Cell line,31
+cell line name,31
+b cell type,31
+gestational stage,31
+gvhd status,31
+age fraction,31
+treatment/passsage,31
+sample beneath,30
+single or double infected,30
+viral concentration,30
+pna,30
+induction time,30
+virus added,30
+normal vs covid-19,30
+tissue from postmortem or living patient,30
+line name in manuscript,30
+age of pregnant women,30
+neural tube defect,30
+tcell type,30
+source cell line,30
+age at skin biopsy,30
+derived cell line,30
+cell line/type,30
+vaccinated,30
+tumor tissue source,30
+cell passage,30
+rna prep,30
+pre-treatment,30
+lentiviral mediated overexpression,30
+pretreatment time,30
+biopsied region,30
+schedule,30
+Time after induction,30
+tumor organ site,30
+pathological diagonosis,30
+biogroup,30
+transgene1,30
+transgene2,30
+preparation method,30
+differentiation state,30
+phenotypes,30
+library barcode,30
+Medication at blood sampling,30
+knock-in line,30
+post-operative day,30
+rsk1 protein group,30
+sampling point,30
+beadchip section,30
+tw serology results,30
+beadchip barcode,30
+tb strain,30
+brain section,30
+test,30
+spikeinpool,30
+rifapentine (10mm) treated,30
+p. berghei anka-infected,30
+sequencing run / batch,30
+cell culture condition,30
+cell-type,30
+estimated sample purity,30
+"gender,age, tissue type",30
+vaccinated status,30
+fresh frozen (ff) or ffpe,30
+note_other,30
+a260/a280 ratio,30
+rifampin (10mm) treated,30
+p53_status,30
+chemical treatment,30
+parental-strain,30
+promoter,30
+microarray hybridization date,30
+status of disease 5 years,30
+egfr variant,30
+primary_recurrence,30
+no treatment,30
+rifabutin (10mm) treated,30
+knockout status,30
+vehicle (methanol at 0.0025%) treated,30
+treatment_effect,30
+growth time,30
+subject 2 gender,29
+th-mycn mouse genotype,29
+subject 2 age,29
+treatment concentration,29
+cf diagnosis,29
+creatinine,29
+μg cy3 probe hybridized,29
+strain origin,29
+icu_los,29
+los,29
+leukocyte,29
+chip antibody catalog,29
+lymphocytes,29
+subject 2,29
+skin score done by mdm,29
+subject 1 age,29
+subject 1 gender,29
+subject 1,29
+pmol cy3/μg crna,29
+tumor cell line,29
+pseudomonas infection,29
+in vitro or in vivo,29
+infection route,29
+age at examination,29
+geographical origin,29
+clinical_subgroup,29
+immunosuppressors,29
+affected status,29
+procalcitonin,29
+billirubin,29
+sbp_worst_24h,29
+lactate,29
+imatinib naive/resistant,29
+derived from metastatic site,29
+qsofa_admission,29
+qsofa_cat,29
+sofa_baseline,29
+cell cycle stage,29
+microorganism_source_of_infection,29
+mitotic activity,29
+kit expression,29
+cd4 t-cell_count,29
+wga platform_id,29
+gbm subtype,29
+cd69 status,29
+Pathogen,29
+cd117 status,29
+sofa_admission,29
+gcs_worst_24h,29
+microorganism_blood,29
+fio2_worst_24h,29
+spo2_worst_24h,29
+gentype,29
+other_comorbidities,29
+temp_worst_24h,29
+dbp_worst_24h,29
+map_worst_24h,29
+rr_worst_24h,29
+hr_worst_24h,29
+pao2_worst_24h,29
+ltbi status,28
+pulmonary.disease,28
+irc,28
+hta,28
+chip anitbody,28
+tobacco,28
+mv,28
+time infected,28
+cancer.past,28
+zika mcherry reporter status,28
+fb-pmt treatment,28
+psiquiatric,28
+dev_stage at treatment initiation,28
+culture status,28
+active cancer,28
+sum.risk.factors,28
+age at rna isolation,28
+cardiovascular.disease,28
+polyq length,28
+hepatopaty,28
+Ethnic group,28
+donor status,28
+psoriasis area-and-severity index,28
+rin value,28
+genetic modifications,28
+experimental factor,28
+plate code,28
+growth temperature,28
+study protocol,28
+skin phenotype,28
+spike-in organism,28
+jkr-0937 group,28
+nf2 association,28
+bone marrow mononuclear cells sorted from,28
+number of individuals per sample,28
+biopsy collection date,28
+stress condition,28
+incubated with,27
+psoriasis subtype,27
+cell stage,27
+lung radiation dose,27
+cell type source,27
+additional cell lineages present in dataset,27
+transfection time,27
+participant condition,27
+sampling location,27
+participant 2_sex,27
+tissues,27
+participant 2_food_allergy_status,27
+rna_seq_protocol,27
+participant 2_id,27
+participant 1_food_allergy_status,27
+participant 1_sex,27
+participant 1_id,27
+cd44,27
+cxr findings,27
+qft-git,27
+pulmonary compartment,27
+specific primer,27
+sort fraction,27
+intubation_days,27
+interval_death_symptoms_onset_days,27
+pmi_h,27
+h3.3_status,27
+tagtreatment,27
+follicular lymphoma grade,27
+run,27
+culture results,27
+series,27
+ifn-a2b,27
+haematological tumor,27
+participantid,27
+mappedreads,27
+klrg1 marker,27
+5' race primer+adapter,27
+hospitalization,27
+median cv,27
+Age of patient,26
+Duration of psoriasis,26
+pfs.days,26
+pfs.status.censorship,26
+time since sclerosis,26
+Patient identifyier,26
+time since transplant,26
+Overall erythema,26
+Body surface area,26
+culture stage,26
+Induration,26
+donor group,26
+degree of infiltrate,26
+primary cell line,26
+Transgene,26
+Passage,26
+pdxs,26
+previous severity,26
+clone phenotype,26
+clinical,26
+acute skin gvhd,26
+oncologic diagnosis,26
+sclerotic bsa,26
+scd+asthma,26
+skin score,26
+time point days,26
+scd,26
+sample.type,26
+variant,26
+cell samples,26
+cel line,26
+pair.nr,26
+initial p. aeruginosa isolate source,26
+rna extracted from,26
+pfs.time.month,26
+Scaling,26
+gender source,26
+time designation after sclerosis,26
+prior systemic therapy,26
+current pred dose,26
+current systemic therapy,26
+other cgvhd,26
+harvesting,26
+arrayrun,25
+collection_date,25
+ectopic expression,25
+body part,25
+clincal phenotype,25
+twin status,25
+ebv,25
+develpmental stage,25
+death_time,25
+strain/isolate,25
+pathological type,25
+hx_of_gvhd,24
+develomental stage,24
+Construct,24
+shRNA depletion type,24
+pharmacologic treatment type,24
+cell or tissue type,24
+hours of mrna decay,24
+ex vivo infection,24
+interaction status,24
+disease course,24
+aso concentration,24
+rna extraction_method,24
+disease onset,24
+Mouse strain,24
+tert expr,24
+time post_injury,24
+pdc.dtr,24
+pair status,24
+hdh genotype,24
+mouse dietary condition,24
+extract,24
+isrib concentration,24
+differentiation_age,24
+percent_aligned,24
+treatment condition/type,24
+dif,24
+exogenous gene expressed,24
+total rna input,24
+cell preparation,24
+gametocyte status,24
+biological_replicate_number,24
+technical_replicate_number,24
+os_group_median,24
+os_days,24
+date_lastimaging,24
+embryonic day,24
+date_lastfu,24
+date_death,24
+library outgrowth conditions,24
+ercc mix,24
+time post-infection,24
+tumor_size,24
+tumor identifier,24
+idh1_mut,24
+mgmt_methyl,24
+blood island injection,24
+date_dx,24
+cd8 t-cell_count,24
+starting cell,24
+harvest time post treatment,24
+resection_type,24
+spinal cord region,24
+wilms tumor sample,24
+hours post-infection,24
+monocyte,24
+anatomical site,24
+ghd,24
+channel type,24
+days post treatment,24
+seq_index,24
+hyb number,24
+4c viewpoint,24
+tissue subgroup,24
+multiseq barcodes_per_sample_group,24
+clone type,24
+time post treatment,24
+5' adapter ligation method,24
+pathogen strain,24
+pouchitis diagnosis,24
+cell line/tissue source,24
+cell line/tissue,24
+implantation,24
+fip status,24
+biological replicates,24
+cfu delivered,24
+mouse exhibiting symptoms on the day of sample collection,24
+full-length cdna enrichment,24
+ibmec differentiation media volume,24
+parental/reprogrammed state,24
+array id,24
+cytokine exposure,24
+sequencing_day,24
+cd133,24
+date timepoint 1 month post-booster,24
+sorted cell type,24
+lymphocyte,24
+organoid status,24
+peakgh mcg/l,24
+sex steroid priming,24
+experimental reapeat,24
+rv1963c induction state,24
+morphologic form,24
+estimated age,24
+subect status,24
+nf1-affectation status,24
+sampling time point,24
+date 2nd dose bnt162b2,24
+day of collection/passage,24
+date timepoint 3 months post-booster,24
+date 1st dose bnt162b2,24
+oerturbation type,24
+vasopressor,24
+environmental condition,24
+co-culture,24
+sequencing_chip,24
+mortality,24
+molecular condition,24
+covid-19 viremia diagnosis,24
+covid-19 titer,24
+age at timepoint 0,24
+date timepoint 6 months post-booster,24
+tumor sample,23
+comorbidity,23
+passage post cre infection,23
+molecule source,23
+drug administration,23
+maternal disease status,23
+histological subtype,23
+iPSc source,23
+peripheral blood,23
+medical history,23
+sex predicted,23
+os months,23
+donor line,23
+cell dissociation,23
+sepsis stage,23
+p. amoebophila strain,22
+tumor_site,22
+cells/condition,22
+a. castellanii strain,22
+odn,22
+overexpression vector,22
+injected with,22
+associated primary tumor no,22
+metastatic status,22
+l. pneumophila strain,22
+oxygen level,22
+generation,22
+race_ethnicity,22
+de-identified research code,22
+other treatment,22
+strand,22
+cfu group,22
+htt status,22
+replicate type,22
+flowcell id,22
+in vitro transduction,22
+duration of treatment,22
+eae clinical_score,22
+viral rna detected,22
+cut&run antibody,22
+immunophenotype,22
+decode_name,22
+Sample Group,22
+IT15 CAG repeats,22
+fever day,22
+1p/19q,22
+pre-operation radiology,22
+sample status,22
+organism,22
+treatment effect,22
+antibody vendor/catalog,22
+disease condition,22
+modification,22
+respiratory score,21
+somatic mutation,21
+gfp intensity,21
+chemical probe,21
+section nr,21
+antibody target description,21
+htt genotype,21
+genotype/variatation,21
+antibody vendor name,21
+generation/colony,21
+stimulated with,21
+corticosteroids treatment,21
+prbid,21
+illumina index number,21
+developed metastases or not,21
+growth medium/treatment,21
+Karyotype,21
+patient's gender,21
+rna substrate investigated,21
+patient's clinical presentation,21
+hippocampal slice id,21
+electrophysiology,21
+si rna,21
+cultured glioblastoma sample,21
+donor strain,20
+Sample,20
+RIN1,20
+enrichment,20
+vaccination state,20
+At Risk,20
+gant-61 sensitivity,20
+MaternalAge,20
+Parity,20
+StudyID,20
+sars-cov-2 ihc,20
+InfantSex,20
+arthritis,20
+human sci,20
+ba8s18s,20
+glioma model,20
+erythema nodule,20
+who_type_07,20
+Biomaterial,20
+cell transduction,20
+HT29 cells were transfected with siRNA (according to treatment protocol). siRNA,20
+cell marker,20
+lot number,20
+molecular subtype/phenotypic state,20
+human tissue source,20
+Shear exposure,20
+calcium level,20
+oral ulcer,20
+genital ulcer,20
+multimer,20
+ocular involvement,20
+vascular involvement,20
+cns involvement,20
+ba_rin,20
+gastrointestinal involvement,20
+clinpathdx,20
+RNAi treatment,20
+h-v cortical score,20
+sorting,20
+Chief Disease,20
+Order Code,20
+Sample Type,20
+tumoral content,20
+status sample,20
+viral copies/mg tissue,20
+ki67 proliferation marker,20
+infection_state,20
+sox11 status,20
+Post Mortem Interval,20
+samples,20
+Treatment,20
+harvest dpi,20
+h-v striatal score,20
+patient line,20
+Death Cause,20
+virus subtype,20
+xenograft donor id,20
+fed with,20
+Cause of Death,20
+sars-cov-2 innoculation dose,20
+chip processing date,20
+Brain pH,20
+eae day,20
+xenograft pair,20
+injection age,20
+Inflammation,20
+pepd status,20
+type of death,20
+assessement of tissue quality,20
+animal id number,20
+aav vector,19
+ki67 proliferation index,19
+carcinoid syndrome,19
+disease outcome,19
+duration of untreated disease in month,19
+age at onset,19
+radically operated,19
+cold ischemia time,19
+donation time,19
+g207 treatment,19
+strains,19
+drug response,19
+tumor origin,19
+genetic engineering,19
+desiccation,19
+library kit,19
+timepoint_progressors,19
+number of htt polyq repeats,19
+facs-sort criteria,19
+treatment_type,19
+time of treatment,19
+isolation stage,19
+tumor model,19
+sort purification strategy,19
+time point post infection,19
+mni_z,19
+mni_x,19
+brodmann areas,19
+categories_progressors,19
+mni_y,19
+fus aggregation state,19
+tspo cluster,18
+overall survival,18
+radiology,18
+chronic htn,18
+chromosome 22 monosomy,18
+febrile seizure,18
+donor race,18
+culture format,18
+experimental variable,18
+nb differentiation degree,18
+injury model,18
+menstrual phase,18
+sort-gate,18
+chip-seq condition,18
+wt allele cag repeat number,18
+expression construct,18
+medip antibody,18
+date of array hybridisation,18
+culture batch,18
+age of disease onset percentile,18
+age of disease onset,18
+experiment grouping,18
+hd allele cag repeat number,18
+reference epigenome spike-in,18
+sentrix row,18
+infection host,18
+samplegroup,18
+years with hd,18
+mechanical condition,18
+tocilizumab treatment,18
+compound concentration,18
+"donor age, sex",18
+timie,18
+cellular_component,18
+s63845 sensitivity,18
+inducible transgene,18
+tspo expression,18
+reason for liver resection,18
+drug resistance,18
+collection buffer,18
+rna seq_run,18
+vital_status,18
+sample id in rnaseq analysis,18
+patient tumor related pain status,18
+digestion protocol,18
+time post-exposure,18
+t cell activation status,18
+tissue location,18
+age_category,18
+htn,18
+collection point,18
+icu admission,18
+hospital admission,18
+translocations,18
+a1c,18
+height-m,18
+weight-kg,18
+ribodepleted,18
+construct expression,18
+time post bloodmeal,18
+her2,18
+protein expression,18
+mtdna content,17
+parasite/gametocyte stage,17
+composite,17
+viral,17
+absolute cd4 count,17
+level,17
+aligned reads,17
+trimmed reads,17
+raw reads,17
+subject status/id,17
+art treatment,17
+stitched reads,17
+patientcorecode,17
+cell type origin,17
+mouse individual id,17
+day of development,17
+protein,17
+maintissue,17
+clip antibody,17
+sort gate,17
+age at onset of nf2 symptoms,17
+deduplicated reads,17
+sequencing saturation,17
+Labeling Condition,17
+other dx,17
+Hybridization Time,17
+age in months,17
+Wash Condition,17
+transduced,17
+easi/pasi,16
+dex treatment,16
+parent_strain,16
+gene_knockout,16
+ChronicPM,16
+source/differentiation,16
+brain tumor region,16
+serum,16
+common name,16
+cellosaurus id,16
+ethambutol dose,16
+chronic jet lag (cjl) conditions,16
+s. aureus,16
+period of cjl,16
+chx treatment,16
+cell population isolated from ltbmc,16
+zic1 injection,16
+genotype pdgfb gene,16
+genotype trp53,16
+devlopmental stage,16
+pax3 injection,16
+sorting fraction,16
+trasfection,16
+baseline seizure_frequency,16
+viralrna,16
+10x genomics chemistry,16
+adipogenic potential,16
+neovax status,16
+lung section/portion,16
+venetoclax resistance,16
+stn sensitivity,16
+starting amount of total rna,16
+chondrogenic potential,16
+genotype of original donor,16
+kiaaa159-braf fusion,16
+seizure group,16
+pool,16
+treatment agent,16
+compound treatment,16
+sorted fraction,16
+oxygen,16
+labeling protocol,16
+genotype rbpj gene,16
+family code,16
+day of protocol,16
+stn/ibrutinib sensitivity,16
+tmz sensitivity,16
+ecm condition,16
+Patient Number,16
+time post vaccinatino,16
+initial tumor volume,16
+cytogenetic,16
+strain/model,16
+aortic valve,16
+biological eplicate,16
+viral titre,16
+mode of growth,16
+fibrillin fragment,16
+rna extraction,16
+developmental age,16
+dementia status,16
+time of_treatment,16
+RNAi,16
+treatment/infection,16
+autism diagnostic,16
+mantle cell lymphoma (mcl) line,16
+mouse group,16
+quorum sensing (qs) phenotype,16
+cold ischemia_time,16
+performance,16
+ar or asthma,16
+cell status,16
+incubation time,16
+alk mutation status,16
+p218 dose,16
+age tier,16
+mrss score,16
+has_drug,16
+observed tumor grade,16
+mouse id tag,16
+patient_status,16
+fasting,16
+location of tumors,16
+osteogenic potential,16
+vascular support,16
+data analysis id,16
+has_pressure,16
+virus moi,15
+length of culture,15
+h3.3 expression,15
+genes analysed,15
+animal no,15
+sample_label,15
+experiment name,15
+sequencing library id,15
+incidence,15
+gfp,15
+lentivirus infection,15
+risk grade,15
+drug resistant_tb,15
+library preparation protocol,15
+stim,15
+disease classification,15
+lab code,15
+or-s1 concentration,15
+rip,15
+rin number,15
+age of  culture,15
+glioma grade,15
+gender composition,15
+virus dose,15
+differentiation time point,15
+precursor,15
+manuscript library id,15
+catalog number,15
+gel bead version,15
+tumortype,15
+cell line_name,15
+previous diagnosis_of_tb,15
+polarization state,15
+cell_origin,15
+Disputed,15
+surface markers,15
+weekly dosing,15
+bcg scar,15
+a260/a230,15
+primers,15
+phase description,15
+sample name as in counts.txt.gz,15
+verapamil dose,15
+detachment,15
+es line,15
+malignancy class,15
+sample subgroup,15
+tretament,15
+tissue class,15
+tumor class,15
+a260/a280,15
+cd117 staining,15
+pulmonary cavitation,15
+specific-host,15
+age at blood draw,14
+psgl1 status,14
+develoment stage,14
+subset group,14
+brain tumor,14
+Lab ID,14
+genotype/varation,14
+fbn1 genotype,14
+case or control,14
+antigenic stimulation,14
+tg,14
+vaccination status,14
+location/side,14
+hind-limb paralysis,14
+gfp detection,14
+original cell line,14
+sarscov2_infection,14
+differeniation days,14
+disease in non-fip,14
+fcov infection,14
+measure,14
+tisse type,14
+patients,14
+ubi,14
+cell origin,14
+alternative name,14
+vaccination_status,14
+h37rv,14
+pretreatment,14
+genotype abbreviation,14
+experimental run,14
+immune infiltration,14
+sorting profile,14
+ppq sensitivity,13
+paradigm,13
+phlorophore,13
+transplant,13
+sorted population,13
+cell lining,13
+plasmodium berghei strain,13
+jcv replication rate,13
+shrna,13
+functional connectivity,13
+serology,13
+cag repeat,13
+onset age,13
+material type,13
+anti-human sod1 mir,13
+Weight,13
+placental sex,13
+mtap,13
+egfr amplification status,13
+adeno-associated virus injection,13
+bcl2,13
+bcl6,13
+harvest time point,13
+sars-cov-2 status,13
+hpsc,13
+time to relapse,13
+receptor expression,13
+genotyping,13
+pooling,13
+block storage,13
+Tumor Stage,13
+risk group,13
+pfcrt allele,13
+cd8 status,12
+long description,12
+internal sample id,12
+internal patient id,12
+cd3 status,12
+cd4 status,12
+cd45ra status,12
+estimated developmental age,12
+surgical indication,12
+technical replicates,12
+model type,12
+total/partial resection,12
+pre- or post-challenge,12
+fetal lung tissue donor,12
+duration of disease,12
+incubated in,12
+MASTECTOMY,12
+biological source,12
+chemical,12
+melanoma cell type,12
+microarray autogain intensity,12
+rbpms,12
+maturation to macrophage,12
+molarity of infection,12
+escherichia spp,12
+incubation period,12
+diease,12
+chronological age,12
+haemophilus spp,12
+il-8 concentration pg/ml,12
+neutrophil elastase levels,12
+nf1-associated,12
+original tumor,12
+pluripotent,12
+coriell accession,12
+fold enrichment,12
+replica,12
+chemical modification,12
+donor fibroblasts,12
+cutandtag antibody,12
+p75 positive,12
+sample identifier,12
+nacl,12
+melanoma,12
+scale,12
+knockdown target,12
+day of organoid differentiation,12
+major reason_for_surgery,12
+final age at death,12
+duration of cultivation,12
+cell line passage,12
+drinking,12
+blood pressure,12
+culture ph,12
+death day,12
+type of cultivation plate,12
+replicate experiment,12
+name of tissue,12
+company,12
+days under treatment,12
+polarization treatment,12
+treatment type,12
+acute medication,12
+uv/non-uv,12
+chronic medication,12
+antibiotictx,12
+subcellular fraction,12
+renal biopsy,12
+batch of rna isolation,12
+histological findings of renal specimen,12
+ng/ul,12
+dietary regiment,12
+mouse stain,12
+sediment,12
+illumina lane,12
+submission date,12
+hrg expression,12
+inoculation dose,12
+cd34+ hsc donor,12
+surgical approach,12
+clinical manifestation,12
+foxp3 expression,12
+type of insertion,12
+insertion site distance to gene,12
+piggybac insertion site,12
+associated diseses,12
+interstitial pneumonia,12
+engraftment,12
+angiography,12
+staphyloccus spp,12
+chromosome 9 status,12
+product,12
+sorting probe,12
+Sample group,12
+oxygen tension,12
+disease grade,12
+rift valley fever virus,12
+days,12
+viewpoint_analysed,12
+mg2,12
+time after virus injection,12
+div,12
+clone name,12
+brain tissue,12
+agent concentration,12
+lentivirus infected,12
+treatment of mice,12
+xenograft host,12
+monoclonal antibody,12
+ATCC,12
+antibody 1,12
+treatment_dose,12
+antibody vendor,12
+matched l/nl_sample,12
+clarithromycin dose,12
+clone background/id,12
+unique sample identifier,12
+mtb infection,12
+growth phase of cells,12
+autophagy induction,12
+treatment condition,12
+Tumor tissue,12
+age at biopsy,12
+gbm grade,12
+cell type background,12
+radiation response,12
+challenged with,12
+cell line type,12
+operator,12
+start od595,12
+strain id,12
+cell line origin,12
+tb-infection status,12
+worst itch_numeric_rating_scale_(wi-nrs)_score,12
+investigator's global_assessment_(iga)_severity_score,12
+monoclonal antibody supplier,12
+xenografts host mice,12
+antibody 2,12
+sirna type,12
+tumor cell type,12
+time after i.p. injections,12
+seizures/month,12
+source muscle,12
+developmental stage/tumor stage,12
+analysis group,12
+sequenced molecule,12
+sgrna,12
+genetic_modification,12
+4c-seq secondary enzyme,12
+tcr gene,12
+4c-seq primary enzyme,12
+transfection construct,12
+silencing vector,12
+immortalized,12
+mouse status,12
+rel. mir-25 expression,12
+transfection efficiency,12
+group id,12
+tumor inoculation,12
+recombinant proteins,12
+irradiation of gsc,12
+diagnosis2,12
+Drug,12
+time of_dox_treatment,12
+immunization route,12
+muc16 expression,12
+growth factors added on day 0,12
+glioblastoma stem cell culture,12
+primary cell type,12
+density gradient region,12
+"age, yrs",12
+smarcb1 expression,12
+illumina adapter,12
+host age,12
+time point in the model of dormancy,12
+isolation of tumor cells,12
+expressing,12
+efflux status,12
+nik pathway mutation,12
+time post-immunization,12
+oxygenation,12
+scrnaseq method,11
+salt.score,11
+c9orf72-als,11
+tumorgenecity,11
+tb subgroup,11
+organoid generation,11
+array barcode,11
+species,11
+plasmids used,11
+metastatic/primary,11
+primary/ recurrent,11
+ascl1 status,11
+Genetype,11
+integrated diagnosis,11
+recurrent/primary,11
+transfection dosage,11
+duration of infected with pneumocystis,11
+py strain,11
+area/tissue,11
+alopecia.improvement.pct,11
+antibody used,11
+donor id/status,11
+embryos pooled,11
+celll type,11
+antigen capture,11
+plating,11
+chip antibody manufacturer,11
+dsmz no,11
+alopecia.score.post.impovement,11
+urine protein,11
+hydrogen peroxide treatment,11
+initial preparation,10
+h3f3a mutant,10
+anatomic site,10
+lung section,10
+zf vector,10
+enhancer utilized for cell sorting,10
+age at study start,10
+before or after treatment,10
+trt,10
+type of hspn,10
+time of last follow up in months,10
+hist1h3b mutant,10
+"recommended for detection of GATA1 of mouse, rat and human origin. Antibody Target",10
+source id,10
+course of hspn,10
+tissue donor,10
+genotype/disease state,10
+gfap ihc,10
+hto id,10
+mgmt promoter methylation,10
+culture medium,10
+day after intubation,10
+actb2,10
+pcr cycles,10
+viral inactivation,10
+antigen reactivity,10
+inrc therapy response,10
+idh1 mutant,10
+oligo2 ihc,10
+subclone id,10
+rna sample type,10
+symptom duration,10
+treatment/sample type,10
+co-culture condition,10
+chromosome 1p deletion,10
+age of culture when rna harvested,10
+intensive care,10
+merip antibody,10
+chip antibody details,10
+pcr kit,10
+cutting enzymes,10
+PM Status,10
+age at harvest,10
+tp-0903 treatment,10
+transcription factor expression level,10
+camp treatment/level,10
+gestational days,10
+driver gene,10
+ad26.cov. dose,10
+inrg risk stratification,10
+library backbone,10
+il18r1 profile,10
+nf1b,10
+metabolic activity,10
+day post transplant,10
+library label_name,10
+graft recipient strain,10
+cell line for infection,10
+nf1a,10
+malaria status,10
+tissure,10
+bacteria,10
+graft donor strain,10
+Developmental stage,10
+subclone derived from u87mg,10
+chip antibody vandor,10
+status after 5 years,10
+PMD 2,10
+transgenic strain,10
+original biopsy for this patient,10
+polr genotype,10
+animals pooled,10
+maternal state,10
+number of animals,10
+isolated by,10
+CFstatus,10
+age at diagnosis in months,10
+inss disease stage,10
+rescue,10
+PM status,10
+cell model id,10
+injected cell line,10
+tumour cell line used for conditioning medium,9
+process order,9
+process day,9
+oxygen condition,9
+genotype background,9
+exacerbation day,9
+anatomical region,9
+number of_samples,9
+sorting criteria,9
+transduced gene,9
+treatment timing,9
+in vitro lps stimulation,9
+embryo phenotype,9
+geatational days,9
+etiology,9
+host mouse strain,9
+antibody maker,9
+conditioned medium,9
+age/time point,9
+diagnostic ct,9
+cre transgene,9
+subpopulation,9
+hit.status,9
+disase,9
+m.tb culturing coonditions,9
+myc.status,9
+m.tb strain,9
+nember of_samples,9
+infection period,9
+differentiation replicate,9
+h37ra strain,9
+infection rate,9
+weight phenotype,9
+germline mutation,9
+antibody name,9
+cell-subtype,9
+lentiviral transfuction,9
+cytokine secretion,9
+galassi grade,9
+parental cell type,9
+line number according to ninds human genetics resource center dna and cell line repository,9
+number of cag repeats,9
+age range,9
+data presented in the manuscript,9
+cell treated with 2% dmso before infection,9
+ecacc no,9
+time of day,9
+mutation frequency,9
+derived culture,9
+ards,9
+knockout group,9
+subject identifier,9
+resistance profile,9
+growth factors in the culture medium,9
+date of isolation,9
+virus 1 infection,9
+idh-status,9
+virus 2 infection,9
+cel population,9
+sample region,8
+sirna knockdown,8
+culture/treatment,8
+cell number per well,8
+embryo stage,8
+Tgmitfa,8
+transduced shrna,8
+phase of growth,8
+cognitive impairment,8
+quorum sensing status,8
+well diameter in um,8
+molecule purification,8
+c. immitis-infection susceptibility,8
+posttransfection,8
+infection with arthroconidia of c. immitis,8
+post-mortem control case,8
+macrophages,8
+genotype 1,8
+anatomic segment,8
+flourescent marker,8
+activation,8
+growing media conditions,8
+sample code,8
+exogenous treatment,8
+incubation temperature,8
+hpfh,8
+hr1 concentration,8
+digestion enzyme,8
+crispr status,8
+p-bi-tat treatment,8
+nes status,8
+klf1k288x mutation,8
+m. tuberculosis rna,8
+allele,8
+hbf level,8
+clinical comments,8
+disease feature,8
+hamburger and hamilton (hh) stage,8
+survivin localisation,8
+Disease state,8
+derived cell_type,8
+original strain,8
+mds subtype,8
+gc cell pool,8
+transient expression,8
+portion of branchial arch,8
+time point of infection,8
+shRNA number,8
+cartilage pellets,8
+day after transplantation,8
+peptide genotype,8
+secondary antibody,8
+htt polyq,8
+myopathic motor_unit_potentials,8
+"fibrillation potentials,_psws",8
+growth phase/media,8
+ps status,8
+increased insertional_activity,8
+environmental factor,8
+achr binding_ab_positive,8
+cav3/cavin1 mutation,8
+nitrogen source,8
+microglia population,8
+metavir score,8
+overexpressing,8
+ifngamma,8
+genotype 2,8
+covid-19 infection,8
+qc name,8
+age of_diagnosis,8
+sequencing plate,8
+vaccine dose,8
+genotype/treatment,8
+notch1 mutation/expression,8
+shRNA type,8
+timpoint,8
+time since first diagnosis,8
+multiome_modality,8
+age of_onset,8
+cell tyep,8
+neuroblastoma cell line,8
+fus variant,8
+cre status,8
+mitfa,8
+life cycle stage,8
+mutation details,8
+whomax level,8
+selection pressure drugs,8
+mgso4,8
+treatment/group,8
+primary antibody,8
+conditioned media source,8
+shRNA knockdown,8
+tau-redstar expression,8
+uv treatment,8
+rts reaction buffer,8
+sample name synonym,7
+time of_drug_treatment,7
+host tissue,7
+encode accession,7
+incubation,7
+virus genus,7
+chip antibody lot #'2,7
+ggt,7
+Species,7
+ast,7
+bilirubin,7
+alt,7
+chip antibody manufacturers,7
+chip antibody catalog #'s,7
+animal treatment,7
+cell type implantation,7
+virus family,7
+infectious strain,7
+patient age at diagnosis,7
+iclip antibody,7
+skinfold back thickness,7
+culture/clone_id,7
+"developmental stage, weeks",7
+passage/days,7
+shRNA sequence,7
+doi,7
+neural crest-derived,7
+eclip antibody,7
+ap,7
+cx43 expression,7
+PMD 1,7
+histotype,7
+cell type depletion,7
+behavior,6
+Growth Medium,6
+human cell genotype/variation,6
+redstar,6
+ligand side,6
+cross,6
+cocultured with,6
+mouse cell genotype/variation,6
+cftr deletion,6
+Cell strain,6
+origin2,6
+origin1,6
+exposed pollutants,6
+azf deletion,6
+genotype/variaton,6
+sentrixid_sentrixposition,6
+retrieval of sperm from the tese,6
+tubular shadows,6
+protocols,6
+retroviral expression,6
+time after stimulation,6
+age of donor/age of host,6
+tubules sertoli cell only,6
+round of selection,6
+b35 vs c pair,6
+b35 vs b8,6
+devepopmental stage,6
+hairpin,6
+tubules with round spermatids,6
+tubules with elongated spermatids,6
+bergmann-kliesch score,6
+xenograft recipient mice strain,6
+days from treatment,6
+nitrogen,6
+life cycle,6
+molecule subtypes,6
+expression level,6
+tic class,6
+chip antibody reference,6
+chemoterapy drug,6
+wbc count,6
+somatic transgene,6
+tubules with spermatogonia,6
+differentiated cell type,6
+disease name,6
+mean number of oocysts,6
+oocyst prevalence,6
+cytokine production pattern,6
+kr-72 treatment,6
+antibody cat,6
+sampling post confirm,6
+wnt status,6
+days_since_positive_test,6
+stable knockdown,6
+m_abscessus_intracellularlevels,6
+sample state,6
+day post neural induction,6
+age category,6
+antibody lot,6
+b35 vs c,6
+cell type_2,6
+sipool,6
+cell type_1,6
+siv status,6
+tubules with spermatocytes,6
+tn5,6
+dms treatment,6
+antibodies/tag,6
+platlets,6
+m. smegmatis infection status,6
+body weight,6
+sample replicate number,6
+source gender,6
+dignosis,6
+c9orf72 repeat size,6
+smple type,6
+treated with lentivirus,6
+vaccinated with,6
+yap/taz status,6
+fluid,6
+Bra,6
+cell phase,6
+tumor position,6
+number of half-sclerotomes,6
+hippocampal sclerosis,6
+parental/ne-like state,6
+cytokine expression,6
+human tumor cell line,6
+strain_recipient,6
+replicate number,6
+n animals,6
+developmental stage/age,6
+Sex of recipient mice,6
+Sex of donor mice,6
+strain donor,6
+source patient gender,6
+strain recipient,6
+treatment time-point,6
+targeted sequencing,6
+site of_disease_onset,6
+tissur,6
+als status,6
+zone,6
+testosterone treated,6
+genotype of founder fish,6
+zinc status,6
+sorted cell,6
+Sample_reference,6
+cell subsets,6
+stain,6
+Labeling_reference,6
+sorted subset of cells,6
+variation,6
+Extraction_reference,6
+Extraction_amount,6
+time after exposure,6
+genotype & treatment,6
+derived cell type,6
+Subject_reference,6
+Extraction_concentration,6
+gene induction,6
+sample population,6
+pqsA,6
+mother from,6
+day post sars-cov-2,6
+hashtag antibodies,6
+gsc,6
+nodal status,6
+fraction/population,6
+num. arrays,6
+hairpin rna,6
+methylation-enrichment,6
+tobacco use,6
+facs-sorted cell_type,6
+klf4 genotype,6
+sample barcode,6
+media supplement,6
+tnm classification,6
+extraction batch,6
+b35 vs b8 pair,6
+ARN_quality,6
+distant metastasis,6
+In vitro Passage Number,6
+mpo genotype,6
+tissue storage,6
+mating pair,6
+oligo set,6
+mice,6
+iPSc passage,6
+overexpressed target,6
+cell strain,6
+bactin,6
+expression plasmid,6
+daxx status,6
+stem cell clone,6
+drug (ibrutinib) sensitivity,6
+differention day,6
+abcb5,6
+group_tag,6
+cell morphology,6
+subject relationship,6
+shRNA transfection,6
+collection timepoint,6
+organoid formation,6
+ngs_platform_id,5
+pten status,5
+donor sex,5
+in-line barcodes,5
+tissue type type,5
+tranplanted with,5
+invasive behavior,5
+arrayexpress repository sample id,5
+library_strategy,5
+MD,5
+term source ref,5
+cataog number,5
+cell line_infection,5
+global glomerulosclerosis,5
+ifta,5
+marker,5
+culture variation,5
+PMD 3,5
+aCGH,5
+term accession number,5
+of passage,5
+crestin,5
+cmo,5
+cytogenetics,5
+biopsy position,5
+time between dexamethasone administration to t1 blood draw,5
+treehouse id,5
+depletion,5
+Gli1creERT,5
+spike protein used,5
+puromycin selection,5
+sorted,5
+cancer predisposition,5
+karyotyping abnormal,5
+hybrid,5
+original tumor type,5
+days in culture,5
+transfection molecule,5
+post-symptom onset,5
+id,5
+pull-down,5
+mycn amplification,5
+mapalgorithm description,4
+mouse genotype,4
+hla allele,4
+express,4
+knock-in,4
+associate geo_sample,4
+isolation column,4
+pdx specificitiescharacteristics,4
+chip-seq antybody,4
+m.cvipi activity,4
+antibody lot number,4
+shRNA seq,4
+associated geo,4
+stage of disease,4
+eletroporated with,4
+pdl,4
+patient-derived cell line,4
+subect_id,4
+bhlhe40,4
+sample age,4
+number of_animals,4
+eae score,4
+mm stage,4
+passages after establishing stable clones,4
+imq treatment,4
+"Lung carcinoma cell line, ATCC number",4
+par1-3 (pwar1) viewpoint adapter sequence,4
+ipw viewpoint adapter sequence,4
+immunology,4
+treatment/agent,4
+tissue zone,4
+control id,4
+antibody vendor id,4
+afip risk calssification,4
+bmp4 sensitivity,4
+gbm cell population,4
+cell barcode suffix for aggr file,4
+antibody antibody description,4
+shRNA transduced,4
+data type description,4
+culture time,4
+length of infection,4
+acidity,4
+ctcf antibody,4
+mapalgorithm,4
+cocultured,4
+epitope mapping within amino acids 138-158 of myogenin of rat origin. Antibody Target,4
+treament condition,4
+plasmodium infection,4
+media additions,4
+suz12b,4
+source organ,4
+donor gender,4
+suz12a,4
+number of_tracheas,4
+"U6-nf1a-gRNA, mitfa",4
+oxygen status,4
+rna composition,4
+biolobical replicate,4
+atac-seq performed (#) days post treatment with small molecules,4
+pygfp,4
+cd45 status,4
+experiment performed in,4
+strategy,4
+background mice,4
+days of final differentiation,4
+OMP-IRES-tTA,4
+mice group,4
+cell enrichment,4
+phase growth,4
+car-t type,4
+days cultured after cd71+ isolation at day 6,4
+donor disease state,4
+culture supplement,4
+days differentiated,4
+nb treatment,4
+in vivo timepoint,4
+infrequent clonal strain code,4
+morpholino injection at 1-cell stage,4
+australian epidemic strain-1 code,4
+exposesd to,4
+transposon (mini-tn5) knock out,4
+responder status,4
+vector construct,4
+Cells,4
+ab treatment,4
+growth_condition,4
+PMD 5,4
+blood,4
+chip magnetic beads,4
+host mouse_tissue,4
+gating,4
+car-t treatment,4
+growth properties,4
+5´barcode,4
+imatinib-resistance,4
+4c protocol,4
+viral load tertile,3
+vt sample,3
+igf1r localization,3
+iclip antibody cat,3
+severity grade,3
+iclip antibody vendor,3
+infection time point,3
+large cell lung cancer Derived from metastatic site,3
+histopathological diagnostic,3
+excersice type,3
+mrna_preparation_fragment_size_range,3
+rna_preparation_reverse_transcription_protocol,3
+hvc enrichment method,3
+mrna_preparation_initial_mrna_qnty,3
+totalseq hto barcode,3
+transfected vector,3
+extraction_protocol_mrna_enrichment,3
+rna_preparation_5'_rna_adapter_ligation_protocol,3
+diffuse vs limited,3
+totalseq hto,3
+dlbcl molecular subtype,3
+library_generation_pcr_template,3
+rna_preparation_reverse_transcription_primer_sequence,3
+days_post_infection,3
+rna_preparation_5'_dephosphorylation,3
+rna_preparation_3'_rna adapter_ligation_protocol,3
+rna_preparation_3'_rna_adapter_sequence,3
+rna_preparation_5'_rna_adapter_sequence,3
+Morphology,3
+Organ,3
+reactivity,3
+cell subpopulation/marker,3
+donor diagnosis,3
+cell characterization,3
+allergy,3
+rna_preparation_5'_phosphorylation,3
+mcherry,3
+assay type,3
+anatomic site of tumour origin,3
+control source,3
+bacteria tissue,3
+immortalization method,3
+treatment / timepoint,3
+cell lilne,3
+months post infection,3
+Pseudomonas aeruginosa total RNA was isolated from PAO1-psrA,3
+mouse tissue,3
+cd4+ t cells from ot-2 mice day,3
+trans-gene,3
+bacterial cells,3
+details,3
+viral load copies/ml,3
+fibrosis,3
+shRNA construct,3
+tissue extraction,3
+reference lot,3
+ng/µl,3
+extraction_protocol_fragmentation,3
+molecular diagnosis,3
+overexpression status,3
+non-small cell lung cancer Derived from metastatic site,3
+experimental conditions,3
+developmental state,3
+host cells,3
+skin score at biopsy site,3
+adar2 status,3
+bacteria strain,3
+embryo characteristic,3
+reference cat,3
+"Male, 65 years, Primary sites",2
+cell sybtype,2
+ragiographic region,2
+cnv_met_amp,2
+cnv_cdk4_amp,2
+"Female, 59 years, Primary sites",2
+cnv_rb1_del,2
+cnv_cdkn2a_b_del,2
+tisue,2
+aso,2
+data_type,2
+stable transfection,2
+rounds of infection,2
+solvent,2
+cnv_pten_del,2
+cell line source age,2
+sample tag_information,2
+cnv_mdm4_amp,2
+months_survival,2
+progression_status,2
+months_progression,2
+cnv_pdgfra_amp,2
+cell mixing ratio,2
+cnv_mdm2_amp,2
+cell line source tissue,2
+PMD 0,2
+passenge,2
+sars-ncov-2 status,2
+mitf,2
+cell mixture,2
+facs,2
+PMD 7,2
+stage of differentiation,2
+organoid type,2
+cause of death,2
+x-ray radiation,2
+transplanted with,2
+catalog,2
+PMD,2
+treatment_term_name,2
+duration_units,2
+gsc line validated for self-renewal by neurosphere formation,2
+cell line source gender,2
+"BRAIN (CEREBELLUM), BIOPSY",2
+par-clip,2
+trangene,2
+test condition,2
+domain,2
+"BREAST, EXCISIONAL BIOPSY",2
+Hdh genotype,2
+affinity purification,2
+facs strategy,2
+OVARY,2
+MODIFIED RADICAL MASTECTOMY,2
+AXILLARY NODE,2
+BREST,2
+softwareversion description,2
+"BREAST, LOCAL EXCISION",2
+pasaages,2
+ligation,2
+"PER SUBMITTED REPORT, MASTECTOMY",2
+transient overexpression,2
+clip antibody vendor,2
+clip antibody cat,2
+reference condition,2
+tumor who grade,2
+inoculated site,2
+PARTIAL MASTECTOMY,2
+genotype/variataion,2
+COMPLETION MASTECTOMY,2
+cnv_egfr_amp,2
+"LUNG, LUL LOBECTOMY",2
+cnv_chr7_gain,2
+hashing antibodies,2
+cell sub-popuation,2
+cnv_chr10_loss,2
+cnv_chr19_gain,2
+cnv_chr20_gain,2
+mutant_idh1_2,2
+postnatal day,2
+feature type,2
+dsrna,2
+SENTINEL AXILLARY LYMPH NODE,2
+chip seq antibody,2
+life form,2
+selection media,2
+source cells,2
+"BREAST, MASTECTOMY",2
+"BREAST, LUMPECTOMY",2
+phenotye,2
+osition,1
+positive Down screening risk,1
+a small infarction in right parietal white matter,1
+growing conditio,1
+"Female, 57 years, Primary sites",1
+age of patient when tumor sample obtained,1
+sdhb,1
+cd34,1
+Alveolar bone marrow as a cell source for regenerative medicine,1
+Growth day at 37 degree of Celsius,1
+dog-1,1
+mitotic rate,1
+injected cells,1
+paired patien,1
+C. neoformans H99 was coincubated with J774A.1 macrophages at a ratio of 10,1
+hot,1
+Infection Status,1
+incubation partner,1
+"Male, 37 years, Primary sites",1
+cell lie,1
+19q intact) ATRX protein status (IHC,1
+epitope is a synthetic peptide,1
+small cell lung cancer Derived from metastatic site,1
+mesothelioma [23570] Derived from metastatic site,1
+"Female, 72 years, Primary sites",1
+transfectant,1
+mammalian host,1
+epitope mapping at the C-terminus of Stat3 of mouse origin. Antibody Target,1
+"Male, 59 years, Primary sites",1
+small molecule,1
+"Male, 72 years, Primary sites",1
+zebrafish strain,1
+sratin,1
+passage no,1
+differences between alveolar and iliac bone marrow stromal cells. J Bone Miner Res 20,1
+10x barcode,1
+NIH Approval Number,1
+"Male, 60 years, Primary sites",1
diff --git a/RDAS_RDOMICS/scripts/sample_characteristics_harmonization/sample_characteristics_harmonization_output/3_sample_characteristics_key_count_english_only.csv b/RDAS_RDOMICS/scripts/sample_characteristics_harmonization/sample_characteristics_harmonization_output/3_sample_characteristics_key_count_english_only.csv
new file mode 100644
index 0000000..bde39e4
--- /dev/null
+++ b/RDAS_RDOMICS/scripts/sample_characteristics_harmonization/sample_characteristics_harmonization_output/3_sample_characteristics_key_count_english_only.csv
@@ -0,0 +1,2815 @@
+name,count
+tissue,157196
+cell type,97260
+age,73415
+treatment,71874
+gender,53178
+Sex,47903
+genotype,46776
+strain,41490
+cell line,40278
+disease state,31657
+time,17068
+disease,14111
+time point,12459
+group,11700
+diagnosis,11647
+condition,10956
+ethnicity,10118
+sample type,10037
+batch,9770
+timepoint,9424
+patient id,8310
+infection,8270
+individual,8008
+race,7888
+genotype/variation,6816
+subject id,6726
+replicate,5824
+donor,5515
+subject,5499
+chip antibody,5153
+developmental stage,5106
+disease status,4806
+antibody,4446
+Stage,4189
+patient,4121
+day,3722
+clinical info,3680
+visit,3653
+histology,3618
+agent,3539
+vaccine,3535
+plate,3492
+tissue type,3471
+subject status,3306
+protocol,3271
+tumor type,3082
+cohort,3031
+region,2915
+age in years,2898
+molecule subtype,2882
+housing condition,2815
+sample id,2694
+subjectid,2672
+site,2620
+smoking status,2577
+sample,2422
+segment,2380
+stimulation,2378
+strain background,2334
+location,2284
+organismpart,2192
+pasi,2192
+diseasestate,2186
+sample group,2179
+clinical diagnosis,2111
+organism part,2102
+celltype,2035
+phenotype,1959
+pathologic status,1940
+histologic diagnosis,1936
+tissue anatomic site,1936
+grade,1888
+type,1856
+mouse id,1755
+donor id,1737
+experiment,1725
+slide no,1700
+cell description,1693
+reference,1682
+source,1670
+participant id,1666
+Age,1662
+cell sex,1656
+controlid,1655
+molecule type,1618
+datatype description,1606
+datatype,1603
+tumor grade,1602
+sex,1601
+library type,1600
+tst,1588
+passage,1586
+cell,1531
+molecule,1522
+dataset,1520
+collection_method,1517
+cell organism,1508
+well,1500
+Tissue,1499
+segment type,1492
+dose,1480
+roi,1459
+strain/background,1449
+virus,1436
+surgical status,1417
+infection status,1402
+tumor location,1401
+date,1400
+tumor stage,1390
+infection states,1389
+biological replicate,1375
+donor_id,1361
+outcome,1324
+tag,1317
+mouse strain,1292
+culture,1264
+animal,1261
+patientid,1239
+batch id,1213
+tissue source,1209
+individual id,1208
+assay,1202
+clinical status,1187
+geographical region,1182
+labversion,1180
+roi number,1177
+Gender,1172
+protection,1172
+lab,1170
+barcode,1156
+patient_id,1152
+disease group,1144
+passages,1138
+class,1132
+treatment description,1095
+temperature,1094
+tissue/cell type,1069
+final diagnosis,1067
+isolate,1067
+status,1055
+area,1053
+material,1047
+library prep,1030
+animal id,1019
+primary site,1010
+fraction,1003
+cell subtype,1002
+patient diagnosis,1001
+enrollment batch,1000
+pipeline version,1000
+censored,1000
+provider,1000
+parity,998
+lab description,997
+background strain,997
+subtype,994
+treatmentshort,992
+platesimple,992
+patient gender,977
+extraction_protocol,970
+experiment_type,970
+medium,949
+tuberculin skin test,938
+drug treatment,934
+albumin,923
+treated with,920
+country of serum collection,911
+organ failure,910
+infected with,898
+development stage,897
+culture result,894
+hematocrit,883
+age_onset,876
+site_onset,876
+survival_yr,876
+cell_type,875
+clone,871
+hemoglobin,865
+model,861
+bin,855
+cell line id,847
+sampleID,841
+metastasis,840
+age description,839
+cancer status,837
+donor_age,835
+donor_sex,835
+donor_health_status,835
+donor_ethnicity,835
+mouse model,822
+birth_place,813
+severity score,811
+method,810
+cell subset,806
+disease stage,804
+companion animals,804
+agricultural animals,804
+delivery,804
+chip_protocol_chromatin_amount,804
+adjusted household density,804
+chip_protocol,804
+geographic location,804
+treatment group,792
+hours post infection,779
+tissue preparation,779
+treatment time,775
+disease severity,774
+morphology,764
+control,757
+stress,744
+tissue of origin,744
+participant,742
+study,741
+infection protocol,740
+stimulus,736
+control description,731
+background,730
+cell karyotype,726
+patient viral load,726
+case number,726
+patient group,721
+cell lineage,713
+sample source,708
+chip_antibody_provider,708
+sample alias,707
+sample common name,707
+os,703
+chip_antibody_lot,696
+genetic background,683
+chip_protocol_bead_type,680
+chip_antibody,680
+chip_protocol_antibody_amount,680
+chip_protocol_bead_amount,680
+working_diagnosis,678
+first_diagnosis,678
+smoker,670
+field_site,669
+response,667
+irradiated,667
+tissue_type,661
+atmosphere,661
+tumor grading,658
+treatment duration,657
+os_status,656
+growth protocol,654
+sample collection site,652
+age group,642
+flowcell,640
+Race,638
+strain description,638
+infection time,635
+year,633
+transduction,629
+severity,619
+epithelial,618
+first vaccination,614
+second vaccination,614
+geographic origin,610
+patient sample id,610
+pathology,605
+subgroup,601
+sample.id,597
+lane.number,597
+patient age,597
+center,596
+brain region,595
+ID,584
+illness,574
+passage_if_expanded,572
+selection,567
+weight,567
+lane,566
+growth phase,558
+selection marker,554
+doubling time,553
+case,551
+Ethnicity,547
+Illness,546
+sorted cells,546
+infectious agent,546
+sort,542
+covid_status,538
+host,536
+groups,535
+recipient,534
+collection time point,533
+duration,530
+disease duration,527
+cluster,527
+origin,525
+slide,522
+donor age,518
+molecular subgroup,509
+disease_category,507
+resistance,506
+cell population,505
+sample_code,503
+organ/tissue,503
+viral_positivity,500
+immature_granulocytes_percent,500
+culture_result,500
+predicted celltype,500
+institutional tumor diagnosis,500
+volunteer id,500
+age_weeks,500
+genotype_abbreviation,500
+blood sample id,500
+immature_granulocytes_absolute,500
+neoplastic,500
+plate id,500
+predicted parent celltype,500
+smear_results,500
+allele actual,500
+date harvest,500
+well address,500
+age_at_draw,500
+timepoint biopsy,500
+plate_location,500
+allele nominal,500
+match,500
+consortium lung phenotype,500
+time harvest,500
+patient_asymptomatic,500
+blood sample_id,500
+in_covid_only_dataset,500
+malaria_transmission,500
+lymphocyte_percent,500
+lymphocyte_absolute,500
+monocyte_percent,500
+monocyte_absolute,500
+smear microscopy,500
+full_genotype,500
+external_donor_name,500
+instrument model,500
+cell projection,500
+induced,500
+cosmic id,500
+disease location,500
+cell line code,500
+supplier,500
+affy_batch,500
+patient classification_at_first_sample,500
+days since_first_sample,500
+sampling time_point_label,500
+library prep_plate,500
+assigned cluster,500
+time_to_malaria,500
+library preparation method,500
+source_organism,500
+hip_circumference,500
+waist_circumference,500
+disease staging,500
+cancer site,500
+external id,500
+days since first sample,500
+diagnostic_group,500
+probe_detection,500
+reagent,500
+microdissection,500
+age of enrollment,500
+title,500
+immunization dose,500
+days_in_hospital,500
+consortium lung phenotype surrogate variable,500
+filtered peaks,500
+meconium ileus status,500
+sample id alt,500
+patient classification at first sample,500
+age_at_diagnosis,500
+persistent ps aer status,500
+extract name,500
+age of onset of persistent ps aer or censored age,500
+assay name,500
+malaria_status,500
+project,500
+animal replicate,500
+hemisphere_name,500
+injection_materials,500
+platelet_count,500
+classification group,500
+multisector,500
+injection_roi,500
+days since vaccine,500
+surgery number,500
+sample class,500
+sorted compartment,500
+array_design,500
+patient category,500
+chemical compound,500
+vendor id,500
+dev_stage,500
+platform_id_id design,500
+white_blood_cell_count,500
+cluster_label,500
+sample_name,500
+curative_intent,496
+tumor,494
+who category,493
+neuropathological_diagnosis,492
+slide_position,492
+is_technical_replicate,492
+protocol description,492
+duplicate_pair,492
+dementia,492
+clinical_diagnosis,492
+disease_duration_years,492
+age_at_death_years,492
+assayed molecule,489
+material support,489
+Strain,486
+passage number,485
+diagnostic_mean,484
+pathogen,478
+population,477
+library name,476
+infected with/healthy control,476
+code,473
+culture condition,472
+tissue_depot,471
+sample name,470
+red blood cells,460
+lymphs,460
+death,460
+line,459
+white blood cells,458
+isolation_method,455
+sample timing,455
+vaccine doses,455
+covid cat,455
+covid,455
+skin type,452
+vital status,450
+survival_status,450
+progression,448
+site of infection,447
+prior treatment,445
+survival,444
+breed,443
+subject_id,442
+cancer type,439
+infection code,438
+genome build,438
+sample material,438
+specimen,434
+time.from.exposure.months,434
+culture conditions,432
+label,431
+concentration,427
+disease_status,426
+bait,425
+chain,422
+sample collection time,421
+parasitemia,419
+media,417
+reference diagnosis,415
+outlier,414
+library well,412
+library plate,412
+array,407
+condition description,405
+date collected,404
+vaccination,404
+initial ich volume,399
+day of trial,399
+gene_count,399
+adjusted disease severity index,399
+response_group,398
+symptomatic or asymptomatic at sample collection,397
+grouping,395
+platelet,394
+nuclei count,393
+day post infection,391
+non human primate individual id,390
+age at death,387
+days since vaccination,387
+vaccine side effects,387
+vaccine type,387
+age at sample drawn,387
+induction date,385
+library date,385
+antigen,384
+sampling timepoint,383
+markers,382
+technique,381
+exposure,381
+sample preparation,380
+chip antibody vendor,380
+tst skin test,379
+recruiting site,379
+sample_group,377
+slide id,377
+birth date,374
+joint problems,374
+current medication,374
+family history,374
+procedure date,374
+smoking start date,374
+symptoms onset date,374
+blood obtained,374
+diagnosis date,374
+smoking amount,374
+smoking stop date,374
+strain/genotype,371
+subject group,371
+binding density,370
+cap score,369
+mouse number,369
+classification,369
+who grade,367
+gold stage,366
+chip antibody cat,365
+tissue substructure,363
+negative normalization factor,363
+note,363
+history,363
+surface area,363
+tissue structure,363
+year of surgery,363
+replicate description,362
+age in year,362
+link,362
+organ,361
+growth condition,359
+mouse,354
+mutation,354
+experiment group,354
+sample group_label,353
+days of differentiation,353
+treatment location,353
+age at_treatment,353
+treatment age_group,353
+who,349
+source type,345
+nuclei_counts,345
+amplification,341
+additional conditions,340
+sample number within subject,339
+disease symptom,339
+skin,338
+chemotherapy,337
+sample collection,335
+culture type,334
+animal_id,334
+tissue id,333
+with or without clonal heterogeneity,332
+international prognostic index,332
+dead or alive at the end of follow-up,332
+follow up years,332
+total number of genomic aberrations,332
+animal age,330
+seizure,328
+treatment/time point,328
+other diseases,325
+monkey id,324
+amplification cycles,324
+disease type,322
+parasite strain,322
+animal sex,320
+colony of_origin,320
+dosage,319
+cell phenotype,319
+ventilation,319
+week,317
+osteogenesis day,317
+smoke,317
+donor category,317
+hemoglobin genotype,315
+asthma,314
+per lymphocytes,313
+per monocytes,313
+slide name,313
+visit_date,313
+smear_result,313
+timepoint_months,313
+development,310
+disease subtype,308
+mean corpuscular volume,306
+sample time,302
+trachea region,301
+InitialTimePoint,300
+OrganismPart,300
+Prior Treatment,300
+TargetedCellType,300
+Individual,300
+CellLine,300
+job/role,300
+education,300
+DiseaseState,300
+cells,299
+chip-antibody,298
+OS status,297
+category,296
+treatment administration route,296
+treatment frequency,296
+technical replicate,295
+experiment type,295
+anti-centromere,295
+description,294
+age at diagnosis,291
+index,287
+recurrence,286
+os.mos,286
+diagnosis.after.path.re.review,286
+surgical.outcome,286
+diagnosis.of.record,286
+path.stage,286
+differentiation stage,286
+psychiatric disorder,285
+gastrointestinal disorder,285
+cerebral palsy,285
+mutational subclass,285
+study group,285
+genetic testing,285
+birth defects,285
+neurological disorder,285
+developmental/speech disorder,285
+unpublished,284
+diet,284
+city,284
+datasets,284
+medications/vitamin names,284
+virus strain,283
+lung disease,283
+diabetes,283
+chronic diseases,282
+volume,282
+molecular.diagnosis,280
+stimulant,280
+drug,278
+library preparation,277
+geographical location,277
+vaccination.assignment,275
+description of day,275
+subject number,272
+training.test,271
+used for analysis,271
+primary.tumor,271
+tissue.type,271
+tumor_name,270
+differentiation day,270
+block_name,270
+specimen_name,270
+structure acronym,270
+day_of_euthanasia,268
+percent_weight_loss,268
+radiation administered prior to tumor resection,267
+set,267
+genome/variation,266
+sample_set,265
+visit day,265
+immunization,265
+biopsy,260
+read length,259
+donor_id_blinded,258
+experimental group,256
+regimen,256
+histological diagnosis,253
+duplication_rate,251
+align_unique,251
+sample_group_granular,251
+exon_ratio,251
+align_input,251
+reads_all,251
+nuclear_reads,251
+library_prep_date,251
+extract_date,251
+number of malaria infections,250
+volunteer code,250
+treatment dose,248
+molecular classification,248
+age_diagnosis_years,245
+recurrent_status,245
+surgical_interval_mo,245
+tumor localization,243
+repeat,243
+monocytes,242
+age of onset,240
+donor type,240
+paired samples,239
+season,238
+original geo accession,238
+other information,236
+sorting strategy,234
+escape,233
+treatment arm,232
+intrinsic subtype,231
+diffuse,231
+patient.code,231
+hist.score,228
+blood collection tube coating,227
+genetic modification,227
+broad diagnosis,226
+behavior at diagnosis,226
+tumor category,226
+Tumor stage,226
+sample_type,226
+dysplasia now,226
+TimeUnit,225
+sorter day,224
+disease activity,221
+subject condition,221
+tissue subtype,220
+section,219
+treatment withdrawal,217
+treatment initiation,217
+feeding,215
+library protocol,215
+state,214
+subject diagnosis,213
+health state,213
+recreational drugs,212
+art start year,212
+cigarette smoker,212
+sample day,212
+prescription drugs,212
+bal sampling date,212
+active ingredient,212
+medical.history,212
+tissue region,211
+treatment-outcome code,211
+timing,211
+processing,210
+tissue/sample type,209
+library quality,208
+blood_group,208
+sampling_timepoint,208
+differentiation batch,207
+stimulation condition,207
+time post-stimulation,207
+hybridization batch,206
+visit number,205
+pair,205
+cell types,205
+developmental_stage,204
+primary diagnosis,204
+responder cell line,203
+knockout,203
+malaria strain,203
+light condition,203
+diagnosis total,202
+anatomic_location,202
+inflammation_status,202
+diagnosis hep flex,202
+diagnosis recto sigmoid,202
+diagnosis rectum,202
+run_date,202
+pregnancy status,201
+anatomic location,201
+patient_age,201
+patient_visit,201
+days_symptom_onset,201
+lung pathology,200
+muscle mass,200
+radiation.therapy,200
+waist to hip ratio,200
+overall.survival..days,200
+reference genome_for_processed_files,200
+fat mass,200
+reference genome_for_alignment,200
+tumor_entity_subtype,200
+patient sex,199
+sampling time,199
+time_since_onset,198
+primed,198
+library,198
+treatment protocol,197
+brain location,197
+experimental replicate,196
+cirrhosis present,195
+plate_number,195
+patient code,195
+cell line of origin,195
+self_reported_race,195
+chronic hypertension,194
+ga,194
+growth medium,193
+number of relapses,192
+microbiota status,192
+survival after surgery,192
+sputum_smear,191
+region of birth,191
+case/control,191
+sputum_culture,191
+biopsy type,190
+death with metastasis,189
+infection_status,189
+vaccination route,188
+outcome related,188
+couple number,188
+growth,187
+period,186
+buffer,186
+infected/uninfected,186
+bacterium,186
+hours,186
+extraction date,185
+draw_date,185
+comment,184
+patient subgroup,184
+LabeledExtract,183
+patient number,183
+rip antibody,182
+hybridization protocol,182
+stimulation time and condition,182
+antibody manufacturer,182
+cell source,181
+neoplasia type,181
+study id,181
+symptom severity,180
+Histopathological diagnostic,180
+viral shedding,180
+fetal sex,179
+tissue/cell line,179
+tst result,179
+sample tissue,179
+expanded allele cag repeat count,178
+symptomatic,178
+factor,177
+age at_diagnosis,177
+dev stage,177
+paired material support,177
+lineage,176
+molecular subtype,176
+input,174
+day of differentiation,174
+sample_id,173
+diagnosis colonic,172
+hours post-invasion,172
+diagnosis details,172
+Cause of death,172
+treatment response,172
+diagnosis anal perianal,172
+further operations,172
+diagnosis oral,172
+diagnosis rectal,172
+volunteer,171
+smoking,171
+living,170
+survival time,170
+survival cluster,170
+preparation,169
+differentiation,169
+disease_state,169
+duration of illness,168
+long-covid symptoms,168
+overall.survival.months,168
+subset,168
+enzymatic treatment,168
+ancestry,168
+vaccine group,168
+dose group,167
+protect outcome,167
+hypertension,165
+efficacy,164
+days post drug,164
+hours post invasion,162
+group description,162
+mechanical ventilation,162
+collection time point (#) or necropsy,162
+inhibitor treatment,161
+tissue archive method,160
+parasite stage,160
+tumor full_name,160
+strain name,160
+study participant,159
+eye,158
+diabetes_medication,158
+buffer_volume,158
+spike-in cell_line,158
+spike-in cell_type,158
+other_medication,158
+disease_group_detailed,158
+protein exchange,158
+time-point,158
+sample_site,158
+buffer_volume_unit,158
+disease_group,158
+cag_repeat,156
+brain bank,156
+conversion,156
+chip antibody lot,156
+os_month,156
+days after infection,156
+prognosis,156
+study_origin,156
+parasitemia category,155
+tissue origin,155
+library prep. kit,155
+restriction enzyme,153
+differentiation_method,152
+survival status,152
+classifier_mes,152
+pathology_note,152
+differentiation_stage,152
+blood.source,151
+aerosol.run,151
+antibody description,151
+cage,151
+age.days,151
+infection.time.point.days,151
+lane.ordinal,151
+splice variant,150
+clinical diagnosis specimen,150
+clinical diagnosis patient,150
+sample recovery type,150
+embryonic stage,150
+parasite density,150
+sample_barcode,149
+excision year,149
+malign,148
+slide_id,148
+"deceased donors, only left kidney included in the analysis",148
+notes,148
+knockdown,147
+adapter,147
+side,146
+"biopsy data, villus height to crypt depth",146
+transplant type,145
+time points,144
+dose_group,144
+protect_outcome,144
+target gene,143
+identifier,142
+cell_line,142
+patient treatment,141
+chip target,141
+Phenotype,141
+bal_culture,140
+distance from the tumor center,140
+isolate_sensitivity,140
+index_case_disease_site,140
+bal_smear,140
+cag,140
+smear of index case,140
+exposure_latent,140
+pasi score,138
+tissue notes,138
+pathogens,138
+obesity,137
+tumor subgroup,137
+subjects,137
+Other,136
+stress exposure,135
+inflammation status,135
+sample origin,135
+cell fraction,134
+culture duration,134
+years since diagnosis,134
+host cell,134
+responder cells,134
+family,134
+time since steroid dose,134
+components,133
+biopsy site,133
+tissue-of-origin,132
+injection_type,132
+histopathology,132
+donor_genotype,132
+Time,132
+sample collection time post infection,130
+technology,128
+skin disease,128
+biological sex,127
+fibrinogen,126
+ventilator-free days,126
+sofa,126
+genetic class,126
+target molecule,126
+symptom,125
+mutation_carrier_status,124
+cag_repeats,124
+mouse genotype/variation,124
+day-post-infection,123
+line type,123
+phase,123
+Diagnosis,122
+tumor subtype,122
+time post infection,121
+protocol number,121
+scan id,120
+batch group,120
+application,120
+das score,120
+enzyme,120
+steroids,120
+country,120
+biologics,120
+infectivity,120
+tissue processing,119
+stimulation protocol,119
+met_amplification,119
+cell part,118
+serum type,118
+day after seeding,118
+exposed stress,118
+other batch,118
+date of array,117
+line number,117
+os month,116
+day of_tumor_harvest,116
+infection agent,116
+culture media,116
+cell culture,116
+hospital,116
+array batch,116
+marrow,116
+batch.date,116
+harvesting time,115
+immune status,113
+isolation source,113
+previous treatments,113
+cell line source,112
+vaccine regimen,112
+fragments in clean bam,112
+mouse_id,110
+sensor,110
+donor code,110
+total cholesterol,109
+type of sample,109
+fibrosis degree,109
+cell type/line,108
+spike-in,108
+patient population,108
+clinical condition,108
+Histology,107
+collection time,106
+interim pet response,106
+primary tissues,106
+time after treatment,106
+other,106
+growth media,106
+primary/recurrent,105
+infection group,105
+race/ethnicity,105
+drug dose,105
+pasi_total,105
+sample age proxy,105
+admission,105
+variety,105
+age at sampling,105
+patient condition,104
+female,104
+worm infection,104
+family id,104
+watch and wait,104
+Outcome,104
+scar,104
+circumstances,103
+clinical phenotype,103
+sample subseries,103
+lesion,103
+lymphoma type,102
+gestational age,102
+stimulation duration,102
+matched pair id,102
+replicate mouse,102
+target,102
+infected,101
+geo series,101
+replicate id,101
+Tumor size,101
+remission,101
+library strategy,101
+geo accession,101
+Usage number,101
+Exposures,101
+swollen joints,101
+pain,101
+Filter number,101
+tender joints,101
+cortical_score,100
+average library size,100
+striatal_score,100
+viral load,100
+donor number,100
+exposure time,100
+channel count,100
+age of psoriasis onset,100
+current status,100
+localization,99
+hours post-treatment,99
+hemisphere,99
+litter,99
+treatment time point,98
+disease_extension,97
+isolate type,97
+Smoking status,97
+ko induction_time,97
+endoscopic_activity,97
+vector,97
+case_phenotype,97
+tumor status,97
+culture_conditions,96
+transplanted organ,96
+individual identifier,96
+als phenotype,96
+volunteer number,96
+viral strain,96
+days post-vaccination,96
+reporter,96
+primary disease,96
+time of blood draw,96
+age at transplant,96
+incubation conditions,96
+animal name,95
+cell stimulation,95
+roi lot,95
+parasite line,95
+specimen_barcode,95
+mitotic index,94
+chemistry,94
+mouse identifier,94
+neuropathological diagnosis,94
+Condition,93
+microglia media,93
+purification,92
+survival characteristics,92
+sub-population,92
+vaccination dose,92
+histological..subtype,92
+vascular.invasion,92
+mutational.status,92
+health status,92
+lymphocyte.reaction,92
+multifocal,92
+therapy used,92
+tumor.in.left.right.lobe,92
+location of onset,92
+smoker or non smoker,92
+exposed to,92
+vaccination boost,92
+familial anamnesis,92
+age.at.operation,92
+patient source,91
+biopsy number for this subject,91
+disease_stage,91
+tumor region,91
+days post onset of symptoms,90
+onset,90
+cell state,90
+"age, months",90
+sample number,89
+Group,89
+Patient,89
+Status,89
+disease_duration,89
+survival_time,89
+replicate # in experiment,88
+unique_subject_identifier,88
+progression_free_survival,88
+cell compartment,88
+progression_free_survival_censor,88
+bacterial lysate,88
+antibiotic treatment,87
+hour post infection,87
+trial arm,87
+disease category,87
+sample collection time post virus infection,87
+age of death,87
+cell subpopulation,86
+experiment year_month,86
+virus type,86
+unsorted or sorted,86
+AGE,86
+surgery,85
+clinical stage,85
+clinical type,85
+cattle breed,85
+responder,84
+host genotype,84
+survival time in months,84
+tissue/treatment id,84
+instance,84
+culture method,84
+input material,84
+dissection,84
+tumor type/grade,84
+mouse line abbreviation,84
+tissue compartment,83
+alias,83
+virus infection,83
+cell line background,82
+experiment label,82
+infectious challenge,82
+draw day,82
+viral status,82
+pool no,81
+cell density,81
+healthy control,81
+donor_type,81
+integrative analysis,81
+prophylaxis,81
+subclass,80
+simulation,80
+exercise intensity,80
+exposure condition,80
+number of cells,80
+animal identifier,80
+control/intervention,80
+library id,79
+infected host,79
+primary recurrent,79
+relapse time,79
+panel,79
+bacterial strain,79
+infectious_dose,79
+challenge,79
+expression,79
+specimen site,79
+adapter sequence,79
+folder name,79
+age patient,78
+viral genus,78
+viral family,78
+stage of repair process,78
+mib,78
+patient identifier,78
+cell number,78
+fracture site,78
+covid infection_status,77
+karyotype,77
+culture days,77
+geo expression data,77
+covid severity_status,77
+tissue group,77
+host strain,76
+smoking_status,76
+source tissue,76
+immune_or_nasal,76
+cancer stage,76
+treatment status,76
+surgery type,76
+steroids_cat,76
+bacterial infection,76
+any_immune,76
+nasal_steroids,76
+pool id,75
+replicate / experiment,75
+ClinicalInformation,75
+cell lines,75
+minimum reads per cell during initial processing,75
+infection state,75
+spike-ins,75
+number of pooled individuals,75
+peptide,75
+minimum counts per cell threshold used to remove background barcodes,75
+infection duration,75
+preservation method,75
+growth stage,74
+ear treatment,74
+activation agent,74
+radiation,74
+mouse line,74
+clinical outcome,74
+sample plate,74
+parental tumor subtype,74
+bone-marrow grafting status,74
+bone-marrow grafting type,74
+Type,73
+injection site,73
+injected virus,73
+preliminary diagnosis,73
+experimental status,72
+clinical indication,72
+patient identification number,72
+sort population,72
+therapy,72
+metastasis site,72
+variant type,72
+primary tumor site,71
+compound,71
+sample description,71
+storage,71
+age at initiation,70
+embryo,70
+biological drug,70
+parental origin,70
+donor covid_status,70
+anatomical location,70
+fetus,70
+glioma,70
+subcutaneous neurofibromas,70
+plexiform neurofibromas,70
+cutaneous neurofibromas,70
+tags,70
+facial dysmorphism,70
+scoliosis,70
+host mice strain,70
+skin-fold freckling,70
+lesional (ls) vs. normal,69
+Genetic background,69
+Lymph node involvement,69
+Degree of differentiation,69
+compartment,69
+alcohol,69
+host vendor,69
+host strain/background,69
+Histological type,69
+primary_recurrent,68
+mouse selection,68
+restriction enzymes,67
+day blood taken,67
+vs type,67
+structure,67
+steroid,67
+clinically_aggressive,66
+histological.type,66
+ann arbor stage,66
+number of immunization boost,66
+backbone,66
+tissue status,66
+genetic variants,66
+sampling.time,66
+size,66
+treatment_duration,65
+malaria infection,65
+tumor histology,65
+risk,65
+cell markers,65
+metastatic tumor site,65
+control or als,65
+derivation,65
+immune border,64
+comments,64
+illness_duration,64
+lobe,64
+total skin score,64
+lymphocyte_count,64
+lesion_disease_factor,64
+lesion_label,64
+with_lesion_sample,64
+presence_of_parasites_lesion,64
+cytology,64
+roi type,64
+infiltration,64
+rounds_to_cure,64
+id sample,64
+id simple,64
+cag repeat size,64
+library_batch,64
+clinical trial phase,64
+methylation_geo_id,64
+geo_sample_id,64
+vector treatment,64
+severity_score,64
+harvest time,64
+lesion_size,64
+previous drug treatment,64
+enrichment method,63
+library prep person,63
+overall.survival.time,63
+days post infection,63
+ref id,63
+life stage,62
+time in culture,62
+collection day,62
+bleeding,62
+number of_mice,62
+carbon source,62
+stool frequency,62
+antibody group,62
+surgical treatment,62
+vaccine administered,62
+genotype/strain,62
+other biologic medicines use,62
+time of sample collection,61
+clinical presentation,61
+infection type exposure,61
+source cell type,61
+patient_no,61
+aspiration site,61
+corrector,60
+Subsets,60
+stage,60
+days after stimulation,60
+vector constructs,60
+coo,60
+pathogen exposure,60
+viral challenge,60
+SEX,60
+patient no,60
+Case,60
+primary tumor,60
+labeling agent,60
+alive,60
+angiogenesis score,60
+subject age,60
+pediatric patient,60
+tissue/cell info,60
+ras score,60
+cag repeats,60
+sample name in supplementary file,60
+prodromal status,60
+duration of infection,60
+cartridge,60
+covid status,59
+sorted cell_type,59
+sandwich type,59
+subtypes,58
+local skin score,58
+replicates,58
+cycling,58
+location of lesion,58
+library input,58
+experimental condition,58
+respirations per minute,58
+cells detected,58
+types,58
+survival year,58
+gene deletion status,58
+tissue derivation,58
+mutation class,57
+rabbit id,57
+patient response,57
+induction,57
+modifications,57
+rabbit group,57
+experimental set,57
+sampling site,57
+library-type,57
+lesion status,57
+time after infection,57
+treatment outcome,57
+culture platform,57
+alternative sample name,57
+mouse age,57
+treatment/timepoint,57
+age and disease,56
+cag length,56
+fever,56
+publication id,56
+dyspnea / tachypnea,56
+cough,56
+debris removal,56
+data tissue_collection,56
+commercial source,56
+topography,56
+lymph node number,56
+study_id,56
+malignant tumor,56
+primary/metastasis,56
+symptoms,56
+tissue collection,56
+upper or lower extremity,55
+tuberculosis_history,55
+growth pattern,55
+volar or non-volar,55
+family_history,55
+parental line,55
+Differentiation Method,55
+year of isolation,55
+disease model,55
+exitus,55
+Sample ID,55
+kit mutation,54
+library version,54
+perturbation class,54
+perturbation,54
+age at blood collection,54
+initial tumor increase/(-)decrease,54
+primary mutation,54
+clinic status,54
+sort strategy,54
+match degree,54
+organ system,54
+laboratory strain,54
+timepoint_description,54
+copy number gain,54
+sofa score,54
+sample/subject id,53
+als mutation,53
+samples of different individuals pooled,53
+granuloma,53
+FISH origin,53
+age at surgery,53
+collected_by,53
+organoid line,53
+platform,53
+isolation method,52
+cross-linked,52
+brain metastasis,52
+tumor size,52
+biological_replicate,52
+reason for intubation,52
+pregnancy,52
+Genotype,52
+genetic specifics,52
+psoriasis duration,52
+sporozoite age,52
+route administered,52
+organism_status,51
+age/gender,51
+specific heart region,51
+recipient strain,51
+clinical_history,51
+organism_part,51
+treatment stage,51
+tumor side,51
+tumor_grading,51
+extract_protocol,51
+last follow-up,51
+day of tissue harvest,51
+infection strain,51
+vehicle,51
+oxygen percentage,51
+lymph node,51
+health_status,50
+age in_yrs,50
+metastatic site,50
+study number,50
+strain info,50
+Mouse ID,50
+injury/age,50
+cerebral performance category score,50
+bar code,49
+diplopia,49
+tumor source,49
+sex/age,49
+swollen eyelid,49
+ago protein,49
+mutations,49
+decrease of vision,49
+parental cell line,49
+other organ lesion,49
+kit,48
+experimental day,48
+mosquito,48
+sample prep,48
+group label,48
+scan method,48
+onset site,48
+stem cell,48
+experiment batch,48
+day post-infection,48
+sample/time point,48
+treatment_duration_in_hours,48
+subject gender,48
+treatment_time,48
+treatment category,48
+hours_post_infection,48
+slide tissue area,48
+treatment prior to second surgery,47
+cell surface marker,47
+graft source,47
+isolation,47
+relapse,47
+syndrome,47
+age fracture,47
+dissected embryo id number,47
+conditioning received,47
+conditions,47
+developmental stage/tissue,46
+systemic sclerosis subtype,46
+over-expression,46
+to concatenate,46
+patient/control id,46
+parental strain,46
+derived from,46
+total bilirubin,46
+sample id cat,46
+lymphocytes_count,46
+person,46
+BREAST,46
+littermate,46
+ethnic group,46
+run id,46
+monocytes_count,46
+processing batch,46
+parasite density on admission,46
+surface marker,46
+lane id,46
+mean.corpuscular.volume,46
+active_disease,45
+serologic response status,45
+days post-infection,45
+patient sample,45
+host cell line,45
+digestives_symptoms,45
+cell line / strain,45
+radiation sensitivity,45
+major_organ_involvement,45
+subject/sample source id,45
+type of library,45
+tissue acquisition,45
+inoculation,45
+severity binary,45
+cell surface markers,45
+vaccine administration,45
+severe_eosinophilia,45
+receptor status,44
+strain source,44
+histone mark,44
+survival group,44
+host organism,44
+vendor,44
+histological grade,44
+growth type,44
+time of sampling,44
+translocation,44
+modality,44
+clinical phenotype details,44
+cell/tissue type,44
+intervention group,44
+prior chemotherapy,43
+temp,43
+day of collection,43
+collection date,43
+nutritional state,43
+days ill,43
+Tissue Factor,43
+differentiation status,43
+injection,42
+age/disease timepoint,42
+age years,42
+Cluster,42
+markers used for sorting,42
+specificity,42
+differentiation time,42
+number cag repeats,42
+Conditioning,42
+state of culture,42
+Donor type,42
+days post exposure,42
+maternal age,42
+experimental variables,42
+length of exposure,42
+time post-vaccination,42
+days post_infection,42
+age and_strain,42
+antibody treatment,42
+main group,42
+fusion,41
+er status,41
+Disease,41
+tumor/control,41
+post-treatment day,41
+patient id no,40
+patient reference,40
+nicotine,40
+collection,40
+percentage of tumor cells,40
+sample condition,40
+who class,40
+days post-prime,40
+disease phase,40
+overall.survival,40
+gel_bead_version,40
+source cell,40
+treatments,40
+oxygen flow,40
+batch_id,40
+hemolysis score,40
+sample.name,40
+repeated samples,40
+tumor.grade,39
+qualifying condition,39
+radiation exposure,39
+autopsy,39
+days post challenge,39
+sample pool,39
+pipeline.version,39
+cause.of.death,39
+experimental repeat,39
+"normal individual, Tissue",39
+neuropathological.information,39
+tau_score,39
+amyloid,39
+profession,39
+clinical.diagnosis.history,39
+age at biopsy date,39
+freezer,39
+specific,39
+host cell type,38
+pooled,38
+genomic modification,38
+resection,38
+labor,38
+nulliparous,38
+cells_loaded,38
+postsurgical-treatment,38
+isogenic_group,38
+sample_time,38
+histological response,38
+experimental batch,38
+data file subset,38
+Virus Strain,38
+hereditary status,38
+construct,38
+donor no,37
+sample case,37
+data type,37
+library prep kit,37
+virus-stimulation,37
+mating type,37
+drug concentration,37
+perturbation type,37
+Source,37
+Family History,37
+Cycle,37
+tumor vs. normal,37
+paired with,37
+Cell type,37
+Mouse model,36
+location type,36
+batch number,36
+experimental,36
+timepoint_in_hours,36
+environment,36
+day transplantation,36
+growth time mins,36
+first-line therapy,36
+number of replicates,36
+water salinity,36
+clinical group,36
+organ obtained,36
+duration in hours,36
+inhibitor removal,36
+subject label,36
+clinical information,36
+primary cells,36
+subject id/diagnosis,36
+skin anatomy,36
+medicine,36
+time post-treatment,36
+indication,36
+viral infection,36
+maximal prior disease extend,36
+locale,36
+parasite,36
+disease diagnosis,36
+individuals,36
+hours of infection,36
+clone id,36
+Age of Onset,35
+pulldown,35
+experimental design,35
+culture age,35
+Clinical Status,35
+Twin Pair ID,35
+Age at interview & blood sampling,35
+years of disease,35
+strain  background,35
+hours post fertilization,35
+primary vs metastatic,35
+donation source,35
+host_cell_line,35
+nonunion type,35
+person id,35
+biopsy vs surgical resection,35
+developmental stages,35
+labversion description,35
+time_point,34
+day of isolation,34
+body site,34
+disease subset,34
+GOLD stage,34
+conditioned media type,34
+Sample code,34
+Tissue type,34
+cell tye,34
+asbestos-fiber count,34
+Type of Surgery,34
+Dead/Alive,34
+conditioned media origin,34
+untreated/treated,34
+Location of distant metastasis,34
+Age at time of surgery,34
+method of preservation,34
+treated stem cells,34
+tandem repeat number,34
+Location tumor,34
+Tumor type,34
+time post initiation of treatment,33
+tretment,33
+isolate sensitivity,33
+clinical phenotypes,33
+extract protocol,33
+viral infected,33
+chip-antibody vendor,33
+sputum smear status,33
+core code,33
+chip-antibody cat,33
+parasite isolate,33
+growth conditions,33
+age at collection,33
+definite analysis,33
+cell treatment,33
+infectious,33
+total volume,33
+alternative_name,33
+genetic variants inheritance,33
+gene,33
+infection type,32
+time after treatment (and reversal) in hours,32
+water type,32
+virus taxon id,32
+age post-hatch,32
+diffuse/limited,32
+plasmodium falciparum infection status,32
+twins,32
+cultivation,32
+plasmodium strain,32
+animal number,32
+virus accession number,32
+disrupted gene id,32
+KIT mutation,32
+age fraction,31
+maternal health status,31
+gestational stage,31
+cell line name,31
+Cell line,31
+treatment before challenge,31
+study sample number,31
+antibody status,31
+age at time of collection,31
+lymphoma subtype,31
+single or double infection,31
+paired patient,31
+note_other,30
+Medication at blood sampling,30
+knock-in line,30
+post-operative day,30
+sampling point,30
+brain section,30
+test,30
+cell culture condition,30
+phenotypes,30
+chemical treatment,30
+parental-strain,30
+promoter,30
+primary_recurrence,30
+no treatment,30
+knockout status,30
+treatment_effect,30
+growth time,30
+library barcode,30
+cell-type,30
+differentiation state,30
+derived cell line,30
+preparation method,30
+single or double infected,30
+viral concentration,30
+induction time,30
+virus added,30
+neural tube defect,30
+source cell line,30
+age at skin biopsy,30
+line name in manuscript,30
+sample beneath,30
+tumor tissue source,30
+cell passage,30
+pretreatment time,30
+schedule,30
+Time after induction,30
+tumor organ site,30
+cell line/type,30
+mitotic activity,29
+derived from metastatic site,29
+cell cycle stage,29
+microorganism_source_of_infection,29
+microorganism_blood,29
+kit expression,29
+Pathogen,29
+sofa_admission,29
+affected status,29
+lactate,29
+infection route,29
+clinical_subgroup,29
+age at examination,29
+tumor cell line,29
+lymphocytes,29
+los,29
+strain origin,29
+creatinine,29
+geographical origin,29
+treatment concentration,29
+skin phenotype,28
+plate code,28
+growth temperature,28
+study protocol,28
+biopsy collection date,28
+spike-in organism,28
+bone marrow mononuclear cells sorted from,28
+number of individuals per sample,28
+stress condition,28
+genetic modifications,28
+experimental factor,28
+sum.risk.factors,28
+psoriasis area-and-severity index,28
+dev_stage at treatment initiation,28
+pulmonary.disease,28
+time infected,28
+cancer.past,28
+tobacco,28
+culture status,28
+active cancer,28
+cardiovascular.disease,28
+Ethnic group,28
+donor status,28
+specific primer,27
+hospitalization,27
+series,27
+culture results,27
+run,27
+follicular lymphoma grade,27
+interval_death_symptoms_onset_days,27
+intubation_days,27
+sort fraction,27
+pulmonary compartment,27
+sampling location,27
+participant condition,27
+additional cell lineages present in dataset,27
+cell type source,27
+lung radiation dose,27
+cell stage,27
+psoriasis subtype,27
+tissues,27
+cell samples,26
+oncologic diagnosis,26
+clone phenotype,26
+time point days,26
+sample.type,26
+variant,26
+prior systemic therapy,26
+Scaling,26
+gender source,26
+time designation after sclerosis,26
+current systemic therapy,26
+harvesting,26
+clinical,26
+skin score,26
+previous severity,26
+Body surface area,26
+Age of patient,26
+Duration of psoriasis,26
+time since sclerosis,26
+time since transplant,26
+Overall erythema,26
+Passage,26
+culture stage,26
+donor group,26
+degree of infiltrate,26
+primary cell line,26
+Induration,26
+twin status,25
+pathological type,25
+strain/isolate,25
+death_time,25
+body part,25
+ectopic expression,25
+collection_date,25
+tissue subgroup,24
+cell line/tissue,24
+cell line/tissue source,24
+pathogen strain,24
+time post treatment,24
+clone type,24
+hours post-infection,24
+days post treatment,24
+channel type,24
+anatomical site,24
+monocyte,24
+fip status,24
+implantation,24
+organoid status,24
+biological replicates,24
+mouse exhibiting symptoms on the day of sample collection,24
+array id,24
+sorted cell type,24
+lymphocyte,24
+resection_type,24
+sex steroid priming,24
+morphologic form,24
+sampling time point,24
+day of collection/passage,24
+vasopressor,24
+environmental condition,24
+mortality,24
+molecular condition,24
+spinal cord region,24
+tumor identifier,24
+harvest time post treatment,24
+treatment condition/type,24
+Construct,24
+pharmacologic treatment type,24
+cell or tissue type,24
+interaction status,24
+disease course,24
+disease onset,24
+Mouse strain,24
+time post_injury,24
+pair status,24
+mouse dietary condition,24
+extract,24
+starting cell,24
+percent_aligned,24
+differentiation_age,24
+exogenous gene expressed,24
+embryonic day,24
+blood island injection,24
+tumor_size,24
+time post-infection,24
+cell preparation,24
+library outgrowth conditions,24
+os_days,24
+os_group_median,24
+technical_replicate_number,24
+biological_replicate_number,24
+gametocyte status,24
+date_death,24
+medical history,23
+sepsis stage,23
+cell dissociation,23
+donor line,23
+os months,23
+sex predicted,23
+peripheral blood,23
+maternal disease status,23
+drug administration,23
+molecule source,23
+tumor sample,23
+histological subtype,23
+flowcell id,22
+modification,22
+disease condition,22
+treatment effect,22
+organism,22
+sample status,22
+fever day,22
+Sample Group,22
+decode_name,22
+duration of treatment,22
+replicate type,22
+strand,22
+other treatment,22
+race_ethnicity,22
+generation,22
+oxygen level,22
+metastatic status,22
+associated primary tumor no,22
+injected with,22
+cells/condition,22
+tumor_site,22
+generation/colony,21
+electrophysiology,21
+hippocampal slice id,21
+Karyotype,21
+growth medium/treatment,21
+chemical probe,21
+antibody vendor name,21
+somatic mutation,21
+respiratory score,21
+antibody target description,21
+patient line,20
+gastrointestinal involvement,20
+sorting,20
+Chief Disease,20
+Order Code,20
+Sample Type,20
+status sample,20
+infection_state,20
+samples,20
+Treatment,20
+virus subtype,20
+Death Cause,20
+fed with,20
+Cause of Death,20
+chip processing date,20
+injection age,20
+Inflammation,20
+type of death,20
+animal id number,20
+ocular involvement,20
+vascular involvement,20
+StudyID,20
+genital ulcer,20
+arthritis,20
+donor strain,20
+Sample,20
+enrichment,20
+vaccination state,20
+At Risk,20
+oral ulcer,20
+Parity,20
+InfantSex,20
+MaternalAge,20
+glioma model,20
+cell transduction,20
+cell marker,20
+lot number,20
+molecular subtype/phenotypic state,20
+human tissue source,20
+Shear exposure,20
+calcium level,20
+erythema nodule,20
+isolation stage,19
+timepoint_progressors,19
+treatment_type,19
+desiccation,19
+fus aggregation state,19
+tumor model,19
+sort purification strategy,19
+time point post infection,19
+library kit,19
+time of treatment,19
+genetic engineering,19
+age at onset,19
+tumor origin,19
+carcinoid syndrome,19
+duration of untreated disease in month,19
+disease outcome,19
+cold ischemia time,19
+donation time,19
+strains,19
+drug response,19
+digestion protocol,18
+cellular_component,18
+reason for liver resection,18
+drug resistance,18
+collection buffer,18
+vital_status,18
+patient tumor related pain status,18
+hospital admission,18
+time post-exposure,18
+tissue location,18
+age_category,18
+collection point,18
+compound concentration,18
+translocations,18
+construct expression,18
+"donor age, sex",18
+protein expression,18
+mechanical condition,18
+injury model,18
+infection host,18
+overall survival,18
+radiology,18
+febrile seizure,18
+culture format,18
+experimental variable,18
+donor race,18
+menstrual phase,18
+sort-gate,18
+expression construct,18
+culture batch,18
+age of disease onset percentile,18
+age of disease onset,18
+experiment grouping,18
+cell type origin,17
+Wash Condition,17
+age in months,17
+Hybridization Time,17
+Labeling Condition,17
+sort gate,17
+protein,17
+day of development,17
+mouse individual id,17
+clip antibody,17
+stitched reads,17
+subject status/id,17
+raw reads,17
+aligned reads,17
+level,17
+viral,17
+composite,17
+parasite/gametocyte stage,17
+art treatment,17
+cold ischemia_time,16
+cell status,16
+ar or asthma,16
+performance,16
+time of_treatment,16
+mouse group,16
+autism diagnostic,16
+treatment/infection,16
+alk mutation status,16
+dementia status,16
+incubation time,16
+patient_status,16
+age tier,16
+has_drug,16
+mouse id tag,16
+fasting,16
+location of tumors,16
+osteogenic potential,16
+vascular support,16
+data analysis id,16
+has_pressure,16
+viral titre,16
+developmental age,16
+mode of growth,16
+aortic valve,16
+pool,16
+parent_strain,16
+gene_knockout,16
+source/differentiation,16
+brain tumor region,16
+common name,16
+sorting fraction,16
+adipogenic potential,16
+lung section/portion,16
+genotype of original donor,16
+seizure group,16
+serum,16
+treatment agent,16
+day of protocol,16
+compound treatment,16
+strain/model,16
+cytogenetic,16
+Patient Number,16
+initial tumor volume,16
+family code,16
+labeling protocol,16
+oxygen,16
+sorted fraction,16
+cell line_name,15
+detachment,15
+cell_origin,15
+surface markers,15
+weekly dosing,15
+primers,15
+phase description,15
+pulmonary cavitation,15
+es line,15
+malignancy class,15
+sample subgroup,15
+tissue class,15
+tumor class,15
+specific-host,15
+manuscript library id,15
+gel bead version,15
+polarization state,15
+precursor,15
+disease classification,15
+differentiation time point,15
+animal no,15
+sample_label,15
+incidence,15
+risk grade,15
+library preparation protocol,15
+stim,15
+experiment name,15
+lab code,15
+age of  culture,15
+glioma grade,15
+gender composition,15
+length of culture,15
+virus dose,15
+rip,15
+vaccination_status,14
+ubi,14
+cell origin,14
+alternative name,14
+experimental run,14
+pretreatment,14
+genotype abbreviation,14
+immune infiltration,14
+sorting profile,14
+measure,14
+patients,14
+vaccination status,14
+disease in non-fip,14
+genotype/varation,14
+age at blood draw,14
+original cell line,14
+brain tumor,14
+Lab ID,14
+subset group,14
+case or control,14
+antigenic stimulation,14
+location/side,14
+hind-limb paralysis,14
+Weight,13
+risk group,13
+block storage,13
+pooling,13
+receptor expression,13
+time to relapse,13
+harvest time point,13
+placental sex,13
+Tumor Stage,13
+material type,13
+cag repeat,13
+serology,13
+functional connectivity,13
+cell lining,13
+sorted population,13
+paradigm,13
+transplant,13
+onset age,13
+clone background/id,12
+agent concentration,12
+treatment of mice,12
+treatment_dose,12
+antibody vendor,12
+treatment condition,12
+unique sample identifier,12
+growth phase of cells,12
+autophagy induction,12
+clone name,12
+Tumor tissue,12
+brain tissue,12
+rift valley fever virus,12
+div,12
+time after virus injection,12
+days,12
+cell type background,12
+disease grade,12
+oxygen tension,12
+Sample group,12
+sorting probe,12
+product,12
+angiography,12
+engraftment,12
+interstitial pneumonia,12
+age at biopsy,12
+strain id,12
+radiation response,12
+cell line type,12
+oxygenation,12
+time post-immunization,12
+efflux status,12
+expressing,12
+isolation of tumor cells,12
+time point in the model of dormancy,12
+host age,12
+"age, yrs",12
+density gradient region,12
+primary cell type,12
+immunization route,12
+Drug,12
+tumor inoculation,12
+group id,12
+mouse status,12
+genetic_modification,12
+analysis group,12
+developmental stage/tumor stage,12
+source muscle,12
+seizures/month,12
+cell line origin,12
+type of insertion,12
+operator,12
+insertion site distance to gene,12
+tumor cell type,12
+clinical manifestation,12
+chemical,12
+sample identifier,12
+chemical modification,12
+replica,12
+fold enrichment,12
+pluripotent,12
+original tumor,12
+chronological age,12
+incubation period,12
+molarity of infection,12
+maturation to macrophage,12
+melanoma cell type,12
+biological source,12
+scale,12
+MASTECTOMY,12
+duration of disease,12
+fetal lung tissue donor,12
+total/partial resection,12
+model type,12
+technical replicates,12
+surgical indication,12
+internal patient id,12
+internal sample id,12
+long description,12
+surgical approach,12
+melanoma,12
+donor fibroblasts,12
+knockdown target,12
+days under treatment,12
+inoculation dose,12
+submission date,12
+sediment,12
+mouse stain,12
+dietary regiment,12
+histological findings of renal specimen,12
+renal biopsy,12
+chronic medication,12
+acute medication,12
+day of organoid differentiation,12
+polarization treatment,12
+treatment type,12
+company,12
+drinking,12
+major reason_for_surgery,12
+name of tissue,12
+duration of cultivation,12
+cell line passage,12
+final age at death,12
+blood pressure,12
+death day,12
+type of cultivation plate,12
+replicate experiment,12
+hydrogen peroxide treatment,11
+urine protein,11
+chip antibody manufacturer,11
+plating,11
+antibody used,11
+embryos pooled,11
+donor id/status,11
+antigen capture,11
+area/tissue,11
+primary/ recurrent,11
+metastatic/primary,11
+species,11
+array barcode,11
+organoid generation,11
+salt.score,11
+recurrent/primary,11
+graft recipient strain,10
+bacteria,10
+malaria status,10
+cell line for infection,10
+library backbone,10
+library label_name,10
+metabolic activity,10
+Developmental stage,10
+graft donor strain,10
+maternal state,10
+original biopsy for this patient,10
+animals pooled,10
+gestational days,10
+number of animals,10
+isolated by,10
+age at diagnosis in months,10
+rescue,10
+cell model id,10
+injected cell line,10
+driver gene,10
+day post transplant,10
+camp treatment/level,10
+culture medium,10
+initial preparation,10
+transcription factor expression level,10
+lung section,10
+age at study start,10
+before or after treatment,10
+time of last follow up in months,10
+source id,10
+tissue donor,10
+genotype/disease state,10
+anatomic site,10
+day after intubation,10
+intensive care,10
+viral inactivation,10
+cutting enzymes,10
+chip antibody details,10
+age at harvest,10
+treatment/sample type,10
+symptom duration,10
+antigen reactivity,10
+time of day,9
+weight phenotype,9
+antibody name,9
+cell-subtype,9
+parental cell type,9
+number of cag repeats,9
+age range,9
+data presented in the manuscript,9
+differentiation replicate,9
+mutation frequency,9
+derived culture,9
+knockout group,9
+subject identifier,9
+resistance profile,9
+growth factors in the culture medium,9
+date of isolation,9
+infection rate,9
+exacerbation day,9
+infection period,9
+treatment timing,9
+hit.status,9
+process order,9
+process day,9
+genotype background,9
+anatomical region,9
+number of_samples,9
+sorting criteria,9
+oxygen condition,9
+embryo phenotype,9
+host mouse strain,9
+antibody maker,9
+conditioned medium,9
+age/time point,9
+subpopulation,9
+etiology,9
+ps status,8
+overexpressing,8
+microglia population,8
+nitrogen source,8
+environmental factor,8
+peptide genotype,8
+growth phase/media,8
+myopathic motor_unit_potentials,8
+secondary antibody,8
+day after transplantation,8
+vaccine dose,8
+age of_diagnosis,8
+selection pressure drugs,8
+genotype/treatment,8
+time since first diagnosis,8
+age of_onset,8
+neuroblastoma cell line,8
+fus variant,8
+life cycle stage,8
+mutation details,8
+time point of infection,8
+treatment/group,8
+primary antibody,8
+conditioned media source,8
+cartilage pellets,8
+derived cell_type,8
+portion of branchial arch,8
+growing media conditions,8
+sample region,8
+culture/treatment,8
+cell number per well,8
+embryo stage,8
+phase of growth,8
+cognitive impairment,8
+well diameter in um,8
+transient expression,8
+macrophages,8
+anatomic segment,8
+activation,8
+molecule purification,8
+sample code,8
+clinical comments,8
+exogenous treatment,8
+Disease state,8
+disease feature,8
+original strain,8
+allele,8
+nes status,8
+digestion enzyme,8
+incubation temperature,8
+animal treatment,7
+cell type depletion,7
+neural crest-derived,7
+passage/days,7
+"developmental stage, weeks",7
+culture/clone_id,7
+patient age at diagnosis,7
+infectious strain,7
+virus family,7
+cell type implantation,7
+time of_drug_treatment,7
+chip antibody manufacturers,7
+bilirubin,7
+ast,7
+Species,7
+virus genus,7
+incubation,7
+encode accession,7
+host tissue,7
+alt,7
+sample name synonym,7
+variation,6
+stain,6
+Labeling_reference,6
+sorted subset of cells,6
+time after exposure,6
+Extraction_reference,6
+Extraction_amount,6
+Sample_reference,6
+genotype & treatment,6
+cell subsets,6
+testosterone treated,6
+sorted cell,6
+zinc status,6
+genotype of founder fish,6
+Subject_reference,6
+zone,6
+als status,6
+site of_disease_onset,6
+treatment time-point,6
+strain recipient,6
+source patient gender,6
+strain donor,6
+derived cell type,6
+nodal status,6
+Extraction_concentration,6
+gene induction,6
+Sex of recipient mice,6
+organoid formation,6
+collection timepoint,6
+subject relationship,6
+cell morphology,6
+group_tag,6
+stem cell clone,6
+cell strain,6
+overexpressed target,6
+mice,6
+mating pair,6
+tissue storage,6
+distant metastasis,6
+ARN_quality,6
+extraction batch,6
+sample barcode,6
+tobacco use,6
+methylation-enrichment,6
+fraction/population,6
+mother from,6
+sample population,6
+Sex of donor mice,6
+media supplement,6
+developmental stage/age,6
+disease name,6
+tic class,6
+expression level,6
+molecule subtypes,6
+life cycle,6
+nitrogen,6
+days from treatment,6
+tubules with elongated spermatids,6
+tubules with round spermatids,6
+hairpin,6
+round of selection,6
+age of donor/age of host,6
+time after stimulation,6
+protocols,6
+tubular shadows,6
+exposed pollutants,6
+Cell strain,6
+mouse cell genotype/variation,6
+cross,6
+human cell genotype/variation,6
+behavior,6
+replicate number,6
+chip antibody reference,6
+Growth Medium,6
+mean number of oocysts,6
+sample replicate number,6
+human tumor cell line,6
+strain_recipient,6
+parental/ne-like state,6
+hippocampal sclerosis,6
+number of half-sclerotomes,6
+oocyst prevalence,6
+cell phase,6
+Bra,6
+fluid,6
+source gender,6
+tumor position,6
+body weight,6
+antibody lot,6
+age category,6
+day post neural induction,6
+sample state,6
+stable knockdown,6
+days_since_positive_test,6
+sampling post confirm,6
+antibody cat,6
+tubules with spermatocytes,6
+hybrid,5
+depletion,5
+spike protein used,5
+sorted,5
+cancer predisposition,5
+pull-down,5
+original tumor type,5
+days in culture,5
+post-symptom onset,5
+id,5
+biopsy position,5
+cytogenetics,5
+of passage,5
+library_strategy,5
+term accession number,5
+in-line barcodes,5
+tissue type type,5
+invasive behavior,5
+donor sex,5
+term source ref,5
+cell line_infection,5
+marker,5
+culture variation,5
+phase growth,4
+donor gender,4
+number of_tracheas,4
+oxygen status,4
+experiment performed in,4
+strategy,4
+background mice,4
+media additions,4
+mice group,4
+cell enrichment,4
+Cells,4
+donor disease state,4
+culture supplement,4
+infrequent clonal strain code,4
+responder status,4
+vector construct,4
+growth_condition,4
+blood,4
+chip magnetic beads,4
+host mouse_tissue,4
+gating,4
+source organ,4
+days of final differentiation,4
+plasmodium infection,4
+number of_animals,4
+acidity,4
+mouse genotype,4
+express,4
+associate geo_sample,4
+isolation column,4
+antibody lot number,4
+associated geo,4
+stage of disease,4
+patient-derived cell line,4
+sample age,4
+knock-in,4
+passages after establishing stable clones,4
+antibody antibody description,4
+immunology,4
+length of infection,4
+data type description,4
+culture time,4
+antibody vendor id,4
+control id,4
+tissue zone,4
+treatment/agent,4
+mouse tissue,3
+molecular diagnosis,3
+bacterial cells,3
+details,3
+fibrosis,3
+tissue extraction,3
+reference lot,3
+extraction_protocol_fragmentation,3
+skin score at biopsy site,3
+non-small cell lung cancer Derived from metastatic site,3
+experimental conditions,3
+developmental state,3
+host cells,3
+embryo characteristic,3
+reference cat,3
+treatment / timepoint,3
+months post infection,3
+bacteria strain,3
+immortalization method,3
+Organ,3
+bacteria tissue,3
+severity grade,3
+infection time point,3
+large cell lung cancer Derived from metastatic site,3
+diffuse vs limited,3
+days_post_infection,3
+Morphology,3
+histopathological diagnostic,3
+reactivity,3
+cell subpopulation/marker,3
+donor diagnosis,3
+cell characterization,3
+allergy,3
+assay type,3
+control source,3
+tumor who grade,2
+affinity purification,2
+OVARY,2
+AXILLARY NODE,2
+"BREAST, LOCAL EXCISION",2
+ligation,2
+clip antibody vendor,2
+clip antibody cat,2
+reference condition,2
+source cells,2
+PARTIAL MASTECTOMY,2
+COMPLETION MASTECTOMY,2
+postnatal day,2
+feature type,2
+SENTINEL AXILLARY LYMPH NODE,2
+life form,2
+selection media,2
+test condition,2
+"BREAST, MASTECTOMY",2
+domain,2
+cell line source gender,2
+par-clip,2
+cell mixing ratio,2
+data_type,2
+rounds of infection,2
+solvent,2
+"BRAIN (CEREBELLUM), BIOPSY",2
+sample tag_information,2
+months_survival,2
+progression_status,2
+months_progression,2
+cell line source age,2
+cell line source tissue,2
+stage of differentiation,2
+organoid type,2
+cause of death,2
+transplanted with,2
+treatment_term_name,2
+duration_units,2
+cell mixture,2
+incubation partner,1
+small molecule,1
+mammalian host,1
+small cell lung cancer Derived from metastatic site,1
+cell lie,1
+mitotic rate,1
+Infection Status,1
+hot,1
+injected cells,1
+age of patient when tumor sample obtained,1
+positive Down screening risk,1
+passage no,1
diff --git a/RDAS_RDOMICS/scripts/sample_characteristics_harmonization/sample_characteristics_harmonization_output/4_llm_clustered_sample_characteristics.csv b/RDAS_RDOMICS/scripts/sample_characteristics_harmonization/sample_characteristics_harmonization_output/4_llm_clustered_sample_characteristics.csv
new file mode 100644
index 0000000..826da7f
--- /dev/null
+++ b/RDAS_RDOMICS/scripts/sample_characteristics_harmonization/sample_characteristics_harmonization_output/4_llm_clustered_sample_characteristics.csv
@@ -0,0 +1,11 @@
+standardized_term,label_count,total_occurrence_count,labels
+Biospecimen Type,475,393113,"['tissue', 'cell type', 'cell line', 'tissue type', 'celltype', 'tissue anatomic site', 'cell description', 'cell sex', 'cell', 'Tissue', 'tissue source', 'tissue/cell type', 'cell subtype', 'country of serum collection', 'organ failure', 'cell_type', 'cell subset', 'tissue preparation', 'tissue of origin', 'cell karyotype', 'cell lineage', 'tissue_type', 'flowcell', 'sorted cells', 'cell population', 'organ/tissue', 'predicted celltype', 'predicted parent celltype', 'timepoint biopsy', 'lymphocyte_percent', 'lymphocyte_absolute', 'monocyte_percent', 'monocyte_absolute', 'cell projection', 'cell line code', 'white_blood_cell_count', 'tissue_depot', 'red blood cells', 'white blood cells', 'specimen', 'blood obtained', 'tissue substructure', 'tissue structure', 'organ', 'cell phenotype', 'per lymphocytes', 'per monocytes', 'TargetedCellType', 'CellLine', 'cells', 'tissue.type', 'specimen_name', 'biopsy', 'monocytes', 'blood collection tube coating', 'tissue subtype', 'tissue region', 'blood_group', 'cell types', 'responder cell line', 'cell line of origin', 'biopsy type', 'cell source', 'tissue/cell line', 'tissue archive method', 'spike-in cell_line', 'spike-in cell_type', 'tissue origin', 'blood.source', 'clinical diagnosis specimen', 'biopsy data, villus height to crypt depth', 'cell_line', 'tissue notes', 'cell fraction', 'responder cells', 'biopsy site', 'tissue-of-origin', 'tissue processing', 'cell part', 'serum type', 'cell culture', 'cell line source', 'cell type/line', 'primary tissues', 'transplanted organ', 'time of blood draw', 'cell stimulation', 'lymphocyte.reaction', 'cell state', 'cell compartment', 'cell subpopulation', 'tissue compartment', 'cell line background', 'cell density', 'number of cells', 'specimen site', 'cell number', 'tissue group', 'source tissue', 'cell lines', 'minimum reads per cell during initial processing', 'day blood taken', 'tissue status', 'cell markers', 'lymphocyte_count', 'source cell type', 'tissue/cell info', 'sorted cell_type', 'cells detected', 'tissue derivation', 'data tissue_collection', 'tissue collection', 'age at blood collection', 'organ system', 'day of tissue harvest', 'parental cell line', 'other organ lesion', 'stem cell', 'cell surface marker', 'developmental stage/tissue', 'lymphocytes_count', 'monocytes_count', 'tissue acquisition', 'cell surface markers', 'cell/tissue type', 'Tissue Factor', 'percentage of tumor cells', 'source cell', 'age at biopsy date', 'cells_loaded', 'Cell type', 'organ obtained', 'primary cells', 'Age at interview & blood sampling', 'biopsy vs surgical resection', 'Tissue type', 'cell tye', 'treated stem cells', 'cell treatment', 'cell line name', 'Cell line', 'Medication at blood sampling', 'cell culture condition', 'cell-type', 'derived cell line', 'source cell line', 'age at skin biopsy', 'tumor tissue source', 'cell passage', 'tumor organ site', 'cell line/type', 'cell cycle stage', 'tumor cell line', 'lymphocytes', 'biopsy collection date', 'bone marrow mononuclear cells sorted from', 'additional cell lineages present in dataset', 'cell type source', 'cell stage', 'tissues', 'primary cell line', 'tissue subgroup', 'cell line/tissue', 'cell line/tissue source', 'monocyte', 'sorted cell type', 'lymphocyte', 'cell or tissue type', 'starting cell', 'blood island injection', 'cell preparation', 'cell dissociation', 'peripheral blood', 'cells/condition', 'cell transduction', 'cell marker', 'cellular_component', 'tissue location', 'cell type origin', 'cell status', 'serum', 'cell line_name', 'cell_origin', 'tissue class', 'cell origin', 'age at blood draw', 'original cell line', 'cell lining', 'growth phase of cells', 'Tumor tissue', 'brain tissue', 'cell type background', 'age at biopsy', 'cell line type', 'isolation of tumor cells', 'primary cell type', 'cell line origin', 'tumor cell type', 'maturation to macrophage', 'melanoma cell type', 'histological findings of renal specimen', 'renal biopsy', 'name of tissue', 'cell line passage', 'blood pressure', 'area/tissue', 'cell line for infection', 'injected cell line', 'cell-subtype', 'parental cell type', 'neuroblastoma cell line', 'derived cell_type', 'cell number per well', 'macrophages', 'cell type depletion', 'cell type implantation', 'sorted subset of cells', 'cell subsets', 'sorted cell', 'derived cell type', 'cell morphology', 'stem cell clone', 'tissue storage', 'cell phase', 'biopsy position', 'tissue type type', 'cell line_infection', 'cell enrichment', 'Cells', 'blood', 'source organ', 'tissue zone', 'bacterial cells', 'tissue extraction', 'skin score at biopsy site', 'non-small cell lung cancer Derived from metastatic site', 'Organ', 'bacteria tissue', 'large cell lung cancer Derived from metastatic site', 'cell subpopulation/marker', 'cell characterization', 'source cells', 'cell line source gender', 'cell mixing ratio', 'BRAIN (CEREBELLUM), BIOPSY', 'cell line source age', 'cell line source tissue', 'cell mixture', 'small cell lung cancer Derived from metastatic site', 'cell lie', 'injected cells', 'stimulation', 'phenotype', 'well', 'morphology', 'case number', 'transduction', 'sorted compartment', 'population', 'source type', 'number of relapses', 'preparation', 'Phenotype', 'line type', 'clinical phenotype', 'case_phenotype', 'als phenotype', 'sub-population', 'health status', 'bacterial lysate', 'responder', 'simulation', 'karyotype', 'compartment', 'parental line', 'FISH origin', 'surface marker', 'body site', 'clinical phenotypes', 'phenotypes', 'clone phenotype', 'twin status', 'Karyotype', 'enrichment', 'lot number', 'surface markers', 'es line', 'clone name', 'efflux status', 'source muscle', 'fold enrichment', 'sediment', 'initial preparation', 'anatomic site', 'derived culture', 'genotype background', 'subpopulation', 'tic class', 'Morphology', 'chip antibody', 'antibody', 'molecule subtype', 'type', 'molecule type', 'library type', 'molecule', 'isolate', 'material', 'parity', 'background', 'genetic background', 'epithelial', 'culture_result', 'smear_results', 'full_genotype', 'hip_circumference', 'waist_circumference', 'microdissection', 'assayed molecule', 'lymphs', 'line', 'isolation_method', 'skin type', 'library well', 'library plate', 'platelet', 'antigen', 'markers', 'skin', 'colony of_origin', 'hemoglobin genotype', 'trachea region', 'intrinsic subtype', 'anatomic_location', 'anatomic location', 'microbiota status', 'sputum_smear', 'sputum_culture', 'growth', 'eye', 'brain bank', 'splice variant', 'transplant type', 'chip target', 'bal_culture', 'bal_smear', 'smear of index case', 'components', 'fibrinogen', 'target molecule', 'enzyme', 'marrow', 'variety', 'hemisphere', 'microglia media', 'histological..subtype', 'unsorted or sorted', 'input material', 'subclass', 'fracture site', 'immune_or_nasal', 'any_immune', 'Type', 'embryo', 'anatomical location', 'fetus', 'lesional (ls) vs. normal', 'Genetic background', 'Histological type', 'vs type', 'histological.type', 'lobe', 'cytology', 'aspiration site', 'vector constructs', 'sandwich type', 'types', 'modifications', 'library-type', 'lymph node number', 'upper or lower extremity', 'growth pattern', 'volar or non-volar', 'isolation method', 'specific heart region', 'lymph node', 'graft source', 'derived from', 'BREAST', 'type of library', 'fusion', 'hemolysis score', 'autopsy', 'resection', 'construct', 'mating type', 'location type', 'skin anatomy', 'pulldown', 'knock-in line', 'brain section', 'knockout status', 'mitotic activity', 'derived from metastatic site', 'kit expression', 'pulmonary compartment', 'sampling location', 'Body surface area', 'body part', 'anatomical site', 'resection_type', 'morphologic form', 'spinal cord region', 'Construct', 'extract', 'exogenous gene expressed', 'molecule source', 'generation', 'generation/colony', 'electrophysiology', 'glioma model', 'fus aggregation state', 'sort purification strategy', 'protein expression', 'menstrual phase', 'protein', 'clip antibody', 'viral', 'composite', 'osteogenic potential', 'aortic valve', 'adipogenic potential', 'lung section/portion', 'cytogenetic', 'sorted fraction', 'precursor', 'genotype abbreviation', 'sorting profile', 'receptor expression', 'material type', 'cag repeat', 'serology', 'density gradient region', 'pluripotent', 'MASTECTOMY', 'total/partial resection', 'model type', 'type of cultivation plate', 'urine protein', 'embryos pooled', 'lung section', 'anatomical region', 'microglia population', 'fus variant', 'portion of branchial arch', 'anatomic segment', 'allele', 'neural crest-derived', 'molecule subtypes', 'hairpin', 'pull-down', 'cytogenetics', 'marker', 'number of_tracheas', 'knock-in', 'embryo characteristic', 'immortalization method', 'OVARY', 'AXILLARY NODE', 'BREAST, LOCAL EXCISION', 'PARTIAL MASTECTOMY', 'COMPLETION MASTECTOMY', 'SENTINEL AXILLARY LYMPH NODE', 'BREAST, MASTECTOMY', 'small molecule']"
+Biospecimen Disease Condition,560,197439,"['disease state', 'disease', 'diagnosis', 'condition', 'infection', 'disease status', 'tumor type', 'housing condition', 'diseasestate', 'clinical diagnosis', 'histologic diagnosis', 'tumor grade', 'infection status', 'tumor location', 'infection states', 'disease group', 'final diagnosis', 'cancer status', 'hours post infection', 'disease severity', 'infection protocol', 'working_diagnosis', 'first_diagnosis', 'tumor grading', 'pathology', 'disease duration', 'disease_category', 'institutional tumor diagnosis', 'disease location', 'disease staging', 'cancer site', 'tumor', 'neuropathological_diagnosis', 'clinical_diagnosis', 'disease_duration_years', 'culture condition', 'site of infection', 'cancer type', 'infection code', 'culture conditions', 'disease_status', 'reference diagnosis', 'condition description', 'adjusted disease severity index', 'diagnosis date', 'growth condition', 'additional conditions', 'disease symptom', 'other diseases', 'disease type', 'disease subtype', 'DiseaseState', 'diagnosis.after.path.re.review', 'diagnosis.of.record', 'lung disease', 'chronic diseases', 'molecular.diagnosis', 'primary.tumor', 'tumor_name', 'radiation administered prior to tumor resection', 'histological diagnosis', 'tumor localization', 'broad diagnosis', 'behavior at diagnosis', 'tumor category', 'disease activity', 'stimulation condition', 'primary diagnosis', 'light condition', 'diagnosis total', 'diagnosis hep flex', 'diagnosis rectum', 'lung pathology', 'tumor_entity_subtype', 'diagnosis colonic', 'diagnosis details', 'diagnosis anal perianal', 'diagnosis oral', 'diagnosis rectal', 'disease_state', 'tumor full_name', 'disease_group_detailed', 'disease_group', 'pathology_note', 'distance from the tumor center', 'index_case_disease_site', 'tumor subgroup', 'years since diagnosis', 'histopathology', 'skin disease', 'Diagnosis', 'tumor subtype', 'clinical condition', 'infection group', 'worm infection', 'Tumor size', 'disease_extension', 'tumor status', 'culture_conditions', 'primary disease', 'incubation conditions', 'neuropathological diagnosis', 'Condition', 'tumor.in.left.right.lobe', 'tumor region', 'disease_duration', 'hour post infection', 'disease category', 'tumor type/grade', 'virus infection', 'exposure condition', 'bacterial infection', 'infection state', 'infection duration', 'parental tumor subtype', 'preliminary diagnosis', 'primary tumor site', 'malaria infection', 'tumor histology', 'metastatic tumor site', 'lesion_disease_factor', 'infection type exposure', 'primary tumor', 'duration of infection', 'experimental condition', 'malignant tumor', 'disease model', 'initial tumor increase/(-)decrease', 'tumor size', 'tumor_grading', 'tumor source', 'conditioning received', 'conditions', 'active_disease', 'Conditioning', 'Disease', 'tumor/control', 'disease phase', 'tumor.grade', 'qualifying condition', 'clinical.diagnosis.history', 'tumor vs. normal', 'viral infection', 'maximal prior disease extend', 'disease diagnosis', 'hours of infection', 'years of disease', 'disease subset', 'conditioned media type', 'conditioned media origin', 'Location tumor', 'Tumor type', 'growth conditions', 'infection type', 'plasmodium falciparum infection status', 'single or double infection', 'infection route', 'stress condition', 'pulmonary.disease', 'cancer.past', 'active cancer', 'cardiovascular.disease', 'oncologic diagnosis', 'environmental condition', 'molecular condition', 'disease course', 'disease onset', 'tumor_size', 'library outgrowth conditions', 'maternal disease status', 'disease condition', 'associated primary tumor no', 'tumor_site', 'Chief Disease', 'tumor model', 'tumor origin', 'disease outcome', 'mechanical condition', 'Wash Condition', 'Labeling Condition', 'location of tumors', 'brain tumor region', 'initial tumor volume', 'tumor class', 'disease classification', 'disease in non-fip', 'brain tumor', 'treatment condition', 'disease grade', 'tumor inoculation', 'original tumor', 'molarity of infection', 'duration of disease', 'genotype/disease state', 'infection rate', 'infection period', 'oxygen condition', 'conditioned medium', 'conditioned media source', 'growing media conditions', 'Disease state', 'disease feature', 'site of_disease_onset', 'disease name', 'tumor position', 'cancer predisposition', 'original tumor type', 'growth_condition', 'plasmodium infection', 'length of infection', 'molecular diagnosis', 'experimental conditions', 'months post infection', 'tumor who grade', 'reference condition', 'test condition', 'rounds of infection', 'Infection Status', 'clinical info', 'histology', 'primary site', 'brain region', 'who category', 'initial ich volume', 'who grade', 'number of malaria infections', 'section', 'infection_status', 'Histopathological diagnostic', 'hours post-invasion', 'hours post invasion', 'mechanical ventilation', 'antibody description', 'inflammation status', 'injection_type', 'Histology', 'localization', 'isolate type', 'location of onset', 'dissection', 'injection site', 'clinical indication', 'lesion status', 'clinic status', 'metastatic site', 'hours_post_infection', 'injection', 'er status', 'neuropathological.information', 'hours post fertilization', 'viral infected', 'infectious', 'water type', 'maternal health status', 'single or double infected', 'clone type', 'hours post-infection', 'channel type', 'interaction status', 'pair status', 'infection_state', 'vaccination status', 'type of insertion', 'clinical manifestation', 'incubation period', 'viral inactivation', 'environmental factor', 'nes status', 'zinc status', 'round of selection', 'reference lot', 'reference cat', 'histopathological diagnostic', 'cohort', 'smoking status', 'pasi', 'pathologic status', 'grade', 'surgical status', 'outcome', 'status', 'subtype', 'culture result', 'site_onset', 'metastasis', 'severity score', 'stress', 'smoker', 'severity', 'illness', 'Illness', 'viral_positivity', 'neoplastic', 'consortium lung phenotype', 'malaria_transmission', 'consortium lung phenotype surrogate variable', 'meconium ileus status', 'persistent ps aer status', 'malaria_status', 'dementia', 'diagnostic_mean', 'death', 'survival_status', 'progression', 'parasitemia', 'tst skin test', 'joint problems', 'family history', 'symptoms onset date', 'with or without clonal heterogeneity', 'international prognostic index', 'dead or alive at the end of follow-up', 'total number of genomic aberrations', 'seizure', 'asthma', 'smear_result', 'anti-centromere', 'recurrence', 'os.mos', 'surgical.outcome', 'psychiatric disorder', 'gastrointestinal disorder', 'cerebral palsy', 'mutational subclass', 'birth defects', 'neurological disorder', 'developmental/speech disorder', 'diabetes', 'percent_weight_loss', 'molecular classification', 'recurrent_status', 'dysplasia now', 'health state', 'cigarette smoker', 'medical.history', 'inflammation_status', 'pregnancy status', 'cirrhosis present', 'chronic hypertension', 'survival after surgery', 'death with metastasis', 'outcome related', 'infected/uninfected', 'neoplasia type', 'symptom severity', 'viral shedding', 'tst result', 'symptomatic', 'smoking', 'hypertension', 'cag_repeat', 'conversion', 'prognosis', 'parasitemia category', 'survival status', 'parasite density', 'malign', 'protect_outcome', 'isolate_sensitivity', 'exposure_latent', 'pasi score', 'obesity', 'stress exposure', 'genetic class', 'symptom', 'mutation_carrier_status', 'cag_repeats', 'phase', 'das score', 'infectivity', 'total cholesterol', 'fibrosis degree', 'interim pet response', 'primary/recurrent', 'pasi_total', 'Outcome', 'scar', 'lesion', 'lymphoma type', 'remission', 'swollen joints', 'pain', 'tender joints', 'viral load', 'current status', 'Smoking status', 'endoscopic_activity', 'mitotic index', 'survival characteristics', 'vascular.invasion', 'mutational.status', 'multifocal', 'smoker or non smoker', 'exposed to', 'familial anamnesis', 'onset', 'Status', 'progression_free_survival', 'primary recurrent', 'smoking_status', 'clinical outcome', 'metastasis site', 'glioma', 'subcutaneous neurofibromas', 'plexiform neurofibromas', 'cutaneous neurofibromas', 'facial dysmorphism', 'scoliosis', 'skin-fold freckling', 'Lymph node involvement', 'primary_recurrent', 'clinically_aggressive', 'total skin score', 'lesion_label', 'presence_of_parasites_lesion', 'infiltration', 'severity_score', 'lesion_size', 'bleeding', 'stool frequency', 'clinical presentation', 'alive', 'prodromal status', 'subtypes', 'local skin score', 'location of lesion', 'gene deletion status', 'mutation class', 'fever', 'dyspnea / tachypnea', 'cough', 'primary/metastasis', 'symptoms', 'tuberculosis_history', 'family_history', 'exitus', 'primary mutation', 'copy number gain', 'sofa score', 'als mutation', 'granuloma', 'brain metastasis', 'reason for intubation', 'pregnancy', 'clinical_history', 'cerebral performance category score', 'diplopia', 'mutations', 'decrease of vision', 'onset site', 'relapse', 'syndrome', 'systemic sclerosis subtype', 'parasite density on admission', 'serologic response status', 'digestives_symptoms', 'radiation sensitivity', 'major_organ_involvement', 'severity binary', 'severe_eosinophilia', 'receptor status', 'histological grade', 'clinical phenotype details', 'who class', 'cause.of.death', 'histological response', 'hereditary status', 'Family History', 'clinical information', 'parasite', 'primary vs metastatic', 'nonunion type', 'Dead/Alive', 'Location of distant metastasis', 'isolate sensitivity', 'sputum smear status', 'diffuse/limited', 'KIT mutation', 'antibody status', 'lymphoma subtype', 'primary_recurrence', 'neural tube defect', 'sofa_admission', 'affected status', 'skin phenotype', 'sum.risk.factors', 'psoriasis area-and-severity index', 'hospitalization', 'follicular lymphoma grade', 'psoriasis subtype', 'Scaling', 'skin score', 'previous severity', 'Overall erythema', 'degree of infiltrate', 'pathological type', 'fip status', 'mortality', 'gametocyte status', 'medical history', 'histological subtype', 'metastatic status', 'somatic mutation', 'respiratory score', 'gastrointestinal involvement', 'Death Cause', 'Inflammation', 'ocular involvement', 'vascular involvement', 'genital ulcer', 'arthritis', 'At Risk', 'oral ulcer', 'molecular subtype/phenotypic state', 'erythema nodule', 'reason for liver resection', 'injury model', 'febrile seizure', 'ar or asthma', 'autism diagnostic', 'alk mutation status', 'pulmonary cavitation', 'malignancy class', 'risk grade', 'glioma grade', 'immune infiltration', 'hind-limb paralysis', 'rift valley fever virus', 'engraftment', 'interstitial pneumonia', 'seizures/month', 'surgical indication', 'melanoma', 'major reason_for_surgery', 'primary/ recurrent', 'metastatic/primary', 'recurrent/primary', 'weight phenotype', 'resistance profile', 'embryo phenotype', 'etiology', 'myopathic motor_unit_potentials', 'mutation details', 'cognitive impairment', 'distant metastasis', 'tobacco use', 'parental/ne-like state', 'oocyst prevalence', 'post-symptom onset', 'invasive behavior', 'responder status', 'fibrosis', 'severity grade', 'diffuse vs limited', 'allergy', 'months_survival', 'progression_status', 'months_progression', 'mitotic rate', 'positive Down screening risk']"
+Biospecimen Age,413,197068,"['age', 'time', 'time point', 'timepoint', 'developmental stage', 'Stage', 'day', 'agent', 'age in years', 'Age', 'passage', 'tumor stage', 'passages', 'development stage', 'age_onset', 'age description', 'disease stage', 'treatment time', 'age group', 'infection time', 'year', 'passage_if_expanded', 'doubling time', 'infectious agent', 'collection time point', 'age_weeks', 'age_at_draw', 'time harvest', 'sampling time_point_label', 'time_to_malaria', 'reagent', 'age of enrollment', 'days_in_hospital', 'age_at_diagnosis', 'age of onset of persistent ps aer or censored age', 'days since vaccine', 'dev_stage', 'age_at_death_years', 'passage number', 'time.from.exposure.months', 'day of trial', 'day post infection', 'age at death', 'days since vaccination', 'sampling timepoint', 'gold stage', 'year of surgery', 'age in year', 'days of differentiation', 'age at_treatment', 'treatment age_group', 'animal age', 'treatment/time point', 'dosage', 'week', 'osteogenesis day', 'timepoint_months', 'InitialTimePoint', 'age at diagnosis', 'path.stage', 'differentiation stage', 'description of day', 'differentiation day', 'day_of_euthanasia', 'visit day', 'age_diagnosis_years', 'age of onset', 'Tumor stage', 'TimeUnit', 'sorter day', 'art start year', 'sampling_timepoint', 'time post-stimulation', 'developmental_stage', 'days_symptom_onset', 'overall.survival..days', 'sampling time', 'time_since_onset', 'stimulation time and condition', 'age at_diagnosis', 'dev stage', 'lineage', 'day of differentiation', 'survival time', 'days post drug', 'collection time point (#) or necropsy', 'parasite stage', 'time-point', 'days after infection', 'differentiation_stage', 'cage', 'age.days', 'infection.time.point.days', 'embryonic stage', 'excision year', 'time points', 'Time', 'ventilator-free days', 'day-post-infection', 'time post infection', 'day after seeding', 'os month', 'day of_tumor_harvest', 'infection agent', 'harvesting time', 'collection time', 'time after treatment', 'age at sampling', 'gestational age', 'Usage number', 'average library size', 'exposure time', 'age of psoriasis onset', 'treatment time point', 'ko induction_time', 'days post-vaccination', 'age at transplant', 'age.at.operation', 'disease_stage', 'days post onset of symptoms', 'age, months', 'survival_time', 'age of death', 'AGE', 'clinical stage', 'survival time in months', 'draw day', 'relapse time', 'stage of repair process', 'culture days', 'cancer stage', 'growth stage', 'activation agent', 'storage', 'age at initiation', 'ann arbor stage', 'sampling.time', 'harvest time', 'overall.survival.time', 'days post infection', 'life stage', 'time in culture', 'collection day', 'stage', 'days after stimulation', 'labeling agent', 'survival year', 'time after infection', 'treatment/timepoint', 'age and disease', 'year of isolation', 'timepoint_description', 'age at surgery', 'sporozoite age', 'age/gender', 'treatment stage', 'oxygen percentage', 'age in_yrs', 'injury/age', 'sex/age', 'experimental day', 'day post-infection', 'treatment_time', 'age fracture', 'days post-infection', 'time of sampling', 'day of collection', 'days ill', 'age/disease timepoint', 'age years', 'differentiation time', 'days post exposure', 'maternal age', 'time post-vaccination', 'days post_infection', 'post-treatment day', 'days post-prime', 'days post challenge', 'timepoint_in_hours', 'day transplantation', 'growth time mins', 'time post-treatment', 'Age of Onset', 'culture age', 'developmental stages', 'time_point', 'day of isolation', 'GOLD stage', 'Age at time of surgery', 'time post initiation of treatment', 'age at collection', 'time after treatment (and reversal) in hours', 'age post-hatch', 'age fraction', 'gestational stage', 'age at time of collection', 'post-operative day', 'growth time', 'induction time', 'pretreatment time', 'Time after induction', 'age at examination', 'dev_stage at treatment initiation', 'time infected', 'interval_death_symptoms_onset_days', 'intubation_days', 'time point days', 'time designation after sclerosis', 'time since sclerosis', 'time since transplant', 'Passage', 'culture stage', 'death_time', 'time post treatment', 'days post treatment', 'sampling time point', 'day of collection/passage', 'harvest time post treatment', 'time post_injury', 'differentiation_age', 'embryonic day', 'time post-infection', 'os_days', 'sepsis stage', 'fever day', 'injection age', 'MaternalAge', 'isolation stage', 'timepoint_progressors', 'time point post infection', 'time of treatment', 'age at onset', 'duration of untreated disease in month', 'cold ischemia time', 'donation time', 'time post-exposure', 'age_category', 'age of disease onset percentile', 'age of disease onset', 'age in months', 'day of development', 'parasite/gametocyte stage', 'cold ischemia_time', 'time of_treatment', 'incubation time', 'age tier', 'developmental age', 'treatment agent', 'day of protocol', 'differentiation time point', 'age of  culture', 'block storage', 'time to relapse', 'harvest time point', 'Tumor Stage', 'onset age', 'agent concentration', 'time after virus injection', 'days', 'time post-immunization', 'time point in the model of dormancy', 'age, yrs', 'developmental stage/tumor stage', 'chronological age', 'days under treatment', 'final age at death', 'death day', 'Developmental stage', 'gestational days', 'age at diagnosis in months', 'day post transplant', 'age at study start', 'time of last follow up in months', 'day after intubation', 'age at harvest', 'time of day', 'age range', 'exacerbation day', 'process day', 'age/time point', 'day after transplantation', 'age of_diagnosis', 'time since first diagnosis', 'age of_onset', 'life cycle stage', 'time point of infection', 'cartilage pellets', 'embryo stage', 'passage/days', 'developmental stage, weeks', 'time of_drug_treatment', 'time after exposure', 'treatment time-point', 'collection timepoint', 'developmental stage/age', 'days from treatment', 'time after stimulation', 'age category', 'day post neural induction', 'days_since_positive_test', 'days in culture', 'of passage', 'days of final differentiation', 'stage of disease', 'passages after establishing stable clones', 'culture time', 'treatment/agent', 'treatment / timepoint', 'infection time point', 'days_post_infection', 'postnatal day', 'stage of differentiation', 'passage no', 'experiment', 'datatype description', 'collection_method', 'tag', 'culture', 'clinical status', 'fraction', 'lab description', 'survival_yr', 'growth phase', 'case', 'date harvest', 'surgery number', 'survival', 'induction date', 'exposure', 'culture type', 'development', 'category', 'experiment type', 'description', 'state', 'differentiation batch', 'growth medium', 'Cause of death', 'survival cluster', 'differentiation', 'overall.survival.months', 'os_month', 'differentiation_method', 'cag', 'culture media', 'isolation source', 'growth media', 'infected', 'animal name', 'clinical type', 'culture method', 'experiment label', 'infectious challenge', 'experimental status', 'Degree of differentiation', 'Case', 'experimental set', 'sampling site', 'Differentiation Method', 'experiment batch', 'isolation', 'growth type', 'collection date', 'differentiation status', 'state of culture', 'collection', 'overall.survival', 'experimental batch', 'experimental', 'experimental design', 'Clinical Status', 'labversion description', 'Type of Surgery', 'parasite isolate', 'sampling point', 'differentiation state', 'experimental factor', 'culture status', 'harvesting', 'collection_date', 'os months', 'Cause of Death', 'type of death', 'collection buffer', 'collection point', 'overall survival', 'experimental variable', 'culture batch', 'source/differentiation', 'phase description', 'stim', 'experiment name', 'length of culture', 'long description', 'maternal state', 'culture medium', 'differentiation replicate', 'date of isolation', 'process order', 'activation', 'incubation', 'life cycle', 'Growth Medium', 'sorted', 'data type description', 'developmental state', 'cause of death', 'incubation partner', 'birth date', 'follow up years', 'ga', 'hours', 'phase of growth']"
+External_sample_id,415,166895,"['sample type', 'patient id', 'individual', 'subject id', 'donor', 'subject', 'patient', 'subject status', 'sample id', 'subjectid', 'sample', 'sample group', 'mouse id', 'donor id', 'slide no', 'participant id', 'controlid', 'donor_id', 'patientid', 'batch id', 'individual id', 'barcode', 'patient_id', 'animal id', 'patient diagnosis', 'provider', 'patient gender', 'cell line id', 'sampleID', 'donor_age', 'donor_sex', 'donor_health_status', 'donor_ethnicity', 'participant', 'patient viral load', 'patient group', 'sample source', 'chip_antibody_provider', 'sample alias', 'sample common name', 'sample collection site', 'patient sample id', 'sample.id', 'patient age', 'ID', 'covid_status', 'slide', 'donor age', 'sample_code', 'volunteer id', 'blood sample id', 'plate id', 'patient_asymptomatic', 'blood sample_id', 'in_covid_only_dataset', 'external_donor_name', 'cosmic id', 'patient classification_at_first_sample', 'days since_first_sample', 'external id', 'days since first sample', 'sample id alt', 'patient classification at first sample', 'sample class', 'patient category', 'vendor id', 'platform_id_id design', 'sample_name', 'slide_position', 'sample name', 'sample timing', 'covid cat', 'covid', 'subject_id', 'sample material', 'sample collection time', 'symptomatic or asymptomatic at sample collection', 'non human primate individual id', 'vaccine side effects', 'age at sample drawn', 'sample preparation', 'sample_group', 'slide id', 'subject group', 'sample group_label', 'sample number within subject', 'sample collection', 'animal_id', 'tissue id', 'monkey id', 'donor category', 'slide name', 'sample time', 'Individual', 'subject number', 'sample_set', 'donor_id_blinded', 'sample_group_granular', 'donor type', 'paired samples', 'patient.code', 'sample_type', 'subject condition', 'subject diagnosis', 'sample day', 'tissue/sample type', 'hybridization batch', 'diagnosis recto sigmoid', 'patient_age', 'patient_visit', 'patient sex', 'patient code', 'patient subgroup', 'patient number', 'hybridization protocol', 'study id', 'sample tissue', 'sample_id', 'long-covid symptoms', 'study participant', 'sample_site', 'clinical diagnosis patient', 'sample recovery type', 'sample_barcode', 'slide_id', 'deceased donors, only left kidney included in the analysis', 'side', 'identifier', 'patient treatment', 'subjects', 'sample origin', 'time since steroid dose', 'donor_genotype', 'sample collection time post infection', 'scan id', 'steroids', 'mouse_id', 'donor code', 'type of sample', 'patient population', 'sample age proxy', 'patient condition', 'family id', 'sample subseries', 'matched pair id', 'replicate id', 'donor number', 'individual identifier', 'specimen_barcode', 'mouse identifier', 'patient source', 'biopsy number for this subject', 'sample number', 'Patient', 'unique_subject_identifier', 'sample collection time post virus infection', 'tissue/treatment id', 'donor_type', 'animal identifier', 'library id', 'age patient', 'patient identifier', 'covid infection_status', 'covid severity_status', 'steroids_cat', 'nasal_steroids', 'pool id', 'number of pooled individuals', 'peptide', 'minimum counts per cell threshold used to remove background barcodes', 'sample plate', 'patient identification number', 'sample description', 'donor covid_status', 'steroid', 'with_lesion_sample', 'id sample', 'id simple', 'methylation_geo_id', 'geo_sample_id', 'ref id', 'time of sample collection', 'patient_no', 'patient no', 'subject age', 'pediatric patient', 'sample name in supplementary file', 'cartridge', 'covid status', 'rabbit id', 'patient response', 'alternative sample name', 'publication id', 'study_id', 'Sample ID', 'sample/subject id', 'samples of different individuals pooled', 'organoid line', 'tumor side', 'Mouse ID', 'swollen eyelid', 'sample prep', 'sample/time point', 'subject gender', 'slide tissue area', 'dissected embryo id number', 'patient/control id', 'sample id cat', 'run id', 'lane id', 'patient sample', 'subject/sample source id', 'Donor type', 'patient id no', 'patient reference', 'sample condition', 'batch_id', 'sample.name', 'repeated samples', 'sample pool', 'normal individual, Tissue', 'amyloid', 'sample_time', 'donor no', 'sample case', 'subject label', 'subject id/diagnosis', 'individuals', 'clone id', 'Twin Pair ID', 'person id', 'Sample code', 'virus taxon id', 'disrupted gene id', 'study sample number', 'paired patient', 'library barcode', 'sample beneath', 'number of individuals per sample', 'donor status', 'participant condition', 'cell samples', 'sample.type', 'Age of patient', 'donor group', 'organoid status', 'mouse exhibiting symptoms on the day of sample collection', 'array id', 'sex steroid priming', 'tumor identifier', 'donor line', 'tumor sample', 'flowcell id', 'sample status', 'Sample Group', 'hippocampal slice id', 'patient line', 'Sample Type', 'status sample', 'samples', 'animal id number', 'StudyID', 'donor strain', 'Sample', 'carcinoid syndrome', 'patient tumor related pain status', 'donor age, sex', 'donor race', 'Hybridization Time', 'mouse individual id', 'subject status/id', 'patient_status', 'mouse id tag', 'data analysis id', 'genotype of original donor', 'Patient Number', 'sample subgroup', 'manuscript library id', 'sample_label', 'incidence', 'patients', 'Lab ID', 'location/side', 'clone background/id', 'unique sample identifier', 'Sample group', 'strain id', 'group id', 'sample identifier', 'fetal lung tissue donor', 'internal patient id', 'internal sample id', 'donor fibroblasts', 'day of organoid differentiation', 'hydrogen peroxide treatment', 'donor id/status', 'array barcode', 'organoid generation', 'graft donor strain', 'original biopsy for this patient', 'cell model id', 'source id', 'tissue donor', 'treatment/sample type', 'subject identifier', 'number of_samples', 'peptide genotype', 'sample region', 'sample code', 'culture/clone_id', 'patient age at diagnosis', 'sample name synonym', 'Sample_reference', 'Subject_reference', 'source patient gender', 'strain donor', 'organoid formation', 'subject relationship', 'sample barcode', 'sample population', 'Sex of donor mice', 'tubules with elongated spermatids', 'tubules with round spermatids', 'age of donor/age of host', 'sample replicate number', 'fluid', 'sample state', 'hybrid', 'id', 'in-line barcodes', 'donor sex', 'donor gender', 'donor disease state', 'acidity', 'associate geo_sample', 'patient-derived cell line', 'sample age', 'antibody vendor id', 'control id', 'donor diagnosis', 'sample tag_information', 'organoid type', 'age of patient when tumor sample obtained', 'batch', 'replicate', 'plate', 'site', 'location', 'source', 'animal', 'clone', 'study', 'chip_antibody_lot', 'vital status', 'array', 'library date', 'chip antibody vendor', 'volunteer code', 'library', 'plate_number', 'volunteer', 'subset', 'family', 'line number', 'array batch', 'folder name', 'sort population', 'size', 'roi type', 'number of_mice', 'Subsets', 'replicates', 'library input', 'health_status', 'study number', 'bar code', 'person', 'vendor', 'pooled', 'Source', 'chip-antibody vendor', 'alternative_name', 'animal number', 'plate code', 'replicate type', 'antibody vendor name', 'library kit', 'vital_status', 'common name', 'family code', 'animal no', 'alternative name', 'sorted population', 'antibody vendor', 'radiation response', 'library backbone', 'number of animals', 'als status', 'nodal status', 'fraction/population', 'replicate number', 'hippocampal sclerosis', 'tubules with spermatocytes', 'number of_animals', 'associated geo', 'clip antibody vendor', 'enrollment batch', 'code', 'original geo accession', 'hospital', 'volunteer number', 'alias', 'pool no', 'Order Code', 'lab code']"
+Treatment,303,131474,"['treatment', 'group', 'vaccine', 'treatment description', 'treatmentshort', 'drug treatment', 'treatment group', 'control', 'control description', 'treatment duration', 'subgroup', 'groups', 'molecular subgroup', 'diagnostic_group', 'classification group', 'chemical compound', 'infected with/healthy control', 'vaccine doses', 'prior treatment', 'response_group', 'grouping', 'vaccine type', 'current medication', 'experiment group', 'treatment location', 'chemotherapy', 'Prior Treatment', 'treatment administration route', 'treatment frequency', 'study group', 'drug', 'experimental group', 'treatment dose', 'treatment arm', 'treatment withdrawal', 'treatment initiation', 'recreational drugs', 'prescription drugs', 'treatment-outcome code', 'radiation.therapy', 'treatment protocol', 'treatment response', 'enzymatic treatment', 'vaccine group', 'dose group', 'group description', 'inhibitor treatment', 'dose_group', 'batch group', 'previous treatments', 'vaccine regimen', 'drug dose', 'hours post-treatment', 'therapy used', 'Group', 'antibiotic treatment', 'healthy control', 'control/intervention', 'treatment status', 'ear treatment', 'therapy', 'compound', 'biological drug', 'treatment_duration', 'control or als', 'vector treatment', 'previous drug treatment', 'antibody group', 'surgical treatment', 'vaccine administered', 'rabbit group', 'treatment outcome', 'group label', 'treatment_duration_in_hours', 'treatment category', 'treatment prior to second surgery', 'vaccine administration', 'survival group', 'intervention group', 'prior chemotherapy', 'antibody treatment', 'main group', 'treatments', 'postsurgical-treatment', 'isogenic_group', 'drug concentration', 'first-line therapy', 'clinical group', 'treatment before challenge', 'chemical treatment', 'no treatment', 'treatment_effect', 'clinical_subgroup', 'treatment concentration', 'prior systemic therapy', 'current systemic therapy', 'treatment condition/type', 'pharmacologic treatment type', 'os_group_median', 'drug administration', 'treatment effect', 'duration of treatment', 'other treatment', 'growth medium/treatment', 'chemical probe', 'Treatment', 'treatment_type', 'drug response', 'drug resistance', 'compound concentration', 'experiment grouping', 'art treatment', 'treatment/infection', 'has_drug', 'seizure group', 'compound treatment', 'pretreatment', 'subset group', 'case or control', 'risk group', 'treatment of mice', 'treatment_dose', 'Drug', 'analysis group', 'chemical', 'chemical modification', 'chronic medication', 'acute medication', 'polarization treatment', 'treatment type', 'camp treatment/level', 'before or after treatment', 'knockout group', 'treatment timing', 'vaccine dose', 'selection pressure drugs', 'genotype/treatment', 'treatment/group', 'culture/treatment', 'exogenous treatment', 'animal treatment', 'genotype & treatment', 'group_tag', 'mice group', 'control source', 'treatment_term_name', 'segment type', 'response', 'resistance', 'animal replicate', 'classification', 'replicate description', 'genetic modification', 'brain location', 'experimental replicate', 'case/control', 'molecular subtype', 'protect outcome', 'other_medication', 'variant type', 'translocation', 'experimental repeat', 'genomic modification', 'donation source', 'tretment', 'genetic modifications', 'translocations', 'dementia status', 'polarization state', 'experimental run', 'antibody name', 'mutation frequency', 'nitrogen source', 'antibody lot', 'temperature', 'medium', 'tuberculin skin test', 'treated with', 'delivery', 'stimulus', 'chip_antibody', 'irradiated', 'first vaccination', 'second vaccination', 'selection marker', 'induced', 'injection_materials', 'curative_intent', 'media', 'amplification', 'ventilation', 'chip-antibody', 'diet', 'medications/vitamin names', 'stimulant', 'vaccination.assignment', 'surgical_interval_mo', 'active ingredient', 'knockout', 'primed', 'rip antibody', 'antibody manufacturer', 'diabetes_medication', 'chip antibody lot', 'knockdown', 'exposed stress', 'watch and wait', 'Exposures', 'vector', 'trial arm', 'surgery', 'prophylaxis', 'exercise intensity', 'challenge', 'surgery type', 'radiation', 'bone-marrow grafting status', 'bone-marrow grafting type', 'injected virus', 'alcohol', 'number of immunization boost', 'rounds_to_cure', 'clinical trial phase', 'other biologic medicines use', 'pathogen exposure', 'viral challenge', 'culture platform', 'debris removal', 'perturbation class', 'perturbation', 'cross-linked', 'route administered', 'vehicle', 'over-expression', 'length of exposure', 'nicotine', 'oxygen flow', 'radiation exposure', 'library prep kit', 'virus-stimulation', 'perturbation type', 'environment', 'inhibitor removal', 'medicine', 'untreated/treated', 'cultivation', 'growth temperature', 'implantation', 'vasopressor', 'modification', 'oxygen level', 'injected with', 'antibody target description', 'fed with', 'Shear exposure', 'desiccation', 'genetic engineering', 'construct expression', 'culture format', 'expression construct', 'fasting', 'mode of growth', 'gene_knockout', 'vaccination_status', 'antigenic stimulation', 'transplant', 'autophagy induction', 'oxygen tension', 'angiography', 'genetic_modification', 'surgical approach', 'plating', 'antibody used', 'antigen capture', 'rescue', 'intensive care', 'growth factors in the culture medium', 'antibody maker', 'overexpressing', 'growth phase/media', 'secondary antibody', 'primary antibody', 'transient expression', 'testosterone treated', 'gene induction', 'overexpressed target', 'methylation-enrichment', 'media supplement', 'chip antibody reference', 'stable knockdown', 'antibody cat', 'depletion', 'spike protein used', 'phase growth', 'oxygen status', 'strategy', 'media additions', 'culture supplement', 'affinity purification', 'ligation', 'selection media', 'solvent', 'transplanted with']"
+Biospecimen Organism,144,124692,"['strain', 'strain background', 'organismpart', 'organism part', 'cell organism', 'strain/background', 'mouse strain', 'background strain', 'mouse model', 'strain description', 'host', 'source_organism', 'Strain', 'strain/genotype', 'mouse number', 'mouse', 'parasite strain', 'OrganismPart', 'virus strain', 'malaria strain', 'strain name', 'host cell', 'mouse genotype/variation', 'replicate mouse', 'viral strain', 'host genotype', 'mouse line abbreviation', 'infected host', 'bacterial strain', 'host strain', 'mouse line', 'host mice strain', 'host vendor', 'host strain/background', 'mouse selection', 'genotype/strain', 'mouse age', 'laboratory strain', 'organism_status', 'recipient strain', 'organism_part', 'infection strain', 'strain info', 'parental strain', 'host cell line', 'cell line / strain', 'strain source', 'host organism', 'age and_strain', 'host cell type', 'Virus Strain', 'Mouse model', 'strain  background', 'host_cell_line', 'plasmodium strain', 'parental-strain', 'microorganism_source_of_infection', 'microorganism_blood', 'strain origin', 'spike-in organism', 'strain/isolate', 'pathogen strain', 'Mouse strain', 'mouse dietary condition', 'organism', 'human tissue source', 'strains', 'infection host', 'mouse group', 'parent_strain', 'strain/model', 'specific-host', 'host age', 'mouse status', 'mouse stain', 'species', 'graft recipient strain', 'host mouse strain', 'original strain', 'infectious strain', 'Species', 'host tissue', 'strain recipient', 'cell strain', 'Cell strain', 'mouse cell genotype/variation', 'human cell genotype/variation', 'human tumor cell line', 'strain_recipient', 'infrequent clonal strain code', 'host mouse_tissue', 'mouse genotype', 'mouse tissue', 'host cells', 'bacteria strain', 'mammalian host', 'genotype', 'genotype/variation', 'infected with', 'os_status', 'selection', 'OS status', 'genome/variation', 'couple number', 'pathogens', 'immune status', 'parasite line', 'viral status', 'parental origin', 'Genotype', 'specificity', 'specific', 'series', 'strand', 'genotype/varation', 'malaria status', 'ps status', 'stain', 'background mice', 'hot', 'virus', 'companion animals', 'agricultural animals', 'os', 'origin', 'pathogen', 'breed', 'bacterium', 'living', 'litter', 'virus type', 'cattle breed', 'viral genus', 'viral family', 'mosquito', 'Pathogen', 'geographical origin', 'virus subtype', 'bacteria', 'virus family', 'virus genus', 'genotype of founder fish', 'mice', 'life form']"
+Biospecimen Sex,20,104956,"['gender', 'Sex', 'sex', 'Gender', 'animal sex', 'fetal sex', 'biological sex', 'female', 'SEX', 'gender source', 'sex predicted', 'InfantSex', 'gender composition', 'placental sex', 'Sex of recipient mice', 'source gender', 'biologics', 'gene', 'biological source', 'nulliparous']"
+Other,411,93670,"['visit', 'segment', 'reference', 'datatype', 'tst', 'dataset', 'roi', 'date', 'biological replicate', 'assay', 'geographical region', 'labversion', 'roi number', 'protection', 'lab', 'class', 'area', 'library prep', 'pipeline version', 'censored', 'platesimple', 'experiment_type', 'albumin', 'hematocrit', 'hemoglobin', 'model', 'bin', 'birth_place', 'method', 'adjusted household density', 'geographic location', 'field_site', 'atmosphere', 'geographic origin', 'lane.number', 'center', 'weight', 'lane', 'sort', 'recipient', 'cluster', 'immature_granulocytes_percent', 'genotype_abbreviation', 'immature_granulocytes_absolute', 'allele actual', 'well address', 'plate_location', 'allele nominal', 'match', 'smear microscopy', 'instrument model', 'supplier', 'affy_batch', 'library prep_plate', 'assigned cluster', 'probe_detection', 'title', 'filtered peaks', 'extract name', 'assay name', 'project', 'hemisphere_name', 'platelet_count', 'multisector', 'injection_roi', 'array_design', 'cluster_label', 'is_technical_replicate', 'duplicate_pair', 'material support', 'library name', 'genome build', 'label', 'bait', 'chain', 'outlier', 'date collected', 'gene_count', 'nuclei count', 'technique', 'recruiting site', 'procedure date', 'smoking start date', 'smoking amount', 'smoking stop date', 'binding density', 'cap score', 'chip antibody cat', 'negative normalization factor', 'note', 'history', 'surface area', 'link', 'who', 'nuclei_counts', 'amplification cycles', 'smoke', 'visit_date', 'mean corpuscular volume', 'job/role', 'technical replicate', 'index', 'genetic testing', 'unpublished', 'city', 'datasets', 'volume', 'geographical location', 'training.test', 'used for analysis', 'block_name', 'structure acronym', 'set', 'read length', 'duplication_rate', 'align_unique', 'exon_ratio', 'align_input', 'reads_all', 'nuclear_reads', 'library_prep_date', 'extract_date', 'repeat', 'season', 'other information', 'sorting strategy', 'escape', 'diffuse', 'hist.score', 'feeding', 'bal sampling date', 'timing', 'processing', 'library quality', 'visit number', 'pair', 'run_date', 'muscle mass', 'waist to hip ratio', 'reference genome_for_processed_files', 'fat mass', 'reference genome_for_alignment', 'region of birth', 'period', 'buffer', 'extraction date', 'draw_date', 'comment', 'LabeledExtract', 'expanded allele cag repeat count', 'factor', 'paired material support', 'input', 'further operations', 'efficacy', 'buffer_volume', 'protein exchange', 'buffer_volume_unit', 'study_origin', 'library prep. kit', 'restriction enzyme', 'classifier_mes', 'aerosol.run', 'lane.ordinal', 'notes', 'adapter', 'target gene', 'Other', 'technology', 'sofa', 'application', 'country', 'met_amplification', 'other batch', 'date of array', 'batch.date', 'fragments in clean bam', 'sensor', 'spike-in', 'other', 'admission', 'circumstances', 'target', 'geo series', 'library strategy', 'geo accession', 'Filter number', 'cortical_score', 'striatal_score', 'channel count', 'reporter', 'roi lot', 'chemistry', 'purification', 'replicate # in experiment', 'progression_free_survival_censor', 'experiment year_month', 'instance', 'integrative analysis', 'panel', 'expression', 'adapter sequence', 'mib', 'geo expression data', 'replicate / experiment', 'ClinicalInformation', 'spike-ins', 'preservation method', 'tags', 'restriction enzymes', 'structure', 'backbone', 'genetic variants', 'risk', 'immune border', 'comments', 'cag repeat size', 'library_batch', 'enrichment method', 'library prep person', 'carbon source', 'corrector', 'coo', 'angiogenesis score', 'ras score', 'cag repeats', 'cycling', 'respirations per minute', 'cag length', 'commercial source', 'topography', 'kit mutation', 'library version', 'sort strategy', 'match degree', 'collected_by', 'platform', 'biological_replicate', 'genetic specifics', 'last follow-up', 'ago protein', 'kit', 'scan method', 'to concatenate', 'total bilirubin', 'littermate', 'processing batch', 'mean.corpuscular.volume', 'histone mark', 'modality', 'temp', 'nutritional state', 'Cluster', 'markers used for sorting', 'number cag repeats', 'experimental variables', 'gel_bead_version', 'pipeline.version', 'tau_score', 'profession', 'freezer', 'labor', 'data file subset', 'data type', 'Cycle', 'paired with', 'batch number', 'number of replicates', 'water salinity', 'locale', 'asbestos-fiber count', 'method of preservation', 'tandem repeat number', 'core code', 'chip-antibody cat', 'definite analysis', 'total volume', 'genetic variants inheritance', 'twins', 'virus accession number', 'note_other', 'test', 'promoter', 'preparation method', 'line name in manuscript', 'lactate', 'los', 'creatinine', 'tobacco', 'specific primer', 'culture results', 'run', 'sort fraction', 'variant', 'clinical', 'ectopic expression', 'biological replicates', 'percent_aligned', 'technical_replicate_number', 'biological_replicate_number', 'date_death', 'decode_name', 'sorting', 'chip processing date', 'Parity', 'calcium level', 'hospital admission', 'radiology', 'sort-gate', 'sort gate', 'stitched reads', 'raw reads', 'aligned reads', 'level', 'performance', 'vascular support', 'has_pressure', 'viral titre', 'pool', 'sorting fraction', 'oxygen', 'detachment', 'primers', 'gel bead version', 'rip', 'ubi', 'measure', 'Weight', 'pooling', 'functional connectivity', 'paradigm', 'div', 'sorting probe', 'product', 'oxygenation', 'expressing', 'operator', 'insertion site distance to gene', 'replica', 'scale', 'technical replicates', 'knockdown target', 'submission date', 'company', 'drinking', 'replicate experiment', 'chip antibody manufacturer', 'salt.score', 'library label_name', 'metabolic activity', 'animals pooled', 'isolated by', 'driver gene', 'transcription factor expression level', 'cutting enzymes', 'chip antibody details', 'antigen reactivity', 'number of cag repeats', 'data presented in the manuscript', 'hit.status', 'sorting criteria', 'well diameter in um', 'molecule purification', 'clinical comments', 'digestion enzyme', 'incubation temperature', 'chip antibody manufacturers', 'bilirubin', 'ast', 'encode accession', 'alt', 'variation', 'Labeling_reference', 'Extraction_reference', 'Extraction_amount', 'zone', 'mating pair', 'ARN_quality', 'extraction batch', 'mother from', 'expression level', 'nitrogen', 'tubular shadows', 'exposed pollutants', 'cross', 'behavior', 'mean number of oocysts', 'number of half-sclerotomes', 'Bra', 'body weight', 'sampling post confirm', 'library_strategy', 'term accession number', 'term source ref', 'experiment performed in', 'vector construct', 'chip magnetic beads', 'gating', 'express', 'isolation column', 'antibody lot number', 'antibody antibody description', 'immunology', 'details', 'reactivity', 'assay type', 'clip antibody cat', 'feature type', 'domain', 'par-clip', 'data_type']"
+Biospecimen Race,10,19755,"['ethnicity', 'race', 'Race', 'Ethnicity', 'self_reported_race', 'race/ethnicity', 'ethnic group', 'Ethnic group', 'race_ethnicity', 'ancestry']"
+Treatment Dosage Regimen,63,19368,"['protocol', 'dose', 'extraction_protocol', 'chip_protocol_chromatin_amount', 'chip_protocol', 'chip_protocol_bead_type', 'chip_protocol_antibody_amount', 'chip_protocol_bead_amount', 'growth protocol', 'duration', 'immunization dose', 'protocol description', 'concentration', 'regimen', 'library protocol', 'duration of illness', 'culture duration', 'protocol number', 'stimulation protocol', 'stimulation duration', 'vaccination dose', 'infectious_dose', 'illness_duration', 'psoriasis duration', 'extract_protocol', 'duration in hours', 'extract protocol', 'viral concentration', 'study protocol', 'lung radiation dose', 'Duration of psoriasis', 'Induration', 'digestion protocol', 'labeling protocol', 'library preparation protocol', 'virus dose', 'inoculation dose', 'dietary regiment', 'duration of cultivation', 'symptom duration', 'Extraction_concentration', 'protocols', 'extraction_protocol_fragmentation', 'duration_units', 'region', 'library preparation method', 'vaccination', 'mutation', 'education', 'library preparation', 'immunization', 'vaccination route', 'vaccination boost', 'derivation', 'induction', 'inoculation', 'indication', 'virus added', 'vaccination state', 'immunization route', 'culture variation', 'schedule', 'weekly dosing']"
diff --git a/RDAS_RDOMICS/scripts/sample_characteristics_harmonization/sample_characteristics_harmonization_output/4_sample_characteristics_vocabulary_fixed.csv b/RDAS_RDOMICS/scripts/sample_characteristics_harmonization/sample_characteristics_harmonization_output/4_sample_characteristics_vocabulary_fixed.csv
new file mode 100644
index 0000000..fc916a0
--- /dev/null
+++ b/RDAS_RDOMICS/scripts/sample_characteristics_harmonization/sample_characteristics_harmonization_output/4_sample_characteristics_vocabulary_fixed.csv
@@ -0,0 +1,11 @@
+standarized_term,synonym,Example_entrys,Definition
+External_sample_id,"patient_id, patient no, patient id, patient', Patient, patients, patient id, patientid, patient_id, patient id no","50,371,018",internal IDs for the patients involved in clinical trials. This id should be included as external sample id only.
+Biospecimen Organism,"species, cell organism, host organism, organism_status, source_organism, microorganism_source_of_infection, microorganism_blood","Homo sapiens, Mus musculus, Danio rerio",Any living biological system (from bacteria to plants to humans)
+Biospecimen Type,"sample type, Specimen type, type of sample, specimen type, physical sample type, specimen_type, Sample Type, Type of Biospecimen, Specimen Type, Biospecimen Type, physical_sample_type, SPEC, tissue type, cell lline, tissue location, cell type, cell name, organismpart, tissue anatomic site, Tissue type, name of tissue, tissue origin, tumor tissue source, tissue/cell info, tissue/cell type, cell line source tissue, cell line/tissue source, tissue location, brain tissue, tissue zone","blood, cell, tissue, feces, Cerebrospinal fluid, stem cell, iPSC, NK cell, liver tissue, brain tissue, red blood cell","The type of a material sample taken from a biological entity for testing, diagnostic, propagation, treatment or research purposes. This includes particular types of cellular molecules, cells, tissues, organs, body fluids, embryos, and body excretory substances. This category also include sub-type of biospecimen, such as cells, tissues, fluids"
+Biospecimen Age,"age, sample collection time, sample age, donor age, cell culture time, age in year, age(year), age of onset, age_weeks, age patient, subject age, age in yrs, age at draw, age at diagnosis","30 years old,24 hours",the age at the time of the collection of biospecimen. Years / months for human donor and hours / days for cell culture 
+Biospecimen Sex,"sex, gender, sugject gender, gender source, patient gender, source patient gender, donor gender, cell line source gender, sex/age, donor sex, animal sex, detal sex, biological sex, SEX, infantSex, sext of nodor mice","male, female",the sex at birth of the donor if the biospecimen is collected from a human donors or cell lines are derived from human tissues
+Biospecimen Race,"race, race/ethnicity, donor race, Ethnicity, self reported Ethnicity, donor ethnicity, race_ethinicity","Caucasian, Asian American, Hispanic, Latin-Americans",the race of the donor if the biospecimen is collected from human donors or cell lines are derived from human tissues. the Ethnicity of the donor if the biospecimen is collected from human donors or cell lines are derived from human tissues
+Biospecimen Disease Condition,"condition, disease status, diagnosis, cohort, stage, subject status, patient status, developmental stage, primary disease, disease classification, diesase group, stage of disease, disease subtpe, lung diseaes, disease condition, disease phase, disease subset, patient condition, sample condition, clinical condition, participant condition","disease (such as cancer), control, healthy, healthy contol, pseudo surgery, simulattion",the disease condition of the donor or other samples
+Treatment,"treatment, intervention, treatment condition, culture condition, growth condition, labeling condition, treatment type, treatment/group, genotype/treatment, culture/treatment, no treatment, treatment, active ingredient, drug treatment, antibody treatment, chemical treatment, treatment agent, treatment/agent, compound treatment, treatment term name, polarization treatment, growth medium/treatment, surgical treatment category, treatment art, treatment condition/type","treatment, placebo, oberservation, drug name, placebo, saline","the treatment group of specimen donor or cell line or animial models, and the name of the treatment"
+Treatment Dosage Regimen,"dosage, treatment description, treatment protocol, treatment dose, treatment_dose, treatment tming, time of drug treatment, days under treatment, duration of treatment, days under treatment, infectious_dose, dose group, vaccine doses, drug dose, lung radiation dose,  treatment dose, drug concentration, drug administration, agent concentration","treatment duration, treatment time, concentration","A Dosage Regimen is the schedule of doses of a medicine outlining the instructions for its safe and effective administration. It includes dose size frequency of administration time interval between administrations duration of treatment administration instructions route of administration dosage form and dosage modifications."
+Other,,,Other labels that do not belong to any other categories. 
\ No newline at end of file
diff --git a/RDAS_RDOMICS/scripts/sample_characteristics_harmonization/sample_characteristics_harmonization_output/5_subclustered_sample_characteristics_v1.csv b/RDAS_RDOMICS/scripts/sample_characteristics_harmonization/sample_characteristics_harmonization_output/5_subclustered_sample_characteristics_v1.csv
new file mode 100644
index 0000000..4c581d7
--- /dev/null
+++ b/RDAS_RDOMICS/scripts/sample_characteristics_harmonization/sample_characteristics_harmonization_output/5_subclustered_sample_characteristics_v1.csv
@@ -0,0 +1,70 @@
+main_category,subcategory,labels
+Biospecimen Type,Tissue and Cell Types,"['tissue', 'cell type', 'cell line', 'tissue type', 'celltype', 'tissue anatomic site', 'cell description', 'cell sex', 'cell', 'Tissue', 'tissue source', 'tissue/cell type', 'cell subtype', 'country of serum collection', 'organ failure', 'cell_type', 'cell subset', 'tissue preparation', 'tissue of origin', 'cell karyotype', 'cell lineage', 'tissue_type', 'flowcell', 'sorted cells', 'cell population', 'organ/tissue', 'predicted celltype', 'predicted parent celltype', 'timepoint biopsy', 'lymphocyte_percent', 'lymphocyte_absolute', 'monocyte_percent', 'monocyte_absolute', 'cell projection', 'cell line code', 'white_blood_cell_count', 'tissue_depot', 'red blood cells', 'white blood cells', 'specimen', 'blood obtained', 'tissue substructure', 'tissue structure', 'organ', 'cell phenotype', 'per lymphocytes', 'per monocytes', 'TargetedCellType', 'CellLine', 'cells', 'tissue.type', 'specimen_name', 'biopsy', 'monocytes', 'blood collection tube coating', 'tissue subtype', 'tissue region', 'blood_group', 'cell types', 'responder cell line', 'cell line of origin', 'biopsy type', 'cell source', 'tissue/cell line', 'tissue archive method', 'spike-in cell_line', 'spike-in cell_type', 'tissue origin', 'blood.source', 'clinical diagnosis specimen', 'biopsy data, villus height to crypt depth', 'cell_line', 'tissue notes', 'cell fraction', 'responder cells', 'biopsy site', 'tissue-of-origin', 'tissue processing', 'cell part']"
+Biospecimen Type,Cell and Tissue Sources,"['serum type', 'cell culture', 'cell line source', 'cell type/line', 'primary tissues', 'transplanted organ', 'time of blood draw', 'cell stimulation', 'lymphocyte.reaction', 'cell state', 'cell compartment', 'cell subpopulation', 'tissue compartment', 'cell line background', 'cell density', 'number of cells', 'specimen site', 'cell number', 'tissue group', 'source tissue', 'cell lines', 'minimum reads per cell during initial processing', 'day blood taken', 'tissue status', 'cell markers', 'lymphocyte_count', 'source cell type', 'tissue/cell info', 'sorted cell_type', 'cells detected', 'tissue derivation', 'data tissue_collection', 'tissue collection', 'age at blood collection', 'organ system', 'day of tissue harvest', 'parental cell line', 'other organ lesion', 'stem cell', 'cell surface marker', 'developmental stage/tissue', 'lymphocytes_count', 'monocytes_count', 'tissue acquisition', 'cell surface markers', 'cell/tissue type', 'Tissue Factor', 'percentage of tumor cells', 'source cell', 'age at biopsy date', 'cells_loaded', 'Cell type', 'organ obtained', 'primary cells', 'Age at interview & blood sampling', 'biopsy vs surgical resection', 'Tissue type', 'cell tye', 'treated stem cells', 'cell treatment', 'cell line name', 'Cell line', 'Medication at blood sampling', 'cell culture condition', 'cell-type', 'derived cell line', 'source cell line', 'age at skin biopsy', 'tumor tissue source', 'cell passage', 'tumor organ site', 'cell line/type', 'cell cycle stage', 'tumor cell line', 'lymphocytes', 'biopsy collection date', 'bone marrow mononuclear cells sorted from', 'additional cell lineages present in dataset', 'cell type source']"
+Biospecimen Type,Cell and Tissue Subgroups,"['cell stage', 'tissues', 'primary cell line', 'tissue subgroup', 'cell line/tissue', 'cell line/tissue source', 'monocyte', 'sorted cell type', 'lymphocyte', 'cell or tissue type', 'starting cell', 'blood island injection', 'cell preparation', 'cell dissociation', 'peripheral blood', 'cells/condition', 'cell transduction', 'cell marker', 'cellular_component', 'tissue location', 'cell type origin', 'cell status', 'serum', 'cell line_name', 'cell_origin', 'tissue class', 'cell origin', 'age at blood draw', 'original cell line', 'cell lining', 'growth phase of cells', 'Tumor tissue', 'brain tissue', 'cell type background', 'age at biopsy', 'cell line type', 'isolation of tumor cells', 'primary cell type', 'cell line origin', 'tumor cell type', 'maturation to macrophage', 'melanoma cell type', 'histological findings of renal specimen', 'renal biopsy', 'name of tissue', 'cell line passage', 'blood pressure', 'area/tissue', 'cell line for infection', 'injected cell line', 'cell-subtype', 'parental cell type', 'neuroblastoma cell line', 'derived cell_type', 'cell number per well', 'macrophages', 'cell type depletion', 'cell type implantation', 'sorted subset of cells', 'cell subsets', 'sorted cell', 'derived cell type', 'cell morphology', 'stem cell clone', 'tissue storage', 'cell phase', 'biopsy position', 'tissue type type', 'cell line_infection', 'cell enrichment', 'Cells', 'blood', 'source organ', 'tissue zone', 'bacterial cells', 'tissue extraction', 'skin score at biopsy site', 'non-small cell lung cancer Derived from metastatic site', 'Organ']"
+Biospecimen Type,Cell and Tissue Characterization,"['bacteria tissue', 'large cell lung cancer Derived from metastatic site', 'cell subpopulation/marker', 'cell characterization', 'source cells', 'cell line source gender', 'cell mixing ratio', 'BRAIN (CEREBELLUM), BIOPSY', 'cell line source age', 'cell line source tissue', 'cell mixture', 'small cell lung cancer Derived from metastatic site', 'cell lie', 'injected cells', 'stimulation', 'phenotype', 'well', 'morphology', 'case number', 'transduction', 'sorted compartment', 'population', 'source type', 'number of relapses', 'preparation', 'Phenotype', 'line type', 'clinical phenotype', 'case_phenotype', 'als phenotype', 'sub-population', 'health status', 'bacterial lysate', 'responder', 'simulation', 'karyotype', 'compartment', 'parental line', 'FISH origin', 'surface marker', 'body site', 'clinical phenotypes', 'phenotypes', 'clone phenotype', 'twin status', 'Karyotype', 'enrichment', 'lot number', 'surface markers', 'es line', 'clone name', 'efflux status', 'source muscle', 'fold enrichment', 'sediment', 'initial preparation', 'anatomic site', 'derived culture', 'genotype background', 'subpopulation', 'tic class', 'Morphology', 'chip antibody', 'antibody', 'molecule subtype', 'type', 'molecule type', 'library type', 'molecule', 'isolate', 'material', 'parity', 'background', 'genetic background', 'epithelial', 'culture_result', 'smear_results', 'full_genotype', 'hip_circumference']"
+Biospecimen Type,Sample Isolation and Preparation,"['waist_circumference', 'microdissection', 'assayed molecule', 'lymphs', 'line', 'isolation_method', 'skin type', 'library well', 'library plate', 'platelet', 'antigen', 'markers', 'skin', 'colony of_origin', 'hemoglobin genotype', 'trachea region', 'intrinsic subtype', 'anatomic_location', 'anatomic location', 'microbiota status', 'sputum_smear', 'sputum_culture', 'growth', 'eye', 'brain bank', 'splice variant', 'transplant type', 'chip target', 'bal_culture', 'bal_smear', 'smear of index case', 'components', 'fibrinogen', 'target molecule', 'enzyme', 'marrow', 'variety', 'hemisphere', 'microglia media', 'histological..subtype', 'unsorted or sorted', 'input material', 'subclass', 'fracture site', 'immune_or_nasal', 'any_immune', 'Type', 'embryo', 'anatomical location', 'fetus', 'lesional (ls) vs. normal', 'Genetic background', 'Histological type', 'vs type', 'histological.type', 'lobe', 'cytology', 'aspiration site', 'vector constructs', 'sandwich type', 'types', 'modifications', 'library-type', 'lymph node number', 'upper or lower extremity', 'growth pattern', 'volar or non-volar', 'isolation method', 'specific heart region', 'lymph node', 'graft source', 'derived from', 'BREAST', 'type of library', 'fusion', 'hemolysis score', 'autopsy', 'resection', 'construct']"
+Biospecimen Type,Tissue and Cell Features,"['mating type', 'location type', 'skin anatomy', 'pulldown', 'knock-in line', 'brain section', 'knockout status', 'mitotic activity', 'derived from metastatic site', 'kit expression', 'pulmonary compartment', 'sampling location', 'Body surface area', 'body part', 'anatomical site', 'resection_type', 'morphologic form', 'spinal cord region', 'Construct', 'extract', 'exogenous gene expressed', 'molecule source', 'generation', 'generation/colony', 'electrophysiology', 'glioma model', 'fus aggregation state', 'sort purification strategy', 'protein expression', 'menstrual phase', 'protein', 'clip antibody', 'viral', 'composite', 'osteogenic potential', 'aortic valve', 'adipogenic potential', 'lung section/portion', 'cytogenetic', 'sorted fraction', 'precursor', 'genotype abbreviation', 'sorting profile', 'receptor expression', 'material type', 'cag repeat', 'serology', 'density gradient region', 'pluripotent', 'MASTECTOMY', 'total/partial resection', 'model type', 'type of cultivation plate', 'urine protein', 'embryos pooled', 'lung section', 'anatomical region', 'microglia population', 'fus variant', 'portion of branchial arch', 'anatomic segment', 'allele', 'neural crest-derived', 'molecule subtypes', 'hairpin', 'pull-down', 'cytogenetics', 'marker', 'number of_tracheas', 'knock-in', 'embryo characteristic', 'immortalization method', 'OVARY', 'AXILLARY NODE', 'BREAST, LOCAL EXCISION', 'PARTIAL MASTECTOMY', 'COMPLETION MASTECTOMY', 'SENTINEL AXILLARY LYMPH NODE', 'BREAST, MASTECTOMY']"
+Biospecimen Type,Small Molecules,['small molecule']
+Biospecimen Disease Condition,Disease State,"['disease state', 'disease', 'diagnosis', 'condition', 'infection', 'disease status', 'tumor type', 'housing condition', 'diseasestate', 'clinical diagnosis', 'histologic diagnosis', 'tumor grade', 'infection status', 'tumor location', 'infection states', 'disease group', 'final diagnosis', 'cancer status', 'hours post infection', 'disease severity', 'infection protocol', 'working_diagnosis', 'first_diagnosis', 'tumor grading', 'pathology', 'disease duration', 'disease_category', 'institutional tumor diagnosis', 'disease location', 'disease staging', 'cancer site', 'tumor', 'neuropathological_diagnosis', 'clinical_diagnosis', 'disease_duration_years', 'culture condition', 'site of infection', 'cancer type', 'infection code', 'culture conditions', 'disease_status', 'reference diagnosis', 'condition description', 'adjusted disease severity index', 'diagnosis date', 'growth condition', 'additional conditions', 'disease symptom', 'other diseases', 'disease type', 'disease subtype', 'DiseaseState', 'diagnosis.after.path.re.review', 'diagnosis.of.record', 'lung disease', 'chronic diseases', 'molecular.diagnosis', 'primary.tumor', 'tumor_name', 'radiation administered prior to tumor resection', 'histological diagnosis', 'tumor localization', 'broad diagnosis', 'behavior at diagnosis', 'tumor category', 'disease activity', 'stimulation condition', 'primary diagnosis', 'light condition', 'diagnosis total', 'diagnosis hep flex', 'diagnosis rectum', 'lung pathology', 'tumor_entity_subtype', 'diagnosis colonic', 'diagnosis details', 'diagnosis anal perianal', 'diagnosis oral', 'diagnosis rectal', 'disease_state', 'tumor full_name', 'disease_group_detailed', 'disease_group', 'pathology_note', 'distance from the tumor center', 'index_case_disease_site', 'tumor subgroup', 'years since diagnosis', 'histopathology', 'skin disease', 'Diagnosis', 'tumor subtype', 'clinical condition']"
+Biospecimen Disease Condition,Disease Characteristics,"['infection group', 'worm infection', 'Tumor size', 'disease_extension', 'tumor status', 'culture_conditions', 'primary disease', 'incubation conditions', 'neuropathological diagnosis', 'Condition', 'tumor.in.left.right.lobe', 'tumor region', 'disease_duration', 'hour post infection', 'disease category', 'tumor type/grade', 'virus infection', 'exposure condition', 'bacterial infection', 'infection state', 'infection duration', 'parental tumor subtype', 'preliminary diagnosis', 'primary tumor site', 'malaria infection', 'tumor histology', 'metastatic tumor site', 'lesion_disease_factor', 'infection type exposure', 'primary tumor', 'duration of infection', 'experimental condition', 'malignant tumor', 'disease model', 'initial tumor increase/(-)decrease', 'tumor size', 'tumor_grading', 'tumor source', 'conditioning received', 'conditions', 'active_disease', 'Conditioning', 'Disease', 'tumor/control', 'disease phase', 'tumor.grade', 'qualifying condition', 'clinical.diagnosis.history', 'tumor vs. normal', 'viral infection', 'maximal prior disease extend', 'disease diagnosis', 'hours of infection', 'years of disease', 'disease subset', 'conditioned media type', 'conditioned media origin', 'Location tumor', 'Tumor type', 'growth conditions', 'infection type', 'plasmodium falciparum infection status', 'single or double infection', 'infection route', 'stress condition', 'pulmonary.disease', 'cancer.past', 'active cancer', 'cardiovascular.disease', 'oncologic diagnosis', 'environmental condition', 'molecular condition', 'disease course', 'disease onset', 'tumor_size', 'library outgrowth conditions', 'maternal disease status', 'disease condition', 'associated primary tumor no', 'tumor_site', 'Chief Disease', 'tumor model', 'tumor origin', 'disease outcome', 'mechanical condition', 'Wash Condition', 'Labeling Condition', 'location of tumors', 'brain tumor region', 'initial tumor volume', 'tumor class', 'disease classification', 'disease in non-fip']"
+Biospecimen Disease Condition,Disease Attributes,"['brain tumor', 'treatment condition', 'disease grade', 'tumor inoculation', 'original tumor', 'molarity of infection', 'duration of disease', 'genotype/disease state', 'infection rate', 'infection period', 'oxygen condition', 'conditioned medium', 'conditioned media source', 'growing media conditions', 'Disease state', 'disease feature', 'site of_disease_onset', 'disease name', 'tumor position', 'cancer predisposition', 'original tumor type', 'growth_condition', 'plasmodium infection', 'length of infection', 'molecular diagnosis', 'experimental conditions', 'months post infection', 'tumor who grade', 'reference condition', 'test condition', 'rounds of infection', 'Infection Status', 'clinical info', 'histology', 'primary site', 'brain region', 'who category', 'initial ich volume', 'who grade', 'number of malaria infections', 'section', 'infection_status', 'Histopathological diagnostic', 'hours post-invasion', 'hours post invasion', 'mechanical ventilation', 'antibody description', 'inflammation status', 'injection_type', 'Histology', 'localization', 'isolate type', 'location of onset', 'dissection', 'injection site', 'clinical indication', 'lesion status', 'clinic status', 'metastatic site', 'hours_post_infection', 'injection', 'er status', 'neuropathological.information', 'hours post fertilization', 'viral infected', 'infectious', 'water type', 'maternal health status', 'single or double infected', 'clone type', 'hours post-infection', 'channel type', 'interaction status', 'pair status', 'infection_state', 'vaccination status', 'type of insertion', 'clinical manifestation', 'incubation period', 'viral inactivation', 'environmental factor', 'nes status', 'zinc status', 'round of selection', 'reference lot', 'reference cat', 'histopathological diagnostic', 'cohort', 'smoking status', 'pasi', 'pathologic status', 'grade', 'surgical status']"
+Biospecimen Disease Condition,Disease Status,"['outcome', 'status', 'subtype', 'culture result', 'site_onset', 'metastasis', 'severity score', 'stress', 'smoker', 'severity', 'illness', 'Illness', 'viral_positivity', 'neoplastic', 'consortium lung phenotype', 'malaria_transmission', 'consortium lung phenotype surrogate variable', 'meconium ileus status', 'persistent ps aer status', 'malaria_status', 'dementia', 'diagnostic_mean', 'death', 'survival_status', 'progression', 'parasitemia', 'tst skin test', 'joint problems', 'family history', 'symptoms onset date', 'with or without clonal heterogeneity', 'international prognostic index', 'dead or alive at the end of follow-up', 'total number of genomic aberrations', 'seizure', 'asthma', 'smear_result', 'anti-centromere', 'recurrence', 'os.mos', 'surgical.outcome', 'psychiatric disorder', 'gastrointestinal disorder', 'cerebral palsy', 'mutational subclass', 'birth defects', 'neurological disorder', 'developmental/speech disorder', 'diabetes', 'percent_weight_loss', 'molecular classification', 'recurrent_status', 'dysplasia now', 'health state', 'cigarette smoker', 'medical.history', 'inflammation_status', 'pregnancy status', 'cirrhosis present', 'chronic hypertension', 'survival after surgery', 'death with metastasis', 'outcome related', 'infected/uninfected', 'neoplasia type', 'symptom severity', 'viral shedding', 'tst result', 'symptomatic', 'smoking', 'hypertension', 'cag_repeat', 'conversion', 'prognosis', 'parasitemia category', 'survival status', 'parasite density', 'malign', 'protect_outcome', 'isolate_sensitivity', 'exposure_latent', 'pasi score', 'obesity', 'stress exposure', 'genetic class', 'symptom', 'mutation_carrier_status', 'cag_repeats', 'phase', 'das score', 'infectivity', 'total cholesterol', 'fibrosis degree']"
+Biospecimen Disease Condition,Disease Progression,"['interim pet response', 'primary/recurrent', 'pasi_total', 'Outcome', 'scar', 'lesion', 'lymphoma type', 'remission', 'swollen joints', 'pain', 'tender joints', 'viral load', 'current status', 'Smoking status', 'endoscopic_activity', 'mitotic index', 'survival characteristics', 'vascular.invasion', 'mutational.status', 'multifocal', 'smoker or non smoker', 'exposed to', 'familial anamnesis', 'onset', 'Status', 'progression_free_survival', 'primary recurrent', 'smoking_status', 'clinical outcome', 'metastasis site', 'glioma', 'subcutaneous neurofibromas', 'plexiform neurofibromas', 'cutaneous neurofibromas', 'facial dysmorphism', 'scoliosis', 'skin-fold freckling', 'Lymph node involvement', 'primary_recurrent', 'clinically_aggressive', 'total skin score', 'lesion_label', 'presence_of_parasites_lesion', 'infiltration', 'severity_score', 'lesion_size', 'bleeding', 'stool frequency', 'clinical presentation', 'alive', 'prodromal status', 'subtypes', 'local skin score', 'location of lesion', 'gene deletion status', 'mutation class', 'fever', 'dyspnea / tachypnea', 'cough', 'primary/metastasis', 'symptoms', 'tuberculosis_history', 'family_history', 'exitus', 'primary mutation', 'copy number gain', 'sofa score', 'als mutation', 'granuloma', 'brain metastasis', 'reason for intubation', 'pregnancy', 'clinical_history', 'cerebral performance category score', 'diplopia', 'mutations', 'decrease of vision', 'onset site', 'relapse', 'syndrome', 'systemic sclerosis subtype', 'parasite density on admission', 'serologic response status', 'digestives_symptoms', 'radiation sensitivity', 'major_organ_involvement', 'severity binary', 'severe_eosinophilia', 'receptor status', 'histological grade', 'clinical phenotype details', 'who class', 'cause.of.death']"
+Biospecimen Disease Condition,Disease Details,"['histological response', 'hereditary status', 'Family History', 'clinical information', 'parasite', 'primary vs metastatic', 'nonunion type', 'Dead/Alive', 'Location of distant metastasis', 'isolate sensitivity', 'sputum smear status', 'diffuse/limited', 'KIT mutation', 'antibody status', 'lymphoma subtype', 'primary_recurrence', 'neural tube defect', 'sofa_admission', 'affected status', 'skin phenotype', 'sum.risk.factors', 'psoriasis area-and-severity index', 'hospitalization', 'follicular lymphoma grade', 'psoriasis subtype', 'Scaling', 'skin score', 'previous severity', 'Overall erythema', 'degree of infiltrate', 'pathological type', 'fip status', 'mortality', 'gametocyte status', 'medical history', 'histological subtype', 'metastatic status', 'somatic mutation', 'respiratory score', 'gastrointestinal involvement', 'Death Cause', 'Inflammation', 'ocular involvement', 'vascular involvement', 'genital ulcer', 'arthritis', 'At Risk', 'oral ulcer', 'molecular subtype/phenotypic state', 'erythema nodule', 'reason for liver resection', 'injury model', 'febrile seizure', 'ar or asthma', 'autism diagnostic', 'alk mutation status', 'pulmonary cavitation', 'malignancy class', 'risk grade', 'glioma grade', 'immune infiltration', 'hind-limb paralysis', 'rift valley fever virus', 'engraftment', 'interstitial pneumonia', 'seizures/month', 'surgical indication', 'melanoma', 'major reason_for_surgery', 'primary/ recurrent', 'metastatic/primary', 'recurrent/primary', 'weight phenotype', 'resistance profile', 'embryo phenotype', 'etiology', 'myopathic motor_unit_potentials', 'mutation details', 'cognitive impairment', 'distant metastasis', 'tobacco use', 'parental/ne-like state', 'oocyst prevalence', 'post-symptom onset', 'invasive behavior', 'responder status', 'fibrosis', 'severity grade', 'diffuse vs limited', 'allergy', 'months_survival', 'progression_status', 'months_progression']"
+Biospecimen Disease Condition,Disease Severity,"['mitotic rate', 'positive Down screening risk']"
+Biospecimen Age,Developmental Timepoints,"['age', 'time', 'time point', 'timepoint', 'developmental stage', 'Stage', 'day', 'agent', 'age in years', 'Age', 'passage', 'tumor stage', 'passages', 'development stage', 'age_onset', 'age description', 'disease stage', 'treatment time', 'age group', 'infection time', 'year', 'passage_if_expanded', 'doubling time', 'infectious agent', 'collection time point', 'age_weeks', 'age_at_draw', 'time harvest', 'sampling time_point_label', 'time_to_malaria', 'reagent', 'age of enrollment', 'days_in_hospital', 'age_at_diagnosis', 'age of onset of persistent ps aer or censored age', 'days since vaccine', 'dev_stage', 'age_at_death_years', 'passage number', 'time.from.exposure.months', 'day of trial', 'day post infection', 'age at death', 'days since vaccination', 'sampling timepoint', 'gold stage', 'year of surgery', 'age in year', 'days of differentiation', 'age at_treatment', 'treatment age_group', 'animal age', 'treatment/time point', 'dosage', 'week', 'osteogenesis day', 'timepoint_months', 'InitialTimePoint', 'age at diagnosis', 'path.stage', 'differentiation stage', 'description of day', 'differentiation day', 'day_of_euthanasia', 'visit day', 'age_diagnosis_years', 'age of onset', 'Tumor stage']"
+Biospecimen Age,Timepoints and Durations,"['TimeUnit', 'sorter day', 'art start year', 'sampling_timepoint', 'time post-stimulation', 'developmental_stage', 'days_symptom_onset', 'overall.survival..days', 'sampling time', 'time_since_onset', 'stimulation time and condition', 'age at_diagnosis', 'dev stage', 'lineage', 'day of differentiation', 'survival time', 'days post drug', 'collection time point (#) or necropsy', 'parasite stage', 'time-point', 'days after infection', 'differentiation_stage', 'cage', 'age.days', 'infection.time.point.days', 'embryonic stage', 'excision year', 'time points', 'Time', 'ventilator-free days', 'day-post-infection', 'time post infection', 'day after seeding', 'os month', 'day of_tumor_harvest', 'infection agent', 'harvesting time', 'collection time', 'time after treatment', 'age at sampling', 'gestational age', 'Usage number', 'average library size', 'exposure time', 'age of psoriasis onset', 'treatment time point', 'ko induction_time', 'days post-vaccination', 'age at transplant', 'age.at.operation', 'disease_stage', 'days post onset of symptoms', 'age, months', 'survival_time', 'age of death', 'AGE', 'clinical stage', 'survival time in months', 'draw day', 'relapse time', 'stage of repair process', 'culture days', 'cancer stage', 'growth stage', 'activation agent', 'storage', 'age at initiation', 'ann arbor stage']"
+Biospecimen Age,Sampling and Survival Times,"['sampling.time', 'harvest time', 'overall.survival.time', 'days post infection', 'life stage', 'time in culture', 'collection day', 'stage', 'days after stimulation', 'labeling agent', 'survival year', 'time after infection', 'treatment/timepoint', 'age and disease', 'year of isolation', 'timepoint_description', 'age at surgery', 'sporozoite age', 'age/gender', 'treatment stage', 'oxygen percentage', 'age in_yrs', 'injury/age', 'sex/age', 'experimental day', 'day post-infection', 'treatment_time', 'age fracture', 'days post-infection', 'time of sampling', 'day of collection', 'days ill', 'age/disease timepoint', 'age years', 'differentiation time', 'days post exposure', 'maternal age', 'time post-vaccination', 'days post_infection', 'post-treatment day', 'days post-prime', 'days post challenge', 'timepoint_in_hours', 'day transplantation', 'growth time mins', 'time post-treatment', 'Age of Onset', 'culture age', 'developmental stages', 'time_point', 'day of isolation', 'GOLD stage', 'Age at time of surgery', 'time post initiation of treatment', 'age at collection', 'time after treatment (and reversal) in hours', 'age post-hatch', 'age fraction', 'gestational stage', 'age at time of collection', 'post-operative day', 'growth time', 'induction time', 'pretreatment time', 'Time after induction', 'age at examination', 'dev_stage at treatment initiation', 'time infected']"
+Biospecimen Age,Post-Event Timepoints,"['interval_death_symptoms_onset_days', 'intubation_days', 'time point days', 'time designation after sclerosis', 'time since sclerosis', 'time since transplant', 'Passage', 'culture stage', 'death_time', 'time post treatment', 'days post treatment', 'sampling time point', 'day of collection/passage', 'harvest time post treatment', 'time post_injury', 'differentiation_age', 'embryonic day', 'time post-infection', 'os_days', 'sepsis stage', 'fever day', 'injection age', 'MaternalAge', 'isolation stage', 'timepoint_progressors', 'time point post infection', 'time of treatment', 'age at onset', 'duration of untreated disease in month', 'cold ischemia time', 'donation time', 'time post-exposure', 'age_category', 'age of disease onset percentile', 'age of disease onset', 'age in months', 'day of development', 'parasite/gametocyte stage', 'cold ischemia_time', 'time of_treatment', 'incubation time', 'age tier', 'developmental age', 'treatment agent', 'day of protocol', 'differentiation time point', 'age of  culture', 'block storage', 'time to relapse', 'harvest time point', 'Tumor Stage', 'onset age', 'agent concentration', 'time after virus injection', 'days', 'time post-immunization', 'time point in the model of dormancy', 'age, yrs', 'developmental stage/tumor stage', 'chronological age', 'days under treatment', 'final age at death', 'death day', 'Developmental stage', 'gestational days', 'age at diagnosis in months', 'day post transplant', 'age at study start']"
+Biospecimen Age,Age and Time Ranges,"['time of last follow up in months', 'day after intubation', 'age at harvest', 'time of day', 'age range', 'exacerbation day', 'process day', 'age/time point', 'day after transplantation', 'age of_diagnosis', 'time since first diagnosis', 'age of_onset', 'life cycle stage', 'time point of infection', 'cartilage pellets', 'embryo stage', 'passage/days', 'developmental stage, weeks', 'time of_drug_treatment', 'time after exposure', 'treatment time-point', 'collection timepoint', 'developmental stage/age', 'days from treatment', 'time after stimulation', 'age category', 'day post neural induction', 'days_since_positive_test', 'days in culture', 'of passage', 'days of final differentiation', 'stage of disease', 'passages after establishing stable clones', 'culture time', 'treatment/agent', 'treatment / timepoint', 'infection time point', 'days_post_infection', 'postnatal day', 'stage of differentiation', 'passage no', 'experiment', 'datatype description', 'collection_method', 'tag', 'culture', 'clinical status', 'fraction', 'lab description', 'survival_yr', 'growth phase', 'case', 'date harvest', 'surgery number', 'survival', 'induction date', 'exposure', 'culture type', 'development', 'category', 'experiment type', 'description', 'state', 'differentiation batch', 'growth medium', 'Cause of death', 'survival cluster', 'differentiation']"
+Biospecimen Age,Experimental Conditions,"['overall.survival.months', 'os_month', 'differentiation_method', 'cag', 'culture media', 'isolation source', 'growth media', 'infected', 'animal name', 'clinical type', 'culture method', 'experiment label', 'infectious challenge', 'experimental status', 'Degree of differentiation', 'Case', 'experimental set', 'sampling site', 'Differentiation Method', 'experiment batch', 'isolation', 'growth type', 'collection date', 'differentiation status', 'state of culture', 'collection', 'overall.survival', 'experimental batch', 'experimental', 'experimental design', 'Clinical Status', 'labversion description', 'Type of Surgery', 'parasite isolate', 'sampling point', 'differentiation state', 'experimental factor', 'culture status', 'harvesting', 'collection_date', 'os months', 'Cause of Death', 'type of death', 'collection buffer', 'collection point', 'overall survival', 'experimental variable', 'culture batch', 'source/differentiation', 'phase description', 'stim', 'experiment name', 'length of culture', 'long description', 'maternal state', 'culture medium', 'differentiation replicate', 'date of isolation', 'process order', 'activation', 'incubation', 'life cycle', 'Growth Medium', 'sorted', 'data type description', 'developmental state', 'cause of death', 'incubation partner']"
+Biospecimen Age,Temporal References,"['birth date', 'follow up years', 'ga', 'hours', 'phase of growth']"
+External_sample_id,Sample Identification,"['sample type', 'patient id', 'individual', 'subject id', 'donor', 'subject', 'patient', 'subject status', 'sample id', 'subjectid', 'sample', 'sample group', 'mouse id', 'donor id', 'slide no', 'participant id', 'controlid', 'donor_id', 'patientid', 'batch id', 'individual id', 'barcode', 'patient_id', 'animal id', 'patient diagnosis', 'provider', 'patient gender', 'cell line id', 'sampleID', 'donor_age', 'donor_sex', 'donor_health_status', 'donor_ethnicity', 'participant', 'patient viral load', 'patient group', 'sample source', 'chip_antibody_provider', 'sample alias', 'sample common name', 'sample collection site', 'patient sample id', 'sample.id', 'patient age', 'ID', 'covid_status', 'slide', 'donor age', 'sample_code', 'volunteer id', 'blood sample id', 'plate id', 'patient_asymptomatic', 'blood sample_id', 'in_covid_only_dataset', 'external_donor_name', 'cosmic id', 'patient classification_at_first_sample', 'days since_first_sample', 'external id', 'days since first sample', 'sample id alt', 'patient classification at first sample', 'sample class', 'patient category', 'vendor id', 'platform_id_id design', 'sample_name', 'slide_position']"
+External_sample_id,Sample Characteristics,"['sample name', 'sample timing', 'covid cat', 'covid', 'subject_id', 'sample material', 'sample collection time', 'symptomatic or asymptomatic at sample collection', 'non human primate individual id', 'vaccine side effects', 'age at sample drawn', 'sample preparation', 'sample_group', 'slide id', 'subject group', 'sample group_label', 'sample number within subject', 'sample collection', 'animal_id', 'tissue id', 'monkey id', 'donor category', 'slide name', 'sample time', 'Individual', 'subject number', 'sample_set', 'donor_id_blinded', 'sample_group_granular', 'donor type', 'paired samples', 'patient.code', 'sample_type', 'subject condition', 'subject diagnosis', 'sample day', 'tissue/sample type', 'hybridization batch', 'diagnosis recto sigmoid', 'patient_age', 'patient_visit', 'patient sex', 'patient code', 'patient subgroup', 'patient number', 'hybridization protocol', 'study id', 'sample tissue', 'sample_id', 'long-covid symptoms', 'study participant', 'sample_site', 'clinical diagnosis patient', 'sample recovery type', 'sample_barcode', 'slide_id', 'deceased donors, only left kidney included in the analysis', 'side', 'identifier', 'patient treatment', 'subjects', 'sample origin', 'time since steroid dose', 'donor_genotype', 'sample collection time post infection', 'scan id', 'steroids', 'mouse_id', 'donor code']"
+External_sample_id,Sample Attributes,"['type of sample', 'patient population', 'sample age proxy', 'patient condition', 'family id', 'sample subseries', 'matched pair id', 'replicate id', 'donor number', 'individual identifier', 'specimen_barcode', 'mouse identifier', 'patient source', 'biopsy number for this subject', 'sample number', 'Patient', 'unique_subject_identifier', 'sample collection time post virus infection', 'tissue/treatment id', 'donor_type', 'animal identifier', 'library id', 'age patient', 'patient identifier', 'covid infection_status', 'covid severity_status', 'steroids_cat', 'nasal_steroids', 'pool id', 'number of pooled individuals', 'peptide', 'minimum counts per cell threshold used to remove background barcodes', 'sample plate', 'patient identification number', 'sample description', 'donor covid_status', 'steroid', 'with_lesion_sample', 'id sample', 'id simple', 'methylation_geo_id', 'geo_sample_id', 'ref id', 'time of sample collection', 'patient_no', 'patient no', 'subject age', 'pediatric patient', 'sample name in supplementary file', 'cartridge', 'covid status', 'rabbit id', 'patient response', 'alternative sample name', 'publication id', 'study_id', 'Sample ID', 'sample/subject id', 'samples of different individuals pooled', 'organoid line', 'tumor side', 'Mouse ID', 'swollen eyelid', 'sample prep', 'sample/time point', 'subject gender', 'slide tissue area', 'dissected embryo id number', 'patient/control id']"
+External_sample_id,Sample Tracking,"['sample id cat', 'run id', 'lane id', 'patient sample', 'subject/sample source id', 'Donor type', 'patient id no', 'patient reference', 'sample condition', 'batch_id', 'sample.name', 'repeated samples', 'sample pool', 'normal individual, Tissue', 'amyloid', 'sample_time', 'donor no', 'sample case', 'subject label', 'subject id/diagnosis', 'individuals', 'clone id', 'Twin Pair ID', 'person id', 'Sample code', 'virus taxon id', 'disrupted gene id', 'study sample number', 'paired patient', 'library barcode', 'sample beneath', 'number of individuals per sample', 'donor status', 'participant condition', 'cell samples', 'sample.type', 'Age of patient', 'donor group', 'organoid status', 'mouse exhibiting symptoms on the day of sample collection', 'array id', 'sex steroid priming', 'tumor identifier', 'donor line', 'tumor sample', 'flowcell id', 'sample status', 'Sample Group', 'hippocampal slice id', 'patient line', 'Sample Type', 'status sample', 'samples', 'animal id number', 'StudyID', 'donor strain', 'Sample', 'carcinoid syndrome', 'patient tumor related pain status', 'donor age, sex', 'donor race', 'Hybridization Time', 'mouse individual id', 'subject status/id', 'patient_status', 'mouse id tag', 'data analysis id', 'genotype of original donor', 'Patient Number']"
+External_sample_id,Sample Classification,"['sample subgroup', 'manuscript library id', 'sample_label', 'incidence', 'patients', 'Lab ID', 'location/side', 'clone background/id', 'unique sample identifier', 'Sample group', 'strain id', 'group id', 'sample identifier', 'fetal lung tissue donor', 'internal patient id', 'internal sample id', 'donor fibroblasts', 'day of organoid differentiation', 'hydrogen peroxide treatment', 'donor id/status', 'array barcode', 'organoid generation', 'graft donor strain', 'original biopsy for this patient', 'cell model id', 'source id', 'tissue donor', 'treatment/sample type', 'subject identifier', 'number of_samples', 'peptide genotype', 'sample region', 'sample code', 'culture/clone_id', 'patient age at diagnosis', 'sample name synonym', 'Sample_reference', 'Subject_reference', 'source patient gender', 'strain donor', 'organoid formation', 'subject relationship', 'sample barcode', 'sample population', 'Sex of donor mice', 'tubules with elongated spermatids', 'tubules with round spermatids', 'age of donor/age of host', 'sample replicate number', 'fluid', 'sample state', 'hybrid', 'id', 'in-line barcodes', 'donor sex', 'donor gender', 'donor disease state', 'acidity', 'associate geo_sample', 'patient-derived cell line', 'sample age', 'antibody vendor id', 'control id', 'donor diagnosis', 'sample tag_information', 'organoid type', 'age of patient when tumor sample obtained', 'batch', 'replicate']"
+External_sample_id,Sample Context,"['plate', 'site', 'location', 'source', 'animal', 'clone', 'study', 'chip_antibody_lot', 'vital status', 'array', 'library date', 'chip antibody vendor', 'volunteer code', 'library', 'plate_number', 'volunteer', 'subset', 'family', 'line number', 'array batch', 'folder name', 'sort population', 'size', 'roi type', 'number of_mice', 'Subsets', 'replicates', 'library input', 'health_status', 'study number', 'bar code', 'person', 'vendor', 'pooled', 'Source', 'chip-antibody vendor', 'alternative_name', 'animal number', 'plate code', 'replicate type', 'antibody vendor name', 'library kit', 'vital_status', 'common name', 'family code', 'animal no', 'alternative name', 'sorted population', 'antibody vendor', 'radiation response', 'library backbone', 'number of animals', 'als status', 'nodal status', 'fraction/population', 'replicate number', 'hippocampal sclerosis', 'tubules with spermatocytes', 'number of_animals', 'associated geo', 'clip antibody vendor', 'enrollment batch', 'code', 'original geo accession', 'hospital', 'volunteer number', 'alias', 'pool no', 'Order Code']"
+External_sample_id,Lab Identifier,['lab code']
+Treatment,General Treatment Info,"['treatment', 'group', 'vaccine', 'treatment description', 'treatmentshort', 'drug treatment', 'treatment group', 'control', 'control description', 'treatment duration', 'subgroup', 'groups', 'molecular subgroup', 'diagnostic_group', 'classification group', 'chemical compound', 'infected with/healthy control', 'vaccine doses', 'prior treatment', 'response_group', 'grouping', 'vaccine type', 'current medication', 'experiment group', 'treatment location', 'chemotherapy', 'Prior Treatment', 'treatment administration route', 'treatment frequency', 'study group', 'drug', 'experimental group', 'treatment dose', 'treatment arm', 'treatment withdrawal', 'treatment initiation', 'recreational drugs', 'prescription drugs', 'treatment-outcome code', 'radiation.therapy', 'treatment protocol', 'treatment response', 'enzymatic treatment', 'vaccine group', 'dose group', 'group description', 'inhibitor treatment', 'dose_group', 'batch group', 'previous treatments']"
+Treatment,Treatment Details,"['vaccine regimen', 'drug dose', 'hours post-treatment', 'therapy used', 'Group', 'antibiotic treatment', 'healthy control', 'control/intervention', 'treatment status', 'ear treatment', 'therapy', 'compound', 'biological drug', 'treatment_duration', 'control or als', 'vector treatment', 'previous drug treatment', 'antibody group', 'surgical treatment', 'vaccine administered', 'rabbit group', 'treatment outcome', 'group label', 'treatment_duration_in_hours', 'treatment category', 'treatment prior to second surgery', 'vaccine administration', 'survival group', 'intervention group', 'prior chemotherapy', 'antibody treatment', 'main group', 'treatments', 'postsurgical-treatment', 'isogenic_group', 'drug concentration', 'first-line therapy', 'clinical group', 'treatment before challenge', 'chemical treatment', 'no treatment', 'treatment_effect', 'clinical_subgroup', 'treatment concentration', 'prior systemic therapy', 'current systemic therapy', 'treatment condition/type', 'pharmacologic treatment type', 'os_group_median', 'drug administration']"
+Treatment,Treatment Outcomes,"['treatment effect', 'duration of treatment', 'other treatment', 'growth medium/treatment', 'chemical probe', 'Treatment', 'treatment_type', 'drug response', 'drug resistance', 'compound concentration', 'experiment grouping', 'art treatment', 'treatment/infection', 'has_drug', 'seizure group', 'compound treatment', 'pretreatment', 'subset group', 'case or control', 'risk group', 'treatment of mice', 'treatment_dose', 'Drug', 'analysis group', 'chemical', 'chemical modification', 'chronic medication', 'acute medication', 'polarization treatment', 'treatment type', 'camp treatment/level', 'before or after treatment', 'knockout group', 'treatment timing', 'vaccine dose', 'selection pressure drugs', 'genotype/treatment', 'treatment/group', 'culture/treatment', 'exogenous treatment', 'animal treatment', 'genotype & treatment', 'group_tag', 'mice group', 'control source', 'treatment_term_name', 'segment type', 'response', 'resistance', 'animal replicate']"
+Treatment,Experimental Design,"['classification', 'replicate description', 'genetic modification', 'brain location', 'experimental replicate', 'case/control', 'molecular subtype', 'protect outcome', 'other_medication', 'variant type', 'translocation', 'experimental repeat', 'genomic modification', 'donation source', 'tretment', 'genetic modifications', 'translocations', 'dementia status', 'polarization state', 'experimental run', 'antibody name', 'mutation frequency', 'nitrogen source', 'antibody lot', 'temperature', 'medium', 'tuberculin skin test', 'treated with', 'delivery', 'stimulus', 'chip_antibody', 'irradiated', 'first vaccination', 'second vaccination', 'selection marker', 'induced', 'injection_materials', 'curative_intent', 'media', 'amplification', 'ventilation', 'chip-antibody', 'diet', 'medications/vitamin names', 'stimulant', 'vaccination.assignment', 'surgical_interval_mo', 'active ingredient', 'knockout', 'primed']"
+Treatment,Interventions,"['rip antibody', 'antibody manufacturer', 'diabetes_medication', 'chip antibody lot', 'knockdown', 'exposed stress', 'watch and wait', 'Exposures', 'vector', 'trial arm', 'surgery', 'prophylaxis', 'exercise intensity', 'challenge', 'surgery type', 'radiation', 'bone-marrow grafting status', 'bone-marrow grafting type', 'injected virus', 'alcohol', 'number of immunization boost', 'rounds_to_cure', 'clinical trial phase', 'other biologic medicines use', 'pathogen exposure', 'viral challenge', 'culture platform', 'debris removal', 'perturbation class', 'perturbation', 'cross-linked', 'route administered', 'vehicle', 'over-expression', 'length of exposure', 'nicotine', 'oxygen flow', 'radiation exposure', 'library prep kit', 'virus-stimulation', 'perturbation type', 'environment', 'inhibitor removal', 'medicine', 'untreated/treated', 'cultivation', 'growth temperature', 'implantation', 'vasopressor', 'modification']"
+Treatment,Environmental Conditions,"['oxygen level', 'injected with', 'antibody target description', 'fed with', 'Shear exposure', 'desiccation', 'genetic engineering', 'construct expression', 'culture format', 'expression construct', 'fasting', 'mode of growth', 'gene_knockout', 'vaccination_status', 'antigenic stimulation', 'transplant', 'autophagy induction', 'oxygen tension', 'angiography', 'genetic_modification', 'surgical approach', 'plating', 'antibody used', 'antigen capture', 'rescue', 'intensive care', 'growth factors in the culture medium', 'antibody maker', 'overexpressing', 'growth phase/media', 'secondary antibody', 'primary antibody', 'transient expression', 'testosterone treated', 'gene induction', 'overexpressed target', 'methylation-enrichment', 'media supplement', 'chip antibody reference', 'stable knockdown', 'antibody cat', 'depletion', 'spike protein used', 'phase growth', 'oxygen status', 'strategy', 'media additions', 'culture supplement', 'affinity purification', 'ligation']"
+Treatment,Cell Culture,"['selection media', 'solvent', 'transplanted with']"
+Biospecimen Organism,Strain,"['strain', 'strain background', 'strain/background', 'mouse strain', 'background strain', 'strain description', 'strain/genotype', 'parasite strain', 'virus strain', 'malaria strain', 'strain name', 'viral strain', 'bacterial strain', 'host strain', 'genotype/strain', 'laboratory strain', 'recipient strain', 'infection strain', 'strain info', 'parental strain', 'strain source', 'strain origin', 'strain/isolate', 'pathogen strain', 'Mouse strain', 'parent_strain', 'original strain', 'infectious strain', 'cell strain', 'Cell strain', 'strain_recipient', 'infrequent clonal strain code', 'Strain', 'age and_strain', 'Virus Strain', 'strain  background', 'plasmodium strain', 'parental-strain', 'strains', 'strain/model', 'graft recipient strain', 'strain recipient', 'bacteria strain']"
+Biospecimen Organism,Organism,"['organism', 'organism part', 'cell organism', 'host', 'source_organism', 'OrganismPart', 'host cell', 'host genotype', 'host mice strain', 'host vendor', 'host strain/background', 'mouse line abbreviation', 'mouse line', 'host cell line', 'host organism', 'host cell type', 'host_cell_line', 'specific-host', 'host age', 'host mouse strain', 'host mouse_tissue', 'host cells', 'host tissue', 'mammalian host', 'organism_status', 'organism_part', 'spike-in organism', 'organismpart']"
+Biospecimen Organism,Mouse,"['mouse', 'mouse number', 'mouse genotype/variation', 'replicate mouse', 'mouse age', 'mouse selection', 'mouse dietary condition', 'mouse group', 'mouse status', 'mouse stain', 'mouse tissue', 'mouse genotype', 'mouse cell genotype/variation', 'Mouse model', 'mouse model']"
+Biospecimen Organism,Species,"['species', 'Species', 'genotype', 'genotype/variation', 'human cell genotype/variation', 'breed', 'cattle breed', 'geographical origin', 'genotype of founder fish', 'life form', 'litter', 'origin', 'parental origin', 'specificity', 'specific', 'living']"
+Biospecimen Organism,Pathogen,"['pathogen', 'pathogens', 'ps status', 'viral status', 'immune status', 'os', 'Genotype', 'genome/variation', 'genotype/varation', 'bacteria', 'bacterium', 'mosquito', 'parasite line', 'viral family', 'viral genus', 'virus', 'virus family', 'virus genus', 'virus subtype', 'virus type', 'Pathogen']"
+Biospecimen Organism,Host Infection,"['infected host', 'infection host', 'infected with', 'microorganism_source_of_infection', 'microorganism_blood', 'os_status', 'human tissue source', 'human tumor cell line', 'cell line / strain', 'malaria status', 'OS status']"
+Biospecimen Organism,Organism Miscellaneous,"['couple number', 'selection', 'series', 'stain', 'strand', 'hot', 'agricultural animals', 'background mice', 'companion animals', 'mice']"
+Biospecimen Sex,General Sex,"['gender', 'Sex', 'sex', 'Gender', 'SEX']"
+Biospecimen Sex,Specific Sex,"['female', 'fetal sex', 'biological sex', 'InfantSex', 'placental sex']"
+Biospecimen Sex,Predicted or Determined Sex,"['sex predicted', 'Sex of recipient mice']"
+Biospecimen Sex,Source of Sex Information,"['gender source', 'source gender']"
+Biospecimen Sex,Sex Composition,['gender composition']
+Biospecimen Sex,Animal Sex,['animal sex']
+Biospecimen Sex,Biological Attributes,"['biologics', 'biological source', 'gene']"
+Biospecimen Sex,Reproductive Status,['nulliparous']
+Other,Study Attributes,"['visit', 'segment', 'reference', 'datatype', 'tst', 'dataset', 'roi', 'date', 'biological replicate', 'assay', 'geographical region', 'labversion', 'roi number', 'protection', 'lab', 'class', 'area', 'library prep', 'pipeline version', 'censored', 'platesimple', 'experiment_type', 'albumin', 'hematocrit', 'hemoglobin', 'model', 'bin', 'birth_place', 'method', 'adjusted household density', 'geographic location', 'field_site', 'atmosphere', 'geographic origin', 'lane.number', 'center', 'weight', 'lane', 'sort', 'recipient', 'cluster', 'immature_granulocytes_percent', 'genotype_abbreviation', 'immature_granulocytes_absolute', 'allele actual', 'well address', 'plate_location', 'allele nominal', 'match', 'smear microscopy', 'instrument model', 'supplier', 'affy_batch', 'library prep_plate', 'assigned cluster', 'probe_detection', 'title', 'filtered peaks', 'extract name', 'assay name', 'project', 'hemisphere_name', 'platelet_count', 'multisector', 'injection_roi', 'array_design', 'cluster_label', 'is_technical_replicate']"
+Other,Sequencing Details,"['duplicate_pair', 'material support', 'library name', 'genome build', 'label', 'bait', 'chain', 'outlier', 'date collected', 'gene_count', 'nuclei count', 'technique', 'recruiting site', 'procedure date', 'smoking start date', 'smoking amount', 'smoking stop date', 'binding density', 'cap score', 'chip antibody cat', 'negative normalization factor', 'note', 'history', 'surface area', 'link', 'who', 'nuclei_counts', 'amplification cycles', 'smoke', 'visit_date', 'mean corpuscular volume', 'job/role', 'technical replicate', 'index', 'genetic testing', 'unpublished', 'city', 'datasets', 'volume', 'geographical location', 'training.test', 'used for analysis', 'block_name', 'structure acronym', 'set', 'read length', 'duplication_rate', 'align_unique', 'exon_ratio', 'align_input', 'reads_all', 'nuclear_reads', 'library_prep_date', 'extract_date', 'repeat', 'season', 'other information', 'sorting strategy', 'escape', 'diffuse', 'hist.score', 'feeding', 'bal sampling date', 'timing', 'processing', 'library quality', 'visit number', 'pair']"
+Other,Physical and Demographic Attributes,"['run_date', 'muscle mass', 'waist to hip ratio', 'reference genome_for_processed_files', 'fat mass', 'reference genome_for_alignment', 'region of birth', 'period', 'buffer', 'extraction date', 'draw_date', 'comment', 'LabeledExtract', 'expanded allele cag repeat count', 'factor', 'paired material support', 'input', 'further operations', 'efficacy', 'buffer_volume', 'protein exchange', 'buffer_volume_unit', 'study_origin', 'library prep. kit', 'restriction enzyme', 'classifier_mes', 'aerosol.run', 'lane.ordinal', 'notes', 'adapter', 'target gene', 'Other', 'technology', 'sofa', 'application', 'country', 'met_amplification', 'other batch', 'date of array', 'batch.date', 'fragments in clean bam', 'sensor', 'spike-in', 'other', 'admission', 'circumstances', 'target', 'geo series', 'library strategy', 'geo accession', 'Filter number', 'cortical_score', 'striatal_score', 'channel count', 'reporter', 'roi lot', 'chemistry', 'purification', 'replicate # in experiment', 'progression_free_survival_censor', 'experiment year_month', 'instance', 'integrative analysis', 'panel', 'expression', 'adapter sequence', 'mib', 'geo expression data']"
+Other,Sample and Experimental Conditions,"['replicate / experiment', 'ClinicalInformation', 'spike-ins', 'preservation method', 'tags', 'restriction enzymes', 'structure', 'backbone', 'genetic variants', 'risk', 'immune border', 'comments', 'cag repeat size', 'library_batch', 'enrichment method', 'library prep person', 'carbon source', 'corrector', 'coo', 'angiogenesis score', 'ras score', 'cag repeats', 'cycling', 'respirations per minute', 'cag length', 'commercial source', 'topography', 'kit mutation', 'library version', 'sort strategy', 'match degree', 'collected_by', 'platform', 'biological_replicate', 'genetic specifics', 'last follow-up', 'ago protein', 'kit', 'scan method', 'to concatenate', 'total bilirubin', 'littermate', 'processing batch', 'mean.corpuscular.volume', 'histone mark', 'modality', 'temp', 'nutritional state', 'Cluster', 'markers used for sorting', 'number cag repeats', 'experimental variables', 'gel_bead_version', 'pipeline.version', 'tau_score', 'profession', 'freezer', 'labor', 'data file subset', 'data type', 'Cycle', 'paired with', 'batch number', 'number of replicates', 'water salinity', 'locale', 'asbestos-fiber count', 'method of preservation']"
+Other,Genetic and Molecular Features,"['tandem repeat number', 'core code', 'chip-antibody cat', 'definite analysis', 'total volume', 'genetic variants inheritance', 'twins', 'virus accession number', 'note_other', 'test', 'promoter', 'preparation method', 'line name in manuscript', 'lactate', 'los', 'creatinine', 'tobacco', 'specific primer', 'culture results', 'run', 'sort fraction', 'variant', 'clinical', 'ectopic expression', 'biological replicates', 'percent_aligned', 'technical_replicate_number', 'biological_replicate_number', 'date_death', 'decode_name', 'sorting', 'chip processing date', 'Parity', 'calcium level', 'hospital admission', 'radiology', 'sort-gate', 'sort gate', 'stitched reads', 'raw reads', 'aligned reads', 'level', 'performance', 'vascular support', 'has_pressure', 'viral titre', 'pool', 'sorting fraction', 'oxygen', 'detachment', 'primers', 'gel bead version', 'rip', 'ubi', 'measure', 'Weight', 'pooling', 'functional connectivity', 'paradigm', 'div', 'sorting probe', 'product', 'oxygenation', 'expressing', 'operator', 'insertion site distance to gene', 'replica', 'scale']"
+Other,Experimental and Technical Specifications,"['technical replicates', 'knockdown target', 'submission date', 'company', 'drinking', 'replicate experiment', 'chip antibody manufacturer', 'salt.score', 'library label_name', 'metabolic activity', 'animals pooled', 'isolated by', 'driver gene', 'transcription factor expression level', 'cutting enzymes', 'chip antibody details', 'antigen reactivity', 'number of cag repeats', 'data presented in the manuscript', 'hit.status', 'sorting criteria', 'well diameter in um', 'molecule purification', 'clinical comments', 'digestion enzyme', 'incubation temperature', 'chip antibody manufacturers', 'bilirubin', 'ast', 'encode accession', 'alt', 'variation', 'Labeling_reference', 'Extraction_reference', 'Extraction_amount', 'zone', 'mating pair', 'ARN_quality', 'extraction batch', 'mother from', 'expression level', 'nitrogen', 'tubular shadows', 'exposed pollutants', 'cross', 'behavior', 'mean number of oocysts', 'number of half-sclerotomes', 'Bra', 'body weight', 'sampling post confirm', 'library_strategy', 'term accession number', 'term source ref', 'experiment performed in', 'vector construct', 'chip magnetic beads', 'gating', 'express', 'isolation column', 'antibody lot number', 'antibody antibody description', 'immunology', 'details', 'reactivity', 'assay type', 'clip antibody cat', 'feature type']"
+Other,Data Characteristics,"['domain', 'par-clip', 'data_type']"
+Biospecimen Race,Self-Reported Race,"['self_reported_race', 'race/ethnicity', 'race_ethnicity']"
+Biospecimen Race,Ethnic Grouping,"['ethnic group', 'Ethnic group', 'ethnicity', 'Ethnicity']"
+Biospecimen Race,Ancestral Origin,['ancestry']
+Biospecimen Race,Race General Classification,"['race', 'Race']"
+Treatment Dosage Regimen,Protocol Details,"['protocol', 'protocol description', 'protocol number', 'study protocol', 'digestion protocol', 'labeling protocol', 'library preparation protocol', 'library preparation method', 'extraction_protocol', 'extract_protocol', 'extract protocol', 'extraction_protocol_fragmentation', 'chip_protocol', 'chip_protocol_chromatin_amount', 'chip_protocol_bead_type', 'chip_protocol_antibody_amount', 'chip_protocol_bead_amount', 'growth protocol', 'stimulation protocol', 'library protocol']"
+Treatment Dosage Regimen,Dosage and Concentration,"['dose', 'immunization dose', 'vaccination dose', 'infectious_dose', 'virus dose', 'inoculation dose', 'lung radiation dose', 'concentration', 'viral concentration', 'Extraction_concentration']"
+Treatment Dosage Regimen,Duration and Time,"['duration', 'duration of illness', 'culture duration', 'stimulation duration', 'duration in hours', 'duration_units', 'duration of cultivation', 'symptom duration', 'psoriasis duration', 'Duration of psoriasis', 'illness_duration']"
+Treatment Dosage Regimen,Vaccination and Immunization,"['vaccination', 'immunization', 'vaccination route', 'vaccination boost', 'vaccination state', 'immunization route']"
+Treatment Dosage Regimen,Regimen and Schedule,"['regimen', 'schedule', 'dietary regiment', 'weekly dosing']"
+Treatment Dosage Regimen,Biological and Technical Parameters,"['mutation', 'education', 'derivation', 'induction', 'inoculation', 'indication', 'virus added', 'culture variation', 'Induration']"
+Treatment Dosage Regimen,Library and Data Preparation,"['library preparation', 'library protocol']"
+Treatment Dosage Regimen,General and Miscellaneous,"['region', 'protocols']"
diff --git a/RDAS_RDOMICS/scripts/sample_characteristics_harmonization/sample_characteristics_harmonization_output/5_subclustered_sample_characteristics_v2_expert_consolidated.csv b/RDAS_RDOMICS/scripts/sample_characteristics_harmonization/sample_characteristics_harmonization_output/5_subclustered_sample_characteristics_v2_expert_consolidated.csv
new file mode 100644
index 0000000..2d824c9
--- /dev/null
+++ b/RDAS_RDOMICS/scripts/sample_characteristics_harmonization/sample_characteristics_harmonization_output/5_subclustered_sample_characteristics_v2_expert_consolidated.csv
@@ -0,0 +1,18 @@
+main_category,subcategory,labels
+Biospecimen Type,Tissue and Cell Types,"['cell stage', 'tissues', 'primary cell line', 'tissue subgroup', 'cell line/tissue', 'cell line/tissue source', 'monocyte', 'sorted cell type', 'lymphocyte', 'cell or tissue type','tissue', 'cell type', 'cell line', 'tissue type', 'celltype', 'tissue anatomic site', 'cell description', 'cell sex', 'cell', 'Tissue', 'tissue source', 'tissue/cell type', 'cell subtype', 'country of serum collection', 'cell_type', 'cell subset', 'tissue preparation', 'tissue of origin', 'cell karyotype', 'cell lineage', 'tissue_type', 'flowcell', 'sorted cells', 'cell population', 'organ/tissue', 'predicted celltype', 'predicted parent celltype', 'timepoint biopsy', 'lymphocyte_percent', 'lymphocyte_absolute', 'monocyte_percent', 'monocyte_absolute', 'cell projection', 'cell line code', 'white_blood_cell_count', 'tissue_depot', 'red blood cells', 'white blood cells', 'specimen', 'blood obtained', 'tissue substructure', 'tissue structure', 'organ', 'cell phenotype', 'per lymphocytes', 'per monocytes', 'TargetedCellType', 'CellLine', 'cells', 'tissue.type', 'biopsy', 'monocytes', 'blood collection tube coating', 'blood_group', 'cell types', 'responder cell line', 'cell line of origin', 'biopsy type', 'cell source', 'tissue/cell line', 'tissue archive method', 'spike-in cell_line', 'spike-in cell_type', 'tissue origin', 'blood.source', 'clinical diagnosis specimen', 'biopsy data, villus height to crypt depth', 'cell_line', 'tissue notes', 'cell fraction', 'responder cells', 'biopsy site', 'tissue-of-origin', 'tissue processing', 'cell part', 'cell line_name', 'cell_origin', 'tissue class', 'cell origin', 'tissue location', 'cell type origin', 'cell line type', 'isolation of tumor cells', 'primary cell type', 'cell line origin', 'tumor cell type', 'original cell line', 'cell lining', 'Tumor tissue', 'brain tissue', 'cell type background',  'cell-subtype', 'Cells', 'blood', 'source organ', 'tissue zone', 'bacterial cells', 'tissue extraction', 'cell line source', 'cell type/line', 'source cell type', 'tissue/cell info', 'tissue group', 'source tissue', 'cell lines', 'cell/tissue type', 'Tissue Factor', 'Cell type', 'organ obtained', 'primary cells', 'tissue compartment', 'cell line background', 'data tissue_collection', 'tissue collection', 'cell line name', 'Cell line', 'cell-type', 'derived cell line', 'source cell line', 'tumor tissue source', 'stem cell', 'source cell',  'Tissue type', 'cell tye', 'tumor organ site', 'cell line/type', 'tumor cell line', 'lymphocytes', 'cell type source', 'tissue subtype', 'tissue region',  'cell lie', 'area/tissue', 'Organ', 'Type', 'Histological type', 'vs type', 'histological.type', 'sample_type']"
+Biospecimen Type,Cell and Tissue Characteristics,"['serum type', 'specimen_name', 'cell culture', 'primary tissues', 'transplanted organ', 'lymphocyte.reaction', 'cell state', 'cell compartment', 'cell subpopulation', 'cell density', 'specimen site', 'cell number',  'lymphocyte_count', 'sorted cell_type', 'cells detected', 'tissue derivation', 'age at blood collection', 'organ system', 'developmental stage/tissue', 'lymphocytes_count', 'monocytes_count', 'tissue acquisition', 'cell surface markers', 'percentage of tumor cells', 'age at biopsy date', 'cells_loaded', 'Age at interview & blood sampling', 'biopsy vs surgical resection', 'treated stem cells', 'age at skin biopsy', 'cell passage', 'cell cycle stage', 'biopsy collection date', 'bone marrow mononuclear cells sorted from', 'additional cell lineages present in dataset', 'bacteria tissue', 'organ failure', 'large cell lung cancer Derived from metastatic site', 'cell subpopulation/marker', 'cell characterization', 'source cells', 'cell line source gender', 'cell mixing ratio', 'BRAIN (CEREBELLUM), BIOPSY', 'cell line source age', 'cell line source tissue', 'cell mixture', 'small cell lung cancer Derived from metastatic site', 'injected cells', 'stimulation', 'phenotype', 'morphology', 'case number', 'transduction', 'sorted compartment', 'population', 'source type', 'number of relapses', 'Phenotype', 'line type', 'clinical phenotype', 'case_phenotype', 'als phenotype', 'sub-population', 'health status', 'bacterial lysate', 'responder', 'simulation', 'karyotype', 'compartment', 'parental line', 'FISH origin', 'surface marker', 'body site', 'clinical phenotypes', 'phenotypes', 'clone phenotype', 'twin status', 'Karyotype', 'enrichment', 'lot number', 'surface markers', 'es line', 'clone name', 'efflux status', 'source muscle', 'fold enrichment', 'sediment', 'initial preparation', 'anatomic site', 'derived culture', 'genotype background', 'Morphology', 'chip antibody', 'antibody', 'molecule subtype', 'type', 'molecule type', 'library type', 'molecule', 'isolate', 'material', 'parity', 'background', 'genetic background', 'epithelial', 'culture_result', 'smear_results', 'full_genotype', 'hip_circumference',  'starting cell', 'blood island injection', 'cell preparation', 'cell dissociation', 'peripheral blood', 'cells/condition', 'cell status', 'serum',  'age at blood draw',  'growth phase of cells',  'age at biopsy', 'maturation to macrophage', 'melanoma cell type', 'histological findings of renal specimen', 'renal biopsy', 'name of tissue', 'cell line passage', 'blood pressure', 'cell line for infection', 'injected cell line', 'parental cell type', 'neuroblastoma cell line', 'derived cell_type', 'cell number per well', 'macrophages', 'cell type depletion', 'cell type implantation', 'sorted subset of cells', 'cell subsets', 'sorted cell', 'derived cell type', 'cell morphology', 'biologics', 'biological source', 'gene', 'nulliparous',  'allele nominal', 'organoid line', 'tumor side']"
+Biospecimen Type,Sample Isolation and Preparation,"['library prep', 'protocol', 'protocol description', 'protocol number', 'study protocol', 'digestion protocol', 'labeling protocol', 'library preparation protocol', 'library preparation method', 'extraction_protocol', 'extract_protocol', 'extract protocol', 'extraction_protocol_fragmentation', 'chip_protocol', 'chip_protocol_chromatin_amount', 'chip_protocol_bead_type', 'chip_protocol_antibody_amount', 'chip_protocol_bead_amount', 'growth protocol', 'stimulation protocol', 'library protocol', 'protocols', 'library preparation', 'library protocol', 'waist_circumference', 'microdissection', 'assayed molecule', 'lymphs', 'line', 'isolation_method', 'skin type', 'library well', 'library plate', 'platelet', 'antigen', 'markers', 'skin', 'colony of_origin', 'hemoglobin genotype', 'trachea region', 'intrinsic subtype', 'anatomic_location', 'anatomic location', 'microbiota status', 'sputum_smear', 'sputum_culture', 'growth', 'eye', 'brain bank', 'splice variant', 'transplant type', 'chip target', 'bal_culture', 'bal_smear', 'smear of index case', 'components', 'fibrinogen', 'target molecule', 'enzyme', 'marrow', 'variety', 'hemisphere', 'microglia media', 'histological..subtype', 'unsorted or sorted', 'input material', 'subclass', 'fracture site', 'immune_or_nasal', 'any_immune', 'embryo', 'anatomical location', 'fetus', 'lesional (ls) vs. normal', 'Genetic background', 'lobe', 'cytology', 'aspiration site', 'vector constructs', 'sandwich type', 'types', 'modifications', 'library-type', 'lymph node number', 'upper or lower extremity', 'growth pattern', 'volar or non-volar', 'isolation method', 'specific heart region', 'lymph node', 'graft source', 'derived from', 'BREAST', 'type of library', 'fusion', 'hemolysis score', 'autopsy', 'resection', 'construct', 'preparation']"
+Biospecimen Disease Condition,Disease State,"['disease state', 'disease', 'diagnosis', 'condition', 'infection', 'disease status', 'tumor type', 'housing condition', 'diseasestate', 'clinical diagnosis', 'histologic diagnosis', 'tumor grade', 'infection status', 'tumor location', 'infection states', 'disease group', 'final diagnosis', 'cancer status', 'hours post infection', 'disease severity', 'infection protocol', 'working_diagnosis', 'first_diagnosis', 'tumor grading', 'pathology', 'disease duration', 'disease_category', 'institutional tumor diagnosis', 'disease location', 'disease staging', 'cancer site', 'tumor', 'neuropathological_diagnosis', 'clinical_diagnosis', 'disease_duration_years', 'culture condition', 'site of infection', 'cancer type', 'infection code', 'culture conditions', 'disease_status', 'reference diagnosis', 'condition description', 'adjusted disease severity index', 'diagnosis date', 'growth condition', 'additional conditions', 'disease symptom', 'other diseases', 'disease type', 'disease subtype', 'DiseaseState', 'diagnosis.after.path.re.review', 'diagnosis.of.record', 'lung disease', 'chronic diseases', 'molecular.diagnosis', 'primary.tumor', 'tumor_name', 'radiation administered prior to tumor resection', 'histological diagnosis', 'tumor localization', 'broad diagnosis', 'behavior at diagnosis', 'tumor category', 'disease activity', 'stimulation condition', 'primary diagnosis', 'light condition', 'diagnosis total', 'diagnosis hep flex', 'diagnosis rectum', 'lung pathology', 'tumor_entity_subtype', 'diagnosis colonic', 'diagnosis details', 'diagnosis anal perianal', 'diagnosis oral', 'diagnosis rectal', 'disease_state', 'tumor full_name', 'disease_group_detailed', 'disease_group', 'pathology_note', 'distance from the tumor center', 'index_case_disease_site', 'tumor subgroup', 'years since diagnosis', 'histopathology', 'skin disease', 'Diagnosis', 'tumor subtype', 'clinical condition', 'Condition', 'conditions',  'Disease', 'maternal disease status', 'disease condition', 'tumor vs. normal', 'tumor status', 'tumor/control',  'disease diagnosis',  'disease classification', 'illness', 'Illness', 'status', 'Status',  'groups', 'diagnostic_group', 'classification group',  'subgroup', 'Group', 'control or als',  'clinical group', 'clinical_subgroup', 'group label', 'case or control', 'genotype & treatment', 'group_tag', 'experiment grouping',  'sample group', 'patient diagnosis', 'donor_health_status',  'patient category', 'sample_group', 'Sample Group', 'patient_status', 'patient group', 'donor disease state',  'donor diagnosis', 'health_status', 'Sample group', 'subject id/diagnosis', 'subject condition', 'subject diagnosis', 'clinical diagnosis patient']"
+Biospecimen Disease Condition,Disease Characteristics,"['infection group', 'worm infection', 'Tumor size', 'disease_extension', 'primary disease', 'incubation conditions', 'neuropathological diagnosis',  'tumor.in.left.right.lobe', 'tumor region', 'disease_duration', 'hour post infection', 'disease category', 'tumor type/grade', 'virus infection',  'bacterial infection', 'infection state', 'infection duration', 'parental tumor subtype', 'preliminary diagnosis', 'primary tumor site', 'malaria infection', 'tumor histology', 'metastatic tumor site', 'lesion_disease_factor', 'infection type exposure', 'primary tumor', 'duration of infection', 'experimental condition', 'malignant tumor', 'disease model', 'initial tumor increase/(-)decrease', 'tumor size', 'tumor_grading', 'tumor source', 'conditioning received', 'active_disease', 'Conditioning', 'disease phase', 'tumor.grade', 'qualifying condition', 'clinical.diagnosis.history', 'viral infection', 'maximal prior disease extend', 'hours of infection', 'years of disease', 'disease subset', 'conditioned media type', 'conditioned media origin', 'Location tumor', 'Tumor type', 'growth conditions', 'infection type', 'plasmodium falciparum infection status', 'single or double infection', 'infection route', 'stress condition', 'pulmonary.disease', 'cancer.past', 'active cancer', 'cardiovascular.disease', 'oncologic diagnosis', 'environmental condition', 'molecular condition', 'disease course', 'disease onset', 'tumor_size', 'library outgrowth conditions',  'associated primary tumor no', 'tumor_site', 'Chief Disease', 'tumor model', 'tumor origin', 'disease outcome', 'mechanical condition', 'Wash Condition', 'Labeling Condition', 'location of tumors', 'brain tumor region', 'initial tumor volume', 'tumor class', 'disease in non-fip', 'brain tumor',  'disease grade', 'tumor inoculation', 'original tumor', 'molarity of infection', 'duration of disease', 'genotype/disease state', 'infection rate', 'infection period', 'oxygen condition', 'conditioned medium', 'conditioned media source', 'growing media conditions', 'Disease state', 'disease feature', 'site of_disease_onset', 'disease name', 'tumor position', 'cancer predisposition', 'original tumor type', 'growth_condition', 'plasmodium infection', 'length of infection', 'molecular diagnosis', 'experimental conditions', 'months post infection', 'tumor who grade', 'reference condition', 'test condition', 'rounds of infection', 'Infection Status', 'clinical info', 'histology', 'primary site', 'brain region', 'who category', 'initial ich volume', 'who grade', 'number of malaria infections', 'section', 'infection_status', 'Histopathological diagnostic', 'hours post-invasion', 'hours post invasion', 'mechanical ventilation', 'antibody description', 'inflammation status', 'injection_type', 'Histology', 'localization', 'isolate type', 'location of onset', 'dissection', 'injection site', 'clinical indication', 'lesion status', 'clinic status', 'metastatic site', 'hours_post_infection', 'injection', 'er status', 'neuropathological.information', 'hours post fertilization', 'viral infected', 'infectious', 'water type', 'maternal health status', 'single or double infected', 'clone type', 'hours post-infection', 'channel type', 'interaction status', 'pair status', 'infection_state', 'vaccination status', 'type of insertion', 'clinical manifestation', 'incubation period', 'viral inactivation', 'environmental factor', 'nes status', 'zinc status', 'round of selection', 'reference lot', 'reference cat', 'histopathological diagnostic', 'cohort', 'smoking status', 'pasi', 'pathologic status', 'grade', 'surgical status', 'outcome', 'subtype', 'culture result', 'site_onset', 'metastasis', 'severity score', 'stress', 'smoker', 'severity',  'viral_positivity', 'neoplastic', 'consortium lung phenotype', 'malaria_transmission', 'consortium lung phenotype surrogate variable', 'meconium ileus status', 'persistent ps aer status', 'malaria_status', 'dementia', 'diagnostic_mean', 'death', 'survival_status', 'progression', 'parasitemia', 'family history', 'symptoms onset date', 'with or without clonal heterogeneity', 'international prognostic index', 'seizure', 'asthma', 'smear_result', 'anti-centromere', 'recurrence', 'psychiatric disorder', 'gastrointestinal disorder', 'cerebral palsy', 'mutational subclass', 'birth defects', 'neurological disorder', 'developmental/speech disorder', 'diabetes', 'percent_weight_loss', 'molecular classification', 'recurrent_status', 'dysplasia now', 'health state', 'cigarette smoker', 'medical.history', 'inflammation_status', 'pregnancy status', 'cirrhosis present', 'chronic hypertension', 'survival after surgery', 'death with metastasis', 'outcome related', 'infected/uninfected', 'neoplasia type', 'symptom severity', 'viral shedding', 'tst result', 'symptomatic', 'smoking', 'hypertension', 'cag_repeat', 'conversion', 'prognosis', 'parasitemia category', 'survival status', 'exposure_latent', 'pasi score', 'obesity', 'stress exposure', 'genetic class', 'symptom', 'mutation_carrier_status', 'cag_repeats', 'phase', 'das score', 'infectivity', 'total cholesterol', 'fibrosis degree', 'Smoking status',  'primary/metastasis']"
+Biospecimen Disease Condition,Disease Progression,"['interim pet response', 'primary/recurrent', 'pasi_total', 'Outcome', 'remission', 'swollen joints', 'current status', 'endoscopic_activity', 'mitotic index', 'survival characteristics', 'vascular.invasion', 'mutational.status', 'multifocal', 'smoker or non smoker', 'exposed to', 'familial anamnesis', 'onset', 'progression_free_survival', 'primary recurrent', 'smoking_status', 'clinical outcome', 'metastasis site', 'glioma', 'subcutaneous neurofibromas', 'plexiform neurofibromas', 'cutaneous neurofibromas', 'facial dysmorphism', 'scoliosis', 'skin-fold freckling', 'Lymph node involvement', 'primary_recurrent', 'clinically_aggressive', 'total skin score', 'lesion_label', 'presence_of_parasites_lesion', 'infiltration', 'severity_score', 'lesion_size', 'bleeding', 'stool frequency', 'clinical presentation', 'alive', 'prodromal status', 'mutation class', 'fever', 'symptoms', 'tuberculosis_history', 'family_history', 'exitus', 'primary mutation', 'copy number gain', 'sofa score', 'als mutation', 'granuloma', 'brain metastasis', 'reason for intubation', 'relapse', 'syndrome', 'systemic sclerosis subtype', 'parasite density on admission', 'serologic response status', 'digestives_symptoms', 'radiation sensitivity', 'major_organ_involvement', 'severity binary', 'severe_eosinophilia', 'receptor status', 'histological grade', 'clinical phenotype details', 'cause.of.death']"
+Biospecimen Disease Condition,Disease Details,"['histological response', 'hereditary status', 'Family History', 'clinical information', 'parasite', 'primary vs metastatic', 'nonunion type', 'Dead/Alive', 'Location of distant metastasis', 'isolate sensitivity', 'sputum smear status', 'diffuse/limited', 'KIT mutation', 'antibody status', 'lymphoma subtype', 'primary_recurrence', 'neural tube defect', 'sofa_admission', 'affected status', 'skin phenotype', 'sum.risk.factors', 'psoriasis area-and-severity index', 'hospitalization', 'follicular lymphoma grade', 'psoriasis subtype', 'Scaling', 'skin score', 'previous severity', 'Overall erythema', 'degree of infiltrate', 'pathological type', 'fip status', 'mortality', 'gametocyte status', 'medical history', 'histological subtype', 'metastatic status', 'somatic mutation', 'respiratory score', 'gastrointestinal involvement', 'Death Cause', 'Inflammation', 'ocular involvement', 'vascular involvement', 'genital ulcer', 'arthritis', 'At Risk', 'oral ulcer', 'molecular subtype/phenotypic state', 'erythema nodule', 'reason for liver resection', 'injury model', 'febrile seizure', 'ar or asthma', 'autism diagnostic', 'alk mutation status', 'pulmonary cavitation', 'malignancy class', 'risk grade', 'glioma grade', 'immune infiltration', 'hind-limb paralysis', 'rift valley fever virus', 'engraftment', 'interstitial pneumonia', 'seizures/month', 'surgical indication', 'melanoma', 'major reason_for_surgery', 'primary/ recurrent', 'metastatic/primary', 'recurrent/primary', 'weight phenotype', 'resistance profile', 'embryo phenotype', 'etiology', 'myopathic motor_unit_potentials', 'mutation details', 'cognitive impairment', 'distant metastasis', 'tobacco use', 'parental/ne-like state', 'oocyst prevalence', 'post-symptom onset', 'invasive behavior', 'responder status', 'fibrosis', 'severity grade', 'diffuse vs limited', 'allergy', 'months_survival', 'progression_status', 'months_progression']"
+Biospecimen Disease Condition,Disease Severity,"['mitotic rate', 'positive Down screening risk', 'who class']"
+Biospecimen Age,Biospecimen Age,"['age', 'age/gender', 'time', 'time point', 'intubation_days', 'time point days', 'timepoint', 'Time after induction', 'age in years',  'age in_yrs', 'days post infection', 'time after infection', 'Age', 'age and disease', 'age, months', 'AGE',  'draw day', 'day of_tumor_harvest', 'day-post-infection', 'time post infection', 'day after seeding', 'sampling_timepoint', 'time-point', 'days after infection', 'collection time', 'time after treatment', 'age at sampling', 'age description', 'age group', 'year', 'collection time point', 'age_weeks', 'age_at_draw', 'time harvest', 'time points', 'Time', 'harvesting time', 'sampling timepoint', 'sampling time',  'year of surgery', 'age in year', 'animal age', 'day after intubation', 'age at harvest', 'time of day', 'age range', 'age/time point', 'life cycle stage', 'time point of infection', 'passage/days', 'collection timepoint', 'developmental stage/age', 'time after stimulation', 'age category', 'day post neural induction', 'days in culture', 'culture time', 'days_post_infection', 'date harvest', 'sampling.time', 'harvest time', 'age.days', 'time in culture', 'collection day', 'days after stimulation','sex/age', 'day post-infection', 'age years', 'Age at time of surgery', 'age at collection', 'culture age', 'age at time of collection', 'age at examination',  'age post-hatch', 'time infected',  'sampling time point', 'incubation time', 'time after virus injection', 'days', 'day of collection/passage', 'harvest time post treatment', 'harvest time point', 'age, yrs',  'age in months', 'age tier' ]"
+Treatment,General Treatment Info,"['treatment', 'treatment condition', 'group', 'vaccine', 'treatment description', 'treatmentshort', 'drug treatment', 'treatment group', 'control', 'control description', 'treatment duration', 'chemical compound', 'infected with/healthy control', 'vaccine doses', 'prior treatment', 'response_group', 'grouping', 'vaccine type', 'current medication', 'treatment location', 'chemotherapy', 'Prior Treatment', 'treatment administration route', 'treatment frequency', 'study group', 'drug', 'experimental group', 'treatment dose', 'treatment arm', 'prescription drugs', 'treatment-outcome code', 'radiation.therapy', 'treatment protocol', 'cell treatment', 'enzymatic treatment', 'vaccine group', 'dose group', 'group description', 'inhibitor treatment', 'dose_group', 'batch group', 'previous treatments', 'cell stimulation', 'Medication at blood sampling', 'exposure condition', 'therapy used', 'antibiotic treatment', 'healthy control', 'control/intervention', 'treatment status', 'ear treatment', 'therapy', 'compound', 'biological drug', 'treatment category', 'vaccine administration', 'intervention group', 'antibody treatment', 'treatments', 'first-line therapy', 'chemical treatment', 'no treatment', 'treatment condition/type', 'pharmacologic treatment type', 'drug administration', 'Treatment', 'treatment_type', 'Drug', 'treatment type', 'animal treatment', 'Exposures', 'perturbation class', 'perturbation',  'medicine', 'untreated/treated', 'patient treatment', 'treatment/sample type',  'treatment of mice',  'compound treatment', 'chronic medication', 'acute medication', 'diabetes_medication']"
+Biospecimen Organism,Cell Strain,"['strain', 'strain background', 'strain/background', 'mouse strain', 'background strain', 'strain description', 'strain/genotype', 'parasite strain', 'virus strain', 'malaria strain', 'strain name', 'viral strain', 'bacterial strain', 'host strain', 'genotype/strain', 'laboratory strain', 'recipient strain', 'infection strain', 'strain info', 'parental strain', 'strain source', 'strain origin', 'strain/isolate', 'pathogen strain', 'Mouse strain', 'parent_strain', 'original strain', 'infectious strain', 'cell strain', 'Cell strain', 'strain_recipient', 'infrequent clonal strain code', 'Strain', 'age and_strain', 'Virus Strain', 'strain  background', 'plasmodium strain', 'parental-strain', 'strains', 'strain/model', 'graft recipient strain', 'strain recipient', 'bacteria strain']"
+Biospecimen Organism,Organism,"['organism', 'organism part', 'cell organism', 'host', 'source_organism', 'OrganismPart', 'host cell', 'host genotype', 'host mice strain', 'host vendor', 'host strain/background', 'mouse line abbreviation', 'mouse line', 'host cell line', 'host organism', 'host cell type', 'host_cell_line', 'specific-host', 'host age', 'species', 'Species',  'host mouse strain', 'host mouse_tissue', 'host cells', 'host tissue', 'breed', 'cattle breed', 'mammalian host', 'organism_status', 'organism_part', 'spike-in organism', 'organismpart', 'human cell genotype/variation']"
+Biospecimen Sex,Sex,"['gender', 'Sex', 'sex', 'Gender', 'SEX', 'female', 'fetal sex', 'biological sex', 'InfantSex', 'placental sex', 'sex predicted', 'Sex of recipient mice', 'gender source', 'source gender', 'gender composition', 'animal sex', 'donor_sex', 'donor age, sex', 'Sex of donor mice', 'donor sex', 'donor gender',  'subject gender', 'source patient gender', 'patient sex']"
+Biospecimen Race,Race/Ethnic,"['self_reported_race', 'race/ethnicity', 'race_ethnicity', 'ethnic group', 'Ethnic group', 'ethnicity', 'Ethnicity', 'race', 'Race', 'donor_ethnicity', 'donor race']"
+Biospecimen Race,Ancestral Origin,['ancestry']
+Treatment Dosage Regimen,Treatment Schedule,"['dose', 'immunization dose', 'vaccination dos+F61e', 'infectious_dose', 'virus dose', 'inoculation dose', 'lung radiation dose', 'concentration', 'viral concentration', 'Extraction_concentration', 'rip antibody', 'regimen', 'schedule', 'dietary regiment', 'weekly dosing']"
+Treatment Dosage Regimen,Treatment Duration,"['duration', 'duration of illness', 'culture duration', 'stimulation duration', 'duration in hours', 'duration_units', 'duration of cultivation', 'symptom duration', 'psoriasis duration', 'Duration of psoriasis', 'illness_duration']"
\ No newline at end of file
diff --git a/RDAS_RDOMICS/scripts/sample_characteristics_harmonization/sample_characteristics_harmonization_output/clustering_confidence_report.csv b/RDAS_RDOMICS/scripts/sample_characteristics_harmonization/sample_characteristics_harmonization_output/clustering_confidence_report.csv
new file mode 100644
index 0000000..b77ba8a
--- /dev/null
+++ b/RDAS_RDOMICS/scripts/sample_characteristics_harmonization/sample_characteristics_harmonization_output/clustering_confidence_report.csv
@@ -0,0 +1,2815 @@
+label,count,category,method,confidence,details
+age,73415,Biospecimen Age,keyword,HIGH,exact_match: age
+time,17068,Biospecimen Age,keyword,HIGH,exact_match: time
+time point,12459,Biospecimen Age,keyword,HIGH,exact_match: time
+timepoint,9424,Biospecimen Age,keyword,MEDIUM,keyword: timepoint
+developmental stage,5106,Biospecimen Age,keyword,MEDIUM,keyword: developmental stage
+Stage,4189,Biospecimen Age,keyword,MEDIUM,pattern: .*age.*
+day,3722,Biospecimen Age,keyword,HIGH,exact_match: day
+agent,3539,Biospecimen Age,keyword,MEDIUM,pattern: .*age.*
+age in years,2898,Biospecimen Age,keyword,HIGH,exact_match: age
+experiment,1725,Biospecimen Age,similarity,MEDIUM,Similar to: experimental day (score: 0.769)
+Age,1662,Biospecimen Age,keyword,HIGH,exact_match: age
+datatype description,1606,Biospecimen Age,similarity,MEDIUM,Similar to: age description (score: 0.800)
+passage,1586,Biospecimen Age,keyword,MEDIUM,keyword: passage
+collection_method,1517,Biospecimen Age,similarity,MEDIUM,Similar to: collection time (score: 0.750)
+tumor stage,1390,Biospecimen Age,keyword,MEDIUM,pattern: .*age.*
+tag,1317,Biospecimen Age,similarity,MEDIUM,Similar to: stage (score: 0.750)
+culture,1264,Biospecimen Age,similarity,MEDIUM,Similar to: culture age (score: 0.778)
+clinical status,1187,Biospecimen Age,similarity,MEDIUM,Similar to: clinical stage (score: 0.828)
+passages,1138,Biospecimen Age,keyword,MEDIUM,keyword: passage
+fraction,1003,Biospecimen Age,similarity,MEDIUM,Similar to: age fraction (score: 0.800)
+lab description,997,Biospecimen Age,similarity,MEDIUM,Similar to: age description (score: 0.867)
+development stage,897,Biospecimen Age,keyword,MEDIUM,pattern: .*age.*
+age_onset,876,Biospecimen Age,keyword,MEDIUM,pattern: .*age.*
+survival_yr,876,Biospecimen Age,similarity,MEDIUM,Similar to: survival year (score: 0.833)
+age description,839,Biospecimen Age,keyword,HIGH,exact_match: age
+disease stage,804,Biospecimen Age,keyword,MEDIUM,pattern: .*age.*
+treatment time,775,Biospecimen Age,keyword,HIGH,exact_match: time
+age group,642,Biospecimen Age,keyword,HIGH,exact_match: age
+infection time,635,Biospecimen Age,keyword,HIGH,exact_match: time
+year,633,Biospecimen Age,keyword,HIGH,exact_match: year
+passage_if_expanded,572,Biospecimen Age,keyword,MEDIUM,keyword: passage
+growth phase,558,Biospecimen Age,similarity,MEDIUM,Similar to: growth stage (score: 0.750)
+doubling time,553,Biospecimen Age,keyword,HIGH,exact_match: time
+case,551,Biospecimen Age,similarity,MEDIUM,Similar to: cage (score: 0.750)
+infectious agent,546,Biospecimen Age,keyword,MEDIUM,pattern: .*age.*
+collection time point,533,Biospecimen Age,keyword,HIGH,exact_match: time
+age_weeks,500,Biospecimen Age,keyword,MEDIUM,pattern: .*age.*
+age_at_draw,500,Biospecimen Age,keyword,MEDIUM,pattern: .*age.*
+time harvest,500,Biospecimen Age,keyword,HIGH,exact_match: time
+sampling time_point_label,500,Biospecimen Age,keyword,LOW,pattern: .*time.*
+time_to_malaria,500,Biospecimen Age,keyword,LOW,pattern: .*time.*
+reagent,500,Biospecimen Age,keyword,MEDIUM,pattern: .*age.*
+age of enrollment,500,Biospecimen Age,keyword,HIGH,exact_match: age
+days_in_hospital,500,Biospecimen Age,keyword,LOW,pattern: .*day.*
+age_at_diagnosis,500,Biospecimen Age,keyword,MEDIUM,pattern: .*age.*
+age of onset of persistent ps aer or censored age,500,Biospecimen Age,keyword,HIGH,exact_match: age
+days since vaccine,500,Biospecimen Age,keyword,LOW,pattern: .*day.*
+dev_stage,500,Biospecimen Age,keyword,MEDIUM,pattern: .*age.*
+date harvest,500,Biospecimen Age,similarity,MEDIUM,Similar to: time harvest (score: 0.833)
+surgery number,500,Biospecimen Age,similarity,MEDIUM,Similar to: usage number (score: 0.769)
+age_at_death_years,492,Biospecimen Age,keyword,MEDIUM,pattern: .*age.*
+passage number,485,Biospecimen Age,keyword,MEDIUM,keyword: passage
+survival,444,Biospecimen Age,similarity,MEDIUM,Similar to: survival time (score: 0.762)
+time.from.exposure.months,434,Biospecimen Age,keyword,LOW,pattern: .*time.*
+day of trial,399,Biospecimen Age,keyword,HIGH,exact_match: day
+day post infection,391,Biospecimen Age,keyword,HIGH,exact_match: day
+age at death,387,Biospecimen Age,keyword,HIGH,exact_match: age
+days since vaccination,387,Biospecimen Age,keyword,LOW,pattern: .*day.*
+induction date,385,Biospecimen Age,similarity,MEDIUM,Similar to: induction time (score: 0.857)
+sampling timepoint,383,Biospecimen Age,keyword,MEDIUM,keyword: timepoint
+exposure,381,Biospecimen Age,similarity,MEDIUM,Similar to: exposure time (score: 0.762)
+birth date,374,Biospecimen Age,llm,HIGH,"Birth date is used to calculate age, which fits well with the Biospecimen Age category."
+gold stage,366,Biospecimen Age,keyword,MEDIUM,pattern: .*age.*
+year of surgery,363,Biospecimen Age,keyword,HIGH,exact_match: year
+age in year,362,Biospecimen Age,keyword,HIGH,exact_match: age
+days of differentiation,353,Biospecimen Age,keyword,LOW,pattern: .*day.*
+age at_treatment,353,Biospecimen Age,keyword,HIGH,exact_match: age
+treatment age_group,353,Biospecimen Age,keyword,MEDIUM,pattern: .*age.*
+culture type,334,Biospecimen Age,similarity,MEDIUM,Similar to: culture time (score: 0.833)
+follow up years,332,Biospecimen Age,llm,HIGH,"Refers to the time period of follow-up, which is related to the age of the biospecimen"
+animal age,330,Biospecimen Age,keyword,HIGH,exact_match: age
+treatment/time point,328,Biospecimen Age,keyword,MEDIUM,keyword: time point
+dosage,319,Biospecimen Age,keyword,MEDIUM,pattern: .*age.*
+week,317,Biospecimen Age,keyword,HIGH,exact_match: week
+osteogenesis day,317,Biospecimen Age,keyword,HIGH,exact_match: day
+timepoint_months,313,Biospecimen Age,keyword,MEDIUM,keyword: timepoint
+development,310,Biospecimen Age,similarity,MEDIUM,Similar to: development stage (score: 0.786)
+InitialTimePoint,300,Biospecimen Age,keyword,MEDIUM,keyword: timepoint
+category,296,Biospecimen Age,similarity,MEDIUM,Similar to: age_category (score: 0.800)
+experiment type,295,Biospecimen Age,similarity,MEDIUM,Similar to: experimental day (score: 0.774)
+description,294,Biospecimen Age,similarity,MEDIUM,Similar to: age description (score: 0.846)
+age at diagnosis,291,Biospecimen Age,keyword,HIGH,exact_match: age
+path.stage,286,Biospecimen Age,keyword,MEDIUM,pattern: .*age.*
+differentiation stage,286,Biospecimen Age,keyword,MEDIUM,pattern: .*age.*
+description of day,275,Biospecimen Age,keyword,HIGH,exact_match: day
+differentiation day,270,Biospecimen Age,keyword,HIGH,exact_match: day
+day_of_euthanasia,268,Biospecimen Age,keyword,LOW,pattern: .*day.*
+visit day,265,Biospecimen Age,keyword,HIGH,exact_match: day
+age_diagnosis_years,245,Biospecimen Age,keyword,MEDIUM,pattern: .*age.*
+age of onset,240,Biospecimen Age,keyword,HIGH,exact_match: age
+Tumor stage,226,Biospecimen Age,keyword,MEDIUM,pattern: .*age.*
+TimeUnit,225,Biospecimen Age,keyword,LOW,pattern: .*time.*
+sorter day,224,Biospecimen Age,keyword,HIGH,exact_match: day
+state,214,Biospecimen Age,similarity,MEDIUM,Similar to: stage (score: 0.800)
+art start year,212,Biospecimen Age,keyword,HIGH,exact_match: year
+sampling_timepoint,208,Biospecimen Age,keyword,MEDIUM,keyword: timepoint
+time post-stimulation,207,Biospecimen Age,keyword,HIGH,exact_match: time
+differentiation batch,207,Biospecimen Age,similarity,MEDIUM,Similar to: differentiation day (score: 0.850)
+developmental_stage,204,Biospecimen Age,keyword,MEDIUM,pattern: .*age.*
+days_symptom_onset,201,Biospecimen Age,keyword,LOW,pattern: .*day.*
+overall.survival..days,200,Biospecimen Age,keyword,LOW,pattern: .*day.*
+sampling time,199,Biospecimen Age,keyword,HIGH,exact_match: time
+time_since_onset,198,Biospecimen Age,keyword,LOW,pattern: .*time.*
+ga,194,Biospecimen Age,llm,MEDIUM,GA is likely an abbreviation for Gestational Age
+growth medium,193,Biospecimen Age,similarity,MEDIUM,Similar to: growth time (score: 0.750)
+hours,186,Biospecimen Age,llm,MEDIUM,"This label could refer to the age of a biospecimen in hours, such as the time elapsed since collection."
+stimulation time and condition,182,Biospecimen Age,keyword,HIGH,exact_match: time
+age at_diagnosis,177,Biospecimen Age,keyword,HIGH,exact_match: age
+dev stage,177,Biospecimen Age,keyword,MEDIUM,pattern: .*age.*
+lineage,176,Biospecimen Age,keyword,MEDIUM,pattern: .*age.*
+day of differentiation,174,Biospecimen Age,keyword,HIGH,exact_match: day
+Cause of death,172,Biospecimen Age,similarity,MEDIUM,Similar to: age of death (score: 0.846)
+survival time,170,Biospecimen Age,keyword,HIGH,exact_match: time
+survival cluster,170,Biospecimen Age,similarity,MEDIUM,Similar to: survival time (score: 0.759)
+differentiation,169,Biospecimen Age,similarity,MEDIUM,Similar to: differentiation day (score: 0.882)
+overall.survival.months,168,Biospecimen Age,similarity,MEDIUM,Similar to: overall.survival.time (score: 0.818)
+days post drug,164,Biospecimen Age,keyword,LOW,pattern: .*day.*
+collection time point (#) or necropsy,162,Biospecimen Age,keyword,HIGH,exact_match: time
+parasite stage,160,Biospecimen Age,keyword,MEDIUM,pattern: .*age.*
+time-point,158,Biospecimen Age,keyword,LOW,pattern: .*time.*
+days after infection,156,Biospecimen Age,keyword,LOW,pattern: .*day.*
+os_month,156,Biospecimen Age,similarity,MEDIUM,Similar to: os month (score: 0.875)
+differentiation_stage,152,Biospecimen Age,keyword,MEDIUM,pattern: .*age.*
+differentiation_method,152,Biospecimen Age,similarity,MEDIUM,Similar to: differentiation_age (score: 0.829)
+cage,151,Biospecimen Age,keyword,MEDIUM,pattern: .*age.*
+age.days,151,Biospecimen Age,keyword,MEDIUM,pattern: .*age.*
+infection.time.point.days,151,Biospecimen Age,keyword,LOW,pattern: .*day.*
+embryonic stage,150,Biospecimen Age,keyword,MEDIUM,pattern: .*age.*
+excision year,149,Biospecimen Age,keyword,HIGH,exact_match: year
+time points,144,Biospecimen Age,keyword,HIGH,exact_match: time
+cag,140,Biospecimen Age,similarity,MEDIUM,Similar to: cage (score: 0.857)
+Time,132,Biospecimen Age,keyword,HIGH,exact_match: time
+ventilator-free days,126,Biospecimen Age,keyword,LOW,pattern: .*day.*
+day-post-infection,123,Biospecimen Age,keyword,LOW,pattern: .*day.*
+time post infection,121,Biospecimen Age,keyword,HIGH,exact_match: time
+day after seeding,118,Biospecimen Age,keyword,HIGH,exact_match: day
+os month,116,Biospecimen Age,keyword,HIGH,exact_match: month
+day of_tumor_harvest,116,Biospecimen Age,keyword,HIGH,exact_match: day
+infection agent,116,Biospecimen Age,keyword,MEDIUM,pattern: .*age.*
+culture media,116,Biospecimen Age,similarity,MEDIUM,Similar to: culture days (score: 0.800)
+harvesting time,115,Biospecimen Age,keyword,HIGH,exact_match: time
+isolation source,113,Biospecimen Age,similarity,MEDIUM,Similar to: isolation stage (score: 0.774)
+collection time,106,Biospecimen Age,keyword,HIGH,exact_match: time
+time after treatment,106,Biospecimen Age,keyword,HIGH,exact_match: time
+growth media,106,Biospecimen Age,similarity,MEDIUM,Similar to: growth time (score: 0.783)
+age at sampling,105,Biospecimen Age,keyword,HIGH,exact_match: age
+gestational age,102,Biospecimen Age,keyword,HIGH,exact_match: age
+Usage number,101,Biospecimen Age,keyword,MEDIUM,pattern: .*age.*
+infected,101,Biospecimen Age,similarity,MEDIUM,Similar to: time infected (score: 0.762)
+average library size,100,Biospecimen Age,keyword,MEDIUM,pattern: .*age.*
+exposure time,100,Biospecimen Age,keyword,HIGH,exact_match: time
+age of psoriasis onset,100,Biospecimen Age,keyword,HIGH,exact_match: age
+treatment time point,98,Biospecimen Age,keyword,HIGH,exact_match: time
+ko induction_time,97,Biospecimen Age,keyword,LOW,pattern: .*time.*
+days post-vaccination,96,Biospecimen Age,keyword,LOW,pattern: .*day.*
+age at transplant,96,Biospecimen Age,keyword,HIGH,exact_match: age
+animal name,95,Biospecimen Age,similarity,MEDIUM,Similar to: animal age (score: 0.857)
+age.at.operation,92,Biospecimen Age,keyword,MEDIUM,pattern: .*age.*
+disease_stage,91,Biospecimen Age,keyword,MEDIUM,pattern: .*age.*
+days post onset of symptoms,90,Biospecimen Age,keyword,LOW,pattern: .*day.*
+"age, months",90,Biospecimen Age,keyword,MEDIUM,pattern: .*age.*
+survival_time,89,Biospecimen Age,keyword,LOW,pattern: .*time.*
+age of death,87,Biospecimen Age,keyword,HIGH,exact_match: age
+AGE,86,Biospecimen Age,keyword,HIGH,exact_match: age
+clinical stage,85,Biospecimen Age,keyword,MEDIUM,pattern: .*age.*
+clinical type,85,Biospecimen Age,similarity,MEDIUM,Similar to: clinical stage (score: 0.815)
+survival time in months,84,Biospecimen Age,keyword,HIGH,exact_match: time
+culture method,84,Biospecimen Age,similarity,MEDIUM,Similar to: culture time (score: 0.769)
+draw day,82,Biospecimen Age,keyword,HIGH,exact_match: day
+experiment label,82,Biospecimen Age,similarity,MEDIUM,Similar to: experimental day (score: 0.750)
+infectious challenge,82,Biospecimen Age,similarity,MEDIUM,Similar to: infectious agent (score: 0.778)
+relapse time,79,Biospecimen Age,keyword,HIGH,exact_match: time
+stage of repair process,78,Biospecimen Age,keyword,MEDIUM,pattern: .*age.*
+culture days,77,Biospecimen Age,keyword,LOW,pattern: .*day.*
+cancer stage,76,Biospecimen Age,keyword,MEDIUM,pattern: .*age.*
+growth stage,74,Biospecimen Age,keyword,MEDIUM,pattern: .*age.*
+activation agent,74,Biospecimen Age,keyword,MEDIUM,pattern: .*age.*
+experimental status,72,Biospecimen Age,similarity,MEDIUM,Similar to: experimental day (score: 0.800)
+storage,71,Biospecimen Age,keyword,MEDIUM,pattern: .*age.*
+age at initiation,70,Biospecimen Age,keyword,HIGH,exact_match: age
+Degree of differentiation,69,Biospecimen Age,similarity,MEDIUM,Similar to: stage of differentiation (score: 0.857)
+ann arbor stage,66,Biospecimen Age,keyword,MEDIUM,pattern: .*age.*
+sampling.time,66,Biospecimen Age,keyword,LOW,pattern: .*time.*
+harvest time,64,Biospecimen Age,keyword,HIGH,exact_match: time
+overall.survival.time,63,Biospecimen Age,keyword,LOW,pattern: .*time.*
+days post infection,63,Biospecimen Age,keyword,LOW,pattern: .*day.*
+life stage,62,Biospecimen Age,keyword,MEDIUM,pattern: .*age.*
+time in culture,62,Biospecimen Age,keyword,HIGH,exact_match: time
+collection day,62,Biospecimen Age,keyword,HIGH,exact_match: day
+stage,60,Biospecimen Age,keyword,MEDIUM,pattern: .*age.*
+days after stimulation,60,Biospecimen Age,keyword,LOW,pattern: .*day.*
+labeling agent,60,Biospecimen Age,keyword,MEDIUM,pattern: .*age.*
+Case,60,Biospecimen Age,similarity,MEDIUM,Similar to: cage (score: 0.750)
+survival year,58,Biospecimen Age,keyword,HIGH,exact_match: year
+time after infection,57,Biospecimen Age,keyword,HIGH,exact_match: time
+treatment/timepoint,57,Biospecimen Age,keyword,MEDIUM,keyword: timepoint
+experimental set,57,Biospecimen Age,similarity,MEDIUM,Similar to: experimental day (score: 0.812)
+sampling site,57,Biospecimen Age,similarity,MEDIUM,Similar to: sampling time (score: 0.846)
+age and disease,56,Biospecimen Age,keyword,HIGH,exact_match: age
+year of isolation,55,Biospecimen Age,keyword,HIGH,exact_match: year
+Differentiation Method,55,Biospecimen Age,similarity,MEDIUM,Similar to: differentiation time (score: 0.857)
+timepoint_description,54,Biospecimen Age,keyword,MEDIUM,keyword: timepoint
+age at surgery,53,Biospecimen Age,keyword,HIGH,exact_match: age
+sporozoite age,52,Biospecimen Age,keyword,HIGH,exact_match: age
+age/gender,51,Biospecimen Age,keyword,MEDIUM,pattern: .*age.*
+treatment stage,51,Biospecimen Age,keyword,MEDIUM,pattern: .*age.*
+oxygen percentage,51,Biospecimen Age,keyword,MEDIUM,pattern: .*age.*
+age in_yrs,50,Biospecimen Age,keyword,HIGH,exact_match: age
+injury/age,50,Biospecimen Age,keyword,MEDIUM,pattern: .*age.*
+sex/age,49,Biospecimen Age,keyword,MEDIUM,pattern: .*age.*
+experimental day,48,Biospecimen Age,keyword,HIGH,exact_match: day
+day post-infection,48,Biospecimen Age,keyword,HIGH,exact_match: day
+treatment_time,48,Biospecimen Age,keyword,LOW,pattern: .*time.*
+experiment batch,48,Biospecimen Age,similarity,MEDIUM,Similar to: experimental day (score: 0.750)
+age fracture,47,Biospecimen Age,keyword,HIGH,exact_match: age
+isolation,47,Biospecimen Age,similarity,MEDIUM,Similar to: isolation stage (score: 0.750)
+days post-infection,45,Biospecimen Age,keyword,LOW,pattern: .*day.*
+time of sampling,44,Biospecimen Age,keyword,HIGH,exact_match: time
+growth type,44,Biospecimen Age,similarity,MEDIUM,Similar to: growth time (score: 0.818)
+day of collection,43,Biospecimen Age,keyword,HIGH,exact_match: day
+days ill,43,Biospecimen Age,keyword,LOW,pattern: .*day.*
+collection date,43,Biospecimen Age,similarity,MEDIUM,Similar to: collection day (score: 0.897)
+differentiation status,43,Biospecimen Age,similarity,MEDIUM,Similar to: differentiation stage (score: 0.884)
+age/disease timepoint,42,Biospecimen Age,keyword,MEDIUM,keyword: timepoint
+age years,42,Biospecimen Age,keyword,HIGH,exact_match: age
+differentiation time,42,Biospecimen Age,keyword,HIGH,exact_match: time
+days post exposure,42,Biospecimen Age,keyword,LOW,pattern: .*day.*
+maternal age,42,Biospecimen Age,keyword,HIGH,exact_match: age
+time post-vaccination,42,Biospecimen Age,keyword,HIGH,exact_match: time
+days post_infection,42,Biospecimen Age,keyword,LOW,pattern: .*day.*
+state of culture,42,Biospecimen Age,similarity,MEDIUM,Similar to: age of  culture (score: 0.839)
+post-treatment day,41,Biospecimen Age,keyword,HIGH,exact_match: day
+days post-prime,40,Biospecimen Age,keyword,LOW,pattern: .*day.*
+collection,40,Biospecimen Age,similarity,MEDIUM,Similar to: collection day (score: 0.833)
+overall.survival,40,Biospecimen Age,similarity,MEDIUM,Similar to: overall.survival.time (score: 0.865)
+days post challenge,39,Biospecimen Age,keyword,LOW,pattern: .*day.*
+experimental batch,38,Biospecimen Age,similarity,MEDIUM,Similar to: experimental day (score: 0.824)
+timepoint_in_hours,36,Biospecimen Age,keyword,MEDIUM,keyword: timepoint
+day transplantation,36,Biospecimen Age,keyword,HIGH,exact_match: day
+growth time mins,36,Biospecimen Age,keyword,HIGH,exact_match: time
+time post-treatment,36,Biospecimen Age,keyword,HIGH,exact_match: time
+experimental,36,Biospecimen Age,similarity,MEDIUM,Similar to: experimental day (score: 0.857)
+Age of Onset,35,Biospecimen Age,keyword,HIGH,exact_match: age
+culture age,35,Biospecimen Age,keyword,HIGH,exact_match: age
+developmental stages,35,Biospecimen Age,keyword,MEDIUM,keyword: developmental stage
+experimental design,35,Biospecimen Age,similarity,MEDIUM,Similar to: experimental day (score: 0.800)
+Clinical Status,35,Biospecimen Age,similarity,MEDIUM,Similar to: clinical stage (score: 0.828)
+labversion description,35,Biospecimen Age,similarity,MEDIUM,Similar to: age description (score: 0.757)
+time_point,34,Biospecimen Age,keyword,LOW,pattern: .*time.*
+day of isolation,34,Biospecimen Age,keyword,HIGH,exact_match: day
+GOLD stage,34,Biospecimen Age,keyword,MEDIUM,pattern: .*age.*
+Age at time of surgery,34,Biospecimen Age,keyword,HIGH,exact_match: age
+Type of Surgery,34,Biospecimen Age,similarity,MEDIUM,Similar to: year of surgery (score: 0.867)
+time post initiation of treatment,33,Biospecimen Age,keyword,HIGH,exact_match: time
+age at collection,33,Biospecimen Age,keyword,HIGH,exact_match: age
+parasite isolate,33,Biospecimen Age,similarity,MEDIUM,Similar to: parasite stage (score: 0.800)
+time after treatment (and reversal) in hours,32,Biospecimen Age,keyword,HIGH,exact_match: time
+age post-hatch,32,Biospecimen Age,keyword,HIGH,exact_match: age
+age fraction,31,Biospecimen Age,keyword,HIGH,exact_match: age
+gestational stage,31,Biospecimen Age,keyword,MEDIUM,pattern: .*age.*
+age at time of collection,31,Biospecimen Age,keyword,HIGH,exact_match: age
+post-operative day,30,Biospecimen Age,keyword,HIGH,exact_match: day
+growth time,30,Biospecimen Age,keyword,HIGH,exact_match: time
+induction time,30,Biospecimen Age,keyword,HIGH,exact_match: time
+pretreatment time,30,Biospecimen Age,keyword,HIGH,exact_match: time
+Time after induction,30,Biospecimen Age,keyword,HIGH,exact_match: time
+sampling point,30,Biospecimen Age,similarity,MEDIUM,Similar to: sampling timepoint (score: 0.875)
+differentiation state,30,Biospecimen Age,similarity,HIGH,Similar to: differentiation stage (score: 0.952)
+age at examination,29,Biospecimen Age,keyword,HIGH,exact_match: age
+dev_stage at treatment initiation,28,Biospecimen Age,keyword,MEDIUM,pattern: .*age.*
+time infected,28,Biospecimen Age,keyword,HIGH,exact_match: time
+experimental factor,28,Biospecimen Age,similarity,MEDIUM,Similar to: experimental day (score: 0.800)
+culture status,28,Biospecimen Age,similarity,MEDIUM,Similar to: culture stage (score: 0.815)
+interval_death_symptoms_onset_days,27,Biospecimen Age,keyword,LOW,pattern: .*day.*
+intubation_days,27,Biospecimen Age,keyword,LOW,pattern: .*day.*
+time point days,26,Biospecimen Age,keyword,HIGH,exact_match: time
+time designation after sclerosis,26,Biospecimen Age,keyword,HIGH,exact_match: time
+time since sclerosis,26,Biospecimen Age,keyword,HIGH,exact_match: time
+time since transplant,26,Biospecimen Age,keyword,HIGH,exact_match: time
+Passage,26,Biospecimen Age,keyword,MEDIUM,keyword: passage
+culture stage,26,Biospecimen Age,keyword,MEDIUM,pattern: .*age.*
+harvesting,26,Biospecimen Age,similarity,MEDIUM,Similar to: harvesting time (score: 0.800)
+death_time,25,Biospecimen Age,keyword,LOW,pattern: .*time.*
+collection_date,25,Biospecimen Age,similarity,MEDIUM,Similar to: collection day (score: 0.828)
+time post treatment,24,Biospecimen Age,keyword,HIGH,exact_match: time
+days post treatment,24,Biospecimen Age,keyword,LOW,pattern: .*day.*
+sampling time point,24,Biospecimen Age,keyword,HIGH,exact_match: time
+day of collection/passage,24,Biospecimen Age,keyword,HIGH,exact_match: day
+harvest time post treatment,24,Biospecimen Age,keyword,HIGH,exact_match: time
+time post_injury,24,Biospecimen Age,keyword,HIGH,exact_match: time
+differentiation_age,24,Biospecimen Age,keyword,MEDIUM,pattern: .*age.*
+embryonic day,24,Biospecimen Age,keyword,HIGH,exact_match: day
+time post-infection,24,Biospecimen Age,keyword,HIGH,exact_match: time
+os_days,24,Biospecimen Age,keyword,LOW,pattern: .*day.*
+sepsis stage,23,Biospecimen Age,keyword,MEDIUM,pattern: .*age.*
+os months,23,Biospecimen Age,similarity,HIGH,Similar to: os month (score: 0.941)
+fever day,22,Biospecimen Age,keyword,HIGH,exact_match: day
+injection age,20,Biospecimen Age,keyword,HIGH,exact_match: age
+MaternalAge,20,Biospecimen Age,keyword,MEDIUM,pattern: .*age.*
+Cause of Death,20,Biospecimen Age,similarity,MEDIUM,Similar to: age of death (score: 0.846)
+type of death,20,Biospecimen Age,similarity,MEDIUM,Similar to: age of death (score: 0.800)
+isolation stage,19,Biospecimen Age,keyword,MEDIUM,pattern: .*age.*
+timepoint_progressors,19,Biospecimen Age,keyword,MEDIUM,keyword: timepoint
+time point post infection,19,Biospecimen Age,keyword,HIGH,exact_match: time
+time of treatment,19,Biospecimen Age,keyword,HIGH,exact_match: time
+age at onset,19,Biospecimen Age,keyword,HIGH,exact_match: age
+duration of untreated disease in month,19,Biospecimen Age,keyword,HIGH,exact_match: month
+cold ischemia time,19,Biospecimen Age,keyword,HIGH,exact_match: time
+donation time,19,Biospecimen Age,keyword,HIGH,exact_match: time
+time post-exposure,18,Biospecimen Age,keyword,HIGH,exact_match: time
+age_category,18,Biospecimen Age,keyword,MEDIUM,pattern: .*age.*
+age of disease onset percentile,18,Biospecimen Age,keyword,HIGH,exact_match: age
+age of disease onset,18,Biospecimen Age,keyword,HIGH,exact_match: age
+collection buffer,18,Biospecimen Age,similarity,MEDIUM,Similar to: collection time (score: 0.750)
+collection point,18,Biospecimen Age,similarity,MEDIUM,Similar to: collection timepoint (score: 0.889)
+overall survival,18,Biospecimen Age,similarity,MEDIUM,Similar to: overall.survival.time (score: 0.811)
+experimental variable,18,Biospecimen Age,similarity,MEDIUM,Similar to: experimental day (score: 0.757)
+culture batch,18,Biospecimen Age,similarity,MEDIUM,Similar to: culture age (score: 0.750)
+age in months,17,Biospecimen Age,keyword,HIGH,exact_match: age
+day of development,17,Biospecimen Age,keyword,HIGH,exact_match: day
+parasite/gametocyte stage,17,Biospecimen Age,keyword,MEDIUM,pattern: .*age.*
+cold ischemia_time,16,Biospecimen Age,keyword,LOW,pattern: .*time.*
+time of_treatment,16,Biospecimen Age,keyword,HIGH,exact_match: time
+incubation time,16,Biospecimen Age,keyword,HIGH,exact_match: time
+age tier,16,Biospecimen Age,keyword,HIGH,exact_match: age
+developmental age,16,Biospecimen Age,keyword,HIGH,exact_match: age
+treatment agent,16,Biospecimen Age,keyword,MEDIUM,pattern: .*age.*
+day of protocol,16,Biospecimen Age,keyword,HIGH,exact_match: day
+source/differentiation,16,Biospecimen Age,similarity,MEDIUM,Similar to: days of differentiation (score: 0.756)
+differentiation time point,15,Biospecimen Age,keyword,HIGH,exact_match: time
+age of  culture,15,Biospecimen Age,keyword,HIGH,exact_match: age
+phase description,15,Biospecimen Age,similarity,MEDIUM,Similar to: age description (score: 0.875)
+stim,15,Biospecimen Age,similarity,MEDIUM,Similar to: time (score: 0.750)
+experiment name,15,Biospecimen Age,similarity,MEDIUM,Similar to: experimental day (score: 0.774)
+length of culture,15,Biospecimen Age,similarity,MEDIUM,Similar to: age of  culture (score: 0.750)
+block storage,13,Biospecimen Age,keyword,MEDIUM,pattern: .*age.*
+time to relapse,13,Biospecimen Age,keyword,HIGH,exact_match: time
+harvest time point,13,Biospecimen Age,keyword,HIGH,exact_match: time
+Tumor Stage,13,Biospecimen Age,keyword,MEDIUM,pattern: .*age.*
+onset age,13,Biospecimen Age,keyword,HIGH,exact_match: age
+agent concentration,12,Biospecimen Age,keyword,MEDIUM,pattern: .*age.*
+time after virus injection,12,Biospecimen Age,keyword,HIGH,exact_match: time
+days,12,Biospecimen Age,keyword,LOW,pattern: .*day.*
+time post-immunization,12,Biospecimen Age,keyword,HIGH,exact_match: time
+time point in the model of dormancy,12,Biospecimen Age,keyword,HIGH,exact_match: time
+"age, yrs",12,Biospecimen Age,keyword,MEDIUM,pattern: .*age.*
+developmental stage/tumor stage,12,Biospecimen Age,keyword,MEDIUM,keyword: developmental stage
+chronological age,12,Biospecimen Age,keyword,HIGH,exact_match: age
+days under treatment,12,Biospecimen Age,keyword,LOW,pattern: .*day.*
+final age at death,12,Biospecimen Age,keyword,HIGH,exact_match: age
+death day,12,Biospecimen Age,keyword,HIGH,exact_match: day
+long description,12,Biospecimen Age,similarity,MEDIUM,Similar to: age description (score: 0.839)
+Developmental stage,10,Biospecimen Age,keyword,MEDIUM,keyword: developmental stage
+gestational days,10,Biospecimen Age,keyword,LOW,pattern: .*day.*
+age at diagnosis in months,10,Biospecimen Age,keyword,HIGH,exact_match: age
+day post transplant,10,Biospecimen Age,keyword,HIGH,exact_match: day
+age at study start,10,Biospecimen Age,keyword,HIGH,exact_match: age
+time of last follow up in months,10,Biospecimen Age,keyword,HIGH,exact_match: time
+day after intubation,10,Biospecimen Age,keyword,HIGH,exact_match: day
+age at harvest,10,Biospecimen Age,keyword,HIGH,exact_match: age
+maternal state,10,Biospecimen Age,similarity,MEDIUM,Similar to: maternal age (score: 0.846)
+culture medium,10,Biospecimen Age,similarity,MEDIUM,Similar to: culture time (score: 0.769)
+time of day,9,Biospecimen Age,keyword,HIGH,exact_match: day
+age range,9,Biospecimen Age,keyword,HIGH,exact_match: age
+exacerbation day,9,Biospecimen Age,keyword,HIGH,exact_match: day
+process day,9,Biospecimen Age,keyword,HIGH,exact_match: day
+age/time point,9,Biospecimen Age,keyword,MEDIUM,keyword: time point
+differentiation replicate,9,Biospecimen Age,similarity,MEDIUM,Similar to: differentiation time point (score: 0.784)
+date of isolation,9,Biospecimen Age,similarity,HIGH,Similar to: day of isolation (score: 0.909)
+process order,9,Biospecimen Age,similarity,MEDIUM,Similar to: process day (score: 0.750)
+day after transplantation,8,Biospecimen Age,keyword,HIGH,exact_match: day
+age of_diagnosis,8,Biospecimen Age,keyword,HIGH,exact_match: age
+time since first diagnosis,8,Biospecimen Age,keyword,HIGH,exact_match: time
+age of_onset,8,Biospecimen Age,keyword,HIGH,exact_match: age
+life cycle stage,8,Biospecimen Age,keyword,MEDIUM,pattern: .*age.*
+time point of infection,8,Biospecimen Age,keyword,HIGH,exact_match: time
+cartilage pellets,8,Biospecimen Age,keyword,MEDIUM,pattern: .*age.*
+embryo stage,8,Biospecimen Age,keyword,MEDIUM,pattern: .*age.*
+activation,8,Biospecimen Age,similarity,MEDIUM,Similar to: activation agent (score: 0.769)
+phase of growth,8,Biospecimen Age,llm,MEDIUM,Phase of growth could be related to the age or developmental stage of the biospecimen.
+passage/days,7,Biospecimen Age,keyword,MEDIUM,keyword: passage
+"developmental stage, weeks",7,Biospecimen Age,keyword,MEDIUM,keyword: developmental stage
+time of_drug_treatment,7,Biospecimen Age,keyword,HIGH,exact_match: time
+incubation,7,Biospecimen Age,similarity,MEDIUM,Similar to: incubation time (score: 0.800)
+time after exposure,6,Biospecimen Age,keyword,HIGH,exact_match: time
+treatment time-point,6,Biospecimen Age,keyword,LOW,pattern: .*time.*
+collection timepoint,6,Biospecimen Age,keyword,MEDIUM,keyword: timepoint
+developmental stage/age,6,Biospecimen Age,keyword,MEDIUM,keyword: developmental stage
+days from treatment,6,Biospecimen Age,keyword,LOW,pattern: .*day.*
+time after stimulation,6,Biospecimen Age,keyword,HIGH,exact_match: time
+age category,6,Biospecimen Age,keyword,HIGH,exact_match: age
+day post neural induction,6,Biospecimen Age,keyword,HIGH,exact_match: day
+days_since_positive_test,6,Biospecimen Age,keyword,LOW,pattern: .*day.*
+life cycle,6,Biospecimen Age,similarity,MEDIUM,Similar to: life cycle stage (score: 0.769)
+Growth Medium,6,Biospecimen Age,similarity,MEDIUM,Similar to: growth time (score: 0.750)
+days in culture,5,Biospecimen Age,keyword,LOW,pattern: .*day.*
+of passage,5,Biospecimen Age,keyword,MEDIUM,keyword: passage
+sorted,5,Biospecimen Age,similarity,MEDIUM,Similar to: sorter day (score: 0.750)
+days of final differentiation,4,Biospecimen Age,keyword,LOW,pattern: .*day.*
+stage of disease,4,Biospecimen Age,keyword,MEDIUM,pattern: .*age.*
+passages after establishing stable clones,4,Biospecimen Age,keyword,MEDIUM,keyword: passage
+culture time,4,Biospecimen Age,keyword,HIGH,exact_match: time
+treatment/agent,4,Biospecimen Age,keyword,MEDIUM,pattern: .*age.*
+data type description,4,Biospecimen Age,similarity,MEDIUM,Similar to: age description (score: 0.778)
+treatment / timepoint,3,Biospecimen Age,keyword,MEDIUM,keyword: timepoint
+infection time point,3,Biospecimen Age,keyword,HIGH,exact_match: time
+days_post_infection,3,Biospecimen Age,keyword,LOW,pattern: .*day.*
+developmental state,3,Biospecimen Age,similarity,HIGH,Similar to: developmental stage (score: 0.947)
+postnatal day,2,Biospecimen Age,keyword,HIGH,exact_match: day
+stage of differentiation,2,Biospecimen Age,keyword,MEDIUM,pattern: .*age.*
+cause of death,2,Biospecimen Age,similarity,MEDIUM,Similar to: age of death (score: 0.846)
+passage no,1,Biospecimen Age,keyword,MEDIUM,keyword: passage
+incubation partner,1,Biospecimen Age,similarity,MEDIUM,Similar to: incubation time (score: 0.788)
+disease state,31657,Biospecimen Disease Condition,keyword,HIGH,exact_match: disease
+disease,14111,Biospecimen Disease Condition,keyword,HIGH,exact_match: disease
+diagnosis,11647,Biospecimen Disease Condition,keyword,HIGH,exact_match: diagnosis
+condition,10956,Biospecimen Disease Condition,keyword,HIGH,exact_match: condition
+infection,8270,Biospecimen Disease Condition,keyword,HIGH,exact_match: infection
+disease status,4806,Biospecimen Disease Condition,keyword,HIGH,exact_match: disease
+clinical info,3680,Biospecimen Disease Condition,similarity,MEDIUM,Similar to: clinical diagnosis (score: 0.774)
+histology,3618,Biospecimen Disease Condition,similarity,MEDIUM,Similar to: histopathology (score: 0.783)
+tumor type,3082,Biospecimen Disease Condition,keyword,HIGH,exact_match: tumor
+cohort,3031,Biospecimen Disease Condition,llm,MEDIUM,"A cohort is a group of individuals with a shared characteristic, such as a disease condition, which is a common context in biomedical research."
+housing condition,2815,Biospecimen Disease Condition,keyword,HIGH,exact_match: condition
+smoking status,2577,Biospecimen Disease Condition,llm,MEDIUM,"Smoking status is a risk factor for various diseases, and is often considered a disease condition or a characteristic of the biospecimen donor."
+pasi,2192,Biospecimen Disease Condition,llm,MEDIUM,"PASI is an acronym for Psoriasis Area and Severity Index, which is a measure of disease severity in psoriasis patients, indicating a disease condition."
+diseasestate,2186,Biospecimen Disease Condition,keyword,LOW,pattern: .*disease.*
+clinical diagnosis,2111,Biospecimen Disease Condition,keyword,HIGH,exact_match: diagnosis
+pathologic status,1940,Biospecimen Disease Condition,llm,HIGH,Pathologic status is a characteristic of the disease condition of the donor or sample.
+histologic diagnosis,1936,Biospecimen Disease Condition,keyword,HIGH,exact_match: diagnosis
+grade,1888,Biospecimen Disease Condition,llm,HIGH,Grade is often used to describe the severity or stage of a disease condition.
+tumor grade,1602,Biospecimen Disease Condition,keyword,HIGH,exact_match: tumor
+surgical status,1417,Biospecimen Disease Condition,llm,HIGH,Surgical status is a condition of the donor
+infection status,1402,Biospecimen Disease Condition,keyword,HIGH,exact_match: infection
+tumor location,1401,Biospecimen Disease Condition,keyword,HIGH,exact_match: tumor
+infection states,1389,Biospecimen Disease Condition,keyword,HIGH,exact_match: infection
+outcome,1324,Biospecimen Disease Condition,llm,HIGH,Outcome is a condition of the donor
+disease group,1144,Biospecimen Disease Condition,keyword,HIGH,exact_match: disease
+final diagnosis,1067,Biospecimen Disease Condition,keyword,HIGH,exact_match: diagnosis
+status,1055,Biospecimen Disease Condition,llm,HIGH,Status often refers to the disease condition or health status of the donor or sample.
+primary site,1010,Biospecimen Disease Condition,similarity,MEDIUM,Similar to: primary tumor site (score: 0.800)
+subtype,994,Biospecimen Disease Condition,llm,HIGH,"Subtype is a characteristic of a disease or condition, which can be considered a type of biospecimen disease condition."
+culture result,894,Biospecimen Disease Condition,llm,HIGH,Culture result is a diagnostic outcome that indicates the disease condition of the donor or sample.
+site_onset,876,Biospecimen Disease Condition,llm,HIGH,"Site onset refers to the location where a disease or condition first appears, which is related to the disease condition of the donor or sample."
+metastasis,840,Biospecimen Disease Condition,llm,HIGH,"Metastasis is a characteristic of cancer, which is a disease condition of the donor or sample."
+cancer status,837,Biospecimen Disease Condition,keyword,HIGH,exact_match: cancer
+severity score,811,Biospecimen Disease Condition,llm,HIGH,Severity score is a measure of the disease condition
+hours post infection,779,Biospecimen Disease Condition,keyword,HIGH,exact_match: infection
+disease severity,774,Biospecimen Disease Condition,keyword,HIGH,exact_match: disease
+stress,744,Biospecimen Disease Condition,llm,MEDIUM,Stress could be a factor contributing to a disease condition
+infection protocol,740,Biospecimen Disease Condition,keyword,HIGH,exact_match: infection
+working_diagnosis,678,Biospecimen Disease Condition,keyword,LOW,pattern: .*diagnosis.*
+first_diagnosis,678,Biospecimen Disease Condition,keyword,LOW,pattern: .*diagnosis.*
+smoker,670,Biospecimen Disease Condition,llm,HIGH,Smoker is a disease condition or risk factor associated with certain health outcomes
+tumor grading,658,Biospecimen Disease Condition,keyword,HIGH,exact_match: tumor
+severity,619,Biospecimen Disease Condition,llm,HIGH,Describes the extent or degree of a disease condition
+pathology,605,Biospecimen Disease Condition,keyword,MEDIUM,keyword: pathology
+brain region,595,Biospecimen Disease Condition,similarity,MEDIUM,Similar to: brain tumor region (score: 0.800)
+illness,574,Biospecimen Disease Condition,llm,HIGH,Illness is a synonym for disease condition
+Illness,546,Biospecimen Disease Condition,llm,HIGH,Illness is a synonym for disease condition
+disease duration,527,Biospecimen Disease Condition,keyword,HIGH,exact_match: disease
+disease_category,507,Biospecimen Disease Condition,keyword,LOW,pattern: .*disease.*
+institutional tumor diagnosis,500,Biospecimen Disease Condition,keyword,HIGH,exact_match: diagnosis
+disease location,500,Biospecimen Disease Condition,keyword,HIGH,exact_match: disease
+disease staging,500,Biospecimen Disease Condition,keyword,HIGH,exact_match: disease
+cancer site,500,Biospecimen Disease Condition,keyword,HIGH,exact_match: cancer
+viral_positivity,500,Biospecimen Disease Condition,llm,HIGH,"Viral positivity indicates the presence of a virus, which is a disease condition."
+neoplastic,500,Biospecimen Disease Condition,llm,HIGH,"Neoplastic refers to the presence of abnormal or cancerous cells, which is a disease condition."
+consortium lung phenotype,500,Biospecimen Disease Condition,llm,HIGH,"This label seems to be related to the disease condition or phenotype of the biospecimen, specifically lung-related."
+malaria_transmission,500,Biospecimen Disease Condition,llm,HIGH,This label seems to be related to the disease condition or transmission of malaria.
+consortium lung phenotype surrogate variable,500,Biospecimen Disease Condition,llm,MEDIUM,"This label seems to be related to the disease condition or phenotype of the biospecimen, but it is not a clear fit into this category."
+meconium ileus status,500,Biospecimen Disease Condition,llm,HIGH,"This label is likely related to the disease condition of the biospecimen, as meconium ileus is a medical condition."
+persistent ps aer status,500,Biospecimen Disease Condition,llm,HIGH,"This label is likely related to the disease condition of the biospecimen, as it seems to be a medical condition or diagnosis."
+malaria_status,500,Biospecimen Disease Condition,llm,HIGH,Describes the disease condition of the donor or sample
+tumor,494,Biospecimen Disease Condition,keyword,HIGH,exact_match: tumor
+who category,493,Biospecimen Disease Condition,similarity,MEDIUM,Similar to: tumor category (score: 0.769)
+neuropathological_diagnosis,492,Biospecimen Disease Condition,keyword,LOW,pattern: .*diagnosis.*
+clinical_diagnosis,492,Biospecimen Disease Condition,keyword,LOW,pattern: .*diagnosis.*
+disease_duration_years,492,Biospecimen Disease Condition,keyword,LOW,pattern: .*disease.*
+dementia,492,Biospecimen Disease Condition,llm,HIGH,Specific disease condition
+diagnostic_mean,484,Biospecimen Disease Condition,llm,MEDIUM,Could be related to disease condition or diagnosis
+culture condition,472,Biospecimen Disease Condition,keyword,HIGH,exact_match: condition
+death,460,Biospecimen Disease Condition,llm,MEDIUM,Could be related to disease condition or outcome
+survival_status,450,Biospecimen Disease Condition,llm,HIGH,"Survival status is a characteristic of the disease condition, describing the outcome of the patient."
+progression,448,Biospecimen Disease Condition,llm,HIGH,"Progression is a characteristic of the disease condition, describing the advancement of the disease."
+site of infection,447,Biospecimen Disease Condition,keyword,HIGH,exact_match: infection
+cancer type,439,Biospecimen Disease Condition,keyword,HIGH,exact_match: cancer
+infection code,438,Biospecimen Disease Condition,keyword,HIGH,exact_match: infection
+culture conditions,432,Biospecimen Disease Condition,keyword,LOW,pattern: .*condition.*
+disease_status,426,Biospecimen Disease Condition,keyword,LOW,pattern: .*disease.*
+parasitemia,419,Biospecimen Disease Condition,llm,HIGH,"Parasitemia refers to the presence of parasites in the blood, which is a disease condition."
+reference diagnosis,415,Biospecimen Disease Condition,keyword,HIGH,exact_match: diagnosis
+condition description,405,Biospecimen Disease Condition,keyword,HIGH,exact_match: condition
+adjusted disease severity index,399,Biospecimen Disease Condition,keyword,HIGH,exact_match: disease
+initial ich volume,399,Biospecimen Disease Condition,similarity,MEDIUM,Similar to: initial tumor volume (score: 0.789)
+tst skin test,379,Biospecimen Disease Condition,llm,MEDIUM,"Tst skin test is a diagnostic test, which may be related to a disease condition."
+diagnosis date,374,Biospecimen Disease Condition,keyword,HIGH,exact_match: diagnosis
+joint problems,374,Biospecimen Disease Condition,llm,HIGH,"This label refers to a specific health issue, which aligns with the definition of Biospecimen Disease Condition."
+family history,374,Biospecimen Disease Condition,llm,HIGH,"Family history is often used to understand genetic predispositions to diseases, which is related to the disease condition of the donor."
+symptoms onset date,374,Biospecimen Disease Condition,llm,HIGH,"This label refers to the timing of disease symptoms, which is related to the disease condition of the donor."
+who grade,367,Biospecimen Disease Condition,similarity,MEDIUM,Similar to: tumor who grade (score: 0.750)
+growth condition,359,Biospecimen Disease Condition,keyword,HIGH,exact_match: condition
+additional conditions,340,Biospecimen Disease Condition,keyword,LOW,pattern: .*condition.*
+disease symptom,339,Biospecimen Disease Condition,keyword,HIGH,exact_match: disease
+with or without clonal heterogeneity,332,Biospecimen Disease Condition,llm,MEDIUM,Describes a characteristic of the biospecimen related to disease or condition
+international prognostic index,332,Biospecimen Disease Condition,llm,HIGH,A specific index used to predict disease outcome
+dead or alive at the end of follow-up,332,Biospecimen Disease Condition,llm,HIGH,Describes the outcome of the disease or condition
+total number of genomic aberrations,332,Biospecimen Disease Condition,llm,HIGH,Describes a characteristic of the biospecimen related to disease or condition
+seizure,328,Biospecimen Disease Condition,llm,HIGH,"Seizure is a medical condition, so it fits well into the Biospecimen Disease Condition category."
+other diseases,325,Biospecimen Disease Condition,keyword,LOW,pattern: .*disease.*
+disease type,322,Biospecimen Disease Condition,keyword,HIGH,exact_match: disease
+asthma,314,Biospecimen Disease Condition,llm,HIGH,"Asthma is a medical condition, so it fits well into the Biospecimen Disease Condition category."
+smear_result,313,Biospecimen Disease Condition,llm,HIGH,"The term 'smear_result' suggests a diagnostic or analytical outcome, which is often related to a disease condition."
+disease subtype,308,Biospecimen Disease Condition,keyword,HIGH,exact_match: disease
+DiseaseState,300,Biospecimen Disease Condition,keyword,LOW,pattern: .*disease.*
+anti-centromere,295,Biospecimen Disease Condition,llm,HIGH,"The term 'anti-centromere' suggests a specific type of antibody or disease marker, which is often related to a disease condition."
+diagnosis.after.path.re.review,286,Biospecimen Disease Condition,keyword,LOW,pattern: .*diagnosis.*
+diagnosis.of.record,286,Biospecimen Disease Condition,keyword,LOW,pattern: .*diagnosis.*
+recurrence,286,Biospecimen Disease Condition,llm,HIGH,"Recurrence is a term often used to describe the return of a disease, which fits well within the disease condition category."
+os.mos,286,Biospecimen Disease Condition,llm,HIGH,"OS.MOS likely stands for overall survival months, which is a measure of disease outcome, fitting the disease condition category."
+surgical.outcome,286,Biospecimen Disease Condition,llm,HIGH,"Surgical outcome is a result of a medical intervention, often related to disease treatment, which aligns with the disease condition category."
+psychiatric disorder,285,Biospecimen Disease Condition,llm,HIGH,"Psychiatric disorder is a type of disease condition, making it a clear fit for this category."
+gastrointestinal disorder,285,Biospecimen Disease Condition,llm,HIGH,"Gastrointestinal disorder is a specific type of disease condition, fitting well within this category."
+cerebral palsy,285,Biospecimen Disease Condition,llm,HIGH,"Cerebral palsy is a medical condition, making it a clear fit for the disease condition category."
+mutational subclass,285,Biospecimen Disease Condition,llm,HIGH,"Mutational subclass refers to a specific genetic mutation related to a disease, which is a characteristic of the disease condition."
+birth defects,285,Biospecimen Disease Condition,llm,HIGH,Birth defects are a type of disease condition
+neurological disorder,285,Biospecimen Disease Condition,llm,HIGH,Neurological disorder is a type of disease condition
+developmental/speech disorder,285,Biospecimen Disease Condition,llm,HIGH,Developmental/speech disorder is a type of disease condition
+lung disease,283,Biospecimen Disease Condition,keyword,HIGH,exact_match: disease
+diabetes,283,Biospecimen Disease Condition,llm,HIGH,Diabetes is a disease condition
+chronic diseases,282,Biospecimen Disease Condition,keyword,LOW,pattern: .*disease.*
+molecular.diagnosis,280,Biospecimen Disease Condition,keyword,LOW,pattern: .*diagnosis.*
+primary.tumor,271,Biospecimen Disease Condition,keyword,LOW,pattern: .*tumor.*
+tumor_name,270,Biospecimen Disease Condition,keyword,LOW,pattern: .*tumor.*
+percent_weight_loss,268,Biospecimen Disease Condition,llm,HIGH,Weight loss is often a symptom or indicator of a disease condition
+radiation administered prior to tumor resection,267,Biospecimen Disease Condition,keyword,HIGH,exact_match: tumor
+histological diagnosis,253,Biospecimen Disease Condition,keyword,HIGH,exact_match: diagnosis
+number of malaria infections,250,Biospecimen Disease Condition,similarity,MEDIUM,Similar to: malaria infection (score: 0.756)
+molecular classification,248,Biospecimen Disease Condition,llm,HIGH,Refers to the molecular characteristics of a disease or condition
+recurrent_status,245,Biospecimen Disease Condition,llm,HIGH,"Refers to the status of a disease or condition, specifically whether it is recurrent"
+tumor localization,243,Biospecimen Disease Condition,keyword,HIGH,exact_match: tumor
+broad diagnosis,226,Biospecimen Disease Condition,keyword,HIGH,exact_match: diagnosis
+behavior at diagnosis,226,Biospecimen Disease Condition,keyword,HIGH,exact_match: diagnosis
+tumor category,226,Biospecimen Disease Condition,keyword,HIGH,exact_match: tumor
+dysplasia now,226,Biospecimen Disease Condition,llm,HIGH,Dysplasia is a disease condition
+disease activity,221,Biospecimen Disease Condition,keyword,HIGH,exact_match: disease
+section,219,Biospecimen Disease Condition,similarity,MEDIUM,Similar to: infection (score: 0.750)
+health state,213,Biospecimen Disease Condition,llm,HIGH,Health state is a condition of the donor
+cigarette smoker,212,Biospecimen Disease Condition,llm,HIGH,Cigarette smoker is a condition of the donor
+medical.history,212,Biospecimen Disease Condition,llm,HIGH,Medical history is a condition of the donor
+stimulation condition,207,Biospecimen Disease Condition,keyword,HIGH,exact_match: condition
+primary diagnosis,204,Biospecimen Disease Condition,keyword,HIGH,exact_match: diagnosis
+light condition,203,Biospecimen Disease Condition,keyword,HIGH,exact_match: condition
+diagnosis total,202,Biospecimen Disease Condition,keyword,HIGH,exact_match: diagnosis
+diagnosis hep flex,202,Biospecimen Disease Condition,keyword,HIGH,exact_match: diagnosis
+diagnosis rectum,202,Biospecimen Disease Condition,keyword,HIGH,exact_match: diagnosis
+inflammation_status,202,Biospecimen Disease Condition,llm,HIGH,Refers to the condition or status of inflammation in the biospecimen
+pregnancy status,201,Biospecimen Disease Condition,llm,HIGH,Pregnancy is a specific condition or status of the donor.
+lung pathology,200,Biospecimen Disease Condition,keyword,MEDIUM,keyword: pathology
+tumor_entity_subtype,200,Biospecimen Disease Condition,keyword,LOW,pattern: .*tumor.*
+cirrhosis present,195,Biospecimen Disease Condition,llm,HIGH,Cirrhosis is a disease condition
+chronic hypertension,194,Biospecimen Disease Condition,llm,HIGH,Chronic hypertension is a disease condition
+survival after surgery,192,Biospecimen Disease Condition,llm,HIGH,Survival after surgery is a disease condition outcome
+infection_status,189,Biospecimen Disease Condition,similarity,HIGH,Similar to: infection status (score: 0.938)
+death with metastasis,189,Biospecimen Disease Condition,llm,HIGH,"This label describes a disease condition, specifically the outcome of metastasis."
+outcome related,188,Biospecimen Disease Condition,llm,HIGH,This label is related to the outcome of a disease condition.
+infected/uninfected,186,Biospecimen Disease Condition,llm,HIGH,"This label describes a disease condition, specifically the presence or absence of an infection."
+neoplasia type,181,Biospecimen Disease Condition,llm,HIGH,Directly related to disease condition
+Histopathological diagnostic,180,Biospecimen Disease Condition,similarity,MEDIUM,Similar to: histological diagnosis (score: 0.840)
+symptom severity,180,Biospecimen Disease Condition,llm,HIGH,Directly related to disease condition
+viral shedding,180,Biospecimen Disease Condition,llm,HIGH,Viral shedding is a condition related to the presence of a virus in a biological sample.
+tst result,179,Biospecimen Disease Condition,llm,HIGH,"TST result likely refers to a Tuberculosis Skin Test result, indicating a disease condition."
+symptomatic,178,Biospecimen Disease Condition,llm,HIGH,"Symptomatic indicates the presence of symptoms, which is a characteristic of a disease condition."
+diagnosis colonic,172,Biospecimen Disease Condition,keyword,HIGH,exact_match: diagnosis
+diagnosis details,172,Biospecimen Disease Condition,keyword,HIGH,exact_match: diagnosis
+diagnosis anal perianal,172,Biospecimen Disease Condition,keyword,HIGH,exact_match: diagnosis
+diagnosis oral,172,Biospecimen Disease Condition,keyword,HIGH,exact_match: diagnosis
+diagnosis rectal,172,Biospecimen Disease Condition,keyword,HIGH,exact_match: diagnosis
+hours post-invasion,172,Biospecimen Disease Condition,similarity,MEDIUM,Similar to: hours post infection (score: 0.769)
+smoking,171,Biospecimen Disease Condition,llm,HIGH,"Smoking is a condition or status of the donor, which is related to their health or disease state."
+disease_state,169,Biospecimen Disease Condition,keyword,LOW,pattern: .*disease.*
+hypertension,165,Biospecimen Disease Condition,llm,HIGH,"Hypertension is a disease condition of the donor, which is a characteristic of the biospecimen."
+hours post invasion,162,Biospecimen Disease Condition,similarity,MEDIUM,Similar to: hours post infection (score: 0.821)
+mechanical ventilation,162,Biospecimen Disease Condition,similarity,MEDIUM,Similar to: mechanical condition (score: 0.810)
+tumor full_name,160,Biospecimen Disease Condition,keyword,HIGH,exact_match: tumor
+disease_group_detailed,158,Biospecimen Disease Condition,keyword,LOW,pattern: .*disease.*
+disease_group,158,Biospecimen Disease Condition,keyword,LOW,pattern: .*disease.*
+cag_repeat,156,Biospecimen Disease Condition,llm,HIGH,"Cag repeat is a genetic marker associated with certain diseases, such as Huntington's disease."
+conversion,156,Biospecimen Disease Condition,llm,MEDIUM,"Conversion could refer to a change in disease status or progression, but it's not entirely clear without more context."
+prognosis,156,Biospecimen Disease Condition,llm,HIGH,"Prognosis refers to the predicted outcome or progression of a disease, which is a characteristic of the biospecimen's disease condition."
+parasitemia category,155,Biospecimen Disease Condition,llm,HIGH,Parasitemia is a disease condition related to the presence of parasites in the blood.
+pathology_note,152,Biospecimen Disease Condition,keyword,MEDIUM,keyword: pathology
+survival status,152,Biospecimen Disease Condition,llm,HIGH,Survival status is related to the disease condition of the donor or sample.
+antibody description,151,Biospecimen Disease Condition,similarity,MEDIUM,Similar to: condition description (score: 0.780)
+parasite density,150,Biospecimen Disease Condition,llm,HIGH,Parasite density is a measure of disease condition
+malign,148,Biospecimen Disease Condition,llm,HIGH,Malign is a characteristic of disease condition
+protect_outcome,144,Biospecimen Disease Condition,llm,MEDIUM,"Protect outcome is related to disease condition, but the term is not very specific"
+distance from the tumor center,140,Biospecimen Disease Condition,keyword,HIGH,exact_match: tumor
+index_case_disease_site,140,Biospecimen Disease Condition,keyword,LOW,pattern: .*disease.*
+isolate_sensitivity,140,Biospecimen Disease Condition,llm,MEDIUM,The term 'isolate_sensitivity' likely refers to the sensitivity of an isolated microorganism to certain treatments or conditions.
+exposure_latent,140,Biospecimen Disease Condition,llm,MEDIUM,The term 'exposure_latent' likely refers to the latent period of exposure to a disease or condition.
+pasi score,138,Biospecimen Disease Condition,llm,HIGH,"The term 'pasi score' likely refers to the Psoriasis Area and Severity Index, a measure of disease severity."
+tumor subgroup,137,Biospecimen Disease Condition,keyword,HIGH,exact_match: tumor
+obesity,137,Biospecimen Disease Condition,llm,HIGH,The term 'obesity' likely refers to a disease condition or status.
+inflammation status,135,Biospecimen Disease Condition,similarity,MEDIUM,Similar to: infection status (score: 0.800)
+stress exposure,135,Biospecimen Disease Condition,llm,MEDIUM,Stress exposure can be a condition or factor affecting the biospecimen.
+years since diagnosis,134,Biospecimen Disease Condition,keyword,HIGH,exact_match: diagnosis
+histopathology,132,Biospecimen Disease Condition,keyword,MEDIUM,keyword: pathology
+injection_type,132,Biospecimen Disease Condition,similarity,MEDIUM,Similar to: infection type (score: 0.857)
+skin disease,128,Biospecimen Disease Condition,keyword,HIGH,exact_match: disease
+genetic class,126,Biospecimen Disease Condition,llm,MEDIUM,Genetic class could refer to a disease condition or genetic characteristic of the biospecimen.
+symptom,125,Biospecimen Disease Condition,llm,HIGH,Symptoms are manifestations of a disease condition
+mutation_carrier_status,124,Biospecimen Disease Condition,llm,HIGH,Mutation carrier status is related to disease condition
+cag_repeats,124,Biospecimen Disease Condition,llm,HIGH,CAG repeats are associated with disease conditions such as Huntington's disease
+phase,123,Biospecimen Disease Condition,llm,MEDIUM,Phase could refer to the stage of a disease
+Diagnosis,122,Biospecimen Disease Condition,keyword,HIGH,exact_match: diagnosis
+tumor subtype,122,Biospecimen Disease Condition,keyword,HIGH,exact_match: tumor
+das score,120,Biospecimen Disease Condition,llm,MEDIUM,DAS score is a measure of disease activity
+infectivity,120,Biospecimen Disease Condition,llm,HIGH,"Infectivity is a measure of the ability of a pathogen to infect a host, which is a disease condition."
+total cholesterol,109,Biospecimen Disease Condition,llm,MEDIUM,"This label could be related to a disease condition or a biomarker, but it is not a clear fit into any category."
+fibrosis degree,109,Biospecimen Disease Condition,llm,HIGH,"This label is related to the extent or severity of fibrosis, which is a disease condition."
+clinical condition,108,Biospecimen Disease Condition,keyword,HIGH,exact_match: condition
+Histology,107,Biospecimen Disease Condition,similarity,MEDIUM,Similar to: histopathology (score: 0.783)
+interim pet response,106,Biospecimen Disease Condition,llm,HIGH,"This label is related to the response to a treatment or intervention, which is a disease condition."
+infection group,105,Biospecimen Disease Condition,keyword,HIGH,exact_match: infection
+primary/recurrent,105,Biospecimen Disease Condition,llm,HIGH,"This label is related to the stage or type of disease, which is a disease condition."
+pasi_total,105,Biospecimen Disease Condition,llm,HIGH,PASI (Psoriasis Area and Severity Index) is a measure of disease severity
+worm infection,104,Biospecimen Disease Condition,keyword,HIGH,exact_match: infection
+Outcome,104,Biospecimen Disease Condition,llm,HIGH,Refers to the result or consequence of a disease or treatment
+scar,104,Biospecimen Disease Condition,llm,HIGH,A characteristic of a disease or injury
+lesion,103,Biospecimen Disease Condition,llm,HIGH,A characteristic of a disease or injury
+lymphoma type,102,Biospecimen Disease Condition,llm,HIGH,"Lymphoma is a type of cancer, and the label refers to the specific type of lymphoma, which is a disease condition."
+Tumor size,101,Biospecimen Disease Condition,keyword,HIGH,exact_match: tumor
+remission,101,Biospecimen Disease Condition,llm,HIGH,"Remission is a state of a disease, and the label refers to the disease condition of the biospecimen."
+swollen joints,101,Biospecimen Disease Condition,llm,HIGH,"Swollen joints is a symptom of a disease, and the label refers to the disease condition of the biospecimen."
+pain,101,Biospecimen Disease Condition,llm,HIGH,Pain is a symptom or condition often associated with a disease or disorder.
+tender joints,101,Biospecimen Disease Condition,llm,HIGH,"Tender joints are a symptom often associated with conditions like arthritis, indicating a disease or disorder."
+viral load,100,Biospecimen Disease Condition,llm,HIGH,"Viral load is a measure of the amount of virus present in the body, often used to monitor disease progression or response to treatment."
+current status,100,Biospecimen Disease Condition,llm,MEDIUM,"Current status could refer to the current state of a disease or condition, but it is somewhat ambiguous without more context."
+localization,99,Biospecimen Disease Condition,similarity,MEDIUM,Similar to: tumor localization (score: 0.800)
+disease_extension,97,Biospecimen Disease Condition,keyword,LOW,pattern: .*disease.*
+tumor status,97,Biospecimen Disease Condition,keyword,HIGH,exact_match: tumor
+isolate type,97,Biospecimen Disease Condition,similarity,MEDIUM,Similar to: disease type (score: 0.750)
+Smoking status,97,Biospecimen Disease Condition,llm,HIGH,Smoking status is a condition that can affect the biospecimen
+endoscopic_activity,97,Biospecimen Disease Condition,llm,HIGH,Endoscopic activity is a measure of disease activity
+culture_conditions,96,Biospecimen Disease Condition,keyword,LOW,pattern: .*condition.*
+primary disease,96,Biospecimen Disease Condition,keyword,HIGH,exact_match: disease
+incubation conditions,96,Biospecimen Disease Condition,keyword,LOW,pattern: .*condition.*
+neuropathological diagnosis,94,Biospecimen Disease Condition,keyword,HIGH,exact_match: diagnosis
+mitotic index,94,Biospecimen Disease Condition,llm,HIGH,"Mitotic index is a measure of the number of cells in a sample that are actively dividing, which can be an indicator of disease condition."
+Condition,93,Biospecimen Disease Condition,keyword,HIGH,exact_match: condition
+tumor.in.left.right.lobe,92,Biospecimen Disease Condition,keyword,LOW,pattern: .*tumor.*
+location of onset,92,Biospecimen Disease Condition,similarity,MEDIUM,Similar to: location of tumors (score: 0.800)
+survival characteristics,92,Biospecimen Disease Condition,llm,HIGH,"Survival characteristics refer to the ability of cells or tissues to survive under certain conditions, which can be an indicator of disease condition."
+vascular.invasion,92,Biospecimen Disease Condition,llm,HIGH,"Vascular invasion refers to the ability of cancer cells to invade blood vessels, which is a characteristic of disease condition."
+mutational.status,92,Biospecimen Disease Condition,llm,HIGH,"Mutational status refers to the presence or absence of specific genetic mutations, which can be an indicator of disease condition."
+multifocal,92,Biospecimen Disease Condition,llm,HIGH,Multifocal refers to a disease condition affecting multiple sites or areas.
+smoker or non smoker,92,Biospecimen Disease Condition,llm,HIGH,"Smoking status is a risk factor for certain diseases, so it is related to the disease condition of the donor."
+exposed to,92,Biospecimen Disease Condition,llm,HIGH,"Exposure to certain substances or conditions can contribute to disease development, making it relevant to the disease condition."
+familial anamnesis,92,Biospecimen Disease Condition,llm,HIGH,"Familial anamnesis refers to the medical history of a family, which can be relevant to understanding genetic predispositions to diseases."
+tumor region,91,Biospecimen Disease Condition,keyword,HIGH,exact_match: tumor
+onset,90,Biospecimen Disease Condition,llm,HIGH,"Onset refers to the beginning or start of a disease, which is a key aspect of the disease condition."
+disease_duration,89,Biospecimen Disease Condition,keyword,LOW,pattern: .*disease.*
+Status,89,Biospecimen Disease Condition,llm,MEDIUM,"Status can refer to the current state of a disease or condition, making it somewhat related to the disease condition, but it is a bit more general."
+progression_free_survival,88,Biospecimen Disease Condition,llm,HIGH,"Progression-free survival is a measure of the time during and after treatment of a disease that a patient lives with the disease but it does not get any worse, making it relevant to the disease condition."
+hour post infection,87,Biospecimen Disease Condition,keyword,HIGH,exact_match: infection
+disease category,87,Biospecimen Disease Condition,keyword,HIGH,exact_match: disease
+tumor type/grade,84,Biospecimen Disease Condition,keyword,HIGH,exact_match: tumor
+dissection,84,Biospecimen Disease Condition,similarity,MEDIUM,Similar to: disease location (score: 0.769)
+virus infection,83,Biospecimen Disease Condition,keyword,HIGH,exact_match: infection
+exposure condition,80,Biospecimen Disease Condition,keyword,HIGH,exact_match: condition
+primary recurrent,79,Biospecimen Disease Condition,llm,HIGH,Primary recurrent likely refers to the disease status or condition of the biospecimen donor.
+bacterial infection,76,Biospecimen Disease Condition,keyword,HIGH,exact_match: infection
+smoking_status,76,Biospecimen Disease Condition,llm,HIGH,Smoking status is a condition or characteristic of the donor that can affect the biospecimen.
+infection state,75,Biospecimen Disease Condition,keyword,HIGH,exact_match: infection
+infection duration,75,Biospecimen Disease Condition,keyword,HIGH,exact_match: infection
+parental tumor subtype,74,Biospecimen Disease Condition,keyword,HIGH,exact_match: tumor
+clinical outcome,74,Biospecimen Disease Condition,llm,HIGH,Clinical outcome is related to the disease condition or status of the biospecimen donor.
+preliminary diagnosis,73,Biospecimen Disease Condition,keyword,HIGH,exact_match: diagnosis
+injection site,73,Biospecimen Disease Condition,similarity,MEDIUM,Similar to: infection state (score: 0.828)
+clinical indication,72,Biospecimen Disease Condition,similarity,MEDIUM,Similar to: clinical condition (score: 0.865)
+metastasis site,72,Biospecimen Disease Condition,llm,HIGH,"Metastasis site is related to the disease condition or status of the biospecimen donor, specifically the location of cancer metastasis."
+primary tumor site,71,Biospecimen Disease Condition,keyword,HIGH,exact_match: tumor
+glioma,70,Biospecimen Disease Condition,llm,HIGH,Glioma is a type of disease or medical condition
+subcutaneous neurofibromas,70,Biospecimen Disease Condition,llm,HIGH,Subcutaneous neurofibromas is a type of disease or medical condition
+plexiform neurofibromas,70,Biospecimen Disease Condition,llm,HIGH,Plexiform neurofibromas is a type of disease or medical condition
+cutaneous neurofibromas,70,Biospecimen Disease Condition,llm,HIGH,Cutaneous neurofibromas is a type of disease or medical condition
+facial dysmorphism,70,Biospecimen Disease Condition,llm,HIGH,Facial dysmorphism is a disease condition or symptom
+scoliosis,70,Biospecimen Disease Condition,llm,HIGH,Scoliosis is a disease condition or symptom
+skin-fold freckling,70,Biospecimen Disease Condition,llm,HIGH,Skin-fold freckling is a disease condition or symptom
+Lymph node involvement,69,Biospecimen Disease Condition,llm,HIGH,Lymph node involvement is a disease condition or symptom
+primary_recurrent,68,Biospecimen Disease Condition,llm,HIGH,"This label suggests a disease condition or status, which fits well with the Biospecimen Disease Condition category."
+clinically_aggressive,66,Biospecimen Disease Condition,llm,HIGH,"This label suggests a disease condition or status, which fits well with the Biospecimen Disease Condition category."
+malaria infection,65,Biospecimen Disease Condition,keyword,HIGH,exact_match: infection
+tumor histology,65,Biospecimen Disease Condition,keyword,HIGH,exact_match: tumor
+metastatic tumor site,65,Biospecimen Disease Condition,keyword,HIGH,exact_match: tumor
+lesion_disease_factor,64,Biospecimen Disease Condition,keyword,LOW,pattern: .*disease.*
+total skin score,64,Biospecimen Disease Condition,llm,HIGH,Refers to a measure of disease severity or progression
+lesion_label,64,Biospecimen Disease Condition,llm,HIGH,Refers to a specific type of disease or abnormality
+presence_of_parasites_lesion,64,Biospecimen Disease Condition,llm,HIGH,Refers to the presence of a specific disease or abnormality
+infiltration,64,Biospecimen Disease Condition,llm,HIGH,Infiltration is a term used to describe the invasion of a tissue or organ by a disease or a foreign substance. It is a disease condition.
+severity_score,64,Biospecimen Disease Condition,llm,HIGH,Severity score is a term used to describe the severity of a disease or condition. It is a disease condition.
+lesion_size,64,Biospecimen Disease Condition,llm,HIGH,Lesion size is a term used to describe the size of a lesion or abnormal growth. It is a disease condition.
+bleeding,62,Biospecimen Disease Condition,llm,MEDIUM,Bleeding could be a symptom or a condition related to a disease.
+stool frequency,62,Biospecimen Disease Condition,llm,MEDIUM,Stool frequency could be a symptom or a condition related to a disease.
+infection type exposure,61,Biospecimen Disease Condition,keyword,HIGH,exact_match: infection
+clinical presentation,61,Biospecimen Disease Condition,llm,HIGH,Clinical presentation is a term used to describe the symptoms and signs of a disease.
+primary tumor,60,Biospecimen Disease Condition,keyword,HIGH,exact_match: tumor
+duration of infection,60,Biospecimen Disease Condition,keyword,HIGH,exact_match: infection
+alive,60,Biospecimen Disease Condition,llm,MEDIUM,The term 'alive' can be related to the disease condition or status of a biospecimen.
+prodromal status,60,Biospecimen Disease Condition,llm,HIGH,"This label refers to the status of a disease before its full onset, which is a characteristic of the biospecimen donor's disease condition."
+experimental condition,58,Biospecimen Disease Condition,keyword,HIGH,exact_match: condition
+subtypes,58,Biospecimen Disease Condition,llm,HIGH,"This label refers to specific subcategories of a disease or condition, which is a characteristic of the biospecimen donor's disease condition."
+local skin score,58,Biospecimen Disease Condition,llm,HIGH,"This label refers to a measure of the severity of a skin condition, which is a characteristic of the biospecimen donor's disease condition."
+location of lesion,58,Biospecimen Disease Condition,llm,HIGH,"This label refers to the location of a disease-related lesion, which is a characteristic of the biospecimen donor's disease condition."
+gene deletion status,58,Biospecimen Disease Condition,llm,HIGH,Gene deletion status is a characteristic of the biospecimen's disease condition or genetic modification.
+lesion status,57,Biospecimen Disease Condition,similarity,MEDIUM,Similar to: infection status (score: 0.759)
+mutation class,57,Biospecimen Disease Condition,llm,HIGH,Mutation class is a characteristic of the biospecimen's disease condition or genetic modification.
+malignant tumor,56,Biospecimen Disease Condition,keyword,HIGH,exact_match: tumor
+fever,56,Biospecimen Disease Condition,llm,HIGH,"Fever is a symptom or characteristic of a disease condition, making it a good fit for the Biospecimen Disease Condition category."
+dyspnea / tachypnea,56,Biospecimen Disease Condition,llm,HIGH,These are symptoms of a disease condition
+cough,56,Biospecimen Disease Condition,llm,HIGH,This is a symptom of a disease condition
+primary/metastasis,56,Biospecimen Disease Condition,llm,HIGH,This describes a disease condition
+symptoms,56,Biospecimen Disease Condition,llm,HIGH,This is a general term for disease conditions
+disease model,55,Biospecimen Disease Condition,keyword,HIGH,exact_match: disease
+tuberculosis_history,55,Biospecimen Disease Condition,llm,HIGH,Indicates the disease condition or medical history of the donor.
+family_history,55,Biospecimen Disease Condition,llm,HIGH,Indicates the disease condition or medical history of the donor's family.
+exitus,55,Biospecimen Disease Condition,llm,HIGH,Refers to the outcome or status of the disease condition.
+initial tumor increase/(-)decrease,54,Biospecimen Disease Condition,keyword,HIGH,exact_match: tumor
+clinic status,54,Biospecimen Disease Condition,similarity,MEDIUM,Similar to: cancer status (score: 0.769)
+primary mutation,54,Biospecimen Disease Condition,llm,HIGH,Primary mutation likely refers to the disease condition or genetic mutation present in the biospecimen.
+copy number gain,54,Biospecimen Disease Condition,llm,HIGH,Copy number gain likely refers to a genetic abnormality or disease condition present in the biospecimen.
+sofa score,54,Biospecimen Disease Condition,llm,HIGH,"Sofa score is a measure of disease severity, likely referring to the disease condition present in the biospecimen."
+als mutation,53,Biospecimen Disease Condition,llm,HIGH,"ALS mutation likely refers to a specific genetic mutation associated with Amyotrophic Lateral Sclerosis (ALS), a disease condition present in the biospecimen."
+granuloma,53,Biospecimen Disease Condition,llm,HIGH,"Granuloma is a disease condition, often associated with inflammation and infection."
+tumor size,52,Biospecimen Disease Condition,keyword,HIGH,exact_match: tumor
+brain metastasis,52,Biospecimen Disease Condition,llm,HIGH,"Brain metastasis is a disease condition, specifically a type of cancer that has spread to the brain."
+reason for intubation,52,Biospecimen Disease Condition,llm,MEDIUM,"Reason for intubation could be related to the disease condition or medical procedure, but it is not a direct disease condition."
+pregnancy,52,Biospecimen Disease Condition,llm,HIGH,"Pregnancy is a specific condition or state of the donor, which fits well with the definition of Biospecimen Disease Condition."
+tumor_grading,51,Biospecimen Disease Condition,keyword,LOW,pattern: .*tumor.*
+clinical_history,51,Biospecimen Disease Condition,llm,HIGH,"Clinical history pertains to the health status or disease conditions of the donor, aligning with Biospecimen Disease Condition."
+metastatic site,50,Biospecimen Disease Condition,similarity,MEDIUM,Similar to: metastatic tumor site (score: 0.833)
+cerebral performance category score,50,Biospecimen Disease Condition,llm,HIGH,"This label refers to a clinical assessment score, which is related to the disease condition of the donor."
+tumor source,49,Biospecimen Disease Condition,keyword,HIGH,exact_match: tumor
+diplopia,49,Biospecimen Disease Condition,llm,HIGH,"Diplopia is a medical condition, so it fits well into the disease condition category."
+mutations,49,Biospecimen Disease Condition,llm,HIGH,"Mutations can be related to disease conditions, so this label fits well into this category."
+decrease of vision,49,Biospecimen Disease Condition,llm,HIGH,"This label refers to a medical condition, so it fits well into the disease condition category."
+hours_post_infection,48,Biospecimen Disease Condition,similarity,HIGH,Similar to: hours post infection (score: 0.900)
+onset site,48,Biospecimen Disease Condition,llm,HIGH,"The term 'onset site' likely refers to the location where a disease or condition first manifests, which is a characteristic of the disease condition."
+conditioning received,47,Biospecimen Disease Condition,keyword,LOW,pattern: .*condition.*
+conditions,47,Biospecimen Disease Condition,keyword,LOW,pattern: .*condition.*
+relapse,47,Biospecimen Disease Condition,llm,HIGH,"Relapse refers to the recurrence of a disease or condition, which is a characteristic of the disease condition."
+syndrome,47,Biospecimen Disease Condition,llm,HIGH,"Syndrome refers to a set of symptoms or characteristics that define a particular disease or condition, which is a characteristic of the disease condition."
+systemic sclerosis subtype,46,Biospecimen Disease Condition,llm,HIGH,"Systemic sclerosis subtype refers to a specific classification or category of a disease or condition, which is a characteristic of the disease condition."
+parasite density on admission,46,Biospecimen Disease Condition,llm,HIGH,Parasite density on admission is a measure of disease severity or status
+active_disease,45,Biospecimen Disease Condition,keyword,LOW,pattern: .*disease.*
+serologic response status,45,Biospecimen Disease Condition,llm,HIGH,Serologic response status is a measure of disease status or immune response
+digestives_symptoms,45,Biospecimen Disease Condition,llm,HIGH,Digestive symptoms are a manifestation of disease or condition
+radiation sensitivity,45,Biospecimen Disease Condition,llm,HIGH,"Radiation sensitivity is a condition or characteristic of the biospecimen, indicating its response to radiation."
+major_organ_involvement,45,Biospecimen Disease Condition,llm,HIGH,"Major organ involvement is a characteristic of the disease condition of the biospecimen, indicating the extent of the disease."
+severity binary,45,Biospecimen Disease Condition,llm,HIGH,"Severity binary is a characteristic of the disease condition of the biospecimen, indicating the severity of the disease."
+severe_eosinophilia,45,Biospecimen Disease Condition,llm,HIGH,"Severe eosinophilia is a characteristic of the disease condition of the biospecimen, indicating a specific type of disease."
+receptor status,44,Biospecimen Disease Condition,llm,HIGH,"Receptor status is a characteristic of the disease condition of the biospecimen, indicating the presence or absence of specific receptors."
+histological grade,44,Biospecimen Disease Condition,llm,HIGH,"Histological grade is a characteristic of the disease condition of the biospecimen, indicating the severity of the disease based on histological examination."
+clinical phenotype details,44,Biospecimen Disease Condition,llm,HIGH,Clinical phenotype details are related to the disease condition of the donor or sample.
+Conditioning,42,Biospecimen Disease Condition,keyword,LOW,pattern: .*condition.*
+injection,42,Biospecimen Disease Condition,similarity,MEDIUM,Similar to: infection (score: 0.889)
+Disease,41,Biospecimen Disease Condition,keyword,HIGH,exact_match: disease
+tumor/control,41,Biospecimen Disease Condition,keyword,LOW,pattern: .*tumor.*
+er status,41,Biospecimen Disease Condition,similarity,MEDIUM,Similar to: cancer status (score: 0.818)
+disease phase,40,Biospecimen Disease Condition,keyword,HIGH,exact_match: disease
+who class,40,Biospecimen Disease Condition,llm,HIGH,"This label refers to a classification of disease or condition, which is a characteristic of the biospecimen."
+tumor.grade,39,Biospecimen Disease Condition,keyword,LOW,pattern: .*tumor.*
+qualifying condition,39,Biospecimen Disease Condition,keyword,HIGH,exact_match: condition
+clinical.diagnosis.history,39,Biospecimen Disease Condition,keyword,LOW,pattern: .*diagnosis.*
+neuropathological.information,39,Biospecimen Disease Condition,similarity,MEDIUM,Similar to: neuropathological_diagnosis (score: 0.750)
+cause.of.death,39,Biospecimen Disease Condition,llm,HIGH,"Cause of death is a condition or disease that led to the death of the donor, so it fits well with the Biospecimen Disease Condition category."
+histological response,38,Biospecimen Disease Condition,llm,HIGH,"Histological response refers to the body's reaction to a disease or treatment, which is a characteristic of the donor's disease condition."
+hereditary status,38,Biospecimen Disease Condition,llm,HIGH,"Hereditary status refers to the genetic predisposition to a disease, which is a characteristic of the donor's disease condition."
+tumor vs. normal,37,Biospecimen Disease Condition,keyword,HIGH,exact_match: tumor
+Family History,37,Biospecimen Disease Condition,llm,MEDIUM,"Family History can be related to the disease condition of the donor, but it is not a direct disease condition. It is more of a risk factor or a characteristic of the donor."
+viral infection,36,Biospecimen Disease Condition,keyword,HIGH,exact_match: infection
+maximal prior disease extend,36,Biospecimen Disease Condition,keyword,HIGH,exact_match: disease
+disease diagnosis,36,Biospecimen Disease Condition,keyword,HIGH,exact_match: disease
+hours of infection,36,Biospecimen Disease Condition,keyword,HIGH,exact_match: infection
+clinical information,36,Biospecimen Disease Condition,llm,MEDIUM,"This label is somewhat ambiguous, but it could refer to the disease condition or clinical status of the sample donor, which is a characteristic of the sample."
+parasite,36,Biospecimen Disease Condition,llm,MEDIUM,"This label could refer to the presence of a parasite in the sample, which is a characteristic of the sample's disease condition."
+years of disease,35,Biospecimen Disease Condition,keyword,HIGH,exact_match: disease
+hours post fertilization,35,Biospecimen Disease Condition,similarity,MEDIUM,Similar to: hours post infection (score: 0.773)
+primary vs metastatic,35,Biospecimen Disease Condition,llm,HIGH,"This label refers to the disease condition of the biospecimen, specifically whether it is primary or metastatic."
+nonunion type,35,Biospecimen Disease Condition,llm,HIGH,"Nonunion type refers to a specific type of bone fracture that fails to heal, indicating a disease condition."
+disease subset,34,Biospecimen Disease Condition,keyword,HIGH,exact_match: disease
+conditioned media type,34,Biospecimen Disease Condition,keyword,LOW,pattern: .*condition.*
+conditioned media origin,34,Biospecimen Disease Condition,keyword,LOW,pattern: .*condition.*
+Location tumor,34,Biospecimen Disease Condition,keyword,HIGH,exact_match: tumor
+Tumor type,34,Biospecimen Disease Condition,keyword,HIGH,exact_match: tumor
+Dead/Alive,34,Biospecimen Disease Condition,llm,HIGH,"This label refers to the status of the biospecimen, which can be an indicator of disease condition."
+Location of distant metastasis,34,Biospecimen Disease Condition,llm,HIGH,"This label refers to the location of metastasis, which is a characteristic of the disease condition."
+growth conditions,33,Biospecimen Disease Condition,keyword,LOW,pattern: .*condition.*
+viral infected,33,Biospecimen Disease Condition,similarity,MEDIUM,Similar to: viral infection (score: 0.828)
+infectious,33,Biospecimen Disease Condition,similarity,MEDIUM,Similar to: infection (score: 0.842)
+isolate sensitivity,33,Biospecimen Disease Condition,llm,HIGH,"This label refers to the sensitivity of an isolate, which is related to the disease condition of the biospecimen."
+sputum smear status,33,Biospecimen Disease Condition,llm,HIGH,"This label refers to the status of a sputum smear, which is a diagnostic test for diseases such as tuberculosis."
+infection type,32,Biospecimen Disease Condition,keyword,HIGH,exact_match: infection
+plasmodium falciparum infection status,32,Biospecimen Disease Condition,keyword,HIGH,exact_match: infection
+water type,32,Biospecimen Disease Condition,similarity,MEDIUM,Similar to: cancer type (score: 0.762)
+diffuse/limited,32,Biospecimen Disease Condition,llm,HIGH,"This label seems to describe a disease condition or subtype, which fits well with the Biospecimen Disease Condition category."
+KIT mutation,32,Biospecimen Disease Condition,llm,HIGH,"This label seems to describe a specific genetic mutation, which could be related to a disease condition or subtype, fitting well with the Biospecimen Disease Condition category."
+single or double infection,31,Biospecimen Disease Condition,keyword,HIGH,exact_match: infection
+maternal health status,31,Biospecimen Disease Condition,similarity,MEDIUM,Similar to: maternal disease status (score: 0.800)
+antibody status,31,Biospecimen Disease Condition,llm,HIGH,"This label seems to describe the presence or absence of antibodies, which could be related to a disease condition or immune response, fitting well with the Biospecimen Disease Condition category."
+lymphoma subtype,31,Biospecimen Disease Condition,llm,HIGH,"This label seems to describe a specific subtype of lymphoma, which fits well with the Biospecimen Disease Condition category."
+single or double infected,30,Biospecimen Disease Condition,similarity,HIGH,Similar to: single or double infection (score: 0.902)
+primary_recurrence,30,Biospecimen Disease Condition,llm,HIGH,primary_recurrence refers to a disease condition or status
+neural tube defect,30,Biospecimen Disease Condition,llm,HIGH,neural tube defect refers to a disease condition or status
+infection route,29,Biospecimen Disease Condition,keyword,HIGH,exact_match: infection
+sofa_admission,29,Biospecimen Disease Condition,llm,MEDIUM,"This label seems to refer to a disease condition or severity score, but the exact meaning is unclear without more context."
+affected status,29,Biospecimen Disease Condition,llm,MEDIUM,"This label seems to refer to whether the biospecimen is affected by a disease or condition, but the exact meaning is unclear without more context."
+stress condition,28,Biospecimen Disease Condition,keyword,HIGH,exact_match: condition
+pulmonary.disease,28,Biospecimen Disease Condition,keyword,LOW,pattern: .*disease.*
+cancer.past,28,Biospecimen Disease Condition,keyword,LOW,pattern: .*cancer.*
+active cancer,28,Biospecimen Disease Condition,keyword,HIGH,exact_match: cancer
+cardiovascular.disease,28,Biospecimen Disease Condition,keyword,LOW,pattern: .*disease.*
+skin phenotype,28,Biospecimen Disease Condition,llm,MEDIUM,"Skin phenotype could be related to a disease condition, but it's also possible that it refers to a normal characteristic of the biospecimen donor."
+sum.risk.factors,28,Biospecimen Disease Condition,llm,MEDIUM,"Sum of risk factors could be related to the disease condition of the donor, but it's also possible that it refers to a general health metric."
+psoriasis area-and-severity index,28,Biospecimen Disease Condition,llm,HIGH,This label explicitly refers to a disease condition (psoriasis) and a metric used to assess its severity.
+hospitalization,27,Biospecimen Disease Condition,llm,HIGH,Indicates a disease condition or health status
+follicular lymphoma grade,27,Biospecimen Disease Condition,llm,HIGH,Indicates a specific disease condition or diagnosis
+psoriasis subtype,27,Biospecimen Disease Condition,llm,HIGH,Psoriasis subtype is a specific disease condition of the donor or sample.
+oncologic diagnosis,26,Biospecimen Disease Condition,keyword,HIGH,exact_match: diagnosis
+Scaling,26,Biospecimen Disease Condition,llm,MEDIUM,"Scaling could refer to the severity or progression of a disease condition, such as psoriasis."
+skin score,26,Biospecimen Disease Condition,llm,MEDIUM,"Skin score could refer to the severity or progression of a disease condition, such as psoriasis."
+previous severity,26,Biospecimen Disease Condition,llm,MEDIUM,"Previous severity could refer to the severity or progression of a disease condition, such as psoriasis."
+Overall erythema,26,Biospecimen Disease Condition,llm,HIGH,Erythema is a disease condition characterized by redness of the skin
+degree of infiltrate,26,Biospecimen Disease Condition,llm,HIGH,Infiltrate is a disease condition characterized by the presence of abnormal cells or substances in a tissue
+pathological type,25,Biospecimen Disease Condition,llm,HIGH,Pathological type refers to the type of disease or abnormality present in a biospecimen
+environmental condition,24,Biospecimen Disease Condition,keyword,HIGH,exact_match: condition
+molecular condition,24,Biospecimen Disease Condition,keyword,HIGH,exact_match: condition
+disease course,24,Biospecimen Disease Condition,keyword,HIGH,exact_match: disease
+disease onset,24,Biospecimen Disease Condition,keyword,HIGH,exact_match: disease
+tumor_size,24,Biospecimen Disease Condition,keyword,LOW,pattern: .*tumor.*
+library outgrowth conditions,24,Biospecimen Disease Condition,keyword,LOW,pattern: .*condition.*
+clone type,24,Biospecimen Disease Condition,similarity,MEDIUM,Similar to: cancer type (score: 0.762)
+hours post-infection,24,Biospecimen Disease Condition,similarity,HIGH,Similar to: hours post infection (score: 0.950)
+channel type,24,Biospecimen Disease Condition,similarity,MEDIUM,Similar to: cancer type (score: 0.783)
+interaction status,24,Biospecimen Disease Condition,similarity,MEDIUM,Similar to: infection status (score: 0.882)
+pair status,24,Biospecimen Disease Condition,similarity,MEDIUM,Similar to: cancer status (score: 0.750)
+fip status,24,Biospecimen Disease Condition,llm,HIGH,"FIP status refers to the presence or absence of feline infectious peritonitis, a disease condition"
+mortality,24,Biospecimen Disease Condition,llm,HIGH,"This label refers to the state of being dead, which fits into the Biospecimen Disease Condition category as it describes the condition of the biospecimen."
+gametocyte status,24,Biospecimen Disease Condition,llm,HIGH,"This label describes the disease condition of the biospecimen, specifically the presence or absence of gametocytes."
+maternal disease status,23,Biospecimen Disease Condition,keyword,HIGH,exact_match: disease
+medical history,23,Biospecimen Disease Condition,llm,HIGH,"This label describes the disease condition or medical history of the donor, which is a characteristic of the biospecimen."
+histological subtype,23,Biospecimen Disease Condition,llm,HIGH,Histological subtype is a characteristic of the disease condition of the donor or sample.
+disease condition,22,Biospecimen Disease Condition,keyword,HIGH,exact_match: disease
+associated primary tumor no,22,Biospecimen Disease Condition,keyword,HIGH,exact_match: tumor
+tumor_site,22,Biospecimen Disease Condition,keyword,LOW,pattern: .*tumor.*
+metastatic status,22,Biospecimen Disease Condition,llm,HIGH,Metastatic status is a characteristic of the disease condition of the donor or sample.
+somatic mutation,21,Biospecimen Disease Condition,llm,HIGH,Somatic mutation is a type of disease condition or status
+respiratory score,21,Biospecimen Disease Condition,llm,HIGH,Respiratory score is a measure of disease condition or status
+Chief Disease,20,Biospecimen Disease Condition,keyword,HIGH,exact_match: disease
+infection_state,20,Biospecimen Disease Condition,similarity,HIGH,Similar to: infection state (score: 0.933)
+gastrointestinal involvement,20,Biospecimen Disease Condition,llm,HIGH,Gastrointestinal involvement is a type of disease condition or status
+Death Cause,20,Biospecimen Disease Condition,llm,HIGH,Death cause is related to the disease condition of the donor.
+Inflammation,20,Biospecimen Disease Condition,llm,HIGH,Inflammation is a disease condition.
+ocular involvement,20,Biospecimen Disease Condition,llm,HIGH,ocular involvement is related to the disease condition of the donor.
+vascular involvement,20,Biospecimen Disease Condition,llm,HIGH,vascular involvement is related to the disease condition of the donor.
+genital ulcer,20,Biospecimen Disease Condition,llm,HIGH,genital ulcer is a disease condition.
+arthritis,20,Biospecimen Disease Condition,llm,HIGH,arthritis is a disease condition.
+At Risk,20,Biospecimen Disease Condition,llm,HIGH,At Risk is a condition or status of the donor or sample
+oral ulcer,20,Biospecimen Disease Condition,llm,HIGH,oral ulcer is a disease condition of the donor or sample
+molecular subtype/phenotypic state,20,Biospecimen Disease Condition,llm,HIGH,molecular subtype/phenotypic state is a disease condition or status of the donor or sample
+erythema nodule,20,Biospecimen Disease Condition,llm,HIGH,erythema nodule is a disease condition of the donor or sample
+tumor model,19,Biospecimen Disease Condition,keyword,HIGH,exact_match: tumor
+tumor origin,19,Biospecimen Disease Condition,keyword,HIGH,exact_match: tumor
+disease outcome,19,Biospecimen Disease Condition,keyword,HIGH,exact_match: disease
+mechanical condition,18,Biospecimen Disease Condition,keyword,HIGH,exact_match: condition
+reason for liver resection,18,Biospecimen Disease Condition,llm,HIGH,Reason for liver resection is related to the disease condition or medical reason for the biospecimen collection.
+injury model,18,Biospecimen Disease Condition,llm,HIGH,Injury model is a condition or disease state of the biospecimen
+febrile seizure,18,Biospecimen Disease Condition,llm,HIGH,Febrile seizure is a disease condition of the biospecimen
+Wash Condition,17,Biospecimen Disease Condition,keyword,HIGH,exact_match: condition
+Labeling Condition,17,Biospecimen Disease Condition,keyword,HIGH,exact_match: condition
+location of tumors,16,Biospecimen Disease Condition,keyword,LOW,pattern: .*tumor.*
+brain tumor region,16,Biospecimen Disease Condition,keyword,HIGH,exact_match: tumor
+initial tumor volume,16,Biospecimen Disease Condition,keyword,HIGH,exact_match: tumor
+ar or asthma,16,Biospecimen Disease Condition,llm,HIGH,"The label refers to a specific disease condition, asthma."
+autism diagnostic,16,Biospecimen Disease Condition,llm,HIGH,"The label refers to a specific disease condition, autism."
+alk mutation status,16,Biospecimen Disease Condition,llm,HIGH,"The label refers to a specific genetic mutation status, which is related to disease condition."
+tumor class,15,Biospecimen Disease Condition,keyword,HIGH,exact_match: tumor
+disease classification,15,Biospecimen Disease Condition,keyword,HIGH,exact_match: disease
+pulmonary cavitation,15,Biospecimen Disease Condition,llm,HIGH,"Pulmonary cavitation is a disease condition that affects the lungs, which is a characteristic of a biospecimen disease condition."
+malignancy class,15,Biospecimen Disease Condition,llm,HIGH,"Malignancy class refers to the classification of a tumor or cancer, which is a characteristic of a biospecimen disease condition."
+risk grade,15,Biospecimen Disease Condition,llm,HIGH,Likely refers to the severity or stage of a disease
+glioma grade,15,Biospecimen Disease Condition,llm,HIGH,"Specifically refers to the grade or severity of glioma, a type of brain cancer"
+disease in non-fip,14,Biospecimen Disease Condition,keyword,HIGH,exact_match: disease
+brain tumor,14,Biospecimen Disease Condition,keyword,HIGH,exact_match: tumor
+vaccination status,14,Biospecimen Disease Condition,similarity,MEDIUM,Similar to: infection status (score: 0.765)
+immune infiltration,14,Biospecimen Disease Condition,llm,HIGH,"Immune infiltration is a condition or status of the biospecimen, indicating the presence of immune cells."
+hind-limb paralysis,14,Biospecimen Disease Condition,llm,HIGH,"Hind-limb paralysis is a condition or status of the biospecimen, indicating a specific disease or disorder."
+treatment condition,12,Biospecimen Disease Condition,keyword,HIGH,exact_match: condition
+disease grade,12,Biospecimen Disease Condition,keyword,HIGH,exact_match: disease
+tumor inoculation,12,Biospecimen Disease Condition,keyword,HIGH,exact_match: tumor
+original tumor,12,Biospecimen Disease Condition,keyword,HIGH,exact_match: tumor
+molarity of infection,12,Biospecimen Disease Condition,keyword,HIGH,exact_match: infection
+duration of disease,12,Biospecimen Disease Condition,keyword,HIGH,exact_match: disease
+type of insertion,12,Biospecimen Disease Condition,similarity,MEDIUM,Similar to: site of infection (score: 0.765)
+clinical manifestation,12,Biospecimen Disease Condition,similarity,MEDIUM,Similar to: clinical condition (score: 0.750)
+incubation period,12,Biospecimen Disease Condition,similarity,MEDIUM,Similar to: infection period (score: 0.848)
+rift valley fever virus,12,Biospecimen Disease Condition,llm,HIGH,"This label refers to a specific disease condition, which is a viral infection."
+engraftment,12,Biospecimen Disease Condition,llm,HIGH,"This label refers to a specific biological process, which could be related to a disease condition."
+interstitial pneumonia,12,Biospecimen Disease Condition,llm,HIGH,"This label refers to a specific disease condition, which is a type of lung infection."
+seizures/month,12,Biospecimen Disease Condition,llm,HIGH,Seizures/month is a measure of disease condition or status.
+surgical indication,12,Biospecimen Disease Condition,llm,HIGH,"Surgical indication refers to the medical reason for performing a surgical procedure, which is related to the disease condition of the biospecimen."
+melanoma,12,Biospecimen Disease Condition,llm,HIGH,"Melanoma is a type of cancer, which is a disease condition"
+major reason_for_surgery,12,Biospecimen Disease Condition,llm,MEDIUM,This label could be related to the disease condition or medical history of the patient
+primary/ recurrent,11,Biospecimen Disease Condition,llm,HIGH,Primary/recurrent is a disease condition or status
+metastatic/primary,11,Biospecimen Disease Condition,llm,HIGH,Metastatic/primary is a disease condition or status
+recurrent/primary,11,Biospecimen Disease Condition,llm,HIGH,Indicates the disease condition of the donor or sample
+genotype/disease state,10,Biospecimen Disease Condition,keyword,MEDIUM,keyword: disease state
+viral inactivation,10,Biospecimen Disease Condition,similarity,MEDIUM,Similar to: viral infection (score: 0.788)
+infection rate,9,Biospecimen Disease Condition,keyword,HIGH,exact_match: infection
+infection period,9,Biospecimen Disease Condition,keyword,HIGH,exact_match: infection
+oxygen condition,9,Biospecimen Disease Condition,keyword,HIGH,exact_match: condition
+conditioned medium,9,Biospecimen Disease Condition,keyword,LOW,pattern: .*condition.*
+weight phenotype,9,Biospecimen Disease Condition,llm,MEDIUM,"Could be related to a disease condition or phenotype, but the connection is not clear without more context."
+resistance profile,9,Biospecimen Disease Condition,llm,HIGH,"This label refers to the disease condition or status of the biospecimen, specifically its resistance profile."
+embryo phenotype,9,Biospecimen Disease Condition,llm,HIGH,"This label refers to the disease condition or status of the biospecimen, specifically the phenotype of the embryo."
+etiology,9,Biospecimen Disease Condition,llm,HIGH,"Etiology refers to the cause or origin of a disease, which is closely related to the disease condition of the donor or sample."
+conditioned media source,8,Biospecimen Disease Condition,keyword,LOW,pattern: .*condition.*
+growing media conditions,8,Biospecimen Disease Condition,keyword,LOW,pattern: .*condition.*
+Disease state,8,Biospecimen Disease Condition,keyword,HIGH,exact_match: disease
+disease feature,8,Biospecimen Disease Condition,keyword,HIGH,exact_match: disease
+environmental factor,8,Biospecimen Disease Condition,similarity,MEDIUM,Similar to: environmental condition (score: 0.791)
+nes status,8,Biospecimen Disease Condition,similarity,MEDIUM,Similar to: cancer status (score: 0.783)
+myopathic motor_unit_potentials,8,Biospecimen Disease Condition,llm,HIGH,"Myopathic motor_unit_potentials is a term that describes a specific disease condition or abnormality, which is related to the disease condition of the donor or sample."
+mutation details,8,Biospecimen Disease Condition,llm,HIGH,Mutation details are related to the disease condition of the donor or sample.
+cognitive impairment,8,Biospecimen Disease Condition,llm,HIGH,Cognitive impairment is a disease condition or status of the donor or sample.
+site of_disease_onset,6,Biospecimen Disease Condition,keyword,LOW,pattern: .*disease.*
+disease name,6,Biospecimen Disease Condition,keyword,HIGH,exact_match: disease
+tumor position,6,Biospecimen Disease Condition,keyword,HIGH,exact_match: tumor
+zinc status,6,Biospecimen Disease Condition,similarity,MEDIUM,Similar to: cancer status (score: 0.750)
+round of selection,6,Biospecimen Disease Condition,similarity,MEDIUM,Similar to: rounds of infection (score: 0.811)
+distant metastasis,6,Biospecimen Disease Condition,llm,HIGH,Distant metastasis is a disease condition
+tobacco use,6,Biospecimen Disease Condition,llm,MEDIUM,Tobacco use is a risk factor for disease
+parental/ne-like state,6,Biospecimen Disease Condition,llm,MEDIUM,"This label seems to describe a condition or state of the biospecimen, but it's not entirely clear."
+oocyst prevalence,6,Biospecimen Disease Condition,llm,MEDIUM,"This label seems to describe a condition or state of the biospecimen, but it's not entirely clear."
+cancer predisposition,5,Biospecimen Disease Condition,keyword,HIGH,exact_match: cancer
+original tumor type,5,Biospecimen Disease Condition,keyword,HIGH,exact_match: tumor
+post-symptom onset,5,Biospecimen Disease Condition,llm,HIGH,"Post-symptom onset refers to the time after symptoms of a disease have appeared, which is relevant to the disease condition of the biospecimen."
+invasive behavior,5,Biospecimen Disease Condition,llm,HIGH,Invasive behavior is a characteristic of a disease condition
+growth_condition,4,Biospecimen Disease Condition,keyword,LOW,pattern: .*condition.*
+plasmodium infection,4,Biospecimen Disease Condition,keyword,HIGH,exact_match: infection
+length of infection,4,Biospecimen Disease Condition,keyword,HIGH,exact_match: infection
+responder status,4,Biospecimen Disease Condition,llm,MEDIUM,"Responder status could refer to the response of a patient or sample to a treatment, which is related to the disease condition."
+molecular diagnosis,3,Biospecimen Disease Condition,keyword,HIGH,exact_match: diagnosis
+experimental conditions,3,Biospecimen Disease Condition,keyword,LOW,pattern: .*condition.*
+months post infection,3,Biospecimen Disease Condition,keyword,HIGH,exact_match: infection
+reference lot,3,Biospecimen Disease Condition,similarity,MEDIUM,Similar to: reference condition (score: 0.750)
+reference cat,3,Biospecimen Disease Condition,similarity,MEDIUM,Similar to: reference condition (score: 0.750)
+histopathological diagnostic,3,Biospecimen Disease Condition,similarity,MEDIUM,Similar to: histological diagnosis (score: 0.840)
+fibrosis,3,Biospecimen Disease Condition,llm,HIGH,"This label describes a disease condition, which is a characteristic of the biospecimen."
+severity grade,3,Biospecimen Disease Condition,llm,HIGH,"Severity grade is a measure of the extent or severity of a disease or condition, which fits well with the Biospecimen Disease Condition category."
+diffuse vs limited,3,Biospecimen Disease Condition,llm,HIGH,"Diffuse vs limited is a classification of disease extent or progression, which aligns with the Biospecimen Disease Condition category."
+allergy,3,Biospecimen Disease Condition,llm,HIGH,"Allergy is a specific type of disease condition, making it a good fit for the Biospecimen Disease Condition category."
+tumor who grade,2,Biospecimen Disease Condition,keyword,HIGH,exact_match: tumor
+reference condition,2,Biospecimen Disease Condition,keyword,HIGH,exact_match: condition
+test condition,2,Biospecimen Disease Condition,keyword,HIGH,exact_match: condition
+rounds of infection,2,Biospecimen Disease Condition,keyword,HIGH,exact_match: infection
+months_survival,2,Biospecimen Disease Condition,llm,HIGH,months_survival is a measure of disease progression or outcome
+progression_status,2,Biospecimen Disease Condition,llm,HIGH,progression_status describes the disease condition or progression
+months_progression,2,Biospecimen Disease Condition,llm,HIGH,"This label seems to describe the progression of a disease, which fits well with the Biospecimen Disease Condition category."
+Infection Status,1,Biospecimen Disease Condition,keyword,HIGH,exact_match: infection
+mitotic rate,1,Biospecimen Disease Condition,llm,MEDIUM,"This label seems to describe a characteristic of a disease or condition, but it could also be a feature of a biospecimen. Without more context, it's difficult to determine the best category."
+positive Down screening risk,1,Biospecimen Disease Condition,llm,HIGH,"This label appears to describe a disease or condition, specifically a risk factor for Down syndrome, which fits well with the Biospecimen Disease Condition category."
+genotype,46776,Biospecimen Organism,similarity,MEDIUM,Similar to: host genotype (score: 0.762)
+strain,41490,Biospecimen Organism,keyword,HIGH,exact_match: strain
+genotype/variation,6816,Biospecimen Organism,similarity,MEDIUM,Similar to: mouse genotype/variation (score: 0.857)
+strain background,2334,Biospecimen Organism,keyword,HIGH,exact_match: strain
+organismpart,2192,Biospecimen Organism,keyword,LOW,pattern: .*organism.*
+organism part,2102,Biospecimen Organism,keyword,HIGH,exact_match: organism
+cell organism,1508,Biospecimen Organism,keyword,HIGH,exact_match: organism
+strain/background,1449,Biospecimen Organism,keyword,LOW,pattern: .*strain.*
+virus,1436,Biospecimen Organism,llm,HIGH,Virus is a type of organism
+mouse strain,1292,Biospecimen Organism,keyword,HIGH,exact_match: strain
+background strain,997,Biospecimen Organism,keyword,HIGH,exact_match: strain
+infected with,898,Biospecimen Organism,similarity,MEDIUM,Similar to: infected host (score: 0.769)
+mouse model,822,Biospecimen Organism,keyword,MEDIUM,keyword: mouse
+companion animals,804,Biospecimen Organism,llm,HIGH,Companion animals are a type of living biological system
+agricultural animals,804,Biospecimen Organism,llm,HIGH,Agricultural animals are a type of living biological system
+os,703,Biospecimen Organism,llm,LOW,"OS could be an abbreviation for organism or species, but it is unclear without more context"
+os_status,656,Biospecimen Organism,similarity,MEDIUM,Similar to: mouse status (score: 0.762)
+strain description,638,Biospecimen Organism,keyword,HIGH,exact_match: strain
+selection,567,Biospecimen Organism,similarity,MEDIUM,Similar to: mouse selection (score: 0.750)
+host,536,Biospecimen Organism,keyword,MEDIUM,keyword: host
+origin,525,Biospecimen Organism,llm,HIGH,The term 'origin' often refers to the source or species of a biological sample.
+source_organism,500,Biospecimen Organism,keyword,LOW,pattern: .*organism.*
+Strain,486,Biospecimen Organism,keyword,HIGH,exact_match: strain
+pathogen,478,Biospecimen Organism,llm,HIGH,Pathogen is a type of organism
+breed,443,Biospecimen Organism,llm,HIGH,"Breed is a characteristic of the biospecimen organism, describing the specific breed of animal from which the sample was taken."
+strain/genotype,371,Biospecimen Organism,keyword,LOW,pattern: .*strain.*
+mouse number,369,Biospecimen Organism,keyword,MEDIUM,keyword: mouse
+mouse,354,Biospecimen Organism,keyword,MEDIUM,keyword: mouse
+parasite strain,322,Biospecimen Organism,keyword,HIGH,exact_match: strain
+OrganismPart,300,Biospecimen Organism,keyword,LOW,pattern: .*organism.*
+OS status,297,Biospecimen Organism,similarity,MEDIUM,Similar to: mouse status (score: 0.857)
+virus strain,283,Biospecimen Organism,keyword,HIGH,exact_match: strain
+genome/variation,266,Biospecimen Organism,similarity,MEDIUM,Similar to: mouse genotype/variation (score: 0.750)
+malaria strain,203,Biospecimen Organism,keyword,HIGH,exact_match: strain
+couple number,188,Biospecimen Organism,similarity,MEDIUM,Similar to: mouse number (score: 0.800)
+bacterium,186,Biospecimen Organism,llm,HIGH,This label refers to a type of microorganism.
+living,170,Biospecimen Organism,llm,HIGH,"Living refers to the organism being alive, which is a characteristic of the biospecimen organism."
+strain name,160,Biospecimen Organism,keyword,HIGH,exact_match: strain
+pathogens,138,Biospecimen Organism,similarity,MEDIUM,Similar to: pathogen strain (score: 0.750)
+host cell,134,Biospecimen Organism,keyword,MEDIUM,keyword: host
+mouse genotype/variation,124,Biospecimen Organism,keyword,MEDIUM,keyword: mouse
+immune status,113,Biospecimen Organism,similarity,MEDIUM,Similar to: mouse status (score: 0.800)
+replicate mouse,102,Biospecimen Organism,keyword,MEDIUM,keyword: mouse
+litter,99,Biospecimen Organism,llm,HIGH,"Litter refers to a group of animals, likely the source of biospecimens"
+viral strain,96,Biospecimen Organism,keyword,HIGH,exact_match: strain
+parasite line,95,Biospecimen Organism,similarity,MEDIUM,Similar to: parasite strain (score: 0.786)
+virus type,86,Biospecimen Organism,llm,HIGH,"This label refers to the type of virus, which is a characteristic of the biological organism being studied."
+cattle breed,85,Biospecimen Organism,llm,HIGH,"This label refers to the breed of cattle, which is a characteristic of the biological organism being studied."
+host genotype,84,Biospecimen Organism,keyword,MEDIUM,keyword: host
+mouse line abbreviation,84,Biospecimen Organism,keyword,MEDIUM,keyword: mouse
+viral status,82,Biospecimen Organism,similarity,MEDIUM,Similar to: viral strain (score: 0.750)
+infected host,79,Biospecimen Organism,keyword,MEDIUM,keyword: host
+bacterial strain,79,Biospecimen Organism,keyword,HIGH,exact_match: strain
+viral genus,78,Biospecimen Organism,llm,HIGH,"A viral genus is a classification of viruses, which fits into the category of Biospecimen Organism."
+viral family,78,Biospecimen Organism,llm,HIGH,"A viral family is a classification of viruses, which fits into the category of Biospecimen Organism."
+host strain,76,Biospecimen Organism,keyword,HIGH,exact_match: strain
+mouse line,74,Biospecimen Organism,keyword,MEDIUM,keyword: mouse
+host mice strain,70,Biospecimen Organism,keyword,HIGH,exact_match: strain
+parental origin,70,Biospecimen Organism,similarity,MEDIUM,Similar to: parental strain (score: 0.800)
+host vendor,69,Biospecimen Organism,keyword,MEDIUM,keyword: host
+host strain/background,69,Biospecimen Organism,keyword,MEDIUM,keyword: host
+mouse selection,68,Biospecimen Organism,keyword,MEDIUM,keyword: mouse
+genotype/strain,62,Biospecimen Organism,keyword,LOW,pattern: .*strain.*
+mouse age,57,Biospecimen Organism,keyword,MEDIUM,keyword: mouse
+laboratory strain,54,Biospecimen Organism,keyword,HIGH,exact_match: strain
+Genotype,52,Biospecimen Organism,similarity,MEDIUM,Similar to: host genotype (score: 0.762)
+organism_status,51,Biospecimen Organism,keyword,LOW,pattern: .*organism.*
+recipient strain,51,Biospecimen Organism,keyword,HIGH,exact_match: strain
+organism_part,51,Biospecimen Organism,keyword,LOW,pattern: .*organism.*
+infection strain,51,Biospecimen Organism,keyword,HIGH,exact_match: strain
+strain info,50,Biospecimen Organism,keyword,HIGH,exact_match: strain
+mosquito,48,Biospecimen Organism,llm,HIGH,"Mosquito is a living organism, so it fits well into the biospecimen organism category."
+parental strain,46,Biospecimen Organism,keyword,HIGH,exact_match: strain
+host cell line,45,Biospecimen Organism,keyword,MEDIUM,keyword: host
+cell line / strain,45,Biospecimen Organism,keyword,HIGH,exact_match: strain
+strain source,44,Biospecimen Organism,keyword,HIGH,exact_match: strain
+host organism,44,Biospecimen Organism,keyword,HIGH,exact_match: organism
+age and_strain,42,Biospecimen Organism,keyword,LOW,pattern: .*strain.*
+specificity,42,Biospecimen Organism,similarity,MEDIUM,Similar to: specific-host (score: 0.750)
+specific,39,Biospecimen Organism,similarity,MEDIUM,Similar to: specific-host (score: 0.762)
+host cell type,38,Biospecimen Organism,keyword,MEDIUM,keyword: host
+Virus Strain,38,Biospecimen Organism,keyword,HIGH,exact_match: strain
+Mouse model,36,Biospecimen Organism,keyword,MEDIUM,keyword: mouse
+strain  background,35,Biospecimen Organism,keyword,HIGH,exact_match: strain
+host_cell_line,35,Biospecimen Organism,keyword,MEDIUM,keyword: host
+plasmodium strain,32,Biospecimen Organism,keyword,HIGH,exact_match: strain
+parental-strain,30,Biospecimen Organism,keyword,LOW,pattern: .*strain.*
+microorganism_source_of_infection,29,Biospecimen Organism,keyword,LOW,pattern: .*organism.*
+microorganism_blood,29,Biospecimen Organism,keyword,LOW,pattern: .*organism.*
+strain origin,29,Biospecimen Organism,keyword,HIGH,exact_match: strain
+Pathogen,29,Biospecimen Organism,llm,HIGH,A pathogen is a type of organism that can cause disease.
+geographical origin,29,Biospecimen Organism,llm,MEDIUM,"Geographical origin could relate to the source or host organism, but it's a bit of a stretch. It might also relate to the donor's origin, which is not explicitly covered by the categories."
+spike-in organism,28,Biospecimen Organism,keyword,HIGH,exact_match: organism
+series,27,Biospecimen Organism,similarity,MEDIUM,Similar to: species (score: 0.769)
+strain/isolate,25,Biospecimen Organism,keyword,LOW,pattern: .*strain.*
+pathogen strain,24,Biospecimen Organism,keyword,HIGH,exact_match: strain
+Mouse strain,24,Biospecimen Organism,keyword,HIGH,exact_match: strain
+mouse dietary condition,24,Biospecimen Organism,keyword,MEDIUM,keyword: mouse
+organism,22,Biospecimen Organism,keyword,HIGH,exact_match: organism
+strand,22,Biospecimen Organism,similarity,MEDIUM,Similar to: strain (score: 0.833)
+human tissue source,20,Biospecimen Organism,keyword,MEDIUM,keyword: human
+virus subtype,20,Biospecimen Organism,llm,HIGH,Virus subtype is a type of organism or species
+strains,19,Biospecimen Organism,keyword,LOW,pattern: .*strain.*
+infection host,18,Biospecimen Organism,keyword,MEDIUM,keyword: host
+mouse group,16,Biospecimen Organism,keyword,MEDIUM,keyword: mouse
+parent_strain,16,Biospecimen Organism,keyword,LOW,pattern: .*strain.*
+strain/model,16,Biospecimen Organism,keyword,LOW,pattern: .*strain.*
+specific-host,15,Biospecimen Organism,keyword,MEDIUM,keyword: host
+genotype/varation,14,Biospecimen Organism,similarity,MEDIUM,Similar to: mouse genotype/variation (score: 0.829)
+host age,12,Biospecimen Organism,keyword,MEDIUM,keyword: host
+mouse status,12,Biospecimen Organism,keyword,MEDIUM,keyword: mouse
+mouse stain,12,Biospecimen Organism,keyword,MEDIUM,keyword: mouse
+species,11,Biospecimen Organism,keyword,HIGH,exact_match: species
+graft recipient strain,10,Biospecimen Organism,keyword,HIGH,exact_match: strain
+malaria status,10,Biospecimen Organism,similarity,MEDIUM,Similar to: malaria strain (score: 0.786)
+bacteria,10,Biospecimen Organism,llm,HIGH,Refers to a type of living biological system
+host mouse strain,9,Biospecimen Organism,keyword,HIGH,exact_match: strain
+original strain,8,Biospecimen Organism,keyword,HIGH,exact_match: strain
+ps status,8,Biospecimen Organism,similarity,MEDIUM,Similar to: mouse status (score: 0.762)
+infectious strain,7,Biospecimen Organism,keyword,HIGH,exact_match: strain
+Species,7,Biospecimen Organism,keyword,HIGH,exact_match: species
+host tissue,7,Biospecimen Organism,keyword,MEDIUM,keyword: host
+virus family,7,Biospecimen Organism,llm,HIGH,"A virus family is a classification of viruses, which could be considered a type of biospecimen organism."
+virus genus,7,Biospecimen Organism,llm,HIGH,Virus genus is a characteristic of the organism
+strain recipient,6,Biospecimen Organism,keyword,HIGH,exact_match: strain
+cell strain,6,Biospecimen Organism,keyword,HIGH,exact_match: strain
+Cell strain,6,Biospecimen Organism,keyword,HIGH,exact_match: strain
+mouse cell genotype/variation,6,Biospecimen Organism,keyword,MEDIUM,keyword: mouse
+human cell genotype/variation,6,Biospecimen Organism,keyword,MEDIUM,keyword: human
+human tumor cell line,6,Biospecimen Organism,keyword,MEDIUM,keyword: human
+strain_recipient,6,Biospecimen Organism,keyword,LOW,pattern: .*strain.*
+stain,6,Biospecimen Organism,similarity,HIGH,Similar to: strain (score: 0.909)
+genotype of founder fish,6,Biospecimen Organism,llm,HIGH,Provides information about the genetic makeup of the organism
+mice,6,Biospecimen Organism,llm,HIGH,Specifies the type of organism
+infrequent clonal strain code,4,Biospecimen Organism,keyword,HIGH,exact_match: strain
+host mouse_tissue,4,Biospecimen Organism,keyword,MEDIUM,keyword: mouse
+mouse genotype,4,Biospecimen Organism,keyword,MEDIUM,keyword: mouse
+background mice,4,Biospecimen Organism,similarity,MEDIUM,Similar to: background strain (score: 0.750)
+mouse tissue,3,Biospecimen Organism,keyword,MEDIUM,keyword: mouse
+host cells,3,Biospecimen Organism,keyword,MEDIUM,keyword: host
+bacteria strain,3,Biospecimen Organism,keyword,HIGH,exact_match: strain
+life form,2,Biospecimen Organism,llm,MEDIUM,"This label could refer to the organism from which the biospecimen was derived, but it is not a very specific or common term in this context."
+mammalian host,1,Biospecimen Organism,keyword,MEDIUM,keyword: host
+hot,1,Biospecimen Organism,similarity,MEDIUM,Similar to: host (score: 0.857)
+ethnicity,10118,Biospecimen Race,keyword,HIGH,exact_match: ethnicity
+race,7888,Biospecimen Race,keyword,HIGH,exact_match: race
+Race,638,Biospecimen Race,keyword,HIGH,exact_match: race
+Ethnicity,547,Biospecimen Race,keyword,HIGH,exact_match: ethnicity
+self_reported_race,195,Biospecimen Race,keyword,LOW,pattern: .*race.*
+ancestry,168,Biospecimen Race,llm,HIGH,"Ancestry is related to the race or ethnicity of the donor, which is a characteristic of the biospecimen."
+race/ethnicity,105,Biospecimen Race,keyword,MEDIUM,keyword: ethnicity
+ethnic group,46,Biospecimen Race,keyword,LOW,pattern: .*ethnic.*
+Ethnic group,28,Biospecimen Race,keyword,LOW,pattern: .*ethnic.*
+race_ethnicity,22,Biospecimen Race,keyword,MEDIUM,keyword: ethnicity
+gender,53178,Biospecimen Sex,keyword,HIGH,exact_match: gender
+Sex,47903,Biospecimen Sex,keyword,HIGH,exact_match: sex
+sex,1601,Biospecimen Sex,keyword,HIGH,exact_match: sex
+Gender,1172,Biospecimen Sex,keyword,HIGH,exact_match: gender
+animal sex,320,Biospecimen Sex,keyword,HIGH,exact_match: sex
+fetal sex,179,Biospecimen Sex,keyword,HIGH,exact_match: sex
+biological sex,127,Biospecimen Sex,keyword,HIGH,exact_match: sex
+biologics,120,Biospecimen Sex,similarity,MEDIUM,Similar to: biological sex (score: 0.783)
+female,104,Biospecimen Sex,keyword,HIGH,exact_match: female
+SEX,60,Biospecimen Sex,keyword,HIGH,exact_match: sex
+nulliparous,38,Biospecimen Sex,llm,HIGH,"Nulliparous refers to a woman who has never given birth, which is a characteristic of the donor's sex."
+gene,33,Biospecimen Sex,similarity,MEDIUM,Similar to: gender (score: 0.800)
+gender source,26,Biospecimen Sex,keyword,HIGH,exact_match: gender
+sex predicted,23,Biospecimen Sex,keyword,HIGH,exact_match: sex
+InfantSex,20,Biospecimen Sex,keyword,LOW,pattern: .*sex.*
+gender composition,15,Biospecimen Sex,keyword,HIGH,exact_match: gender
+placental sex,13,Biospecimen Sex,keyword,HIGH,exact_match: sex
+biological source,12,Biospecimen Sex,similarity,MEDIUM,Similar to: biological sex (score: 0.839)
+Sex of recipient mice,6,Biospecimen Sex,keyword,HIGH,exact_match: sex
+source gender,6,Biospecimen Sex,keyword,HIGH,exact_match: gender
+tissue,157196,Biospecimen Type,keyword,HIGH,exact_match: tissue
+cell type,97260,Biospecimen Type,keyword,HIGH,exact_match: cell
+cell line,40278,Biospecimen Type,keyword,HIGH,exact_match: cell
+chip antibody,5153,Biospecimen Type,llm,HIGH,"The term 'chip antibody' likely refers to a specific type of antibody used in a microarray chip experiment, which is a type of biospecimen."
+antibody,4446,Biospecimen Type,llm,HIGH,"An antibody is a type of biospecimen, specifically a protein used in various biological assays."
+tissue type,3471,Biospecimen Type,keyword,HIGH,exact_match: tissue
+molecule subtype,2882,Biospecimen Type,llm,HIGH,"A molecule subtype is a specific type of biospecimen, referring to a particular category of molecules."
+stimulation,2378,Biospecimen Type,similarity,MEDIUM,Similar to: cell stimulation (score: 0.815)
+celltype,2035,Biospecimen Type,keyword,HIGH,exact_match: celltype
+phenotype,1959,Biospecimen Type,similarity,MEDIUM,Similar to: cell phenotype (score: 0.783)
+tissue anatomic site,1936,Biospecimen Type,keyword,HIGH,exact_match: tissue
+type,1856,Biospecimen Type,llm,HIGH,"Type is a general term that can refer to the type of biospecimen, such as tissue or cell type."
+cell description,1693,Biospecimen Type,keyword,HIGH,exact_match: cell
+cell sex,1656,Biospecimen Type,keyword,HIGH,exact_match: cell
+molecule type,1618,Biospecimen Type,llm,HIGH,"Molecule type refers to the type of molecules present in the biospecimen, such as DNA or protein."
+library type,1600,Biospecimen Type,llm,HIGH,"Library type refers to the type of biospecimen library, such as a DNA or RNA library."
+cell,1531,Biospecimen Type,keyword,HIGH,exact_match: cell
+molecule,1522,Biospecimen Type,llm,HIGH,Molecule is a type of biospecimen
+well,1500,Biospecimen Type,similarity,MEDIUM,Similar to: cell (score: 0.750)
+Tissue,1499,Biospecimen Type,keyword,HIGH,exact_match: tissue
+tissue source,1209,Biospecimen Type,keyword,HIGH,exact_match: tissue
+tissue/cell type,1069,Biospecimen Type,keyword,LOW,pattern: .*tissue.*
+isolate,1067,Biospecimen Type,llm,HIGH,"Isolate refers to a type of biospecimen, often a microorganism isolated from a sample."
+material,1047,Biospecimen Type,llm,HIGH,"Material refers to the type of biospecimen, such as tissue, blood, or cells."
+cell subtype,1002,Biospecimen Type,keyword,HIGH,exact_match: cell
+parity,998,Biospecimen Type,llm,HIGH,"Parity is a characteristic of a biological sample, specifically related to the number of times a woman has given birth, which can be considered a type of biospecimen characteristic."
+country of serum collection,911,Biospecimen Type,keyword,HIGH,exact_match: serum
+organ failure,910,Biospecimen Type,keyword,HIGH,exact_match: organ
+cell_type,875,Biospecimen Type,keyword,LOW,pattern: .*cell.*
+cell subset,806,Biospecimen Type,keyword,HIGH,exact_match: cell
+tissue preparation,779,Biospecimen Type,keyword,HIGH,exact_match: tissue
+morphology,764,Biospecimen Type,similarity,MEDIUM,Similar to: cell morphology (score: 0.800)
+tissue of origin,744,Biospecimen Type,keyword,HIGH,exact_match: tissue
+background,730,Biospecimen Type,llm,MEDIUM,Background could refer to the type of sample or cell line used as a control
+cell karyotype,726,Biospecimen Type,keyword,HIGH,exact_match: cell
+case number,726,Biospecimen Type,similarity,MEDIUM,Similar to: cell number (score: 0.818)
+cell lineage,713,Biospecimen Type,keyword,HIGH,exact_match: cell
+genetic background,683,Biospecimen Type,llm,HIGH,Genetic background refers to the genetic makeup of an organism or cell line
+tissue_type,661,Biospecimen Type,keyword,LOW,pattern: .*tissue.*
+flowcell,640,Biospecimen Type,keyword,LOW,pattern: .*cell.*
+transduction,629,Biospecimen Type,similarity,MEDIUM,Similar to: cell transduction (score: 0.828)
+epithelial,618,Biospecimen Type,llm,HIGH,Refers to a type of tissue or cell
+sorted cells,546,Biospecimen Type,keyword,LOW,pattern: .*cell.*
+cell population,505,Biospecimen Type,keyword,HIGH,exact_match: cell
+organ/tissue,503,Biospecimen Type,keyword,LOW,pattern: .*tissue.*
+predicted celltype,500,Biospecimen Type,keyword,HIGH,exact_match: celltype
+predicted parent celltype,500,Biospecimen Type,keyword,HIGH,exact_match: celltype
+timepoint biopsy,500,Biospecimen Type,keyword,MEDIUM,keyword: biopsy
+lymphocyte_percent,500,Biospecimen Type,keyword,MEDIUM,keyword: lymphocyte
+lymphocyte_absolute,500,Biospecimen Type,keyword,MEDIUM,keyword: lymphocyte
+monocyte_percent,500,Biospecimen Type,keyword,MEDIUM,keyword: monocyte
+monocyte_absolute,500,Biospecimen Type,keyword,MEDIUM,keyword: monocyte
+cell projection,500,Biospecimen Type,keyword,HIGH,exact_match: cell
+cell line code,500,Biospecimen Type,keyword,HIGH,exact_match: cell
+white_blood_cell_count,500,Biospecimen Type,keyword,LOW,pattern: .*cell.*
+sorted compartment,500,Biospecimen Type,similarity,MEDIUM,Similar to: tissue compartment (score: 0.778)
+culture_result,500,Biospecimen Type,llm,MEDIUM,"Culture result could refer to the type of biospecimen obtained from a culture, such as a cell line or microorganism."
+smear_results,500,Biospecimen Type,llm,MEDIUM,"Smear results could refer to the type of biospecimen obtained from a smear, such as a blood smear or tissue smear."
+full_genotype,500,Biospecimen Type,llm,HIGH,"Genotype is a characteristic of a biospecimen, specifically describing its genetic makeup."
+hip_circumference,500,Biospecimen Type,llm,MEDIUM,"Hip circumference is a physical characteristic of a biospecimen, specifically describing its size or shape."
+waist_circumference,500,Biospecimen Type,llm,LOW,"This label could be related to the type of biospecimen, but it is more likely to be a measurement or characteristic of the donor."
+microdissection,500,Biospecimen Type,llm,HIGH,"This label is likely related to the type of biospecimen, as microdissection is a technique used to isolate specific cells or tissues."
+assayed molecule,489,Biospecimen Type,llm,HIGH,Type of molecule being analyzed or measured
+population,477,Biospecimen Type,similarity,MEDIUM,Similar to: cell population (score: 0.800)
+tissue_depot,471,Biospecimen Type,keyword,LOW,pattern: .*tissue.*
+red blood cells,460,Biospecimen Type,keyword,HIGH,exact_match: blood
+lymphs,460,Biospecimen Type,llm,HIGH,Lymphs is a type of biospecimen
+line,459,Biospecimen Type,llm,HIGH,Line could refer to a cell line
+white blood cells,458,Biospecimen Type,keyword,HIGH,exact_match: blood
+isolation_method,455,Biospecimen Type,llm,HIGH,"Isolation method is a characteristic of the biospecimen type, describing how the sample was obtained."
+skin type,452,Biospecimen Type,llm,HIGH,"Skin type is a characteristic of the biospecimen type, describing the type of skin from which the sample was taken."
+specimen,434,Biospecimen Type,keyword,MEDIUM,keyword: specimen
+library well,412,Biospecimen Type,llm,MEDIUM,Library well refers to a specific type of biospecimen or sample used in experiments.
+library plate,412,Biospecimen Type,llm,MEDIUM,Library plate refers to a specific type of biospecimen or sample used in experiments.
+platelet,394,Biospecimen Type,llm,HIGH,"Platelet is a type of cellular component, which fits well with the Biospecimen Type category."
+antigen,384,Biospecimen Type,llm,HIGH,"Antigen is a type of biomolecule, which fits well with the Biospecimen Type category."
+markers,382,Biospecimen Type,llm,HIGH,"Markers are often used to identify specific cells or tissues, which fits well with the Biospecimen Type category."
+blood obtained,374,Biospecimen Type,keyword,HIGH,exact_match: blood
+tissue substructure,363,Biospecimen Type,keyword,HIGH,exact_match: tissue
+tissue structure,363,Biospecimen Type,keyword,HIGH,exact_match: tissue
+organ,361,Biospecimen Type,keyword,HIGH,exact_match: organ
+source type,345,Biospecimen Type,similarity,MEDIUM,Similar to: source cell type (score: 0.815)
+skin,338,Biospecimen Type,llm,HIGH,Refers to a specific type of biospecimen
+colony of_origin,320,Biospecimen Type,llm,HIGH,"Colony of origin refers to the type of biological sample, so it fits well into the Biospecimen Type category."
+cell phenotype,319,Biospecimen Type,keyword,HIGH,exact_match: cell
+hemoglobin genotype,315,Biospecimen Type,llm,HIGH,"Hemoglobin genotype refers to the type of biological sample, so it fits well into the Biospecimen Type category."
+per lymphocytes,313,Biospecimen Type,keyword,MEDIUM,keyword: lymphocyte
+per monocytes,313,Biospecimen Type,keyword,MEDIUM,keyword: monocyte
+trachea region,301,Biospecimen Type,llm,HIGH,"The term 'trachea region' suggests a specific anatomical location, which is often used to describe the type of biospecimen."
+TargetedCellType,300,Biospecimen Type,keyword,LOW,pattern: .*cell.*
+CellLine,300,Biospecimen Type,keyword,LOW,pattern: .*cell.*
+cells,299,Biospecimen Type,keyword,LOW,pattern: .*cell.*
+tissue.type,271,Biospecimen Type,keyword,LOW,pattern: .*tissue.*
+specimen_name,270,Biospecimen Type,keyword,MEDIUM,keyword: specimen
+biopsy,260,Biospecimen Type,keyword,MEDIUM,keyword: biopsy
+monocytes,242,Biospecimen Type,keyword,MEDIUM,keyword: monocyte
+intrinsic subtype,231,Biospecimen Type,llm,MEDIUM,"Intrinsic subtype could be related to the type of biospecimen, but it is not entirely clear."
+blood collection tube coating,227,Biospecimen Type,keyword,HIGH,exact_match: blood
+tissue subtype,220,Biospecimen Type,keyword,HIGH,exact_match: tissue
+tissue region,211,Biospecimen Type,keyword,HIGH,exact_match: tissue
+blood_group,208,Biospecimen Type,keyword,LOW,pattern: .*blood.*
+cell types,205,Biospecimen Type,keyword,HIGH,exact_match: cell
+responder cell line,203,Biospecimen Type,keyword,HIGH,exact_match: cell
+anatomic_location,202,Biospecimen Type,llm,HIGH,Refers to the specific location or site of the biospecimen
+anatomic location,201,Biospecimen Type,llm,HIGH,Anatomic location refers to the specific part of the body from which the biospecimen is taken.
+cell line of origin,195,Biospecimen Type,keyword,HIGH,exact_match: cell
+number of relapses,192,Biospecimen Type,similarity,MEDIUM,Similar to: number of cells (score: 0.788)
+microbiota status,192,Biospecimen Type,llm,MEDIUM,Microbiota status refers to the type of microbiota present in a sample
+sputum_smear,191,Biospecimen Type,llm,HIGH,Sputum smear is a type of biospecimen
+sputum_culture,191,Biospecimen Type,llm,HIGH,Sputum culture is a type of biospecimen
+biopsy type,190,Biospecimen Type,keyword,MEDIUM,keyword: biopsy
+growth,187,Biospecimen Type,llm,MEDIUM,"This label could refer to the type of biospecimen, such as a cell culture or tissue sample, that is growing."
+cell source,181,Biospecimen Type,keyword,HIGH,exact_match: cell
+tissue/cell line,179,Biospecimen Type,keyword,LOW,pattern: .*tissue.*
+preparation,169,Biospecimen Type,similarity,MEDIUM,Similar to: cell preparation (score: 0.815)
+tissue archive method,160,Biospecimen Type,keyword,HIGH,exact_match: tissue
+spike-in cell_line,158,Biospecimen Type,keyword,LOW,pattern: .*cell.*
+spike-in cell_type,158,Biospecimen Type,keyword,LOW,pattern: .*cell.*
+eye,158,Biospecimen Type,llm,HIGH,"Eye refers to the type of biospecimen, which is a characteristic of the sample."
+brain bank,156,Biospecimen Type,llm,HIGH,"Brain bank refers to a collection of brain tissue samples, which is a type of biospecimen."
+tissue origin,155,Biospecimen Type,keyword,HIGH,exact_match: tissue
+blood.source,151,Biospecimen Type,keyword,LOW,pattern: .*blood.*
+clinical diagnosis specimen,150,Biospecimen Type,keyword,MEDIUM,keyword: specimen
+splice variant,150,Biospecimen Type,llm,MEDIUM,"Splice variant is related to the type of biospecimen, specifically the type of RNA or protein produced by alternative splicing."
+"biopsy data, villus height to crypt depth",146,Biospecimen Type,keyword,MEDIUM,keyword: biopsy
+transplant type,145,Biospecimen Type,llm,HIGH,Transplant type is a characteristic of biospecimen type
+cell_line,142,Biospecimen Type,keyword,LOW,pattern: .*cell.*
+Phenotype,141,Biospecimen Type,similarity,MEDIUM,Similar to: cell phenotype (score: 0.783)
+chip target,141,Biospecimen Type,llm,HIGH,The term 'chip target' likely refers to the type of biospecimen used in a microarray experiment.
+bal_culture,140,Biospecimen Type,llm,HIGH,The term 'bal_culture' likely refers to a type of biospecimen culture.
+bal_smear,140,Biospecimen Type,llm,HIGH,The term 'bal_smear' likely refers to a type of biospecimen smear.
+smear of index case,140,Biospecimen Type,llm,HIGH,The term 'smear of index case' likely refers to a type of biospecimen smear.
+tissue notes,138,Biospecimen Type,keyword,HIGH,exact_match: tissue
+cell fraction,134,Biospecimen Type,keyword,HIGH,exact_match: cell
+responder cells,134,Biospecimen Type,keyword,LOW,pattern: .*cell.*
+biopsy site,133,Biospecimen Type,keyword,MEDIUM,keyword: biopsy
+components,133,Biospecimen Type,llm,MEDIUM,"Components could refer to the type of biospecimen, such as cellular components."
+tissue-of-origin,132,Biospecimen Type,keyword,LOW,pattern: .*tissue.*
+fibrinogen,126,Biospecimen Type,llm,HIGH,"Fibrinogen is a type of protein, which could be a biospecimen type."
+target molecule,126,Biospecimen Type,llm,HIGH,"Target molecule could refer to a specific type of biospecimen, such as a protein or gene."
+line type,123,Biospecimen Type,similarity,MEDIUM,Similar to: cell line type (score: 0.783)
+enzyme,120,Biospecimen Type,llm,MEDIUM,Enzyme could refer to a type of biospecimen
+tissue processing,119,Biospecimen Type,keyword,HIGH,exact_match: tissue
+cell part,118,Biospecimen Type,keyword,HIGH,exact_match: cell
+serum type,118,Biospecimen Type,keyword,HIGH,exact_match: serum
+cell culture,116,Biospecimen Type,keyword,HIGH,exact_match: cell
+marrow,116,Biospecimen Type,llm,HIGH,"Marrow is a type of biospecimen, specifically a type of tissue."
+cell line source,112,Biospecimen Type,keyword,HIGH,exact_match: cell
+cell type/line,108,Biospecimen Type,keyword,HIGH,exact_match: cell
+primary tissues,106,Biospecimen Type,keyword,LOW,pattern: .*tissue.*
+variety,105,Biospecimen Type,llm,MEDIUM,Could refer to the type of biospecimen or cell line
+clinical phenotype,103,Biospecimen Type,similarity,MEDIUM,Similar to: cell phenotype (score: 0.812)
+hemisphere,99,Biospecimen Type,llm,HIGH,"Hemisphere refers to a part of the brain, which is a type of biospecimen"
+case_phenotype,97,Biospecimen Type,similarity,MEDIUM,Similar to: cell phenotype (score: 0.786)
+transplanted organ,96,Biospecimen Type,keyword,HIGH,exact_match: organ
+time of blood draw,96,Biospecimen Type,keyword,HIGH,exact_match: blood
+als phenotype,96,Biospecimen Type,similarity,MEDIUM,Similar to: cell phenotype (score: 0.815)
+cell stimulation,95,Biospecimen Type,keyword,HIGH,exact_match: cell
+microglia media,93,Biospecimen Type,llm,MEDIUM,"Microglia media refers to the type of cell culture medium used to grow microglia cells, which is a type of biospecimen."
+lymphocyte.reaction,92,Biospecimen Type,keyword,MEDIUM,keyword: lymphocyte
+sub-population,92,Biospecimen Type,similarity,MEDIUM,Similar to: cell subpopulation (score: 0.812)
+health status,92,Biospecimen Type,similarity,MEDIUM,Similar to: cell status (score: 0.750)
+histological..subtype,92,Biospecimen Type,llm,HIGH,"Histological subtype refers to the specific type of tissue or cell morphology, which is a characteristic of the biospecimen."
+cell state,90,Biospecimen Type,keyword,HIGH,exact_match: cell
+cell compartment,88,Biospecimen Type,keyword,HIGH,exact_match: cell
+bacterial lysate,88,Biospecimen Type,similarity,MEDIUM,Similar to: bacterial cells (score: 0.774)
+cell subpopulation,86,Biospecimen Type,keyword,HIGH,exact_match: cell
+unsorted or sorted,86,Biospecimen Type,llm,MEDIUM,"This label may refer to the type of sample or the level of processing it has undergone, which could be related to the biospecimen type."
+responder,84,Biospecimen Type,similarity,MEDIUM,Similar to: responder cells (score: 0.750)
+input material,84,Biospecimen Type,llm,HIGH,Input material likely refers to the type of biological sample used as the starting material for an experiment.
+tissue compartment,83,Biospecimen Type,keyword,HIGH,exact_match: tissue
+cell line background,82,Biospecimen Type,keyword,HIGH,exact_match: cell
+cell density,81,Biospecimen Type,keyword,HIGH,exact_match: cell
+number of cells,80,Biospecimen Type,keyword,LOW,pattern: .*cell.*
+simulation,80,Biospecimen Type,similarity,MEDIUM,Similar to: cell stimulation (score: 0.769)
+subclass,80,Biospecimen Type,llm,MEDIUM,Subclass might refer to a specific subtype of a biospecimen.
+specimen site,79,Biospecimen Type,keyword,MEDIUM,keyword: specimen
+cell number,78,Biospecimen Type,keyword,HIGH,exact_match: cell
+fracture site,78,Biospecimen Type,llm,HIGH,"A fracture site is a specific type of biospecimen, which fits into the category of Biospecimen Type."
+tissue group,77,Biospecimen Type,keyword,HIGH,exact_match: tissue
+karyotype,77,Biospecimen Type,similarity,MEDIUM,Similar to: cell karyotype (score: 0.783)
+source tissue,76,Biospecimen Type,keyword,HIGH,exact_match: tissue
+immune_or_nasal,76,Biospecimen Type,llm,MEDIUM,"This label seems to describe the type of biospecimen, possibly indicating whether it is from the immune system or nasal passages."
+any_immune,76,Biospecimen Type,llm,MEDIUM,"This label seems to describe the type of biospecimen, possibly indicating whether it is related to the immune system."
+cell lines,75,Biospecimen Type,keyword,HIGH,exact_match: cell
+minimum reads per cell during initial processing,75,Biospecimen Type,keyword,HIGH,exact_match: cell
+Type,73,Biospecimen Type,llm,HIGH,"Type is a general term that can refer to the type of biospecimen, and this label likely refers to the type of sample or material."
+embryo,70,Biospecimen Type,llm,HIGH,Embryo is a type of biospecimen
+anatomical location,70,Biospecimen Type,llm,HIGH,Anatomical location refers to the type of tissue or organ from which the biospecimen is derived
+fetus,70,Biospecimen Type,llm,HIGH,Fetus is a type of biospecimen
+compartment,69,Biospecimen Type,similarity,MEDIUM,Similar to: cell compartment (score: 0.815)
+lesional (ls) vs. normal,69,Biospecimen Type,llm,HIGH,Lesional vs. normal is a type of biospecimen
+Genetic background,69,Biospecimen Type,llm,HIGH,Genetic background is a type of biospecimen
+Histological type,69,Biospecimen Type,llm,HIGH,Histological type is a type of biospecimen
+day blood taken,67,Biospecimen Type,keyword,HIGH,exact_match: blood
+vs type,67,Biospecimen Type,llm,MEDIUM,"This label could be related to the type of biospecimen, but the meaning is not entirely clear without more context."
+tissue status,66,Biospecimen Type,keyword,HIGH,exact_match: tissue
+histological.type,66,Biospecimen Type,llm,HIGH,"This label clearly refers to the type of biospecimen, specifically histological type."
+cell markers,65,Biospecimen Type,keyword,HIGH,exact_match: cell
+lymphocyte_count,64,Biospecimen Type,keyword,MEDIUM,keyword: lymphocyte
+lobe,64,Biospecimen Type,llm,HIGH,"Refers to a specific part of an organ, which is a type of biospecimen"
+cytology,64,Biospecimen Type,llm,HIGH,"Cytology is a branch of biology that studies the structure, function, and chemistry of cells. It is a type of biospecimen."
+source cell type,61,Biospecimen Type,keyword,HIGH,exact_match: cell
+aspiration site,61,Biospecimen Type,llm,MEDIUM,"Aspiration site could be related to the type of biospecimen collected, such as a tissue or fluid sample."
+tissue/cell info,60,Biospecimen Type,keyword,LOW,pattern: .*tissue.*
+vector constructs,60,Biospecimen Type,llm,HIGH,Vector constructs are a type of biospecimen used in molecular biology.
+sorted cell_type,59,Biospecimen Type,keyword,LOW,pattern: .*cell.*
+sandwich type,59,Biospecimen Type,llm,HIGH,"This label likely refers to the type of biospecimen or sample used in an experiment, such as a sandwich ELISA."
+cells detected,58,Biospecimen Type,keyword,LOW,pattern: .*cell.*
+tissue derivation,58,Biospecimen Type,keyword,HIGH,exact_match: tissue
+types,58,Biospecimen Type,llm,HIGH,"The label 'types' is a synonym for 'sample type' or 'specimen type', which fits well within the Biospecimen Type category."
+modifications,57,Biospecimen Type,llm,MEDIUM,"Modifications could refer to changes made to the biospecimen, which might relate to its type or characteristics."
+library-type,57,Biospecimen Type,llm,HIGH,"Library-type is a specific characteristic of the biospecimen, likely referring to the type of library prepared from the sample."
+data tissue_collection,56,Biospecimen Type,keyword,LOW,pattern: .*tissue.*
+tissue collection,56,Biospecimen Type,keyword,HIGH,exact_match: tissue
+lymph node number,56,Biospecimen Type,llm,MEDIUM,This could be a characteristic of a biospecimen
+parental line,55,Biospecimen Type,similarity,MEDIUM,Similar to: parental cell line (score: 0.839)
+upper or lower extremity,55,Biospecimen Type,llm,HIGH,Refers to the type of tissue or anatomical site from which the biospecimen is derived.
+growth pattern,55,Biospecimen Type,llm,HIGH,Describes the type of cellular growth or tissue morphology.
+volar or non-volar,55,Biospecimen Type,llm,HIGH,Refers to the specific anatomical location or type of tissue from which the biospecimen is derived.
+age at blood collection,54,Biospecimen Type,keyword,HIGH,exact_match: blood
+organ system,54,Biospecimen Type,keyword,HIGH,exact_match: organ
+FISH origin,53,Biospecimen Type,similarity,MEDIUM,Similar to: tissue origin (score: 0.750)
+isolation method,52,Biospecimen Type,llm,MEDIUM,"Isolation method could be related to the type of biospecimen, such as cell isolation or tissue isolation."
+day of tissue harvest,51,Biospecimen Type,keyword,HIGH,exact_match: tissue
+specific heart region,51,Biospecimen Type,llm,HIGH,"Specific heart region indicates the type or source of the biospecimen, fitting the definition of Biospecimen Type."
+lymph node,51,Biospecimen Type,llm,HIGH,"Lymph node specifies the type or source of the biospecimen, fitting the definition of Biospecimen Type."
+parental cell line,49,Biospecimen Type,keyword,HIGH,exact_match: cell
+other organ lesion,49,Biospecimen Type,keyword,HIGH,exact_match: organ
+stem cell,48,Biospecimen Type,keyword,HIGH,exact_match: cell
+cell surface marker,47,Biospecimen Type,keyword,HIGH,exact_match: cell
+graft source,47,Biospecimen Type,llm,HIGH,"Graft source refers to the origin or type of biological material used for grafting, which is a characteristic of the biospecimen type."
+developmental stage/tissue,46,Biospecimen Type,keyword,LOW,pattern: .*tissue.*
+lymphocytes_count,46,Biospecimen Type,keyword,MEDIUM,keyword: lymphocyte
+monocytes_count,46,Biospecimen Type,keyword,MEDIUM,keyword: monocyte
+surface marker,46,Biospecimen Type,similarity,MEDIUM,Similar to: cell surface marker (score: 0.848)
+derived from,46,Biospecimen Type,llm,HIGH,"Derived from refers to the origin or source of a biospecimen, which is a characteristic of the biospecimen type."
+BREAST,46,Biospecimen Type,llm,HIGH,BREAST refers to a type of tissue or organ
+tissue acquisition,45,Biospecimen Type,keyword,HIGH,exact_match: tissue
+cell surface markers,45,Biospecimen Type,keyword,HIGH,exact_match: cell
+type of library,45,Biospecimen Type,llm,HIGH,"Type of library refers to the type of biospecimen, in this case, a library of biological samples."
+cell/tissue type,44,Biospecimen Type,keyword,LOW,pattern: .*tissue.*
+Tissue Factor,43,Biospecimen Type,keyword,HIGH,exact_match: tissue
+fusion,41,Biospecimen Type,llm,MEDIUM,"This label could refer to a type of biospecimen, such as a fusion of different cell types."
+percentage of tumor cells,40,Biospecimen Type,keyword,LOW,pattern: .*cell.*
+source cell,40,Biospecimen Type,keyword,HIGH,exact_match: cell
+hemolysis score,40,Biospecimen Type,llm,MEDIUM,"This label could refer to a characteristic of the biospecimen, such as the degree of hemolysis."
+age at biopsy date,39,Biospecimen Type,keyword,MEDIUM,keyword: biopsy
+autopsy,39,Biospecimen Type,llm,HIGH,"Autopsy is a procedure for obtaining biospecimens, so it fits well with the Biospecimen Type category."
+cells_loaded,38,Biospecimen Type,keyword,LOW,pattern: .*cell.*
+resection,38,Biospecimen Type,llm,HIGH,"Resection is a procedure for obtaining biospecimens, so it fits well with the Biospecimen Type category."
+construct,38,Biospecimen Type,llm,MEDIUM,"Construct can refer to a type of biospecimen, such as a recombinant DNA construct."
+Cell type,37,Biospecimen Type,keyword,HIGH,exact_match: cell
+mating type,37,Biospecimen Type,llm,HIGH,"Mating type is a characteristic of biological samples, particularly in the context of cell lines or organisms, which fits well within the Biospecimen Type category."
+organ obtained,36,Biospecimen Type,keyword,HIGH,exact_match: organ
+primary cells,36,Biospecimen Type,keyword,LOW,pattern: .*cell.*
+location type,36,Biospecimen Type,llm,MEDIUM,"Location type could refer to the type of tissue or organ from which a biological sample is derived, which fits within the Biospecimen Type category."
+skin anatomy,36,Biospecimen Type,llm,HIGH,"This label refers to the type of tissue or anatomical location of the sample, which is a characteristic of the sample."
+Age at interview & blood sampling,35,Biospecimen Type,keyword,HIGH,exact_match: blood
+biopsy vs surgical resection,35,Biospecimen Type,keyword,MEDIUM,keyword: biopsy
+pulldown,35,Biospecimen Type,llm,HIGH,"Pulldown is a laboratory technique used to isolate specific proteins or nucleic acids from a sample, suggesting it is a type of biospecimen."
+Tissue type,34,Biospecimen Type,keyword,HIGH,exact_match: tissue
+cell tye,34,Biospecimen Type,keyword,HIGH,exact_match: cell
+treated stem cells,34,Biospecimen Type,keyword,MEDIUM,keyword: stem cell
+body site,34,Biospecimen Type,similarity,MEDIUM,Similar to: biopsy site (score: 0.800)
+cell treatment,33,Biospecimen Type,keyword,HIGH,exact_match: cell
+clinical phenotypes,33,Biospecimen Type,similarity,MEDIUM,Similar to: cell phenotype (score: 0.788)
+cell line name,31,Biospecimen Type,keyword,HIGH,exact_match: cell
+Cell line,31,Biospecimen Type,keyword,HIGH,exact_match: cell
+Medication at blood sampling,30,Biospecimen Type,keyword,HIGH,exact_match: blood
+cell culture condition,30,Biospecimen Type,keyword,HIGH,exact_match: cell
+cell-type,30,Biospecimen Type,keyword,LOW,pattern: .*cell.*
+derived cell line,30,Biospecimen Type,keyword,HIGH,exact_match: cell
+source cell line,30,Biospecimen Type,keyword,HIGH,exact_match: cell
+age at skin biopsy,30,Biospecimen Type,keyword,MEDIUM,keyword: biopsy
+tumor tissue source,30,Biospecimen Type,keyword,HIGH,exact_match: tissue
+cell passage,30,Biospecimen Type,keyword,HIGH,exact_match: cell
+tumor organ site,30,Biospecimen Type,keyword,HIGH,exact_match: organ
+cell line/type,30,Biospecimen Type,keyword,HIGH,exact_match: cell
+phenotypes,30,Biospecimen Type,similarity,MEDIUM,Similar to: cell phenotype (score: 0.750)
+knock-in line,30,Biospecimen Type,llm,HIGH,knock-in line refers to a type of genetically modified cell line
+brain section,30,Biospecimen Type,llm,HIGH,brain section refers to a type of tissue sample
+knockout status,30,Biospecimen Type,llm,HIGH,knockout status refers to a type of genetically modified cell line
+cell cycle stage,29,Biospecimen Type,keyword,HIGH,exact_match: cell
+tumor cell line,29,Biospecimen Type,keyword,HIGH,exact_match: cell
+lymphocytes,29,Biospecimen Type,keyword,MEDIUM,keyword: lymphocyte
+mitotic activity,29,Biospecimen Type,llm,HIGH,"Mitotic activity is a characteristic of cells, which is a type of biospecimen."
+derived from metastatic site,29,Biospecimen Type,llm,HIGH,"This label describes the origin of the biospecimen, which is a characteristic of its type."
+kit expression,29,Biospecimen Type,llm,HIGH,"Kit expression is a characteristic of cells, which is a type of biospecimen."
+biopsy collection date,28,Biospecimen Type,keyword,MEDIUM,keyword: biopsy
+bone marrow mononuclear cells sorted from,28,Biospecimen Type,keyword,LOW,pattern: .*cell.*
+additional cell lineages present in dataset,27,Biospecimen Type,keyword,HIGH,exact_match: cell
+cell type source,27,Biospecimen Type,keyword,HIGH,exact_match: cell
+cell stage,27,Biospecimen Type,keyword,HIGH,exact_match: cell
+tissues,27,Biospecimen Type,keyword,LOW,pattern: .*tissue.*
+pulmonary compartment,27,Biospecimen Type,llm,HIGH,Refers to a specific type of biological sample or tissue
+sampling location,27,Biospecimen Type,llm,HIGH,"Sampling location is related to the type of biospecimen, such as tissue or cell type."
+primary cell line,26,Biospecimen Type,keyword,HIGH,exact_match: cell
+clone phenotype,26,Biospecimen Type,similarity,MEDIUM,Similar to: cell phenotype (score: 0.828)
+Body surface area,26,Biospecimen Type,llm,MEDIUM,"Body surface area could refer to the type of biospecimen, such as skin or tissue type."
+twin status,25,Biospecimen Type,similarity,MEDIUM,Similar to: tissue status (score: 0.750)
+body part,25,Biospecimen Type,llm,HIGH,Body part refers to the type of tissue or organ from which the biospecimen is derived
+tissue subgroup,24,Biospecimen Type,keyword,HIGH,exact_match: tissue
+cell line/tissue,24,Biospecimen Type,keyword,HIGH,exact_match: cell
+cell line/tissue source,24,Biospecimen Type,keyword,HIGH,exact_match: cell
+monocyte,24,Biospecimen Type,keyword,MEDIUM,keyword: monocyte
+sorted cell type,24,Biospecimen Type,keyword,HIGH,exact_match: cell
+lymphocyte,24,Biospecimen Type,keyword,MEDIUM,keyword: lymphocyte
+cell or tissue type,24,Biospecimen Type,keyword,HIGH,exact_match: tissue
+starting cell,24,Biospecimen Type,keyword,HIGH,exact_match: cell
+blood island injection,24,Biospecimen Type,keyword,HIGH,exact_match: blood
+cell preparation,24,Biospecimen Type,keyword,HIGH,exact_match: cell
+anatomical site,24,Biospecimen Type,llm,HIGH,Anatomical site refers to the specific location in the body from which the biospecimen is derived
+resection_type,24,Biospecimen Type,llm,HIGH,"This label refers to the type of surgical removal of a biospecimen, which fits into the Biospecimen Type category."
+morphologic form,24,Biospecimen Type,llm,HIGH,"This label refers to the shape or structure of a biospecimen, which fits into the Biospecimen Type category."
+spinal cord region,24,Biospecimen Type,llm,HIGH,"This label refers to a specific part of the spinal cord, which fits into the Biospecimen Type category as it describes the type of biospecimen."
+Construct,24,Biospecimen Type,llm,HIGH,"This label refers to a specific type of biospecimen, such as a cell line or tissue sample, which fits into the Biospecimen Type category."
+extract,24,Biospecimen Type,llm,HIGH,"This label refers to a type of biospecimen that has been extracted from a larger sample, which fits into the Biospecimen Type category."
+exogenous gene expressed,24,Biospecimen Type,llm,HIGH,"This label indicates the type of gene expressed in the biospecimen, which is a characteristic of the biospecimen."
+cell dissociation,23,Biospecimen Type,keyword,HIGH,exact_match: cell
+peripheral blood,23,Biospecimen Type,keyword,HIGH,exact_match: blood
+molecule source,23,Biospecimen Type,llm,HIGH,"This label indicates the type of molecule or biospecimen, which is a characteristic of the biospecimen."
+cells/condition,22,Biospecimen Type,keyword,LOW,pattern: .*cell.*
+generation,22,Biospecimen Type,llm,MEDIUM,"Generation could refer to the type of cellular molecule, cell, or tissue."
+Karyotype,21,Biospecimen Type,similarity,MEDIUM,Similar to: cell karyotype (score: 0.783)
+generation/colony,21,Biospecimen Type,llm,MEDIUM,"Generation/colony could refer to the type of cellular molecule, cell, or tissue."
+electrophysiology,21,Biospecimen Type,llm,HIGH,Electrophysiology is a type of biospecimen or sample type
+cell transduction,20,Biospecimen Type,keyword,HIGH,exact_match: cell
+cell marker,20,Biospecimen Type,keyword,HIGH,exact_match: cell
+enrichment,20,Biospecimen Type,similarity,MEDIUM,Similar to: cell enrichment (score: 0.800)
+lot number,20,Biospecimen Type,similarity,MEDIUM,Similar to: cell number (score: 0.762)
+glioma model,20,Biospecimen Type,llm,HIGH,glioma model is a type of biospecimen or sample
+fus aggregation state,19,Biospecimen Type,llm,MEDIUM,"Fus aggregation state could refer to the physical state of a biospecimen, such as its aggregation or dispersion."
+sort purification strategy,19,Biospecimen Type,llm,HIGH,Sort purification strategy refers to the method used to isolate or purify a specific type of biospecimen.
+cellular_component,18,Biospecimen Type,keyword,LOW,pattern: .*cell.*
+tissue location,18,Biospecimen Type,keyword,HIGH,exact_match: tissue
+protein expression,18,Biospecimen Type,llm,MEDIUM,"Protein expression could refer to the type of biospecimen, such as a protein or a cell line expressing a specific protein."
+menstrual phase,18,Biospecimen Type,llm,MEDIUM,"Menstrual phase could be a characteristic of the biospecimen type, such as a specific type of tissue or cell"
+cell type origin,17,Biospecimen Type,keyword,HIGH,exact_match: cell
+protein,17,Biospecimen Type,llm,HIGH,Protein is a type of biospecimen
+clip antibody,17,Biospecimen Type,llm,HIGH,Clip antibody is a type of biospecimen
+viral,17,Biospecimen Type,llm,HIGH,Viral is a type of biospecimen
+composite,17,Biospecimen Type,llm,HIGH,Composite is a type of biospecimen
+cell status,16,Biospecimen Type,keyword,HIGH,exact_match: cell
+serum,16,Biospecimen Type,keyword,HIGH,exact_match: serum
+osteogenic potential,16,Biospecimen Type,llm,MEDIUM,"The label refers to a specific characteristic of a biospecimen, osteogenic potential, which is related to its type or properties."
+aortic valve,16,Biospecimen Type,llm,HIGH,"Aortic valve is a specific type of tissue or organ, which fits into the Biospecimen Type category."
+adipogenic potential,16,Biospecimen Type,llm,MEDIUM,"Adipogenic potential refers to the ability of cells to differentiate into adipocytes, which could be related to the type of biospecimen."
+lung section/portion,16,Biospecimen Type,llm,HIGH,"Lung section/portion is a specific type of tissue or organ, which fits into the Biospecimen Type category."
+cytogenetic,16,Biospecimen Type,llm,HIGH,"Cytogenetic refers to the study of chromosomes and their abnormalities, which is a characteristic of a biospecimen type."
+sorted fraction,16,Biospecimen Type,llm,HIGH,Sorted fraction refers to a specific type of biospecimen that has been sorted or separated based on certain characteristics.
+cell line_name,15,Biospecimen Type,keyword,HIGH,exact_match: cell
+cell_origin,15,Biospecimen Type,keyword,LOW,pattern: .*cell.*
+tissue class,15,Biospecimen Type,keyword,HIGH,exact_match: tissue
+surface markers,15,Biospecimen Type,similarity,MEDIUM,Similar to: cell surface markers (score: 0.857)
+es line,15,Biospecimen Type,similarity,MEDIUM,Similar to: cell line (score: 0.750)
+precursor,15,Biospecimen Type,llm,MEDIUM,Could refer to a type of biospecimen or cell line
+cell origin,14,Biospecimen Type,keyword,HIGH,exact_match: cell
+age at blood draw,14,Biospecimen Type,keyword,HIGH,exact_match: blood
+original cell line,14,Biospecimen Type,keyword,HIGH,exact_match: cell
+genotype abbreviation,14,Biospecimen Type,llm,HIGH,"Genotype abbreviation is related to the type of biospecimen, specifically the genetic makeup of the sample."
+sorting profile,14,Biospecimen Type,llm,HIGH,"Sorting profile is related to the type of biospecimen, specifically the characteristics of the cells or molecules being sorted."
+cell lining,13,Biospecimen Type,keyword,HIGH,exact_match: cell
+receptor expression,13,Biospecimen Type,llm,HIGH,"Receptor expression is a characteristic of a biospecimen, specifically a type of molecular feature."
+material type,13,Biospecimen Type,llm,HIGH,"Material type is a synonym for biospecimen type, referring to the type of material sample taken."
+cag repeat,13,Biospecimen Type,llm,HIGH,"Cag repeat is a characteristic of a biospecimen, specifically a type of genetic feature."
+serology,13,Biospecimen Type,llm,HIGH,"Serology is a characteristic of a biospecimen, specifically a type of immunological feature."
+growth phase of cells,12,Biospecimen Type,keyword,LOW,pattern: .*cell.*
+Tumor tissue,12,Biospecimen Type,keyword,HIGH,exact_match: tissue
+brain tissue,12,Biospecimen Type,keyword,HIGH,exact_match: tissue
+cell type background,12,Biospecimen Type,keyword,HIGH,exact_match: cell
+age at biopsy,12,Biospecimen Type,keyword,MEDIUM,keyword: biopsy
+cell line type,12,Biospecimen Type,keyword,HIGH,exact_match: cell
+isolation of tumor cells,12,Biospecimen Type,keyword,LOW,pattern: .*cell.*
+primary cell type,12,Biospecimen Type,keyword,HIGH,exact_match: cell
+cell line origin,12,Biospecimen Type,keyword,HIGH,exact_match: cell
+tumor cell type,12,Biospecimen Type,keyword,HIGH,exact_match: cell
+maturation to macrophage,12,Biospecimen Type,keyword,MEDIUM,keyword: macrophage
+melanoma cell type,12,Biospecimen Type,keyword,HIGH,exact_match: cell
+histological findings of renal specimen,12,Biospecimen Type,keyword,MEDIUM,keyword: specimen
+renal biopsy,12,Biospecimen Type,keyword,MEDIUM,keyword: biopsy
+name of tissue,12,Biospecimen Type,keyword,HIGH,exact_match: tissue
+cell line passage,12,Biospecimen Type,keyword,HIGH,exact_match: cell
+blood pressure,12,Biospecimen Type,keyword,HIGH,exact_match: blood
+clone name,12,Biospecimen Type,similarity,MEDIUM,Similar to: cell line name (score: 0.750)
+efflux status,12,Biospecimen Type,similarity,MEDIUM,Similar to: cell status (score: 0.750)
+source muscle,12,Biospecimen Type,similarity,MEDIUM,Similar to: source cell (score: 0.750)
+fold enrichment,12,Biospecimen Type,similarity,MEDIUM,Similar to: cell enrichment (score: 0.800)
+sediment,12,Biospecimen Type,similarity,MEDIUM,Similar to: specimen (score: 0.750)
+density gradient region,12,Biospecimen Type,llm,HIGH,Density gradient region is a type of sample or biospecimen.
+pluripotent,12,Biospecimen Type,llm,HIGH,"Pluripotent refers to the ability of a cell to develop into multiple cell types, which is a characteristic of a biospecimen type."
+MASTECTOMY,12,Biospecimen Type,llm,HIGH,"Mastectomy is a surgical procedure that involves the removal of breast tissue, which is a type of biospecimen."
+total/partial resection,12,Biospecimen Type,llm,HIGH,"Total/partial resection refers to the extent of tissue removal during a surgical procedure, which is a characteristic of a biospecimen type."
+model type,12,Biospecimen Type,llm,HIGH,"Model type refers to the type of biological model used, such as a cell line or animal model, which is a characteristic of a biospecimen type."
+type of cultivation plate,12,Biospecimen Type,llm,MEDIUM,This label could be related to the type of sample or material used in the experiment
+area/tissue,11,Biospecimen Type,keyword,LOW,pattern: .*tissue.*
+urine protein,11,Biospecimen Type,llm,HIGH,Urine protein is a type of biospecimen
+embryos pooled,11,Biospecimen Type,llm,HIGH,Embryos pooled is a type of biospecimen
+cell line for infection,10,Biospecimen Type,keyword,HIGH,exact_match: cell
+injected cell line,10,Biospecimen Type,keyword,HIGH,exact_match: cell
+initial preparation,10,Biospecimen Type,similarity,MEDIUM,Similar to: tissue preparation (score: 0.757)
+anatomic site,10,Biospecimen Type,similarity,MEDIUM,Similar to: tissue anatomic site (score: 0.788)
+lung section,10,Biospecimen Type,llm,HIGH,"Refers to a specific type of biospecimen, in this case, a section of lung tissue."
+cell-subtype,9,Biospecimen Type,keyword,LOW,pattern: .*cell.*
+parental cell type,9,Biospecimen Type,keyword,HIGH,exact_match: cell
+derived culture,9,Biospecimen Type,similarity,MEDIUM,Similar to: derived cell_type (score: 0.750)
+genotype background,9,Biospecimen Type,similarity,MEDIUM,Similar to: cell type background (score: 0.821)
+subpopulation,9,Biospecimen Type,similarity,MEDIUM,Similar to: cell subpopulation (score: 0.839)
+anatomical region,9,Biospecimen Type,llm,HIGH,"This label refers to the type of biospecimen, specifically the anatomical region from which it was taken."
+neuroblastoma cell line,8,Biospecimen Type,keyword,HIGH,exact_match: cell
+derived cell_type,8,Biospecimen Type,keyword,LOW,pattern: .*cell.*
+cell number per well,8,Biospecimen Type,keyword,HIGH,exact_match: cell
+macrophages,8,Biospecimen Type,keyword,MEDIUM,keyword: macrophage
+microglia population,8,Biospecimen Type,llm,HIGH,"Microglia population refers to a specific type of cell or cellular component, which is a characteristic of the biospecimen."
+fus variant,8,Biospecimen Type,llm,HIGH,"Fus variant refers to a specific type of genetic variant or mutation, which is a characteristic of the biospecimen."
+portion of branchial arch,8,Biospecimen Type,llm,HIGH,Portion of branchial arch refers to a specific type of biospecimen or tissue.
+anatomic segment,8,Biospecimen Type,llm,HIGH,Anatomic segment refers to a specific type of biospecimen or tissue.
+allele,8,Biospecimen Type,llm,MEDIUM,"An allele is a variant of a gene, which could be considered a type of biospecimen."
+cell type depletion,7,Biospecimen Type,keyword,HIGH,exact_match: cell
+cell type implantation,7,Biospecimen Type,keyword,HIGH,exact_match: cell
+neural crest-derived,7,Biospecimen Type,llm,MEDIUM,"This label describes the origin of the biospecimen, which could be considered a type of biospecimen."
+sorted subset of cells,6,Biospecimen Type,keyword,LOW,pattern: .*cell.*
+cell subsets,6,Biospecimen Type,keyword,HIGH,exact_match: cell
+sorted cell,6,Biospecimen Type,keyword,HIGH,exact_match: cell
+derived cell type,6,Biospecimen Type,keyword,HIGH,exact_match: cell
+cell morphology,6,Biospecimen Type,keyword,HIGH,exact_match: cell
+stem cell clone,6,Biospecimen Type,keyword,HIGH,exact_match: cell
+tissue storage,6,Biospecimen Type,keyword,HIGH,exact_match: tissue
+cell phase,6,Biospecimen Type,keyword,HIGH,exact_match: cell
+tic class,6,Biospecimen Type,similarity,MEDIUM,Similar to: tissue class (score: 0.762)
+molecule subtypes,6,Biospecimen Type,llm,HIGH,Molecule subtypes are a type of biospecimen
+hairpin,6,Biospecimen Type,llm,HIGH,"Hairpin is a type of RNA structure, which is a biospecimen"
+biopsy position,5,Biospecimen Type,keyword,MEDIUM,keyword: biopsy
+tissue type type,5,Biospecimen Type,keyword,HIGH,exact_match: tissue
+cell line_infection,5,Biospecimen Type,keyword,HIGH,exact_match: cell
+pull-down,5,Biospecimen Type,llm,MEDIUM,Pull-down is a laboratory technique that could be related to the type of biospecimen or sample preparation.
+cytogenetics,5,Biospecimen Type,llm,MEDIUM,"Cytogenetics is the study of chromosomes and their abnormalities, which could be related to the type of biospecimen or sample preparation."
+marker,5,Biospecimen Type,llm,MEDIUM,"Marker could refer to a type of biospecimen, such as a biomarker"
+cell enrichment,4,Biospecimen Type,keyword,HIGH,exact_match: cell
+Cells,4,Biospecimen Type,keyword,LOW,pattern: .*cell.*
+blood,4,Biospecimen Type,keyword,HIGH,exact_match: blood
+source organ,4,Biospecimen Type,keyword,HIGH,exact_match: organ
+tissue zone,4,Biospecimen Type,keyword,HIGH,exact_match: tissue
+number of_tracheas,4,Biospecimen Type,llm,HIGH,"Number of tracheas is a characteristic of a biospecimen type, such as a tissue sample"
+knock-in,4,Biospecimen Type,llm,HIGH,"This label describes a type of genetic modification, which is a characteristic of the biospecimen."
+bacterial cells,3,Biospecimen Type,keyword,LOW,pattern: .*cell.*
+tissue extraction,3,Biospecimen Type,keyword,HIGH,exact_match: tissue
+skin score at biopsy site,3,Biospecimen Type,keyword,MEDIUM,keyword: biopsy
+non-small cell lung cancer Derived from metastatic site,3,Biospecimen Type,keyword,HIGH,exact_match: cell
+Organ,3,Biospecimen Type,keyword,HIGH,exact_match: organ
+bacteria tissue,3,Biospecimen Type,keyword,HIGH,exact_match: tissue
+large cell lung cancer Derived from metastatic site,3,Biospecimen Type,keyword,HIGH,exact_match: cell
+cell subpopulation/marker,3,Biospecimen Type,keyword,HIGH,exact_match: cell
+cell characterization,3,Biospecimen Type,keyword,HIGH,exact_match: cell
+Morphology,3,Biospecimen Type,similarity,MEDIUM,Similar to: cell morphology (score: 0.800)
+embryo characteristic,3,Biospecimen Type,llm,HIGH,"This label describes a type of biospecimen, which is a characteristic of the biospecimen."
+immortalization method,3,Biospecimen Type,llm,HIGH,"This label describes a method used to create an immortalized cell line, which is a characteristic of the biospecimen."
+source cells,2,Biospecimen Type,keyword,LOW,pattern: .*cell.*
+cell line source gender,2,Biospecimen Type,keyword,HIGH,exact_match: cell
+cell mixing ratio,2,Biospecimen Type,keyword,HIGH,exact_match: cell
+"BRAIN (CEREBELLUM), BIOPSY",2,Biospecimen Type,keyword,MEDIUM,keyword: biopsy
+cell line source age,2,Biospecimen Type,keyword,HIGH,exact_match: cell
+cell line source tissue,2,Biospecimen Type,keyword,HIGH,exact_match: tissue
+cell mixture,2,Biospecimen Type,keyword,HIGH,exact_match: cell
+OVARY,2,Biospecimen Type,llm,HIGH,"OVARY is a specific type of tissue or organ, making it a good fit for the Biospecimen Type category."
+AXILLARY NODE,2,Biospecimen Type,llm,HIGH,"AXILLARY NODE is a specific type of tissue or anatomical location, making it a good fit for the Biospecimen Type category."
+"BREAST, LOCAL EXCISION",2,Biospecimen Type,llm,HIGH,"This label refers to a specific type of surgical procedure, which is a characteristic of the biospecimen."
+PARTIAL MASTECTOMY,2,Biospecimen Type,llm,HIGH,"Similar to BREAST, LOCAL EXCISION, this label refers to a specific type of surgical procedure, which is a characteristic of the biospecimen."
+COMPLETION MASTECTOMY,2,Biospecimen Type,llm,HIGH,"This label also refers to a specific type of surgical procedure, which is a characteristic of the biospecimen."
+SENTINEL AXILLARY LYMPH NODE,2,Biospecimen Type,llm,HIGH,"This label refers to a specific type of biospecimen, which is a characteristic of the sample."
+"BREAST, MASTECTOMY",2,Biospecimen Type,llm,HIGH,"BREAST, MASTECTOMY describes the type of biospecimen"
+small cell lung cancer Derived from metastatic site,1,Biospecimen Type,keyword,HIGH,exact_match: cell
+cell lie,1,Biospecimen Type,keyword,HIGH,exact_match: cell
+injected cells,1,Biospecimen Type,keyword,LOW,pattern: .*cell.*
+small molecule,1,Biospecimen Type,llm,MEDIUM,"This label could refer to a type of biospecimen, such as a small molecule sample, but it's not entirely clear without more context."
+sample type,10037,External_sample_id,keyword,MEDIUM,keyword: sample
+batch,9770,External_sample_id,similarity,MEDIUM,Similar to: batch id (score: 0.769)
+patient id,8310,External_sample_id,keyword,HIGH,exact_match: patient id
+individual,8008,External_sample_id,keyword,MEDIUM,keyword: id
+subject id,6726,External_sample_id,keyword,HIGH,exact_match: subject id
+replicate,5824,External_sample_id,similarity,MEDIUM,Similar to: replicate id (score: 0.857)
+donor,5515,External_sample_id,keyword,MEDIUM,keyword: donor
+subject,5499,External_sample_id,keyword,MEDIUM,keyword: subject
+patient,4121,External_sample_id,keyword,MEDIUM,keyword: patient
+plate,3492,External_sample_id,similarity,MEDIUM,Similar to: plate id (score: 0.769)
+subject status,3306,External_sample_id,keyword,MEDIUM,keyword: subject
+sample id,2694,External_sample_id,keyword,HIGH,exact_match: sample id
+subjectid,2672,External_sample_id,keyword,MEDIUM,keyword: id
+site,2620,External_sample_id,similarity,MEDIUM,Similar to: side (score: 0.750)
+sample,2422,External_sample_id,keyword,MEDIUM,keyword: sample
+location,2284,External_sample_id,similarity,MEDIUM,Similar to: location/side (score: 0.762)
+sample group,2179,External_sample_id,keyword,MEDIUM,keyword: sample
+mouse id,1755,External_sample_id,keyword,MEDIUM,keyword: id
+donor id,1737,External_sample_id,keyword,HIGH,exact_match: donor id
+slide no,1700,External_sample_id,keyword,MEDIUM,keyword: id
+source,1670,External_sample_id,similarity,MEDIUM,Similar to: source id (score: 0.800)
+participant id,1666,External_sample_id,keyword,MEDIUM,keyword: id
+controlid,1655,External_sample_id,keyword,MEDIUM,keyword: id
+donor_id,1361,External_sample_id,keyword,HIGH,exact_match: donor_id
+animal,1261,External_sample_id,similarity,MEDIUM,Similar to: animal id (score: 0.800)
+patientid,1239,External_sample_id,keyword,MEDIUM,keyword: patient
+batch id,1213,External_sample_id,keyword,MEDIUM,keyword: id
+individual id,1208,External_sample_id,keyword,MEDIUM,keyword: id
+barcode,1156,External_sample_id,keyword,MEDIUM,keyword: barcode
+patient_id,1152,External_sample_id,keyword,HIGH,exact_match: patient_id
+animal id,1019,External_sample_id,keyword,MEDIUM,keyword: id
+patient diagnosis,1001,External_sample_id,keyword,MEDIUM,keyword: patient
+provider,1000,External_sample_id,keyword,MEDIUM,keyword: id
+enrollment batch,1000,External_sample_id,llm,MEDIUM,"Enrollment batch could refer to a group of patients or samples, but it is not a clear fit for any category."
+patient gender,977,External_sample_id,keyword,MEDIUM,keyword: patient
+clone,871,External_sample_id,similarity,MEDIUM,Similar to: clone id (score: 0.769)
+cell line id,847,External_sample_id,keyword,MEDIUM,keyword: id
+sampleID,841,External_sample_id,keyword,MEDIUM,keyword: id
+donor_age,835,External_sample_id,keyword,MEDIUM,keyword: donor
+donor_sex,835,External_sample_id,keyword,MEDIUM,keyword: donor
+donor_health_status,835,External_sample_id,keyword,MEDIUM,keyword: donor
+donor_ethnicity,835,External_sample_id,keyword,MEDIUM,keyword: donor
+participant,742,External_sample_id,keyword,MEDIUM,keyword: participant
+study,741,External_sample_id,similarity,MEDIUM,Similar to: studyid (score: 0.833)
+patient viral load,726,External_sample_id,keyword,MEDIUM,keyword: patient
+patient group,721,External_sample_id,keyword,MEDIUM,keyword: patient
+sample source,708,External_sample_id,keyword,MEDIUM,keyword: sample
+chip_antibody_provider,708,External_sample_id,keyword,MEDIUM,keyword: id
+sample alias,707,External_sample_id,keyword,MEDIUM,keyword: sample
+sample common name,707,External_sample_id,keyword,MEDIUM,keyword: sample
+chip_antibody_lot,696,External_sample_id,similarity,MEDIUM,Similar to: chip_antibody_provider (score: 0.769)
+sample collection site,652,External_sample_id,keyword,MEDIUM,keyword: sample
+patient sample id,610,External_sample_id,keyword,MEDIUM,keyword: patient
+sample.id,597,External_sample_id,keyword,MEDIUM,keyword: id
+patient age,597,External_sample_id,keyword,MEDIUM,keyword: patient
+ID,584,External_sample_id,keyword,MEDIUM,keyword: id
+covid_status,538,External_sample_id,keyword,MEDIUM,keyword: id
+slide,522,External_sample_id,keyword,MEDIUM,keyword: id
+donor age,518,External_sample_id,keyword,MEDIUM,keyword: donor
+sample_code,503,External_sample_id,keyword,MEDIUM,keyword: sample
+volunteer id,500,External_sample_id,keyword,MEDIUM,keyword: id
+blood sample id,500,External_sample_id,keyword,MEDIUM,keyword: id
+plate id,500,External_sample_id,keyword,MEDIUM,keyword: id
+patient_asymptomatic,500,External_sample_id,keyword,MEDIUM,keyword: patient
+blood sample_id,500,External_sample_id,keyword,HIGH,exact_match: sample_id
+in_covid_only_dataset,500,External_sample_id,keyword,MEDIUM,keyword: id
+external_donor_name,500,External_sample_id,keyword,MEDIUM,keyword: donor
+cosmic id,500,External_sample_id,keyword,MEDIUM,keyword: id
+patient classification_at_first_sample,500,External_sample_id,keyword,MEDIUM,keyword: patient
+days since_first_sample,500,External_sample_id,keyword,MEDIUM,keyword: sample
+external id,500,External_sample_id,keyword,MEDIUM,keyword: id
+days since first sample,500,External_sample_id,keyword,MEDIUM,keyword: sample
+sample id alt,500,External_sample_id,keyword,MEDIUM,keyword: id
+patient classification at first sample,500,External_sample_id,keyword,MEDIUM,keyword: patient
+sample class,500,External_sample_id,keyword,MEDIUM,keyword: sample
+patient category,500,External_sample_id,keyword,MEDIUM,keyword: patient
+vendor id,500,External_sample_id,keyword,MEDIUM,keyword: id
+platform_id_id design,500,External_sample_id,keyword,MEDIUM,keyword: id
+sample_name,500,External_sample_id,keyword,MEDIUM,keyword: sample
+slide_position,492,External_sample_id,keyword,MEDIUM,keyword: id
+code,473,External_sample_id,llm,MEDIUM,Could be an internal ID for patients
+sample name,470,External_sample_id,keyword,MEDIUM,keyword: sample
+sample timing,455,External_sample_id,keyword,MEDIUM,keyword: sample
+covid cat,455,External_sample_id,keyword,MEDIUM,keyword: id
+covid,455,External_sample_id,keyword,MEDIUM,keyword: id
+vital status,450,External_sample_id,similarity,MEDIUM,Similar to: covid status (score: 0.750)
+subject_id,442,External_sample_id,keyword,HIGH,exact_match: subject_id
+sample material,438,External_sample_id,keyword,MEDIUM,keyword: sample
+sample collection time,421,External_sample_id,keyword,MEDIUM,keyword: sample
+array,407,External_sample_id,similarity,MEDIUM,Similar to: array id (score: 0.769)
+symptomatic or asymptomatic at sample collection,397,External_sample_id,keyword,MEDIUM,keyword: sample
+non human primate individual id,390,External_sample_id,keyword,MEDIUM,keyword: id
+vaccine side effects,387,External_sample_id,keyword,MEDIUM,keyword: id
+age at sample drawn,387,External_sample_id,keyword,MEDIUM,keyword: sample
+library date,385,External_sample_id,similarity,MEDIUM,Similar to: library id (score: 0.818)
+sample preparation,380,External_sample_id,keyword,MEDIUM,keyword: sample
+chip antibody vendor,380,External_sample_id,similarity,MEDIUM,Similar to: antibody vendor id (score: 0.789)
+sample_group,377,External_sample_id,keyword,MEDIUM,keyword: sample
+slide id,377,External_sample_id,keyword,MEDIUM,keyword: id
+subject group,371,External_sample_id,keyword,MEDIUM,keyword: subject
+sample group_label,353,External_sample_id,keyword,MEDIUM,keyword: sample
+sample number within subject,339,External_sample_id,keyword,MEDIUM,keyword: sample
+sample collection,335,External_sample_id,keyword,MEDIUM,keyword: sample
+animal_id,334,External_sample_id,keyword,MEDIUM,keyword: id
+tissue id,333,External_sample_id,keyword,MEDIUM,keyword: id
+monkey id,324,External_sample_id,keyword,MEDIUM,keyword: id
+donor category,317,External_sample_id,keyword,MEDIUM,keyword: donor
+slide name,313,External_sample_id,keyword,MEDIUM,keyword: id
+sample time,302,External_sample_id,keyword,MEDIUM,keyword: sample
+Individual,300,External_sample_id,keyword,MEDIUM,keyword: id
+subject number,272,External_sample_id,keyword,MEDIUM,keyword: subject
+sample_set,265,External_sample_id,keyword,MEDIUM,keyword: sample
+donor_id_blinded,258,External_sample_id,keyword,MEDIUM,keyword: id
+sample_group_granular,251,External_sample_id,keyword,MEDIUM,keyword: sample
+volunteer code,250,External_sample_id,similarity,MEDIUM,Similar to: volunteer id (score: 0.846)
+donor type,240,External_sample_id,keyword,MEDIUM,keyword: donor
+paired samples,239,External_sample_id,keyword,MEDIUM,keyword: sample
+original geo accession,238,External_sample_id,llm,HIGH,Original geo accession seems to be an identifier for samples.
+patient.code,231,External_sample_id,keyword,MEDIUM,keyword: patient
+sample_type,226,External_sample_id,keyword,MEDIUM,keyword: sample
+subject condition,221,External_sample_id,keyword,MEDIUM,keyword: subject
+subject diagnosis,213,External_sample_id,keyword,MEDIUM,keyword: subject
+sample day,212,External_sample_id,keyword,MEDIUM,keyword: sample
+tissue/sample type,209,External_sample_id,keyword,MEDIUM,keyword: sample
+hybridization batch,206,External_sample_id,keyword,MEDIUM,keyword: id
+diagnosis recto sigmoid,202,External_sample_id,keyword,MEDIUM,keyword: id
+patient_age,201,External_sample_id,keyword,MEDIUM,keyword: patient
+patient_visit,201,External_sample_id,keyword,MEDIUM,keyword: patient
+patient sex,199,External_sample_id,keyword,MEDIUM,keyword: patient
+library,198,External_sample_id,similarity,MEDIUM,Similar to: library id (score: 0.824)
+patient code,195,External_sample_id,keyword,MEDIUM,keyword: patient
+plate_number,195,External_sample_id,similarity,MEDIUM,Similar to: patient number (score: 0.769)
+patient subgroup,184,External_sample_id,keyword,MEDIUM,keyword: patient
+patient number,183,External_sample_id,keyword,MEDIUM,keyword: patient
+hybridization protocol,182,External_sample_id,keyword,MEDIUM,keyword: id
+study id,181,External_sample_id,keyword,MEDIUM,keyword: id
+sample tissue,179,External_sample_id,keyword,MEDIUM,keyword: sample
+sample_id,173,External_sample_id,keyword,HIGH,exact_match: sample_id
+volunteer,171,External_sample_id,similarity,MEDIUM,Similar to: volunteer id (score: 0.857)
+long-covid symptoms,168,External_sample_id,keyword,MEDIUM,keyword: id
+subset,168,External_sample_id,similarity,MEDIUM,Similar to: subject (score: 0.769)
+study participant,159,External_sample_id,keyword,MEDIUM,keyword: participant
+sample_site,158,External_sample_id,keyword,MEDIUM,keyword: sample
+clinical diagnosis patient,150,External_sample_id,keyword,MEDIUM,keyword: patient
+sample recovery type,150,External_sample_id,keyword,MEDIUM,keyword: sample
+sample_barcode,149,External_sample_id,keyword,MEDIUM,keyword: sample
+slide_id,148,External_sample_id,keyword,MEDIUM,keyword: id
+"deceased donors, only left kidney included in the analysis",148,External_sample_id,keyword,MEDIUM,keyword: id
+side,146,External_sample_id,keyword,MEDIUM,keyword: id
+identifier,142,External_sample_id,keyword,MEDIUM,keyword: id
+patient treatment,141,External_sample_id,keyword,MEDIUM,keyword: patient
+subjects,137,External_sample_id,keyword,MEDIUM,keyword: subject
+sample origin,135,External_sample_id,keyword,MEDIUM,keyword: sample
+time since steroid dose,134,External_sample_id,keyword,MEDIUM,keyword: id
+family,134,External_sample_id,similarity,MEDIUM,Similar to: family id (score: 0.800)
+donor_genotype,132,External_sample_id,keyword,MEDIUM,keyword: donor
+sample collection time post infection,130,External_sample_id,keyword,MEDIUM,keyword: sample
+scan id,120,External_sample_id,keyword,MEDIUM,keyword: id
+steroids,120,External_sample_id,keyword,MEDIUM,keyword: id
+line number,117,External_sample_id,similarity,MEDIUM,Similar to: sample number (score: 0.750)
+array batch,116,External_sample_id,similarity,MEDIUM,Similar to: array barcode (score: 0.750)
+hospital,116,External_sample_id,llm,LOW,"Hospital could be a part of an external sample ID, but it is not entirely clear without more context."
+mouse_id,110,External_sample_id,keyword,MEDIUM,keyword: id
+donor code,110,External_sample_id,keyword,MEDIUM,keyword: donor
+type of sample,109,External_sample_id,keyword,MEDIUM,keyword: sample
+patient population,108,External_sample_id,keyword,MEDIUM,keyword: patient
+sample age proxy,105,External_sample_id,keyword,MEDIUM,keyword: sample
+patient condition,104,External_sample_id,keyword,MEDIUM,keyword: patient
+family id,104,External_sample_id,keyword,MEDIUM,keyword: id
+sample subseries,103,External_sample_id,keyword,MEDIUM,keyword: sample
+matched pair id,102,External_sample_id,keyword,MEDIUM,keyword: id
+replicate id,101,External_sample_id,keyword,MEDIUM,keyword: id
+donor number,100,External_sample_id,keyword,MEDIUM,keyword: donor
+individual identifier,96,External_sample_id,keyword,MEDIUM,keyword: id
+volunteer number,96,External_sample_id,llm,HIGH,Volunteer number is an identifier for a participant in a study
+specimen_barcode,95,External_sample_id,keyword,MEDIUM,keyword: barcode
+mouse identifier,94,External_sample_id,keyword,MEDIUM,keyword: id
+patient source,91,External_sample_id,keyword,MEDIUM,keyword: patient
+biopsy number for this subject,91,External_sample_id,keyword,MEDIUM,keyword: subject
+sample number,89,External_sample_id,keyword,MEDIUM,keyword: sample
+Patient,89,External_sample_id,keyword,MEDIUM,keyword: patient
+unique_subject_identifier,88,External_sample_id,keyword,MEDIUM,keyword: id
+sample collection time post virus infection,87,External_sample_id,keyword,MEDIUM,keyword: sample
+tissue/treatment id,84,External_sample_id,keyword,MEDIUM,keyword: id
+alias,83,External_sample_id,llm,HIGH,Alias is likely an alternative identifier for a sample or patient.
+donor_type,81,External_sample_id,keyword,MEDIUM,keyword: donor
+pool no,81,External_sample_id,llm,HIGH,Pool no is likely a unique identifier for a sample pool.
+animal identifier,80,External_sample_id,keyword,MEDIUM,keyword: id
+library id,79,External_sample_id,keyword,MEDIUM,keyword: id
+folder name,79,External_sample_id,similarity,MEDIUM,Similar to: slide name (score: 0.762)
+age patient,78,External_sample_id,keyword,MEDIUM,keyword: patient
+patient identifier,78,External_sample_id,keyword,MEDIUM,keyword: patient
+covid infection_status,77,External_sample_id,keyword,MEDIUM,keyword: id
+covid severity_status,77,External_sample_id,keyword,MEDIUM,keyword: id
+steroids_cat,76,External_sample_id,keyword,MEDIUM,keyword: id
+nasal_steroids,76,External_sample_id,keyword,MEDIUM,keyword: id
+pool id,75,External_sample_id,keyword,MEDIUM,keyword: id
+number of pooled individuals,75,External_sample_id,keyword,MEDIUM,keyword: id
+peptide,75,External_sample_id,keyword,MEDIUM,keyword: id
+minimum counts per cell threshold used to remove background barcodes,75,External_sample_id,keyword,MEDIUM,keyword: barcode
+sample plate,74,External_sample_id,keyword,MEDIUM,keyword: sample
+patient identification number,72,External_sample_id,keyword,MEDIUM,keyword: patient
+sort population,72,External_sample_id,similarity,MEDIUM,Similar to: sample population (score: 0.750)
+sample description,71,External_sample_id,keyword,MEDIUM,keyword: sample
+donor covid_status,70,External_sample_id,keyword,MEDIUM,keyword: id
+steroid,67,External_sample_id,keyword,MEDIUM,keyword: id
+size,66,External_sample_id,similarity,MEDIUM,Similar to: side (score: 0.750)
+with_lesion_sample,64,External_sample_id,keyword,MEDIUM,keyword: sample
+id sample,64,External_sample_id,keyword,MEDIUM,keyword: id
+id simple,64,External_sample_id,keyword,MEDIUM,keyword: id
+methylation_geo_id,64,External_sample_id,keyword,MEDIUM,keyword: id
+geo_sample_id,64,External_sample_id,keyword,MEDIUM,keyword: id
+roi type,64,External_sample_id,similarity,MEDIUM,Similar to: organoid type (score: 0.762)
+ref id,63,External_sample_id,keyword,MEDIUM,keyword: id
+number of_mice,62,External_sample_id,similarity,MEDIUM,Similar to: number of_samples (score: 0.774)
+time of sample collection,61,External_sample_id,keyword,MEDIUM,keyword: sample
+patient_no,61,External_sample_id,keyword,MEDIUM,keyword: patient
+patient no,60,External_sample_id,keyword,MEDIUM,keyword: patient
+subject age,60,External_sample_id,keyword,MEDIUM,keyword: subject
+pediatric patient,60,External_sample_id,keyword,MEDIUM,keyword: patient
+sample name in supplementary file,60,External_sample_id,keyword,MEDIUM,keyword: sample
+cartridge,60,External_sample_id,keyword,MEDIUM,keyword: id
+Subsets,60,External_sample_id,similarity,MEDIUM,Similar to: subjects (score: 0.800)
+covid status,59,External_sample_id,keyword,MEDIUM,keyword: id
+replicates,58,External_sample_id,similarity,MEDIUM,Similar to: replicate id (score: 0.818)
+library input,58,External_sample_id,similarity,MEDIUM,Similar to: library id (score: 0.783)
+rabbit id,57,External_sample_id,keyword,MEDIUM,keyword: id
+patient response,57,External_sample_id,keyword,MEDIUM,keyword: patient
+alternative sample name,57,External_sample_id,keyword,MEDIUM,keyword: sample
+publication id,56,External_sample_id,keyword,MEDIUM,keyword: id
+study_id,56,External_sample_id,keyword,MEDIUM,keyword: id
+Sample ID,55,External_sample_id,keyword,HIGH,exact_match: sample id
+sample/subject id,53,External_sample_id,keyword,MEDIUM,keyword: id
+samples of different individuals pooled,53,External_sample_id,keyword,MEDIUM,keyword: id
+organoid line,53,External_sample_id,keyword,MEDIUM,keyword: id
+tumor side,51,External_sample_id,keyword,MEDIUM,keyword: id
+Mouse ID,50,External_sample_id,keyword,MEDIUM,keyword: id
+health_status,50,External_sample_id,similarity,MEDIUM,Similar to: donor_health_status (score: 0.812)
+study number,50,External_sample_id,similarity,MEDIUM,Similar to: study sample number (score: 0.774)
+swollen eyelid,49,External_sample_id,keyword,MEDIUM,keyword: id
+bar code,49,External_sample_id,similarity,HIGH,Similar to: barcode (score: 0.933)
+sample prep,48,External_sample_id,keyword,MEDIUM,keyword: sample
+sample/time point,48,External_sample_id,keyword,MEDIUM,keyword: sample
+subject gender,48,External_sample_id,keyword,MEDIUM,keyword: subject
+slide tissue area,48,External_sample_id,keyword,MEDIUM,keyword: id
+dissected embryo id number,47,External_sample_id,keyword,MEDIUM,keyword: id
+patient/control id,46,External_sample_id,keyword,MEDIUM,keyword: patient
+sample id cat,46,External_sample_id,keyword,MEDIUM,keyword: id
+run id,46,External_sample_id,keyword,MEDIUM,keyword: id
+lane id,46,External_sample_id,keyword,MEDIUM,keyword: id
+person,46,External_sample_id,similarity,MEDIUM,Similar to: person id (score: 0.800)
+patient sample,45,External_sample_id,keyword,MEDIUM,keyword: patient
+subject/sample source id,45,External_sample_id,keyword,MEDIUM,keyword: id
+vendor,44,External_sample_id,similarity,MEDIUM,Similar to: vendor id (score: 0.800)
+Donor type,42,External_sample_id,keyword,MEDIUM,keyword: donor
+patient id no,40,External_sample_id,keyword,MEDIUM,keyword: patient
+patient reference,40,External_sample_id,keyword,MEDIUM,keyword: patient
+sample condition,40,External_sample_id,keyword,MEDIUM,keyword: sample
+batch_id,40,External_sample_id,keyword,MEDIUM,keyword: id
+sample.name,40,External_sample_id,keyword,MEDIUM,keyword: sample
+repeated samples,40,External_sample_id,keyword,MEDIUM,keyword: sample
+sample pool,39,External_sample_id,keyword,MEDIUM,keyword: sample
+"normal individual, Tissue",39,External_sample_id,keyword,MEDIUM,keyword: id
+amyloid,39,External_sample_id,keyword,MEDIUM,keyword: id
+sample_time,38,External_sample_id,keyword,MEDIUM,keyword: sample
+pooled,38,External_sample_id,similarity,MEDIUM,Similar to: pool id (score: 0.769)
+donor no,37,External_sample_id,keyword,MEDIUM,keyword: donor
+sample case,37,External_sample_id,keyword,MEDIUM,keyword: sample
+Source,37,External_sample_id,similarity,MEDIUM,Similar to: source id (score: 0.800)
+subject label,36,External_sample_id,keyword,MEDIUM,keyword: subject
+subject id/diagnosis,36,External_sample_id,keyword,MEDIUM,keyword: id
+individuals,36,External_sample_id,keyword,MEDIUM,keyword: id
+clone id,36,External_sample_id,keyword,MEDIUM,keyword: id
+Twin Pair ID,35,External_sample_id,keyword,MEDIUM,keyword: id
+person id,35,External_sample_id,keyword,MEDIUM,keyword: id
+Sample code,34,External_sample_id,keyword,MEDIUM,keyword: sample
+chip-antibody vendor,33,External_sample_id,similarity,MEDIUM,Similar to: antibody vendor id (score: 0.789)
+alternative_name,33,External_sample_id,similarity,MEDIUM,Similar to: alternative sample name (score: 0.769)
+virus taxon id,32,External_sample_id,keyword,MEDIUM,keyword: id
+disrupted gene id,32,External_sample_id,keyword,MEDIUM,keyword: id
+animal number,32,External_sample_id,similarity,MEDIUM,Similar to: animal id number (score: 0.897)
+study sample number,31,External_sample_id,keyword,MEDIUM,keyword: sample
+paired patient,31,External_sample_id,keyword,MEDIUM,keyword: patient
+library barcode,30,External_sample_id,keyword,MEDIUM,keyword: barcode
+sample beneath,30,External_sample_id,keyword,MEDIUM,keyword: sample
+number of individuals per sample,28,External_sample_id,keyword,MEDIUM,keyword: id
+donor status,28,External_sample_id,keyword,MEDIUM,keyword: donor
+plate code,28,External_sample_id,similarity,MEDIUM,Similar to: patient code (score: 0.818)
+participant condition,27,External_sample_id,keyword,MEDIUM,keyword: participant
+cell samples,26,External_sample_id,keyword,MEDIUM,keyword: sample
+sample.type,26,External_sample_id,keyword,MEDIUM,keyword: sample
+Age of patient,26,External_sample_id,keyword,MEDIUM,keyword: patient
+donor group,26,External_sample_id,keyword,MEDIUM,keyword: donor
+organoid status,24,External_sample_id,keyword,MEDIUM,keyword: id
+mouse exhibiting symptoms on the day of sample collection,24,External_sample_id,keyword,MEDIUM,keyword: sample
+array id,24,External_sample_id,keyword,MEDIUM,keyword: id
+sex steroid priming,24,External_sample_id,keyword,MEDIUM,keyword: id
+tumor identifier,24,External_sample_id,keyword,MEDIUM,keyword: id
+donor line,23,External_sample_id,keyword,MEDIUM,keyword: donor
+tumor sample,23,External_sample_id,keyword,MEDIUM,keyword: sample
+flowcell id,22,External_sample_id,keyword,MEDIUM,keyword: id
+sample status,22,External_sample_id,keyword,MEDIUM,keyword: sample
+Sample Group,22,External_sample_id,keyword,MEDIUM,keyword: sample
+replicate type,22,External_sample_id,similarity,MEDIUM,Similar to: replicate id (score: 0.769)
+hippocampal slice id,21,External_sample_id,keyword,MEDIUM,keyword: id
+antibody vendor name,21,External_sample_id,similarity,MEDIUM,Similar to: antibody vendor id (score: 0.842)
+patient line,20,External_sample_id,keyword,MEDIUM,keyword: patient
+Sample Type,20,External_sample_id,keyword,MEDIUM,keyword: sample
+status sample,20,External_sample_id,keyword,MEDIUM,keyword: sample
+samples,20,External_sample_id,keyword,MEDIUM,keyword: sample
+animal id number,20,External_sample_id,keyword,MEDIUM,keyword: id
+StudyID,20,External_sample_id,keyword,MEDIUM,keyword: id
+donor strain,20,External_sample_id,keyword,MEDIUM,keyword: donor
+Sample,20,External_sample_id,keyword,MEDIUM,keyword: sample
+Order Code,20,External_sample_id,llm,HIGH,Order Code is likely an internal ID for the patients involved in clinical trials
+carcinoid syndrome,19,External_sample_id,keyword,MEDIUM,keyword: id
+library kit,19,External_sample_id,similarity,MEDIUM,Similar to: library id (score: 0.857)
+patient tumor related pain status,18,External_sample_id,keyword,MEDIUM,keyword: patient
+"donor age, sex",18,External_sample_id,keyword,MEDIUM,keyword: donor
+donor race,18,External_sample_id,keyword,MEDIUM,keyword: donor
+vital_status,18,External_sample_id,similarity,MEDIUM,Similar to: covid_status (score: 0.750)
+Hybridization Time,17,External_sample_id,keyword,MEDIUM,keyword: id
+mouse individual id,17,External_sample_id,keyword,MEDIUM,keyword: id
+subject status/id,17,External_sample_id,keyword,MEDIUM,keyword: id
+patient_status,16,External_sample_id,keyword,MEDIUM,keyword: patient
+mouse id tag,16,External_sample_id,keyword,MEDIUM,keyword: id
+data analysis id,16,External_sample_id,keyword,MEDIUM,keyword: id
+genotype of original donor,16,External_sample_id,keyword,MEDIUM,keyword: donor
+Patient Number,16,External_sample_id,keyword,MEDIUM,keyword: patient
+common name,16,External_sample_id,similarity,MEDIUM,Similar to: sample common name (score: 0.759)
+family code,16,External_sample_id,similarity,MEDIUM,Similar to: family id (score: 0.800)
+sample subgroup,15,External_sample_id,keyword,MEDIUM,keyword: sample
+manuscript library id,15,External_sample_id,keyword,MEDIUM,keyword: id
+sample_label,15,External_sample_id,keyword,MEDIUM,keyword: sample
+incidence,15,External_sample_id,keyword,MEDIUM,keyword: id
+animal no,15,External_sample_id,similarity,MEDIUM,Similar to: animal id (score: 0.778)
+lab code,15,External_sample_id,llm,HIGH,Could be an internal ID for tracking samples
+patients,14,External_sample_id,keyword,MEDIUM,keyword: patient
+Lab ID,14,External_sample_id,keyword,MEDIUM,keyword: id
+location/side,14,External_sample_id,keyword,MEDIUM,keyword: id
+alternative name,14,External_sample_id,similarity,MEDIUM,Similar to: alternative sample name (score: 0.821)
+sorted population,13,External_sample_id,similarity,MEDIUM,Similar to: sample population (score: 0.765)
+clone background/id,12,External_sample_id,keyword,MEDIUM,keyword: id
+unique sample identifier,12,External_sample_id,keyword,MEDIUM,keyword: id
+Sample group,12,External_sample_id,keyword,MEDIUM,keyword: sample
+strain id,12,External_sample_id,keyword,MEDIUM,keyword: id
+group id,12,External_sample_id,keyword,MEDIUM,keyword: id
+sample identifier,12,External_sample_id,keyword,MEDIUM,keyword: id
+fetal lung tissue donor,12,External_sample_id,keyword,MEDIUM,keyword: donor
+internal patient id,12,External_sample_id,keyword,MEDIUM,keyword: patient
+internal sample id,12,External_sample_id,keyword,MEDIUM,keyword: id
+donor fibroblasts,12,External_sample_id,keyword,MEDIUM,keyword: donor
+day of organoid differentiation,12,External_sample_id,keyword,MEDIUM,keyword: id
+antibody vendor,12,External_sample_id,similarity,HIGH,Similar to: antibody vendor id (score: 0.909)
+radiation response,12,External_sample_id,similarity,MEDIUM,Similar to: patient response (score: 0.765)
+hydrogen peroxide treatment,11,External_sample_id,keyword,MEDIUM,keyword: id
+donor id/status,11,External_sample_id,keyword,MEDIUM,keyword: id
+array barcode,11,External_sample_id,keyword,MEDIUM,keyword: barcode
+organoid generation,11,External_sample_id,keyword,MEDIUM,keyword: id
+graft donor strain,10,External_sample_id,keyword,MEDIUM,keyword: donor
+original biopsy for this patient,10,External_sample_id,keyword,MEDIUM,keyword: patient
+cell model id,10,External_sample_id,keyword,MEDIUM,keyword: id
+source id,10,External_sample_id,keyword,MEDIUM,keyword: id
+tissue donor,10,External_sample_id,keyword,MEDIUM,keyword: donor
+treatment/sample type,10,External_sample_id,keyword,MEDIUM,keyword: sample
+library backbone,10,External_sample_id,similarity,MEDIUM,Similar to: library barcode (score: 0.839)
+number of animals,10,External_sample_id,similarity,MEDIUM,Similar to: number of_samples (score: 0.765)
+subject identifier,9,External_sample_id,keyword,MEDIUM,keyword: id
+number of_samples,9,External_sample_id,keyword,MEDIUM,keyword: sample
+peptide genotype,8,External_sample_id,keyword,MEDIUM,keyword: id
+sample region,8,External_sample_id,keyword,MEDIUM,keyword: sample
+sample code,8,External_sample_id,keyword,MEDIUM,keyword: sample
+culture/clone_id,7,External_sample_id,keyword,MEDIUM,keyword: id
+patient age at diagnosis,7,External_sample_id,keyword,MEDIUM,keyword: patient
+sample name synonym,7,External_sample_id,keyword,MEDIUM,keyword: sample
+Sample_reference,6,External_sample_id,keyword,MEDIUM,keyword: sample
+Subject_reference,6,External_sample_id,keyword,MEDIUM,keyword: subject
+source patient gender,6,External_sample_id,keyword,MEDIUM,keyword: patient
+strain donor,6,External_sample_id,keyword,MEDIUM,keyword: donor
+organoid formation,6,External_sample_id,keyword,MEDIUM,keyword: id
+subject relationship,6,External_sample_id,keyword,MEDIUM,keyword: subject
+sample barcode,6,External_sample_id,keyword,MEDIUM,keyword: sample
+sample population,6,External_sample_id,keyword,MEDIUM,keyword: sample
+Sex of donor mice,6,External_sample_id,keyword,MEDIUM,keyword: donor
+tubules with elongated spermatids,6,External_sample_id,keyword,MEDIUM,keyword: id
+tubules with round spermatids,6,External_sample_id,keyword,MEDIUM,keyword: id
+age of donor/age of host,6,External_sample_id,keyword,MEDIUM,keyword: donor
+sample replicate number,6,External_sample_id,keyword,MEDIUM,keyword: sample
+fluid,6,External_sample_id,keyword,MEDIUM,keyword: id
+sample state,6,External_sample_id,keyword,MEDIUM,keyword: sample
+als status,6,External_sample_id,similarity,MEDIUM,Similar to: sample status (score: 0.783)
+nodal status,6,External_sample_id,similarity,MEDIUM,Similar to: covid status (score: 0.750)
+fraction/population,6,External_sample_id,similarity,MEDIUM,Similar to: patient population (score: 0.757)
+replicate number,6,External_sample_id,similarity,MEDIUM,Similar to: sample replicate number (score: 0.821)
+hippocampal sclerosis,6,External_sample_id,similarity,MEDIUM,Similar to: hippocampal slice id (score: 0.780)
+tubules with spermatocytes,6,External_sample_id,similarity,MEDIUM,Similar to: tubules with round spermatids (score: 0.764)
+hybrid,5,External_sample_id,keyword,MEDIUM,keyword: id
+id,5,External_sample_id,keyword,MEDIUM,keyword: id
+in-line barcodes,5,External_sample_id,keyword,MEDIUM,keyword: barcode
+donor sex,5,External_sample_id,keyword,MEDIUM,keyword: donor
+donor gender,4,External_sample_id,keyword,MEDIUM,keyword: donor
+donor disease state,4,External_sample_id,keyword,MEDIUM,keyword: donor
+acidity,4,External_sample_id,keyword,MEDIUM,keyword: id
+associate geo_sample,4,External_sample_id,keyword,MEDIUM,keyword: sample
+patient-derived cell line,4,External_sample_id,keyword,MEDIUM,keyword: patient
+sample age,4,External_sample_id,keyword,MEDIUM,keyword: sample
+antibody vendor id,4,External_sample_id,keyword,MEDIUM,keyword: id
+control id,4,External_sample_id,keyword,MEDIUM,keyword: id
+number of_animals,4,External_sample_id,similarity,MEDIUM,Similar to: number of_samples (score: 0.824)
+associated geo,4,External_sample_id,similarity,MEDIUM,Similar to: associate geo_sample (score: 0.765)
+donor diagnosis,3,External_sample_id,keyword,MEDIUM,keyword: donor
+sample tag_information,2,External_sample_id,keyword,MEDIUM,keyword: sample
+organoid type,2,External_sample_id,keyword,MEDIUM,keyword: id
+clip antibody vendor,2,External_sample_id,similarity,MEDIUM,Similar to: antibody vendor id (score: 0.789)
+age of patient when tumor sample obtained,1,External_sample_id,keyword,MEDIUM,keyword: patient
+visit,3653,Other,llm,MEDIUM,"The term 'visit' does not fit well into any of the predefined categories, as it likely refers to a study visit or a time point in a clinical trial."
+segment,2380,Other,llm,LOW,"The term 'segment' is ambiguous and could refer to various concepts in biomedical research, such as a segment of DNA or a segment of a clinical trial."
+reference,1682,Other,llm,LOW,Reference is not clearly related to any of the predefined categories.
+datatype,1603,Other,llm,LOW,Datatype is not clearly related to any of the predefined categories.
+tst,1588,Other,llm,LOW,Tst is not clearly related to any of the predefined categories.
+dataset,1520,Other,llm,HIGH,Dataset is not a characteristic of a biospecimen
+roi,1459,Other,llm,HIGH,ROI is not a characteristic of a biospecimen
+date,1400,Other,llm,HIGH,Date is not a characteristic of a biospecimen
+biological replicate,1375,Other,llm,HIGH,Biological replicate is not a characteristic of a biospecimen
+assay,1202,Other,llm,HIGH,"Assay is a laboratory test or analysis, which does not fit into any of the predefined categories."
+geographical region,1182,Other,llm,HIGH,"Geographical region is not a characteristic of a biospecimen, but rather a location."
+labversion,1180,Other,llm,HIGH,"Labversion is likely a version number for a laboratory protocol or software, which does not fit into any of the predefined categories."
+roi number,1177,Other,llm,HIGH,"ROI number is likely a unique identifier for a region of interest, which does not fit into any of the predefined categories."
+protection,1172,Other,llm,HIGH,"Protection is not a characteristic of a biospecimen, but rather a concept related to data or sample security."
+lab,1170,Other,llm,HIGH,"Lab is a location or facility, not a characteristic of a biospecimen."
+class,1132,Other,llm,HIGH,"Class is a general term that could refer to many things, but in this context, it does not fit into any of the predefined categories."
+area,1053,Other,llm,LOW,"Area is too vague and could refer to many things, such as a geographic area, a body area, or a research area."
+library prep,1030,Other,llm,MEDIUM,"Library prep refers to a laboratory protocol, but it does not fit well into any of the predefined categories."
+pipeline version,1000,Other,llm,LOW,"Pipeline version refers to a software or analysis pipeline, which does not fit well into any of the predefined categories."
+censored,1000,Other,llm,LOW,Censored is a statistical term that does not fit well into any of the predefined categories.
+platesimple,992,Other,llm,LOW,"Platesimple is not a clear or common term in biomedical context, and does not fit well into any of the predefined categories."
+experiment_type,970,Other,llm,LOW,"Experiment type is not a characteristic of a biospecimen, but rather a description of the experimental design or methodology."
+albumin,923,Other,llm,LOW,"Albumin is a protein, but it is not a characteristic of a biospecimen, and does not fit well into any of the predefined categories."
+hematocrit,883,Other,llm,MEDIUM,Hematocrit is a blood test result that does not fit into any specific category.
+hemoglobin,865,Other,llm,MEDIUM,Hemoglobin is a blood test result that does not fit into any specific category.
+model,861,Other,llm,LOW,"Model is a vague term that could refer to various concepts, but it does not fit into any specific category."
+bin,855,Other,llm,LOW,"Bin is a vague term that could refer to various concepts, but it does not fit into any specific category."
+birth_place,813,Other,llm,LOW,Birth place is a demographic information that does not fit into any specific category.
+method,810,Other,llm,LOW,Method is a general term that does not fit well into any specific category
+adjusted household density,804,Other,llm,LOW,Adjusted household density is not directly related to biomedical samples
+geographic location,804,Other,llm,LOW,Geographic location is not directly related to biomedical samples
+field_site,669,Other,llm,LOW,Field site is unclear and does not fit into any other category
+atmosphere,661,Other,llm,HIGH,Does not fit into any specific biomedical sample characteristic category
+geographic origin,610,Other,llm,HIGH,Does not fit into any specific biomedical sample characteristic category
+lane.number,597,Other,llm,HIGH,Does not fit into any specific biomedical sample characteristic category
+center,596,Other,llm,HIGH,Does not fit into any specific biomedical sample characteristic category
+weight,567,Other,llm,MEDIUM,Weight is not directly related to any of the predefined categories
+lane,566,Other,llm,LOW,"Lane is likely related to sequencing or experimental setup, but does not fit any predefined category"
+sort,542,Other,llm,LOW,"Sort is likely related to experimental setup or data processing, but does not fit any predefined category"
+recipient,534,Other,llm,LOW,"Recipient is likely related to the sample donor or experimental setup, but does not fit any predefined category"
+cluster,527,Other,llm,LOW,"Cluster is likely related to data analysis or experimental setup, but does not fit any predefined category"
+immature_granulocytes_percent,500,Other,llm,MEDIUM,"This label appears to be a measurement or characteristic of a specific cell type, but it doesn't fit neatly into any of the predefined categories."
+genotype_abbreviation,500,Other,llm,MEDIUM,"Genotype abbreviation is a specific piece of information about a biospecimen, but it doesn't fit into any of the predefined categories."
+immature_granulocytes_absolute,500,Other,llm,MEDIUM,"Similar to immature_granulocytes_percent, this label appears to be a measurement or characteristic of a specific cell type, but it doesn't fit neatly into any of the predefined categories."
+allele actual,500,Other,llm,HIGH,This label does not fit into any predefined category. It seems to be related to genetic data.
+well address,500,Other,llm,HIGH,This label does not fit into any predefined category. It seems to be related to laboratory equipment or experimental setup.
+plate_location,500,Other,llm,HIGH,This label does not fit into any predefined category. It seems to be related to laboratory equipment or experimental setup.
+allele nominal,500,Other,llm,HIGH,This label does not fit into any predefined category. It seems to be related to genetic data.
+match,500,Other,llm,HIGH,This label does not fit into any predefined category. It seems to be related to data processing or analysis.
+smear microscopy,500,Other,llm,HIGH,This label does not fit into any predefined category. It seems to be related to a laboratory technique or diagnostic method.
+instrument model,500,Other,llm,HIGH,"Instrument model is not a characteristic of a biospecimen, but rather of the equipment used to analyze or process it."
+supplier,500,Other,llm,HIGH,"Supplier is not a characteristic of a biospecimen, but rather of the source or provider of the biospecimen."
+affy_batch,500,Other,llm,HIGH,"Affy_batch is not a characteristic of a biospecimen, but rather of the batch or group of biospecimens being analyzed."
+library prep_plate,500,Other,llm,HIGH,"Library prep_plate is not a characteristic of a biospecimen, but rather of the laboratory process or protocol used to prepare the biospecimen."
+assigned cluster,500,Other,llm,HIGH,"Assigned cluster is not a characteristic of a biospecimen, but rather of the analysis or classification of the biospecimen."
+probe_detection,500,Other,llm,HIGH,"This label does not fit into any of the predefined categories, as it seems to be related to a laboratory technique or experimental method."
+title,500,Other,llm,HIGH,"This label does not fit into any of the predefined categories, as it seems to be a metadata label rather than a characteristic of the biospecimen."
+filtered peaks,500,Other,llm,HIGH,"This label does not fit into any of the predefined categories, as it seems to be related to a laboratory technique or experimental method."
+extract name,500,Other,llm,HIGH,Does not fit into any specific biomedical sample characteristic category
+assay name,500,Other,llm,HIGH,Does not fit into any specific biomedical sample characteristic category
+project,500,Other,llm,HIGH,Does not fit into any specific biomedical sample characteristic category
+hemisphere_name,500,Other,llm,HIGH,Does not fit into any specific biomedical sample characteristic category
+platelet_count,500,Other,llm,HIGH,Does not fit into any specific biomedical sample characteristic category
+multisector,500,Other,llm,HIGH,Does not fit into any specific biomedical sample characteristic category
+injection_roi,500,Other,llm,LOW,"Unclear meaning, possibly related to imaging or experimental setup"
+array_design,500,Other,llm,LOW,"Unclear meaning, possibly related to experimental setup or data analysis"
+cluster_label,500,Other,llm,LOW,"Unclear meaning, possibly related to data analysis or clustering algorithms"
+is_technical_replicate,492,Other,llm,LOW,"Unclear meaning, possibly related to experimental design or data quality control"
+duplicate_pair,492,Other,llm,LOW,"Unclear meaning, possibly related to experimental design or data quality control"
+material support,489,Other,llm,LOW,Does not fit well into any category
+library name,476,Other,llm,LOW,Does not fit well into any category
+genome build,438,Other,llm,LOW,"Genome build is not a characteristic of any of the predefined categories, but rather a characteristic of the data itself."
+label,431,Other,llm,LOW,Label is a generic term that does not fit into any of the predefined categories.
+bait,425,Other,llm,LOW,"Bait is not a characteristic of any of the predefined categories, but rather a term used in experimental design."
+chain,422,Other,llm,LOW,The term 'chain' is ambiguous and does not fit well into any specific biomedical sample characteristic category.
+outlier,414,Other,llm,LOW,Outlier is a statistical term and does not fit well into any specific biomedical sample characteristic category.
+date collected,404,Other,llm,LOW,Date collected is a metadata attribute and does not fit well into any specific biomedical sample characteristic category.
+gene_count,399,Other,llm,LOW,Gene count is a data analysis attribute and does not fit well into any specific biomedical sample characteristic category.
+nuclei count,393,Other,llm,MEDIUM,"Nuclei count is a quantitative measurement, but it does not fit well with any of the predefined categories."
+technique,381,Other,llm,MEDIUM,"Technique is a method or approach, which does not fit well with any of the predefined categories."
+recruiting site,379,Other,llm,LOW,"Recruiting site is likely related to clinical trials, but it does not fit well with any of the predefined categories."
+procedure date,374,Other,llm,MEDIUM,"This label does not fit well into any of the predefined categories, as it seems to refer to a specific event or intervention rather than a characteristic of the biospecimen."
+smoking start date,374,Other,llm,MEDIUM,"This label does not fit well into any of the predefined categories, as it seems to refer to a specific event or behavior rather than a characteristic of the biospecimen."
+smoking amount,374,Other,llm,MEDIUM,"This label does not fit well into any of the predefined categories, as it seems to refer to a specific behavior or habit rather than a characteristic of the biospecimen."
+smoking stop date,374,Other,llm,MEDIUM,"This label does not fit well into any of the predefined categories, as it seems to refer to a specific event or behavior rather than a characteristic of the biospecimen."
+binding density,370,Other,llm,LOW,"This label seems to refer to a specific measurement or property, but it is unclear what it relates to without more context. It does not fit well into any of the predefined categories."
+cap score,369,Other,llm,HIGH,The label does not fit into any specific biomedical sample characteristic category.
+chip antibody cat,365,Other,llm,HIGH,The label does not fit into any specific biomedical sample characteristic category.
+negative normalization factor,363,Other,llm,HIGH,The label does not fit into any specific biomedical sample characteristic category.
+note,363,Other,llm,HIGH,The label does not fit into any specific biomedical sample characteristic category.
+history,363,Other,llm,HIGH,The label does not fit into any specific biomedical sample characteristic category.
+surface area,363,Other,llm,HIGH,The label does not fit into any specific biomedical sample characteristic category.
+link,362,Other,llm,HIGH,The label does not fit into any specific biomedical sample characteristic category.
+who,349,Other,llm,HIGH,The label does not fit into any specific biomedical sample characteristic category.
+nuclei_counts,345,Other,llm,HIGH,"Does not fit into any specific category, but could be related to Biospecimen Type or Biospecimen Age"
+amplification cycles,324,Other,llm,MEDIUM,"Amplification cycles is a laboratory technique, but it doesn't fit well into any of the predefined categories."
+smoke,317,Other,llm,LOW,"Smoke is not clearly related to any of the predefined categories, so it's categorized as Other."
+visit_date,313,Other,llm,LOW,"Visit date is not clearly related to any of the predefined categories, so it's categorized as Other."
+mean corpuscular volume,306,Other,llm,MEDIUM,"This label appears to be a clinical measurement, but it doesn't fit neatly into any of the predefined categories."
+job/role,300,Other,llm,LOW,This label appears to be unrelated to biomedical samples or characteristics.
+technical replicate,295,Other,llm,LOW,"This label appears to be related to experimental design or methodology, rather than a biomedical sample characteristic."
+index,287,Other,llm,LOW,This label is too vague to be confidently assigned to any category.
+genetic testing,285,Other,llm,MEDIUM,"Genetic testing is a method or process rather than a characteristic of a biospecimen, so it doesn't fit neatly into any of the predefined categories."
+unpublished,284,Other,llm,LOW,Unpublished does not fit into any of the predefined categories
+city,284,Other,llm,LOW,City does not fit into any of the predefined categories
+datasets,284,Other,llm,LOW,Datasets does not fit into any of the predefined categories
+volume,282,Other,llm,LOW,"Volume is not a clear fit for any category, could be related to sample volume but not enough context"
+geographical location,277,Other,llm,LOW,"Geographical location is not a clear fit for any category, could be related to sample collection but not enough context"
+training.test,271,Other,llm,LOW,"Training test is not a clear fit for any category, could be related to data analysis but not enough context"
+used for analysis,271,Other,llm,LOW,"Used for analysis is not a clear fit for any category, could be related to data analysis but not enough context"
+block_name,270,Other,llm,LOW,"Block name is not a clear fit for any category, could be related to experimental design but not enough context"
+structure acronym,270,Other,llm,HIGH,Does not fit into any specific biomedical sample characteristic category
+set,267,Other,llm,HIGH,Too vague and does not fit into any specific biomedical sample characteristic category
+read length,259,Other,llm,HIGH,"Relates to sequencing data, not a biomedical sample characteristic"
+duplication_rate,251,Other,llm,HIGH,"Relates to sequencing data, not a biomedical sample characteristic"
+align_unique,251,Other,llm,HIGH,"Relates to sequencing data, not a biomedical sample characteristic"
+exon_ratio,251,Other,llm,HIGH,"Relates to sequencing data, not a biomedical sample characteristic"
+align_input,251,Other,llm,HIGH,"Relates to sequencing data, not a biomedical sample characteristic"
+reads_all,251,Other,llm,HIGH,Does not fit into any specific biomedical sample characteristic category
+nuclear_reads,251,Other,llm,HIGH,Does not fit into any specific biomedical sample characteristic category
+library_prep_date,251,Other,llm,HIGH,Does not fit into any specific biomedical sample characteristic category
+extract_date,251,Other,llm,HIGH,Does not fit into any specific biomedical sample characteristic category
+repeat,243,Other,llm,LOW,"Unclear what this label refers to, could be related to treatment or biospecimen, but not enough information"
+season,238,Other,llm,HIGH,Season does not fit into any specific biomedical sample characteristic category.
+other information,236,Other,llm,HIGH,Other information is too vague to fit into any specific biomedical sample characteristic category.
+sorting strategy,234,Other,llm,HIGH,Sorting strategy does not fit into any specific biomedical sample characteristic category.
+escape,233,Other,llm,HIGH,Escape does not fit into any specific biomedical sample characteristic category.
+diffuse,231,Other,llm,HIGH,Diffuse does not fit into any specific biomedical sample characteristic category.
+hist.score,228,Other,llm,HIGH,Hist.score does not fit into any specific biomedical sample characteristic category.
+feeding,215,Other,llm,LOW,Does not fit well into any category
+bal sampling date,212,Other,llm,LOW,Does not fit well into any category
+timing,211,Other,llm,LOW,Does not fit well into any category
+processing,210,Other,llm,HIGH,Does not fit into any specific biomedical sample characteristic category
+library quality,208,Other,llm,HIGH,Does not fit into any specific biomedical sample characteristic category
+visit number,205,Other,llm,HIGH,Does not fit into any specific biomedical sample characteristic category
+pair,205,Other,llm,HIGH,Does not fit into any specific biomedical sample characteristic category
+run_date,202,Other,llm,HIGH,Does not fit into any specific biomedical sample characteristic category
+muscle mass,200,Other,llm,MEDIUM,Muscle mass is a characteristic of the donor but does not fit into any specific category.
+waist to hip ratio,200,Other,llm,MEDIUM,Waist to hip ratio is a characteristic of the donor but does not fit into any specific category.
+reference genome_for_processed_files,200,Other,llm,LOW,Reference genome is related to data processing and not directly related to biospecimen characteristics.
+fat mass,200,Other,llm,MEDIUM,Fat mass is a characteristic of the donor but does not fit into any specific category.
+reference genome_for_alignment,200,Other,llm,LOW,Reference genome is related to data processing and not directly related to biospecimen characteristics.
+region of birth,191,Other,llm,LOW,Region of birth does not fit into any specific category
+period,186,Other,llm,LOW,"This label is too vague and could refer to many different things, such as a time period or a menstrual period."
+buffer,186,Other,llm,LOW,"This label is too vague and could refer to many different things, such as a chemical buffer or a buffer zone."
+extraction date,185,Other,llm,HIGH,Does not fit into any specific biomedical sample characteristic category
+draw_date,185,Other,llm,HIGH,Does not fit into any specific biomedical sample characteristic category
+comment,184,Other,llm,HIGH,Does not fit into any specific biomedical sample characteristic category
+LabeledExtract,183,Other,llm,HIGH,Does not fit into any specific biomedical sample characteristic category
+expanded allele cag repeat count,178,Other,llm,LOW,"This label appears to be related to genetic information, but does not fit neatly into any predefined category."
+factor,177,Other,llm,LOW,This label is too vague to be assigned to a specific category without more context.
+paired material support,177,Other,llm,LOW,This label does not appear to be related to any biomedical sample characteristic.
+input,174,Other,llm,LOW,This label is too vague to be assigned to a specific category without more context.
+further operations,172,Other,llm,LOW,This label does not appear to be related to any biomedical sample characteristic.
+efficacy,164,Other,llm,LOW,"Efficacy is not a characteristic of the biospecimen itself, but rather a measure of the effectiveness of a treatment or intervention."
+buffer_volume,158,Other,llm,LOW,"Buffer volume is not a characteristic of the biospecimen itself, but rather a laboratory or experimental parameter."
+protein exchange,158,Other,llm,HIGH,"Does not fit into any specific category, but could be related to experimental conditions."
+buffer_volume_unit,158,Other,llm,HIGH,"Does not fit into any specific category, but could be related to experimental conditions."
+study_origin,156,Other,llm,HIGH,"Study origin does not fit into any specific category, but could be related to the study design or experimental conditions."
+library prep. kit,155,Other,llm,HIGH,"Library preparation kits are laboratory reagents used for preparing DNA or RNA libraries for sequencing, but they don't fit into any specific biomedical sample characteristic category."
+restriction enzyme,153,Other,llm,HIGH,"Restriction enzymes are laboratory reagents used for cutting DNA at specific sequences, but they don't fit into any specific biomedical sample characteristic category."
+classifier_mes,152,Other,llm,LOW,Classifier_mes is unclear and doesn't fit into any specific biomedical sample characteristic category.
+aerosol.run,151,Other,llm,LOW,Aerosol.run is unclear and doesn't fit into any specific biomedical sample characteristic category.
+lane.ordinal,151,Other,llm,LOW,Lane.ordinal is unclear and doesn't fit into any specific biomedical sample characteristic category.
+notes,148,Other,llm,LOW,Notes is a general term that does not fit into any specific category
+adapter,147,Other,llm,LOW,Adapter is a general term that does not fit into any specific category
+target gene,143,Other,llm,LOW,Target gene is a general term that does not fit into any specific category
+Other,136,Other,llm,HIGH,This label is too vague and does not fit into any other category.
+technology,128,Other,llm,HIGH,Technology is not directly related to biospecimen characteristics.
+sofa,126,Other,llm,HIGH,Sofa is not related to biospecimen characteristics.
+application,120,Other,llm,LOW,Application does not fit well into any biomedical sample characteristic category
+country,120,Other,llm,LOW,Country does not fit well into any biomedical sample characteristic category
+met_amplification,119,Other,llm,LOW,"Met_amplification is not clearly related to any of the predefined categories, but it could be related to a specific experimental or analytical technique."
+other batch,118,Other,llm,LOW,"Other batch is not clearly related to any of the predefined categories, but it could be related to a specific experimental or analytical technique."
+date of array,117,Other,llm,LOW,"Date of array is not clearly related to any of the predefined categories, but it could be related to a specific experimental or analytical technique."
+batch.date,116,Other,llm,LOW,"Batch.date is not clearly related to any of the predefined categories, but it could be related to a specific experimental or analytical technique."
+fragments in clean bam,112,Other,llm,HIGH,This label does not fit into any specific biomedical sample characteristic category. It appears to be related to bioinformatics processing.
+sensor,110,Other,llm,HIGH,This label does not fit into any specific biomedical sample characteristic category. It appears to be related to experimental setup or equipment.
+spike-in,108,Other,llm,HIGH,This label does not fit into any specific biomedical sample characteristic category. It appears to be related to experimental design or quality control.
+other,106,Other,llm,HIGH,This label is too vague and does not fit into any specific biomedical sample characteristic category.
+admission,105,Other,llm,LOW,"Could be related to hospital admission, but unclear how it relates to biospecimen characteristics"
+circumstances,103,Other,llm,LOW,Too vague to determine a clear relationship to biospecimen characteristics
+target,102,Other,llm,LOW,The label is too vague and does not fit into any specific category.
+geo series,101,Other,llm,LOW,"The label appears to be related to a series of geographic locations, but it does not fit into any specific category."
+library strategy,101,Other,llm,LOW,"The label appears to be related to a laboratory technique, but it does not fit into any specific category."
+geo accession,101,Other,llm,LOW,"The label appears to be related to a geographic location, but it does not fit into any specific category."
+Filter number,101,Other,llm,LOW,"This label does not fit well into any of the predefined categories, as it seems to be related to a technical or procedural aspect rather than a biological characteristic."
+cortical_score,100,Other,llm,MEDIUM,"This label does not fit well into any of the predefined categories, as it seems to be related to a specific measurement or assessment rather than a biological characteristic."
+striatal_score,100,Other,llm,MEDIUM,"Similar to cortical_score, this label does not fit well into any of the predefined categories, as it seems to be related to a specific measurement or assessment rather than a biological characteristic."
+channel count,100,Other,llm,LOW,"This label does not fit well into any of the predefined categories, as it seems to be related to a technical or procedural aspect rather than a biological characteristic."
+reporter,96,Other,llm,LOW,Reporter is not clearly related to any of the predefined categories
+roi lot,95,Other,llm,LOW,Roi lot is not clearly related to any of the predefined categories
+chemistry,94,Other,llm,LOW,"Chemistry is a broad term that could refer to many things, but in the context of biomedical samples, it does not fit neatly into any of the predefined categories."
+purification,92,Other,llm,LOW,"Purification is a process that is applied to biospecimens, but it is not a characteristic of the biospecimen itself."
+replicate # in experiment,88,Other,llm,HIGH,This label refers to the experimental design and does not fit into any of the predefined biomedical categories.
+progression_free_survival_censor,88,Other,llm,HIGH,"This label does not fit into any specific biomedical sample characteristic category, as it appears to be related to a clinical outcome or endpoint rather than a sample characteristic."
+experiment year_month,86,Other,llm,HIGH,"This label appears to be related to the timing or date of the experiment, which is not a characteristic of the sample itself."
+instance,84,Other,llm,HIGH,This label is too vague and does not fit into any specific biomedical sample characteristic category.
+integrative analysis,81,Other,llm,LOW,"Integrative analysis is a research approach, not a sample characteristic."
+panel,79,Other,llm,HIGH,"The term 'panel' is too broad and does not fit into any specific category. It could refer to a panel of genes, a panel of samples, or a panel of experts."
+expression,79,Other,llm,HIGH,"The term 'expression' is too broad and does not fit into any specific category. It could refer to gene expression, protein expression, or other types of expression."
+adapter sequence,79,Other,llm,HIGH,"The term 'adapter sequence' is a technical term in molecular biology, but it does not fit into any specific category."
+mib,78,Other,llm,LOW,The term 'mib' is unclear and does not fit into any specific category.
+geo expression data,77,Other,llm,LOW,This label does not fit into any of the predefined categories as it seems to be related to a type of data rather than a sample characteristic.
+replicate / experiment,75,Other,llm,LOW,This label does not fit into any of the predefined categories as it seems to be related to the experimental design rather than a sample characteristic.
+ClinicalInformation,75,Other,llm,LOW,This label is too broad and does not fit into any of the predefined categories as it could encompass various types of clinical information.
+spike-ins,75,Other,llm,LOW,This label does not fit into any of the predefined categories as it seems to be related to a type of control or reference sample rather than a sample characteristic.
+preservation method,75,Other,llm,HIGH,"Preservation method is not directly related to any of the predefined categories, but it is an important characteristic of biospecimens."
+tags,70,Other,llm,LOW,Tags is not a clear biomedical term and does not fit into any other category
+restriction enzymes,67,Other,llm,LOW,"This label does not fit well with any of the predefined categories, as it seems to be related to a laboratory technique or reagent."
+structure,67,Other,llm,LOW,"This label is too vague and does not fit well with any of the predefined categories, as it could refer to various aspects of biospecimens or experiments."
+backbone,66,Other,llm,LOW,"This label does not fit well with any of the predefined categories, as it could refer to various aspects of biospecimens or experiments, such as molecular structure or experimental design."
+genetic variants,66,Other,llm,HIGH,"Does not fit into any specific category, but could be related to Biospecimen Disease Condition or Biospecimen Type"
+risk,65,Other,llm,HIGH,"Does not fit into any specific category, but could be related to Biospecimen Disease Condition or Treatment"
+immune border,64,Other,llm,HIGH,"Does not fit into any specific category, but could be related to Biospecimen Disease Condition or Biospecimen Type"
+comments,64,Other,llm,HIGH,"Does not fit into any specific category, likely free text or notes"
+cag repeat size,64,Other,llm,MEDIUM,CAG repeat size is a genetic term that refers to the number of CAG repeats in a gene. It does not fit into any of the predefined categories.
+library_batch,64,Other,llm,LOW,Library batch is a term used in molecular biology to describe a batch of DNA libraries. It does not fit into any of the predefined categories.
+enrichment method,63,Other,llm,HIGH,"This label does not fit into any specific category, but it could be related to sample preparation or processing."
+library prep person,63,Other,llm,HIGH,"This label does not fit into any specific category, but it could be related to sample preparation or processing."
+carbon source,62,Other,llm,HIGH,"This label does not fit into any specific category, but it could be related to cell culture or microbiology."
+corrector,60,Other,llm,LOW,The term 'corrector' is not clearly related to any of the predefined categories.
+coo,60,Other,llm,LOW,The term 'coo' is not clearly related to any of the predefined categories.
+angiogenesis score,60,Other,llm,LOW,The term 'angiogenesis score' is not clearly related to any of the predefined categories.
+ras score,60,Other,llm,LOW,The term 'ras score' is not clearly related to any of the predefined categories.
+cag repeats,60,Other,llm,HIGH,This label does not fit into any predefined category as it refers to a specific genetic characteristic.
+cycling,58,Other,llm,MEDIUM,"This label could refer to various biological processes, but without more context, it is difficult to assign it to a specific category."
+respirations per minute,58,Other,llm,HIGH,"This label refers to a physiological measurement, but it does not fit into any predefined category as it is not a characteristic of the biospecimen itself."
+cag length,56,Other,llm,LOW,"Cag length does not fit neatly into any of the predefined categories, and without more context, it's difficult to determine its relevance."
+commercial source,56,Other,llm,LOW,This does not fit well into any category
+topography,56,Other,llm,LOW,This does not fit well into any category
+kit mutation,54,Other,llm,LOW,"Does not fit into any specific category, possibly related to experimental or technical aspects."
+library version,54,Other,llm,LOW,"Does not fit into any specific category, possibly related to experimental or technical aspects."
+sort strategy,54,Other,llm,LOW,"Sort strategy does not fit well into any of the predefined categories, as it likely refers to a laboratory or analytical technique."
+match degree,54,Other,llm,LOW,"Match degree does not fit well into any of the predefined categories, as it likely refers to a measure of similarity or correlation."
+collected_by,53,Other,llm,LOW,"This label does not fit into any specific category, as it refers to the person or entity collecting the sample."
+platform,53,Other,llm,LOW,"This label is likely referring to the experimental or analytical platform used, which does not fit into any specific category."
+biological_replicate,52,Other,llm,LOW,"This label refers to the experimental design, specifically the use of biological replicates, which does not fit into any specific category."
+genetic specifics,52,Other,llm,LOW,"Genetic specifics could relate to various aspects of biospecimen characteristics, but it does not fit neatly into any predefined category without more context."
+last follow-up,51,Other,llm,LOW,"Last follow-up does not directly relate to any biospecimen characteristic but could be relevant in a clinical trial context, thus not fitting neatly into any predefined category."
+ago protein,49,Other,llm,LOW,"This label seems to be related to a protein, but it does not fit well into any of the predefined categories."
+kit,48,Other,llm,LOW,This label does not provide enough information to be categorized into any of the predefined categories.
+scan method,48,Other,llm,LOW,This label does not provide enough information to be categorized into any of the predefined categories.
+to concatenate,46,Other,llm,LOW,"The term 'to concatenate' is not clearly related to any of the predefined categories, and its meaning is more related to data processing or manipulation."
+total bilirubin,46,Other,llm,HIGH,"Total bilirubin is a clinical measurement, not a characteristic of a biospecimen"
+littermate,46,Other,llm,MEDIUM,"Littermate is a term used in animal studies, but it does not fit well into any of the predefined categories"
+processing batch,46,Other,llm,HIGH,"Processing batch is a laboratory or experimental parameter, not a characteristic of a biospecimen"
+mean.corpuscular.volume,46,Other,llm,HIGH,"Mean corpuscular volume is a clinical measurement, not a characteristic of a biospecimen"
+histone mark,44,Other,llm,MEDIUM,"Histone mark is a specific type of epigenetic modification, but it does not fit well into any of the predefined categories."
+modality,44,Other,llm,HIGH,Modality does not fit into any specific biomedical sample characteristic category.
+temp,43,Other,llm,HIGH,Temp does not fit into any specific biomedical sample characteristic category.
+nutritional state,43,Other,llm,HIGH,Nutritional state does not fit into any specific biomedical sample characteristic category.
+Cluster,42,Other,llm,HIGH,Cluster does not fit into any specific biomedical sample characteristic category.
+markers used for sorting,42,Other,llm,HIGH,Markers used for sorting does not fit into any specific biomedical sample characteristic category.
+number cag repeats,42,Other,llm,HIGH,Number cag repeats does not fit into any specific biomedical sample characteristic category.
+experimental variables,42,Other,llm,HIGH,Experimental variables does not fit into any specific biomedical sample characteristic category.
+gel_bead_version,40,Other,llm,LOW,"This label does not fit into any of the predefined categories, as it appears to be a technical or experimental parameter."
+pipeline.version,39,Other,llm,HIGH,"This label does not fit well with any biomedical sample characteristic categories, so it is categorized as Other."
+tau_score,39,Other,llm,MEDIUM,"Tau score is a measure of tau protein levels, but it does not fit well with any biomedical sample characteristic categories, so it is categorized as Other."
+profession,39,Other,llm,HIGH,"Profession is not a biomedical sample characteristic, so it is categorized as Other."
+freezer,39,Other,llm,HIGH,"Freezer is a storage condition, but it does not fit well with any biomedical sample characteristic categories, so it is categorized as Other."
+labor,38,Other,llm,HIGH,"Labor is not a biomedical sample characteristic, so it is categorized as Other."
+data file subset,38,Other,llm,LOW,"Data file subset does not fit into any of the predefined categories, as it is related to data organization rather than biomedical sample characteristics."
+data type,37,Other,llm,LOW,"Data type does not fit into any of the predefined categories, as it is related to data organization rather than biomedical sample characteristics."
+Cycle,37,Other,llm,LOW,"Cycle could refer to various aspects of a biological sample, such as cell cycle or treatment cycle, but without more context, it is difficult to assign it to a specific category."
+paired with,37,Other,llm,LOW,"Paired with is a vague term that could refer to various aspects of a biological sample, such as paired samples or paired treatments, but without more context, it is difficult to assign it to a specific category."
+batch number,36,Other,llm,LOW,"Batch number is a label that does not fit well within any of the predefined categories, as it is more related to the sample processing or storage rather than a characteristic of the biological sample itself."
+number of replicates,36,Other,llm,HIGH,"This label does not fit into any specific biomedical sample characteristic category, as it refers to the experimental design rather than a sample characteristic."
+water salinity,36,Other,llm,HIGH,"This label does not fit into any specific biomedical sample characteristic category, as it refers to an environmental condition rather than a sample characteristic."
+locale,36,Other,llm,HIGH,"This label does not fit into any specific biomedical sample characteristic category, as it refers to a geographical location rather than a sample characteristic."
+asbestos-fiber count,34,Other,llm,MEDIUM,"This label does not fit into any of the predefined categories, as it appears to be a measurement of asbestos fibers, which is not directly related to biospecimen characteristics."
+method of preservation,34,Other,llm,MEDIUM,"This label does not fit into any of the predefined categories, as it appears to be a method used to preserve the biospecimen, which is not directly related to biospecimen characteristics."
+tandem repeat number,34,Other,llm,HIGH,This label does not fit into any predefined category as it refers to a specific genetic feature.
+core code,33,Other,llm,MEDIUM,This label does not provide enough context to be assigned to a specific category.
+chip-antibody cat,33,Other,llm,MEDIUM,"This label appears to be related to a specific experimental technique, but does not fit into any predefined category."
+definite analysis,33,Other,llm,MEDIUM,This label does not provide enough context to be assigned to a specific category.
+total volume,33,Other,llm,MEDIUM,"This label refers to a physical property of the biospecimen, but does not fit into any predefined category."
+genetic variants inheritance,33,Other,llm,HIGH,"This label refers to a specific genetic feature, but does not fit into any predefined category."
+twins,32,Other,llm,MEDIUM,"This label does not fit well with any of the predefined categories, as it does not describe a biospecimen characteristic directly."
+virus accession number,32,Other,llm,LOW,"This label does not fit well with any of the predefined categories, as it seems to be a unique identifier for a virus rather than a biospecimen characteristic."
+note_other,30,Other,llm,LOW,"This label is too vague and does not provide enough information to categorize it accurately, so it is assigned to the Other category."
+test,30,Other,llm,LOW,test is too vague to be assigned to a specific category
+promoter,30,Other,llm,LOW,"promoter is a term from molecular biology, but it does not fit well into any of the predefined categories"
+preparation method,30,Other,llm,LOW,preparation method is a term that does not fit well into any of the predefined categories
+line name in manuscript,30,Other,llm,HIGH,"This label does not fit into any specific biomedical sample characteristic category, as it seems to refer to a naming convention in a manuscript rather than a characteristic of the biospecimen itself."
+lactate,29,Other,llm,HIGH,"Lactate is a biomarker or a chemical compound, not fitting well into any of the predefined categories."
+los,29,Other,llm,HIGH,"LOS typically stands for Length of Stay, which is a clinical or administrative metric rather than a biospecimen characteristic."
+creatinine,29,Other,llm,HIGH,"Creatinine is a biomarker or a chemical compound, not fitting well into any of the predefined categories."
+tobacco,28,Other,llm,HIGH,Does not fit into any specific biomedical sample characteristic category
+specific primer,27,Other,llm,HIGH,Does not fit into any specific biomedical sample characteristic category
+culture results,27,Other,llm,HIGH,Does not fit into any specific biomedical sample characteristic category
+run,27,Other,llm,HIGH,Does not fit into any specific biomedical sample characteristic category
+sort fraction,27,Other,llm,HIGH,Does not fit into any specific biomedical sample characteristic category
+variant,26,Other,llm,LOW,"Variant is a general term that could refer to many things, such as genetic variants or experimental variants, and does not fit well into any specific category."
+clinical,26,Other,llm,LOW,"Clinical is a general term that could refer to many things, such as clinical trials or clinical samples, and does not fit well into any specific category."
+ectopic expression,25,Other,llm,LOW,"Ectopic expression refers to the expression of a gene or protein in an abnormal location, but it does not fit well into any of the predefined categories"
+biological replicates,24,Other,llm,LOW,This label does not fit into any of the predefined categories as it refers to the number of times a biological experiment is repeated.
+percent_aligned,24,Other,llm,HIGH,This label does not fit into any of the predefined categories as it seems to be related to sequencing data quality rather than a biospecimen characteristic.
+technical_replicate_number,24,Other,llm,HIGH,This label is related to experimental design and does not describe a biospecimen characteristic.
+biological_replicate_number,24,Other,llm,HIGH,"Similar to technical replicate, this label is related to experimental design and does not describe a biospecimen characteristic."
+date_death,24,Other,llm,HIGH,This label is related to the donor's medical history but does not describe a biospecimen characteristic.
+decode_name,22,Other,llm,LOW,Decode_name does not fit well into any of the predefined categories.
+sorting,20,Other,llm,LOW,"Sorting is not a clear fit for any category, but could be related to sample processing"
+chip processing date,20,Other,llm,LOW,chip processing date is not directly related to any of the predefined categories.
+Parity,20,Other,llm,MEDIUM,"Parity is a demographic characteristic, but it does not fit well into any of the predefined categories"
+calcium level,20,Other,llm,LOW,"calcium level is a measurement or characteristic, but it does not fit well into any of the predefined categories"
+hospital admission,18,Other,llm,LOW,"Hospital admission is not directly related to biospecimen characteristics, but rather to the clinical context."
+radiology,18,Other,llm,LOW,"Radiology is a medical imaging technique, not a characteristic of a biospecimen"
+sort-gate,18,Other,llm,LOW,"Sort-gate is a laboratory technique, not a characteristic of a biospecimen"
+sort gate,17,Other,llm,LOW,"Sort gate is a laboratory technique, not a characteristic of a biospecimen"
+stitched reads,17,Other,llm,LOW,"Stitched reads is a term related to sequencing data, but it does not fit into any of the predefined categories"
+raw reads,17,Other,llm,LOW,"Raw reads is a term related to sequencing data, but it does not fit into any of the predefined categories"
+aligned reads,17,Other,llm,LOW,"Aligned reads is a term related to sequencing data, but it does not fit into any of the predefined categories"
+level,17,Other,llm,LOW,"Level is a term that can have multiple meanings, but it does not fit into any of the predefined categories"
+performance,16,Other,llm,LOW,"The label does not fit well into any of the predefined categories, as it is too vague and does not have a clear biological context."
+vascular support,16,Other,llm,LOW,"The label does not fit well into any of the predefined categories, as it is too vague and does not have a clear biological context."
+has_pressure,16,Other,llm,LOW,"The label does not fit well into any of the predefined categories, as it is too vague and does not have a clear biological context."
+viral titre,16,Other,llm,HIGH,"Viral titre is a measure of the concentration of virus in a sample, which does not fit into any of the predefined categories."
+pool,16,Other,llm,HIGH,"Pool is a general term that could refer to a collection of samples or data, but it does not fit into any of the predefined categories."
+sorting fraction,16,Other,llm,MEDIUM,"Sorting fraction could refer to a specific subset of cells or samples, but it does not fit into any of the predefined categories."
+oxygen,16,Other,llm,LOW,"Oxygen is not a characteristic of a biospecimen, but rather an environmental factor that may affect the biospecimen."
+detachment,15,Other,llm,LOW,"Detachment is not a characteristic of a biospecimen, but rather a process or event that may occur during sample collection or processing."
+primers,15,Other,llm,LOW,"Primers are not a characteristic of a biospecimen, but rather a type of molecular reagent used in laboratory experiments."
+gel bead version,15,Other,llm,LOW,No clear connection to any predefined category
+rip,15,Other,llm,LOW,No clear connection to any predefined category
+ubi,14,Other,llm,LOW,No clear connection to any predefined category
+measure,14,Other,llm,LOW,"Measure is a vague term that could refer to various aspects of the biospecimen, but it does not fit well into any specific category."
+Weight,13,Other,llm,LOW,Weight is a physical characteristic that does not fit well into any specific category related to biospecimens.
+pooling,13,Other,llm,LOW,Pooling is a process or technique that does not fit well into any specific category related to biospecimens.
+functional connectivity,13,Other,llm,LOW,Functional connectivity is a complex concept that doesn't fit well into any of the predefined categories.
+paradigm,13,Other,llm,LOW,Paradigm is a broad concept that doesn't fit well into any of the predefined categories.
+div,12,Other,llm,LOW,This label is unclear and does not fit into any specific category.
+sorting probe,12,Other,llm,LOW,This label is unclear and does not fit into any specific category.
+product,12,Other,llm,LOW,This label is unclear and does not fit into any specific category.
+oxygenation,12,Other,llm,HIGH,"Oxygenation is a process or condition, not a characteristic of a biospecimen."
+expressing,12,Other,llm,HIGH,"Expressing is a process or condition, not a characteristic of a biospecimen."
+operator,12,Other,llm,HIGH,Operator is not a characteristic of a biospecimen.
+insertion site distance to gene,12,Other,llm,HIGH,"Insertion site distance to gene is a specific detail about a genetic modification, not a characteristic of a biospecimen."
+replica,12,Other,llm,HIGH,Replica is not a characteristic of a biospecimen.
+scale,12,Other,llm,LOW,"Scale is a vague term that could refer to many things, but it doesn't fit well into any of the predefined categories."
+technical replicates,12,Other,llm,LOW,"Technical replicates refer to repeated measurements or experiments, which doesn't fit well into any of the predefined categories."
+knockdown target,12,Other,llm,MEDIUM,"This label does not fit well into any predefined category, but it could be related to a specific experimental design or technique"
+submission date,12,Other,llm,LOW,"This label is not related to biomedical sample characteristics, but rather to the metadata of the sample submission"
+company,12,Other,llm,LOW,"This label is not related to biomedical sample characteristics, but rather to the metadata of the sample submission"
+drinking,12,Other,llm,LOW,"This label is not related to biomedical sample characteristics, but rather to the metadata of the sample submission or a specific experimental design"
+replicate experiment,12,Other,llm,LOW,"This label is not related to biomedical sample characteristics, but rather to the experimental design or methodology"
+chip antibody manufacturer,11,Other,llm,MEDIUM,Manufacturer information is not directly related to biospecimen characteristics
+salt.score,11,Other,llm,LOW,No clear connection to any predefined category
+library label_name,10,Other,llm,LOW,No clear connection to any predefined category
+metabolic activity,10,Other,llm,LOW,No clear connection to any predefined category
+animals pooled,10,Other,llm,LOW,No clear connection to any predefined category
+isolated by,10,Other,llm,LOW,No clear connection to any predefined category
+driver gene,10,Other,llm,HIGH,"Does not fit into any predefined category, as it refers to a specific gene that drives a particular biological process."
+transcription factor expression level,10,Other,llm,HIGH,"Does not fit into any predefined category, as it refers to the level of expression of a specific transcription factor."
+cutting enzymes,10,Other,llm,HIGH,"Does not fit into any predefined category, as it refers to a specific type of enzyme used in molecular biology techniques."
+chip antibody details,10,Other,llm,HIGH,"Does not fit into any predefined category, as it refers to specific details about antibodies used in a microarray chip experiment."
+antigen reactivity,10,Other,llm,HIGH,"Does not fit into any predefined category, as it refers to the reactivity of an antigen with an antibody or immune cell."
+number of cag repeats,9,Other,llm,HIGH,This label does not fit into any predefined category as it refers to a specific genetic characteristic.
+data presented in the manuscript,9,Other,llm,HIGH,This label does not fit into any predefined category as it refers to the content of a manuscript.
+hit.status,9,Other,llm,MEDIUM,This label does not fit into any predefined category as its meaning is unclear without more context.
+sorting criteria,9,Other,llm,MEDIUM,This label does not fit into any predefined category as its meaning is unclear without more context.
+well diameter in um,8,Other,llm,LOW,Well diameter in um is a physical measurement that does not fit into any specific biospecimen category.
+molecule purification,8,Other,llm,HIGH,"This label does not fit into any specific category, but it could be related to the process of sample preparation."
+clinical comments,8,Other,llm,HIGH,"This label does not fit into any specific category, but it could be related to additional information about the sample or patient."
+digestion enzyme,8,Other,llm,HIGH,"This label does not fit into any specific category, but it could be related to the process of sample preparation."
+incubation temperature,8,Other,llm,HIGH,"This label does not fit into any specific category, but it could be related to the conditions under which the sample was processed."
+chip antibody manufacturers,7,Other,llm,HIGH,"This label does not fit into any specific category, but it could be related to the reagents used in the experiment."
+bilirubin,7,Other,llm,HIGH,"Bilirubin is a biomarker, not a characteristic of a biospecimen"
+ast,7,Other,llm,HIGH,"AST is a biomarker, not a characteristic of a biospecimen"
+encode accession,7,Other,llm,HIGH,"Encode accession is a reference to a database, not a characteristic of a biospecimen"
+alt,7,Other,llm,LOW,ALT is ambiguous and could refer to a biomarker or other non-biospecimen characteristic
+variation,6,Other,llm,HIGH,"Variation is a general term that could refer to many things, not a characteristic of a biospecimen"
+Labeling_reference,6,Other,llm,HIGH,"Labeling reference is a reference to a protocol or method, not a characteristic of a biospecimen"
+Extraction_reference,6,Other,llm,HIGH,"Extraction reference is a reference to a protocol or method, not a characteristic of a biospecimen"
+Extraction_amount,6,Other,llm,HIGH,"Does not fit into any specific category, but could be related to sample processing"
+zone,6,Other,llm,LOW,"Could be related to sample location or processing, but unclear without more context"
+mating pair,6,Other,llm,LOW,"Could be related to sample collection or experimental design, but unclear without more context"
+ARN_quality,6,Other,llm,LOW,ARN_quality does not fit well into any category
+extraction batch,6,Other,llm,LOW,Extraction batch does not fit well into any category
+mother from,6,Other,llm,LOW,Mother from does not fit well into any category
+expression level,6,Other,llm,LOW,Expression level does not fit well into any category
+nitrogen,6,Other,llm,LOW,"Nitrogen is a chemical element, not a biospecimen characteristic"
+tubular shadows,6,Other,llm,LOW,"Tubular shadows are a radiological feature, not a biospecimen characteristic"
+exposed pollutants,6,Other,llm,LOW,"Exposed pollutants are an environmental factor, not a biospecimen characteristic"
+cross,6,Other,llm,LOW,"Cross is a vague term, not a biospecimen characteristic"
+behavior,6,Other,llm,LOW,"Behavior is a complex trait, not a biospecimen characteristic"
+mean number of oocysts,6,Other,llm,HIGH,"This label refers to a specific measurement or count, but it doesn't fit into any of the predefined categories."
+number of half-sclerotomes,6,Other,llm,HIGH,"This label refers to a specific measurement or count, but it doesn't fit into any of the predefined categories."
+Bra,6,Other,llm,LOW,This label is unclear and doesn't seem to fit into any of the predefined categories.
+body weight,6,Other,llm,HIGH,"This label refers to a specific measurement, but it doesn't fit into any of the predefined categories."
+sampling post confirm,6,Other,llm,LOW,This label is unclear and doesn't seem to fit into any of the predefined categories.
+library_strategy,5,Other,llm,LOW,"Library strategy is a term related to sequencing or genomics, but it does not fit well into any of the predefined categories."
+term accession number,5,Other,llm,LOW,"Term accession number is likely a reference to a database or cataloging system, but it does not fit well into any of the predefined categories."
+term source ref,5,Other,llm,LOW,Term source ref does not fit into any specific biomedical sample characteristic category
+experiment performed in,4,Other,llm,LOW,Experiment performed in does not fit into any specific biomedical sample characteristic category
+vector construct,4,Other,llm,LOW,"Vector construct is a term related to genetic engineering, but it doesn't fit well into any of the predefined categories."
+chip magnetic beads,4,Other,llm,LOW,"Chip magnetic beads are a type of laboratory tool, but it doesn't fit well into any of the predefined categories."
+gating,4,Other,llm,LOW,"Gating is a term related to flow cytometry, but it doesn't fit well into any of the predefined categories."
+express,4,Other,llm,LOW,"Express is a term related to gene expression, but it doesn't fit well into any of the predefined categories."
+isolation column,4,Other,llm,LOW,"Isolation column is a type of laboratory tool, but it doesn't fit well into any of the predefined categories."
+antibody lot number,4,Other,llm,HIGH,"This label does not fit into any of the predefined categories. It seems to be related to the antibody used in the experiment, but it does not describe a characteristic of the biospecimen."
+antibody antibody description,4,Other,llm,HIGH,"This label does not fit into any of the predefined categories. It seems to be related to the antibody used in the experiment, but it does not describe a characteristic of the biospecimen."
+immunology,4,Other,llm,HIGH,"This label does not fit into any of the predefined categories. It seems to be related to the field of study, but it does not describe a characteristic of the biospecimen."
+details,3,Other,llm,HIGH,This label is too vague and does not fit into any of the predefined categories.
+reactivity,3,Other,llm,LOW,"Reactivity is a broad term that could apply to various biological contexts, such as immune response or chemical reactions, but does not fit neatly into any of the predefined categories."
+assay type,3,Other,llm,LOW,"Assay type refers to the method or technique used for a biological experiment or measurement, which does not fit into any of the predefined categories focused on sample characteristics."
+clip antibody cat,2,Other,llm,LOW,"This label does not fit well with any of the predefined categories, as it seems to be related to a specific experimental or analytical technique."
+feature type,2,Other,llm,LOW,This label is too vague and does not fit well with any of the predefined categories.
+domain,2,Other,llm,LOW,Domain is a general term that does not fit well into any specific category
+par-clip,2,Other,llm,LOW,par-clip is a specific technique or method that does not fit well into any specific category
+data_type,2,Other,llm,LOW,data_type is a general term that does not fit well into any specific category
+treatment,71874,Treatment,keyword,HIGH,exact_match: treatment
+group,11700,Treatment,keyword,HIGH,exact_match: group
+vaccine,3535,Treatment,keyword,MEDIUM,keyword: vaccine
+segment type,1492,Treatment,similarity,MEDIUM,Similar to: treatment type (score: 0.769)
+treatment description,1095,Treatment,keyword,HIGH,exact_match: treatment
+temperature,1094,Treatment,llm,MEDIUM,"Temperature could be a condition or parameter of a treatment, such as a temperature-controlled environment for cell culture."
+treatmentshort,992,Treatment,keyword,LOW,pattern: .*treatment.*
+medium,949,Treatment,llm,MEDIUM,"Medium can refer to the culture medium used to grow cells or microorganisms, which can be considered a type of treatment or experimental condition."
+tuberculin skin test,938,Treatment,llm,HIGH,"Tuberculin skin test is a type of treatment or diagnostic test, which can be considered a type of treatment."
+drug treatment,934,Treatment,keyword,HIGH,exact_match: treatment
+treated with,920,Treatment,llm,HIGH,"Treated with is a clear indication of a treatment or intervention, which can be considered a type of treatment."
+delivery,804,Treatment,llm,MEDIUM,Delivery could refer to the administration of a treatment
+treatment group,792,Treatment,keyword,HIGH,exact_match: treatment
+control,757,Treatment,keyword,HIGH,exact_match: control
+stimulus,736,Treatment,llm,HIGH,Stimulus is a type of treatment or intervention applied to cells or organisms
+control description,731,Treatment,keyword,HIGH,exact_match: control
+chip_antibody,680,Treatment,llm,HIGH,Chip antibody refers to a type of treatment or intervention used in chromatin immunoprecipitation experiments
+response,667,Treatment,similarity,MEDIUM,Similar to: drug response (score: 0.762)
+irradiated,667,Treatment,llm,HIGH,Irradiated refers to a type of treatment or intervention involving exposure to radiation
+treatment duration,657,Treatment,keyword,HIGH,exact_match: treatment
+first vaccination,614,Treatment,llm,HIGH,Describes a specific treatment or intervention
+second vaccination,614,Treatment,llm,HIGH,Describes a specific treatment or intervention
+subgroup,601,Treatment,keyword,LOW,pattern: .*group.*
+selection marker,554,Treatment,llm,MEDIUM,Selection marker is related to the treatment or experimental condition of the sample
+groups,535,Treatment,keyword,LOW,pattern: .*group.*
+molecular subgroup,509,Treatment,keyword,LOW,pattern: .*group.*
+resistance,506,Treatment,similarity,MEDIUM,Similar to: drug resistance (score: 0.800)
+diagnostic_group,500,Treatment,keyword,LOW,pattern: .*group.*
+classification group,500,Treatment,keyword,HIGH,exact_match: group
+chemical compound,500,Treatment,keyword,MEDIUM,keyword: compound
+animal replicate,500,Treatment,similarity,MEDIUM,Similar to: animal treatment (score: 0.750)
+induced,500,Treatment,llm,MEDIUM,"Induced could refer to a treatment or experimental condition applied to a biospecimen, but the context is unclear."
+injection_materials,500,Treatment,llm,HIGH,Describes the treatment or intervention applied to the sample
+curative_intent,496,Treatment,llm,HIGH,Related to treatment goals or outcomes
+infected with/healthy control,476,Treatment,keyword,HIGH,exact_match: control
+vaccine doses,455,Treatment,keyword,MEDIUM,keyword: vaccine
+prior treatment,445,Treatment,keyword,HIGH,exact_match: treatment
+media,417,Treatment,llm,MEDIUM,"Media can refer to the culture medium used in experiments, which can be considered a type of treatment or experimental condition."
+response_group,398,Treatment,keyword,LOW,pattern: .*group.*
+grouping,395,Treatment,keyword,LOW,pattern: .*group.*
+vaccine type,387,Treatment,keyword,MEDIUM,keyword: vaccine
+current medication,374,Treatment,keyword,HIGH,exact_match: medication
+classification,369,Treatment,similarity,MEDIUM,Similar to: classification group (score: 0.824)
+replicate description,362,Treatment,similarity,MEDIUM,Similar to: treatment description (score: 0.810)
+experiment group,354,Treatment,keyword,HIGH,exact_match: group
+treatment location,353,Treatment,keyword,HIGH,exact_match: treatment
+amplification,341,Treatment,llm,MEDIUM,Could be a type of treatment or experimental condition
+chemotherapy,337,Treatment,keyword,MEDIUM,keyword: therapy
+ventilation,319,Treatment,llm,MEDIUM,"Ventilation can be a medical treatment, so it fits into the Treatment category."
+Prior Treatment,300,Treatment,keyword,HIGH,exact_match: treatment
+chip-antibody,298,Treatment,llm,MEDIUM,"The term 'chip-antibody' suggests a type of treatment or experimental condition, but it's not entirely clear."
+treatment administration route,296,Treatment,keyword,HIGH,exact_match: treatment
+treatment frequency,296,Treatment,keyword,HIGH,exact_match: treatment
+study group,285,Treatment,keyword,HIGH,exact_match: group
+diet,284,Treatment,llm,MEDIUM,Diet can be considered as a type of treatment
+medications/vitamin names,284,Treatment,llm,HIGH,Medications/vitamin names are a type of treatment
+stimulant,280,Treatment,llm,MEDIUM,Stimulant could be a type of treatment or intervention
+drug,278,Treatment,keyword,HIGH,exact_match: drug
+vaccination.assignment,275,Treatment,llm,HIGH,Vaccination assignment is a type of treatment or intervention
+experimental group,256,Treatment,keyword,HIGH,exact_match: group
+treatment dose,248,Treatment,keyword,HIGH,exact_match: treatment
+surgical_interval_mo,245,Treatment,llm,HIGH,"Refers to the time interval between surgical procedures, which is a treatment-related characteristic"
+treatment arm,232,Treatment,keyword,HIGH,exact_match: treatment
+genetic modification,227,Treatment,similarity,MEDIUM,Similar to: chemical modification (score: 0.780)
+treatment withdrawal,217,Treatment,keyword,HIGH,exact_match: treatment
+treatment initiation,217,Treatment,keyword,HIGH,exact_match: treatment
+recreational drugs,212,Treatment,keyword,LOW,pattern: .*drug.*
+prescription drugs,212,Treatment,keyword,LOW,pattern: .*drug.*
+active ingredient,212,Treatment,llm,HIGH,Active ingredient is a treatment
+treatment-outcome code,211,Treatment,keyword,LOW,pattern: .*treatment.*
+knockout,203,Treatment,llm,HIGH,Refers to a specific type of genetic modification or experimental design
+radiation.therapy,200,Treatment,keyword,MEDIUM,keyword: therapy
+primed,198,Treatment,llm,MEDIUM,Primed could refer to a treatment or preparation of the biospecimen or donor.
+treatment protocol,197,Treatment,keyword,HIGH,exact_match: treatment
+brain location,197,Treatment,similarity,MEDIUM,Similar to: treatment location (score: 0.750)
+experimental replicate,196,Treatment,similarity,MEDIUM,Similar to: experimental group (score: 0.750)
+case/control,191,Treatment,similarity,MEDIUM,Similar to: case or control (score: 0.815)
+rip antibody,182,Treatment,llm,MEDIUM,Could be related to treatment or intervention
+antibody manufacturer,182,Treatment,llm,MEDIUM,Could be related to treatment or intervention
+molecular subtype,176,Treatment,similarity,MEDIUM,Similar to: molecular subgroup (score: 0.800)
+treatment response,172,Treatment,keyword,HIGH,exact_match: treatment
+enzymatic treatment,168,Treatment,keyword,HIGH,exact_match: treatment
+vaccine group,168,Treatment,keyword,HIGH,exact_match: group
+dose group,167,Treatment,keyword,HIGH,exact_match: group
+protect outcome,167,Treatment,similarity,MEDIUM,Similar to: treatment outcome (score: 0.750)
+group description,162,Treatment,keyword,HIGH,exact_match: group
+inhibitor treatment,161,Treatment,keyword,HIGH,exact_match: treatment
+other_medication,158,Treatment,similarity,MEDIUM,Similar to: acute medication (score: 0.750)
+diabetes_medication,158,Treatment,llm,HIGH,"Diabetes medication is a type of treatment, which is a characteristic of the biospecimen."
+chip antibody lot,156,Treatment,llm,HIGH,"Chip antibody lot refers to a specific batch of antibodies used in an experiment, which could be considered a treatment or experimental condition."
+knockdown,147,Treatment,llm,HIGH,Knockdown is a type of treatment or experimental condition
+dose_group,144,Treatment,keyword,LOW,pattern: .*group.*
+batch group,120,Treatment,keyword,HIGH,exact_match: group
+exposed stress,118,Treatment,llm,MEDIUM,"Exposed stress could be a type of treatment or experimental condition, but it is not entirely clear without more context."
+previous treatments,113,Treatment,keyword,LOW,pattern: .*treatment.*
+vaccine regimen,112,Treatment,keyword,MEDIUM,keyword: vaccine
+drug dose,105,Treatment,keyword,HIGH,exact_match: drug
+watch and wait,104,Treatment,llm,HIGH,A treatment approach where no immediate intervention is taken
+Exposures,101,Treatment,llm,MEDIUM,"The label refers to the exposure of the biospecimen to certain conditions or substances, which could be related to treatment."
+hours post-treatment,99,Treatment,keyword,LOW,pattern: .*treatment.*
+vector,97,Treatment,llm,HIGH,Vector is a type of treatment or intervention
+therapy used,92,Treatment,keyword,HIGH,exact_match: therapy
+Group,89,Treatment,keyword,HIGH,exact_match: group
+antibiotic treatment,87,Treatment,keyword,HIGH,exact_match: treatment
+trial arm,87,Treatment,llm,HIGH,"This label likely refers to the treatment group or arm of a clinical trial, which is a characteristic of the sample."
+surgery,85,Treatment,llm,HIGH,"This label likely refers to a medical intervention or treatment, which is a characteristic of the sample."
+healthy control,81,Treatment,keyword,HIGH,exact_match: control
+prophylaxis,81,Treatment,llm,HIGH,Prophylaxis is a type of treatment or preventive measure.
+control/intervention,80,Treatment,keyword,MEDIUM,keyword: intervention
+exercise intensity,80,Treatment,llm,MEDIUM,Exercise intensity could be a treatment or intervention condition.
+challenge,79,Treatment,llm,HIGH,"In a biological context, a 'challenge' often refers to a treatment or intervention designed to test the response of a system or organism."
+treatment status,76,Treatment,keyword,HIGH,exact_match: treatment
+surgery type,76,Treatment,llm,HIGH,Surgery type is a form of treatment that can be applied to a biospecimen donor.
+ear treatment,74,Treatment,keyword,HIGH,exact_match: treatment
+radiation,74,Treatment,llm,HIGH,"Radiation is a type of treatment, and this label likely refers to the treatment group or condition of the biospecimen donor."
+bone-marrow grafting status,74,Treatment,llm,HIGH,"Bone-marrow grafting status is a type of treatment or intervention, and this label likely refers to the treatment group or condition of the biospecimen donor."
+bone-marrow grafting type,74,Treatment,llm,HIGH,"Bone-marrow grafting type is a type of treatment or intervention, and this label likely refers to the treatment group or condition of the biospecimen donor."
+injected virus,73,Treatment,llm,HIGH,"Injected virus is a type of treatment or intervention, and this label likely refers to the treatment group or condition of the biospecimen donor."
+therapy,72,Treatment,keyword,HIGH,exact_match: therapy
+variant type,72,Treatment,similarity,MEDIUM,Similar to: vaccine type (score: 0.750)
+compound,71,Treatment,keyword,MEDIUM,keyword: compound
+biological drug,70,Treatment,keyword,HIGH,exact_match: drug
+alcohol,69,Treatment,llm,HIGH,Alcohol is a type of treatment or intervention
+number of immunization boost,66,Treatment,llm,HIGH,"This label suggests a treatment or intervention, specifically the number of immunization boosts, which fits well with the Treatment category."
+treatment_duration,65,Treatment,keyword,LOW,pattern: .*treatment.*
+control or als,65,Treatment,keyword,HIGH,exact_match: control
+vector treatment,64,Treatment,keyword,HIGH,exact_match: treatment
+previous drug treatment,64,Treatment,keyword,HIGH,exact_match: treatment
+rounds_to_cure,64,Treatment,llm,HIGH,Rounds to cure is a term used to describe the number of treatments or rounds of treatment required to cure a disease. It is a treatment-related label.
+clinical trial phase,64,Treatment,llm,HIGH,Clinical trial phase is a term used to describe the stage of a clinical trial. It is a treatment-related label.
+antibody group,62,Treatment,keyword,HIGH,exact_match: group
+surgical treatment,62,Treatment,keyword,HIGH,exact_match: treatment
+vaccine administered,62,Treatment,keyword,MEDIUM,keyword: vaccine
+other biologic medicines use,62,Treatment,llm,HIGH,This label is related to the treatment or medication used by the patient.
+pathogen exposure,60,Treatment,llm,MEDIUM,Pathogen exposure can be considered a type of treatment or intervention.
+viral challenge,60,Treatment,llm,HIGH,Viral challenge is a type of treatment or intervention used in biomedical research.
+rabbit group,57,Treatment,keyword,HIGH,exact_match: group
+treatment outcome,57,Treatment,keyword,HIGH,exact_match: treatment
+culture platform,57,Treatment,llm,MEDIUM,"Culture platform might refer to the conditions or method used to culture cells, which could be considered a type of treatment or experimental condition."
+debris removal,56,Treatment,llm,MEDIUM,This could be a treatment or procedure
+perturbation class,54,Treatment,llm,HIGH,Perturbation class likely refers to the type of treatment or intervention applied to the biospecimen.
+perturbation,54,Treatment,llm,HIGH,"Similar to perturbation class, perturbation likely refers to the treatment or intervention applied to the biospecimen."
+cross-linked,52,Treatment,llm,MEDIUM,Cross-linking is a type of treatment or processing step that can be applied to biospecimens.
+route administered,52,Treatment,llm,HIGH,"Route administered refers to how a treatment was given, which aligns with the definition of Treatment."
+vehicle,51,Treatment,llm,MEDIUM,"Vehicle could refer to the medium or agent used in treatment, which somewhat aligns with the Treatment category, though it's less direct than other labels."
+group label,48,Treatment,keyword,HIGH,exact_match: group
+treatment_duration_in_hours,48,Treatment,keyword,LOW,pattern: .*treatment.*
+treatment category,48,Treatment,keyword,HIGH,exact_match: treatment
+treatment prior to second surgery,47,Treatment,keyword,HIGH,exact_match: treatment
+over-expression,46,Treatment,llm,MEDIUM,"Over-expression refers to the increased production of a particular gene or protein, which could be a result of a treatment or experimental condition."
+vaccine administration,45,Treatment,keyword,MEDIUM,keyword: vaccine
+survival group,44,Treatment,keyword,HIGH,exact_match: group
+intervention group,44,Treatment,keyword,HIGH,exact_match: group
+translocation,44,Treatment,similarity,MEDIUM,Similar to: treatment location (score: 0.774)
+prior chemotherapy,43,Treatment,keyword,MEDIUM,keyword: therapy
+antibody treatment,42,Treatment,keyword,HIGH,exact_match: treatment
+main group,42,Treatment,keyword,HIGH,exact_match: group
+length of exposure,42,Treatment,llm,HIGH,"This label refers to the duration of exposure to a treatment or condition, which is a characteristic of the treatment."
+treatments,40,Treatment,keyword,LOW,pattern: .*treatment.*
+nicotine,40,Treatment,llm,HIGH,"This label refers to a specific treatment or substance, which is a characteristic of the treatment."
+oxygen flow,40,Treatment,llm,HIGH,"This label refers to a specific treatment or condition, which is a characteristic of the treatment."
+experimental repeat,39,Treatment,similarity,MEDIUM,Similar to: experimental group (score: 0.811)
+radiation exposure,39,Treatment,llm,HIGH,"This label refers to a specific treatment or condition, which is a characteristic of the treatment."
+postsurgical-treatment,38,Treatment,keyword,LOW,pattern: .*treatment.*
+isogenic_group,38,Treatment,keyword,LOW,pattern: .*group.*
+genomic modification,38,Treatment,similarity,MEDIUM,Similar to: chemical modification (score: 0.829)
+drug concentration,37,Treatment,keyword,HIGH,exact_match: drug
+library prep kit,37,Treatment,llm,MEDIUM,Library prep kit can refer to a type of treatment or protocol used to prepare biospecimens for sequencing.
+virus-stimulation,37,Treatment,llm,HIGH,Virus-stimulation refers to a type of treatment or protocol used to stimulate a response in biospecimens.
+perturbation type,37,Treatment,llm,HIGH,"Perturbation type refers to the type of treatment or intervention applied to a biological sample, which aligns with the Treatment category."
+first-line therapy,36,Treatment,keyword,HIGH,exact_match: therapy
+clinical group,36,Treatment,keyword,HIGH,exact_match: group
+environment,36,Treatment,llm,MEDIUM,"Environment could refer to the conditions under which a biological sample is grown or treated, which aligns with the Treatment category."
+inhibitor removal,36,Treatment,llm,HIGH,"This label refers to a specific treatment or intervention applied to the sample, which is a characteristic of the sample."
+medicine,36,Treatment,llm,HIGH,"This label refers to a specific treatment or intervention applied to the sample, which is a characteristic of the sample."
+donation source,35,Treatment,similarity,MEDIUM,Similar to: control source (score: 0.759)
+untreated/treated,34,Treatment,llm,HIGH,"This label refers to whether the biospecimen has received treatment or not, which is a characteristic of the treatment category."
+tretment,33,Treatment,similarity,HIGH,Similar to: treatment (score: 0.941)
+cultivation,32,Treatment,llm,MEDIUM,"This label could be related to the treatment or growth conditions of a biospecimen, which fits with the Treatment category."
+treatment before challenge,31,Treatment,keyword,HIGH,exact_match: treatment
+chemical treatment,30,Treatment,keyword,HIGH,exact_match: treatment
+no treatment,30,Treatment,keyword,HIGH,exact_match: treatment
+treatment_effect,30,Treatment,keyword,LOW,pattern: .*treatment.*
+clinical_subgroup,29,Treatment,keyword,LOW,pattern: .*group.*
+treatment concentration,29,Treatment,keyword,HIGH,exact_match: treatment
+genetic modifications,28,Treatment,similarity,MEDIUM,Similar to: chemical modification (score: 0.762)
+growth temperature,28,Treatment,llm,HIGH,"Growth temperature is a condition under which cells or organisms are cultured, which fits well with the treatment category."
+prior systemic therapy,26,Treatment,keyword,HIGH,exact_match: therapy
+current systemic therapy,26,Treatment,keyword,HIGH,exact_match: therapy
+treatment condition/type,24,Treatment,keyword,HIGH,exact_match: treatment
+pharmacologic treatment type,24,Treatment,keyword,HIGH,exact_match: treatment
+os_group_median,24,Treatment,keyword,LOW,pattern: .*group.*
+implantation,24,Treatment,llm,HIGH,"Implantation refers to the insertion of a device or material into the body, which is a type of treatment"
+vasopressor,24,Treatment,llm,HIGH,"This label refers to a type of medication used to treat low blood pressure, which fits into the Treatment category."
+drug administration,23,Treatment,keyword,HIGH,exact_match: drug
+treatment effect,22,Treatment,keyword,HIGH,exact_match: treatment
+duration of treatment,22,Treatment,keyword,HIGH,exact_match: treatment
+other treatment,22,Treatment,keyword,HIGH,exact_match: treatment
+modification,22,Treatment,llm,MEDIUM,Modification could refer to a treatment or intervention applied to the specimen donor or cell line.
+oxygen level,22,Treatment,llm,MEDIUM,Oxygen level could refer to a treatment condition or culture condition.
+injected with,22,Treatment,llm,HIGH,Injected with refers to a treatment or intervention applied to the specimen donor or cell line.
+growth medium/treatment,21,Treatment,keyword,LOW,pattern: .*treatment.*
+chemical probe,21,Treatment,keyword,MEDIUM,keyword: chemical
+antibody target description,21,Treatment,llm,HIGH,Antibody target description is a type of treatment or intervention
+Treatment,20,Treatment,keyword,HIGH,exact_match: treatment
+fed with,20,Treatment,llm,MEDIUM,fed with could be related to the treatment or diet of the donor.
+Shear exposure,20,Treatment,llm,MEDIUM,Shear exposure could be a type of treatment or intervention
+treatment_type,19,Treatment,keyword,LOW,pattern: .*treatment.*
+drug response,19,Treatment,keyword,HIGH,exact_match: drug
+desiccation,19,Treatment,llm,HIGH,Desiccation is a process that can be applied to biospecimens as a treatment or preservation method.
+genetic engineering,19,Treatment,llm,HIGH,"Genetic engineering is a type of treatment or modification applied to biospecimens, such as cells or organisms."
+drug resistance,18,Treatment,keyword,HIGH,exact_match: drug
+compound concentration,18,Treatment,keyword,MEDIUM,keyword: compound
+experiment grouping,18,Treatment,keyword,LOW,pattern: .*group.*
+translocations,18,Treatment,similarity,MEDIUM,Similar to: treatment location (score: 0.750)
+construct expression,18,Treatment,llm,HIGH,"Construct expression refers to the expression of a specific genetic construct, which can be a result of genetic engineering or other treatments."
+culture format,18,Treatment,llm,MEDIUM,Culture format could be a treatment condition or growth condition of the biospecimen
+expression construct,18,Treatment,llm,MEDIUM,Expression construct could be a treatment condition or a way to manipulate the biospecimen
+art treatment,17,Treatment,keyword,HIGH,exact_match: treatment
+treatment/infection,16,Treatment,keyword,LOW,pattern: .*treatment.*
+has_drug,16,Treatment,keyword,LOW,pattern: .*drug.*
+seizure group,16,Treatment,keyword,HIGH,exact_match: group
+compound treatment,16,Treatment,keyword,HIGH,exact_match: treatment
+dementia status,16,Treatment,similarity,MEDIUM,Similar to: treatment status (score: 0.774)
+fasting,16,Treatment,llm,MEDIUM,"The label could refer to a treatment or intervention, such as fasting, which is a specific condition or regimen."
+mode of growth,16,Treatment,llm,MEDIUM,"Mode of growth could refer to the conditions under which cells or organisms are grown, which might be related to treatment or culture conditions."
+gene_knockout,16,Treatment,llm,HIGH,"Gene knockout is a specific type of genetic modification, which could be considered a treatment or intervention."
+polarization state,15,Treatment,similarity,MEDIUM,Similar to: polarization treatment (score: 0.850)
+pretreatment,14,Treatment,keyword,LOW,pattern: .*treatment.*
+subset group,14,Treatment,keyword,HIGH,exact_match: group
+case or control,14,Treatment,keyword,HIGH,exact_match: control
+experimental run,14,Treatment,similarity,MEDIUM,Similar to: experimental group (score: 0.882)
+vaccination_status,14,Treatment,llm,HIGH,"Refers to whether a subject has received a vaccination, which is a type of treatment"
+antigenic stimulation,14,Treatment,llm,HIGH,Antigenic stimulation is a type of treatment or intervention that stimulates an immune response.
+risk group,13,Treatment,keyword,HIGH,exact_match: group
+transplant,13,Treatment,llm,HIGH,Transplant is a type of treatment or intervention.
+treatment of mice,12,Treatment,keyword,HIGH,exact_match: treatment
+treatment_dose,12,Treatment,keyword,LOW,pattern: .*treatment.*
+Drug,12,Treatment,keyword,HIGH,exact_match: drug
+analysis group,12,Treatment,keyword,HIGH,exact_match: group
+chemical,12,Treatment,keyword,MEDIUM,keyword: chemical
+chemical modification,12,Treatment,keyword,MEDIUM,keyword: chemical
+chronic medication,12,Treatment,keyword,HIGH,exact_match: medication
+acute medication,12,Treatment,keyword,HIGH,exact_match: medication
+polarization treatment,12,Treatment,keyword,HIGH,exact_match: treatment
+treatment type,12,Treatment,keyword,HIGH,exact_match: treatment
+autophagy induction,12,Treatment,llm,HIGH,"Autophagy induction is a type of treatment or intervention, specifically a cellular process."
+oxygen tension,12,Treatment,llm,MEDIUM,"This label could refer to a specific condition or treatment protocol, but it is not entirely clear."
+angiography,12,Treatment,llm,MEDIUM,"This label refers to a medical imaging technique, which could be part of a treatment protocol."
+genetic_modification,12,Treatment,llm,HIGH,Genetic modification is a type of treatment or intervention.
+surgical approach,12,Treatment,llm,HIGH,"Surgical approach refers to the method or technique used to perform a surgical procedure, which is a type of treatment."
+plating,11,Treatment,llm,MEDIUM,Plating could refer to a treatment or experimental condition
+antibody used,11,Treatment,llm,HIGH,Antibody used is a type of treatment or experimental condition
+antigen capture,11,Treatment,llm,MEDIUM,Antigen capture could refer to a treatment or experimental condition
+camp treatment/level,10,Treatment,keyword,LOW,pattern: .*treatment.*
+before or after treatment,10,Treatment,keyword,HIGH,exact_match: treatment
+rescue,10,Treatment,llm,MEDIUM,Could refer to a treatment or intervention
+intensive care,10,Treatment,llm,HIGH,Refers to a specific type of medical treatment or care.
+knockout group,9,Treatment,keyword,HIGH,exact_match: group
+treatment timing,9,Treatment,keyword,HIGH,exact_match: treatment
+antibody name,9,Treatment,similarity,MEDIUM,Similar to: antibody treatment (score: 0.774)
+mutation frequency,9,Treatment,similarity,MEDIUM,Similar to: treatment frequency (score: 0.757)
+growth factors in the culture medium,9,Treatment,llm,HIGH,"This label refers to the treatment or culture conditions of the biospecimen, specifically the growth factors used."
+antibody maker,9,Treatment,llm,HIGH,The term 'antibody maker' suggests a treatment or intervention that involves the production of antibodies.
+vaccine dose,8,Treatment,keyword,MEDIUM,keyword: vaccine
+selection pressure drugs,8,Treatment,keyword,LOW,pattern: .*drug.*
+genotype/treatment,8,Treatment,keyword,LOW,pattern: .*treatment.*
+treatment/group,8,Treatment,keyword,LOW,pattern: .*treatment.*
+culture/treatment,8,Treatment,keyword,LOW,pattern: .*treatment.*
+exogenous treatment,8,Treatment,keyword,HIGH,exact_match: treatment
+nitrogen source,8,Treatment,similarity,MEDIUM,Similar to: control source (score: 0.759)
+overexpressing,8,Treatment,llm,HIGH,Overexpressing implies a genetic modification or treatment that results in the increased production of a particular gene or protein.
+growth phase/media,8,Treatment,llm,HIGH,"Growth phase/media suggests a specific condition or environment in which cells or organisms are grown, which is a type of treatment or intervention."
+secondary antibody,8,Treatment,llm,HIGH,"Secondary antibody implies a treatment or intervention that involves the use of antibodies, which is a type of treatment or intervention."
+primary antibody,8,Treatment,llm,HIGH,Primary antibody is a type of treatment or intervention.
+transient expression,8,Treatment,llm,MEDIUM,Transient expression could be related to a specific treatment or experimental condition.
+animal treatment,7,Treatment,keyword,HIGH,exact_match: treatment
+genotype & treatment,6,Treatment,keyword,HIGH,exact_match: treatment
+group_tag,6,Treatment,keyword,LOW,pattern: .*group.*
+antibody lot,6,Treatment,similarity,MEDIUM,Similar to: antibody group (score: 0.769)
+testosterone treated,6,Treatment,llm,HIGH,Indicates a specific treatment applied to the sample
+gene induction,6,Treatment,llm,HIGH,Indicates a specific treatment or manipulation applied to the sample
+overexpressed target,6,Treatment,llm,HIGH,Indicates a specific treatment or manipulation applied to the sample
+methylation-enrichment,6,Treatment,llm,MEDIUM,Methylation-enrichment is a type of treatment
+media supplement,6,Treatment,llm,MEDIUM,Media supplement is a type of treatment
+chip antibody reference,6,Treatment,llm,MEDIUM,Chip antibody reference might be related to a treatment or experimental condition
+stable knockdown,6,Treatment,llm,MEDIUM,This label seems to describe a treatment or experimental condition.
+antibody cat,6,Treatment,llm,HIGH,The term 'antibody cat' likely refers to a category of antibodies used in treatment or research.
+depletion,5,Treatment,llm,HIGH,Depletion is a type of treatment or experimental condition.
+spike protein used,5,Treatment,llm,HIGH,"Spike protein is often used in treatments or experimental conditions, especially in the context of COVID-19 research."
+mice group,4,Treatment,keyword,HIGH,exact_match: group
+phase growth,4,Treatment,llm,MEDIUM,Phase growth could refer to a treatment condition or stage
+oxygen status,4,Treatment,llm,MEDIUM,Oxygen status could refer to a treatment condition or environment
+strategy,4,Treatment,llm,MEDIUM,Strategy could refer to a treatment approach or plan
+media additions,4,Treatment,llm,HIGH,"Media additions are substances added to cell cultures to promote growth, which can be considered a type of treatment."
+culture supplement,4,Treatment,llm,HIGH,"Culture supplements are substances added to cell cultures to promote growth, which can be considered a type of treatment."
+control source,3,Treatment,keyword,HIGH,exact_match: control
+treatment_term_name,2,Treatment,keyword,LOW,pattern: .*treatment.*
+affinity purification,2,Treatment,llm,MEDIUM,"Affinity purification is a laboratory technique used to isolate specific molecules, which could be considered a type of treatment or processing step for biospecimens."
+ligation,2,Treatment,llm,HIGH,"Ligation is a medical treatment or procedure, which fits well with the treatment category."
+selection media,2,Treatment,llm,HIGH,Selection media is a type of treatment condition for cell culture
+solvent,2,Treatment,llm,MEDIUM,Solvent can be a component of a treatment condition
+transplanted with,2,Treatment,llm,HIGH,"This label appears to describe a treatment or intervention, which aligns with the Treatment category."
+protocol,3271,Treatment Dosage Regimen,keyword,MEDIUM,keyword: protocol
+region,2915,Treatment Dosage Regimen,similarity,MEDIUM,Similar to: regimen (score: 0.769)
+dose,1480,Treatment Dosage Regimen,keyword,HIGH,exact_match: dose
+extraction_protocol,970,Treatment Dosage Regimen,keyword,MEDIUM,keyword: protocol
+chip_protocol_chromatin_amount,804,Treatment Dosage Regimen,keyword,MEDIUM,keyword: protocol
+chip_protocol,804,Treatment Dosage Regimen,keyword,MEDIUM,keyword: protocol
+chip_protocol_bead_type,680,Treatment Dosage Regimen,keyword,MEDIUM,keyword: protocol
+chip_protocol_antibody_amount,680,Treatment Dosage Regimen,keyword,MEDIUM,keyword: protocol
+chip_protocol_bead_amount,680,Treatment Dosage Regimen,keyword,MEDIUM,keyword: protocol
+growth protocol,654,Treatment Dosage Regimen,keyword,MEDIUM,keyword: protocol
+duration,530,Treatment Dosage Regimen,keyword,HIGH,exact_match: duration
+immunization dose,500,Treatment Dosage Regimen,keyword,HIGH,exact_match: dose
+library preparation method,500,Treatment Dosage Regimen,similarity,MEDIUM,Similar to: library preparation protocol (score: 0.815)
+protocol description,492,Treatment Dosage Regimen,keyword,MEDIUM,keyword: protocol
+concentration,427,Treatment Dosage Regimen,keyword,HIGH,exact_match: concentration
+vaccination,404,Treatment Dosage Regimen,similarity,MEDIUM,Similar to: vaccination dose (score: 0.815)
+mutation,354,Treatment Dosage Regimen,similarity,MEDIUM,Similar to: duration (score: 0.750)
+education,300,Treatment Dosage Regimen,similarity,MEDIUM,Similar to: duration (score: 0.824)
+library preparation,277,Treatment Dosage Regimen,similarity,MEDIUM,Similar to: library preparation protocol (score: 0.809)
+immunization,265,Treatment Dosage Regimen,similarity,MEDIUM,Similar to: immunization dose (score: 0.828)
+regimen,256,Treatment Dosage Regimen,keyword,MEDIUM,keyword: regimen
+library protocol,215,Treatment Dosage Regimen,keyword,MEDIUM,keyword: protocol
+vaccination route,188,Treatment Dosage Regimen,similarity,MEDIUM,Similar to: vaccination dose (score: 0.848)
+duration of illness,168,Treatment Dosage Regimen,keyword,HIGH,exact_match: duration
+culture duration,134,Treatment Dosage Regimen,keyword,HIGH,exact_match: duration
+protocol number,121,Treatment Dosage Regimen,keyword,MEDIUM,keyword: protocol
+stimulation protocol,119,Treatment Dosage Regimen,keyword,MEDIUM,keyword: protocol
+stimulation duration,102,Treatment Dosage Regimen,keyword,HIGH,exact_match: duration
+vaccination dose,92,Treatment Dosage Regimen,keyword,HIGH,exact_match: dose
+vaccination boost,92,Treatment Dosage Regimen,similarity,MEDIUM,Similar to: vaccination dose (score: 0.848)
+infectious_dose,79,Treatment Dosage Regimen,keyword,LOW,pattern: .*dose.*
+derivation,65,Treatment Dosage Regimen,similarity,MEDIUM,Similar to: duration (score: 0.778)
+illness_duration,64,Treatment Dosage Regimen,keyword,LOW,pattern: .*duration.*
+induction,57,Treatment Dosage Regimen,similarity,MEDIUM,Similar to: induration (score: 0.842)
+psoriasis duration,52,Treatment Dosage Regimen,keyword,HIGH,exact_match: duration
+extract_protocol,51,Treatment Dosage Regimen,keyword,MEDIUM,keyword: protocol
+inoculation,45,Treatment Dosage Regimen,similarity,MEDIUM,Similar to: inoculation dose (score: 0.815)
+duration in hours,36,Treatment Dosage Regimen,keyword,HIGH,exact_match: duration
+indication,36,Treatment Dosage Regimen,similarity,MEDIUM,Similar to: induration (score: 0.800)
+extract protocol,33,Treatment Dosage Regimen,keyword,MEDIUM,keyword: protocol
+viral concentration,30,Treatment Dosage Regimen,keyword,HIGH,exact_match: concentration
+virus added,30,Treatment Dosage Regimen,similarity,MEDIUM,Similar to: virus dose (score: 0.762)
+schedule,30,Treatment Dosage Regimen,llm,MEDIUM,"This label could refer to the schedule of doses of a medicine, which is part of the dosage regimen."
+study protocol,28,Treatment Dosage Regimen,keyword,MEDIUM,keyword: protocol
+lung radiation dose,27,Treatment Dosage Regimen,keyword,HIGH,exact_match: dose
+Duration of psoriasis,26,Treatment Dosage Regimen,keyword,HIGH,exact_match: duration
+Induration,26,Treatment Dosage Regimen,keyword,LOW,pattern: .*duration.*
+vaccination state,20,Treatment Dosage Regimen,similarity,MEDIUM,Similar to: vaccination dose (score: 0.848)
+digestion protocol,18,Treatment Dosage Regimen,keyword,MEDIUM,keyword: protocol
+labeling protocol,16,Treatment Dosage Regimen,keyword,MEDIUM,keyword: protocol
+library preparation protocol,15,Treatment Dosage Regimen,keyword,MEDIUM,keyword: protocol
+virus dose,15,Treatment Dosage Regimen,keyword,HIGH,exact_match: dose
+weekly dosing,15,Treatment Dosage Regimen,llm,HIGH,"Weekly dosing refers to a specific schedule of doses, which is a characteristic of a treatment dosage regimen."
+inoculation dose,12,Treatment Dosage Regimen,keyword,HIGH,exact_match: dose
+dietary regiment,12,Treatment Dosage Regimen,keyword,MEDIUM,keyword: regimen
+duration of cultivation,12,Treatment Dosage Regimen,keyword,HIGH,exact_match: duration
+immunization route,12,Treatment Dosage Regimen,similarity,MEDIUM,Similar to: immunization dose (score: 0.857)
+symptom duration,10,Treatment Dosage Regimen,keyword,HIGH,exact_match: duration
+Extraction_concentration,6,Treatment Dosage Regimen,keyword,LOW,pattern: .*concentration.*
+protocols,6,Treatment Dosage Regimen,keyword,MEDIUM,keyword: protocol
+culture variation,5,Treatment Dosage Regimen,similarity,MEDIUM,Similar to: culture duration (score: 0.848)
+extraction_protocol_fragmentation,3,Treatment Dosage Regimen,keyword,MEDIUM,keyword: protocol
+duration_units,2,Treatment Dosage Regimen,keyword,LOW,pattern: .*duration.*
diff --git a/RDAS_RDOMICS/scripts/sample_characteristics_harmonization/similarity_cutoff_evaluation/assignments_cutoff_0_70.csv b/RDAS_RDOMICS/scripts/sample_characteristics_harmonization/similarity_cutoff_evaluation/assignments_cutoff_0_70.csv
new file mode 100644
index 0000000..a258204
--- /dev/null
+++ b/RDAS_RDOMICS/scripts/sample_characteristics_harmonization/similarity_cutoff_evaluation/assignments_cutoff_0_70.csv
@@ -0,0 +1,535 @@
+label,count,best_reference_label,best_similarity_score,assigned_category,assigned_at_0_70,assigned_at_0_75,assigned_at_0_80
+genotype,46776,host genotype,0.7619047619047619,Biospecimen Organism,True,True,False
+batch,9770,batch id,0.7692307692307693,External_sample_id,True,True,False
+genotype/variation,6816,mouse genotype/variation,0.8571428571428571,Biospecimen Organism,True,True,True
+replicate,5824,replicate id,0.8571428571428571,External_sample_id,True,True,True
+antibody,4446,antibody group,0.7272727272727273,Treatment,True,False,False
+clinical info,3680,clinical diagnosis,0.7741935483870968,Biospecimen Disease Condition,True,True,False
+visit,3653,visit day,0.7142857142857143,Biospecimen Age,True,False,False
+histology,3618,histopathology,0.782608695652174,Biospecimen Disease Condition,True,True,False
+plate,3492,plate id,0.7692307692307693,External_sample_id,True,True,False
+region,2915,regimen,0.7692307692307693,Treatment Dosage Regimen,True,True,False
+molecule subtype,2882,cell subtype,0.7142857142857143,Biospecimen Type,True,False,False
+site,2620,side,0.75,External_sample_id,True,True,False
+segment,2380,reagent,0.7142857142857143,Biospecimen Age,True,False,False
+stimulation,2378,cell stimulation,0.8148148148148148,Biospecimen Type,True,True,True
+location,2284,location/side,0.7619047619047619,External_sample_id,True,True,False
+phenotype,1959,cell phenotype,0.782608695652174,Biospecimen Type,True,True,False
+experiment,1725,experimental day,0.7692307692307693,Biospecimen Age,True,True,False
+reference,1682,sample_reference,0.72,External_sample_id,True,False,False
+source,1670,source id,0.8,External_sample_id,True,True,True
+datatype description,1606,age description,0.8,Biospecimen Age,True,True,True
+library type,1600,library id,0.7272727272727273,External_sample_id,True,False,False
+collection_method,1517,collection time,0.75,Biospecimen Age,True,True,False
+well,1500,cell,0.75,Biospecimen Type,True,True,False
+segment type,1492,treatment type,0.7692307692307693,Treatment,True,True,False
+surgical status,1417,surgical treatment,0.7272727272727273,Treatment,True,False,False
+biological replicate,1375,biological sex,0.7058823529411765,Biospecimen Sex,True,False,False
+tag,1317,stage,0.75,Biospecimen Age,True,True,False
+culture,1264,culture age,0.7777777777777778,Biospecimen Age,True,True,False
+animal,1261,animal id,0.8,External_sample_id,True,True,True
+clinical status,1187,clinical stage,0.8275862068965517,Biospecimen Age,True,True,True
+roi number,1177,mouse number,0.7272727272727273,Biospecimen Organism,True,False,False
+protection,1172,cell projection,0.72,Biospecimen Type,True,False,False
+status,1055,cell status,0.7058823529411765,Biospecimen Type,True,False,False
+material,1047,maternalage,0.7368421052631579,Biospecimen Age,True,False,False
+library prep,1030,library barcode,0.7407407407407407,External_sample_id,True,False,False
+primary site,1010,primary tumor site,0.8,Biospecimen Disease Condition,True,True,True
+fraction,1003,age fraction,0.8,Biospecimen Age,True,True,True
+lab description,997,age description,0.8666666666666667,Biospecimen Age,True,True,True
+subtype,994,cell subtype,0.7368421052631579,Biospecimen Type,True,False,False
+platesimple,992,patient sample,0.72,External_sample_id,True,False,False
+experiment_type,970,experimental day,0.7096774193548387,Biospecimen Age,True,False,False
+infected with,898,infected host,0.7692307692307693,Biospecimen Organism,True,True,False
+culture result,894,culture age,0.72,Biospecimen Age,True,False,False
+survival_yr,876,survival year,0.8333333333333334,Biospecimen Age,True,True,True
+site_onset,876,age_onset,0.7368421052631579,Biospecimen Age,True,False,False
+clone,871,clone id,0.7692307692307693,External_sample_id,True,True,False
+morphology,764,cell morphology,0.8,Biospecimen Type,True,True,True
+study,741,studyid,0.8333333333333334,External_sample_id,True,True,True
+background,730,strain background,0.7407407407407407,Biospecimen Organism,True,False,False
+case number,726,cell number,0.8181818181818182,Biospecimen Type,True,True,True
+chip_antibody_lot,696,chip_antibody_provider,0.7692307692307693,External_sample_id,True,True,False
+genetic background,683,cell line background,0.7368421052631579,Biospecimen Type,True,False,False
+chip_antibody,680,chip_antibody_provider,0.7428571428571429,External_sample_id,True,False,False
+response,667,drug response,0.7619047619047619,Treatment,True,True,False
+os_status,656,mouse status,0.7619047619047619,Biospecimen Organism,True,True,False
+transduction,629,cell transduction,0.8275862068965517,Biospecimen Type,True,True,True
+first vaccination,614,time post-vaccination,0.7368421052631579,Biospecimen Age,True,False,False
+second vaccination,614,days since vaccination,0.7,Biospecimen Age,True,False,False
+brain region,595,brain tumor region,0.8,Biospecimen Disease Condition,True,True,True
+selection,567,mouse selection,0.75,Biospecimen Organism,True,True,False
+lane,566,lane id,0.7272727272727273,External_sample_id,True,False,False
+growth phase,558,growth stage,0.75,Biospecimen Age,True,True,False
+case,551,cage,0.75,Biospecimen Age,True,True,False
+recipient,534,recipient strain,0.72,Biospecimen Organism,True,False,False
+origin,525,organ,0.7272727272727273,Biospecimen Type,True,False,False
+resistance,506,drug resistance,0.8,Treatment,True,True,True
+date harvest,500,time harvest,0.8333333333333334,Biospecimen Age,True,True,True
+library preparation method,500,library preparation protocol,0.8148148148148148,Treatment Dosage Regimen,True,True,True
+sorted compartment,500,tissue compartment,0.7777777777777778,Biospecimen Type,True,True,False
+surgery number,500,usage number,0.7692307692307693,Biospecimen Age,True,True,False
+animal replicate,500,animal treatment,0.75,Treatment,True,True,False
+injection_roi,500,infection,0.7272727272727273,Biospecimen Disease Condition,True,False,False
+malaria_status,500,malaria strain,0.7142857142857143,Biospecimen Organism,True,False,False
+genotype_abbreviation,500,mouse genotype/variation,0.7111111111111111,Biospecimen Organism,True,False,False
+who category,493,tumor category,0.7692307692307693,Biospecimen Disease Condition,True,True,False
+diagnostic_mean,484,diagnostic_group,0.7096774193548387,Treatment,True,False,False
+pathogen,478,pathology,0.7058823529411765,Biospecimen Disease Condition,True,False,False
+population,477,cell population,0.8,Biospecimen Type,True,True,True
+library name,476,library barcode,0.7407407407407407,External_sample_id,True,False,False
+code,473,barcode,0.7272727272727273,External_sample_id,True,False,False
+death,460,death day,0.7142857142857143,Biospecimen Age,True,False,False
+lymphs,460,lymphocytes,0.7058823529411765,Biospecimen Type,True,False,False
+line,459,lineage,0.7272727272727273,Biospecimen Age,True,False,False
+vital status,450,covid status,0.75,External_sample_id,True,True,False
+survival_status,450,survival_time,0.7142857142857143,Biospecimen Age,True,False,False
+survival,444,survival time,0.7619047619047619,Biospecimen Age,True,True,False
+parasitemia,419,parasite stage,0.72,Biospecimen Age,True,False,False
+library well,412,library id,0.7272727272727273,External_sample_id,True,False,False
+library plate,412,library barcode,0.7142857142857143,External_sample_id,True,False,False
+array,407,array id,0.7692307692307693,External_sample_id,True,True,False
+vaccination,404,vaccination dose,0.8148148148148148,Treatment Dosage Regimen,True,True,True
+initial ich volume,399,initial tumor volume,0.7894736842105263,Biospecimen Disease Condition,True,True,False
+induction date,385,induction time,0.8571428571428571,Biospecimen Age,True,True,True
+library date,385,library id,0.8181818181818182,External_sample_id,True,True,True
+markers,382,cell markers,0.7368421052631579,Biospecimen Type,True,False,False
+exposure,381,exposure time,0.7619047619047619,Biospecimen Age,True,True,False
+chip antibody vendor,380,antibody vendor id,0.7894736842105263,External_sample_id,True,True,False
+classification,369,classification group,0.8235294117647058,Treatment,True,True,True
+who grade,367,tumor who grade,0.75,Biospecimen Disease Condition,True,True,False
+surface area,363,cell surface marker,0.7096774193548387,Biospecimen Type,True,False,False
+replicate description,362,treatment description,0.8095238095238095,Treatment,True,True,True
+mutation,354,duration,0.75,Treatment Dosage Regimen,True,True,False
+source type,345,source cell type,0.8148148148148148,Biospecimen Type,True,True,True
+culture type,334,culture time,0.8333333333333334,Biospecimen Age,True,True,True
+seizure,328,seizure group,0.7,Treatment,True,False,False
+visit_date,313,visit day,0.7368421052631579,Biospecimen Age,True,False,False
+development,310,development stage,0.7857142857142857,Biospecimen Age,True,True,False
+education,300,duration,0.8235294117647058,Treatment Dosage Regimen,True,True,True
+OS status,297,mouse status,0.8571428571428571,Biospecimen Organism,True,True,True
+category,296,age_category,0.8,Biospecimen Age,True,True,True
+experiment type,295,experimental day,0.7741935483870968,Biospecimen Age,True,True,False
+description,294,age description,0.8461538461538461,Biospecimen Age,True,True,True
+city,284,acidity,0.7272727272727273,External_sample_id,True,False,False
+stimulant,280,timeunit,0.7058823529411765,Biospecimen Age,True,False,False
+library preparation,277,library preparation protocol,0.8085106382978723,Treatment Dosage Regimen,True,True,True
+genome/variation,266,mouse genotype/variation,0.75,Biospecimen Organism,True,True,False
+immunization,265,immunization dose,0.8275862068965517,Treatment Dosage Regimen,True,True,True
+volunteer code,250,volunteer id,0.8461538461538461,External_sample_id,True,True,True
+number of malaria infections,250,malaria infection,0.7555555555555555,Biospecimen Disease Condition,True,True,False
+molecular classification,248,molecular condition,0.7441860465116279,Biospecimen Disease Condition,True,False,False
+genetic modification,227,chemical modification,0.7804878048780488,Treatment,True,True,False
+section,219,infection,0.75,Biospecimen Disease Condition,True,True,False
+state,214,stage,0.8,Biospecimen Age,True,True,True
+health state,213,cell state,0.7272727272727273,Biospecimen Type,True,False,False
+bal sampling date,212,sampling time,0.7333333333333333,Biospecimen Age,True,False,False
+processing,210,tissue processing,0.7407407407407407,Biospecimen Type,True,False,False
+library quality,208,library id,0.72,External_sample_id,True,False,False
+differentiation batch,207,differentiation day,0.85,Biospecimen Age,True,True,True
+knockout,203,knockout group,0.7272727272727273,Treatment,True,False,False
+inflammation_status,202,infection status,0.7428571428571429,Biospecimen Disease Condition,True,False,False
+pregnancy status,201,organoid status,0.7096774193548387,External_sample_id,True,False,False
+anatomic location,201,tumor location,0.7096774193548387,Biospecimen Disease Condition,True,False,False
+library,198,library id,0.8235294117647058,External_sample_id,True,True,True
+brain location,197,treatment location,0.75,Treatment,True,True,False
+experimental replicate,196,experimental group,0.75,Treatment,True,True,False
+plate_number,195,patient number,0.7692307692307693,External_sample_id,True,True,False
+growth medium,193,growth time,0.75,Biospecimen Age,True,True,False
+number of relapses,192,number of cells,0.7878787878787878,Biospecimen Type,True,True,False
+case/control,191,case or control,0.8148148148148148,Treatment,True,True,True
+infection_status,189,infection status,0.9375,Biospecimen Disease Condition,True,True,True
+vaccination route,188,vaccination dose,0.8484848484848485,Treatment Dosage Regimen,True,True,True
+couple number,188,mouse number,0.8,Biospecimen Organism,True,True,True
+growth,187,growth time,0.7058823529411765,Biospecimen Age,True,False,False
+extraction date,185,exacerbation day,0.7096774193548387,Biospecimen Age,True,False,False
+draw_date,185,draw day,0.7058823529411765,Biospecimen Age,True,False,False
+Histopathological diagnostic,180,histological diagnosis,0.84,Biospecimen Disease Condition,True,True,True
+symptomatic,178,symptom duration,0.7407407407407407,Treatment Dosage Regimen,True,False,False
+molecular subtype,176,molecular subgroup,0.8,Treatment,True,True,True
+Cause of death,172,age of death,0.8461538461538461,Biospecimen Age,True,True,True
+hours post-invasion,172,hours post infection,0.7692307692307693,Biospecimen Disease Condition,True,True,False
+volunteer,171,volunteer id,0.8571428571428571,External_sample_id,True,True,True
+survival cluster,170,survival time,0.7586206896551724,Biospecimen Age,True,True,False
+differentiation,169,differentiation day,0.8823529411764706,Biospecimen Age,True,True,True
+preparation,169,cell preparation,0.8148148148148148,Biospecimen Type,True,True,True
+overall.survival.months,168,overall.survival.time,0.8181818181818182,Biospecimen Age,True,True,True
+subset,168,subject,0.7692307692307693,External_sample_id,True,True,False
+protect outcome,167,treatment outcome,0.75,Treatment,True,True,False
+hours post invasion,162,hours post infection,0.8205128205128205,Biospecimen Disease Condition,True,True,True
+mechanical ventilation,162,mechanical condition,0.8095238095238095,Biospecimen Disease Condition,True,True,True
+other_medication,158,acute medication,0.75,Treatment,True,True,False
+diabetes_medication,158,acute medication,0.7428571428571429,Treatment,True,False,False
+os_month,156,os month,0.875,Biospecimen Age,True,True,True
+study_origin,156,study_id,0.7,External_sample_id,True,False,False
+parasitemia category,155,patient category,0.7222222222222222,External_sample_id,True,False,False
+differentiation_method,152,differentiation_age,0.8292682926829268,Biospecimen Age,True,True,True
+survival status,152,survival time,0.7142857142857143,Biospecimen Age,True,False,False
+antibody description,151,condition description,0.7804878048780488,Biospecimen Disease Condition,True,True,False
+notes,148,monocytes,0.7142857142857143,Biospecimen Type,True,False,False
+Phenotype,141,cell phenotype,0.782608695652174,Biospecimen Type,True,True,False
+cag,140,cage,0.8571428571428571,Biospecimen Age,True,True,True
+exposure_latent,140,exposure time,0.7142857142857143,Biospecimen Age,True,False,False
+pathogens,138,pathogen strain,0.75,Biospecimen Organism,True,True,False
+inflammation status,135,infection status,0.8,Biospecimen Disease Condition,True,True,True
+family,134,family id,0.8,External_sample_id,True,True,True
+injection_type,132,infection type,0.8571428571428571,Biospecimen Disease Condition,True,True,True
+technology,128,pathology,0.7368421052631579,Biospecimen Disease Condition,True,False,False
+line type,123,cell line type,0.782608695652174,Biospecimen Type,True,True,False
+biologics,120,biological sex,0.782608695652174,Biospecimen Sex,True,True,False
+application,120,publication id,0.72,External_sample_id,True,False,False
+infectivity,120,infection type,0.72,Biospecimen Disease Condition,True,False,False
+country,120,control,0.7142857142857143,Treatment,True,False,False
+line number,117,sample number,0.75,External_sample_id,True,True,False
+culture media,116,culture days,0.8,Biospecimen Age,True,True,True
+array batch,116,array barcode,0.75,External_sample_id,True,True,False
+immune status,113,mouse status,0.8,Biospecimen Organism,True,True,True
+isolation source,113,isolation stage,0.7741935483870968,Biospecimen Age,True,True,False
+Histology,107,histopathology,0.782608695652174,Biospecimen Disease Condition,True,True,False
+growth media,106,growth time,0.782608695652174,Biospecimen Age,True,True,False
+clinical phenotype,103,cell phenotype,0.8125,Biospecimen Type,True,True,True
+target,102,stage,0.7272727272727273,Biospecimen Age,True,False,False
+infected,101,time infected,0.7619047619047619,Biospecimen Age,True,True,False
+Exposures,101,exposure time,0.7272727272727273,Biospecimen Age,True,False,False
+pain,101,patient,0.7272727272727273,External_sample_id,True,False,False
+current status,100,treatment status,0.7333333333333333,Treatment,True,False,False
+viral load,100,patient viral load,0.7142857142857143,External_sample_id,True,False,False
+localization,99,tumor localization,0.8,Biospecimen Disease Condition,True,True,True
+case_phenotype,97,cell phenotype,0.7857142857142857,Biospecimen Type,True,True,False
+isolate type,97,disease type,0.75,Biospecimen Disease Condition,True,True,False
+als phenotype,96,cell phenotype,0.8148148148148148,Biospecimen Type,True,True,True
+volunteer number,96,mouse number,0.7142857142857143,Biospecimen Organism,True,False,False
+animal name,95,animal age,0.8571428571428571,Biospecimen Age,True,True,True
+parasite line,95,parasite strain,0.7857142857142857,Biospecimen Organism,True,True,False
+vaccination boost,92,vaccination dose,0.8484848484848485,Treatment Dosage Regimen,True,True,True
+sub-population,92,cell subpopulation,0.8125,Biospecimen Type,True,True,True
+location of onset,92,location of tumors,0.8,Biospecimen Disease Condition,True,True,True
+health status,92,cell status,0.75,Biospecimen Type,True,True,False
+purification,92,duration,0.7,Treatment Dosage Regimen,True,False,False
+onset,90,age_onset,0.7142857142857143,Biospecimen Age,True,False,False
+Status,89,cell status,0.7058823529411765,Biospecimen Type,True,False,False
+bacterial lysate,88,bacterial cells,0.7741935483870968,Biospecimen Type,True,True,False
+experiment year_month,86,experiment group,0.7027027027027027,Treatment,True,False,False
+virus type,86,serum type,0.7,Biospecimen Type,True,False,False
+clinical type,85,clinical stage,0.8148148148148148,Biospecimen Age,True,True,True
+culture method,84,culture time,0.7692307692307693,Biospecimen Age,True,True,False
+dissection,84,disease location,0.7692307692307693,Biospecimen Disease Condition,True,True,False
+responder,84,responder cells,0.75,Biospecimen Type,True,True,False
+infectious challenge,82,infectious agent,0.7777777777777778,Biospecimen Age,True,True,False
+experiment label,82,experimental day,0.75,Biospecimen Age,True,True,False
+viral status,82,viral strain,0.75,Biospecimen Organism,True,True,False
+pool no,81,pool id,0.7142857142857143,External_sample_id,True,False,False
+simulation,80,cell stimulation,0.7692307692307693,Biospecimen Type,True,True,False
+subclass,80,tissue class,0.7,Biospecimen Type,True,False,False
+folder name,79,slide name,0.7619047619047619,External_sample_id,True,True,False
+karyotype,77,cell karyotype,0.782608695652174,Biospecimen Type,True,True,False
+surgery type,76,serum type,0.7272727272727273,Biospecimen Type,True,False,False
+ClinicalInformation,75,clinical condition,0.7027027027027027,Biospecimen Disease Condition,True,False,False
+clinical outcome,74,clinical stage,0.7333333333333333,Biospecimen Age,True,False,False
+radiation,74,duration,0.7058823529411765,Treatment Dosage Regimen,True,False,False
+injection site,73,infection state,0.8275862068965517,Biospecimen Disease Condition,True,True,True
+injected virus,73,injected cells,0.7142857142857143,Biospecimen Type,True,False,False
+clinical indication,72,clinical condition,0.8648648648648649,Biospecimen Disease Condition,True,True,True
+experimental status,72,experimental day,0.8,Biospecimen Age,True,True,True
+sort population,72,sample population,0.75,External_sample_id,True,True,False
+variant type,72,vaccine type,0.75,Treatment,True,True,False
+metastasis site,72,metastatic tumor site,0.7222222222222222,Biospecimen Disease Condition,True,False,False
+parental origin,70,parental strain,0.8,Biospecimen Organism,True,True,True
+Degree of differentiation,69,stage of differentiation,0.8571428571428571,Biospecimen Age,True,True,True
+compartment,69,cell compartment,0.8148148148148148,Biospecimen Type,True,True,True
+Genetic background,69,cell line background,0.7368421052631579,Biospecimen Type,True,False,False
+Histological type,69,biological sex,0.7096774193548387,Biospecimen Sex,True,False,False
+structure,67,tissue structure,0.72,Biospecimen Type,True,False,False
+vs type,67,serum type,0.7058823529411765,Biospecimen Type,True,False,False
+size,66,side,0.75,External_sample_id,True,True,False
+derivation,65,duration,0.7777777777777778,Treatment Dosage Regimen,True,True,False
+roi type,64,organoid type,0.7619047619047619,External_sample_id,True,True,False
+infiltration,64,induration,0.7272727272727273,Treatment Dosage Regimen,True,False,False
+library_batch,64,library barcode,0.7142857142857143,External_sample_id,True,False,False
+cytology,64,pathology,0.7058823529411765,Biospecimen Disease Condition,True,False,False
+clinical trial phase,64,clinical stage,0.7058823529411765,Biospecimen Age,True,False,False
+number of_mice,62,number of_samples,0.7741935483870968,External_sample_id,True,True,False
+carbon source,62,control source,0.7407407407407407,Treatment,True,False,False
+clinical presentation,61,clinical condition,0.717948717948718,Biospecimen Disease Condition,True,False,False
+Subsets,60,subjects,0.8,External_sample_id,True,True,True
+Case,60,cage,0.75,Biospecimen Age,True,True,False
+replicates,58,replicate id,0.8181818181818182,External_sample_id,True,True,True
+library input,58,library id,0.782608695652174,External_sample_id,True,True,False
+location of lesion,58,location of tumors,0.7222222222222222,Biospecimen Disease Condition,True,False,False
+subtypes,58,cell subtype,0.7,Biospecimen Type,True,False,False
+sampling site,57,sampling time,0.8461538461538461,Biospecimen Age,True,True,True
+induction,57,induration,0.8421052631578947,Treatment Dosage Regimen,True,True,True
+experimental set,57,experimental day,0.8125,Biospecimen Age,True,True,True
+lesion status,57,infection status,0.7586206896551724,Biospecimen Disease Condition,True,True,False
+culture platform,57,culture time,0.7142857142857143,Biospecimen Age,True,False,False
+modifications,57,chemical modification,0.7058823529411765,Treatment,True,False,False
+fever,56,fever day,0.7142857142857143,Biospecimen Age,True,False,False
+commercial source,56,cell source,0.7142857142857143,Biospecimen Type,True,False,False
+Differentiation Method,55,differentiation time,0.8571428571428571,Biospecimen Age,True,True,True
+parental line,55,parental cell line,0.8387096774193549,Biospecimen Type,True,True,True
+growth pattern,55,growth time,0.72,Biospecimen Age,True,False,False
+clinic status,54,cancer status,0.7692307692307693,Biospecimen Disease Condition,True,True,False
+library version,54,library id,0.72,External_sample_id,True,False,False
+perturbation,54,duration,0.7,Treatment Dosage Regimen,True,False,False
+FISH origin,53,tissue origin,0.75,Biospecimen Type,True,True,False
+Genotype,52,host genotype,0.7619047619047619,Biospecimen Organism,True,True,False
+route administered,52,vaccine administered,0.7368421052631579,Treatment,True,False,False
+isolation method,52,isolation stage,0.7096774193548387,Biospecimen Age,True,False,False
+clinical_history,51,clinical.diagnosis.history,0.7142857142857143,Biospecimen Disease Condition,True,False,False
+lymph node,51,lymphocyte,0.7,Biospecimen Type,True,False,False
+metastatic site,50,metastatic tumor site,0.8333333333333334,Biospecimen Disease Condition,True,True,True
+health_status,50,donor_health_status,0.8125,External_sample_id,True,True,True
+study number,50,study sample number,0.7741935483870968,External_sample_id,True,True,False
+bar code,49,barcode,0.9333333333333333,External_sample_id,True,True,True
+mutations,49,duration,0.7058823529411765,Treatment Dosage Regimen,True,False,False
+hours_post_infection,48,hours post infection,0.9,Biospecimen Disease Condition,True,True,True
+experiment batch,48,experimental day,0.75,Biospecimen Age,True,True,False
+onset site,48,onset age,0.7368421052631579,Biospecimen Age,True,False,False
+isolation,47,isolation stage,0.75,Biospecimen Age,True,True,False
+relapse,47,relapse time,0.7368421052631579,Biospecimen Age,True,False,False
+graft source,47,gender source,0.72,Biospecimen Sex,True,False,False
+surface marker,46,cell surface marker,0.8484848484848485,Biospecimen Type,True,True,True
+person,46,person id,0.8,External_sample_id,True,True,True
+inoculation,45,inoculation dose,0.8148148148148148,Treatment Dosage Regimen,True,True,True
+digestives_symptoms,45,disease symptom,0.7058823529411765,Biospecimen Disease Condition,True,False,False
+growth type,44,growth time,0.8181818181818182,Biospecimen Age,True,True,True
+vendor,44,vendor id,0.8,External_sample_id,True,True,True
+translocation,44,treatment location,0.7741935483870968,Treatment,True,True,False
+receptor status,44,tumor status,0.7407407407407407,Biospecimen Disease Condition,True,False,False
+histological grade,44,histological diagnosis,0.7,Biospecimen Disease Condition,True,False,False
+collection date,43,collection day,0.896551724137931,Biospecimen Age,True,True,True
+differentiation status,43,differentiation stage,0.8837209302325582,Biospecimen Age,True,True,True
+nutritional state,43,gestational stage,0.7058823529411765,Biospecimen Age,True,False,False
+injection,42,infection,0.8888888888888888,Biospecimen Disease Condition,True,True,True
+state of culture,42,age of  culture,0.8387096774193549,Biospecimen Age,True,True,True
+specificity,42,specific-host,0.75,Biospecimen Organism,True,True,False
+experimental variables,42,experimental day,0.7368421052631579,Biospecimen Age,True,False,False
+er status,41,cancer status,0.8181818181818182,Biospecimen Disease Condition,True,True,True
+overall.survival,40,overall.survival.time,0.8648648648648649,Biospecimen Age,True,True,True
+collection,40,collection day,0.8333333333333334,Biospecimen Age,True,True,True
+who class,40,tumor class,0.7,Biospecimen Disease Condition,True,False,False
+experimental repeat,39,experimental group,0.8108108108108109,Treatment,True,True,True
+specific,39,specific-host,0.7619047619047619,Biospecimen Organism,True,True,False
+neuropathological.information,39,neuropathological_diagnosis,0.75,Biospecimen Disease Condition,True,True,False
+radiation exposure,39,lung radiation dose,0.7027027027027027,Treatment Dosage Regimen,True,False,False
+genomic modification,38,chemical modification,0.8292682926829268,Treatment,True,True,True
+experimental batch,38,experimental day,0.8235294117647058,Biospecimen Age,True,True,True
+pooled,38,pool id,0.7692307692307693,External_sample_id,True,True,False
+Source,37,source id,0.8,External_sample_id,True,True,True
+virus-stimulation,37,time post-stimulation,0.7368421052631579,Biospecimen Age,True,False,False
+paired with,37,paired patient,0.72,External_sample_id,True,False,False
+experimental,36,experimental day,0.8571428571428571,Biospecimen Age,True,True,True
+indication,36,induration,0.8,Treatment Dosage Regimen,True,True,True
+number of replicates,36,number of cells,0.7428571428571429,Biospecimen Type,True,False,False
+location type,36,location tumor,0.7407407407407407,Biospecimen Disease Condition,True,False,False
+clinical information,36,clinical condition,0.7368421052631579,Biospecimen Disease Condition,True,False,False
+parasite,36,parasite stage,0.7272727272727273,Biospecimen Age,True,False,False
+inhibitor removal,36,inhibitor treatment,0.7222222222222222,Treatment,True,False,False
+Clinical Status,35,clinical stage,0.8275862068965517,Biospecimen Age,True,True,True
+experimental design,35,experimental day,0.8,Biospecimen Age,True,True,True
+hours post fertilization,35,hours post infection,0.7727272727272727,Biospecimen Disease Condition,True,True,False
+donation source,35,control source,0.7586206896551724,Treatment,True,True,False
+labversion description,35,age description,0.7567567567567568,Biospecimen Age,True,True,False
+Type of Surgery,34,year of surgery,0.8666666666666667,Biospecimen Age,True,True,True
+body site,34,biopsy site,0.8,Biospecimen Type,True,True,True
+tretment,33,treatment,0.9411764705882353,Treatment,True,True,True
+infectious,33,infection,0.8421052631578947,Biospecimen Disease Condition,True,True,True
+viral infected,33,viral infection,0.8275862068965517,Biospecimen Disease Condition,True,True,True
+parasite isolate,33,parasite stage,0.8,Biospecimen Age,True,True,True
+gene,33,gender,0.8,Biospecimen Sex,True,True,True
+chip-antibody vendor,33,antibody vendor id,0.7894736842105263,External_sample_id,True,True,False
+clinical phenotypes,33,cell phenotype,0.7878787878787878,Biospecimen Type,True,True,False
+alternative_name,33,alternative sample name,0.7692307692307693,External_sample_id,True,True,False
+core code,33,donor code,0.7368421052631579,External_sample_id,True,False,False
+sputum smear status,33,tumor status,0.7096774193548387,Biospecimen Disease Condition,True,False,False
+animal number,32,animal id number,0.896551724137931,External_sample_id,True,True,True
+water type,32,cancer type,0.7619047619047619,Biospecimen Disease Condition,True,True,False
+maternal health status,31,maternal disease status,0.8,Biospecimen Disease Condition,True,True,True
+antibody status,31,organoid status,0.7333333333333333,External_sample_id,True,False,False
+differentiation state,30,differentiation stage,0.9523809523809523,Biospecimen Age,True,True,True
+single or double infected,30,single or double infection,0.9019607843137255,Biospecimen Disease Condition,True,True,True
+sampling point,30,sampling timepoint,0.875,Biospecimen Age,True,True,True
+virus added,30,virus dose,0.7619047619047619,Treatment Dosage Regimen,True,True,False
+phenotypes,30,cell phenotype,0.75,Biospecimen Type,True,True,False
+brain section,30,infection,0.7272727272727273,Biospecimen Disease Condition,True,False,False
+affected status,29,infection status,0.7096774193548387,Biospecimen Disease Condition,True,False,False
+derived from metastatic site,29,large cell lung cancer derived from metastatic site,0.7088607594936709,Biospecimen Type,True,False,False
+Pathogen,29,pathology,0.7058823529411765,Biospecimen Disease Condition,True,False,False
+plate code,28,patient code,0.8181818181818182,External_sample_id,True,True,True
+culture status,28,culture stage,0.8148148148148148,Biospecimen Age,True,True,True
+experimental factor,28,experimental day,0.8,Biospecimen Age,True,True,True
+genetic modifications,28,chemical modification,0.7619047619047619,Treatment,True,True,False
+skin phenotype,28,cell phenotype,0.7142857142857143,Biospecimen Type,True,False,False
+series,27,species,0.7692307692307693,Biospecimen Organism,True,True,False
+sampling location,27,sampling timepoint,0.7428571428571429,Biospecimen Age,True,False,False
+sort fraction,27,age fraction,0.72,Biospecimen Age,True,False,False
+pulmonary compartment,27,cell compartment,0.7027027027027027,Biospecimen Type,True,False,False
+clone phenotype,26,cell phenotype,0.8275862068965517,Biospecimen Type,True,True,True
+harvesting,26,harvesting time,0.8,Biospecimen Age,True,True,True
+clinical,26,clinical stage,0.7272727272727273,Biospecimen Age,True,False,False
+collection_date,25,collection day,0.8275862068965517,Biospecimen Age,True,True,True
+twin status,25,tissue status,0.75,Biospecimen Type,True,True,False
+hours post-infection,24,hours post infection,0.95,Biospecimen Disease Condition,True,True,True
+interaction status,24,infection status,0.8823529411764706,Biospecimen Disease Condition,True,True,True
+channel type,24,cancer type,0.782608695652174,Biospecimen Disease Condition,True,True,False
+clone type,24,cancer type,0.7619047619047619,Biospecimen Disease Condition,True,True,False
+pair status,24,cancer status,0.75,Biospecimen Disease Condition,True,True,False
+anatomical site,24,tissue anatomic site,0.7428571428571429,Biospecimen Type,True,False,False
+fip status,24,covid status,0.7272727272727273,External_sample_id,True,False,False
+resection_type,24,infection type,0.7142857142857143,Biospecimen Disease Condition,True,False,False
+implantation,24,cell type implantation,0.7058823529411765,Biospecimen Type,True,False,False
+os months,23,os month,0.9411764705882353,Biospecimen Age,True,True,True
+molecule source,23,sample source,0.7142857142857143,External_sample_id,True,False,False
+histological subtype,23,biological sex,0.7058823529411765,Biospecimen Sex,True,False,False
+strand,22,strain,0.8333333333333334,Biospecimen Organism,True,True,True
+replicate type,22,replicate id,0.7692307692307693,External_sample_id,True,True,False
+metastatic status,22,metastatic tumor site,0.7368421052631579,Biospecimen Disease Condition,True,False,False
+modification,22,chemical modification,0.7272727272727273,Treatment,True,False,False
+generation,22,age fraction,0.7272727272727273,Biospecimen Age,True,False,False
+antibody vendor name,21,antibody vendor id,0.8421052631578947,External_sample_id,True,True,True
+Karyotype,21,cell karyotype,0.782608695652174,Biospecimen Type,True,True,False
+antibody target description,21,age description,0.7142857142857143,Biospecimen Age,True,False,False
+infection_state,20,infection state,0.9333333333333333,Biospecimen Disease Condition,True,True,True
+vaccination state,20,vaccination dose,0.8484848484848485,Treatment Dosage Regimen,True,True,True
+Cause of Death,20,age of death,0.8461538461538461,Biospecimen Age,True,True,True
+type of death,20,age of death,0.8,Biospecimen Age,True,True,True
+enrichment,20,cell enrichment,0.8,Biospecimen Type,True,True,True
+lot number,20,cell number,0.7619047619047619,Biospecimen Type,True,True,False
+virus subtype,20,tissue subtype,0.7407407407407407,Biospecimen Type,True,False,False
+Shear exposure,20,time after exposure,0.7272727272727273,Biospecimen Age,True,False,False
+Order Code,20,donor code,0.7,External_sample_id,True,False,False
+Death Cause,20,death day,0.7,Biospecimen Age,True,False,False
+library kit,19,library id,0.8571428571428571,External_sample_id,True,True,True
+collection point,18,collection timepoint,0.8888888888888888,Biospecimen Age,True,True,True
+overall survival,18,overall.survival.time,0.8108108108108109,Biospecimen Age,True,True,True
+experimental variable,18,experimental day,0.7567567567567568,Biospecimen Age,True,True,False
+collection buffer,18,collection time,0.75,Biospecimen Age,True,True,False
+vital_status,18,covid_status,0.75,External_sample_id,True,True,False
+translocations,18,treatment location,0.75,Treatment,True,True,False
+culture batch,18,culture age,0.75,Biospecimen Age,True,True,False
+culture format,18,culture duration,0.7333333333333333,Treatment Dosage Regimen,True,False,False
+family code,16,family id,0.8,External_sample_id,True,True,True
+dementia status,16,treatment status,0.7741935483870968,Treatment,True,True,False
+common name,16,sample common name,0.7586206896551724,External_sample_id,True,True,False
+source/differentiation,16,days of differentiation,0.7555555555555555,Biospecimen Age,True,True,False
+sorted fraction,16,age fraction,0.7407407407407407,Biospecimen Age,True,False,False
+pool,16,pool id,0.7272727272727273,External_sample_id,True,False,False
+sorting fraction,16,age fraction,0.7142857142857143,Biospecimen Age,True,False,False
+autism diagnostic,16,patient diagnosis,0.7058823529411765,External_sample_id,True,False,False
+phase description,15,age description,0.875,Biospecimen Age,True,True,True
+surface markers,15,cell surface markers,0.8571428571428571,Biospecimen Type,True,True,True
+polarization state,15,polarization treatment,0.85,Treatment,True,True,True
+animal no,15,animal id,0.7777777777777778,External_sample_id,True,True,False
+experiment name,15,experimental day,0.7741935483870968,Biospecimen Age,True,True,False
+es line,15,cell line,0.75,Biospecimen Type,True,True,False
+stim,15,time,0.75,Biospecimen Age,True,True,False
+length of culture,15,age of  culture,0.75,Biospecimen Age,True,True,False
+lab code,15,lab id,0.7142857142857143,External_sample_id,True,False,False
+risk grade,15,risk group,0.7,Treatment,True,False,False
+experimental run,14,experimental group,0.8823529411764706,Treatment,True,True,True
+genotype/varation,14,mouse genotype/variation,0.8292682926829268,Biospecimen Organism,True,True,True
+alternative name,14,alternative sample name,0.8205128205128205,External_sample_id,True,True,True
+vaccination status,14,infection status,0.7647058823529411,Biospecimen Disease Condition,True,True,False
+genotype abbreviation,14,mouse line abbreviation,0.7272727272727273,Biospecimen Organism,True,False,False
+antigenic stimulation,14,time post-stimulation,0.7142857142857143,Biospecimen Age,True,False,False
+vaccination_status,14,infection status,0.7058823529411765,Biospecimen Disease Condition,True,False,False
+sorted population,13,sample population,0.7647058823529411,External_sample_id,True,True,False
+transplant,13,age at transplant,0.7407407407407407,Biospecimen Age,True,False,False
+material type,13,maternal age,0.72,Biospecimen Age,True,False,False
+pooling,13,pool id,0.7142857142857143,External_sample_id,True,False,False
+antibody vendor,12,antibody vendor id,0.9090909090909091,External_sample_id,True,True,True
+immunization route,12,immunization dose,0.8571428571428571,Treatment Dosage Regimen,True,True,True
+incubation period,12,infection period,0.8484848484848485,Biospecimen Disease Condition,True,True,True
+biological source,12,biological sex,0.8387096774193549,Biospecimen Sex,True,True,True
+long description,12,age description,0.8387096774193549,Biospecimen Age,True,True,True
+fold enrichment,12,cell enrichment,0.8,Biospecimen Type,True,True,True
+radiation response,12,patient response,0.7647058823529411,External_sample_id,True,True,False
+type of insertion,12,site of infection,0.7647058823529411,Biospecimen Disease Condition,True,True,False
+clone name,12,cell line name,0.75,Biospecimen Type,True,True,False
+efflux status,12,cell status,0.75,Biospecimen Type,True,True,False
+source muscle,12,source cell,0.75,Biospecimen Type,True,True,False
+clinical manifestation,12,clinical condition,0.75,Biospecimen Disease Condition,True,True,False
+sediment,12,specimen,0.75,Biospecimen Type,True,True,False
+oxygenation,12,oxygen condition,0.7407407407407407,Biospecimen Disease Condition,True,False,False
+replica,12,replicate id,0.7368421052631579,External_sample_id,True,False,False
+model type,12,cell type,0.7368421052631579,Biospecimen Type,True,False,False
+oxygen tension,12,oxygen condition,0.7333333333333333,Biospecimen Disease Condition,True,False,False
+genetic_modification,12,chemical modification,0.7317073170731707,Treatment,True,False,False
+scale,12,sample,0.7272727272727273,External_sample_id,True,False,False
+engraftment,12,treatment,0.7,Treatment,True,False,False
+antibody used,11,antibody group,0.7407407407407407,Treatment,True,False,False
+plating,11,patient,0.7142857142857143,External_sample_id,True,False,False
+maternal state,10,maternal age,0.8461538461538461,Biospecimen Age,True,True,True
+library backbone,10,library barcode,0.8387096774193549,External_sample_id,True,True,True
+anatomic site,10,tissue anatomic site,0.7878787878787878,Biospecimen Type,True,True,False
+viral inactivation,10,viral infection,0.7878787878787878,Biospecimen Disease Condition,True,True,False
+malaria status,10,malaria strain,0.7857142857142857,Biospecimen Organism,True,True,False
+culture medium,10,culture time,0.7692307692307693,Biospecimen Age,True,True,False
+number of animals,10,number of_samples,0.7647058823529411,External_sample_id,True,True,False
+initial preparation,10,tissue preparation,0.7567567567567568,Biospecimen Type,True,True,False
+date of isolation,9,day of isolation,0.9090909090909091,Biospecimen Age,True,True,True
+subpopulation,9,cell subpopulation,0.8387096774193549,Biospecimen Type,True,True,True
+genotype background,9,cell type background,0.8205128205128205,Biospecimen Type,True,True,True
+differentiation replicate,9,differentiation time point,0.7843137254901961,Biospecimen Age,True,True,False
+antibody name,9,antibody treatment,0.7741935483870968,Treatment,True,True,False
+mutation frequency,9,treatment frequency,0.7567567567567568,Treatment,True,True,False
+derived culture,9,derived cell_type,0.75,Biospecimen Type,True,True,False
+process order,9,process day,0.75,Biospecimen Age,True,True,False
+weight phenotype,9,cell phenotype,0.7333333333333333,Biospecimen Type,True,False,False
+embryo phenotype,9,cell phenotype,0.7333333333333333,Biospecimen Type,True,False,False
+number of cag repeats,9,number of cells,0.7222222222222222,Biospecimen Type,True,False,False
+antibody maker,9,antibody group,0.7142857142857143,Treatment,True,False,False
+etiology,9,pathology,0.7058823529411765,Biospecimen Disease Condition,True,False,False
+environmental factor,8,environmental condition,0.7906976744186046,Biospecimen Disease Condition,True,True,False
+nes status,8,cancer status,0.782608695652174,Biospecimen Disease Condition,True,True,False
+activation,8,activation agent,0.7692307692307693,Biospecimen Age,True,True,False
+ps status,8,mouse status,0.7619047619047619,Biospecimen Organism,True,True,False
+nitrogen source,8,control source,0.7586206896551724,Treatment,True,True,False
+microglia population,8,cell population,0.7428571428571429,Biospecimen Type,True,False,False
+clinical comments,8,clinical condition,0.7428571428571429,Biospecimen Disease Condition,True,False,False
+incubation temperature,8,incubation time,0.7027027027027027,Biospecimen Age,True,False,False
+incubation,7,incubation time,0.8,Biospecimen Age,True,True,True
+stain,6,strain,0.9090909090909091,Biospecimen Organism,True,True,True
+replicate number,6,sample replicate number,0.8205128205128205,External_sample_id,True,True,True
+round of selection,6,rounds of infection,0.8108108108108109,Biospecimen Disease Condition,True,True,True
+als status,6,sample status,0.782608695652174,External_sample_id,True,True,False
+hippocampal sclerosis,6,hippocampal slice id,0.7804878048780488,External_sample_id,True,True,False
+life cycle,6,life cycle stage,0.7692307692307693,Biospecimen Age,True,True,False
+antibody lot,6,antibody group,0.7692307692307693,Treatment,True,True,False
+tubules with spermatocytes,6,tubules with round spermatids,0.7636363636363637,External_sample_id,True,True,False
+tic class,6,tissue class,0.7619047619047619,Biospecimen Type,True,True,False
+fraction/population,6,patient population,0.7567567567567568,External_sample_id,True,True,False
+zinc status,6,cancer status,0.75,Biospecimen Disease Condition,True,True,False
+nodal status,6,covid status,0.75,External_sample_id,True,True,False
+Growth Medium,6,growth time,0.75,Biospecimen Age,True,True,False
+antibody cat,6,antibody treatment,0.7333333333333333,Treatment,True,False,False
+Extraction_amount,6,extraction_protocol,0.7222222222222222,Treatment Dosage Regimen,True,False,False
+variation,6,duration,0.7058823529411765,Treatment Dosage Regimen,True,False,False
+Labeling_reference,6,sample_reference,0.7058823529411765,External_sample_id,True,False,False
+gene induction,6,time after induction,0.7058823529411765,Biospecimen Age,True,False,False
+sampling post confirm,6,sampling time,0.7058823529411765,Biospecimen Age,True,False,False
+Extraction_reference,6,patient reference,0.7027027027027027,External_sample_id,True,False,False
+culture variation,5,culture duration,0.8484848484848485,Treatment Dosage Regimen,True,True,True
+sorted,5,sorter day,0.75,Biospecimen Age,True,True,False
+post-symptom onset,5,days_symptom_onset,0.7222222222222222,Biospecimen Age,True,False,False
+marker,5,cell marker,0.7058823529411765,Biospecimen Type,True,False,False
+number of_animals,4,number of_samples,0.8235294117647058,External_sample_id,True,True,True
+data type description,4,age description,0.7777777777777778,Biospecimen Age,True,True,False
+associated geo,4,associate geo_sample,0.7647058823529411,External_sample_id,True,True,False
+background mice,4,background strain,0.75,Biospecimen Organism,True,True,False
+number of_tracheas,4,number of_samples,0.7428571428571429,External_sample_id,True,False,False
+oxygen status,4,mouse status,0.72,Biospecimen Organism,True,False,False
+responder status,4,donor status,0.7142857142857143,External_sample_id,True,False,False
+developmental state,3,developmental stage,0.9473684210526315,Biospecimen Age,True,True,True
+histopathological diagnostic,3,histological diagnosis,0.84,Biospecimen Disease Condition,True,True,True
+Morphology,3,cell morphology,0.8,Biospecimen Type,True,True,True
+reference lot,3,reference condition,0.75,Biospecimen Disease Condition,True,True,False
+reference cat,3,reference condition,0.75,Biospecimen Disease Condition,True,True,False
+reactivity,3,acidity,0.7058823529411765,External_sample_id,True,False,False
+cause of death,2,age of death,0.8461538461538461,Biospecimen Age,True,True,True
+clip antibody vendor,2,antibody vendor id,0.7894736842105263,External_sample_id,True,True,False
+transplanted with,2,transplanted organ,0.7428571428571429,Biospecimen Type,True,False,False
+feature type,2,tumor type,0.7272727272727273,Biospecimen Disease Condition,True,False,False
+months_progression,2,timepoint_progressors,0.717948717948718,Biospecimen Age,True,False,False
+hot,1,host,0.8571428571428571,Biospecimen Organism,True,True,True
+incubation partner,1,incubation time,0.7878787878787878,Biospecimen Age,True,True,False
diff --git a/RDAS_RDOMICS/scripts/sample_characteristics_harmonization/similarity_cutoff_evaluation/assignments_cutoff_0_75.csv b/RDAS_RDOMICS/scripts/sample_characteristics_harmonization/similarity_cutoff_evaluation/assignments_cutoff_0_75.csv
new file mode 100644
index 0000000..66ca481
--- /dev/null
+++ b/RDAS_RDOMICS/scripts/sample_characteristics_harmonization/similarity_cutoff_evaluation/assignments_cutoff_0_75.csv
@@ -0,0 +1,334 @@
+label,count,best_reference_label,best_similarity_score,assigned_category,assigned_at_0_70,assigned_at_0_75,assigned_at_0_80
+genotype,46776,host genotype,0.7619047619047619,Biospecimen Organism,True,True,False
+batch,9770,batch id,0.7692307692307693,External_sample_id,True,True,False
+genotype/variation,6816,mouse genotype/variation,0.8571428571428571,Biospecimen Organism,True,True,True
+replicate,5824,replicate id,0.8571428571428571,External_sample_id,True,True,True
+clinical info,3680,clinical diagnosis,0.7741935483870968,Biospecimen Disease Condition,True,True,False
+histology,3618,histopathology,0.782608695652174,Biospecimen Disease Condition,True,True,False
+plate,3492,plate id,0.7692307692307693,External_sample_id,True,True,False
+region,2915,regimen,0.7692307692307693,Treatment Dosage Regimen,True,True,False
+site,2620,side,0.75,External_sample_id,True,True,False
+stimulation,2378,cell stimulation,0.8148148148148148,Biospecimen Type,True,True,True
+location,2284,location/side,0.7619047619047619,External_sample_id,True,True,False
+phenotype,1959,cell phenotype,0.782608695652174,Biospecimen Type,True,True,False
+experiment,1725,experimental day,0.7692307692307693,Biospecimen Age,True,True,False
+source,1670,source id,0.8,External_sample_id,True,True,True
+datatype description,1606,age description,0.8,Biospecimen Age,True,True,True
+collection_method,1517,collection time,0.75,Biospecimen Age,True,True,False
+well,1500,cell,0.75,Biospecimen Type,True,True,False
+segment type,1492,treatment type,0.7692307692307693,Treatment,True,True,False
+tag,1317,stage,0.75,Biospecimen Age,True,True,False
+culture,1264,culture age,0.7777777777777778,Biospecimen Age,True,True,False
+animal,1261,animal id,0.8,External_sample_id,True,True,True
+clinical status,1187,clinical stage,0.8275862068965517,Biospecimen Age,True,True,True
+primary site,1010,primary tumor site,0.8,Biospecimen Disease Condition,True,True,True
+fraction,1003,age fraction,0.8,Biospecimen Age,True,True,True
+lab description,997,age description,0.8666666666666667,Biospecimen Age,True,True,True
+infected with,898,infected host,0.7692307692307693,Biospecimen Organism,True,True,False
+survival_yr,876,survival year,0.8333333333333334,Biospecimen Age,True,True,True
+clone,871,clone id,0.7692307692307693,External_sample_id,True,True,False
+morphology,764,cell morphology,0.8,Biospecimen Type,True,True,True
+study,741,studyid,0.8333333333333334,External_sample_id,True,True,True
+case number,726,cell number,0.8181818181818182,Biospecimen Type,True,True,True
+chip_antibody_lot,696,chip_antibody_provider,0.7692307692307693,External_sample_id,True,True,False
+response,667,drug response,0.7619047619047619,Treatment,True,True,False
+os_status,656,mouse status,0.7619047619047619,Biospecimen Organism,True,True,False
+transduction,629,cell transduction,0.8275862068965517,Biospecimen Type,True,True,True
+brain region,595,brain tumor region,0.8,Biospecimen Disease Condition,True,True,True
+selection,567,mouse selection,0.75,Biospecimen Organism,True,True,False
+growth phase,558,growth stage,0.75,Biospecimen Age,True,True,False
+case,551,cage,0.75,Biospecimen Age,True,True,False
+resistance,506,drug resistance,0.8,Treatment,True,True,True
+date harvest,500,time harvest,0.8333333333333334,Biospecimen Age,True,True,True
+library preparation method,500,library preparation protocol,0.8148148148148148,Treatment Dosage Regimen,True,True,True
+sorted compartment,500,tissue compartment,0.7777777777777778,Biospecimen Type,True,True,False
+surgery number,500,usage number,0.7692307692307693,Biospecimen Age,True,True,False
+animal replicate,500,animal treatment,0.75,Treatment,True,True,False
+who category,493,tumor category,0.7692307692307693,Biospecimen Disease Condition,True,True,False
+population,477,cell population,0.8,Biospecimen Type,True,True,True
+vital status,450,covid status,0.75,External_sample_id,True,True,False
+survival,444,survival time,0.7619047619047619,Biospecimen Age,True,True,False
+array,407,array id,0.7692307692307693,External_sample_id,True,True,False
+vaccination,404,vaccination dose,0.8148148148148148,Treatment Dosage Regimen,True,True,True
+initial ich volume,399,initial tumor volume,0.7894736842105263,Biospecimen Disease Condition,True,True,False
+induction date,385,induction time,0.8571428571428571,Biospecimen Age,True,True,True
+library date,385,library id,0.8181818181818182,External_sample_id,True,True,True
+exposure,381,exposure time,0.7619047619047619,Biospecimen Age,True,True,False
+chip antibody vendor,380,antibody vendor id,0.7894736842105263,External_sample_id,True,True,False
+classification,369,classification group,0.8235294117647058,Treatment,True,True,True
+who grade,367,tumor who grade,0.75,Biospecimen Disease Condition,True,True,False
+replicate description,362,treatment description,0.8095238095238095,Treatment,True,True,True
+mutation,354,duration,0.75,Treatment Dosage Regimen,True,True,False
+source type,345,source cell type,0.8148148148148148,Biospecimen Type,True,True,True
+culture type,334,culture time,0.8333333333333334,Biospecimen Age,True,True,True
+development,310,development stage,0.7857142857142857,Biospecimen Age,True,True,False
+education,300,duration,0.8235294117647058,Treatment Dosage Regimen,True,True,True
+OS status,297,mouse status,0.8571428571428571,Biospecimen Organism,True,True,True
+category,296,age_category,0.8,Biospecimen Age,True,True,True
+experiment type,295,experimental day,0.7741935483870968,Biospecimen Age,True,True,False
+description,294,age description,0.8461538461538461,Biospecimen Age,True,True,True
+library preparation,277,library preparation protocol,0.8085106382978723,Treatment Dosage Regimen,True,True,True
+genome/variation,266,mouse genotype/variation,0.75,Biospecimen Organism,True,True,False
+immunization,265,immunization dose,0.8275862068965517,Treatment Dosage Regimen,True,True,True
+volunteer code,250,volunteer id,0.8461538461538461,External_sample_id,True,True,True
+number of malaria infections,250,malaria infection,0.7555555555555555,Biospecimen Disease Condition,True,True,False
+genetic modification,227,chemical modification,0.7804878048780488,Treatment,True,True,False
+section,219,infection,0.75,Biospecimen Disease Condition,True,True,False
+state,214,stage,0.8,Biospecimen Age,True,True,True
+differentiation batch,207,differentiation day,0.85,Biospecimen Age,True,True,True
+library,198,library id,0.8235294117647058,External_sample_id,True,True,True
+brain location,197,treatment location,0.75,Treatment,True,True,False
+experimental replicate,196,experimental group,0.75,Treatment,True,True,False
+plate_number,195,patient number,0.7692307692307693,External_sample_id,True,True,False
+growth medium,193,growth time,0.75,Biospecimen Age,True,True,False
+number of relapses,192,number of cells,0.7878787878787878,Biospecimen Type,True,True,False
+case/control,191,case or control,0.8148148148148148,Treatment,True,True,True
+infection_status,189,infection status,0.9375,Biospecimen Disease Condition,True,True,True
+vaccination route,188,vaccination dose,0.8484848484848485,Treatment Dosage Regimen,True,True,True
+couple number,188,mouse number,0.8,Biospecimen Organism,True,True,True
+Histopathological diagnostic,180,histological diagnosis,0.84,Biospecimen Disease Condition,True,True,True
+molecular subtype,176,molecular subgroup,0.8,Treatment,True,True,True
+Cause of death,172,age of death,0.8461538461538461,Biospecimen Age,True,True,True
+hours post-invasion,172,hours post infection,0.7692307692307693,Biospecimen Disease Condition,True,True,False
+volunteer,171,volunteer id,0.8571428571428571,External_sample_id,True,True,True
+survival cluster,170,survival time,0.7586206896551724,Biospecimen Age,True,True,False
+differentiation,169,differentiation day,0.8823529411764706,Biospecimen Age,True,True,True
+preparation,169,cell preparation,0.8148148148148148,Biospecimen Type,True,True,True
+overall.survival.months,168,overall.survival.time,0.8181818181818182,Biospecimen Age,True,True,True
+subset,168,subject,0.7692307692307693,External_sample_id,True,True,False
+protect outcome,167,treatment outcome,0.75,Treatment,True,True,False
+hours post invasion,162,hours post infection,0.8205128205128205,Biospecimen Disease Condition,True,True,True
+mechanical ventilation,162,mechanical condition,0.8095238095238095,Biospecimen Disease Condition,True,True,True
+other_medication,158,acute medication,0.75,Treatment,True,True,False
+os_month,156,os month,0.875,Biospecimen Age,True,True,True
+differentiation_method,152,differentiation_age,0.8292682926829268,Biospecimen Age,True,True,True
+antibody description,151,condition description,0.7804878048780488,Biospecimen Disease Condition,True,True,False
+Phenotype,141,cell phenotype,0.782608695652174,Biospecimen Type,True,True,False
+cag,140,cage,0.8571428571428571,Biospecimen Age,True,True,True
+pathogens,138,pathogen strain,0.75,Biospecimen Organism,True,True,False
+inflammation status,135,infection status,0.8,Biospecimen Disease Condition,True,True,True
+family,134,family id,0.8,External_sample_id,True,True,True
+injection_type,132,infection type,0.8571428571428571,Biospecimen Disease Condition,True,True,True
+line type,123,cell line type,0.782608695652174,Biospecimen Type,True,True,False
+biologics,120,biological sex,0.782608695652174,Biospecimen Sex,True,True,False
+line number,117,sample number,0.75,External_sample_id,True,True,False
+culture media,116,culture days,0.8,Biospecimen Age,True,True,True
+array batch,116,array barcode,0.75,External_sample_id,True,True,False
+immune status,113,mouse status,0.8,Biospecimen Organism,True,True,True
+isolation source,113,isolation stage,0.7741935483870968,Biospecimen Age,True,True,False
+Histology,107,histopathology,0.782608695652174,Biospecimen Disease Condition,True,True,False
+growth media,106,growth time,0.782608695652174,Biospecimen Age,True,True,False
+clinical phenotype,103,cell phenotype,0.8125,Biospecimen Type,True,True,True
+infected,101,time infected,0.7619047619047619,Biospecimen Age,True,True,False
+localization,99,tumor localization,0.8,Biospecimen Disease Condition,True,True,True
+case_phenotype,97,cell phenotype,0.7857142857142857,Biospecimen Type,True,True,False
+isolate type,97,disease type,0.75,Biospecimen Disease Condition,True,True,False
+als phenotype,96,cell phenotype,0.8148148148148148,Biospecimen Type,True,True,True
+animal name,95,animal age,0.8571428571428571,Biospecimen Age,True,True,True
+parasite line,95,parasite strain,0.7857142857142857,Biospecimen Organism,True,True,False
+vaccination boost,92,vaccination dose,0.8484848484848485,Treatment Dosage Regimen,True,True,True
+sub-population,92,cell subpopulation,0.8125,Biospecimen Type,True,True,True
+location of onset,92,location of tumors,0.8,Biospecimen Disease Condition,True,True,True
+health status,92,cell status,0.75,Biospecimen Type,True,True,False
+bacterial lysate,88,bacterial cells,0.7741935483870968,Biospecimen Type,True,True,False
+clinical type,85,clinical stage,0.8148148148148148,Biospecimen Age,True,True,True
+culture method,84,culture time,0.7692307692307693,Biospecimen Age,True,True,False
+dissection,84,disease location,0.7692307692307693,Biospecimen Disease Condition,True,True,False
+responder,84,responder cells,0.75,Biospecimen Type,True,True,False
+infectious challenge,82,infectious agent,0.7777777777777778,Biospecimen Age,True,True,False
+experiment label,82,experimental day,0.75,Biospecimen Age,True,True,False
+viral status,82,viral strain,0.75,Biospecimen Organism,True,True,False
+simulation,80,cell stimulation,0.7692307692307693,Biospecimen Type,True,True,False
+folder name,79,slide name,0.7619047619047619,External_sample_id,True,True,False
+karyotype,77,cell karyotype,0.782608695652174,Biospecimen Type,True,True,False
+injection site,73,infection state,0.8275862068965517,Biospecimen Disease Condition,True,True,True
+clinical indication,72,clinical condition,0.8648648648648649,Biospecimen Disease Condition,True,True,True
+experimental status,72,experimental day,0.8,Biospecimen Age,True,True,True
+sort population,72,sample population,0.75,External_sample_id,True,True,False
+variant type,72,vaccine type,0.75,Treatment,True,True,False
+parental origin,70,parental strain,0.8,Biospecimen Organism,True,True,True
+Degree of differentiation,69,stage of differentiation,0.8571428571428571,Biospecimen Age,True,True,True
+compartment,69,cell compartment,0.8148148148148148,Biospecimen Type,True,True,True
+size,66,side,0.75,External_sample_id,True,True,False
+derivation,65,duration,0.7777777777777778,Treatment Dosage Regimen,True,True,False
+roi type,64,organoid type,0.7619047619047619,External_sample_id,True,True,False
+number of_mice,62,number of_samples,0.7741935483870968,External_sample_id,True,True,False
+Subsets,60,subjects,0.8,External_sample_id,True,True,True
+Case,60,cage,0.75,Biospecimen Age,True,True,False
+replicates,58,replicate id,0.8181818181818182,External_sample_id,True,True,True
+library input,58,library id,0.782608695652174,External_sample_id,True,True,False
+sampling site,57,sampling time,0.8461538461538461,Biospecimen Age,True,True,True
+induction,57,induration,0.8421052631578947,Treatment Dosage Regimen,True,True,True
+experimental set,57,experimental day,0.8125,Biospecimen Age,True,True,True
+lesion status,57,infection status,0.7586206896551724,Biospecimen Disease Condition,True,True,False
+Differentiation Method,55,differentiation time,0.8571428571428571,Biospecimen Age,True,True,True
+parental line,55,parental cell line,0.8387096774193549,Biospecimen Type,True,True,True
+clinic status,54,cancer status,0.7692307692307693,Biospecimen Disease Condition,True,True,False
+FISH origin,53,tissue origin,0.75,Biospecimen Type,True,True,False
+Genotype,52,host genotype,0.7619047619047619,Biospecimen Organism,True,True,False
+metastatic site,50,metastatic tumor site,0.8333333333333334,Biospecimen Disease Condition,True,True,True
+health_status,50,donor_health_status,0.8125,External_sample_id,True,True,True
+study number,50,study sample number,0.7741935483870968,External_sample_id,True,True,False
+bar code,49,barcode,0.9333333333333333,External_sample_id,True,True,True
+hours_post_infection,48,hours post infection,0.9,Biospecimen Disease Condition,True,True,True
+experiment batch,48,experimental day,0.75,Biospecimen Age,True,True,False
+isolation,47,isolation stage,0.75,Biospecimen Age,True,True,False
+surface marker,46,cell surface marker,0.8484848484848485,Biospecimen Type,True,True,True
+person,46,person id,0.8,External_sample_id,True,True,True
+inoculation,45,inoculation dose,0.8148148148148148,Treatment Dosage Regimen,True,True,True
+growth type,44,growth time,0.8181818181818182,Biospecimen Age,True,True,True
+vendor,44,vendor id,0.8,External_sample_id,True,True,True
+translocation,44,treatment location,0.7741935483870968,Treatment,True,True,False
+collection date,43,collection day,0.896551724137931,Biospecimen Age,True,True,True
+differentiation status,43,differentiation stage,0.8837209302325582,Biospecimen Age,True,True,True
+injection,42,infection,0.8888888888888888,Biospecimen Disease Condition,True,True,True
+state of culture,42,age of  culture,0.8387096774193549,Biospecimen Age,True,True,True
+specificity,42,specific-host,0.75,Biospecimen Organism,True,True,False
+er status,41,cancer status,0.8181818181818182,Biospecimen Disease Condition,True,True,True
+overall.survival,40,overall.survival.time,0.8648648648648649,Biospecimen Age,True,True,True
+collection,40,collection day,0.8333333333333334,Biospecimen Age,True,True,True
+experimental repeat,39,experimental group,0.8108108108108109,Treatment,True,True,True
+specific,39,specific-host,0.7619047619047619,Biospecimen Organism,True,True,False
+neuropathological.information,39,neuropathological_diagnosis,0.75,Biospecimen Disease Condition,True,True,False
+genomic modification,38,chemical modification,0.8292682926829268,Treatment,True,True,True
+experimental batch,38,experimental day,0.8235294117647058,Biospecimen Age,True,True,True
+pooled,38,pool id,0.7692307692307693,External_sample_id,True,True,False
+Source,37,source id,0.8,External_sample_id,True,True,True
+experimental,36,experimental day,0.8571428571428571,Biospecimen Age,True,True,True
+indication,36,induration,0.8,Treatment Dosage Regimen,True,True,True
+Clinical Status,35,clinical stage,0.8275862068965517,Biospecimen Age,True,True,True
+experimental design,35,experimental day,0.8,Biospecimen Age,True,True,True
+hours post fertilization,35,hours post infection,0.7727272727272727,Biospecimen Disease Condition,True,True,False
+donation source,35,control source,0.7586206896551724,Treatment,True,True,False
+labversion description,35,age description,0.7567567567567568,Biospecimen Age,True,True,False
+Type of Surgery,34,year of surgery,0.8666666666666667,Biospecimen Age,True,True,True
+body site,34,biopsy site,0.8,Biospecimen Type,True,True,True
+tretment,33,treatment,0.9411764705882353,Treatment,True,True,True
+infectious,33,infection,0.8421052631578947,Biospecimen Disease Condition,True,True,True
+viral infected,33,viral infection,0.8275862068965517,Biospecimen Disease Condition,True,True,True
+parasite isolate,33,parasite stage,0.8,Biospecimen Age,True,True,True
+gene,33,gender,0.8,Biospecimen Sex,True,True,True
+chip-antibody vendor,33,antibody vendor id,0.7894736842105263,External_sample_id,True,True,False
+clinical phenotypes,33,cell phenotype,0.7878787878787878,Biospecimen Type,True,True,False
+alternative_name,33,alternative sample name,0.7692307692307693,External_sample_id,True,True,False
+animal number,32,animal id number,0.896551724137931,External_sample_id,True,True,True
+water type,32,cancer type,0.7619047619047619,Biospecimen Disease Condition,True,True,False
+maternal health status,31,maternal disease status,0.8,Biospecimen Disease Condition,True,True,True
+differentiation state,30,differentiation stage,0.9523809523809523,Biospecimen Age,True,True,True
+single or double infected,30,single or double infection,0.9019607843137255,Biospecimen Disease Condition,True,True,True
+sampling point,30,sampling timepoint,0.875,Biospecimen Age,True,True,True
+virus added,30,virus dose,0.7619047619047619,Treatment Dosage Regimen,True,True,False
+phenotypes,30,cell phenotype,0.75,Biospecimen Type,True,True,False
+plate code,28,patient code,0.8181818181818182,External_sample_id,True,True,True
+culture status,28,culture stage,0.8148148148148148,Biospecimen Age,True,True,True
+experimental factor,28,experimental day,0.8,Biospecimen Age,True,True,True
+genetic modifications,28,chemical modification,0.7619047619047619,Treatment,True,True,False
+series,27,species,0.7692307692307693,Biospecimen Organism,True,True,False
+clone phenotype,26,cell phenotype,0.8275862068965517,Biospecimen Type,True,True,True
+harvesting,26,harvesting time,0.8,Biospecimen Age,True,True,True
+collection_date,25,collection day,0.8275862068965517,Biospecimen Age,True,True,True
+twin status,25,tissue status,0.75,Biospecimen Type,True,True,False
+hours post-infection,24,hours post infection,0.95,Biospecimen Disease Condition,True,True,True
+interaction status,24,infection status,0.8823529411764706,Biospecimen Disease Condition,True,True,True
+channel type,24,cancer type,0.782608695652174,Biospecimen Disease Condition,True,True,False
+clone type,24,cancer type,0.7619047619047619,Biospecimen Disease Condition,True,True,False
+pair status,24,cancer status,0.75,Biospecimen Disease Condition,True,True,False
+os months,23,os month,0.9411764705882353,Biospecimen Age,True,True,True
+strand,22,strain,0.8333333333333334,Biospecimen Organism,True,True,True
+replicate type,22,replicate id,0.7692307692307693,External_sample_id,True,True,False
+antibody vendor name,21,antibody vendor id,0.8421052631578947,External_sample_id,True,True,True
+Karyotype,21,cell karyotype,0.782608695652174,Biospecimen Type,True,True,False
+infection_state,20,infection state,0.9333333333333333,Biospecimen Disease Condition,True,True,True
+vaccination state,20,vaccination dose,0.8484848484848485,Treatment Dosage Regimen,True,True,True
+Cause of Death,20,age of death,0.8461538461538461,Biospecimen Age,True,True,True
+type of death,20,age of death,0.8,Biospecimen Age,True,True,True
+enrichment,20,cell enrichment,0.8,Biospecimen Type,True,True,True
+lot number,20,cell number,0.7619047619047619,Biospecimen Type,True,True,False
+library kit,19,library id,0.8571428571428571,External_sample_id,True,True,True
+collection point,18,collection timepoint,0.8888888888888888,Biospecimen Age,True,True,True
+overall survival,18,overall.survival.time,0.8108108108108109,Biospecimen Age,True,True,True
+experimental variable,18,experimental day,0.7567567567567568,Biospecimen Age,True,True,False
+collection buffer,18,collection time,0.75,Biospecimen Age,True,True,False
+vital_status,18,covid_status,0.75,External_sample_id,True,True,False
+translocations,18,treatment location,0.75,Treatment,True,True,False
+culture batch,18,culture age,0.75,Biospecimen Age,True,True,False
+family code,16,family id,0.8,External_sample_id,True,True,True
+dementia status,16,treatment status,0.7741935483870968,Treatment,True,True,False
+common name,16,sample common name,0.7586206896551724,External_sample_id,True,True,False
+source/differentiation,16,days of differentiation,0.7555555555555555,Biospecimen Age,True,True,False
+phase description,15,age description,0.875,Biospecimen Age,True,True,True
+surface markers,15,cell surface markers,0.8571428571428571,Biospecimen Type,True,True,True
+polarization state,15,polarization treatment,0.85,Treatment,True,True,True
+animal no,15,animal id,0.7777777777777778,External_sample_id,True,True,False
+experiment name,15,experimental day,0.7741935483870968,Biospecimen Age,True,True,False
+es line,15,cell line,0.75,Biospecimen Type,True,True,False
+stim,15,time,0.75,Biospecimen Age,True,True,False
+length of culture,15,age of  culture,0.75,Biospecimen Age,True,True,False
+experimental run,14,experimental group,0.8823529411764706,Treatment,True,True,True
+genotype/varation,14,mouse genotype/variation,0.8292682926829268,Biospecimen Organism,True,True,True
+alternative name,14,alternative sample name,0.8205128205128205,External_sample_id,True,True,True
+vaccination status,14,infection status,0.7647058823529411,Biospecimen Disease Condition,True,True,False
+sorted population,13,sample population,0.7647058823529411,External_sample_id,True,True,False
+antibody vendor,12,antibody vendor id,0.9090909090909091,External_sample_id,True,True,True
+immunization route,12,immunization dose,0.8571428571428571,Treatment Dosage Regimen,True,True,True
+incubation period,12,infection period,0.8484848484848485,Biospecimen Disease Condition,True,True,True
+biological source,12,biological sex,0.8387096774193549,Biospecimen Sex,True,True,True
+long description,12,age description,0.8387096774193549,Biospecimen Age,True,True,True
+fold enrichment,12,cell enrichment,0.8,Biospecimen Type,True,True,True
+radiation response,12,patient response,0.7647058823529411,External_sample_id,True,True,False
+type of insertion,12,site of infection,0.7647058823529411,Biospecimen Disease Condition,True,True,False
+clone name,12,cell line name,0.75,Biospecimen Type,True,True,False
+efflux status,12,cell status,0.75,Biospecimen Type,True,True,False
+source muscle,12,source cell,0.75,Biospecimen Type,True,True,False
+clinical manifestation,12,clinical condition,0.75,Biospecimen Disease Condition,True,True,False
+sediment,12,specimen,0.75,Biospecimen Type,True,True,False
+maternal state,10,maternal age,0.8461538461538461,Biospecimen Age,True,True,True
+library backbone,10,library barcode,0.8387096774193549,External_sample_id,True,True,True
+anatomic site,10,tissue anatomic site,0.7878787878787878,Biospecimen Type,True,True,False
+viral inactivation,10,viral infection,0.7878787878787878,Biospecimen Disease Condition,True,True,False
+malaria status,10,malaria strain,0.7857142857142857,Biospecimen Organism,True,True,False
+culture medium,10,culture time,0.7692307692307693,Biospecimen Age,True,True,False
+number of animals,10,number of_samples,0.7647058823529411,External_sample_id,True,True,False
+initial preparation,10,tissue preparation,0.7567567567567568,Biospecimen Type,True,True,False
+date of isolation,9,day of isolation,0.9090909090909091,Biospecimen Age,True,True,True
+subpopulation,9,cell subpopulation,0.8387096774193549,Biospecimen Type,True,True,True
+genotype background,9,cell type background,0.8205128205128205,Biospecimen Type,True,True,True
+differentiation replicate,9,differentiation time point,0.7843137254901961,Biospecimen Age,True,True,False
+antibody name,9,antibody treatment,0.7741935483870968,Treatment,True,True,False
+mutation frequency,9,treatment frequency,0.7567567567567568,Treatment,True,True,False
+derived culture,9,derived cell_type,0.75,Biospecimen Type,True,True,False
+process order,9,process day,0.75,Biospecimen Age,True,True,False
+environmental factor,8,environmental condition,0.7906976744186046,Biospecimen Disease Condition,True,True,False
+nes status,8,cancer status,0.782608695652174,Biospecimen Disease Condition,True,True,False
+activation,8,activation agent,0.7692307692307693,Biospecimen Age,True,True,False
+ps status,8,mouse status,0.7619047619047619,Biospecimen Organism,True,True,False
+nitrogen source,8,control source,0.7586206896551724,Treatment,True,True,False
+incubation,7,incubation time,0.8,Biospecimen Age,True,True,True
+stain,6,strain,0.9090909090909091,Biospecimen Organism,True,True,True
+replicate number,6,sample replicate number,0.8205128205128205,External_sample_id,True,True,True
+round of selection,6,rounds of infection,0.8108108108108109,Biospecimen Disease Condition,True,True,True
+als status,6,sample status,0.782608695652174,External_sample_id,True,True,False
+hippocampal sclerosis,6,hippocampal slice id,0.7804878048780488,External_sample_id,True,True,False
+life cycle,6,life cycle stage,0.7692307692307693,Biospecimen Age,True,True,False
+antibody lot,6,antibody group,0.7692307692307693,Treatment,True,True,False
+tubules with spermatocytes,6,tubules with round spermatids,0.7636363636363637,External_sample_id,True,True,False
+tic class,6,tissue class,0.7619047619047619,Biospecimen Type,True,True,False
+fraction/population,6,patient population,0.7567567567567568,External_sample_id,True,True,False
+zinc status,6,cancer status,0.75,Biospecimen Disease Condition,True,True,False
+nodal status,6,covid status,0.75,External_sample_id,True,True,False
+Growth Medium,6,growth time,0.75,Biospecimen Age,True,True,False
+culture variation,5,culture duration,0.8484848484848485,Treatment Dosage Regimen,True,True,True
+sorted,5,sorter day,0.75,Biospecimen Age,True,True,False
+number of_animals,4,number of_samples,0.8235294117647058,External_sample_id,True,True,True
+data type description,4,age description,0.7777777777777778,Biospecimen Age,True,True,False
+associated geo,4,associate geo_sample,0.7647058823529411,External_sample_id,True,True,False
+background mice,4,background strain,0.75,Biospecimen Organism,True,True,False
+developmental state,3,developmental stage,0.9473684210526315,Biospecimen Age,True,True,True
+histopathological diagnostic,3,histological diagnosis,0.84,Biospecimen Disease Condition,True,True,True
+Morphology,3,cell morphology,0.8,Biospecimen Type,True,True,True
+reference lot,3,reference condition,0.75,Biospecimen Disease Condition,True,True,False
+reference cat,3,reference condition,0.75,Biospecimen Disease Condition,True,True,False
+cause of death,2,age of death,0.8461538461538461,Biospecimen Age,True,True,True
+clip antibody vendor,2,antibody vendor id,0.7894736842105263,External_sample_id,True,True,False
+hot,1,host,0.8571428571428571,Biospecimen Organism,True,True,True
+incubation partner,1,incubation time,0.7878787878787878,Biospecimen Age,True,True,False
diff --git a/RDAS_RDOMICS/scripts/sample_characteristics_harmonization/similarity_cutoff_evaluation/assignments_cutoff_0_80.csv b/RDAS_RDOMICS/scripts/sample_characteristics_harmonization/similarity_cutoff_evaluation/assignments_cutoff_0_80.csv
new file mode 100644
index 0000000..c230c8f
--- /dev/null
+++ b/RDAS_RDOMICS/scripts/sample_characteristics_harmonization/similarity_cutoff_evaluation/assignments_cutoff_0_80.csv
@@ -0,0 +1,164 @@
+label,count,best_reference_label,best_similarity_score,assigned_category,assigned_at_0_70,assigned_at_0_75,assigned_at_0_80
+genotype/variation,6816,mouse genotype/variation,0.8571428571428571,Biospecimen Organism,True,True,True
+replicate,5824,replicate id,0.8571428571428571,External_sample_id,True,True,True
+stimulation,2378,cell stimulation,0.8148148148148148,Biospecimen Type,True,True,True
+source,1670,source id,0.8,External_sample_id,True,True,True
+datatype description,1606,age description,0.8,Biospecimen Age,True,True,True
+animal,1261,animal id,0.8,External_sample_id,True,True,True
+clinical status,1187,clinical stage,0.8275862068965517,Biospecimen Age,True,True,True
+primary site,1010,primary tumor site,0.8,Biospecimen Disease Condition,True,True,True
+fraction,1003,age fraction,0.8,Biospecimen Age,True,True,True
+lab description,997,age description,0.8666666666666667,Biospecimen Age,True,True,True
+survival_yr,876,survival year,0.8333333333333334,Biospecimen Age,True,True,True
+morphology,764,cell morphology,0.8,Biospecimen Type,True,True,True
+study,741,studyid,0.8333333333333334,External_sample_id,True,True,True
+case number,726,cell number,0.8181818181818182,Biospecimen Type,True,True,True
+transduction,629,cell transduction,0.8275862068965517,Biospecimen Type,True,True,True
+brain region,595,brain tumor region,0.8,Biospecimen Disease Condition,True,True,True
+resistance,506,drug resistance,0.8,Treatment,True,True,True
+date harvest,500,time harvest,0.8333333333333334,Biospecimen Age,True,True,True
+library preparation method,500,library preparation protocol,0.8148148148148148,Treatment Dosage Regimen,True,True,True
+population,477,cell population,0.8,Biospecimen Type,True,True,True
+vaccination,404,vaccination dose,0.8148148148148148,Treatment Dosage Regimen,True,True,True
+induction date,385,induction time,0.8571428571428571,Biospecimen Age,True,True,True
+library date,385,library id,0.8181818181818182,External_sample_id,True,True,True
+classification,369,classification group,0.8235294117647058,Treatment,True,True,True
+replicate description,362,treatment description,0.8095238095238095,Treatment,True,True,True
+source type,345,source cell type,0.8148148148148148,Biospecimen Type,True,True,True
+culture type,334,culture time,0.8333333333333334,Biospecimen Age,True,True,True
+education,300,duration,0.8235294117647058,Treatment Dosage Regimen,True,True,True
+OS status,297,mouse status,0.8571428571428571,Biospecimen Organism,True,True,True
+category,296,age_category,0.8,Biospecimen Age,True,True,True
+description,294,age description,0.8461538461538461,Biospecimen Age,True,True,True
+library preparation,277,library preparation protocol,0.8085106382978723,Treatment Dosage Regimen,True,True,True
+immunization,265,immunization dose,0.8275862068965517,Treatment Dosage Regimen,True,True,True
+volunteer code,250,volunteer id,0.8461538461538461,External_sample_id,True,True,True
+state,214,stage,0.8,Biospecimen Age,True,True,True
+differentiation batch,207,differentiation day,0.85,Biospecimen Age,True,True,True
+library,198,library id,0.8235294117647058,External_sample_id,True,True,True
+case/control,191,case or control,0.8148148148148148,Treatment,True,True,True
+infection_status,189,infection status,0.9375,Biospecimen Disease Condition,True,True,True
+vaccination route,188,vaccination dose,0.8484848484848485,Treatment Dosage Regimen,True,True,True
+couple number,188,mouse number,0.8,Biospecimen Organism,True,True,True
+Histopathological diagnostic,180,histological diagnosis,0.84,Biospecimen Disease Condition,True,True,True
+molecular subtype,176,molecular subgroup,0.8,Treatment,True,True,True
+Cause of death,172,age of death,0.8461538461538461,Biospecimen Age,True,True,True
+volunteer,171,volunteer id,0.8571428571428571,External_sample_id,True,True,True
+differentiation,169,differentiation day,0.8823529411764706,Biospecimen Age,True,True,True
+preparation,169,cell preparation,0.8148148148148148,Biospecimen Type,True,True,True
+overall.survival.months,168,overall.survival.time,0.8181818181818182,Biospecimen Age,True,True,True
+hours post invasion,162,hours post infection,0.8205128205128205,Biospecimen Disease Condition,True,True,True
+mechanical ventilation,162,mechanical condition,0.8095238095238095,Biospecimen Disease Condition,True,True,True
+os_month,156,os month,0.875,Biospecimen Age,True,True,True
+differentiation_method,152,differentiation_age,0.8292682926829268,Biospecimen Age,True,True,True
+cag,140,cage,0.8571428571428571,Biospecimen Age,True,True,True
+inflammation status,135,infection status,0.8,Biospecimen Disease Condition,True,True,True
+family,134,family id,0.8,External_sample_id,True,True,True
+injection_type,132,infection type,0.8571428571428571,Biospecimen Disease Condition,True,True,True
+culture media,116,culture days,0.8,Biospecimen Age,True,True,True
+immune status,113,mouse status,0.8,Biospecimen Organism,True,True,True
+clinical phenotype,103,cell phenotype,0.8125,Biospecimen Type,True,True,True
+localization,99,tumor localization,0.8,Biospecimen Disease Condition,True,True,True
+als phenotype,96,cell phenotype,0.8148148148148148,Biospecimen Type,True,True,True
+animal name,95,animal age,0.8571428571428571,Biospecimen Age,True,True,True
+vaccination boost,92,vaccination dose,0.8484848484848485,Treatment Dosage Regimen,True,True,True
+sub-population,92,cell subpopulation,0.8125,Biospecimen Type,True,True,True
+location of onset,92,location of tumors,0.8,Biospecimen Disease Condition,True,True,True
+clinical type,85,clinical stage,0.8148148148148148,Biospecimen Age,True,True,True
+injection site,73,infection state,0.8275862068965517,Biospecimen Disease Condition,True,True,True
+clinical indication,72,clinical condition,0.8648648648648649,Biospecimen Disease Condition,True,True,True
+experimental status,72,experimental day,0.8,Biospecimen Age,True,True,True
+parental origin,70,parental strain,0.8,Biospecimen Organism,True,True,True
+Degree of differentiation,69,stage of differentiation,0.8571428571428571,Biospecimen Age,True,True,True
+compartment,69,cell compartment,0.8148148148148148,Biospecimen Type,True,True,True
+Subsets,60,subjects,0.8,External_sample_id,True,True,True
+replicates,58,replicate id,0.8181818181818182,External_sample_id,True,True,True
+sampling site,57,sampling time,0.8461538461538461,Biospecimen Age,True,True,True
+induction,57,induration,0.8421052631578947,Treatment Dosage Regimen,True,True,True
+experimental set,57,experimental day,0.8125,Biospecimen Age,True,True,True
+Differentiation Method,55,differentiation time,0.8571428571428571,Biospecimen Age,True,True,True
+parental line,55,parental cell line,0.8387096774193549,Biospecimen Type,True,True,True
+metastatic site,50,metastatic tumor site,0.8333333333333334,Biospecimen Disease Condition,True,True,True
+health_status,50,donor_health_status,0.8125,External_sample_id,True,True,True
+bar code,49,barcode,0.9333333333333333,External_sample_id,True,True,True
+hours_post_infection,48,hours post infection,0.9,Biospecimen Disease Condition,True,True,True
+surface marker,46,cell surface marker,0.8484848484848485,Biospecimen Type,True,True,True
+person,46,person id,0.8,External_sample_id,True,True,True
+inoculation,45,inoculation dose,0.8148148148148148,Treatment Dosage Regimen,True,True,True
+growth type,44,growth time,0.8181818181818182,Biospecimen Age,True,True,True
+vendor,44,vendor id,0.8,External_sample_id,True,True,True
+collection date,43,collection day,0.896551724137931,Biospecimen Age,True,True,True
+differentiation status,43,differentiation stage,0.8837209302325582,Biospecimen Age,True,True,True
+injection,42,infection,0.8888888888888888,Biospecimen Disease Condition,True,True,True
+state of culture,42,age of  culture,0.8387096774193549,Biospecimen Age,True,True,True
+er status,41,cancer status,0.8181818181818182,Biospecimen Disease Condition,True,True,True
+overall.survival,40,overall.survival.time,0.8648648648648649,Biospecimen Age,True,True,True
+collection,40,collection day,0.8333333333333334,Biospecimen Age,True,True,True
+experimental repeat,39,experimental group,0.8108108108108109,Treatment,True,True,True
+genomic modification,38,chemical modification,0.8292682926829268,Treatment,True,True,True
+experimental batch,38,experimental day,0.8235294117647058,Biospecimen Age,True,True,True
+Source,37,source id,0.8,External_sample_id,True,True,True
+experimental,36,experimental day,0.8571428571428571,Biospecimen Age,True,True,True
+indication,36,induration,0.8,Treatment Dosage Regimen,True,True,True
+Clinical Status,35,clinical stage,0.8275862068965517,Biospecimen Age,True,True,True
+experimental design,35,experimental day,0.8,Biospecimen Age,True,True,True
+Type of Surgery,34,year of surgery,0.8666666666666667,Biospecimen Age,True,True,True
+body site,34,biopsy site,0.8,Biospecimen Type,True,True,True
+tretment,33,treatment,0.9411764705882353,Treatment,True,True,True
+infectious,33,infection,0.8421052631578947,Biospecimen Disease Condition,True,True,True
+viral infected,33,viral infection,0.8275862068965517,Biospecimen Disease Condition,True,True,True
+parasite isolate,33,parasite stage,0.8,Biospecimen Age,True,True,True
+gene,33,gender,0.8,Biospecimen Sex,True,True,True
+animal number,32,animal id number,0.896551724137931,External_sample_id,True,True,True
+maternal health status,31,maternal disease status,0.8,Biospecimen Disease Condition,True,True,True
+differentiation state,30,differentiation stage,0.9523809523809523,Biospecimen Age,True,True,True
+single or double infected,30,single or double infection,0.9019607843137255,Biospecimen Disease Condition,True,True,True
+sampling point,30,sampling timepoint,0.875,Biospecimen Age,True,True,True
+plate code,28,patient code,0.8181818181818182,External_sample_id,True,True,True
+culture status,28,culture stage,0.8148148148148148,Biospecimen Age,True,True,True
+experimental factor,28,experimental day,0.8,Biospecimen Age,True,True,True
+clone phenotype,26,cell phenotype,0.8275862068965517,Biospecimen Type,True,True,True
+harvesting,26,harvesting time,0.8,Biospecimen Age,True,True,True
+collection_date,25,collection day,0.8275862068965517,Biospecimen Age,True,True,True
+hours post-infection,24,hours post infection,0.95,Biospecimen Disease Condition,True,True,True
+interaction status,24,infection status,0.8823529411764706,Biospecimen Disease Condition,True,True,True
+os months,23,os month,0.9411764705882353,Biospecimen Age,True,True,True
+strand,22,strain,0.8333333333333334,Biospecimen Organism,True,True,True
+antibody vendor name,21,antibody vendor id,0.8421052631578947,External_sample_id,True,True,True
+infection_state,20,infection state,0.9333333333333333,Biospecimen Disease Condition,True,True,True
+vaccination state,20,vaccination dose,0.8484848484848485,Treatment Dosage Regimen,True,True,True
+Cause of Death,20,age of death,0.8461538461538461,Biospecimen Age,True,True,True
+type of death,20,age of death,0.8,Biospecimen Age,True,True,True
+enrichment,20,cell enrichment,0.8,Biospecimen Type,True,True,True
+library kit,19,library id,0.8571428571428571,External_sample_id,True,True,True
+collection point,18,collection timepoint,0.8888888888888888,Biospecimen Age,True,True,True
+overall survival,18,overall.survival.time,0.8108108108108109,Biospecimen Age,True,True,True
+family code,16,family id,0.8,External_sample_id,True,True,True
+phase description,15,age description,0.875,Biospecimen Age,True,True,True
+surface markers,15,cell surface markers,0.8571428571428571,Biospecimen Type,True,True,True
+polarization state,15,polarization treatment,0.85,Treatment,True,True,True
+experimental run,14,experimental group,0.8823529411764706,Treatment,True,True,True
+genotype/varation,14,mouse genotype/variation,0.8292682926829268,Biospecimen Organism,True,True,True
+alternative name,14,alternative sample name,0.8205128205128205,External_sample_id,True,True,True
+antibody vendor,12,antibody vendor id,0.9090909090909091,External_sample_id,True,True,True
+immunization route,12,immunization dose,0.8571428571428571,Treatment Dosage Regimen,True,True,True
+incubation period,12,infection period,0.8484848484848485,Biospecimen Disease Condition,True,True,True
+biological source,12,biological sex,0.8387096774193549,Biospecimen Sex,True,True,True
+long description,12,age description,0.8387096774193549,Biospecimen Age,True,True,True
+fold enrichment,12,cell enrichment,0.8,Biospecimen Type,True,True,True
+maternal state,10,maternal age,0.8461538461538461,Biospecimen Age,True,True,True
+library backbone,10,library barcode,0.8387096774193549,External_sample_id,True,True,True
+date of isolation,9,day of isolation,0.9090909090909091,Biospecimen Age,True,True,True
+subpopulation,9,cell subpopulation,0.8387096774193549,Biospecimen Type,True,True,True
+genotype background,9,cell type background,0.8205128205128205,Biospecimen Type,True,True,True
+incubation,7,incubation time,0.8,Biospecimen Age,True,True,True
+stain,6,strain,0.9090909090909091,Biospecimen Organism,True,True,True
+replicate number,6,sample replicate number,0.8205128205128205,External_sample_id,True,True,True
+round of selection,6,rounds of infection,0.8108108108108109,Biospecimen Disease Condition,True,True,True
+culture variation,5,culture duration,0.8484848484848485,Treatment Dosage Regimen,True,True,True
+number of_animals,4,number of_samples,0.8235294117647058,External_sample_id,True,True,True
+developmental state,3,developmental stage,0.9473684210526315,Biospecimen Age,True,True,True
+histopathological diagnostic,3,histological diagnosis,0.84,Biospecimen Disease Condition,True,True,True
+Morphology,3,cell morphology,0.8,Biospecimen Type,True,True,True
+cause of death,2,age of death,0.8461538461538461,Biospecimen Age,True,True,True
+hot,1,host,0.8571428571428571,Biospecimen Organism,True,True,True
diff --git a/RDAS_RDOMICS/scripts/sample_characteristics_harmonization/similarity_cutoff_evaluation/best_similarity_matches.csv b/RDAS_RDOMICS/scripts/sample_characteristics_harmonization/similarity_cutoff_evaluation/best_similarity_matches.csv
new file mode 100644
index 0000000..ea32b1e
--- /dev/null
+++ b/RDAS_RDOMICS/scripts/sample_characteristics_harmonization/similarity_cutoff_evaluation/best_similarity_matches.csv
@@ -0,0 +1,1379 @@
+label,count,best_reference_label,best_similarity_score,assigned_category,assigned_at_0_70,assigned_at_0_75,assigned_at_0_80
+differentiation state,30,differentiation stage,0.9523809523809523,Biospecimen Age,True,True,True
+hours post-infection,24,hours post infection,0.95,Biospecimen Disease Condition,True,True,True
+developmental state,3,developmental stage,0.9473684210526315,Biospecimen Age,True,True,True
+tretment,33,treatment,0.9411764705882353,Treatment,True,True,True
+os months,23,os month,0.9411764705882353,Biospecimen Age,True,True,True
+infection_status,189,infection status,0.9375,Biospecimen Disease Condition,True,True,True
+bar code,49,barcode,0.9333333333333333,External_sample_id,True,True,True
+infection_state,20,infection state,0.9333333333333333,Biospecimen Disease Condition,True,True,True
+antibody vendor,12,antibody vendor id,0.9090909090909091,External_sample_id,True,True,True
+date of isolation,9,day of isolation,0.9090909090909091,Biospecimen Age,True,True,True
+stain,6,strain,0.9090909090909091,Biospecimen Organism,True,True,True
+single or double infected,30,single or double infection,0.9019607843137255,Biospecimen Disease Condition,True,True,True
+hours_post_infection,48,hours post infection,0.9,Biospecimen Disease Condition,True,True,True
+collection date,43,collection day,0.896551724137931,Biospecimen Age,True,True,True
+animal number,32,animal id number,0.896551724137931,External_sample_id,True,True,True
+injection,42,infection,0.8888888888888888,Biospecimen Disease Condition,True,True,True
+collection point,18,collection timepoint,0.8888888888888888,Biospecimen Age,True,True,True
+differentiation status,43,differentiation stage,0.8837209302325582,Biospecimen Age,True,True,True
+differentiation,169,differentiation day,0.8823529411764706,Biospecimen Age,True,True,True
+interaction status,24,infection status,0.8823529411764706,Biospecimen Disease Condition,True,True,True
+experimental run,14,experimental group,0.8823529411764706,Treatment,True,True,True
+os_month,156,os month,0.875,Biospecimen Age,True,True,True
+sampling point,30,sampling timepoint,0.875,Biospecimen Age,True,True,True
+phase description,15,age description,0.875,Biospecimen Age,True,True,True
+lab description,997,age description,0.8666666666666667,Biospecimen Age,True,True,True
+Type of Surgery,34,year of surgery,0.8666666666666667,Biospecimen Age,True,True,True
+clinical indication,72,clinical condition,0.8648648648648649,Biospecimen Disease Condition,True,True,True
+overall.survival,40,overall.survival.time,0.8648648648648649,Biospecimen Age,True,True,True
+genotype/variation,6816,mouse genotype/variation,0.8571428571428571,Biospecimen Organism,True,True,True
+replicate,5824,replicate id,0.8571428571428571,External_sample_id,True,True,True
+induction date,385,induction time,0.8571428571428571,Biospecimen Age,True,True,True
+OS status,297,mouse status,0.8571428571428571,Biospecimen Organism,True,True,True
+volunteer,171,volunteer id,0.8571428571428571,External_sample_id,True,True,True
+cag,140,cage,0.8571428571428571,Biospecimen Age,True,True,True
+injection_type,132,infection type,0.8571428571428571,Biospecimen Disease Condition,True,True,True
+animal name,95,animal age,0.8571428571428571,Biospecimen Age,True,True,True
+Degree of differentiation,69,stage of differentiation,0.8571428571428571,Biospecimen Age,True,True,True
+Differentiation Method,55,differentiation time,0.8571428571428571,Biospecimen Age,True,True,True
+experimental,36,experimental day,0.8571428571428571,Biospecimen Age,True,True,True
+library kit,19,library id,0.8571428571428571,External_sample_id,True,True,True
+surface markers,15,cell surface markers,0.8571428571428571,Biospecimen Type,True,True,True
+immunization route,12,immunization dose,0.8571428571428571,Treatment Dosage Regimen,True,True,True
+hot,1,host,0.8571428571428571,Biospecimen Organism,True,True,True
+differentiation batch,207,differentiation day,0.85,Biospecimen Age,True,True,True
+polarization state,15,polarization treatment,0.85,Treatment,True,True,True
+vaccination route,188,vaccination dose,0.8484848484848485,Treatment Dosage Regimen,True,True,True
+vaccination boost,92,vaccination dose,0.8484848484848485,Treatment Dosage Regimen,True,True,True
+surface marker,46,cell surface marker,0.8484848484848485,Biospecimen Type,True,True,True
+vaccination state,20,vaccination dose,0.8484848484848485,Treatment Dosage Regimen,True,True,True
+incubation period,12,infection period,0.8484848484848485,Biospecimen Disease Condition,True,True,True
+culture variation,5,culture duration,0.8484848484848485,Treatment Dosage Regimen,True,True,True
+description,294,age description,0.8461538461538461,Biospecimen Age,True,True,True
+volunteer code,250,volunteer id,0.8461538461538461,External_sample_id,True,True,True
+Cause of death,172,age of death,0.8461538461538461,Biospecimen Age,True,True,True
+sampling site,57,sampling time,0.8461538461538461,Biospecimen Age,True,True,True
+Cause of Death,20,age of death,0.8461538461538461,Biospecimen Age,True,True,True
+maternal state,10,maternal age,0.8461538461538461,Biospecimen Age,True,True,True
+cause of death,2,age of death,0.8461538461538461,Biospecimen Age,True,True,True
+induction,57,induration,0.8421052631578947,Treatment Dosage Regimen,True,True,True
+infectious,33,infection,0.8421052631578947,Biospecimen Disease Condition,True,True,True
+antibody vendor name,21,antibody vendor id,0.8421052631578947,External_sample_id,True,True,True
+Histopathological diagnostic,180,histological diagnosis,0.84,Biospecimen Disease Condition,True,True,True
+histopathological diagnostic,3,histological diagnosis,0.84,Biospecimen Disease Condition,True,True,True
+parental line,55,parental cell line,0.8387096774193549,Biospecimen Type,True,True,True
+state of culture,42,age of  culture,0.8387096774193549,Biospecimen Age,True,True,True
+biological source,12,biological sex,0.8387096774193549,Biospecimen Sex,True,True,True
+long description,12,age description,0.8387096774193549,Biospecimen Age,True,True,True
+library backbone,10,library barcode,0.8387096774193549,External_sample_id,True,True,True
+subpopulation,9,cell subpopulation,0.8387096774193549,Biospecimen Type,True,True,True
+survival_yr,876,survival year,0.8333333333333334,Biospecimen Age,True,True,True
+study,741,studyid,0.8333333333333334,External_sample_id,True,True,True
+date harvest,500,time harvest,0.8333333333333334,Biospecimen Age,True,True,True
+culture type,334,culture time,0.8333333333333334,Biospecimen Age,True,True,True
+metastatic site,50,metastatic tumor site,0.8333333333333334,Biospecimen Disease Condition,True,True,True
+collection,40,collection day,0.8333333333333334,Biospecimen Age,True,True,True
+strand,22,strain,0.8333333333333334,Biospecimen Organism,True,True,True
+differentiation_method,152,differentiation_age,0.8292682926829268,Biospecimen Age,True,True,True
+genomic modification,38,chemical modification,0.8292682926829268,Treatment,True,True,True
+genotype/varation,14,mouse genotype/variation,0.8292682926829268,Biospecimen Organism,True,True,True
+clinical status,1187,clinical stage,0.8275862068965517,Biospecimen Age,True,True,True
+transduction,629,cell transduction,0.8275862068965517,Biospecimen Type,True,True,True
+immunization,265,immunization dose,0.8275862068965517,Treatment Dosage Regimen,True,True,True
+injection site,73,infection state,0.8275862068965517,Biospecimen Disease Condition,True,True,True
+Clinical Status,35,clinical stage,0.8275862068965517,Biospecimen Age,True,True,True
+viral infected,33,viral infection,0.8275862068965517,Biospecimen Disease Condition,True,True,True
+clone phenotype,26,cell phenotype,0.8275862068965517,Biospecimen Type,True,True,True
+collection_date,25,collection day,0.8275862068965517,Biospecimen Age,True,True,True
+classification,369,classification group,0.8235294117647058,Treatment,True,True,True
+education,300,duration,0.8235294117647058,Treatment Dosage Regimen,True,True,True
+library,198,library id,0.8235294117647058,External_sample_id,True,True,True
+experimental batch,38,experimental day,0.8235294117647058,Biospecimen Age,True,True,True
+number of_animals,4,number of_samples,0.8235294117647058,External_sample_id,True,True,True
+hours post invasion,162,hours post infection,0.8205128205128205,Biospecimen Disease Condition,True,True,True
+alternative name,14,alternative sample name,0.8205128205128205,External_sample_id,True,True,True
+genotype background,9,cell type background,0.8205128205128205,Biospecimen Type,True,True,True
+replicate number,6,sample replicate number,0.8205128205128205,External_sample_id,True,True,True
+case number,726,cell number,0.8181818181818182,Biospecimen Type,True,True,True
+library date,385,library id,0.8181818181818182,External_sample_id,True,True,True
+overall.survival.months,168,overall.survival.time,0.8181818181818182,Biospecimen Age,True,True,True
+replicates,58,replicate id,0.8181818181818182,External_sample_id,True,True,True
+growth type,44,growth time,0.8181818181818182,Biospecimen Age,True,True,True
+er status,41,cancer status,0.8181818181818182,Biospecimen Disease Condition,True,True,True
+plate code,28,patient code,0.8181818181818182,External_sample_id,True,True,True
+stimulation,2378,cell stimulation,0.8148148148148148,Biospecimen Type,True,True,True
+library preparation method,500,library preparation protocol,0.8148148148148148,Treatment Dosage Regimen,True,True,True
+vaccination,404,vaccination dose,0.8148148148148148,Treatment Dosage Regimen,True,True,True
+source type,345,source cell type,0.8148148148148148,Biospecimen Type,True,True,True
+case/control,191,case or control,0.8148148148148148,Treatment,True,True,True
+preparation,169,cell preparation,0.8148148148148148,Biospecimen Type,True,True,True
+als phenotype,96,cell phenotype,0.8148148148148148,Biospecimen Type,True,True,True
+clinical type,85,clinical stage,0.8148148148148148,Biospecimen Age,True,True,True
+compartment,69,cell compartment,0.8148148148148148,Biospecimen Type,True,True,True
+inoculation,45,inoculation dose,0.8148148148148148,Treatment Dosage Regimen,True,True,True
+culture status,28,culture stage,0.8148148148148148,Biospecimen Age,True,True,True
+clinical phenotype,103,cell phenotype,0.8125,Biospecimen Type,True,True,True
+sub-population,92,cell subpopulation,0.8125,Biospecimen Type,True,True,True
+experimental set,57,experimental day,0.8125,Biospecimen Age,True,True,True
+health_status,50,donor_health_status,0.8125,External_sample_id,True,True,True
+experimental repeat,39,experimental group,0.8108108108108109,Treatment,True,True,True
+overall survival,18,overall.survival.time,0.8108108108108109,Biospecimen Age,True,True,True
+round of selection,6,rounds of infection,0.8108108108108109,Biospecimen Disease Condition,True,True,True
+replicate description,362,treatment description,0.8095238095238095,Treatment,True,True,True
+mechanical ventilation,162,mechanical condition,0.8095238095238095,Biospecimen Disease Condition,True,True,True
+library preparation,277,library preparation protocol,0.8085106382978723,Treatment Dosage Regimen,True,True,True
+source,1670,source id,0.8,External_sample_id,True,True,True
+datatype description,1606,age description,0.8,Biospecimen Age,True,True,True
+animal,1261,animal id,0.8,External_sample_id,True,True,True
+primary site,1010,primary tumor site,0.8,Biospecimen Disease Condition,True,True,True
+fraction,1003,age fraction,0.8,Biospecimen Age,True,True,True
+morphology,764,cell morphology,0.8,Biospecimen Type,True,True,True
+brain region,595,brain tumor region,0.8,Biospecimen Disease Condition,True,True,True
+resistance,506,drug resistance,0.8,Treatment,True,True,True
+population,477,cell population,0.8,Biospecimen Type,True,True,True
+category,296,age_category,0.8,Biospecimen Age,True,True,True
+state,214,stage,0.8,Biospecimen Age,True,True,True
+couple number,188,mouse number,0.8,Biospecimen Organism,True,True,True
+molecular subtype,176,molecular subgroup,0.8,Treatment,True,True,True
+inflammation status,135,infection status,0.8,Biospecimen Disease Condition,True,True,True
+family,134,family id,0.8,External_sample_id,True,True,True
+culture media,116,culture days,0.8,Biospecimen Age,True,True,True
+immune status,113,mouse status,0.8,Biospecimen Organism,True,True,True
+localization,99,tumor localization,0.8,Biospecimen Disease Condition,True,True,True
+location of onset,92,location of tumors,0.8,Biospecimen Disease Condition,True,True,True
+experimental status,72,experimental day,0.8,Biospecimen Age,True,True,True
+parental origin,70,parental strain,0.8,Biospecimen Organism,True,True,True
+Subsets,60,subjects,0.8,External_sample_id,True,True,True
+person,46,person id,0.8,External_sample_id,True,True,True
+vendor,44,vendor id,0.8,External_sample_id,True,True,True
+Source,37,source id,0.8,External_sample_id,True,True,True
+indication,36,induration,0.8,Treatment Dosage Regimen,True,True,True
+experimental design,35,experimental day,0.8,Biospecimen Age,True,True,True
+body site,34,biopsy site,0.8,Biospecimen Type,True,True,True
+parasite isolate,33,parasite stage,0.8,Biospecimen Age,True,True,True
+gene,33,gender,0.8,Biospecimen Sex,True,True,True
+maternal health status,31,maternal disease status,0.8,Biospecimen Disease Condition,True,True,True
+experimental factor,28,experimental day,0.8,Biospecimen Age,True,True,True
+harvesting,26,harvesting time,0.8,Biospecimen Age,True,True,True
+type of death,20,age of death,0.8,Biospecimen Age,True,True,True
+enrichment,20,cell enrichment,0.8,Biospecimen Type,True,True,True
+family code,16,family id,0.8,External_sample_id,True,True,True
+fold enrichment,12,cell enrichment,0.8,Biospecimen Type,True,True,True
+incubation,7,incubation time,0.8,Biospecimen Age,True,True,True
+Morphology,3,cell morphology,0.8,Biospecimen Type,True,True,True
+environmental factor,8,environmental condition,0.7906976744186046,Biospecimen Disease Condition,True,True,False
+initial ich volume,399,initial tumor volume,0.7894736842105263,Biospecimen Disease Condition,True,True,False
+chip antibody vendor,380,antibody vendor id,0.7894736842105263,External_sample_id,True,True,False
+chip-antibody vendor,33,antibody vendor id,0.7894736842105263,External_sample_id,True,True,False
+clip antibody vendor,2,antibody vendor id,0.7894736842105263,External_sample_id,True,True,False
+number of relapses,192,number of cells,0.7878787878787878,Biospecimen Type,True,True,False
+clinical phenotypes,33,cell phenotype,0.7878787878787878,Biospecimen Type,True,True,False
+anatomic site,10,tissue anatomic site,0.7878787878787878,Biospecimen Type,True,True,False
+viral inactivation,10,viral infection,0.7878787878787878,Biospecimen Disease Condition,True,True,False
+incubation partner,1,incubation time,0.7878787878787878,Biospecimen Age,True,True,False
+development,310,development stage,0.7857142857142857,Biospecimen Age,True,True,False
+case_phenotype,97,cell phenotype,0.7857142857142857,Biospecimen Type,True,True,False
+parasite line,95,parasite strain,0.7857142857142857,Biospecimen Organism,True,True,False
+malaria status,10,malaria strain,0.7857142857142857,Biospecimen Organism,True,True,False
+differentiation replicate,9,differentiation time point,0.7843137254901961,Biospecimen Age,True,True,False
+histology,3618,histopathology,0.782608695652174,Biospecimen Disease Condition,True,True,False
+phenotype,1959,cell phenotype,0.782608695652174,Biospecimen Type,True,True,False
+Phenotype,141,cell phenotype,0.782608695652174,Biospecimen Type,True,True,False
+line type,123,cell line type,0.782608695652174,Biospecimen Type,True,True,False
+biologics,120,biological sex,0.782608695652174,Biospecimen Sex,True,True,False
+Histology,107,histopathology,0.782608695652174,Biospecimen Disease Condition,True,True,False
+growth media,106,growth time,0.782608695652174,Biospecimen Age,True,True,False
+karyotype,77,cell karyotype,0.782608695652174,Biospecimen Type,True,True,False
+library input,58,library id,0.782608695652174,External_sample_id,True,True,False
+channel type,24,cancer type,0.782608695652174,Biospecimen Disease Condition,True,True,False
+Karyotype,21,cell karyotype,0.782608695652174,Biospecimen Type,True,True,False
+nes status,8,cancer status,0.782608695652174,Biospecimen Disease Condition,True,True,False
+als status,6,sample status,0.782608695652174,External_sample_id,True,True,False
+genetic modification,227,chemical modification,0.7804878048780488,Treatment,True,True,False
+antibody description,151,condition description,0.7804878048780488,Biospecimen Disease Condition,True,True,False
+hippocampal sclerosis,6,hippocampal slice id,0.7804878048780488,External_sample_id,True,True,False
+culture,1264,culture age,0.7777777777777778,Biospecimen Age,True,True,False
+sorted compartment,500,tissue compartment,0.7777777777777778,Biospecimen Type,True,True,False
+infectious challenge,82,infectious agent,0.7777777777777778,Biospecimen Age,True,True,False
+derivation,65,duration,0.7777777777777778,Treatment Dosage Regimen,True,True,False
+animal no,15,animal id,0.7777777777777778,External_sample_id,True,True,False
+data type description,4,age description,0.7777777777777778,Biospecimen Age,True,True,False
+clinical info,3680,clinical diagnosis,0.7741935483870968,Biospecimen Disease Condition,True,True,False
+experiment type,295,experimental day,0.7741935483870968,Biospecimen Age,True,True,False
+isolation source,113,isolation stage,0.7741935483870968,Biospecimen Age,True,True,False
+bacterial lysate,88,bacterial cells,0.7741935483870968,Biospecimen Type,True,True,False
+number of_mice,62,number of_samples,0.7741935483870968,External_sample_id,True,True,False
+study number,50,study sample number,0.7741935483870968,External_sample_id,True,True,False
+translocation,44,treatment location,0.7741935483870968,Treatment,True,True,False
+dementia status,16,treatment status,0.7741935483870968,Treatment,True,True,False
+experiment name,15,experimental day,0.7741935483870968,Biospecimen Age,True,True,False
+antibody name,9,antibody treatment,0.7741935483870968,Treatment,True,True,False
+hours post fertilization,35,hours post infection,0.7727272727272727,Biospecimen Disease Condition,True,True,False
+batch,9770,batch id,0.7692307692307693,External_sample_id,True,True,False
+plate,3492,plate id,0.7692307692307693,External_sample_id,True,True,False
+region,2915,regimen,0.7692307692307693,Treatment Dosage Regimen,True,True,False
+experiment,1725,experimental day,0.7692307692307693,Biospecimen Age,True,True,False
+segment type,1492,treatment type,0.7692307692307693,Treatment,True,True,False
+infected with,898,infected host,0.7692307692307693,Biospecimen Organism,True,True,False
+clone,871,clone id,0.7692307692307693,External_sample_id,True,True,False
+chip_antibody_lot,696,chip_antibody_provider,0.7692307692307693,External_sample_id,True,True,False
+surgery number,500,usage number,0.7692307692307693,Biospecimen Age,True,True,False
+who category,493,tumor category,0.7692307692307693,Biospecimen Disease Condition,True,True,False
+array,407,array id,0.7692307692307693,External_sample_id,True,True,False
+plate_number,195,patient number,0.7692307692307693,External_sample_id,True,True,False
+hours post-invasion,172,hours post infection,0.7692307692307693,Biospecimen Disease Condition,True,True,False
+subset,168,subject,0.7692307692307693,External_sample_id,True,True,False
+culture method,84,culture time,0.7692307692307693,Biospecimen Age,True,True,False
+dissection,84,disease location,0.7692307692307693,Biospecimen Disease Condition,True,True,False
+simulation,80,cell stimulation,0.7692307692307693,Biospecimen Type,True,True,False
+clinic status,54,cancer status,0.7692307692307693,Biospecimen Disease Condition,True,True,False
+pooled,38,pool id,0.7692307692307693,External_sample_id,True,True,False
+alternative_name,33,alternative sample name,0.7692307692307693,External_sample_id,True,True,False
+series,27,species,0.7692307692307693,Biospecimen Organism,True,True,False
+replicate type,22,replicate id,0.7692307692307693,External_sample_id,True,True,False
+culture medium,10,culture time,0.7692307692307693,Biospecimen Age,True,True,False
+activation,8,activation agent,0.7692307692307693,Biospecimen Age,True,True,False
+life cycle,6,life cycle stage,0.7692307692307693,Biospecimen Age,True,True,False
+antibody lot,6,antibody group,0.7692307692307693,Treatment,True,True,False
+vaccination status,14,infection status,0.7647058823529411,Biospecimen Disease Condition,True,True,False
+sorted population,13,sample population,0.7647058823529411,External_sample_id,True,True,False
+radiation response,12,patient response,0.7647058823529411,External_sample_id,True,True,False
+type of insertion,12,site of infection,0.7647058823529411,Biospecimen Disease Condition,True,True,False
+number of animals,10,number of_samples,0.7647058823529411,External_sample_id,True,True,False
+associated geo,4,associate geo_sample,0.7647058823529411,External_sample_id,True,True,False
+tubules with spermatocytes,6,tubules with round spermatids,0.7636363636363637,External_sample_id,True,True,False
+genotype,46776,host genotype,0.7619047619047619,Biospecimen Organism,True,True,False
+location,2284,location/side,0.7619047619047619,External_sample_id,True,True,False
+response,667,drug response,0.7619047619047619,Treatment,True,True,False
+os_status,656,mouse status,0.7619047619047619,Biospecimen Organism,True,True,False
+survival,444,survival time,0.7619047619047619,Biospecimen Age,True,True,False
+exposure,381,exposure time,0.7619047619047619,Biospecimen Age,True,True,False
+infected,101,time infected,0.7619047619047619,Biospecimen Age,True,True,False
+folder name,79,slide name,0.7619047619047619,External_sample_id,True,True,False
+roi type,64,organoid type,0.7619047619047619,External_sample_id,True,True,False
+Genotype,52,host genotype,0.7619047619047619,Biospecimen Organism,True,True,False
+specific,39,specific-host,0.7619047619047619,Biospecimen Organism,True,True,False
+water type,32,cancer type,0.7619047619047619,Biospecimen Disease Condition,True,True,False
+virus added,30,virus dose,0.7619047619047619,Treatment Dosage Regimen,True,True,False
+genetic modifications,28,chemical modification,0.7619047619047619,Treatment,True,True,False
+clone type,24,cancer type,0.7619047619047619,Biospecimen Disease Condition,True,True,False
+lot number,20,cell number,0.7619047619047619,Biospecimen Type,True,True,False
+ps status,8,mouse status,0.7619047619047619,Biospecimen Organism,True,True,False
+tic class,6,tissue class,0.7619047619047619,Biospecimen Type,True,True,False
+survival cluster,170,survival time,0.7586206896551724,Biospecimen Age,True,True,False
+lesion status,57,infection status,0.7586206896551724,Biospecimen Disease Condition,True,True,False
+donation source,35,control source,0.7586206896551724,Treatment,True,True,False
+common name,16,sample common name,0.7586206896551724,External_sample_id,True,True,False
+nitrogen source,8,control source,0.7586206896551724,Treatment,True,True,False
+labversion description,35,age description,0.7567567567567568,Biospecimen Age,True,True,False
+experimental variable,18,experimental day,0.7567567567567568,Biospecimen Age,True,True,False
+initial preparation,10,tissue preparation,0.7567567567567568,Biospecimen Type,True,True,False
+mutation frequency,9,treatment frequency,0.7567567567567568,Treatment,True,True,False
+fraction/population,6,patient population,0.7567567567567568,External_sample_id,True,True,False
+number of malaria infections,250,malaria infection,0.7555555555555555,Biospecimen Disease Condition,True,True,False
+source/differentiation,16,days of differentiation,0.7555555555555555,Biospecimen Age,True,True,False
+site,2620,side,0.75,External_sample_id,True,True,False
+collection_method,1517,collection time,0.75,Biospecimen Age,True,True,False
+well,1500,cell,0.75,Biospecimen Type,True,True,False
+tag,1317,stage,0.75,Biospecimen Age,True,True,False
+selection,567,mouse selection,0.75,Biospecimen Organism,True,True,False
+growth phase,558,growth stage,0.75,Biospecimen Age,True,True,False
+case,551,cage,0.75,Biospecimen Age,True,True,False
+animal replicate,500,animal treatment,0.75,Treatment,True,True,False
+vital status,450,covid status,0.75,External_sample_id,True,True,False
+who grade,367,tumor who grade,0.75,Biospecimen Disease Condition,True,True,False
+mutation,354,duration,0.75,Treatment Dosage Regimen,True,True,False
+genome/variation,266,mouse genotype/variation,0.75,Biospecimen Organism,True,True,False
+section,219,infection,0.75,Biospecimen Disease Condition,True,True,False
+brain location,197,treatment location,0.75,Treatment,True,True,False
+experimental replicate,196,experimental group,0.75,Treatment,True,True,False
+growth medium,193,growth time,0.75,Biospecimen Age,True,True,False
+protect outcome,167,treatment outcome,0.75,Treatment,True,True,False
+other_medication,158,acute medication,0.75,Treatment,True,True,False
+pathogens,138,pathogen strain,0.75,Biospecimen Organism,True,True,False
+line number,117,sample number,0.75,External_sample_id,True,True,False
+array batch,116,array barcode,0.75,External_sample_id,True,True,False
+isolate type,97,disease type,0.75,Biospecimen Disease Condition,True,True,False
+health status,92,cell status,0.75,Biospecimen Type,True,True,False
+responder,84,responder cells,0.75,Biospecimen Type,True,True,False
+experiment label,82,experimental day,0.75,Biospecimen Age,True,True,False
+viral status,82,viral strain,0.75,Biospecimen Organism,True,True,False
+sort population,72,sample population,0.75,External_sample_id,True,True,False
+variant type,72,vaccine type,0.75,Treatment,True,True,False
+size,66,side,0.75,External_sample_id,True,True,False
+Case,60,cage,0.75,Biospecimen Age,True,True,False
+FISH origin,53,tissue origin,0.75,Biospecimen Type,True,True,False
+experiment batch,48,experimental day,0.75,Biospecimen Age,True,True,False
+isolation,47,isolation stage,0.75,Biospecimen Age,True,True,False
+specificity,42,specific-host,0.75,Biospecimen Organism,True,True,False
+neuropathological.information,39,neuropathological_diagnosis,0.75,Biospecimen Disease Condition,True,True,False
+phenotypes,30,cell phenotype,0.75,Biospecimen Type,True,True,False
+twin status,25,tissue status,0.75,Biospecimen Type,True,True,False
+pair status,24,cancer status,0.75,Biospecimen Disease Condition,True,True,False
+collection buffer,18,collection time,0.75,Biospecimen Age,True,True,False
+vital_status,18,covid_status,0.75,External_sample_id,True,True,False
+translocations,18,treatment location,0.75,Treatment,True,True,False
+culture batch,18,culture age,0.75,Biospecimen Age,True,True,False
+es line,15,cell line,0.75,Biospecimen Type,True,True,False
+stim,15,time,0.75,Biospecimen Age,True,True,False
+length of culture,15,age of  culture,0.75,Biospecimen Age,True,True,False
+clone name,12,cell line name,0.75,Biospecimen Type,True,True,False
+efflux status,12,cell status,0.75,Biospecimen Type,True,True,False
+source muscle,12,source cell,0.75,Biospecimen Type,True,True,False
+clinical manifestation,12,clinical condition,0.75,Biospecimen Disease Condition,True,True,False
+sediment,12,specimen,0.75,Biospecimen Type,True,True,False
+derived culture,9,derived cell_type,0.75,Biospecimen Type,True,True,False
+process order,9,process day,0.75,Biospecimen Age,True,True,False
+zinc status,6,cancer status,0.75,Biospecimen Disease Condition,True,True,False
+nodal status,6,covid status,0.75,External_sample_id,True,True,False
+Growth Medium,6,growth time,0.75,Biospecimen Age,True,True,False
+sorted,5,sorter day,0.75,Biospecimen Age,True,True,False
+background mice,4,background strain,0.75,Biospecimen Organism,True,True,False
+reference lot,3,reference condition,0.75,Biospecimen Disease Condition,True,True,False
+reference cat,3,reference condition,0.75,Biospecimen Disease Condition,True,True,False
+molecular classification,248,molecular condition,0.7441860465116279,Biospecimen Disease Condition,True,False,False
+chip_antibody,680,chip_antibody_provider,0.7428571428571429,External_sample_id,True,False,False
+inflammation_status,202,infection status,0.7428571428571429,Biospecimen Disease Condition,True,False,False
+diabetes_medication,158,acute medication,0.7428571428571429,Treatment,True,False,False
+number of replicates,36,number of cells,0.7428571428571429,Biospecimen Type,True,False,False
+sampling location,27,sampling timepoint,0.7428571428571429,Biospecimen Age,True,False,False
+anatomical site,24,tissue anatomic site,0.7428571428571429,Biospecimen Type,True,False,False
+microglia population,8,cell population,0.7428571428571429,Biospecimen Type,True,False,False
+clinical comments,8,clinical condition,0.7428571428571429,Biospecimen Disease Condition,True,False,False
+number of_tracheas,4,number of_samples,0.7428571428571429,External_sample_id,True,False,False
+transplanted with,2,transplanted organ,0.7428571428571429,Biospecimen Type,True,False,False
+library prep,1030,library barcode,0.7407407407407407,External_sample_id,True,False,False
+background,730,strain background,0.7407407407407407,Biospecimen Organism,True,False,False
+library name,476,library barcode,0.7407407407407407,External_sample_id,True,False,False
+processing,210,tissue processing,0.7407407407407407,Biospecimen Type,True,False,False
+symptomatic,178,symptom duration,0.7407407407407407,Treatment Dosage Regimen,True,False,False
+carbon source,62,control source,0.7407407407407407,Treatment,True,False,False
+receptor status,44,tumor status,0.7407407407407407,Biospecimen Disease Condition,True,False,False
+location type,36,location tumor,0.7407407407407407,Biospecimen Disease Condition,True,False,False
+virus subtype,20,tissue subtype,0.7407407407407407,Biospecimen Type,True,False,False
+sorted fraction,16,age fraction,0.7407407407407407,Biospecimen Age,True,False,False
+transplant,13,age at transplant,0.7407407407407407,Biospecimen Age,True,False,False
+oxygenation,12,oxygen condition,0.7407407407407407,Biospecimen Disease Condition,True,False,False
+antibody used,11,antibody group,0.7407407407407407,Treatment,True,False,False
+material,1047,maternalage,0.7368421052631579,Biospecimen Age,True,False,False
+subtype,994,cell subtype,0.7368421052631579,Biospecimen Type,True,False,False
+site_onset,876,age_onset,0.7368421052631579,Biospecimen Age,True,False,False
+genetic background,683,cell line background,0.7368421052631579,Biospecimen Type,True,False,False
+first vaccination,614,time post-vaccination,0.7368421052631579,Biospecimen Age,True,False,False
+markers,382,cell markers,0.7368421052631579,Biospecimen Type,True,False,False
+visit_date,313,visit day,0.7368421052631579,Biospecimen Age,True,False,False
+technology,128,pathology,0.7368421052631579,Biospecimen Disease Condition,True,False,False
+Genetic background,69,cell line background,0.7368421052631579,Biospecimen Type,True,False,False
+route administered,52,vaccine administered,0.7368421052631579,Treatment,True,False,False
+onset site,48,onset age,0.7368421052631579,Biospecimen Age,True,False,False
+relapse,47,relapse time,0.7368421052631579,Biospecimen Age,True,False,False
+experimental variables,42,experimental day,0.7368421052631579,Biospecimen Age,True,False,False
+virus-stimulation,37,time post-stimulation,0.7368421052631579,Biospecimen Age,True,False,False
+clinical information,36,clinical condition,0.7368421052631579,Biospecimen Disease Condition,True,False,False
+core code,33,donor code,0.7368421052631579,External_sample_id,True,False,False
+metastatic status,22,metastatic tumor site,0.7368421052631579,Biospecimen Disease Condition,True,False,False
+replica,12,replicate id,0.7368421052631579,External_sample_id,True,False,False
+model type,12,cell type,0.7368421052631579,Biospecimen Type,True,False,False
+bal sampling date,212,sampling time,0.7333333333333333,Biospecimen Age,True,False,False
+current status,100,treatment status,0.7333333333333333,Treatment,True,False,False
+clinical outcome,74,clinical stage,0.7333333333333333,Biospecimen Age,True,False,False
+antibody status,31,organoid status,0.7333333333333333,External_sample_id,True,False,False
+culture format,18,culture duration,0.7333333333333333,Treatment Dosage Regimen,True,False,False
+oxygen tension,12,oxygen condition,0.7333333333333333,Biospecimen Disease Condition,True,False,False
+weight phenotype,9,cell phenotype,0.7333333333333333,Biospecimen Type,True,False,False
+embryo phenotype,9,cell phenotype,0.7333333333333333,Biospecimen Type,True,False,False
+antibody cat,6,antibody treatment,0.7333333333333333,Treatment,True,False,False
+genetic_modification,12,chemical modification,0.7317073170731707,Treatment,True,False,False
+antibody,4446,antibody group,0.7272727272727273,Treatment,True,False,False
+library type,1600,library id,0.7272727272727273,External_sample_id,True,False,False
+surgical status,1417,surgical treatment,0.7272727272727273,Treatment,True,False,False
+roi number,1177,mouse number,0.7272727272727273,Biospecimen Organism,True,False,False
+lane,566,lane id,0.7272727272727273,External_sample_id,True,False,False
+origin,525,organ,0.7272727272727273,Biospecimen Type,True,False,False
+injection_roi,500,infection,0.7272727272727273,Biospecimen Disease Condition,True,False,False
+code,473,barcode,0.7272727272727273,External_sample_id,True,False,False
+line,459,lineage,0.7272727272727273,Biospecimen Age,True,False,False
+library well,412,library id,0.7272727272727273,External_sample_id,True,False,False
+city,284,acidity,0.7272727272727273,External_sample_id,True,False,False
+health state,213,cell state,0.7272727272727273,Biospecimen Type,True,False,False
+knockout,203,knockout group,0.7272727272727273,Treatment,True,False,False
+target,102,stage,0.7272727272727273,Biospecimen Age,True,False,False
+Exposures,101,exposure time,0.7272727272727273,Biospecimen Age,True,False,False
+pain,101,patient,0.7272727272727273,External_sample_id,True,False,False
+surgery type,76,serum type,0.7272727272727273,Biospecimen Type,True,False,False
+infiltration,64,induration,0.7272727272727273,Treatment Dosage Regimen,True,False,False
+parasite,36,parasite stage,0.7272727272727273,Biospecimen Age,True,False,False
+brain section,30,infection,0.7272727272727273,Biospecimen Disease Condition,True,False,False
+clinical,26,clinical stage,0.7272727272727273,Biospecimen Age,True,False,False
+fip status,24,covid status,0.7272727272727273,External_sample_id,True,False,False
+modification,22,chemical modification,0.7272727272727273,Treatment,True,False,False
+generation,22,age fraction,0.7272727272727273,Biospecimen Age,True,False,False
+Shear exposure,20,time after exposure,0.7272727272727273,Biospecimen Age,True,False,False
+pool,16,pool id,0.7272727272727273,External_sample_id,True,False,False
+genotype abbreviation,14,mouse line abbreviation,0.7272727272727273,Biospecimen Organism,True,False,False
+scale,12,sample,0.7272727272727273,External_sample_id,True,False,False
+feature type,2,tumor type,0.7272727272727273,Biospecimen Disease Condition,True,False,False
+parasitemia category,155,patient category,0.7222222222222222,External_sample_id,True,False,False
+metastasis site,72,metastatic tumor site,0.7222222222222222,Biospecimen Disease Condition,True,False,False
+location of lesion,58,location of tumors,0.7222222222222222,Biospecimen Disease Condition,True,False,False
+inhibitor removal,36,inhibitor treatment,0.7222222222222222,Treatment,True,False,False
+number of cag repeats,9,number of cells,0.7222222222222222,Biospecimen Type,True,False,False
+Extraction_amount,6,extraction_protocol,0.7222222222222222,Treatment Dosage Regimen,True,False,False
+post-symptom onset,5,days_symptom_onset,0.7222222222222222,Biospecimen Age,True,False,False
+reference,1682,sample_reference,0.72,External_sample_id,True,False,False
+protection,1172,cell projection,0.72,Biospecimen Type,True,False,False
+platesimple,992,patient sample,0.72,External_sample_id,True,False,False
+culture result,894,culture age,0.72,Biospecimen Age,True,False,False
+recipient,534,recipient strain,0.72,Biospecimen Organism,True,False,False
+parasitemia,419,parasite stage,0.72,Biospecimen Age,True,False,False
+library quality,208,library id,0.72,External_sample_id,True,False,False
+application,120,publication id,0.72,External_sample_id,True,False,False
+infectivity,120,infection type,0.72,Biospecimen Disease Condition,True,False,False
+structure,67,tissue structure,0.72,Biospecimen Type,True,False,False
+growth pattern,55,growth time,0.72,Biospecimen Age,True,False,False
+library version,54,library id,0.72,External_sample_id,True,False,False
+graft source,47,gender source,0.72,Biospecimen Sex,True,False,False
+paired with,37,paired patient,0.72,External_sample_id,True,False,False
+sort fraction,27,age fraction,0.72,Biospecimen Age,True,False,False
+material type,13,maternal age,0.72,Biospecimen Age,True,False,False
+oxygen status,4,mouse status,0.72,Biospecimen Organism,True,False,False
+clinical presentation,61,clinical condition,0.717948717948718,Biospecimen Disease Condition,True,False,False
+months_progression,2,timepoint_progressors,0.717948717948718,Biospecimen Age,True,False,False
+visit,3653,visit day,0.7142857142857143,Biospecimen Age,True,False,False
+molecule subtype,2882,cell subtype,0.7142857142857143,Biospecimen Type,True,False,False
+segment,2380,reagent,0.7142857142857143,Biospecimen Age,True,False,False
+malaria_status,500,malaria strain,0.7142857142857143,Biospecimen Organism,True,False,False
+death,460,death day,0.7142857142857143,Biospecimen Age,True,False,False
+survival_status,450,survival_time,0.7142857142857143,Biospecimen Age,True,False,False
+library plate,412,library barcode,0.7142857142857143,External_sample_id,True,False,False
+survival status,152,survival time,0.7142857142857143,Biospecimen Age,True,False,False
+notes,148,monocytes,0.7142857142857143,Biospecimen Type,True,False,False
+exposure_latent,140,exposure time,0.7142857142857143,Biospecimen Age,True,False,False
+country,120,control,0.7142857142857143,Treatment,True,False,False
+viral load,100,patient viral load,0.7142857142857143,External_sample_id,True,False,False
+volunteer number,96,mouse number,0.7142857142857143,Biospecimen Organism,True,False,False
+onset,90,age_onset,0.7142857142857143,Biospecimen Age,True,False,False
+pool no,81,pool id,0.7142857142857143,External_sample_id,True,False,False
+injected virus,73,injected cells,0.7142857142857143,Biospecimen Type,True,False,False
+library_batch,64,library barcode,0.7142857142857143,External_sample_id,True,False,False
+culture platform,57,culture time,0.7142857142857143,Biospecimen Age,True,False,False
+fever,56,fever day,0.7142857142857143,Biospecimen Age,True,False,False
+commercial source,56,cell source,0.7142857142857143,Biospecimen Type,True,False,False
+clinical_history,51,clinical.diagnosis.history,0.7142857142857143,Biospecimen Disease Condition,True,False,False
+skin phenotype,28,cell phenotype,0.7142857142857143,Biospecimen Type,True,False,False
+resection_type,24,infection type,0.7142857142857143,Biospecimen Disease Condition,True,False,False
+molecule source,23,sample source,0.7142857142857143,External_sample_id,True,False,False
+antibody target description,21,age description,0.7142857142857143,Biospecimen Age,True,False,False
+sorting fraction,16,age fraction,0.7142857142857143,Biospecimen Age,True,False,False
+lab code,15,lab id,0.7142857142857143,External_sample_id,True,False,False
+antigenic stimulation,14,time post-stimulation,0.7142857142857143,Biospecimen Age,True,False,False
+pooling,13,pool id,0.7142857142857143,External_sample_id,True,False,False
+plating,11,patient,0.7142857142857143,External_sample_id,True,False,False
+antibody maker,9,antibody group,0.7142857142857143,Treatment,True,False,False
+responder status,4,donor status,0.7142857142857143,External_sample_id,True,False,False
+genotype_abbreviation,500,mouse genotype/variation,0.7111111111111111,Biospecimen Organism,True,False,False
+experiment_type,970,experimental day,0.7096774193548387,Biospecimen Age,True,False,False
+diagnostic_mean,484,diagnostic_group,0.7096774193548387,Treatment,True,False,False
+surface area,363,cell surface marker,0.7096774193548387,Biospecimen Type,True,False,False
+pregnancy status,201,organoid status,0.7096774193548387,External_sample_id,True,False,False
+anatomic location,201,tumor location,0.7096774193548387,Biospecimen Disease Condition,True,False,False
+extraction date,185,exacerbation day,0.7096774193548387,Biospecimen Age,True,False,False
+Histological type,69,biological sex,0.7096774193548387,Biospecimen Sex,True,False,False
+isolation method,52,isolation stage,0.7096774193548387,Biospecimen Age,True,False,False
+sputum smear status,33,tumor status,0.7096774193548387,Biospecimen Disease Condition,True,False,False
+affected status,29,infection status,0.7096774193548387,Biospecimen Disease Condition,True,False,False
+derived from metastatic site,29,large cell lung cancer derived from metastatic site,0.7088607594936709,Biospecimen Type,True,False,False
+biological replicate,1375,biological sex,0.7058823529411765,Biospecimen Sex,True,False,False
+status,1055,cell status,0.7058823529411765,Biospecimen Type,True,False,False
+pathogen,478,pathology,0.7058823529411765,Biospecimen Disease Condition,True,False,False
+lymphs,460,lymphocytes,0.7058823529411765,Biospecimen Type,True,False,False
+stimulant,280,timeunit,0.7058823529411765,Biospecimen Age,True,False,False
+growth,187,growth time,0.7058823529411765,Biospecimen Age,True,False,False
+draw_date,185,draw day,0.7058823529411765,Biospecimen Age,True,False,False
+Status,89,cell status,0.7058823529411765,Biospecimen Type,True,False,False
+radiation,74,duration,0.7058823529411765,Treatment Dosage Regimen,True,False,False
+vs type,67,serum type,0.7058823529411765,Biospecimen Type,True,False,False
+cytology,64,pathology,0.7058823529411765,Biospecimen Disease Condition,True,False,False
+clinical trial phase,64,clinical stage,0.7058823529411765,Biospecimen Age,True,False,False
+modifications,57,chemical modification,0.7058823529411765,Treatment,True,False,False
+mutations,49,duration,0.7058823529411765,Treatment Dosage Regimen,True,False,False
+digestives_symptoms,45,disease symptom,0.7058823529411765,Biospecimen Disease Condition,True,False,False
+nutritional state,43,gestational stage,0.7058823529411765,Biospecimen Age,True,False,False
+Pathogen,29,pathology,0.7058823529411765,Biospecimen Disease Condition,True,False,False
+implantation,24,cell type implantation,0.7058823529411765,Biospecimen Type,True,False,False
+histological subtype,23,biological sex,0.7058823529411765,Biospecimen Sex,True,False,False
+autism diagnostic,16,patient diagnosis,0.7058823529411765,External_sample_id,True,False,False
+vaccination_status,14,infection status,0.7058823529411765,Biospecimen Disease Condition,True,False,False
+etiology,9,pathology,0.7058823529411765,Biospecimen Disease Condition,True,False,False
+variation,6,duration,0.7058823529411765,Treatment Dosage Regimen,True,False,False
+Labeling_reference,6,sample_reference,0.7058823529411765,External_sample_id,True,False,False
+gene induction,6,time after induction,0.7058823529411765,Biospecimen Age,True,False,False
+sampling post confirm,6,sampling time,0.7058823529411765,Biospecimen Age,True,False,False
+marker,5,cell marker,0.7058823529411765,Biospecimen Type,True,False,False
+reactivity,3,acidity,0.7058823529411765,External_sample_id,True,False,False
+experiment year_month,86,experiment group,0.7027027027027027,Treatment,True,False,False
+ClinicalInformation,75,clinical condition,0.7027027027027027,Biospecimen Disease Condition,True,False,False
+radiation exposure,39,lung radiation dose,0.7027027027027027,Treatment Dosage Regimen,True,False,False
+pulmonary compartment,27,cell compartment,0.7027027027027027,Biospecimen Type,True,False,False
+incubation temperature,8,incubation time,0.7027027027027027,Biospecimen Age,True,False,False
+Extraction_reference,6,patient reference,0.7027027027027027,External_sample_id,True,False,False
+second vaccination,614,days since vaccination,0.7,Biospecimen Age,True,False,False
+seizure,328,seizure group,0.7,Treatment,True,False,False
+study_origin,156,study_id,0.7,External_sample_id,True,False,False
+purification,92,duration,0.7,Treatment Dosage Regimen,True,False,False
+virus type,86,serum type,0.7,Biospecimen Type,True,False,False
+subclass,80,tissue class,0.7,Biospecimen Type,True,False,False
+subtypes,58,cell subtype,0.7,Biospecimen Type,True,False,False
+perturbation,54,duration,0.7,Treatment Dosage Regimen,True,False,False
+lymph node,51,lymphocyte,0.7,Biospecimen Type,True,False,False
+histological grade,44,histological diagnosis,0.7,Biospecimen Disease Condition,True,False,False
+who class,40,tumor class,0.7,Biospecimen Disease Condition,True,False,False
+Order Code,20,donor code,0.7,External_sample_id,True,False,False
+Death Cause,20,death day,0.7,Biospecimen Age,True,False,False
+risk grade,15,risk group,0.7,Treatment,True,False,False
+engraftment,12,treatment,0.7,Treatment,True,False,False
+histological response,38,histological diagnosis,0.6976744186046512,Biospecimen Disease Condition,False,False,False
+tandem repeat number,34,sample replicate number,0.6976744186046512,External_sample_id,False,False,False
+lane.number,597,usage number,0.6956521739130435,Biospecimen Age,False,False,False
+extract name,500,strain name,0.6956521739130435,Biospecimen Organism,False,False,False
+family history,374,family id,0.6956521739130435,External_sample_id,False,False,False
+conversion,156,concentration,0.6956521739130435,Treatment Dosage Regimen,False,False,False
+bal_culture,140,cell culture,0.6956521739130435,Biospecimen Type,False,False,False
+das score,120,disease course,0.6956521739130435,Biospecimen Disease Condition,False,False,False
+lymphoma type,102,lymphocyte,0.6956521739130435,Biospecimen Type,False,False,False
+exposed to,92,exposure time,0.6956521739130435,Biospecimen Age,False,False,False
+mating type,37,vaccine type,0.6956521739130435,Treatment,False,False,False
+Family History,37,family id,0.6956521739130435,External_sample_id,False,False,False
+batch number,36,cell number,0.6956521739130435,Biospecimen Type,False,False,False
+injury model,18,tumor model,0.6956521739130435,Biospecimen Disease Condition,False,False,False
+viral titre,16,viral strain,0.6956521739130435,Biospecimen Organism,False,False,False
+bacteria,10,bacterial cells,0.6956521739130435,Biospecimen Type,False,False,False
+animals pooled,10,animal id,0.6956521739130435,External_sample_id,False,False,False
+mating pair,6,twin pair id,0.6956521739130435,External_sample_id,False,False,False
+smoking status,2577,mouse status,0.6923076923076923,Biospecimen Organism,False,False,False
+trachea region,301,tumor region,0.6923076923076923,Biospecimen Disease Condition,False,False,False
+visit number,205,subject number,0.6923076923076923,External_sample_id,False,False,False
+viral shedding,180,viral strain,0.6923076923076923,Biospecimen Organism,False,False,False
+Filter number,101,sample number,0.6923076923076923,External_sample_id,False,False,False
+Smoking status,97,mouse status,0.6923076923076923,Biospecimen Organism,False,False,False
+fracture site,78,culture stage,0.6923076923076923,Biospecimen Age,False,False,False
+smoking_status,76,covid_status,0.6923076923076923,External_sample_id,False,False,False
+spike-ins,75,spike-in organism,0.6923076923076923,Biospecimen Organism,False,False,False
+collected_by,53,collection day,0.6923076923076923,Biospecimen Age,False,False,False
+cause.of.death,39,age of death,0.6923076923076923,Biospecimen Age,False,False,False
+library prep kit,37,library id,0.6923076923076923,External_sample_id,False,False,False
+culture results,27,culture age,0.6923076923076923,Biospecimen Age,False,False,False
+pathological type,25,pathology,0.6923076923076923,Biospecimen Disease Condition,False,False,False
+injected with,22,infected host,0.6923076923076923,Biospecimen Organism,False,False,False
+plate_location,500,tissue location,0.6896551724137931,Biospecimen Type,False,False,False
+transplant type,145,treatment type,0.6896551724137931,Treatment,False,False,False
+input material,84,sample material,0.6896551724137931,External_sample_id,False,False,False
+lymph node number,56,mouse number,0.6896551724137931,Biospecimen Organism,False,False,False
+primary mutation,54,primary tumor,0.6896551724137931,Biospecimen Disease Condition,False,False,False
+lymphoma subtype,31,tumor subtype,0.6896551724137931,Biospecimen Disease Condition,False,False,False
+knockout status,30,knockout group,0.6896551724137931,Treatment,False,False,False
+gametocyte status,24,mouse status,0.6896551724137931,Biospecimen Organism,False,False,False
+primary antibody,8,primary tumor,0.6896551724137931,Biospecimen Disease Condition,False,False,False
+molecule subtypes,6,cell subtype,0.6896551724137931,Biospecimen Type,False,False,False
+selection media,2,collection day,0.6896551724137931,Biospecimen Age,False,False,False
+treated with,920,treatment withdrawal,0.6875,Treatment,False,False,False
+injection_materials,500,injection age,0.6875,Biospecimen Age,False,False,False
+hemoglobin genotype,315,host genotype,0.6875,Biospecimen Organism,False,False,False
+recurrent_status,245,treatment status,0.6875,Treatment,False,False,False
+protect_outcome,144,treatment outcome,0.6875,Treatment,False,False,False
+pathogen exposure,60,pathogen strain,0.6875,Biospecimen Organism,False,False,False
+psoriasis subtype,27,disease subtype,0.6875,Biospecimen Disease Condition,False,False,False
+replicate experiment,12,replicate id,0.6875,External_sample_id,False,False,False
+chip antibody,5153,chip_antibody_provider,0.6857142857142857,External_sample_id,False,False,False
+colony of_origin,320,cell line of origin,0.6857142857142857,Biospecimen Type,False,False,False
+chip-antibody,298,chip_antibody_provider,0.6857142857142857,External_sample_id,False,False,False
+other information,236,other organ lesion,0.6857142857142857,Biospecimen Type,False,False,False
+smear of index case,140,years of disease,0.6857142857142857,Biospecimen Disease Condition,False,False,False
+biological replicates,24,biological sex,0.6857142857142857,Biospecimen Sex,False,False,False
+extraction batch,6,hybridization batch,0.6857142857142857,External_sample_id,False,False,False
+culture supplement,4,culture/treatment,0.6857142857142857,Treatment,False,False,False
+vaccination.assignment,275,activation agent,0.6842105263157895,Biospecimen Age,False,False,False
+chronic hypertension,194,chronic medication,0.6842105263157895,Treatment,False,False,False
+pulmonary cavitation,15,tumor localization,0.6842105263157895,Biospecimen Disease Condition,False,False,False
+immune infiltration,14,vaccine administration,0.6829268292682927,Treatment,False,False,False
+immature_granulocytes_absolute,500,monocyte_absolute,0.6808510638297872,Biospecimen Type,False,False,False
+library prep person,63,library preparation protocol,0.6808510638297872,Treatment Dosage Regimen,False,False,False
+antibody antibody description,4,condition description,0.68,Biospecimen Disease Condition,False,False,False
+grade,1888,race,0.6666666666666666,Biospecimen Race,False,False,False
+type,1856,celltype,0.6666666666666666,Biospecimen Type,False,False,False
+molecule type,1618,mouse genotype,0.6666666666666666,Biospecimen Organism,False,False,False
+virus,1436,virus dose,0.6666666666666666,Treatment Dosage Regimen,False,False,False
+assay,1202,passage,0.6666666666666666,Biospecimen Age,False,False,False
+lab,1170,lab id,0.6666666666666666,External_sample_id,False,False,False
+isolate,1067,strain/isolate,0.6666666666666666,Biospecimen Organism,False,False,False
+geographic location,804,tumor location,0.6666666666666666,Biospecimen Disease Condition,False,False,False
+os,703,host,0.6666666666666666,Biospecimen Organism,False,False,False
+severity,619,disease severity,0.6666666666666666,Biospecimen Disease Condition,False,False,False
+geographic origin,610,strain origin,0.6666666666666666,Biospecimen Organism,False,False,False
+center,596,gender,0.6666666666666666,Biospecimen Sex,False,False,False
+selection marker,554,cell marker,0.6666666666666666,Biospecimen Type,False,False,False
+immature_granulocytes_percent,500,monocyte_percent,0.6666666666666666,Biospecimen Type,False,False,False
+well address,500,cell markers,0.6666666666666666,Biospecimen Type,False,False,False
+full_genotype,500,cell phenotype,0.6666666666666666,Biospecimen Type,False,False,False
+instrument model,500,tumor model,0.6666666666666666,Biospecimen Disease Condition,False,False,False
+microdissection,500,mouse selection,0.6666666666666666,Biospecimen Organism,False,False,False
+title,500,time,0.6666666666666666,Biospecimen Age,False,False,False
+meconium ileus status,500,mouse status,0.6666666666666666,Biospecimen Organism,False,False,False
+assay name,500,passage number,0.6666666666666666,Biospecimen Age,False,False,False
+multisector,500,tissue factor,0.6666666666666666,Biospecimen Type,False,False,False
+skin type,452,spike-in cell_type,0.6666666666666666,Biospecimen Type,False,False,False
+platelet,394,patient,0.6666666666666666,External_sample_id,False,False,False
+antigen,384,agent,0.6666666666666666,Biospecimen Age,False,False,False
+note,363,monocyte,0.6666666666666666,Biospecimen Type,False,False,False
+amplification,341,publication id,0.6666666666666666,External_sample_id,False,False,False
+ventilation,319,cell stimulation,0.6666666666666666,Biospecimen Type,False,False,False
+index,287,side,0.6666666666666666,External_sample_id,False,False,False
+neurological disorder,285,neuropathological diagnosis,0.6666666666666666,Biospecimen Disease Condition,False,False,False
+set,267,sex,0.6666666666666666,Biospecimen Sex,False,False,False
+read length,259,reagent,0.6666666666666666,Biospecimen Age,False,False,False
+duplication_rate,251,infection rate,0.6666666666666666,Biospecimen Disease Condition,False,False,False
+intrinsic subtype,231,tumor subtype,0.6666666666666666,Biospecimen Disease Condition,False,False,False
+timing,211,timepoint,0.6666666666666666,Biospecimen Age,False,False,False
+microbiota status,192,infection status,0.6666666666666666,Biospecimen Disease Condition,False,False,False
+survival after surgery,192,age at surgery,0.6666666666666666,Biospecimen Age,False,False,False
+period,186,person id,0.6666666666666666,External_sample_id,False,False,False
+bacterium,186,bacteria tissue,0.6666666666666666,Biospecimen Type,False,False,False
+hours,186,host,0.6666666666666666,Biospecimen Organism,False,False,False
+chip antibody lot,156,chip_antibody_provider,0.6666666666666666,External_sample_id,False,False,False
+prognosis,156,diagnosis,0.6666666666666666,Biospecimen Disease Condition,False,False,False
+library prep. kit,155,library id,0.6666666666666666,External_sample_id,False,False,False
+parasite density,150,parasite stage,0.6666666666666666,Biospecimen Age,False,False,False
+target gene,143,age/gender,0.6666666666666666,Biospecimen Age,False,False,False
+Other,136,therapy,0.6666666666666666,Treatment,False,False,False
+stress exposure,135,days post exposure,0.6666666666666666,Biospecimen Age,False,False,False
+components,133,compound,0.6666666666666666,Treatment,False,False,False
+phase,123,cell phase,0.6666666666666666,Biospecimen Type,False,False,False
+date of array,117,time of day,0.6666666666666666,Biospecimen Age,False,False,False
+hospital,116,days_in_hospital,0.6666666666666666,Biospecimen Age,False,False,False
+batch.date,116,batch id,0.6666666666666666,External_sample_id,False,False,False
+interim pet response,106,patient response,0.6666666666666666,External_sample_id,False,False,False
+other,106,therapy,0.6666666666666666,Treatment,False,False,False
+library strategy,101,laboratory strain,0.6666666666666666,Biospecimen Organism,False,False,False
+tender joints,101,time points,0.6666666666666666,Biospecimen Age,False,False,False
+chemistry,94,chemotherapy,0.6666666666666666,Treatment,False,False,False
+surgery,85,age at surgery,0.6666666666666666,Biospecimen Age,False,False,False
+viral family,78,viral strain,0.6666666666666666,Biospecimen Organism,False,False,False
+Type,73,celltype,0.6666666666666666,Biospecimen Type,False,False,False
+embryo,70,embryo stage,0.6666666666666666,Biospecimen Age,False,False,False
+anatomical location,70,tumor location,0.6666666666666666,Biospecimen Disease Condition,False,False,False
+tags,70,stage,0.6666666666666666,Biospecimen Age,False,False,False
+clinically_aggressive,66,clinical_diagnosis,0.6666666666666666,Biospecimen Disease Condition,False,False,False
+number of immunization boost,66,immunization dose,0.6666666666666666,Treatment Dosage Regimen,False,False,False
+backbone,66,barcode,0.6666666666666666,External_sample_id,False,False,False
+lesion_label,64,sample_label,0.6666666666666666,External_sample_id,False,False,False
+aspiration site,61,isolation stage,0.6666666666666666,Biospecimen Age,False,False,False
+sandwich type,59,cancer type,0.6666666666666666,Biospecimen Disease Condition,False,False,False
+types,58,cell types,0.6666666666666666,Biospecimen Type,False,False,False
+gene deletion status,58,infection status,0.6666666666666666,Biospecimen Disease Condition,False,False,False
+cag length,56,agent,0.6666666666666666,Biospecimen Age,False,False,False
+scan method,48,scan id,0.6666666666666666,External_sample_id,False,False,False
+processing batch,46,process day,0.6666666666666666,Biospecimen Age,False,False,False
+resection,38,mouse selection,0.6666666666666666,Biospecimen Organism,False,False,False
+data file subset,38,disease subset,0.6666666666666666,Biospecimen Disease Condition,False,False,False
+data type,37,disease type,0.6666666666666666,Biospecimen Disease Condition,False,False,False
+primary vs metastatic,35,primary disease,0.6666666666666666,Biospecimen Disease Condition,False,False,False
+nonunion type,35,infection type,0.6666666666666666,Biospecimen Disease Condition,False,False,False
+definite analysis,33,data analysis id,0.6666666666666666,External_sample_id,False,False,False
+twins,32,strains,0.6666666666666666,Biospecimen Organism,False,False,False
+cultivation,32,activation agent,0.6666666666666666,Biospecimen Age,False,False,False
+run,27,run id,0.6666666666666666,External_sample_id,False,False,False
+variant,26,participant,0.6666666666666666,External_sample_id,False,False,False
+previous severity,26,disease severity,0.6666666666666666,Biospecimen Disease Condition,False,False,False
+Body surface area,26,cell surface marker,0.6666666666666666,Biospecimen Type,False,False,False
+spinal cord region,24,brain tumor region,0.6666666666666666,Biospecimen Disease Condition,False,False,False
+decode_name,22,specimen_name,0.6666666666666666,Biospecimen Type,False,False,False
+Inflammation,20,infection,0.6666666666666666,Biospecimen Disease Condition,False,False,False
+desiccation,19,disease location,0.6666666666666666,Biospecimen Disease Condition,False,False,False
+fus aggregation state,19,infection state,0.6666666666666666,Biospecimen Disease Condition,False,False,False
+radiology,18,pathology,0.6666666666666666,Biospecimen Disease Condition,False,False,False
+primers,15,provider,0.6666666666666666,External_sample_id,False,False,False
+expressing,12,tissue processing,0.6666666666666666,Biospecimen Type,False,False,False
+company,12,compound,0.6666666666666666,Treatment,False,False,False
+type of cultivation plate,12,duration of cultivation,0.6666666666666666,Treatment Dosage Regimen,False,False,False
+antigen capture,11,time in culture,0.6666666666666666,Biospecimen Age,False,False,False
+lung section,10,mouse selection,0.6666666666666666,Biospecimen Organism,False,False,False
+hit.status,9,patient_status,0.6666666666666666,External_sample_id,False,False,False
+anatomical region,9,sample region,0.6666666666666666,External_sample_id,False,False,False
+growth phase/media,8,growth phase of cells,0.6666666666666666,Biospecimen Type,False,False,False
+anatomic segment,8,antibiotic treatment,0.6666666666666666,Treatment,False,False,False
+virus family,7,virus strain,0.6666666666666666,Biospecimen Organism,False,False,False
+virus genus,7,virus dose,0.6666666666666666,Treatment Dosage Regimen,False,False,False
+chip antibody reference,6,chip_antibody_provider,0.6666666666666666,External_sample_id,False,False,False
+term source ref,5,tumor source,0.6666666666666666,Biospecimen Disease Condition,False,False,False
+experiment performed in,4,experiment grouping,0.6666666666666666,Treatment,False,False,False
+strategy,4,storage,0.6666666666666666,Biospecimen Age,False,False,False
+media additions,4,growing media conditions,0.6666666666666666,Biospecimen Disease Condition,False,False,False
+antibody lot number,4,antibody group,0.6666666666666666,Treatment,False,False,False
+embryo characteristic,3,cell characterization,0.6666666666666666,Biospecimen Type,False,False,False
+severity grade,3,disease grade,0.6666666666666666,Biospecimen Disease Condition,False,False,False
+assay type,3,tissue type,0.6666666666666666,Biospecimen Type,False,False,False
+ligation,2,induration,0.6666666666666666,Treatment Dosage Regimen,False,False,False
+developmental/speech disorder,285,developmental stages,0.6530612244897959,Biospecimen Age,False,False,False
+technical_replicate_number,24,sample replicate number,0.6530612244897959,External_sample_id,False,False,False
+chip antibody details,10,chip_antibody_provider,0.6511627906976745,External_sample_id,False,False,False
+original geo accession,238,original cell line,0.65,Biospecimen Type,False,False,False
+clinical phenotype details,44,cell phenotype,0.65,Biospecimen Type,False,False,False
+total/partial resection,12,malaria infection,0.65,Biospecimen Disease Condition,False,False,False
+surgical indication,12,chemical modification,0.65,Treatment,False,False,False
+molecule purification,8,molecular condition,0.65,Biospecimen Disease Condition,False,False,False
+methylation-enrichment,6,methylation_geo_id,0.65,External_sample_id,False,False,False
+isolation column,4,isolation of tumor cells,0.65,Biospecimen Type,False,False,False
+symptoms onset date,374,days_symptom_onset,0.6486486486486487,Biospecimen Age,False,False,False
+technical replicate,295,chemical treatment,0.6486486486486487,Treatment,False,False,False
+length of exposure,42,length of infection,0.6486486486486487,Biospecimen Disease Condition,False,False,False
+chip processing date,20,tissue processing,0.6486486486486487,Biospecimen Type,False,False,False
+mean number of oocysts,6,number of cells,0.6486486486486487,Biospecimen Type,False,False,False
+parental/ne-like state,6,parental strain,0.6486486486486487,Biospecimen Organism,False,False,False
+malaria_transmission,500,malaria strain,0.6470588235294118,Biospecimen Organism,False,False,False
+library prep_plate,500,library protocol,0.6470588235294118,Treatment Dosage Regimen,False,False,False
+surgical.outcome,286,surgical treatment,0.6470588235294118,Treatment,False,False,False
+mutational.status,92,gestational stage,0.6470588235294118,Biospecimen Age,False,False,False
+replicate / experiment,75,replicate id,0.6470588235294118,External_sample_id,False,False,False
+stool frequency,62,treatment frequency,0.6470588235294118,Treatment,False,False,False
+viral challenge,60,days post challenge,0.6470588235294118,Biospecimen Age,False,False,False
+biological_replicate,52,biological sex,0.6470588235294118,Biospecimen Sex,False,False,False
+decrease of vision,49,day of isolation,0.6470588235294118,Biospecimen Age,False,False,False
+environment,36,environmental condition,0.6470588235294118,Biospecimen Disease Condition,False,False,False
+untreated/treated,34,culture/treatment,0.6470588235294118,Treatment,False,False,False
+virus accession number,32,usage number,0.6470588235294118,Biospecimen Age,False,False,False
+preparation method,30,cell preparation,0.6470588235294118,Biospecimen Type,False,False,False
+somatic mutation,21,psoriasis duration,0.6470588235294118,Treatment Dosage Regimen,False,False,False
+metabolic activity,10,disease activity,0.6470588235294118,Biospecimen Disease Condition,False,False,False
+antigen reactivity,10,disease activity,0.6470588235294118,Biospecimen Disease Condition,False,False,False
+pathologic status,1940,patient_status,0.6451612903225806,External_sample_id,False,False,False
+culture_result,500,culture/treatment,0.6451612903225806,Treatment,False,False,False
+isolation_method,455,isolation stage,0.6451612903225806,Biospecimen Age,False,False,False
+date collected,404,tissue collection,0.6451612903225806,Biospecimen Type,False,False,False
+sorting strategy,234,isolation stage,0.6451612903225806,Biospecimen Age,False,False,False
+anatomic_location,202,tumor location,0.6451612903225806,Biospecimen Disease Condition,False,False,False
+histological.type,66,biological sex,0.6451612903225806,Biospecimen Sex,False,False,False
+prodromal status,60,organoid status,0.6451612903225806,External_sample_id,False,False,False
+hereditary status,38,disease status,0.6451612903225806,Biospecimen Disease Condition,False,False,False
+perturbation type,37,infection type,0.6451612903225806,Biospecimen Disease Condition,False,False,False
+hemisphere_name,500,specimen_name,0.6428571428571429,Biospecimen Type,False,False,False
+recruiting site,379,specimen site,0.6428571428571429,Biospecimen Type,False,False,False
+nuclei_counts,345,monocytes_count,0.6428571428571429,Biospecimen Type,False,False,False
+extract_date,251,extract_protocol,0.6428571428571429,Treatment Dosage Regimen,False,False,False
+swollen joints,101,swollen eyelid,0.6428571428571429,External_sample_id,False,False,False
+challenge,79,days post challenge,0.6428571428571429,Biospecimen Age,False,False,False
+als mutation,53,cell stimulation,0.6428571428571429,Biospecimen Type,False,False,False
+brain metastasis,52,brain tissue,0.6428571428571429,Biospecimen Type,False,False,False
+percent_aligned,24,parent_strain,0.6428571428571429,Biospecimen Organism,False,False,False
+driver gene,10,derived cell line,0.6428571428571429,Biospecimen Type,False,False,False
+depletion,5,cell type depletion,0.6428571428571429,Biospecimen Type,False,False,False
+cluster_label,500,sample_label,0.64,External_sample_id,False,False,False
+procedure date,374,process day,0.64,Biospecimen Age,False,False,False
+neoplasia type,181,biopsy type,0.64,Biospecimen Type,False,False,False
+genetic class,126,tissue class,0.64,Biospecimen Type,False,False,False
+spike-in,108,spike-in organism,0.64,Biospecimen Organism,False,False,False
+pasi_total,105,diagnosis total,0.64,Biospecimen Disease Condition,False,False,False
+geo accession,101,age fraction,0.64,Biospecimen Age,False,False,False
+mutation class,57,tumor class,0.64,Biospecimen Disease Condition,False,False,False
+ago protein,49,age of patient,0.64,External_sample_id,False,False,False
+biological_replicate_number,24,sample replicate number,0.64,External_sample_id,False,False,False
+glioma model,20,disease model,0.64,Biospecimen Disease Condition,False,False,False
+menstrual phase,18,cell phase,0.64,Biospecimen Type,False,False,False
+glioma grade,15,disease grade,0.64,Biospecimen Disease Condition,False,False,False
+genotype of founder fish,6,genotype of original donor,0.64,External_sample_id,False,False,False
+outcome,1324,disease outcome,0.6363636363636364,Biospecimen Disease Condition,False,False,False
+project,500,cell projection,0.6363636363636364,Biospecimen Type,False,False,False
+pasi score,138,patient code,0.6363636363636364,External_sample_id,False,False,False
+symptom,125,disease symptom,0.6363636363636364,Biospecimen Disease Condition,False,False,False
+Outcome,104,disease outcome,0.6363636363636364,Biospecimen Disease Condition,False,False,False
+trial arm,87,survival year,0.6363636363636364,Biospecimen Age,False,False,False
+library-type,57,library id,0.6363636363636364,External_sample_id,False,False,False
+kit mutation,54,induration,0.6363636363636364,Treatment Dosage Regimen,False,False,False
+KIT mutation,32,induration,0.6363636363636364,Treatment Dosage Regimen,False,False,False
+creatinine,29,patient line,0.6363636363636364,External_sample_id,False,False,False
+skin score,26,skin disease,0.6363636363636364,Biospecimen Disease Condition,False,False,False
+date_death,24,age at death,0.6363636363636364,Biospecimen Age,False,False,False
+aligned reads,17,age years,0.6363636363636364,Biospecimen Age,False,False,False
+detachment,15,pretreatment,0.6363636363636364,Treatment,False,False,False
+reason for intubation,52,day after intubation,0.6341463414634146,Biospecimen Age,False,False,False
+sort purification strategy,19,infection state,0.6341463414634146,Biospecimen Disease Condition,False,False,False
+censored,1000,cell source,0.631578947368421,Biospecimen Type,False,False,False
+consortium lung phenotype,500,host genotype,0.631578947368421,Biospecimen Organism,False,False,False
+persistent ps aer status,500,disease status,0.631578947368421,Biospecimen Disease Condition,False,False,False
+season,238,disease onset,0.631578947368421,Biospecimen Disease Condition,False,False,False
+factor,177,tissue factor,0.631578947368421,Biospecimen Type,False,False,False
+ancestry,168,cancer site,0.631578947368421,Biospecimen Disease Condition,False,False,False
+met_amplification,119,chemical modification,0.631578947368421,Treatment,False,False,False
+variety,105,vaccine type,0.631578947368421,Treatment,False,False,False
+enrichment method,63,tissue archive method,0.631578947368421,Biospecimen Type,False,False,False
+sort gate,17,sorter day,0.631578947368421,Biospecimen Age,False,False,False
+lung section/portion,16,infection duration,0.631578947368421,Biospecimen Disease Condition,False,False,False
+technical replicates,12,chemical treatment,0.631578947368421,Treatment,False,False,False
+transient expression,8,treatment response,0.631578947368421,Treatment,False,False,False
+par-clip,2,participant,0.631578947368421,External_sample_id,False,False,False
+data_type,2,death_time,0.631578947368421,Biospecimen Age,False,False,False
+chip antibody cat,365,antibody treatment,0.6285714285714286,Treatment,False,False,False
+geographical location,277,tumor location,0.6285714285714286,Biospecimen Disease Condition,False,False,False
+isolate_sensitivity,140,disease activity,0.6285714285714286,Biospecimen Disease Condition,False,False,False
+histological..subtype,92,biological sex,0.6285714285714286,Biospecimen Sex,False,False,False
+primary/metastasis,56,primary diagnosis,0.6285714285714286,Biospecimen Disease Condition,False,False,False
+isolate sensitivity,33,disease severity,0.6285714285714286,Biospecimen Disease Condition,False,False,False
+chip-antibody cat,33,antibody treatment,0.6285714285714286,Treatment,False,False,False
+clip antibody,17,chip_antibody_provider,0.6285714285714286,External_sample_id,False,False,False
+alk mutation status,16,treatment status,0.6285714285714286,Treatment,False,False,False
+mutation details,8,duration of disease,0.6285714285714286,Biospecimen Disease Condition,False,False,False
+clip antibody cat,2,antibody treatment,0.6285714285714286,Treatment,False,False,False
+COMPLETION MASTECTOMY,2,collection day,0.6285714285714286,Biospecimen Age,False,False,False
+class,1132,tumor class,0.625,Biospecimen Disease Condition,False,False,False
+model,861,mouse model,0.625,Biospecimen Organism,False,False,False
+induced,500,incidence,0.625,External_sample_id,False,False,False
+material support,489,bacterial strain,0.625,Biospecimen Organism,False,False,False
+label,431,group label,0.625,Treatment,False,False,False
+smoking amount,374,sampling timepoint,0.625,Biospecimen Age,False,False,False
+anti-centromere,295,patient reference,0.625,External_sample_id,False,False,False
+datasets,284,patients,0.625,External_sample_id,False,False,False
+active ingredient,212,vaccine regimen,0.625,Treatment,False,False,False
+symptom severity,180,disease severity,0.625,Biospecimen Disease Condition,False,False,False
+primary recurrent,79,prior treatment,0.625,Treatment,False,False,False
+construct,38,control,0.625,Treatment,False,False,False
+total volume,33,initial tumor volume,0.625,Biospecimen Disease Condition,False,False,False
+promoter,30,provider,0.625,External_sample_id,False,False,False
+mitotic activity,29,disease activity,0.625,Biospecimen Disease Condition,False,False,False
+geographical origin,29,strain origin,0.625,Biospecimen Organism,False,False,False
+Construct,24,control,0.625,Treatment,False,False,False
+electrophysiology,21,cell morphology,0.625,Biospecimen Type,False,False,False
+sort-gate,18,storage,0.625,Biospecimen Age,False,False,False
+chip antibody manufacturer,11,chip_antibody_provider,0.625,External_sample_id,False,False,False
+vector construct,4,vector treatment,0.625,Treatment,False,False,False
+details,3,fetal sex,0.625,Biospecimen Sex,False,False,False
+progression_status,2,patient_status,0.625,External_sample_id,False,False,False
+mitotic rate,1,antibiotic treatment,0.625,Treatment,False,False,False
+survival characteristics,92,cell characterization,0.6222222222222222,Biospecimen Type,False,False,False
+sputum_culture,191,time in culture,0.6206896551724138,Biospecimen Age,False,False,False
+restriction enzyme,153,strain name,0.6206896551724138,Biospecimen Organism,False,False,False
+splice variant,150,sample material,0.6206896551724138,External_sample_id,False,False,False
+lesion_size,64,with_lesion_sample,0.6206896551724138,External_sample_id,False,False,False
+perturbation class,54,tumor class,0.6206896551724138,Biospecimen Disease Condition,False,False,False
+type of library,45,type of sample,0.6206896551724138,External_sample_id,False,False,False
+water salinity,36,bacteria strain,0.6206896551724138,Biospecimen Organism,False,False,False
+growth temperature,28,growth time,0.6206896551724138,Biospecimen Age,False,False,False
+oxygen level,22,oxygen percentage,0.6206896551724138,Biospecimen Age,False,False,False
+sorting criteria,9,starting cell,0.6206896551724138,Biospecimen Type,False,False,False
+parity,998,patient,0.6153846153846154,External_sample_id,False,False,False
+stress,744,storage,0.6153846153846154,Biospecimen Age,False,False,False
+match,500,batch id,0.6153846153846154,External_sample_id,False,False,False
+supplier,500,slide,0.6153846153846154,External_sample_id,False,False,False
+duplicate_pair,492,replicate id,0.6153846153846154,External_sample_id,False,False,False
+cerebral palsy,285,renal biopsy,0.6153846153846154,Biospecimen Type,False,False,False
+repeat,243,reagent,0.6153846153846154,Biospecimen Age,False,False,False
+primed,198,regimen,0.6153846153846154,Treatment Dosage Regimen,False,False,False
+rip antibody,182,antibody group,0.6153846153846154,Treatment,False,False,False
+antibody manufacturer,182,antibody treatment,0.6153846153846154,Treatment,False,False,False
+living,170,lineage,0.6153846153846154,Biospecimen Age,False,False,False
+other batch,118,other treatment,0.6153846153846154,Treatment,False,False,False
+geo series,101,sample subseries,0.6153846153846154,External_sample_id,False,False,False
+reporter,96,self_reported_race,0.6153846153846154,Biospecimen Race,False,False,False
+vascular.invasion,92,cardiovascular.disease,0.6153846153846154,Biospecimen Disease Condition,False,False,False
+instance,84,stage,0.6153846153846154,Biospecimen Age,False,False,False
+viral genus,78,viral infection,0.6153846153846154,Biospecimen Disease Condition,False,False,False
+cag repeat size,64,age patient,0.6153846153846154,External_sample_id,False,False,False
+ras score,60,race,0.6153846153846154,Biospecimen Race,False,False,False
+symptoms,56,days_symptom_onset,0.6153846153846154,Biospecimen Age,False,False,False
+sort strategy,54,art treatment,0.6153846153846154,Treatment,False,False,False
+syndrome,47,carcinoid syndrome,0.6153846153846154,External_sample_id,False,False,False
+BREAST,46,reagent,0.6153846153846154,Biospecimen Age,False,False,False
+autopsy,39,biopsy,0.6153846153846154,Biospecimen Type,False,False,False
+knock-in line,30,organoid line,0.6153846153846154,External_sample_id,False,False,False
+Scaling,26,strain,0.6153846153846154,Biospecimen Organism,False,False,False
+sorting,20,strain,0.6153846153846154,Biospecimen Organism,False,False,False
+Parity,20,patient,0.6153846153846154,External_sample_id,False,False,False
+fasting,16,strain,0.6153846153846154,Biospecimen Organism,False,False,False
+has_pressure,16,blood pressure,0.6153846153846154,Biospecimen Type,False,False,False
+autophagy induction,12,time after induction,0.6153846153846154,Biospecimen Age,False,False,False
+sorting probe,12,starting cell,0.6153846153846154,Biospecimen Type,False,False,False
+pluripotent,12,prior treatment,0.6153846153846154,Treatment,False,False,False
+melanoma,12,melanoma cell type,0.6153846153846154,Biospecimen Type,False,False,False
+major reason_for_surgery,12,year of surgery,0.6153846153846154,Biospecimen Age,False,False,False
+embryos pooled,11,embryo stage,0.6153846153846154,Biospecimen Age,False,False,False
+metastatic/primary,11,metastatic tumor site,0.6153846153846154,Biospecimen Disease Condition,False,False,False
+testosterone treated,6,time post treatment,0.6153846153846154,Biospecimen Age,False,False,False
+mother from,6,other treatment,0.6153846153846154,Treatment,False,False,False
+gating,4,patient,0.6153846153846154,External_sample_id,False,False,False
+immortalization method,3,immunization dose,0.6153846153846154,Treatment Dosage Regimen,False,False,False
+affinity purification,2,patient population,0.6153846153846154,External_sample_id,False,False,False
+international prognostic index,332,internal patient id,0.6122448979591837,External_sample_id,False,False,False
+Location of distant metastasis,34,duration of disease,0.6122448979591837,Biospecimen Disease Condition,False,False,False
+chip antibody manufacturers,7,chip_antibody_provider,0.6122448979591837,External_sample_id,False,False,False
+waist_circumference,500,patient reference,0.6111111111111112,External_sample_id,False,False,False
+mutational subclass,285,gestational stage,0.6111111111111112,Biospecimen Age,False,False,False
+integrative analysis,81,data analysis id,0.6111111111111112,External_sample_id,False,False,False
+osteogenic potential,16,osteogenesis day,0.6111111111111112,Biospecimen Age,False,False,False
+density gradient region,12,strain origin,0.6111111111111112,Biospecimen Organism,False,False,False
+temperature,1094,age fracture,0.6086956521739131,Biospecimen Age,False,False,False
+illness,574,illness_duration,0.6086956521739131,Treatment Dosage Regimen,False,False,False
+Illness,546,illness_duration,0.6086956521739131,Treatment Dosage Regimen,False,False,False
+block_name,270,block storage,0.6086956521739131,Biospecimen Age,False,False,False
+exon_ratio,251,concentration,0.6086956521739131,Treatment Dosage Regimen,False,False,False
+dysplasia now,226,passage no,0.6086956521739131,Biospecimen Age,False,False,False
+muscle mass,200,mouse status,0.6086956521739131,Biospecimen Organism,False,False,False
+comment,184,cell compartment,0.6086956521739131,Biospecimen Type,False,False,False
+family_history,55,family id,0.6086956521739131,External_sample_id,False,False,False
+match degree,54,batch group,0.6086956521739131,Treatment,False,False,False
+skin anatomy,36,strain name,0.6086956521739131,Biospecimen Organism,False,False,False
+specific primer,27,specimen,0.6086956521739131,Biospecimen Type,False,False,False
+extract,24,extract_protocol,0.6086956521739131,Treatment Dosage Regimen,False,False,False
+serology,13,cell morphology,0.6086956521739131,Biospecimen Type,False,False,False
+urine protein,11,time point,0.6086956521739131,Biospecimen Age,False,False,False
+fibrosis,3,first_diagnosis,0.6086956521739131,Biospecimen Disease Condition,False,False,False
+enrollment batch,1000,age of enrollment,0.6060606060606061,Biospecimen Age,False,False,False
+hip_circumference,500,sample_reference,0.6060606060606061,External_sample_id,False,False,False
+used for analysis,271,data analysis id,0.6060606060606061,External_sample_id,False,False,False
+library_prep_date,251,library protocol,0.6060606060606061,Treatment Dosage Regimen,False,False,False
+channel count,100,mechanical condition,0.6060606060606061,Biospecimen Disease Condition,False,False,False
+familial anamnesis,92,final diagnosis,0.6060606060606061,Biospecimen Disease Condition,False,False,False
+adapter sequence,79,day after seeding,0.6060606060606061,Biospecimen Age,False,False,False
+vector constructs,60,vector treatment,0.6060606060606061,Treatment,False,False,False
+number cag repeats,42,number of cells,0.6060606060606061,Biospecimen Type,False,False,False
+hospitalization,27,tumor localization,0.6060606060606061,Biospecimen Disease Condition,False,False,False
+primary/ recurrent,11,prior treatment,0.6060606060606061,Treatment,False,False,False
+library label_name,10,library barcode,0.6060606060606061,External_sample_id,False,False,False
+resistance profile,9,drug resistance,0.6060606060606061,Treatment,False,False,False
+library_strategy,5,laboratory strain,0.6060606060606061,Biospecimen Organism,False,False,False
+number of half-sclerotomes,6,number of_samples,0.6046511627906976,External_sample_id,False,False,False
+cohort,3031,host,0.6,Biospecimen Organism,False,False,False
+datatype,1603,diseasestate,0.6,Biospecimen Disease Condition,False,False,False
+roi,1459,steroid,0.6,External_sample_id,False,False,False
+date,1400,dosage,0.6,Biospecimen Age,False,False,False
+cluster,527,culture stage,0.6,Biospecimen Age,False,False,False
+probe_detection,500,cell projection,0.6,Biospecimen Type,False,False,False
+platelet_count,500,lymphocyte_count,0.6,Biospecimen Type,False,False,False
+array_design,500,array id,0.6,External_sample_id,False,False,False
+cap score,369,sample code,0.6,External_sample_id,False,False,False
+skin,338,strain,0.6,Biospecimen Organism,False,False,False
+smoke,317,mouse,0.6,Biospecimen Organism,False,False,False
+diabetes,283,diseasestate,0.6,Biospecimen Disease Condition,False,False,False
+training.test,271,strains,0.6,Biospecimen Organism,False,False,False
+escape,233,cage,0.6,Biospecimen Age,False,False,False
+outcome related,188,time to relapse,0.6,Biospecimen Age,False,False,False
+protein exchange,158,sporozoite age,0.6,Biospecimen Age,False,False,False
+target molecule,126,age of  culture,0.6,Biospecimen Age,False,False,False
+cag_repeats,124,age_weeks,0.6,Biospecimen Age,False,False,False
+lesion,103,slide_position,0.6,External_sample_id,False,False,False
+lesional (ls) vs. normal,69,tumor vs. normal,0.6,Biospecimen Disease Condition,False,False,False
+restriction enzymes,67,strain name,0.6,Biospecimen Organism,False,False,False
+coo,60,control,0.6,Treatment,False,False,False
+alive,60,slide,0.6,External_sample_id,False,False,False
+cag repeats,60,age years,0.6,Biospecimen Age,False,False,False
+local skin score,58,cell line code,0.6,Biospecimen Type,False,False,False
+genetic specifics,52,specific-host,0.6,Biospecimen Organism,False,False,False
+radiation sensitivity,45,lung radiation dose,0.6,Treatment Dosage Regimen,False,False,False
+Cluster,42,culture stage,0.6,Biospecimen Age,False,False,False
+locale,36,cage,0.6,Biospecimen Age,False,False,False
+method of preservation,34,sample preparation,0.6,External_sample_id,False,False,False
+lactate,29,placental sex,0.6,Biospecimen Sex,False,False,False
+construct expression,18,control/intervention,0.6,Treatment,False,False,False
+composite,17,biopsy site,0.6,Biospecimen Type,False,False,False
+measure,14,sample source,0.6,External_sample_id,False,False,False
+receptor expression,13,cancer predisposition,0.6,Biospecimen Disease Condition,False,False,False
+surgical approach,12,survival year,0.6,Biospecimen Age,False,False,False
+drinking,12,conditioning,0.6,Biospecimen Disease Condition,False,False,False
+digestion enzyme,8,infection time,0.6,Biospecimen Age,False,False,False
+"BREAST, LOCAL EXCISION",2,treatment location,0.6,Treatment,False,False,False
+reason for liver resection,18,duration of infection,0.5957446808510638,Biospecimen Disease Condition,False,False,False
+paired material support,177,paired patient,0.5945945945945946,External_sample_id,False,False,False
+mutation_carrier_status,124,patient_status,0.5945945945945946,External_sample_id,False,False,False
+replicate # in experiment,88,replicate id,0.5945945945945946,External_sample_id,False,False,False
+preservation method,75,prescription drugs,0.5945945945945946,Treatment,False,False,False
+psoriasis area-and-severity index,28,adjusted disease severity index,0.59375,Biospecimen Disease Condition,False,False,False
+nuclei count,393,monocytes_count,0.5925925925925926,Biospecimen Type,False,False,False
+binding density,370,cell density,0.5925925925925926,Biospecimen Type,False,False,False
+brain bank,156,strain background,0.5925925925925926,Biospecimen Organism,False,False,False
+expression,79,tissue processing,0.5925925925925926,Biospecimen Type,False,False,False
+copy number gain,54,cell number,0.5925925925925926,Biospecimen Type,False,False,False
+oxygen flow,40,oxygen condition,0.5925925925925926,Biospecimen Disease Condition,False,False,False
+profession,39,tissue processing,0.5925925925925926,Biospecimen Type,False,False,False
+note_other,30,monocyte_absolute,0.5925925925925926,Biospecimen Type,False,False,False
+ar or asthma,16,ann arbor stage,0.5925925925925926,Biospecimen Age,False,False,False
+gene_knockout,16,knockout group,0.5925925925925926,Treatment,False,False,False
+seizures/month,12,seizure group,0.5925925925925926,Treatment,False,False,False
+intensive care,10,active cancer,0.5925925925925926,Biospecimen Disease Condition,False,False,False
+phase of growth,8,age of onset,0.5925925925925926,Biospecimen Age,False,False,False
+delivery,804,fever day,0.5882352941176471,Biospecimen Age,False,False,False
+dementia,492,treatment,0.5882352941176471,Treatment,False,False,False
+outlier,414,mouse line,0.5882352941176471,Biospecimen Organism,False,False,False
+amplification cycles,324,infection code,0.5882352941176471,Biospecimen Disease Condition,False,False,False
+genetic testing,285,enzymatic treatment,0.5882352941176471,Treatment,False,False,False
+hist.score,228,storage,0.5882352941176471,Biospecimen Age,False,False,False
+further operations,172,age.at.operation,0.5882352941176471,Biospecimen Age,False,False,False
+sensor,110,host vendor,0.5882352941176471,Biospecimen Organism,False,False,False
+unsorted or sorted,86,tumor organ site,0.5882352941176471,Biospecimen Type,False,False,False
+alias,83,sample alias,0.5882352941176471,External_sample_id,False,False,False
+topography,56,therapy,0.5882352941176471,Treatment,False,False,False
+specific heart region,51,specific-host,0.5882352941176471,Biospecimen Organism,False,False,False
+littermate,46,lineage,0.5882352941176471,Biospecimen Age,False,False,False
+nicotine,40,condition,0.5882352941176471,Biospecimen Disease Condition,False,False,False
+medicine,36,incidence,0.5882352941176471,External_sample_id,False,False,False
+hospital admission,18,host mice strain,0.5882352941176471,Biospecimen Organism,False,False,False
+protein expression,18,patient response,0.5882352941176471,External_sample_id,False,False,False
+raw reads,17,draw day,0.5882352941176471,Biospecimen Age,False,False,False
+viral,17,viral strain,0.5882352941176471,Biospecimen Organism,False,False,False
+sorting profile,14,duration of illness,0.5882352941176471,Treatment Dosage Regimen,False,False,False
+interstitial pneumonia,12,institutional tumor diagnosis,0.5882352941176471,Biospecimen Disease Condition,False,False,False
+salt.score,11,storage,0.5882352941176471,Biospecimen Age,False,False,False
+rescue,10,area/tissue,0.5882352941176471,Biospecimen Type,False,False,False
+nitrogen,6,condition,0.5882352941176471,Biospecimen Disease Condition,False,False,False
+life form,2,slide no,0.5882352941176471,External_sample_id,False,False,False
+medical.history,212,clinical.diagnosis.history,0.5853658536585366,Biospecimen Disease Condition,False,False,False
+progression,448,drug response,0.5833333333333334,Treatment,False,False,False
+smear_result,313,time harvest,0.5833333333333334,Biospecimen Age,False,False,False
+feeding,215,day after seeding,0.5833333333333334,Biospecimen Age,False,False,False
+immune border,64,mouse model,0.5833333333333334,Biospecimen Organism,False,False,False
+comments,64,cell compartment,0.5833333333333334,Biospecimen Type,False,False,False
+sofa score,54,disease course,0.5833333333333334,Biospecimen Disease Condition,False,False,False
+arthritis,20,bacteria tissue,0.5833333333333334,Biospecimen Type,False,False,False
+oral ulcer,20,control source,0.5833333333333334,Treatment,False,False,False
+performance,16,per monocytes,0.5833333333333334,Biospecimen Type,False,False,False
+operator,12,age.at.operation,0.5833333333333334,Biospecimen Age,False,False,False
+immunology,4,lung pathology,0.5833333333333334,Biospecimen Disease Condition,False,False,False
+geographical region,1182,tumor region,0.5806451612903226,Biospecimen Disease Condition,False,False,False
+metastasis,840,metastatic tumor site,0.5806451612903226,Biospecimen Disease Condition,False,False,False
+assigned cluster,500,days in culture,0.5806451612903226,Biospecimen Age,False,False,False
+dyspnea / tachypnea,56,disease type,0.5806451612903226,Biospecimen Disease Condition,False,False,False
+primary_recurrence,30,primary cells,0.5806451612903226,Biospecimen Type,False,False,False
+kit expression,29,tissue processing,0.5806451612903226,Biospecimen Type,False,False,False
+morphologic form,24,cell morphology,0.5806451612903226,Biospecimen Type,False,False,False
+adipogenic potential,16,age patient,0.5806451612903226,External_sample_id,False,False,False
+malignancy class,15,malignant tumor,0.5806451612903226,Biospecimen Disease Condition,False,False,False
+overexpressing,8,tissue processing,0.5806451612903226,Biospecimen Type,False,False,False
+respirations per minute,58,replicate mouse,0.5789473684210527,Biospecimen Organism,False,False,False
+serologic response status,45,drug response,0.5789473684210527,Treatment,False,False,False
+tst,1588,host,0.5714285714285714,Biospecimen Organism,False,False,False
+dataset,1520,disease,0.5714285714285714,Biospecimen Disease Condition,False,False,False
+area,1053,age,0.5714285714285714,Biospecimen Age,False,False,False
+severity score,811,disease course,0.5714285714285714,Biospecimen Disease Condition,False,False,False
+field_site,669,sample_site,0.5714285714285714,External_sample_id,False,False,False
+atmosphere,661,sample prep,0.5714285714285714,External_sample_id,False,False,False
+sort,542,sorter day,0.5714285714285714,Biospecimen Age,False,False,False
+neoplastic,500,cancer.past,0.5714285714285714,Biospecimen Disease Condition,False,False,False
+allele actual,500,sample material,0.5714285714285714,External_sample_id,False,False,False
+filtered peaks,500,paired samples,0.5714285714285714,External_sample_id,False,False,False
+genome build,438,vendor id,0.5714285714285714,External_sample_id,False,False,False
+birth date,374,growth time,0.5714285714285714,Biospecimen Age,False,False,False
+joint problems,374,control,0.5714285714285714,Treatment,False,False,False
+smoking stop date,374,skin score at biopsy site,0.5714285714285714,Biospecimen Type,False,False,False
+history,363,storage,0.5714285714285714,Biospecimen Age,False,False,False
+who,349,host,0.5714285714285714,Biospecimen Organism,False,False,False
+os.mos,286,os month,0.5714285714285714,Biospecimen Age,False,False,False
+diffuse,231,disease,0.5714285714285714,Biospecimen Disease Condition,False,False,False
+run_date,202,run id,0.5714285714285714,External_sample_id,False,False,False
+reference genome_for_alignment,200,reference diagnosis,0.5714285714285714,Biospecimen Disease Condition,False,False,False
+ga,194,organ,0.5714285714285714,Biospecimen Type,False,False,False
+hypertension,165,person id,0.5714285714285714,External_sample_id,False,False,False
+eye,158,year,0.5714285714285714,Biospecimen Age,False,False,False
+cag_repeat,156,cage,0.5714285714285714,Biospecimen Age,False,False,False
+malign,148,malignant tumor,0.5714285714285714,Biospecimen Disease Condition,False,False,False
+chip target,141,cell stage,0.5714285714285714,Biospecimen Type,False,False,False
+admission,105,drug administration,0.5714285714285714,Treatment,False,False,False
+watch and wait,104,wash condition,0.5714285714285714,Biospecimen Disease Condition,False,False,False
+endoscopic_activity,97,disease activity,0.5714285714285714,Biospecimen Disease Condition,False,False,False
+fetus,70,fetal sex,0.5714285714285714,Biospecimen Sex,False,False,False
+scoliosis,70,oncologic diagnosis,0.5714285714285714,Biospecimen Disease Condition,False,False,False
+alcohol,69,control,0.5714285714285714,Treatment,False,False,False
+risk,65,risk group,0.5714285714285714,Treatment,False,False,False
+severity_score,64,covid severity_status,0.5714285714285714,External_sample_id,False,False,False
+cycling,58,lineage,0.5714285714285714,Biospecimen Age,False,False,False
+upper or lower extremity,55,before or after treatment,0.5714285714285714,Treatment,False,False,False
+cross-linked,52,controlid,0.5714285714285714,External_sample_id,False,False,False
+pregnancy,52,organ,0.5714285714285714,Biospecimen Type,False,False,False
+to concatenate,46,tumor location,0.5714285714285714,Biospecimen Disease Condition,False,False,False
+fusion,41,duration,0.5714285714285714,Treatment Dosage Regimen,False,False,False
+tau_score,39,tumor,0.5714285714285714,Biospecimen Disease Condition,False,False,False
+asbestos-fiber count,34,case or control,0.5714285714285714,Treatment,False,False,False
+sofa_admission,29,site of_disease_onset,0.5714285714285714,Biospecimen Disease Condition,False,False,False
+los,29,host,0.5714285714285714,Biospecimen Organism,False,False,False
+tobacco,28,barcode,0.5714285714285714,External_sample_id,False,False,False
+Overall erythema,26,organ system,0.5714285714285714,Biospecimen Type,False,False,False
+degree of infiltrate,26,age of  culture,0.5714285714285714,Biospecimen Age,False,False,False
+mortality,24,tumor status,0.5714285714285714,Biospecimen Disease Condition,False,False,False
+medical history,23,mechanical condition,0.5714285714285714,Biospecimen Disease Condition,False,False,False
+protein,17,patient,0.5714285714285714,External_sample_id,False,False,False
+cag repeat,13,cage,0.5714285714285714,Biospecimen Age,False,False,False
+isolated by,10,sorter day,0.5714285714285714,Biospecimen Age,False,False,False
+fus variant,8,study participant,0.5714285714285714,External_sample_id,False,False,False
+ast,7,days,0.5714285714285714,Biospecimen Age,False,False,False
+mice,6,mice group,0.5714285714285714,Treatment,False,False,False
+distant metastasis,6,disease diagnosis,0.5714285714285714,Biospecimen Disease Condition,False,False,False
+media supplement,6,sample name in supplementary file,0.5714285714285714,External_sample_id,False,False,False
+hairpin,6,paired patient,0.5714285714285714,External_sample_id,False,False,False
+Bra,6,race,0.5714285714285714,Biospecimen Race,False,False,False
+cytogenetics,5,osteogenesis day,0.5714285714285714,Biospecimen Age,False,False,False
+term accession number,5,passage number,0.5714285714285714,Biospecimen Age,False,False,False
+phase growth,4,age group,0.5714285714285714,Biospecimen Age,False,False,False
+AXILLARY NODE,2,library barcode,0.5714285714285714,External_sample_id,False,False,False
+months_survival,2,survival time,0.5714285714285714,Biospecimen Age,False,False,False
+medications/vitamin names,284,medication at blood sampling,0.5660377358490566,Biospecimen Type,False,False,False
+tuberculosis_history,55,clinical.diagnosis.history,0.5652173913043478,Biospecimen Disease Condition,False,False,False
+last follow-up,51,time of last follow up in months,0.5652173913043478,Biospecimen Age,False,False,False
+systemic sclerosis subtype,46,tumor subtype,0.5641025641025641,Biospecimen Disease Condition,False,False,False
+pipeline version,1000,cell line origin,0.5625,Biospecimen Type,False,False,False
+agricultural animals,804,culture time,0.5625,Biospecimen Age,False,False,False
+viral_positivity,500,disease activity,0.5625,Biospecimen Disease Condition,False,False,False
+infected/uninfected,186,infected host,0.5625,Biospecimen Organism,False,False,False
+total cholesterol,109,healthy control,0.5625,Treatment,False,False,False
+primary/recurrent,105,prior treatment,0.5625,Treatment,False,False,False
+primary_recurrent,68,prior treatment,0.5625,Treatment,False,False,False
+angiogenesis score,60,diagnosis oral,0.5625,Biospecimen Disease Condition,False,False,False
+respiratory score,21,replicate mouse,0.5625,Biospecimen Organism,False,False,False
+gel bead version,15,cell preparation,0.5625,Biospecimen Type,False,False,False
+cognitive impairment,8,organismpart,0.5625,Biospecimen Organism,False,False,False
+adjusted household density,804,adjusted disease severity index,0.5614035087719298,Biospecimen Disease Condition,False,False,False
+smear_results,500,time harvest,0.56,Biospecimen Age,False,False,False
+curative_intent,496,time_point,0.56,Biospecimen Age,False,False,False
+gene_count,399,monocytes_count,0.56,Biospecimen Type,False,False,False
+tst skin test,379,tissue notes,0.56,Biospecimen Type,False,False,False
+reads_all,251,repeated samples,0.56,External_sample_id,False,False,False
+circumstances,103,virus strain,0.56,Biospecimen Organism,False,False,False
+remission,101,stress condition,0.56,Biospecimen Disease Condition,False,False,False
+striatal_score,100,sample_code,0.56,External_sample_id,False,False,False
+histone mark,44,excision year,0.56,Biospecimen Age,False,False,False
+vasopressor,24,blood pressure,0.56,Biospecimen Type,False,False,False
+mode of growth,16,mouse group,0.56,Biospecimen Organism,False,False,False
+angiography,12,antibody group,0.56,Treatment,False,False,False
+exogenous gene expressed,24,exogenous treatment,0.5581395348837209,Treatment,False,False,False
+epithelial,618,chemical,0.5555555555555556,Treatment,False,False,False
+affy_batch,500,batch id,0.5555555555555556,External_sample_id,False,False,False
+smoking start date,374,final age at death,0.5555555555555556,Biospecimen Age,False,False,False
+total number of genomic aberrations,332,organoid generation,0.5555555555555556,External_sample_id,False,False,False
+psychiatric disorder,285,chronic diseases,0.5555555555555556,Biospecimen Disease Condition,False,False,False
+volume,282,volunteer id,0.5555555555555556,External_sample_id,False,False,False
+waist to hip ratio,200,patient population,0.5555555555555556,External_sample_id,False,False,False
+fat mass,200,of passage,0.5555555555555556,Biospecimen Age,False,False,False
+region of birth,191,duration of treatment,0.5555555555555556,Treatment,False,False,False
+vector,97,age_category,0.5555555555555556,Biospecimen Age,False,False,False
+multifocal,92,chemical,0.5555555555555556,Treatment,False,False,False
+smoker or non smoker,92,tumor organ site,0.5555555555555556,Biospecimen Type,False,False,False
+mosquito,48,tumor_site,0.5555555555555556,Biospecimen Disease Condition,False,False,False
+over-expression,46,cancer predisposition,0.5555555555555556,Biospecimen Disease Condition,False,False,False
+body part,25,cell part,0.5555555555555556,Biospecimen Type,False,False,False
+generation/colony,21,agent concentration,0.5555555555555556,Biospecimen Age,False,False,False
+precursor,15,person id,0.5555555555555556,External_sample_id,False,False,False
+well diameter in um,8,cell dissociation,0.5555555555555556,Biospecimen Type,False,False,False
+allele,8,sample plate,0.5555555555555556,External_sample_id,False,False,False
+tobacco use,6,barcode,0.5555555555555556,External_sample_id,False,False,False
+express,4,process day,0.5555555555555556,Biospecimen Age,False,False,False
+"BREAST, MASTECTOMY",2,treatment category,0.5555555555555556,Treatment,False,False,False
+domain,2,donor strain,0.5555555555555556,External_sample_id,False,False,False
+allele nominal,500,sample material,0.5517241379310345,External_sample_id,False,False,False
+birth defects,285,treatment effect,0.5517241379310345,Treatment,False,False,False
+structure acronym,270,culture days,0.5517241379310345,Biospecimen Age,False,False,False
+align_input,251,sampling_timepoint,0.5517241379310345,Biospecimen Age,False,False,False
+fibrosis degree,109,diagnosis date,0.5517241379310345,Biospecimen Disease Condition,False,False,False
+total skin score,64,strain source,0.5517241379310345,Biospecimen Organism,False,False,False
+platform,53,platform_id_id design,0.5517241379310345,External_sample_id,False,False,False
+derived from,46,derived cell line,0.5517241379310345,Biospecimen Type,False,False,False
+sum.risk.factors,28,tissue factor,0.5517241379310345,Biospecimen Type,False,False,False
+genital ulcer,20,animal id number,0.5517241379310345,External_sample_id,False,False,False
+stitched reads,17,time to relapse,0.5517241379310345,Biospecimen Age,False,False,False
+submission date,12,diagnosis date,0.5517241379310345,Biospecimen Disease Condition,False,False,False
+expression level,6,excision year,0.5517241379310345,Biospecimen Age,False,False,False
+behavior,6,behavior at diagnosis,0.5517241379310345,Biospecimen Disease Condition,False,False,False
+spike protein used,5,time points,0.5517241379310345,Biospecimen Age,False,False,False
+is_technical_replicate,492,chemical treatment,0.55,Treatment,False,False,False
+exercise intensity,80,experimental condition,0.55,Biospecimen Disease Condition,False,False,False
+Lymph node involvement,69,lymphocyte_percent,0.55,Biospecimen Type,False,False,False
+follicular lymphoma grade,27,tumor who grade,0.55,Biospecimen Disease Condition,False,False,False
+PARTIAL MASTECTOMY,2,parental tumor subtype,0.55,Biospecimen Disease Condition,False,False,False
+pasi,2192,passage,0.5454545454545454,Biospecimen Age,False,False,False
+labversion,1180,age fraction,0.5454545454545454,Biospecimen Age,False,False,False
+medium,949,serum,0.5454545454545454,Biospecimen Type,False,False,False
+tuberculin skin test,938,specimen site,0.5454545454545454,Biospecimen Type,False,False,False
+smoker,670,serum,0.5454545454545454,Biospecimen Type,False,False,False
+breed,443,ref id,0.5454545454545454,External_sample_id,False,False,False
+bait,425,patient,0.5454545454545454,External_sample_id,False,False,False
+chain,422,strain,0.5454545454545454,Biospecimen Organism,False,False,False
+link,362,lineage,0.5454545454545454,Biospecimen Age,False,False,False
+asthma,314,stage,0.5454545454545454,Biospecimen Age,False,False,False
+diet,284,disease,0.5454545454545454,Biospecimen Disease Condition,False,False,False
+surgical_interval_mo,245,survival_time,0.5454545454545454,Biospecimen Age,False,False,False
+pair,205,patient,0.5454545454545454,External_sample_id,False,False,False
+reference genome_for_processed_files,200,reference diagnosis,0.5454545454545454,Biospecimen Disease Condition,False,False,False
+cirrhosis present,195,diagnosis rectum,0.5454545454545454,Biospecimen Disease Condition,False,False,False
+sputum_smear,191,tumor_name,0.5454545454545454,Biospecimen Disease Condition,False,False,False
+obesity,137,host,0.5454545454545454,Biospecimen Organism,False,False,False
+sofa,126,storage,0.5454545454545454,Biospecimen Age,False,False,False
+fragments in clean bam,112,age in year,0.5454545454545454,Biospecimen Age,False,False,False
+scar,104,scan id,0.5454545454545454,External_sample_id,False,False,False
+hemisphere,99,chemotherapy,0.5454545454545454,Treatment,False,False,False
+litter,99,slide,0.5454545454545454,External_sample_id,False,False,False
+mitotic index,94,cosmic id,0.5454545454545454,External_sample_id,False,False,False
+prophylaxis,81,macrophages,0.5454545454545454,Biospecimen Type,False,False,False
+immune_or_nasal,76,internal sample id,0.5454545454545454,External_sample_id,False,False,False
+facial dysmorphism,70,final diagnosis,0.5454545454545454,Biospecimen Disease Condition,False,False,False
+genetic variants,66,pediatric patient,0.5454545454545454,External_sample_id,False,False,False
+volar or non-volar,55,case or control,0.5454545454545454,Treatment,False,False,False
+modality,44,day,0.5454545454545454,Biospecimen Age,False,False,False
+temp,43,therapy,0.5454545454545454,Treatment,False,False,False
+labor,38,lab id,0.5454545454545454,External_sample_id,False,False,False
+test,30,tissues,0.5454545454545454,Biospecimen Type,False,False,False
+neural tube defect,30,single or double infection,0.5454545454545454,Biospecimen Disease Condition,False,False,False
+line name in manuscript,30,time since transplant,0.5454545454545454,Biospecimen Age,False,False,False
+calcium level,20,camp treatment/level,0.5454545454545454,Treatment,False,False,False
+expression construct,18,extraction_concentration,0.5454545454545454,Treatment Dosage Regimen,False,False,False
+oxygen,16,organ,0.5454545454545454,Biospecimen Type,False,False,False
+functional connectivity,13,additional conditions,0.5454545454545454,Biospecimen Disease Condition,False,False,False
+paradigm,13,parasite stage,0.5454545454545454,Biospecimen Age,False,False,False
+cross,6,groups,0.5454545454545454,Treatment,False,False,False
+oocyst prevalence,6,monocyte_percent,0.5454545454545454,Biospecimen Type,False,False,False
+death with metastasis,189,treatment status,0.5405405405405406,Treatment,False,False,False
+ectopic expression,25,cell type depletion,0.5405405405405406,Biospecimen Type,False,False,False
+ocular involvement,20,molecular diagnosis,0.5405405405405406,Biospecimen Disease Condition,False,False,False
+molecule,1522,molecular subgroup,0.5384615384615384,Treatment,False,False,False
+assayed molecule,489,passage no,0.5384615384615384,Biospecimen Age,False,False,False
+recurrence,286,sample_reference,0.5384615384615384,External_sample_id,False,False,False
+align_unique,251,duration_units,0.5384615384615384,Treatment Dosage Regimen,False,False,False
+exposed stress,118,relapse time,0.5384615384615384,Biospecimen Age,False,False,False
+cattle breed,85,sample beneath,0.5384615384615384,External_sample_id,False,False,False
+hemolysis score,40,host tissue,0.5384615384615384,Biospecimen Organism,False,False,False
+molecular subtype/phenotypic state,20,molecular subgroup,0.5384615384615384,Treatment,False,False,False
+febrile seizure,18,cell source,0.5384615384615384,Biospecimen Type,False,False,False
+aortic valve,16,patient sample,0.5384615384615384,External_sample_id,False,False,False
+cytogenetic,16,infection agent,0.5384615384615384,Biospecimen Age,False,False,False
+knockdown target,12,gold stage,0.5384615384615384,Biospecimen Age,False,False,False
+cutting enzymes,10,strain name,0.5384615384615384,Biospecimen Organism,False,False,False
+small molecule,1,cell culture,0.5384615384615384,Biospecimen Type,False,False,False
+gastrointestinal disorder,285,gestational days,0.5365853658536586,Biospecimen Age,False,False,False
+geo expression data,77,age of psoriasis onset,0.5365853658536586,Biospecimen Age,False,False,False
+birth_place,813,race,0.5333333333333333,Biospecimen Race,False,False,False
+method,810,death day,0.5333333333333333,Biospecimen Age,False,False,False
+companion animals,804,donation time,0.5333333333333333,Biospecimen Age,False,False,False
+stimulus,736,tissues,0.5333333333333333,Biospecimen Type,False,False,False
+media,417,sample day,0.5333333333333333,External_sample_id,False,False,False
+technique,381,tissue,0.5333333333333333,Biospecimen Type,False,False,False
+negative normalization factor,363,activation agent,0.5333333333333333,Biospecimen Age,False,False,False
+job/role,300,control,0.5333333333333333,Treatment,False,False,False
+input,174,induration,0.5333333333333333,Treatment Dosage Regimen,False,False,False
+smoking,171,os month,0.5333333333333333,Biospecimen Age,False,False,False
+adapter,147,age tier,0.5333333333333333,Biospecimen Age,False,False,False
+roi lot,95,os month,0.5333333333333333,Biospecimen Age,False,False,False
+bleeding,62,lineage,0.5333333333333333,Biospecimen Age,False,False,False
+debris removal,56,diagnosis rectal,0.5333333333333333,Biospecimen Disease Condition,False,False,False
+vehicle,51,chemical,0.5333333333333333,Treatment,False,False,False
+gel_bead_version,40,age and_strain,0.5333333333333333,Biospecimen Organism,False,False,False
+At Risk,20,"age, yrs",0.5333333333333333,Biospecimen Age,False,False,False
+product,12,provider,0.5333333333333333,External_sample_id,False,False,False
+zone,6,tissue zone,0.5333333333333333,Biospecimen Type,False,False,False
+exposed pollutants,6,mouse status,0.5333333333333333,Biospecimen Organism,False,False,False
+solvent,2,os month,0.5333333333333333,Biospecimen Age,False,False,False
+classifier_mes,152,classification group,0.5294117647058824,Treatment,False,False,False
+vascular support,16,molecular subgroup,0.5294117647058824,Treatment,False,False,False
+secondary antibody,8,stress condition,0.5294117647058824,Biospecimen Disease Condition,False,False,False
+neural crest-derived,7,nasal_steroids,0.5294117647058824,External_sample_id,False,False,False
+cerebral performance category score,50,treatment category,0.5283018867924528,Treatment,False,False,False
+tst result,179,stem cell,0.5263157894736842,Biospecimen Type,False,False,False
+lane.ordinal,151,lane id,0.5263157894736842,External_sample_id,False,False,False
+bal_smear,140,sample_set,0.5263157894736842,External_sample_id,False,False,False
+major_organ_involvement,45,source_organism,0.5263157894736842,Biospecimen Organism,False,False,False
+Dead/Alive,34,death day,0.5263157894736842,Biospecimen Age,False,False,False
+encode accession,7,days since vaccination,0.5263157894736842,Biospecimen Age,False,False,False
+bone-marrow grafting status,74,organoid status,0.5238095238095238,External_sample_id,False,False,False
+other biologic medicines use,62,biological sex,0.5238095238095238,Biospecimen Sex,False,False,False
+vascular involvement,20,cardiovascular.disease,0.5238095238095238,Biospecimen Disease Condition,False,False,False
+irradiated,667,sex predicted,0.5217391304347826,Biospecimen Sex,False,False,False
+knockdown,147,knockout group,0.5217391304347826,Treatment,False,False,False
+corrector,60,collection day,0.5217391304347826,Biospecimen Age,False,False,False
+insertion site distance to gene,12,infection agent,0.5217391304347826,Biospecimen Age,False,False,False
+portion of branchial arch,8,duration of treatment,0.5217391304347826,Treatment,False,False,False
+ARN_quality,6,renal biopsy,0.5217391304347826,Biospecimen Type,False,False,False
+follow up years,332,age in years,0.5185185185185185,Biospecimen Age,False,False,False
+cortical_score,100,active cancer,0.5185185185185185,Biospecimen Disease Condition,False,False,False
+nulliparous,38,in-line barcodes,0.5185185185185185,External_sample_id,False,False,False
+tubular shadows,6,tumor status,0.5185185185185185,Biospecimen Disease Condition,False,False,False
+stable knockdown,6,sample pool,0.5185185185185185,External_sample_id,False,False,False
+dead or alive at the end of follow-up,332,age at time of collection,0.5161290322580645,Biospecimen Age,False,False,False
+cigarette smoker,212,replicate mouse,0.5161290322580645,Biospecimen Organism,False,False,False
+LabeledExtract,183,tissue extraction,0.5161290322580645,Biospecimen Type,False,False,False
+rounds_to_cure,64,background strain,0.5161290322580645,Biospecimen Organism,False,False,False
+severity binary,45,disease severity,0.5161290322580645,Biospecimen Disease Condition,False,False,False
+pipeline.version,39,viral infection,0.5161290322580645,Biospecimen Disease Condition,False,False,False
+erythema nodule,20,peripheral blood,0.5161290322580645,Biospecimen Type,False,False,False
+diffuse vs limited,3,disease stage,0.5161290322580645,Biospecimen Age,False,False,False
+buffer_volume_unit,158,age of enrollment,0.5142857142857142,Biospecimen Age,False,False,False
+skin-fold freckling,70,strain recipient,0.5142857142857142,Biospecimen Organism,False,False,False
+markers used for sorting,42,mouse stain,0.5142857142857142,Biospecimen Organism,False,False,False
+hind-limb paralysis,14,in-line barcodes,0.5142857142857142,External_sample_id,False,False,False
+recurrent/primary,11,current medication,0.5142857142857142,Treatment,False,False,False
+chip magnetic beads,4,chronic diseases,0.5142857142857142,Biospecimen Disease Condition,False,False,False
+subcutaneous neurofibromas,70,subject diagnosis,0.5116279069767442,External_sample_id,False,False,False
+presence_of_parasites_lesion,64,parasite strain,0.5116279069767442,Biospecimen Organism,False,False,False
+gastrointestinal involvement,20,harvesting time,0.5116279069767442,Biospecimen Age,False,False,False
+parasite density on admission,46,strain description,0.5106382978723404,Biospecimen Organism,False,False,False
+growth factors in the culture medium,9,days in culture,0.5098039215686274,Biospecimen Age,False,False,False
+data presented in the manuscript,9,time point in the model of dormancy,0.5074626865671642,Biospecimen Age,False,False,False
+albumin,923,sample timing,0.5,External_sample_id,False,False,False
+hematocrit,883,treatmentshort,0.5,Treatment,False,False,False
+hemoglobin,865,other organ lesion,0.5,Biospecimen Type,False,False,False
+smear microscopy,500,renal biopsy,0.5,Biospecimen Type,False,False,False
+mean corpuscular volume,306,human tumor cell line,0.5,Biospecimen Organism,False,False,False
+percent_weight_loss,268,percentage of tumor cells,0.5,Biospecimen Type,False,False,False
+efficacy,164,chemical,0.5,Treatment,False,False,False
+aerosol.run,151,age group,0.5,Biospecimen Age,False,False,False
+fibrinogen,126,labeling agent,0.5,Biospecimen Age,False,False,False
+enzyme,120,gender,0.5,Biospecimen Sex,False,False,False
+marrow,116,main group,0.5,Treatment,False,False,False
+microglia media,93,chemical modification,0.5,Treatment,False,False,False
+panel,79,age,0.5,Biospecimen Age,False,False,False
+any_immune,76,animal age,0.5,Biospecimen Age,False,False,False
+plexiform neurofibromas,70,donor fibroblasts,0.5,External_sample_id,False,False,False
+cutaneous neurofibromas,70,donor fibroblasts,0.5,External_sample_id,False,False,False
+lobe,64,flowcell,0.5,Biospecimen Type,False,False,False
+granuloma,53,brain tumor,0.5,Biospecimen Disease Condition,False,False,False
+diplopia,49,days_in_hospital,0.5,Biospecimen Age,False,False,False
+freezer,39,fever day,0.5,Biospecimen Age,False,False,False
+Cycle,37,vaccine,0.5,Treatment,False,False,False
+diffuse/limited,32,specimen site,0.5,Biospecimen Type,False,False,False
+schedule,30,celltype,0.5,Biospecimen Type,False,False,False
+genetic engineering,19,oxygen percentage,0.5,Biospecimen Age,False,False,False
+level,17,lineage,0.5,Biospecimen Age,False,False,False
+weekly dosing,15,cell origin,0.5,Biospecimen Type,False,False,False
+rip,15,group,0.5,Treatment,False,False,False
+ubi,14,subjectid,0.5,External_sample_id,False,False,False
+MASTECTOMY,12,day post infection,0.5,Biospecimen Age,False,False,False
+bilirubin,7,biological drug,0.5,Treatment,False,False,False
+alt,7,agent,0.5,Biospecimen Age,False,False,False
+overexpressed target,6,relapse time,0.5,Biospecimen Age,False,False,False
+invasive behavior,5,disease feature,0.5,Biospecimen Disease Condition,False,False,False
+allergy,3,age range,0.5,Biospecimen Age,False,False,False
+OVARY,2,day,0.5,Biospecimen Age,False,False,False
+progression_free_survival_censor,88,lesion_disease_factor,0.49056603773584906,Biospecimen Disease Condition,False,False,False
+genetic variants inheritance,33,time point post infection,0.49056603773584906,Biospecimen Age,False,False,False
+positive Down screening risk,1,conditioning received,0.4897959183673469,Biospecimen Disease Condition,False,False,False
+myopathic motor_unit_potentials,8,pathology_note,0.4888888888888889,Biospecimen Disease Condition,False,False,False
+nuclear_reads,251,ventilator-free days,0.48484848484848486,Biospecimen Age,False,False,False
+buffer_volume,158,initial tumor volume,0.48484848484848486,Biospecimen Disease Condition,False,False,False
+body weight,6,antibody treatment,0.4827586206896552,Treatment,False,False,False
+unpublished,284,publication id,0.48,External_sample_id,False,False,False
+progression_free_survival,88,timepoint_progressors,0.4782608695652174,Biospecimen Age,False,False,False
+exitus,55,replicate mouse,0.47619047619047616,Biospecimen Organism,False,False,False
+fed with,20,age in months,0.47619047619047616,Biospecimen Age,False,False,False
+bone-marrow grafting type,74,donation time,0.47368421052631576,Biospecimen Age,False,False,False
+transcription factor expression level,10,prescription drugs,0.4727272727272727,Treatment,False,False,False
+consortium lung phenotype surrogate variable,500,mouse genotype/variation,0.47058823529411764,Biospecimen Organism,False,False,False
+SENTINEL AXILLARY LYMPH NODE,2,alternative sample name,0.47058823529411764,External_sample_id,False,False,False
+total bilirubin,46,tumor cell line,0.4666666666666667,Biospecimen Type,False,False,False
+weight,567,reagent,0.46153846153846156,Biospecimen Age,False,False,False
+with or without clonal heterogeneity,332,infected with/healthy control,0.46153846153846156,Treatment,False,False,False
+expanded allele cag repeat count,178,cell line background,0.46153846153846156,Biospecimen Type,False,False,False
+glioma,70,lineage,0.46153846153846156,Biospecimen Age,False,False,False
+cough,56,grouping,0.46153846153846156,Treatment,False,False,False
+pulldown,35,donor,0.46153846153846156,External_sample_id,False,False,False
+Weight,13,reagent,0.46153846153846156,Biospecimen Age,False,False,False
+div,12,individual,0.46153846153846156,External_sample_id,False,False,False
+knock-in,4,knockout group,0.45454545454545453,Treatment,False,False,False
+rift valley fever virus,12,time after virus injection,0.4489795918367347,Biospecimen Age,False,False,False
+bin,855,biopsy,0.4444444444444444,Biospecimen Type,False,False,False
+mean.corpuscular.volume,46,cardiovascular.disease,0.4444444444444444,Biospecimen Disease Condition,False,False,False
+severe_eosinophilia,45,disease_extension,0.4444444444444444,Biospecimen Disease Condition,False,False,False
+pull-down,5,donor,0.42857142857142855,External_sample_id,False,False,False
+buffer,186,year,0.4,Biospecimen Age,False,False,False
+mib,78,id,0.4,External_sample_id,False,False,False
+kit,48,patient,0.4,External_sample_id,False,False,False
diff --git a/RDAS_RDOMICS/scripts/sample_characteristics_harmonization/similarity_cutoff_evaluation/cutoff_assignment_counts.csv b/RDAS_RDOMICS/scripts/sample_characteristics_harmonization/similarity_cutoff_evaluation/cutoff_assignment_counts.csv
new file mode 100644
index 0000000..c448731
--- /dev/null
+++ b/RDAS_RDOMICS/scripts/sample_characteristics_harmonization/similarity_cutoff_evaluation/cutoff_assignment_counts.csv
@@ -0,0 +1,4 @@
+cutoff,labels_assigned,label_assignment_rate_among_remaining,occurrences_assigned,occurrence_assignment_rate_among_remaining
+0.70,534,0.3875181422351234,198809,0.5522272806815309
+0.75,333,0.2416545718432511,146907,0.40806026449044897
+0.80,163,0.11828737300435414,42280,0.11744020354820521
diff --git a/RDAS_RDOMICS/scripts/sample_characteristics_harmonization/similarity_cutoff_evaluation/cutoff_manual_accuracy.csv b/RDAS_RDOMICS/scripts/sample_characteristics_harmonization/similarity_cutoff_evaluation/cutoff_manual_accuracy.csv
new file mode 100644
index 0000000..cfcd5a5
--- /dev/null
+++ b/RDAS_RDOMICS/scripts/sample_characteristics_harmonization/similarity_cutoff_evaluation/cutoff_manual_accuracy.csv
@@ -0,0 +1,4 @@
+cutoff,reviewed_labels,reviewed_correct,manual_accuracy
+0.70,150,67,0.44666666666666666
+0.75,100,45,0.45
+0.80,50,24,0.48
diff --git a/RDAS_RDOMICS/scripts/sample_characteristics_harmonization/similarity_cutoff_evaluation/cutoff_summary_table.csv b/RDAS_RDOMICS/scripts/sample_characteristics_harmonization/similarity_cutoff_evaluation/cutoff_summary_table.csv
new file mode 100644
index 0000000..e55131c
--- /dev/null
+++ b/RDAS_RDOMICS/scripts/sample_characteristics_harmonization/similarity_cutoff_evaluation/cutoff_summary_table.csv
@@ -0,0 +1,4 @@
+Similarity_Cutoff,Labels_Assigned,Label_Coverage_Among_Remaining_Labels,Occurrences_Assigned,Occurrence_Coverage_Among_Remaining_Occurrences,Reviewed_Labels,Reviewed_Correct,Manual_Accuracy,Selected_For_Final_Pipeline
+0.70,534,38.8%,198809,55.2%,150,67,44.7%,No
+0.75,333,24.2%,146907,40.8%,100,45,45.0%,Yes
+0.80,163,11.8%,42280,11.7%,50,24,48.0%,No
diff --git a/RDAS_RDOMICS/scripts/sample_characteristics_harmonization/similarity_cutoff_evaluation/cutoff_summary_table.md b/RDAS_RDOMICS/scripts/sample_characteristics_harmonization/similarity_cutoff_evaluation/cutoff_summary_table.md
new file mode 100644
index 0000000..50357ba
--- /dev/null
+++ b/RDAS_RDOMICS/scripts/sample_characteristics_harmonization/similarity_cutoff_evaluation/cutoff_summary_table.md
@@ -0,0 +1,11 @@
+Similarity cutoff evaluation summary
+
+Candidate assignments were evaluated for labels remaining after rule-based matching (n = 1,378 labels). Manual accuracy was calculated as the proportion of reviewed assignments judged correct within the reviewed subset.
+
+| Similarity cutoff | Labels assigned | Label coverage among remaining labels | Occurrences assigned | Occurrence coverage among remaining occurrences | Reviewed labels | Reviewed correct | Manual accuracy |
+|---:|---:|---:|---:|---:|---:|---:|---:|
+| 0.70 | 534 | 38.8% | 198,809 | 55.2% | 150 | 67 | 44.7% |
+| 0.75 | 333 | 24.2% | 146,907 | 40.8% | 100 | 45 | 45.0% |
+| 0.80 | 163 | 11.8% | 42,280 | 11.7% | 50 | 24 | 48.0% |
+
+The 0.75 cutoff was selected for the final pipeline because it provided substantially greater label coverage than 0.80 while maintaining similar manual accuracy.
diff --git a/RDAS_RDOMICS/scripts/sample_characteristics_harmonization/similarity_cutoff_evaluation/evaluate_similarity_cutoffs.py b/RDAS_RDOMICS/scripts/sample_characteristics_harmonization/similarity_cutoff_evaluation/evaluate_similarity_cutoffs.py
new file mode 100644
index 0000000..b5856c9
--- /dev/null
+++ b/RDAS_RDOMICS/scripts/sample_characteristics_harmonization/similarity_cutoff_evaluation/evaluate_similarity_cutoffs.py
@@ -0,0 +1,574 @@
+#!/usr/bin/env python3
+"""
+Evaluate similarity-assignment cutoffs for sample-characteristic labels.
+
+This script reproduces the deterministic rule-based stage and the
+similarity-based stage from 4_llm_clustering_enhanced.py, then evaluates
+candidate similarity cutoffs such as 0.70, 0.75, and 0.80.
+
+Outputs:
+  - best_similarity_matches.csv:
+      Best reference match for every label remaining after rule matching.
+  - assignments_cutoff_<cutoff>.csv:
+      Labels assigned at each similarity cutoff.
+  - cutoff_assignment_counts.csv:
+      Number of labels and occurrences assigned at each cutoff.
+  - manual_review_template.csv:
+      A sampled review sheet with a blank manual_correct column.
+  - cutoff_manual_accuracy.csv:
+      Written only when a completed review file is provided.
+
+Manual review workflow:
+  1. Run this script to generate outputs.
+  2. Fill manual_review_template.csv column manual_correct with 1/0,
+     yes/no, true/false, correct/incorrect, or y/n.
+  3. Rerun this script with --review-file path/to/completed_review.csv.
+"""
+
+from __future__ import annotations
+
+import argparse
+import math
+import re
+from collections import defaultdict
+from difflib import SequenceMatcher
+from pathlib import Path
+from typing import Iterable
+
+import pandas as pd
+
+
+DEFAULT_CUTOFFS = [0.70, 0.75, 0.80]
+
+
+# Copied from 4_llm_clustering_enhanced.py so this evaluation can run without
+# importing the vLLM-dependent clustering script.
+KEYWORD_MAPPINGS = {
+    "External_sample_id": {
+        "exact_matches": [
+            "patient_id",
+            "sample_id",
+            "donor_id",
+            "subject_id",
+            "patient id",
+            "sample id",
+            "donor id",
+            "subject id",
+        ],
+        "keywords": [
+            "patient",
+            "id",
+            "sample",
+            "donor",
+            "subject",
+            "barcode",
+            "participant",
+            "individual",
+            "controlid",
+            "patientid",
+            "subjectid",
+            "sampleid",
+        ],
+        "patterns": [r".*id$", r".*_id$", r"patient.*", r"subject.*", r"donor.*"],
+    },
+    "Biospecimen Organism": {
+        "exact_matches": ["species", "organism", "strain"],
+        "keywords": [
+            "mouse",
+            "human",
+            "homo sapiens",
+            "mus musculus",
+            "host",
+            "background strain",
+            "mouse strain",
+        ],
+        "patterns": [r".*strain.*", r".*organism.*"],
+    },
+    "Biospecimen Type": {
+        "exact_matches": [
+            "tissue",
+            "cell",
+            "blood",
+            "serum",
+            "organ",
+            "cell type",
+            "celltype",
+            "tissue type",
+        ],
+        "keywords": [
+            "lymphocyte",
+            "monocyte",
+            "macrophage",
+            "stem cell",
+            "biopsy",
+            "specimen",
+            "sample type",
+            "fluid",
+            "brain tissue",
+            "liver tissue",
+        ],
+        "patterns": [r".*tissue.*", r".*cell.*", r".*blood.*"],
+    },
+    "Biospecimen Age": {
+        "exact_matches": ["age", "day", "week", "month", "year", "time"],
+        "keywords": [
+            "developmental stage",
+            "passage",
+            "age in",
+            "donor age",
+            "patient age",
+            "time point",
+            "timepoint",
+        ],
+        "patterns": [r".*age.*", r".*day.*", r".*time.*", r".*stage.*"],
+    },
+    "Biospecimen Sex": {
+        "exact_matches": ["sex", "gender", "male", "female"],
+        "keywords": ["donor sex", "patient gender", "cell sex", "animal sex"],
+        "patterns": [r".*sex.*", r".*gender.*"],
+    },
+    "Biospecimen Race": {
+        "exact_matches": ["race", "ethnicity"],
+        "keywords": [
+            "caucasian",
+            "asian",
+            "hispanic",
+            "ethnicity",
+            "donor race",
+            "donor ethnicity",
+        ],
+        "patterns": [r".*race.*", r".*ethnicity.*", r".*ethnic.*"],
+    },
+    "Biospecimen Disease Condition": {
+        "exact_matches": ["disease", "condition", "diagnosis", "cancer", "tumor", "infection"],
+        "keywords": [
+            "disease state",
+            "disease status",
+            "clinical diagnosis",
+            "pathology",
+            "tumor type",
+            "cancer status",
+            "clinical condition",
+        ],
+        "patterns": [
+            r".*disease.*",
+            r".*tumor.*",
+            r".*cancer.*",
+            r".*diagnosis.*",
+            r".*condition.*",
+        ],
+    },
+    "Treatment": {
+        "exact_matches": [
+            "treatment",
+            "drug",
+            "therapy",
+            "medication",
+            "group",
+            "control",
+            "placebo",
+        ],
+        "keywords": [
+            "drug treatment",
+            "therapy",
+            "intervention",
+            "compound",
+            "chemical",
+            "vaccine",
+            "antibody treatment",
+            "chemotherapy",
+        ],
+        "patterns": [r".*treatment.*", r".*drug.*", r".*therapy.*", r".*group.*"],
+    },
+    "Treatment Dosage Regimen": {
+        "exact_matches": ["dose", "dosage", "concentration", "duration"],
+        "keywords": [
+            "treatment dose",
+            "drug dose",
+            "treatment duration",
+            "protocol",
+            "regimen",
+            "drug concentration",
+        ],
+        "patterns": [r".*dose.*", r".*dosage.*", r".*concentration.*", r".*duration.*"],
+    },
+}
+
+
+def parse_cutoffs(raw_cutoffs: Iterable[str]) -> list[float]:
+    cutoffs = [float(value) for value in raw_cutoffs]
+    invalid = [value for value in cutoffs if value <= 0 or value > 1]
+    if invalid:
+        raise ValueError(f"Cutoffs must be in (0, 1], got: {invalid}")
+    return sorted(cutoffs)
+
+
+def cutoff_label(cutoff: float) -> str:
+    return f"{cutoff:.2f}".replace(".", "_")
+
+
+def load_labels(labels_file: Path) -> list[tuple[str, int]]:
+    df = pd.read_csv(labels_file)
+    required_columns = {"name", "count"}
+    missing_columns = required_columns - set(df.columns)
+    if missing_columns:
+        raise ValueError(f"{labels_file} is missing columns: {sorted(missing_columns)}")
+
+    return [(str(row["name"]), int(row["count"])) for _, row in df.iterrows()]
+
+
+def keyword_based_categorization(
+    labels_with_counts: list[tuple[str, int]],
+) -> tuple[dict[str, list[dict]], list[tuple[str, int]]]:
+    """Reproduce the rule-based categorization from the clustering script."""
+    keyword_categorizations = defaultdict(list)
+    remaining_labels = []
+
+    for label, count in labels_with_counts:
+        label_lower = label.lower().strip()
+        best_category = None
+        confidence = "LOW"
+        matched_term = None
+        match_type = None
+
+        for category, mapping in KEYWORD_MAPPINGS.items():
+            for exact_match in mapping["exact_matches"]:
+                exact_lower = exact_match.lower()
+                if exact_lower == label_lower or exact_lower in label_lower.split():
+                    best_category = category
+                    confidence = "HIGH"
+                    matched_term = exact_match
+                    match_type = "exact_match"
+                    break
+
+            if best_category:
+                break
+
+            for keyword in mapping["keywords"]:
+                if keyword.lower() in label_lower:
+                    best_category = category
+                    confidence = "MEDIUM"
+                    matched_term = keyword
+                    match_type = "keyword"
+                    break
+
+            if best_category:
+                break
+
+            for pattern in mapping["patterns"]:
+                if re.search(pattern, label_lower):
+                    if confidence != "MEDIUM":
+                        best_category = category
+                        confidence = "MEDIUM" if "id" in pattern or "age" in pattern else "LOW"
+                        matched_term = pattern
+                        match_type = "pattern"
+                    break
+
+        if best_category:
+            keyword_categorizations[best_category].append(
+                {
+                    "label": label,
+                    "count": count,
+                    "matched_term": matched_term,
+                    "match_type": match_type,
+                    "confidence": confidence,
+                }
+            )
+        else:
+            remaining_labels.append((label, count))
+
+    return dict(keyword_categorizations), remaining_labels
+
+
+def calculate_similarity(text1: str, text2: str) -> float:
+    return SequenceMatcher(None, text1.lower(), text2.lower()).ratio()
+
+
+def build_reference_terms(keyword_results: dict[str, list[dict]]) -> dict[str, list[str]]:
+    reference_terms = {}
+    for category, results in keyword_results.items():
+        reference_terms[category] = [result["label"].lower() for result in results]
+    return reference_terms
+
+
+def find_best_similarity_matches(
+    remaining_labels: list[tuple[str, int]],
+    reference_terms: dict[str, list[str]],
+) -> pd.DataFrame:
+    rows = []
+
+    for label, count in remaining_labels:
+        best_reference = None
+        best_category = None
+        best_score = 0.0
+
+        for category, category_labels in reference_terms.items():
+            for reference_label in category_labels:
+                score = calculate_similarity(label, reference_label)
+                if score > best_score:
+                    best_reference = reference_label
+                    best_category = category
+                    best_score = score
+
+        rows.append(
+            {
+                "label": label,
+                "count": count,
+                "best_reference_label": best_reference,
+                "best_similarity_score": best_score,
+                "assigned_category": best_category,
+            }
+        )
+
+    return pd.DataFrame(rows)
+
+
+def summarize_cutoffs(best_matches: pd.DataFrame, cutoffs: list[float]) -> pd.DataFrame:
+    total_remaining = len(best_matches)
+    total_remaining_occurrences = int(best_matches["count"].sum()) if total_remaining else 0
+    rows = []
+
+    for cutoff in cutoffs:
+        assigned = best_matches[best_matches["best_similarity_score"] >= cutoff]
+        rows.append(
+            {
+                "cutoff": f"{cutoff:.2f}",
+                "labels_assigned": len(assigned),
+                "label_assignment_rate_among_remaining": (
+                    len(assigned) / total_remaining if total_remaining else math.nan
+                ),
+                "occurrences_assigned": int(assigned["count"].sum()) if len(assigned) else 0,
+                "occurrence_assignment_rate_among_remaining": (
+                    assigned["count"].sum() / total_remaining_occurrences
+                    if total_remaining_occurrences
+                    else math.nan
+                ),
+            }
+        )
+
+    return pd.DataFrame(rows)
+
+
+def add_cutoff_membership_columns(best_matches: pd.DataFrame, cutoffs: list[float]) -> pd.DataFrame:
+    output = best_matches.copy()
+    for cutoff in cutoffs:
+        output[f"assigned_at_{cutoff_label(cutoff)}"] = (
+            output["best_similarity_score"] >= cutoff
+        )
+    return output
+
+
+def score_band(score: float, cutoffs: list[float]) -> str:
+    min_cutoff = min(cutoffs)
+    middle_cutoffs = sorted(cutoffs)
+
+    if score < min_cutoff:
+        return f"<{min_cutoff:.2f}"
+
+    for left, right in zip(middle_cutoffs, middle_cutoffs[1:]):
+        if left <= score < right:
+            return f"{left:.2f}_to_lt_{right:.2f}"
+
+    return f">={max(cutoffs):.2f}"
+
+
+def create_review_template(
+    best_matches: pd.DataFrame,
+    cutoffs: list[float],
+    sample_per_band: int,
+    random_seed: int,
+) -> pd.DataFrame:
+    eligible = best_matches[best_matches["best_similarity_score"] >= min(cutoffs)].copy()
+    if eligible.empty:
+        return eligible
+
+    eligible["score_band"] = eligible["best_similarity_score"].apply(
+        lambda value: score_band(float(value), cutoffs)
+    )
+    eligible["eligible_cutoffs"] = eligible["best_similarity_score"].apply(
+        lambda value: ";".join(f"{cutoff:.2f}" for cutoff in cutoffs if value >= cutoff)
+    )
+
+    sampled_groups = []
+    for _, group in eligible.groupby("score_band", sort=True):
+        sample_n = min(sample_per_band, len(group))
+        sampled_groups.append(
+            group.sample(n=sample_n, random_state=random_seed).sort_values(
+                ["best_similarity_score", "count"], ascending=[False, False]
+            )
+        )
+
+    review_df = pd.concat(sampled_groups, ignore_index=True)
+    review_df = review_df.sort_values(
+        ["score_band", "best_similarity_score", "count"],
+        ascending=[True, False, False],
+    )
+    review_df.insert(0, "review_id", range(1, len(review_df) + 1))
+    review_df["manual_correct"] = ""
+    review_df["manual_notes"] = ""
+
+    return review_df[
+        [
+            "review_id",
+            "score_band",
+            "eligible_cutoffs",
+            "label",
+            "count",
+            "best_reference_label",
+            "best_similarity_score",
+            "assigned_category",
+            "manual_correct",
+            "manual_notes",
+        ]
+    ]
+
+
+def parse_manual_correct(value) -> bool | None:
+    if pd.isna(value):
+        return None
+
+    normalized = str(value).strip().lower()
+    if normalized in {"1", "true", "t", "yes", "y", "correct", "c"}:
+        return True
+    if normalized in {"0", "false", "f", "no", "n", "incorrect", "wrong", "w"}:
+        return False
+    if normalized == "":
+        return None
+
+    raise ValueError(
+        "manual_correct must be one of 1/0, yes/no, true/false, "
+        f"correct/incorrect, or blank. Got: {value!r}"
+    )
+
+
+def summarize_manual_accuracy(review_file: Path, cutoffs: list[float]) -> pd.DataFrame:
+    review_df = pd.read_csv(review_file)
+    required_columns = {"best_similarity_score", "manual_correct"}
+    missing_columns = required_columns - set(review_df.columns)
+    if missing_columns:
+        raise ValueError(f"{review_file} is missing columns: {sorted(missing_columns)}")
+
+    review_df["manual_correct_bool"] = review_df["manual_correct"].apply(parse_manual_correct)
+    reviewed = review_df[review_df["manual_correct_bool"].notna()].copy()
+
+    rows = []
+    for cutoff in cutoffs:
+        reviewed_at_cutoff = reviewed[reviewed["best_similarity_score"] >= cutoff]
+        reviewed_n = len(reviewed_at_cutoff)
+        correct_n = int(reviewed_at_cutoff["manual_correct_bool"].sum()) if reviewed_n else 0
+        rows.append(
+            {
+                "cutoff": f"{cutoff:.2f}",
+                "reviewed_labels": reviewed_n,
+                "reviewed_correct": correct_n,
+                "manual_accuracy": correct_n / reviewed_n if reviewed_n else math.nan,
+            }
+        )
+
+    return pd.DataFrame(rows)
+
+
+def write_cutoff_assignment_files(
+    best_matches: pd.DataFrame,
+    cutoffs: list[float],
+    output_dir: Path,
+) -> None:
+    for cutoff in cutoffs:
+        assigned = best_matches[best_matches["best_similarity_score"] >= cutoff].copy()
+        assigned = assigned.sort_values(
+            ["count", "best_similarity_score"], ascending=[False, False]
+        )
+        assigned.to_csv(output_dir / f"assignments_cutoff_{cutoff_label(cutoff)}.csv", index=False)
+
+
+def main() -> None:
+    parser = argparse.ArgumentParser(
+        description="Evaluate candidate cutoffs for similarity-based label assignment."
+    )
+    script_dir = Path(__file__).resolve().parent
+    parser.add_argument(
+        "--labels-file",
+        type=Path,
+        default=script_dir / "3_sample_characteristics_key_count_english_only.csv",
+        help="CSV with columns name,count.",
+    )
+    parser.add_argument(
+        "--output-dir",
+        type=Path,
+        default=script_dir / "similarity_cutoff_evaluation",
+        help="Directory for evaluation outputs.",
+    )
+    parser.add_argument(
+        "--cutoffs",
+        nargs="+",
+        default=[str(value) for value in DEFAULT_CUTOFFS],
+        help="Similarity cutoffs to evaluate, e.g. 0.70 0.75 0.80.",
+    )
+    parser.add_argument(
+        "--review-file",
+        type=Path,
+        default=None,
+        help="Completed manual review CSV with manual_correct filled in.",
+    )
+    parser.add_argument(
+        "--sample-per-band",
+        type=int,
+        default=50,
+        help="Number of labels to sample per score band for manual review.",
+    )
+    parser.add_argument(
+        "--random-seed",
+        type=int,
+        default=13,
+        help="Random seed for reproducible manual-review sampling.",
+    )
+    args = parser.parse_args()
+
+    if args.sample_per_band < 1:
+        raise ValueError("--sample-per-band must be positive")
+
+    cutoffs = parse_cutoffs(args.cutoffs)
+    args.output_dir.mkdir(parents=True, exist_ok=True)
+
+    labels_with_counts = load_labels(args.labels_file)
+    keyword_results, remaining_after_keywords = keyword_based_categorization(labels_with_counts)
+    reference_terms = build_reference_terms(keyword_results)
+    best_matches = find_best_similarity_matches(remaining_after_keywords, reference_terms)
+    best_matches = add_cutoff_membership_columns(best_matches, cutoffs)
+    best_matches = best_matches.sort_values(
+        ["best_similarity_score", "count"], ascending=[False, False]
+    )
+
+    best_matches.to_csv(args.output_dir / "best_similarity_matches.csv", index=False)
+    write_cutoff_assignment_files(best_matches, cutoffs, args.output_dir)
+
+    cutoff_summary = summarize_cutoffs(best_matches, cutoffs)
+    cutoff_summary.to_csv(args.output_dir / "cutoff_assignment_counts.csv", index=False)
+
+    review_template = create_review_template(
+        best_matches=best_matches,
+        cutoffs=cutoffs,
+        sample_per_band=args.sample_per_band,
+        random_seed=args.random_seed,
+    )
+    review_template.to_csv(args.output_dir / "manual_review_template.csv", index=False)
+
+    print("Similarity cutoff evaluation complete.")
+    print(f"Labels loaded: {len(labels_with_counts)}")
+    print(f"Labels assigned by rule-based step: {sum(len(v) for v in keyword_results.values())}")
+    print(f"Labels remaining for similarity evaluation: {len(remaining_after_keywords)}")
+    print("\nAssignment counts by cutoff:")
+    print(cutoff_summary.to_string(index=False))
+    print(f"\nOutputs written to: {args.output_dir}")
+    print("Fill manual_review_template.csv column manual_correct, then rerun with --review-file.")
+
+    if args.review_file:
+        manual_summary = summarize_manual_accuracy(args.review_file, cutoffs)
+        manual_summary.to_csv(args.output_dir / "cutoff_manual_accuracy.csv", index=False)
+        print("\nManual accuracy from reviewed subset:")
+        print(manual_summary.to_string(index=False))
+        print(f"Manual accuracy written to: {args.output_dir / 'cutoff_manual_accuracy.csv'}")
+
+
+if __name__ == "__main__":
+    main()
diff --git a/RDAS_RDOMICS/scripts/sample_characteristics_harmonization/similarity_cutoff_evaluation/manual_review_template.csv b/RDAS_RDOMICS/scripts/sample_characteristics_harmonization/similarity_cutoff_evaluation/manual_review_template.csv
new file mode 100644
index 0000000..deee9e6
--- /dev/null
+++ b/RDAS_RDOMICS/scripts/sample_characteristics_harmonization/similarity_cutoff_evaluation/manual_review_template.csv
@@ -0,0 +1,151 @@
+review_id,score_band,eligible_cutoffs,label,count,best_reference_label,best_similarity_score,assigned_category,manual_correct,manual_notes
+1,0.70_to_lt_0.75,0.70,microglia population,8,cell population,0.7428571428571429,Biospecimen Type,,
+2,0.70_to_lt_0.75,0.70,transplanted with,2,transplanted organ,0.7428571428571429,Biospecimen Type,,
+3,0.70_to_lt_0.75,0.70,library name,476,library barcode,0.7407407407407407,External_sample_id,,
+4,0.70_to_lt_0.75,0.70,symptomatic,178,symptom duration,0.7407407407407407,Treatment Dosage Regimen,,
+5,0.70_to_lt_0.75,0.70,antibody used,11,antibody group,0.7407407407407407,Treatment,,
+6,0.70_to_lt_0.75,0.70,visit_date,313,visit day,0.7368421052631579,Biospecimen Age,,
+7,0.70_to_lt_0.75,0.70,route administered,52,vaccine administered,0.7368421052631579,Treatment,,
+8,0.70_to_lt_0.75,0.70,model type,12,cell type,0.7368421052631579,Biospecimen Type,,
+9,0.70_to_lt_0.75,0.70,knockout,203,knockout group,0.7272727272727273,Treatment,,
+10,0.70_to_lt_0.75,0.70,pain,101,patient,0.7272727272727273,External_sample_id,,
+11,0.70_to_lt_0.75,0.70,surgery type,76,serum type,0.7272727272727273,Biospecimen Type,,
+12,0.70_to_lt_0.75,0.70,infiltration,64,induration,0.7272727272727273,Treatment Dosage Regimen,,
+13,0.70_to_lt_0.75,0.70,genotype abbreviation,14,mouse line abbreviation,0.7272727272727273,Biospecimen Organism,,
+14,0.70_to_lt_0.75,0.70,scale,12,sample,0.7272727272727273,External_sample_id,,
+15,0.70_to_lt_0.75,0.70,Extraction_amount,6,extraction_protocol,0.7222222222222222,Treatment Dosage Regimen,,
+16,0.70_to_lt_0.75,0.70,culture result,894,culture age,0.72,Biospecimen Age,,
+17,0.70_to_lt_0.75,0.70,recipient,534,recipient strain,0.72,Biospecimen Organism,,
+18,0.70_to_lt_0.75,0.70,parasitemia,419,parasite stage,0.72,Biospecimen Age,,
+19,0.70_to_lt_0.75,0.70,library quality,208,library id,0.72,External_sample_id,,
+20,0.70_to_lt_0.75,0.70,infectivity,120,infection type,0.72,Biospecimen Disease Condition,,
+21,0.70_to_lt_0.75,0.70,graft source,47,gender source,0.72,Biospecimen Sex,,
+22,0.70_to_lt_0.75,0.70,paired with,37,paired patient,0.72,External_sample_id,,
+23,0.70_to_lt_0.75,0.70,sort fraction,27,age fraction,0.72,Biospecimen Age,,
+24,0.70_to_lt_0.75,0.70,oxygen status,4,mouse status,0.72,Biospecimen Organism,,
+25,0.70_to_lt_0.75,0.70,clinical presentation,61,clinical condition,0.717948717948718,Biospecimen Disease Condition,,
+26,0.70_to_lt_0.75,0.70,visit,3653,visit day,0.7142857142857143,Biospecimen Age,,
+27,0.70_to_lt_0.75,0.70,malaria_status,500,malaria strain,0.7142857142857143,Biospecimen Organism,,
+28,0.70_to_lt_0.75,0.70,library plate,412,library barcode,0.7142857142857143,External_sample_id,,
+29,0.70_to_lt_0.75,0.70,survival status,152,survival time,0.7142857142857143,Biospecimen Age,,
+30,0.70_to_lt_0.75,0.70,library_batch,64,library barcode,0.7142857142857143,External_sample_id,,
+31,0.70_to_lt_0.75,0.70,culture platform,57,culture time,0.7142857142857143,Biospecimen Age,,
+32,0.70_to_lt_0.75,0.70,commercial source,56,cell source,0.7142857142857143,Biospecimen Type,,
+33,0.70_to_lt_0.75,0.70,molecule source,23,sample source,0.7142857142857143,External_sample_id,,
+34,0.70_to_lt_0.75,0.70,antibody target description,21,age description,0.7142857142857143,Biospecimen Age,,
+35,0.70_to_lt_0.75,0.70,genotype_abbreviation,500,mouse genotype/variation,0.7111111111111111,Biospecimen Organism,,
+36,0.70_to_lt_0.75,0.70,surface area,363,cell surface marker,0.7096774193548387,Biospecimen Type,,
+37,0.70_to_lt_0.75,0.70,pregnancy status,201,organoid status,0.7096774193548387,External_sample_id,,
+38,0.70_to_lt_0.75,0.70,anatomic location,201,tumor location,0.7096774193548387,Biospecimen Disease Condition,,
+39,0.70_to_lt_0.75,0.70,isolation method,52,isolation stage,0.7096774193548387,Biospecimen Age,,
+40,0.70_to_lt_0.75,0.70,lymphs,460,lymphocytes,0.7058823529411765,Biospecimen Type,,
+41,0.70_to_lt_0.75,0.70,modifications,57,chemical modification,0.7058823529411765,Treatment,,
+42,0.70_to_lt_0.75,0.70,digestives_symptoms,45,disease symptom,0.7058823529411765,Biospecimen Disease Condition,,
+43,0.70_to_lt_0.75,0.70,implantation,24,cell type implantation,0.7058823529411765,Biospecimen Type,,
+44,0.70_to_lt_0.75,0.70,Labeling_reference,6,sample_reference,0.7058823529411765,External_sample_id,,
+45,0.70_to_lt_0.75,0.70,reactivity,3,acidity,0.7058823529411765,External_sample_id,,
+46,0.70_to_lt_0.75,0.70,incubation temperature,8,incubation time,0.7027027027027027,Biospecimen Age,,
+47,0.70_to_lt_0.75,0.70,virus type,86,serum type,0.7,Biospecimen Type,,
+48,0.70_to_lt_0.75,0.70,subclass,80,tissue class,0.7,Biospecimen Type,,
+49,0.70_to_lt_0.75,0.70,lymph node,51,lymphocyte,0.7,Biospecimen Type,,
+50,0.70_to_lt_0.75,0.70,who class,40,tumor class,0.7,Biospecimen Disease Condition,,
+51,0.75_to_lt_0.80,0.70;0.75,anatomic site,10,tissue anatomic site,0.7878787878787878,Biospecimen Type,,
+52,0.75_to_lt_0.80,0.70;0.75,viral inactivation,10,viral infection,0.7878787878787878,Biospecimen Disease Condition,,
+53,0.75_to_lt_0.80,0.70;0.75,development,310,development stage,0.7857142857142857,Biospecimen Age,,
+54,0.75_to_lt_0.80,0.70;0.75,parasite line,95,parasite strain,0.7857142857142857,Biospecimen Organism,,
+55,0.75_to_lt_0.80,0.70;0.75,differentiation replicate,9,differentiation time point,0.7843137254901961,Biospecimen Age,,
+56,0.75_to_lt_0.80,0.70;0.75,histology,3618,histopathology,0.782608695652174,Biospecimen Disease Condition,,
+57,0.75_to_lt_0.80,0.70;0.75,Phenotype,141,cell phenotype,0.782608695652174,Biospecimen Type,,
+58,0.75_to_lt_0.80,0.70;0.75,line type,123,cell line type,0.782608695652174,Biospecimen Type,,
+59,0.75_to_lt_0.80,0.70;0.75,growth media,106,growth time,0.782608695652174,Biospecimen Age,,
+60,0.75_to_lt_0.80,0.70;0.75,hippocampal sclerosis,6,hippocampal slice id,0.7804878048780488,External_sample_id,,
+61,0.75_to_lt_0.80,0.70;0.75,sorted compartment,500,tissue compartment,0.7777777777777778,Biospecimen Type,,
+62,0.75_to_lt_0.80,0.70;0.75,infectious challenge,82,infectious agent,0.7777777777777778,Biospecimen Age,,
+63,0.75_to_lt_0.80,0.70;0.75,experiment type,295,experimental day,0.7741935483870968,Biospecimen Age,,
+64,0.75_to_lt_0.80,0.70;0.75,study number,50,study sample number,0.7741935483870968,External_sample_id,,
+65,0.75_to_lt_0.80,0.70;0.75,dementia status,16,treatment status,0.7741935483870968,Treatment,,
+66,0.75_to_lt_0.80,0.70;0.75,antibody name,9,antibody treatment,0.7741935483870968,Treatment,,
+67,0.75_to_lt_0.80,0.70;0.75,experiment,1725,experimental day,0.7692307692307693,Biospecimen Age,,
+68,0.75_to_lt_0.80,0.70;0.75,simulation,80,cell stimulation,0.7692307692307693,Biospecimen Type,,
+69,0.75_to_lt_0.80,0.70;0.75,series,27,species,0.7692307692307693,Biospecimen Organism,,
+70,0.75_to_lt_0.80,0.70;0.75,replicate type,22,replicate id,0.7692307692307693,External_sample_id,,
+71,0.75_to_lt_0.80,0.70;0.75,type of insertion,12,site of infection,0.7647058823529411,Biospecimen Disease Condition,,
+72,0.75_to_lt_0.80,0.70;0.75,number of animals,10,number of_samples,0.7647058823529411,External_sample_id,,
+73,0.75_to_lt_0.80,0.70;0.75,associated geo,4,associate geo_sample,0.7647058823529411,External_sample_id,,
+74,0.75_to_lt_0.80,0.70;0.75,response,667,drug response,0.7619047619047619,Treatment,,
+75,0.75_to_lt_0.80,0.70;0.75,os_status,656,mouse status,0.7619047619047619,Biospecimen Organism,,
+76,0.75_to_lt_0.80,0.70;0.75,infected,101,time infected,0.7619047619047619,Biospecimen Age,,
+77,0.75_to_lt_0.80,0.70;0.75,Genotype,52,host genotype,0.7619047619047619,Biospecimen Organism,,
+78,0.75_to_lt_0.80,0.70;0.75,specific,39,specific-host,0.7619047619047619,Biospecimen Organism,,
+79,0.75_to_lt_0.80,0.70;0.75,virus added,30,virus dose,0.7619047619047619,Treatment Dosage Regimen,,
+80,0.75_to_lt_0.80,0.70;0.75,clone type,24,cancer type,0.7619047619047619,Biospecimen Disease Condition,,
+81,0.75_to_lt_0.80,0.70;0.75,lesion status,57,infection status,0.7586206896551724,Biospecimen Disease Condition,,
+82,0.75_to_lt_0.80,0.70;0.75,nitrogen source,8,control source,0.7586206896551724,Treatment,,
+83,0.75_to_lt_0.80,0.70;0.75,initial preparation,10,tissue preparation,0.7567567567567568,Biospecimen Type,,
+84,0.75_to_lt_0.80,0.70;0.75,tag,1317,stage,0.75,Biospecimen Age,,
+85,0.75_to_lt_0.80,0.70;0.75,selection,567,mouse selection,0.75,Biospecimen Organism,,
+86,0.75_to_lt_0.80,0.70;0.75,growth phase,558,growth stage,0.75,Biospecimen Age,,
+87,0.75_to_lt_0.80,0.70;0.75,mutation,354,duration,0.75,Treatment Dosage Regimen,,
+88,0.75_to_lt_0.80,0.70;0.75,brain location,197,treatment location,0.75,Treatment,,
+89,0.75_to_lt_0.80,0.70;0.75,pathogens,138,pathogen strain,0.75,Biospecimen Organism,,
+90,0.75_to_lt_0.80,0.70;0.75,isolate type,97,disease type,0.75,Biospecimen Disease Condition,,
+91,0.75_to_lt_0.80,0.70;0.75,responder,84,responder cells,0.75,Biospecimen Type,,
+92,0.75_to_lt_0.80,0.70;0.75,specificity,42,specific-host,0.75,Biospecimen Organism,,
+93,0.75_to_lt_0.80,0.70;0.75,translocations,18,treatment location,0.75,Treatment,,
+94,0.75_to_lt_0.80,0.70;0.75,length of culture,15,age of  culture,0.75,Biospecimen Age,,
+95,0.75_to_lt_0.80,0.70;0.75,clone name,12,cell line name,0.75,Biospecimen Type,,
+96,0.75_to_lt_0.80,0.70;0.75,derived culture,9,derived cell_type,0.75,Biospecimen Type,,
+97,0.75_to_lt_0.80,0.70;0.75,process order,9,process day,0.75,Biospecimen Age,,
+98,0.75_to_lt_0.80,0.70;0.75,Growth Medium,6,growth time,0.75,Biospecimen Age,,
+99,0.75_to_lt_0.80,0.70;0.75,sorted,5,sorter day,0.75,Biospecimen Age,,
+100,0.75_to_lt_0.80,0.70;0.75,reference cat,3,reference condition,0.75,Biospecimen Disease Condition,,
+101,>=0.80,0.70;0.75;0.80,infection_state,20,infection state,0.9333333333333333,Biospecimen Disease Condition,,
+102,>=0.80,0.70;0.75;0.80,antibody vendor,12,antibody vendor id,0.9090909090909091,External_sample_id,,
+103,>=0.80,0.70;0.75;0.80,hours_post_infection,48,hours post infection,0.9,Biospecimen Disease Condition,,
+104,>=0.80,0.70;0.75;0.80,animal number,32,animal id number,0.896551724137931,External_sample_id,,
+105,>=0.80,0.70;0.75;0.80,injection,42,infection,0.8888888888888888,Biospecimen Disease Condition,,
+106,>=0.80,0.70;0.75;0.80,differentiation status,43,differentiation stage,0.8837209302325582,Biospecimen Age,,
+107,>=0.80,0.70;0.75;0.80,os_month,156,os month,0.875,Biospecimen Age,,
+108,>=0.80,0.70;0.75;0.80,phase description,15,age description,0.875,Biospecimen Age,,
+109,>=0.80,0.70;0.75;0.80,overall.survival,40,overall.survival.time,0.8648648648648649,Biospecimen Age,,
+110,>=0.80,0.70;0.75;0.80,induction date,385,induction time,0.8571428571428571,Biospecimen Age,,
+111,>=0.80,0.70;0.75;0.80,OS status,297,mouse status,0.8571428571428571,Biospecimen Organism,,
+112,>=0.80,0.70;0.75;0.80,volunteer,171,volunteer id,0.8571428571428571,External_sample_id,,
+113,>=0.80,0.70;0.75;0.80,cag,140,cage,0.8571428571428571,Biospecimen Age,,
+114,>=0.80,0.70;0.75;0.80,polarization state,15,polarization treatment,0.85,Treatment,,
+115,>=0.80,0.70;0.75;0.80,vaccination boost,92,vaccination dose,0.8484848484848485,Treatment Dosage Regimen,,
+116,>=0.80,0.70;0.75;0.80,description,294,age description,0.8461538461538461,Biospecimen Age,,
+117,>=0.80,0.70;0.75;0.80,sampling site,57,sampling time,0.8461538461538461,Biospecimen Age,,
+118,>=0.80,0.70;0.75;0.80,maternal state,10,maternal age,0.8461538461538461,Biospecimen Age,,
+119,>=0.80,0.70;0.75;0.80,parental line,55,parental cell line,0.8387096774193549,Biospecimen Type,,
+120,>=0.80,0.70;0.75;0.80,state of culture,42,age of  culture,0.8387096774193549,Biospecimen Age,,
+121,>=0.80,0.70;0.75;0.80,long description,12,age description,0.8387096774193549,Biospecimen Age,,
+122,>=0.80,0.70;0.75;0.80,subpopulation,9,cell subpopulation,0.8387096774193549,Biospecimen Type,,
+123,>=0.80,0.70;0.75;0.80,survival_yr,876,survival year,0.8333333333333334,Biospecimen Age,,
+124,>=0.80,0.70;0.75;0.80,study,741,studyid,0.8333333333333334,External_sample_id,,
+125,>=0.80,0.70;0.75;0.80,genomic modification,38,chemical modification,0.8292682926829268,Treatment,,
+126,>=0.80,0.70;0.75;0.80,genotype/varation,14,mouse genotype/variation,0.8292682926829268,Biospecimen Organism,,
+127,>=0.80,0.70;0.75;0.80,transduction,629,cell transduction,0.8275862068965517,Biospecimen Type,,
+128,>=0.80,0.70;0.75;0.80,viral infected,33,viral infection,0.8275862068965517,Biospecimen Disease Condition,,
+129,>=0.80,0.70;0.75;0.80,classification,369,classification group,0.8235294117647058,Treatment,,
+130,>=0.80,0.70;0.75;0.80,experimental batch,38,experimental day,0.8235294117647058,Biospecimen Age,,
+131,>=0.80,0.70;0.75;0.80,alternative name,14,alternative sample name,0.8205128205128205,External_sample_id,,
+132,>=0.80,0.70;0.75;0.80,replicate number,6,sample replicate number,0.8205128205128205,External_sample_id,,
+133,>=0.80,0.70;0.75;0.80,case number,726,cell number,0.8181818181818182,Biospecimen Type,,
+134,>=0.80,0.70;0.75;0.80,library date,385,library id,0.8181818181818182,External_sample_id,,
+135,>=0.80,0.70;0.75;0.80,stimulation,2378,cell stimulation,0.8148148148148148,Biospecimen Type,,
+136,>=0.80,0.70;0.75;0.80,library preparation method,500,library preparation protocol,0.8148148148148148,Treatment Dosage Regimen,,
+137,>=0.80,0.70;0.75;0.80,case/control,191,case or control,0.8148148148148148,Treatment,,
+138,>=0.80,0.70;0.75;0.80,preparation,169,cell preparation,0.8148148148148148,Biospecimen Type,,
+139,>=0.80,0.70;0.75;0.80,clinical type,85,clinical stage,0.8148148148148148,Biospecimen Age,,
+140,>=0.80,0.70;0.75;0.80,compartment,69,cell compartment,0.8148148148148148,Biospecimen Type,,
+141,>=0.80,0.70;0.75;0.80,replicate description,362,treatment description,0.8095238095238095,Treatment,,
+142,>=0.80,0.70;0.75;0.80,primary site,1010,primary tumor site,0.8,Biospecimen Disease Condition,,
+143,>=0.80,0.70;0.75;0.80,family,134,family id,0.8,External_sample_id,,
+144,>=0.80,0.70;0.75;0.80,immune status,113,mouse status,0.8,Biospecimen Organism,,
+145,>=0.80,0.70;0.75;0.80,location of onset,92,location of tumors,0.8,Biospecimen Disease Condition,,
+146,>=0.80,0.70;0.75;0.80,experimental status,72,experimental day,0.8,Biospecimen Age,,
+147,>=0.80,0.70;0.75;0.80,Subsets,60,subjects,0.8,External_sample_id,,
+148,>=0.80,0.70;0.75;0.80,parasite isolate,33,parasite stage,0.8,Biospecimen Age,,
+149,>=0.80,0.70;0.75;0.80,experimental factor,28,experimental day,0.8,Biospecimen Age,,
+150,>=0.80,0.70;0.75;0.80,Morphology,3,cell morphology,0.8,Biospecimen Type,,
diff --git a/RDAS_RDOMICS/scripts/sample_characteristics_harmonization/similarity_cutoff_evaluation/manual_review_template_manual_correct.csv b/RDAS_RDOMICS/scripts/sample_characteristics_harmonization/similarity_cutoff_evaluation/manual_review_template_manual_correct.csv
new file mode 100644
index 0000000..85471c3
--- /dev/null
+++ b/RDAS_RDOMICS/scripts/sample_characteristics_harmonization/similarity_cutoff_evaluation/manual_review_template_manual_correct.csv
@@ -0,0 +1,151 @@
+review_id,score_band,eligible_cutoffs,label,count,best_reference_label,best_similarity_score,assigned_category,manual_correct,manual_notes
+1,0.70_to_lt_0.75,0.70,microglia population,8,cell population,0.7428571428571429,Biospecimen Type,1,
+2,0.70_to_lt_0.75,0.70,transplanted with,2,transplanted organ,0.7428571428571429,Biospecimen Type,1,
+3,0.70_to_lt_0.75,0.70,library name,476,library barcode,0.7407407407407407,External_sample_id,1,
+4,0.70_to_lt_0.75,0.70,symptomatic,178,symptom duration,0.7407407407407407,Treatment Dosage Regimen,0,
+5,0.70_to_lt_0.75,0.70,antibody used,11,antibody group,0.7407407407407407,Treatment,1,
+6,0.70_to_lt_0.75,0.70,visit_date,313,visit day,0.7368421052631579,Biospecimen Age,1,
+7,0.70_to_lt_0.75,0.70,route administered,52,vaccine administered,0.7368421052631579,Treatment,0,
+8,0.70_to_lt_0.75,0.70,model type,12,cell type,0.7368421052631579,Biospecimen Type,1,
+9,0.70_to_lt_0.75,0.70,knockout,203,knockout group,0.7272727272727273,Treatment,0,
+10,0.70_to_lt_0.75,0.70,pain,101,patient,0.7272727272727273,External_sample_id,0,
+11,0.70_to_lt_0.75,0.70,surgery type,76,serum type,0.7272727272727273,Biospecimen Type,0,
+12,0.70_to_lt_0.75,0.70,infiltration,64,induration,0.7272727272727273,Treatment Dosage Regimen,0,
+13,0.70_to_lt_0.75,0.70,genotype abbreviation,14,mouse line abbreviation,0.7272727272727273,Biospecimen Organism,1,
+14,0.70_to_lt_0.75,0.70,scale,12,sample,0.7272727272727273,External_sample_id,0,
+15,0.70_to_lt_0.75,0.70,Extraction_amount,6,extraction_protocol,0.7222222222222222,Treatment Dosage Regimen,0,
+16,0.70_to_lt_0.75,0.70,culture result,894,culture age,0.72,Biospecimen Age,0,
+17,0.70_to_lt_0.75,0.70,recipient,534,recipient strain,0.72,Biospecimen Organism,1,
+18,0.70_to_lt_0.75,0.70,parasitemia,419,parasite stage,0.72,Biospecimen Age,0,
+19,0.70_to_lt_0.75,0.70,library quality,208,library id,0.72,External_sample_id,0,
+20,0.70_to_lt_0.75,0.70,infectivity,120,infection type,0.72,Biospecimen Disease Condition,1,
+21,0.70_to_lt_0.75,0.70,graft source,47,gender source,0.72,Biospecimen Sex,0,
+22,0.70_to_lt_0.75,0.70,paired with,37,paired patient,0.72,External_sample_id,1,
+23,0.70_to_lt_0.75,0.70,sort fraction,27,age fraction,0.72,Biospecimen Age,0,
+24,0.70_to_lt_0.75,0.70,oxygen status,4,mouse status,0.72,Biospecimen Organism,0,
+25,0.70_to_lt_0.75,0.70,clinical presentation,61,clinical condition,0.717948717948718,Biospecimen Disease Condition,1,
+26,0.70_to_lt_0.75,0.70,visit,3653,visit day,0.7142857142857143,Biospecimen Age,1,
+27,0.70_to_lt_0.75,0.70,malaria_status,500,malaria strain,0.7142857142857143,Biospecimen Organism,0,
+28,0.70_to_lt_0.75,0.70,library plate,412,library barcode,0.7142857142857143,External_sample_id,1,
+29,0.70_to_lt_0.75,0.70,survival status,152,survival time,0.7142857142857143,Biospecimen Age,0,
+30,0.70_to_lt_0.75,0.70,library_batch,64,library barcode,0.7142857142857143,External_sample_id,1,
+31,0.70_to_lt_0.75,0.70,culture platform,57,culture time,0.7142857142857143,Biospecimen Age,0,
+32,0.70_to_lt_0.75,0.70,commercial source,56,cell source,0.7142857142857143,Biospecimen Type,0,
+33,0.70_to_lt_0.75,0.70,molecule source,23,sample source,0.7142857142857143,External_sample_id,0,
+34,0.70_to_lt_0.75,0.70,antibody target description,21,age description,0.7142857142857143,Biospecimen Age,0,
+35,0.70_to_lt_0.75,0.70,genotype_abbreviation,500,mouse genotype/variation,0.7111111111111111,Biospecimen Organism,1,
+36,0.70_to_lt_0.75,0.70,surface area,363,cell surface marker,0.7096774193548387,Biospecimen Type,0,
+37,0.70_to_lt_0.75,0.70,pregnancy status,201,organoid status,0.7096774193548387,External_sample_id,0,
+38,0.70_to_lt_0.75,0.70,anatomic location,201,tumor location,0.7096774193548387,Biospecimen Disease Condition,0,
+39,0.70_to_lt_0.75,0.70,isolation method,52,isolation stage,0.7096774193548387,Biospecimen Age,0,
+40,0.70_to_lt_0.75,0.70,lymphs,460,lymphocytes,0.7058823529411765,Biospecimen Type,1,
+41,0.70_to_lt_0.75,0.70,modifications,57,chemical modification,0.7058823529411765,Treatment,1,
+42,0.70_to_lt_0.75,0.70,digestives_symptoms,45,disease symptom,0.7058823529411765,Biospecimen Disease Condition,1,
+43,0.70_to_lt_0.75,0.70,implantation,24,cell type implantation,0.7058823529411765,Biospecimen Type,0,
+44,0.70_to_lt_0.75,0.70,Labeling_reference,6,sample_reference,0.7058823529411765,External_sample_id,1,
+45,0.70_to_lt_0.75,0.70,reactivity,3,acidity,0.7058823529411765,External_sample_id,0,
+46,0.70_to_lt_0.75,0.70,incubation temperature,8,incubation time,0.7027027027027027,Biospecimen Age,0,
+47,0.70_to_lt_0.75,0.70,virus type,86,serum type,0.7,Biospecimen Type,0,
+48,0.70_to_lt_0.75,0.70,subclass,80,tissue class,0.7,Biospecimen Type,1,
+49,0.70_to_lt_0.75,0.70,lymph node,51,lymphocyte,0.7,Biospecimen Type,1,
+50,0.70_to_lt_0.75,0.70,who class,40,tumor class,0.7,Biospecimen Disease Condition,1,
+51,0.75_to_lt_0.80,0.70;0.75,anatomic site,10,tissue anatomic site,0.7878787878787878,Biospecimen Type,1,
+52,0.75_to_lt_0.80,0.70;0.75,viral inactivation,10,viral infection,0.7878787878787878,Biospecimen Disease Condition,0,
+53,0.75_to_lt_0.80,0.70;0.75,development,310,development stage,0.7857142857142857,Biospecimen Age,1,
+54,0.75_to_lt_0.80,0.70;0.75,parasite line,95,parasite strain,0.7857142857142857,Biospecimen Organism,1,
+55,0.75_to_lt_0.80,0.70;0.75,differentiation replicate,9,differentiation time point,0.7843137254901961,Biospecimen Age,0,
+56,0.75_to_lt_0.80,0.70;0.75,histology,3618,histopathology,0.782608695652174,Biospecimen Disease Condition,1,
+57,0.75_to_lt_0.80,0.70;0.75,Phenotype,141,cell phenotype,0.782608695652174,Biospecimen Type,1,
+58,0.75_to_lt_0.80,0.70;0.75,line type,123,cell line type,0.782608695652174,Biospecimen Type,1,
+59,0.75_to_lt_0.80,0.70;0.75,growth media,106,growth time,0.782608695652174,Biospecimen Age,0,
+60,0.75_to_lt_0.80,0.70;0.75,hippocampal sclerosis,6,hippocampal slice id,0.7804878048780488,External_sample_id,0,
+61,0.75_to_lt_0.80,0.70;0.75,sorted compartment,500,tissue compartment,0.7777777777777778,Biospecimen Type,1,
+62,0.75_to_lt_0.80,0.70;0.75,infectious challenge,82,infectious agent,0.7777777777777778,Biospecimen Age,0,
+63,0.75_to_lt_0.80,0.70;0.75,experiment type,295,experimental day,0.7741935483870968,Biospecimen Age,0,
+64,0.75_to_lt_0.80,0.70;0.75,study number,50,study sample number,0.7741935483870968,External_sample_id,1,
+65,0.75_to_lt_0.80,0.70;0.75,dementia status,16,treatment status,0.7741935483870968,Treatment,0,
+66,0.75_to_lt_0.80,0.70;0.75,antibody name,9,antibody treatment,0.7741935483870968,Treatment,1,
+67,0.75_to_lt_0.80,0.70;0.75,experiment,1725,experimental day,0.7692307692307693,Biospecimen Age,0,
+68,0.75_to_lt_0.80,0.70;0.75,simulation,80,cell stimulation,0.7692307692307693,Biospecimen Type,0,
+69,0.75_to_lt_0.80,0.70;0.75,series,27,species,0.7692307692307693,Biospecimen Organism,0,
+70,0.75_to_lt_0.80,0.70;0.75,replicate type,22,replicate id,0.7692307692307693,External_sample_id,0,
+71,0.75_to_lt_0.80,0.70;0.75,type of insertion,12,site of infection,0.7647058823529411,Biospecimen Disease Condition,0,
+72,0.75_to_lt_0.80,0.70;0.75,number of animals,10,number of_samples,0.7647058823529411,External_sample_id,0,
+73,0.75_to_lt_0.80,0.70;0.75,associated geo,4,associate geo_sample,0.7647058823529411,External_sample_id,1,
+74,0.75_to_lt_0.80,0.70;0.75,response,667,drug response,0.7619047619047619,Treatment,1,
+75,0.75_to_lt_0.80,0.70;0.75,os_status,656,mouse status,0.7619047619047619,Biospecimen Organism,0,
+76,0.75_to_lt_0.80,0.70;0.75,infected,101,time infected,0.7619047619047619,Biospecimen Age,0,
+77,0.75_to_lt_0.80,0.70;0.75,Genotype,52,host genotype,0.7619047619047619,Biospecimen Organism,1,
+78,0.75_to_lt_0.80,0.70;0.75,specific,39,specific-host,0.7619047619047619,Biospecimen Organism,0,
+79,0.75_to_lt_0.80,0.70;0.75,virus added,30,virus dose,0.7619047619047619,Treatment Dosage Regimen,1,
+80,0.75_to_lt_0.80,0.70;0.75,clone type,24,cancer type,0.7619047619047619,Biospecimen Disease Condition,0,
+81,0.75_to_lt_0.80,0.70;0.75,lesion status,57,infection status,0.7586206896551724,Biospecimen Disease Condition,1,
+82,0.75_to_lt_0.80,0.70;0.75,nitrogen source,8,control source,0.7586206896551724,Treatment,1,
+83,0.75_to_lt_0.80,0.70;0.75,initial preparation,10,tissue preparation,0.7567567567567568,Biospecimen Type,1,
+84,0.75_to_lt_0.80,0.70;0.75,tag,1317,stage,0.75,Biospecimen Age,0,
+85,0.75_to_lt_0.80,0.70;0.75,selection,567,mouse selection,0.75,Biospecimen Organism,0,
+86,0.75_to_lt_0.80,0.70;0.75,growth phase,558,growth stage,0.75,Biospecimen Age,1,
+87,0.75_to_lt_0.80,0.70;0.75,mutation,354,duration,0.75,Treatment Dosage Regimen,0,
+88,0.75_to_lt_0.80,0.70;0.75,brain location,197,treatment location,0.75,Treatment,0,
+89,0.75_to_lt_0.80,0.70;0.75,pathogens,138,pathogen strain,0.75,Biospecimen Organism,1,
+90,0.75_to_lt_0.80,0.70;0.75,isolate type,97,disease type,0.75,Biospecimen Disease Condition,0,
+91,0.75_to_lt_0.80,0.70;0.75,responder,84,responder cells,0.75,Biospecimen Type,0,
+92,0.75_to_lt_0.80,0.70;0.75,specificity,42,specific-host,0.75,Biospecimen Organism,0,
+93,0.75_to_lt_0.80,0.70;0.75,translocations,18,treatment location,0.75,Treatment,0,
+94,0.75_to_lt_0.80,0.70;0.75,length of culture,15,age of  culture,0.75,Biospecimen Age,1,
+95,0.75_to_lt_0.80,0.70;0.75,clone name,12,cell line name,0.75,Biospecimen Type,1,
+96,0.75_to_lt_0.80,0.70;0.75,derived culture,9,derived cell_type,0.75,Biospecimen Type,1,
+97,0.75_to_lt_0.80,0.70;0.75,process order,9,process day,0.75,Biospecimen Age,0,
+98,0.75_to_lt_0.80,0.70;0.75,Growth Medium,6,growth time,0.75,Biospecimen Age,0,
+99,0.75_to_lt_0.80,0.70;0.75,sorted,5,sorter day,0.75,Biospecimen Age,0,
+100,0.75_to_lt_0.80,0.70;0.75,reference cat,3,reference condition,0.75,Biospecimen Disease Condition,0,
+101,>=0.80,0.70;0.75;0.80,infection_state,20,infection state,0.9333333333333333,Biospecimen Disease Condition,1,
+102,>=0.80,0.70;0.75;0.80,antibody vendor,12,antibody vendor id,0.9090909090909091,External_sample_id,0,
+103,>=0.80,0.70;0.75;0.80,hours_post_infection,48,hours post infection,0.9,Biospecimen Disease Condition,0,
+104,>=0.80,0.70;0.75;0.80,animal number,32,animal id number,0.896551724137931,External_sample_id,1,
+105,>=0.80,0.70;0.75;0.80,injection,42,infection,0.8888888888888888,Biospecimen Disease Condition,0,
+106,>=0.80,0.70;0.75;0.80,differentiation status,43,differentiation stage,0.8837209302325582,Biospecimen Age,1,
+107,>=0.80,0.70;0.75;0.80,os_month,156,os month,0.875,Biospecimen Age,1,
+108,>=0.80,0.70;0.75;0.80,phase description,15,age description,0.875,Biospecimen Age,1,
+109,>=0.80,0.70;0.75;0.80,overall.survival,40,overall.survival.time,0.8648648648648649,Biospecimen Age,1,
+110,>=0.80,0.70;0.75;0.80,induction date,385,induction time,0.8571428571428571,Biospecimen Age,1,
+111,>=0.80,0.70;0.75;0.80,OS status,297,mouse status,0.8571428571428571,Biospecimen Organism,0,
+112,>=0.80,0.70;0.75;0.80,volunteer,171,volunteer id,0.8571428571428571,External_sample_id,1,
+113,>=0.80,0.70;0.75;0.80,cag,140,cage,0.8571428571428571,Biospecimen Age,0,
+114,>=0.80,0.70;0.75;0.80,polarization state,15,polarization treatment,0.85,Treatment,0,
+115,>=0.80,0.70;0.75;0.80,vaccination boost,92,vaccination dose,0.8484848484848485,Treatment Dosage Regimen,1,
+116,>=0.80,0.70;0.75;0.80,description,294,age description,0.8461538461538461,Biospecimen Age,0,
+117,>=0.80,0.70;0.75;0.80,sampling site,57,sampling time,0.8461538461538461,Biospecimen Age,0,
+118,>=0.80,0.70;0.75;0.80,maternal state,10,maternal age,0.8461538461538461,Biospecimen Age,0,
+119,>=0.80,0.70;0.75;0.80,parental line,55,parental cell line,0.8387096774193549,Biospecimen Type,1,
+120,>=0.80,0.70;0.75;0.80,state of culture,42,age of  culture,0.8387096774193549,Biospecimen Age,1,
+121,>=0.80,0.70;0.75;0.80,long description,12,age description,0.8387096774193549,Biospecimen Age,0,
+122,>=0.80,0.70;0.75;0.80,subpopulation,9,cell subpopulation,0.8387096774193549,Biospecimen Type,1,
+123,>=0.80,0.70;0.75;0.80,survival_yr,876,survival year,0.8333333333333334,Biospecimen Age,1,
+124,>=0.80,0.70;0.75;0.80,study,741,studyid,0.8333333333333334,External_sample_id,1,
+125,>=0.80,0.70;0.75;0.80,genomic modification,38,chemical modification,0.8292682926829268,Treatment,0,
+126,>=0.80,0.70;0.75;0.80,genotype/varation,14,mouse genotype/variation,0.8292682926829268,Biospecimen Organism,1,
+127,>=0.80,0.70;0.75;0.80,transduction,629,cell transduction,0.8275862068965517,Biospecimen Type,0,
+128,>=0.80,0.70;0.75;0.80,viral infected,33,viral infection,0.8275862068965517,Biospecimen Disease Condition,1,
+129,>=0.80,0.70;0.75;0.80,classification,369,classification group,0.8235294117647058,Treatment,0,
+130,>=0.80,0.70;0.75;0.80,experimental batch,38,experimental day,0.8235294117647058,Biospecimen Age,0,
+131,>=0.80,0.70;0.75;0.80,alternative name,14,alternative sample name,0.8205128205128205,External_sample_id,1,
+132,>=0.80,0.70;0.75;0.80,replicate number,6,sample replicate number,0.8205128205128205,External_sample_id,1,
+133,>=0.80,0.70;0.75;0.80,case number,726,cell number,0.8181818181818182,Biospecimen Type,0,
+134,>=0.80,0.70;0.75;0.80,library date,385,library id,0.8181818181818182,External_sample_id,0,
+135,>=0.80,0.70;0.75;0.80,stimulation,2378,cell stimulation,0.8148148148148148,Biospecimen Type,0,
+136,>=0.80,0.70;0.75;0.80,library preparation method,500,library preparation protocol,0.8148148148148148,Treatment Dosage Regimen,0,
+137,>=0.80,0.70;0.75;0.80,case/control,191,case or control,0.8148148148148148,Treatment,0,
+138,>=0.80,0.70;0.75;0.80,preparation,169,cell preparation,0.8148148148148148,Biospecimen Type,1,
+139,>=0.80,0.70;0.75;0.80,clinical type,85,clinical stage,0.8148148148148148,Biospecimen Age,0,
+140,>=0.80,0.70;0.75;0.80,compartment,69,cell compartment,0.8148148148148148,Biospecimen Type,1,
+141,>=0.80,0.70;0.75;0.80,replicate description,362,treatment description,0.8095238095238095,Treatment,0,
+142,>=0.80,0.70;0.75;0.80,primary site,1010,primary tumor site,0.8,Biospecimen Disease Condition,1,
+143,>=0.80,0.70;0.75;0.80,family,134,family id,0.8,External_sample_id,1,
+144,>=0.80,0.70;0.75;0.80,immune status,113,mouse status,0.8,Biospecimen Organism,0,
+145,>=0.80,0.70;0.75;0.80,location of onset,92,location of tumors,0.8,Biospecimen Disease Condition,1,
+146,>=0.80,0.70;0.75;0.80,experimental status,72,experimental day,0.8,Biospecimen Age,0,
+147,>=0.80,0.70;0.75;0.80,Subsets,60,subjects,0.8,External_sample_id,0,
+148,>=0.80,0.70;0.75;0.80,parasite isolate,33,parasite stage,0.8,Biospecimen Age,0,
+149,>=0.80,0.70;0.75;0.80,experimental factor,28,experimental day,0.8,Biospecimen Age,0,
+150,>=0.80,0.70;0.75;0.80,Morphology,3,cell morphology,0.8,Biospecimen Type,1,
diff --git a/RDAS_RDOMICS/scripts/step1_search_geo.py b/RDAS_RDOMICS/scripts/step1_search_geo.py
new file mode 100644
index 0000000..9715045
--- /dev/null
+++ b/RDAS_RDOMICS/scripts/step1_search_geo.py
@@ -0,0 +1,115 @@
+"""
+Step1 Search the geo keywords for counting the amount of series each gard id
+"""
+
+import os
+import pandas as pd
+import time
+from Bio import Entrez
+from urllib.error import HTTPError, URLError
+
+Entrez.email = os.environ.get("ENTREZ_EMAIL", "")
+
+# Function to perform eSearch query to get dataset IDs for a batch of keywords
+def search_geo_datasets(keywords, max_retries=3):
+    """
+    Searches GEO datasets for given keywords and returns a list of unique dataset IDs.
+    
+    Args:
+        keywords (list): List of keywords to search for.
+        max_retries (int): Maximum number of retries in case of rate limits or errors.
+    
+    Returns:
+        list: List of unique GEO series IDs.
+    """
+    retries = 0
+    id_list = []
+    # Combine keywords into a single search term
+    search_term = ' OR '.join([f'("{kw}"[MeSH Terms] OR {kw}[All Fields])' for kw in keywords]) + ' AND "gse"[Filter]'
+    retstart = 0
+    batch_size = 100
+    print("search_term: ", search_term)
+    while retries < max_retries:
+        try:
+            while True:
+                # Fetch records in batches
+                with Entrez.esearch(
+                    db="gds",
+                    term=search_term,
+                    retstart=retstart,
+                    retmax=batch_size,
+                    usehistory="y",
+                ) as handle:
+                    search_results = Entrez.read(handle)
+                
+                # Extract IDs and add them to the list    
+                batch_id_list = search_results["IdList"]
+                #query_key = search_results["QueryKey"]
+                #print("query_key:", query_key)
+                #web_env = search_results["WebEnv"]
+                #print("web_env:", web_env)
+                id_list.extend(batch_id_list)
+
+                # Check if we have reached the end of results
+                if len(batch_id_list) < batch_size:
+                    break
+
+                # Update the starting point for the next batch
+                retstart += batch_size
+            
+            # Remove duplicates from the accumulated IDs
+            unique_ids = list(set(id_list))
+            print(f"Found {len(unique_ids)} unique series for keywords: {keywords}")
+            return unique_ids
+        except HTTPError as e:
+            if e.code == 429:
+                print(f"Rate limit exceeded. Retrying after delay...({retries + 1}/{max_retries})")
+                time.sleep(5)
+                retries += 1
+            else:
+                print(f"HTTPError occurred: {e}")
+                break
+        except URLError as e:
+            print(f"URLError occurred: {e.reason}")
+            retries += 1
+            time.sleep(5)
+        except Exception as e:
+            print(f"An unexpected error occurred: {e}")
+            break
+
+    print(f"Failed to fetch data for keywords '{keywords}' after {max_retries} attempts.")
+    return []
+
+def process_disease_file(input_file, output_file, batch_size=10):
+    """
+    Processes a disease list file to count GEO datasets for each disease and saves the updated file.
+    
+    Args:
+        input_file (str): Path to the input Excel file.
+        output_file (str): Path to save the updated Excel file.
+        batch_size (int): Number of keywords to process per batch.
+    """
+    df = pd.read_excel(input_file)
+    # Initialize a list to store GEO counts for each disease
+    series_counts = []
+    
+    for disease in df['GARD_Disease']:
+        all_ids = [] # Initialize a list to accumulate all dataset IDs for the current disease
+        keywords = disease.split('; ') # Split the GARD_Disease into individual keywords
+
+        # Process keywords in batches
+        for i in range(0, len(keywords), batch_size):
+            batch_keywords = keywords[i:i + batch_size] # Get the current batch of keywords
+            ids = search_geo_datasets(batch_keywords) # Get the dataset IDs for this batch
+            all_ids.extend(ids) # Accumulate the IDs
+            time.sleep(1) # Adding a small delay between batch requests to reduce load
+
+        # Remove duplicates from the accumulated IDs and count them
+        unique_ids = list(set(all_ids))
+        series_counts.append(len(unique_ids))
+        print(f"Processed Disease: {len(unique_ids)} unique series found.")
+
+    # Add the accumulated GEO counts to the dataframe
+    df['Series_Count'] = series_counts
+    df.to_excel(output_file, index=False)
+    #print(f"Updated Excel file saved to:{output_file}")
diff --git a/RDAS_RDOMICS/scripts/step2_download_matrix_optional.py b/RDAS_RDOMICS/scripts/step2_download_matrix_optional.py
new file mode 100644
index 0000000..e83ec5c
--- /dev/null
+++ b/RDAS_RDOMICS/scripts/step2_download_matrix_optional.py
@@ -0,0 +1,256 @@
+"""
+Step2: Downloading all the series matrix files per GardID based on Entrez esearch in GEO Datasets using keywords with filter gse.
+
+i. esearch
+https://eutils.ncbi.nlm.nih.gov/entrez/eutils/esearch.fcgi?db=gds&term=("{kw}"[MeSH Terms]+OR+"{kw}"[All Fields])+AND+"gse"[Filter]&retmax=10&usehistory=y
+We can get IdList from this page.
+
+
+ii. download matrix files 
+https://ftp.ncbi.nlm.nih.gov/geo/series/GSE47nnn/GSE47603/matrix/
+For instance, GSE47603, we can download its file using the link above.
+
+search_term = ' OR '.join([f'("{kw}"[MeSH Terms] OR {kw}[All Fields])' for kw in keywords]) + ' AND "gse"[Filter]'
+
+"""
+# Since the maximum digits for GSE is 6, we can extract gse directly from the IdList
+import os
+import time
+import requests
+import pandas as pd
+from pathlib import Path
+from urllib.parse import urlencode, quote
+from urllib.error import HTTPError, URLError
+import gzip
+import shutil
+from tqdm import tqdm
+import ftplib
+
+# Entrez email setup for API usage
+from Bio import Entrez
+Entrez.email = os.environ.get("ENTREZ_EMAIL", "")
+
+# Function to format GARD_ID by padding the numeric part with leading zeros to 7 digits
+def format_gard_id(gard_id):
+    prefix, numeric = gard_id.split(":")
+    padded_numeric = numeric.zfill(7) # Pad numeric part to 7 digits
+    return f"{prefix}:{padded_numeric}"
+
+# Function to extract GSE number from IdList
+def extract_gse_number(id_list):
+    gse_ids = []
+    for id_str in id_list:
+        series_id = int(id_str[-6:]) # Extract last six digits
+        gse_id = f"GSE{series_id}"
+        gse_ids.append(gse_id)
+    return gse_ids
+
+# Function to determine the correct FTP directory format based on the series ID
+def format_series_numeric(series_id):
+    try:
+        series_num = int(series_id[3:]) # Extract the numeric part of the series ID 
+        if series_num < 1000:
+            return f"GSEnnn"
+        elif 1000 <= series_num < 10000:
+            return f"GSE{series_id[3]}nnn"
+        elif 10000 <= series_num < 100000:
+            return f"GSE{series_id[3:5]}nnn"
+        else:
+            return f"GSE{series_id[3:6]}nnn"
+    except Exception as e:
+        print(f"Error formatting series ID {series_id}: {e}")
+        return None
+
+
+
+# Function to download matrix files
+def download_matrix_file(gse_id, output_dir):
+    try:
+        series_numeric = format_series_numeric(gse_id)
+        matrix_url = f"https://ftp.ncbi.nlm.nih.gov/geo/series/{series_numeric}/{gse_id}/matrix/{gse_id}_series_matrix.txt.gz"
+        print(f"Attempting to download: {matrix_url}")
+
+        # Create the output directory if it does not exist
+        os.makedirs(output_dir, exist_ok=True)
+        matrix_file_path = Path(output_dir) / f"{gse_id}_series_matrix.txt.gz"
+
+        # Skip download if the file already exists
+        if matrix_file_path.with_suffix("").exists():  
+            print(f"File already exists: {matrix_file_path.with_suffix('')}")
+            return
+        
+        # Fetch and save the file
+        response = requests.get(matrix_url, stream=True)
+        response.raise_for_status() # Raise an exception for HTTP errors
+
+        # Save the file
+        with open(matrix_file_path, "wb") as f:
+            f.write(response.content)
+        
+        # Extract the .gz file
+        with gzip.open(matrix_file_path, "rb") as f_in:
+            with open(matrix_file_path.with_suffix(""), "wb") as f_out: # remove the file suffix(extension) of a path
+                shutil.copyfileobj(f_in, f_out)
+        
+        # Remove the .gz file after extraction
+        os.remove(matrix_file_path)
+        print(f"Downloaded and extracted: {matrix_file_path}")
+
+    except requests.exceptions.HTTPError:
+        print(f"File not found: {matrix_url}. Downloading all files in the matrix directory...")
+        try:
+            # Define the FTP path
+            series_path = f"/geo/series/{series_numeric}/{gse_id}/matrix/"
+            ftp = ftplib.FTP("ftp.ncbi.nlm.nih.gov")
+            ftp.login()
+            ftp.cwd(series_path)
+            
+            # List all files in the directory and download them
+            files = ftp.nlst()
+            for file_name in files:
+                local_path = Path(output_dir) / file_name
+                print(f"Downloading: {file_name}")
+                
+                with open(local_path, "wb") as f:
+                    ftp.retrbinary(f"RETR {file_name}", f.write)
+                
+                # Extract the .gz file
+                if file_name.endswith(".gz"):
+                    with gzip.open(local_path, "rb") as f_in:
+                        with open(local_path.with_suffix(""), "wb") as f_out:
+                            shutil.copyfileobj(f_in, f_out)
+                    os.remove(local_path)  # Remove the .gz file after extraction
+            
+            ftp.quit()
+            print(f"All matrix files downloaded and extracted for {gse_id}.")
+        except Exception as ftp_error:
+            print(f"Failed to download files {gse_id} from matrix directory: {ftp_error}")           
+    except Exception as e:
+        print(f"An unexpected error occurred while downloading {gse_id}: {e}")
+
+        
+
+# Function to perform eSearch and get series IDs for a batch of keywords
+def perform_esearch(keywords, max_retries=3, batch_size=300):
+    """
+    Performs an eSearch query to retrieve all series IDs for given keywords.
+
+    Args:
+        keywords (list): List of keywords to search for.
+        max_retries (int): Number of retry attempts in case of errors.
+        batch_size (int): Number of IDs to retrieve per request.
+
+    Returns:
+        list: A list of all unique GEO series IDs.
+    """
+    
+    search_term = ' OR '.join([f'("{kw}"[MeSH Terms] OR {kw}[All Fields])' for kw in keywords]) + ' AND "gse"[Filter]'
+    retries = 0
+    gse_set = set() # Use a set to store unique GSE IDs
+    retstart = 0 # Start point for fetching results
+    total_results = 0  # Total number of results to fetch
+
+    while retries < max_retries:
+        try:
+            # Perform an initial query to get the total number of results
+            with Entrez.esearch(db="gds", term=search_term, usehistory="y", retmax=1) as handle:
+                search_results = Entrez.read(handle)
+                total_results = int(search_results.get("Count", 0))
+            
+            print(f"Found {total_results} results for the search term.")
+
+            with tqdm(total=total_results, desc="Processing GEO series IDs", unit="id") as pbar:
+                while retstart < total_results:
+                
+                    # Fetch results in batches using retstart
+                    with Entrez.esearch(
+                        db="gds",
+                        term=search_term,
+                        usehistory="y",
+                        retmax=batch_size,
+                        retstart=retstart
+                    ) as handle:
+                        search_results = Entrez.read(handle)
+                    
+                    # Extract IDs and process them into GSE IDs
+                    batch_id_list = search_results["IdList"]
+                    for id_str in batch_id_list:
+                        try:
+                            series_id = int(id_str[-6:])
+                            gse_set.add(f"GSE{series_id}")
+                        except ValueError:
+                            print(f"Skipping invalid ID: {id_str}")
+
+                    # Update progress bar based on the number of processed results
+                    retstart += len(batch_id_list)
+                    pbar.update(len(batch_id_list))
+
+                    if len(batch_id_list) < batch_size:
+                        break # No more results to fetch
+            
+            return list(gse_set)
+
+        except HTTPError as e:
+            if e.code == 429:
+                print(f"Rate limit exceeded. Retrying after delay...({retries + 1}/{max_retries})")
+                time.sleep(5)
+                retries += 1
+            else:
+                print(f"HTTPError occurred: {e}")
+                break
+        except URLError as e:
+            print(f"URLError occurred: {e.reason}")
+            retries += 1
+            time.sleep(5)
+        except Exception as e:
+            print(f"An unexpected error occurred: {e}")
+            break
+    raise Exception("Failed to perform eSearch after multiple attempts.")
+
+
+# Main function to process diseases and download matrix files
+def process_diseases_and_download_matrix(input_file, output_dir, batch_size=10):
+    """
+    Processes diseases from the input file and downloads matrix files.
+
+    Args:
+        input_file (str): Path to the input Excel file with disease data.
+        output_dir (str): Base path to save the downloaded files.
+        batch_size (int): Number of keywords to process per batch.
+    """
+
+    df = pd.read_excel(input_file)
+    # Filter rows where Series_Count > 0
+    df = df[df['Series_Count'] > 0] 
+
+    for _, row in tqdm(df.iterrows(), total=len(df), desc="Processing Diseases"):
+        gard_id = format_gard_id(row['GARD_ID'])
+        keywords = row['GARD_Disease'].split('; ')
+        disease_output_path = Path(output_dir) / gard_id
+
+        # Keep track of downloaded IDs to avoid duplicates
+        downloaded_ids = set()
+
+        print(f"Processing GARD_ID: {gard_id}, Keywords: {keywords}")
+        #all_ids = [] # Initialize a list to accumulate all dataset IDs for the current disease
+        try:
+            # Process keywords in batches
+            for i in range(0, len(keywords), batch_size):
+                batch_keywords = keywords[i:i + batch_size] # Get the current batch of keywords
+                gse_ids = perform_esearch(batch_keywords)
+                if not gse_ids:
+                    continue
+
+                # Convert IdList to GSE IDs
+                #gse_ids = extract_gse_number(batch_ids)
+
+                # Download the matrix files for each unique GSE ID not already downloaded
+                for gse_id in gse_ids:
+                    if gse_id not in downloaded_ids:
+                        print("Start downloading:", gse_id)
+                        download_matrix_file(gse_id, disease_output_path)
+                        downloaded_ids.add(gse_id)
+                time.sleep(1)
+
+        except Exception as e:
+            print(f"Error processing {gard_id}: {e}")
diff --git a/RDAS_RDOMICS/scripts/step3_download_gse_number.py b/RDAS_RDOMICS/scripts/step3_download_gse_number.py
new file mode 100644
index 0000000..020c26c
--- /dev/null
+++ b/RDAS_RDOMICS/scripts/step3_download_gse_number.py
@@ -0,0 +1,151 @@
+"""
+Step3: Extracting all the label and content from web page directly and create GSE tables, instead of using the download matrix file from step2
+i. extract all the information needed from matrix
+ii. parse from web link
+iii. refine to get the final GSE table
+
+"""
+import os
+import time
+import requests
+import pandas as pd
+from pathlib import Path
+from urllib.parse import urlencode, quote
+from urllib.error import HTTPError, URLError
+import gzip
+import shutil
+from tqdm import tqdm
+import ftplib
+import json
+
+# Entrez email setup for API usage
+from Bio import Entrez
+Entrez.email = os.environ.get("ENTREZ_EMAIL", "")
+
+# Function to format GARD_ID by padding the numeric part with leading zeros to 7 digits
+def format_gard_id(gard_id):
+    prefix, numeric = gard_id.split(":")
+    padded_numeric = numeric.zfill(7) # Pad numeric part to 7 digits
+    return f"{prefix}:{padded_numeric}"
+
+
+# Function to perform eSearch and get series IDs for a batch of keywords
+def perform_esearch(keywords, max_retries=3, batch_size=300):
+    """
+    Performs an eSearch query to retrieve all series IDs for given keywords.
+
+    Args:
+        keywords (list): List of keywords to search for.
+        max_retries (int): Number of retry attempts in case of errors.
+        batch_size (int): Number of IDs to retrieve per request.
+
+    Returns:
+        list: A list of all unique GEO series IDs.
+    """
+    
+    search_term = ' OR '.join([f'("{kw}"[MeSH Terms] OR {kw}[All Fields])' for kw in keywords]) + ' AND "gse"[Filter]'
+    retries = 0
+    gse_set = set() # Use a set to store unique GSE IDs
+    retstart = 0 # Start point for fetching results
+    total_results = 0  # Total number of results to fetch
+
+    while retries < max_retries:
+        try:
+            # Perform an initial query to get the total number of results
+            with Entrez.esearch(db="gds", term=search_term, usehistory="y", retmax=1) as handle:
+                search_results = Entrez.read(handle)
+                total_results = int(search_results.get("Count", 0))
+            
+            print(f"Found {total_results} results for the search term.")
+
+            with tqdm(total=total_results, desc="Processing GEO series IDs", unit="id") as pbar:
+                while retstart < total_results:
+                
+                    # Fetch results in batches using retstart
+                    with Entrez.esearch(
+                        db="gds",
+                        term=search_term,
+                        usehistory="y",
+                        retmax=batch_size,
+                        retstart=retstart
+                    ) as handle:
+                        search_results = Entrez.read(handle)
+                    
+                    # Extract IDs and process them into GSE IDs
+                    batch_id_list = search_results["IdList"]
+                    for id_str in batch_id_list:
+                        try:
+                            series_id = int(id_str[-6:])
+                            gse_set.add(f"GSE{series_id}")
+                        except ValueError:
+                            print(f"Skipping invalid ID: {id_str}")
+
+                    # Update progress bar based on the number of processed results
+                    retstart += len(batch_id_list)
+                    pbar.update(len(batch_id_list))
+
+                    if len(batch_id_list) < batch_size:
+                        break # No more results to fetch
+            
+            return list(gse_set)
+
+        except HTTPError as e:
+            if e.code == 429:
+                print(f"Rate limit exceeded. Retrying after delay...({retries + 1}/{max_retries})")
+                time.sleep(5)
+                retries += 1
+            else:
+                print(f"HTTPError occurred: {e}")
+                break
+        except URLError as e:
+            print(f"URLError occurred: {e.reason}")
+            retries += 1
+            time.sleep(5)
+        except Exception as e:
+            print(f"An unexpected error occurred: {e}")
+            break
+    raise Exception("Failed to perform eSearch after multiple attempts.")
+
+
+# Main function to process diseases and download matrix files
+def record_gse_number(input_file, output_file, batch_size=10):
+    """
+    Processes diseases from the input file and saves GSE IDs into a CSV file.
+
+    Args:
+        input_file (str): Path to the input Excel file with disease data.
+        output_csv (str): Path to save the output CSV file.
+        batch_size (int): Number of keywords to process per batch.
+    """
+
+    df = pd.read_excel(input_file)
+    # Filter rows where Series_Count > 0
+    df = df[df['Series_Count'] > 0] 
+
+    gard_to_gse = {}
+
+    for _, row in tqdm(df.iterrows(), total=len(df), desc="Processing Diseases"):
+        gard_id = format_gard_id(row['GARD_ID'])
+        keywords = row['GARD_Disease'].split('; ')
+        print(f"Processing GARD_ID: {gard_id}, Keywords: {keywords}")
+
+
+        gard_to_gse[gard_id] = []
+
+        print(f"Processing GARD_ID: {gard_id}, Keywords: {keywords}")
+        try:
+            # Process keywords in batches
+            for i in range(0, len(keywords), batch_size):
+                batch_keywords = keywords[i:i + batch_size] # Get the current batch of keywords
+                gse_ids = perform_esearch(batch_keywords)
+                gard_to_gse[gard_id].extend(gse_ids)
+                time.sleep(1)
+
+    
+        except Exception as e:
+            print(f"Error processing {gard_id}: {e}")
+        
+        # Save the output
+        with open(output_file, "w") as json_file:
+            json.dump(gard_to_gse, json_file, indent=4)
+        print(f"Saved GSE IDs to {output_file}")
diff --git a/RDAS_RDOMICS/scripts/step4_extract_to_table.py b/RDAS_RDOMICS/scripts/step4_extract_to_table.py
new file mode 100644
index 0000000..c1d7653
--- /dev/null
+++ b/RDAS_RDOMICS/scripts/step4_extract_to_table.py
@@ -0,0 +1,702 @@
+"""
+Now we get the GSE numbers, next we want download all the information we need to form our table
+"""
+import os
+import json
+import pandas as pd
+import requests
+from bs4 import BeautifulSoup
+from tqdm import tqdm
+import re
+from concurrent.futures import ThreadPoolExecutor, as_completed
+from requests.adapters import HTTPAdapter
+from urllib3.util.retry import Retry
+
+#********************
+# Load data functions
+#********************
+def load_json(file_path):
+    with open(file_path, 'r') as f:
+        return json.load(f)
+
+def load_table_template(template_path):
+    return pd.read_excel(template_path, sheet_name=0)
+
+#******************
+# Folder management
+#******************
+def create_output_folder(base_path, gard_id):
+    folder_path = os.path.join(base_path, gard_id)
+    os.makedirs(folder_path, exist_ok=True)
+    return folder_path
+
+# Create a new requests seesion for time efficiency
+def get_requests_session():
+    session = requests.Session()
+    retries = Retry(
+        total=5,
+        backoff_factor=0.5,
+        status_forcelist=[500, 502, 503, 504],
+    )
+    adapter = HTTPAdapter(max_retries=retries)
+    session.mount("http://", adapter)
+    session.mount("https://", adapter)
+    return session
+#***************************************************************************************
+# Web extraction functions
+# Below includes all the functions for extracting information from GEO website 
+#***************************************************************************************
+
+# Main function for the extracting part
+def extract_gse_data(gse_id, session):
+    """Extract relevant GSE information from the GEO page"""
+    base_url = f"https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc={gse_id}"
+    try:
+        response = session.get(base_url)
+        response.raise_for_status() # ensure we catch HTTP errors
+    except requests.exceptions.ConnectionError:
+        # Recreate session in case of session expiration
+        print(f"Session expired. Recreating session for {gse_id}...")
+        session = get_requests_session()
+        response = session.get(base_url)
+        response.raise_for_status()
+
+    
+    series_soup = BeautifulSoup(response.text, "html.parser")
+    # GSEnnn for directory
+    gse_numeric = format_geo_numeric(gse_id)
+
+    # Extract Experiment Content
+    series_geo_accession, series_citations, series_supplementary_file = extract_series_content(series_soup, gse_numeric, gse_id, session)
+    
+    # Platform -> GPL, 
+    platform_title, platform_manufacturer = extract_platform_content(series_soup, session)
+
+    # Sample -> GSM
+    sample_geo_accession, sample_title, sample_organism, sample_source_name, sample_supplementary_file, sample_library_strategy, sample_extracted_molecule, sample_characteristics, sample_biosample, sample_srr = extract_sample_content(series_soup, session) 
+    #sample_external_reference_id = f"Bio-sample id: {sample_biosample or ''}; SRA id: {sample_srr or ''}"
+
+    # Project -> Series_Relation
+    series_project_id, project_title, project_abstract, project_data_type, project_submission = extract_project_content(series_soup, session)    
+   
+
+
+    result = {
+        "Series_geo_accession": series_geo_accession,
+        #"Series_status": series_status,
+        "Series_citations": series_citations, #Pubmed_id
+        "Series_supplementary_file": series_supplementary_file,
+        #"Series_platform_id": series_platform_id,
+        "Platform_title": platform_title,
+        #"Platform_technology": platform_technology,
+        "Platform_manufacturer": platform_manufacturer,
+        #"Platform_supplementary_file": platform_supplementary_file,
+        "Sample_geo_accession": sample_geo_accession,
+        "Sample_title": sample_title,
+        "Sample_organism": sample_organism,
+        "Sample_source_name": sample_source_name, # Disease_status
+        "Sample_supplementary_file": sample_supplementary_file,
+        "Sample_library_strategy": sample_library_strategy,  # sequencing_type
+        "Sample_extracted_molecule": sample_extracted_molecule,   # sequencing_library
+        "Sample_characteristics": sample_characteristics,
+        "Sample_biosample": sample_biosample,
+        "Sample_srr": sample_srr,
+        #"Sample_external_reference_id": sample_external_reference_id,
+        "Series_project_id": series_project_id,
+        "Project_title": project_title,
+        "Project_abstract": project_abstract,
+        "Project_data_type": project_data_type,     #Omics_type
+        "Project_submission": project_submission   # Data_release_date
+        #"Project_relevance": project_relevance,
+    }
+
+    #result.update(gds_details_list)
+
+    return result
+
+# Helper function to determine the correct FTP directory format based on the GEO ID (series/platform)
+def format_geo_numeric(geo_id):
+    try:
+        if not geo_id.startswith(("GSE", "GSM", "GPL")):
+            raise ValueError(f"Invalid GEO ID prefix: {geo_id}")
+        
+        prefix = geo_id[:3]
+        geo_num = geo_id[3:] # Extract the numeric part of the ID 
+        
+        if not geo_num.isdigit():
+            raise ValueError(f"Non-numeric GEO ID: {geo_id}")
+        
+        geo_num = int(geo_num)
+
+        if geo_num < 1000:
+            return f"{prefix}nnn"
+        elif 1000 <= geo_num < 10000:
+            return f"{prefix}{geo_id[3]}nnn"
+        elif 10000 <= geo_num < 100000:
+            return f"{prefix}{geo_id[3:5]}nnn"
+        else:
+            return f"{prefix}{geo_id[3:6]}nnn"
+    except ValueError as ve:
+        print(f"Error formatting series ID {geo_id}:{ve}")
+        raise
+        #return None
+    except Exception as e:
+        print(f"Unexpected error with GEO ID {geo_id}: {e}")
+        raise
+        #return None
+    
+def extract_supplementary_files(soup, geo_numeric, geo_id):
+    """Extract all supplementary file links."""
+    files = []
+    prefix = geo_id[:3]
+    # Find the header row for 'Supplementary file'
+    header_row = soup.find("td", align="middle", text="Supplementary file")
+    if not header_row:
+        return files # return empty if not found
+    
+    # Find the parent table containing supplementary files
+    table = header_row.find_parent("table")
+    if not table:
+        return files
+    
+    # Extract file names from rows below the header
+    for row in table.find_all("tr", valign="top"):
+        file_tag = row.find("td", bgcolor=True)
+        base_url = None
+        if file_tag and (file_tag.text.endswith(".gz") or file_tag.text.endswith(".tar")):
+            file_name = file_tag.text.strip()            
+            if prefix == "GSE":
+                base_url = f"ftp://ftp.ncbi.nlm.nih.gov/geo/series/{geo_numeric}/{geo_id}/suppl/{file_name}"
+            elif prefix == "GPL":
+                base_url = f"ftp://ftp.ncbi.nlm.nih.gov/geo/platforms/{geo_numeric}/{geo_id}/suppl/{file_name}"            
+            if base_url:
+                files.append(base_url)
+            
+    return files
+
+# Extracting helper function groups
+def extract_series_content(series_soup, gse_numeric, gse_id, session):
+    """Extract the publication status."""
+    series_geo_accession = [gse_id]
+    
+    citations_tag = series_soup.find("td", text="Citation(s)")
+    citations = [citations_tag.find_next_sibling("td").text.strip()] if citations_tag and citations_tag.find_next_sibling("td") else []
+
+    series_supplementary_file = extract_supplementary_files(series_soup, gse_numeric, gse_id)
+  
+    return series_geo_accession, citations, series_supplementary_file
+
+
+def extract_platform_content(series_soup, session):
+    # Extract platform id first on series page
+    #platform_id_tag = series_soup.find("td", string=lambda text: text and "Platforms" in text)
+    platform_id_tag = series_soup.find(lambda tag: tag.name == "td" and "Platforms " in tag.get_text())
+
+    #platform_id_tag = series_soup.find("td", text=re.compile(r"Platforms \(\d+\)"))
+    #print("platform_id_tag: ", platform_id_tag)
+    platform_ids = []
+
+    if platform_id_tag:
+        # Navigate to the parent <tr> and then find all <a> tags within it
+        platform_tr = platform_id_tag.find_parent("tr")
+        #print("platform_tr:", platform_tr)
+        if platform_tr:
+            platform_links = platform_tr.find_all("a", href=re.compile(r"acc=GPL"))
+            platform_ids = [link.text.strip() for link in platform_links]
+        
+    #print("platform_ids: ", platform_ids)
+    platform_title = []
+    #platform_technology = []
+    platform_manufacturer = []
+    #platform_supplementary_file = []
+
+    for platform_id in platform_ids:
+        #gpl_numeric = format_geo_numeric(platform_id)
+
+        # Extract from GPL page 
+        platform_url = f"https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc={platform_id}"
+        response = session.get(platform_url)
+        platform_soup = BeautifulSoup(response.text, "html.parser")
+        
+        platform_title_tag = platform_soup.find("td", text="Title")
+        #platform_title[platform_title_tag.find_next_sibling("td").text.strip()] if platform_title_tag and platform_title_tag.find_next_sibling("td") else []
+        platform_title.append(
+            platform_title_tag.find_next_sibling("td").text.strip() if platform_title_tag and platform_title_tag.find_next_sibling("td") else None
+        )
+
+        #platform_technology_tag = platform_soup.find("td", text="Technology type")
+        #platform_technology.append(
+        #    platform_technology_tag.find_next_sibling("td").text.strip() if platform_technology_tag and platform_technology_tag.find_next_sibling("td") else None
+        #)
+
+        platform_manufacturer_tag = platform_soup.find("td", text="Manufacturer")
+        #platform_manufacturer = [platform_manufacturer_tag.find_next_sibling("td").text.strip()] if platform_manufacturer_tag and platform_manufacturer_tag.find_next_sibling("td") else []
+        platform_manufacturer.append(
+            platform_manufacturer_tag.find_next_sibling("td").text.strip() if platform_manufacturer_tag and platform_manufacturer_tag.find_next_sibling("td") else None
+        )
+
+        #platform_supplementary_file.append(
+        #    extract_supplementary_files(platform_soup, gpl_numeric, platform_id)
+        #)
+    
+    return platform_title, platform_manufacturer # platform_ids, platform_technology,platform_supplementary_file
+"""
+# Configure a requests session with retries
+def get_requests_session():
+    session = requests.Session()
+    retries = Retry(
+        total=5,  # Retry up to 5 times
+        backoff_factor=0.5,  # Wait 0.5s, then 1s, 2s, etc.
+        status_forcelist=[500, 502, 503, 504],  # Retry on these HTTP status codes
+    )
+    adapter = HTTPAdapter(max_retries=retries)
+    session.mount("http://", adapter)
+    session.mount("https://", adapter)
+    return session
+"""
+def extract_sample_content(series_soup, session):
+    #session = get_requests_session() # Use session with retries
+
+    # Extract sample_ids
+    sample_text = series_soup.find(text=re.compile(r"^Samples \(\d+"))
+    sample_ids = []
+
+    if sample_text:
+        # Navigate to its parent <td>
+        sample_id_tag = sample_text.find_parent("td")
+        if sample_id_tag and sample_id_tag.find_next_sibling("td"):
+            sample_id_td = sample_id_tag.find_next_sibling("td")
+            # Find all <a> tags containing platform IDs
+            sample_links = sample_id_td.find_all("a")
+            sample_ids = [link.text.strip() for link in sample_links if link.text.startswith("GSM")]
+
+        
+    # Initialize lists    
+    sample_title = []
+    sample_organism = []
+    sample_source_name = []
+    sample_supplementary_file = []
+    sample_library_strategy = []
+    sample_extracted_molecule = []
+    sample_characteristics = []
+    sample_biosample = []
+    sample_srr = []
+
+    for sample_id in sample_ids:
+        if not sample_id.startswith("GSM"):
+            print("******Here is the sample_id*****: ", sample_id)
+        gsm_numeric = format_geo_numeric(sample_id) # GSMnnn
+
+        # Extract from GSM page 
+        sample_url = f"https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc={sample_id}"
+        try:
+            response = session.get(sample_url, timeout=10)
+            response.raise_for_status() # Raise HTTPError for bad responses
+        except requests.exceptions.RequestException as e:
+            print(f"Failed to fetch data for {sample_id}: {e}")
+            continue
+        #response = requests.get(sample_url)
+        sample_soup = BeautifulSoup(response.text, "html.parser")
+        
+        # Extract required fields
+        sample_title_tag = sample_soup.find("td", text="Title")
+        sample_title.append(
+            sample_title_tag.find_next_sibling("td").text.strip() if sample_title_tag and sample_title_tag.find_next_sibling("td") else None
+        )
+        
+        sample_organism_tag = sample_soup.find("td", text="Organism")
+        sample_organism.append(
+            sample_organism_tag.find_next_sibling("td").text.strip() if sample_organism_tag and sample_organism_tag.find_next_sibling("td") else None
+        )
+        
+        sample_source_name_tag = sample_soup.find("td", text="Source name")
+        sample_source_name.append(
+            sample_source_name_tag.find_next_sibling("td").text.strip() if sample_source_name_tag and sample_source_name_tag.find_next_sibling("td") else None
+        )
+
+        sample_extracted_molecule_tag = sample_soup.find("td", text="Extracted molecule")
+        sample_extracted_molecule.append(
+            sample_extracted_molecule_tag.find_next_sibling("td").text.strip() if sample_extracted_molecule_tag and sample_extracted_molecule_tag.find_next_sibling("td") else None
+        )
+
+        sample_library_strategy_tag = sample_soup.find("td", text="Library strategy")
+        sample_library_strategy.append(
+            sample_library_strategy_tag.find_next_sibling("td").text.strip() if sample_library_strategy_tag and sample_library_strategy_tag.find_next_sibling("td") else None
+        )
+        
+
+        # Sample Characteristics
+        sample_characteristics_tag = sample_soup.find("td", text="Characteristics")
+        sample_characteristics_td = sample_characteristics_tag.find_next_sibling("td") if sample_characteristics_tag else None
+        characteristics = ""
+        if sample_characteristics_td:
+            # Extract text and replace <br> with ;
+            characteristics = sample_characteristics_td.get_text(separator="; ").strip()
+        sample_characteristics.append(characteristics)
+
+
+        # Sample supplementary files
+        sample_supplementary_file.append(
+            extract_supplementary_files(sample_soup, gsm_numeric, sample_id)
+        )
+
+        # Sample BioProject        
+        sample_biosample_tag = sample_soup.find("td", text="BioProject")
+        sample_biosample.append(
+            sample_biosample_tag.find_next_sibling("td").text.strip() if sample_biosample_tag and sample_biosample_tag.find_next_sibling("td") else None
+        )
+                
+        # Sample SRA -> SRR
+        sample_sra_link = None
+        sample_srr_number = None
+        # Find the SRA link
+        sample_sra_tag = sample_soup.find("td", text="SRA", valign="top")
+        if sample_sra_tag:
+            next_td = sample_sra_tag.find_next_sibling("td")
+            if next_td:
+                sample_sra_link = next_td.find("a")["href"]
+        # Check if the link was found before making a request
+        if sample_sra_link:
+            response = requests.get(sample_sra_link)
+            sample_sra_soup = BeautifulSoup(response.text, "html.parser")
+            sample_srr_tag = sample_sra_soup.find("a", text=re.compile(r'^SRR\d+'))
+            #print("sample_srr_tag:", sample_srr_tag)
+            sample_srr_number = sample_srr_tag.get_text(strip=True) if sample_srr_tag else None            
+        sample_srr.append(sample_srr_number)       
+
+    return sample_ids, sample_title, sample_organism, sample_source_name, sample_supplementary_file, sample_library_strategy, sample_extracted_molecule, sample_characteristics, sample_biosample, sample_srr
+
+def extract_project_content(series_soup, session):
+    # Initialize variables with default None values
+    project_id, project_title, project_abstract, project_data_type, project_submission = ([],) * 5
+    
+    project_id_tag = series_soup.find("td", text="BioProject")
+    project_link = None
+    #print("project_id_tag: ", project_id_tag)
+
+    if project_id_tag and project_id_tag.find_next_sibling("td"):
+        project_id = [project_id_tag.find_next_sibling("td").text.strip()]
+
+        # Extract project link
+        link_tag = project_id_tag.find_next_sibling("td").find("a")
+        if link_tag and link_tag["href"]:
+            project_link = link_tag["href"]
+            
+            # Handle incomplete link
+            if project_link.startswith("/"):
+                project_link = f"https://www.ncbi.nlm.nih.gov{project_link}"
+
+    if project_link:
+        response = session.get(project_link)
+        project_soup = BeautifulSoup(response.text, "html.parser")
+        # Extract title, abstract, datatype, submission, relevance, geo dataset
+        # Title
+        title_div = project_soup.find('div', class_='Title')
+        if title_div:
+            project_title = [title_div.get_text(separator=' ', strip=True)]
+
+        #print("project_title: ", project_title)
+
+        # abstract
+        abstract_div = project_soup.find('div', id='DescrAll') or project_soup.find('div', class_='Description')
+        if abstract_div:
+            abstract_text = abstract_div.get_text(separator=' ', strip=True).split(' Less...')[0]
+            project_abstract = [abstract_text]
+
+        # Extract data type
+        data_type_tag = project_soup.find('td', class_='CTtitle', text='Data Type')
+        if data_type_tag:
+            data_type_content = data_type_tag.find_next_sibling('td', class_='CTcontent')
+            if data_type_content:
+                project_data_type = [data_type_content.get_text(strip=True)]
+
+        # Extract submission date
+        submission_tag = project_soup.find('td', class_='CTtitle', text='Submission')
+        if submission_tag:
+            submission_content = submission_tag.find_next_sibling('td', class_='CTcontent')
+            if submission_content:
+                project_submission = [submission_content.get_text(separator=' ', strip=True)]
+
+        # Extract relevance
+        #relevance_tag = project_soup.find('td', class_='CTtitle', text='Relevance')
+        #if relevance_tag:
+        #    relevance_content = relevance_tag.find_next_sibling('td', class_='CTcontent')
+        #    if relevance_content:
+        #        project_relevance = [relevance_content.get_text(strip=True)]
+        
+        # Extract dataset link
+        #gds_details_list = extract_dataset_content(project_soup)
+
+    return project_id, project_title, project_abstract, project_data_type, project_submission
+   
+"""
+def extract_dataset_content(project_soup):
+    gds_details_list = []
+
+    # Search GEO DataSets and get gds_search_soup, then find the gds_soup, then extract the contents
+    #dataset_search_link = None
+    dataset_search_link_tag = project_soup.find('a', class_='brieflinkpopperctrl', text='GEO DataSets')
+    if not dataset_search_link_tag or not dataset_search_link_tag['href']:
+        return gds_details_list
+    
+    # Construct the full link
+    dataset_search_link = f"https://www.ncbi.nlm.nih.gov{dataset_search_link_tag['href']}"
+    response = requests.get(dataset_search_link)
+    dataset_search_soup = BeautifulSoup(response.text, "html.parser")
+
+    # Extract all GDS numbers from dataset_search_soup
+    # Find all occurrences of 'Accession:' in <dt> tags
+    accession_tags = dataset_search_soup.find_all('dt', text='Accession:')
+    # Loop through and extract corresponding <dd> values
+    gds_numbers = [tag.find_next_sibling('dd').text.strip() 
+                   for tag in accession_tags 
+                   if tag.find_next_sibling('dd') and tag.find_next_sibling('dd').text.startswith('GDS')]
+    
+    
+    result_gds_list = {
+        "Title": [],
+        "Summary": [],
+        "Organism": [],
+        "Platform": [],
+        "Citation": [],
+        "Reference_Series": [],
+        "Sample_Count": [],
+        "Value_Type": [],
+        "Series_Published": [],
+        "GDS_Number": []
+    }
+
+    # Visit each GDS page and Extract GDS details
+    for gds_number in gds_numbers:
+        gds_url = f"https://www.ncbi.nlm.nih.gov/sites/GDSbrowser?acc={gds_number}"
+        response = requests.get(gds_url)
+        dataset_soup = BeautifulSoup(response.text, "html.parser")
+        gds_details = extract_gds_details(dataset_soup)
+        gds_details["GDS_Number"] = gds_number
+
+        for key,value in gds_details:
+            result_gds_list[key].append(value)
+    print("result_gds_list: ",result_gds_list)
+    return result_gds_list
+
+        #gds_details_list.append(gds_details)
+    #eturn gds_details_list
+
+# Extract details from the dataset_soup table
+def extract_gds_details(dataset_soup):
+    details = {
+        "Title": None,
+        "Summary": None,
+        "Organism": None,
+        "Platform": None,
+        "Citation": None,
+        "Reference_Series": None,
+        "Sample_Count": None,
+        "Value_Type": None,
+        "Series_Published": None,
+    }
+    
+    # Helper function to extract text based on header label
+    def extract_detail(label):
+        header = dataset_soup.find('th', class_='not_caption', text=label)
+        if header:
+            td = header.find_next_sibling('td')
+            if td:
+                return td.get_text(separator=' ', strip=True)
+        return None
+
+    # Extract each field
+    details["Title"] = extract_detail("Title:")
+    details["Summary"] = extract_detail("Summary:")
+    details["Organism"] = extract_detail("Organism:")
+    details["Platform"] = extract_detail("Platform:")
+    details["Citation"] = extract_detail("Citation:")
+    details["Reference Series"] = extract_detail("Reference Series:")
+    details["Sample Count"] = extract_detail("Sample count:")
+    details["Value Type"] = extract_detail("Value type:")
+    details["Series Published"] = extract_detail("Series published:")
+
+    return details
+"""
+#******************
+# Table management
+#******************
+
+def fill_table_with_data(template, data, gard_id, disease_name_list):
+    table = template.copy()
+
+    cleaned_gard_id = f"GARD:{gard_id.split(':')[1].lstrip('0')}"
+    #print("cleaned_gard_id: ", cleaned_gard_id)
+    #print("disease_name_list: ", disease_name_list)
+    disease_df = pd.read_excel(disease_name_list)
+    disease_row = disease_df[disease_df['GARD_ID'] == cleaned_gard_id]
+    #print("disease_row: ",disease_row)
+    # Extract the first part of 'GARD_Disease' separated by ';'
+    if not disease_row.empty:
+        condition_name = disease_row.iloc[0]['GARD_Disease'].split(';')[0].strip()
+        #print("Here condition name:", condition_name)
+    else:
+        condition_name = ''  # Default if not found
+    #print("condition_name: ", condition_name)
+
+    # Fill the Content column with extracted data, Use apply() to insert lists directly
+    # Series
+    # Platform
+    # Define mappings between attributes and data keys
+    attribute_data_mapping = {
+        'External_experiment_source_id': 'Series_geo_accession',
+        #'Publish_date': 'Series_status',
+        'Pubmed_id': 'Series_citations',
+        'Experiment_data_link': 'Series_supplementary_file',
+
+        #'Source_platform_id': 'Series_platform_id',
+        'Platform_name': 'Platform_title',
+        #'Platform_technology': 'Platform_technology',
+        'Platform_manufacturer': 'Platform_manufacturer',
+        #'Platform_supplementary_file': 'Platform_supplementary_file',
+
+        'External_sample_source_id':'Sample_geo_accession',
+        'Sample_name': 'Sample_title',
+        'Sample_organism': 'Sample_organism',
+        #'Specimen_type': 'Sample_source_name',
+        'Disease_status': 'Sample_source_name',
+        'Sample_data_link': 'Sample_supplementary_file',
+        'Sequencing_type': 'Sample_library_strategy',
+        'Sequencing_library': 'Sample_extracted_molecule',
+        'Sample_characteristics': 'Sample_characteristics',
+        'Biosample_id': 'Sample_biosample',
+        'SRA_id': 'Sample_srr',
+        'External_project_source_id': 'Series_project_id',
+        'Project_title': 'Project_title',
+        'Project_description': 'Project_abstract',
+        'Omics_type': 'Project_data_type',    
+        'Data_release_date': 'Project_submission'
+        #'Project_relevance': 'Project_relevance',
+
+        
+    }
+    #print("data.keys():", data.keys())
+    # Apply updates for each attribute
+    for attribute, data_key in attribute_data_mapping.items():
+        mask = table['Attribute'] == attribute
+        if mask.any():
+            table.loc[mask, 'Content'] = table.loc[mask, 'Content'].apply(lambda _: data[data_key])
+
+
+     # Add GardId
+    mask_gard = table['Attribute'] == 'GardId'
+    if mask_gard.any():
+        table.loc[mask_gard, 'Content'] = table.loc[mask_gard, 'Content'].apply(lambda _: [f'{gard_id}'])
+
+    # Add Hosting_repository
+    mask_rare = table['Attribute'] == 'Hosting_repository'
+    if mask_rare.any():
+        table.loc[mask_rare, 'Content'] = table.loc[mask_rare, 'Content'].apply(lambda _: ['GEO'])
+
+    # Add Project_type
+    mask_rare = table['Attribute'] == 'Project_type'
+    if mask_rare.any():
+        table.loc[mask_rare, 'Content'] = table.loc[mask_rare, 'Content'].apply(lambda _: ['Disease Characterization'])
+
+    # Add Condition_name
+    #print("gard_id: ", gard_id) # gard_id:  GARD:0004647
+    mask_condition_name = table['Attribute'] == 'Condition_name'
+    if mask_condition_name.any():
+        table.loc[mask_condition_name, 'Content'] = table.loc[mask_condition_name, 'Content'].apply(lambda _: [f'{condition_name}'])
+
+
+
+
+
+    """
+    # Ensure all rows in 'Content' are lists even if empty
+    # table['Content'] = table['Content'].apply(lambda x: x if isinstance(x, list) else [])
+
+    """
+    return table
+
+def save_table(folder_path, gse_id, table):
+    output_file = os.path.join(folder_path, f"{gse_id}_table.csv")
+    table.to_csv(output_file, index=False)
+
+
+def process_gse(gse_id, gard_id, table_template, disease_name_list, output_dir, session):
+    try:
+        print(f"Processing GSE ID: {gse_id} for GARD ID: {gard_id}")  # Log the GSE ID and GARD ID
+        gard_folder = create_output_folder(output_dir, gard_id)
+        gse_data = extract_gse_data(gse_id, session)
+        filled_table = fill_table_with_data(table_template, gse_data, gard_id, disease_name_list)
+        save_table(gard_folder, gse_id, filled_table)
+    except Exception as e:
+        print(f"Error processing GSE ID {gse_id} for GARD ID {gard_id}: {e}")
+        raise
+#***************************************************************************************
+# Main function for this .py file
+#***************************************************************************************
+def extract_to_table(input_file, table_template, disease_name_list, output_dir):
+    
+    gard_to_gse = load_json(input_file)
+    table_template = load_table_template(table_template)
+    session = get_requests_session()
+
+    with ThreadPoolExecutor(max_workers=8) as executor:
+        futures = []
+        for gard_id, gse_list in gard_to_gse.items():
+
+            for gse_id in gse_list:
+                futures.append(executor.submit(
+                    process_gse, gse_id, gard_id, table_template, disease_name_list, output_dir, session
+                ))
+        for future in tqdm(as_completed(futures), total=len(futures), desc = "Processing GSEs"):
+            future.result()
+    print("Extraction and table creation completed")
+    """
+    session = get_requests_session()
+    
+    base_url = f"https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE4303"
+    try:
+        response = session.get(base_url)
+        response.raise_for_status() # ensure we catch HTTP errors
+    except requests.exceptions.ConnectionError:
+        # Recreate session in case of session expiration
+        session = get_requests_session()
+        response = session.get(base_url)
+        response.raise_for_status()
+
+    
+    series_soup = BeautifulSoup(response.text, "html.parser")
+    platform_title, platform_manufacturer = extract_platform_content(series_soup, session)
+    print("platform_title")
+    for value in platform_title:
+        print(value)
+
+    print("platform_manufacturer")
+    for value in platform_manufacturer:
+        print(value)
+    
+    """
+    
+"""
+def extract_to_table(input_file, table_template, disease_name_list, output_dir):
+    gard_to_gse = load_json(input_file)
+    table_template = load_table_template(table_template)
+    session = get_requests_session() # create a single session
+
+    # Track progress for total GARD IDs
+    with tqdm(total=len(gard_to_gse), desc="Processing GARD IDs") as gard_bar:
+        # Iterate through each GARD ID and corresponding GSEs        
+        for gard_id, gse_list in gard_to_gse.items():
+            gard_folder = create_output_folder(output_dir, gard_id)
+            
+            # Track progress for each GSE list under the current GARD ID
+            with tqdm(total=len(gse_list), desc=f"{gard_id}", leave=False) as gse_bar:
+                for gse_id in gse_list:
+                    print(f"Processing {gse_id} for {gard_id}...")
+                    gse_data = extract_gse_data(gse_id)
+                    filled_table = fill_table_with_data(table_template, gse_data, gard_id, disease_name_list)
+                    save_table(gard_folder, gse_id, filled_table)
+                    gse_bar.update(1)
+
+            gard_bar.update(1)
+    print("Extraction and table creation completed.")
+"""
\ No newline at end of file
diff --git a/RDAS_RDOMICS/scripts/step5_generate_node_mappings.py b/RDAS_RDOMICS/scripts/step5_generate_node_mappings.py
new file mode 100644
index 0000000..3393ed4
--- /dev/null
+++ b/RDAS_RDOMICS/scripts/step5_generate_node_mappings.py
@@ -0,0 +1,949 @@
+"""
+Extract node and mapping files from the GSE tables
+
+"""
+import os
+import pandas as pd
+import traceback
+import ast
+
+
+##################
+# Platform node with platform id.
+##################
+def generate_platform_node(input_path, platform_table, output_path):
+    """
+    Extract Platform information, deduplicate, and assign unique Platform IDs.
+
+    Args:
+        input_path (str): Path to the folder containing CSV files organized in subfolders.
+        platform_table (pd.DataFrame): Existing platform table to check for duplicates.
+
+    Returns:
+        pd.DataFrame: Updated platform table with unique Platform IDs.
+    """
+
+    existing_platforms = set(
+        tuple(x) for x in platform_table[['Platform_name', 'Platform_manufacturer']].dropna().to_numpy()
+    )
+
+    #platform_name_set = set()
+    #platform_manufacturer_set = set()
+    
+    # Iterate through each subfolder
+    for subfolder in os.listdir(input_path):
+        subfolder_path = os.path.join(input_path, subfolder)
+        if not os.path.isdir(subfolder_path):
+            continue
+
+        # Iterate through each CSV file in the subfolder
+        for csv_file in os.listdir(subfolder_path):
+            #if not csv_file.endwith('.csv'):
+            #    continue
+            file_path = os.path.join(subfolder_path, csv_file)
+            df = pd.read_csv(file_path)
+
+            # Filter rows where Primary_category = 'Platform'
+            platform_rows = df[df['Primary_category'] == 'Platform']
+            # Check if the DataFrame has required data
+            if platform_rows.empty or 'Attribute' not in platform_rows.columns or 'Content' not in platform_rows.columns:
+                print(f"Skipping {csv_file}: Missing required data or empty DataFrame.")
+                continue
+
+            
+            try:
+                # Extract Platform_name and Platform_manufacturer rows
+                platform_name_row = platform_rows[platform_rows['Attribute'] == 'Platform_name']
+                platform_manufacturer_row = platform_rows[platform_rows['Attribute'] == 'Platform_manufacturer']
+
+                # Extract and normalize Platform_name
+                platform_name = None
+                if not platform_name_row.empty:
+                    content = platform_name_row['Content'].iloc[0]
+                    try:
+                        platform_name_list = ast.literal_eval(content)
+                        if isinstance(platform_name_list, list) and platform_name_list:
+                            platform_name = platform_name_list[0].strip() if platform_name_list[0] else None
+                    except (ValueError, SyntaxError):
+                        platform_name = None
+
+                # Extract and normalize Platform_manufacturer
+                platform_manufacturer = None
+                if not platform_manufacturer_row.empty:
+                    content = platform_manufacturer_row['Content'].iloc[0]
+                    try:
+                        platform_manufacturer_list = ast.literal_eval(content)
+                        if isinstance(platform_manufacturer_list, list) and platform_manufacturer_list:
+                            platform_manufacturer = platform_manufacturer_list[0].strip() if platform_manufacturer_list[0] else None
+                    except (ValueError, SyntaxError):
+                        platform_manufacturer = None
+
+                # Skip if both values are None
+                if platform_name is None and platform_manufacturer is None:
+                    print(f"Skipping {csv_file}: Both platform_name and platform_manufacturer are None.")
+                    continue
+
+                # Check for duplicates
+                if (platform_name, platform_manufacturer) in existing_platforms:
+                    continue
+
+                # Add to platform table and track the new combination
+                existing_platforms.add((platform_name, platform_manufacturer))
+                platform_table = pd.concat(
+                    [platform_table, pd.DataFrame([{
+                        'Platform_name': platform_name,
+                        'Platform_manufacturer': platform_manufacturer
+                    }])],
+                    ignore_index=True
+                )
+            except Exception as e:
+                print(f"Error processing {csv_file}: {e}")
+                traceback.print_exc()  # Add full traceback for debugging
+                print("Debugging platform_rows DataFrame:")
+                print(platform_rows['Attribute'], " ", platform_rows['Content'])
+
+    # Generate unique Platform IDs for the updated table
+    platform_table['Platform_id'] = [f"GEO-PLT-{str(i).zfill(5)}" for i in range(len(platform_table))]
+
+    # Save to CSV
+    platform_table.to_csv(os.path.join(output_path, 'platform_node.csv'), index=False)
+    return platform_table
+                
+
+##################
+# Experiment node with ids for mapping relationships
+##################
+def generate_experiment_node(input_path, platform_table, output_path):
+    # Initialize a list
+    experiment_data = []
+    # Track seen External_experiment_source_id values
+    seen_experiment_ids = set()
+
+    for subfolder in os.listdir(input_path):
+        subfolder_path = os.path.join(input_path, subfolder)
+        if not os.path.isdir(subfolder_path):
+            continue
+
+        for csv_file in os.listdir(subfolder_path):
+            file_path = os.path.join(subfolder_path, csv_file)
+            df = pd.read_csv(file_path)
+
+            try:
+                # Extract relevant rows for the Experiment node
+                relevant_attributes = [
+                    'Experiment_data_link', 'Omics_type', 'Sequencing_type', 'Sequencing_library',
+                    'External_experiment_source_id', 'External_project_source_id',
+                    'Platform_name', 'Platform_manufacturer'
+                ]
+                relevant_rows = df[df['Attribute'].isin(relevant_attributes)]
+
+                experiment_row = {}
+
+                # Extract values for relevant attributes
+                for attribute in relevant_attributes:
+                    attribute_row =relevant_rows[relevant_rows['Attribute'] == attribute]
+                    if not attribute_row.empty:
+                        # Extract the entire list from the Content column
+                        content_value = (
+                            eval(attribute_row['Content'].iloc[0])
+                            if isinstance(attribute_row['Content'].iloc[0], str) and attribute_row['Content'].iloc[0].startswith('[')
+                            else None
+                        )
+                        # Handle `[None]` in Content by converting it to None
+                        content_value = [x if x is not None else "" for x in content_value] if isinstance(content_value, list) else content_value
+                        experiment_row[attribute] = content_value
+                    else:
+                        experiment_row[attribute] = None  # Add None if the attribute is missing
+
+                # Skip if experiement already exists
+                External_experiment_source_id = experiment_row.get('External_experiment_source_id')
+                if isinstance(External_experiment_source_id, list):
+                    External_experiment_source_id = External_experiment_source_id[0] if External_experiment_source_id else None
+                if External_experiment_source_id in seen_experiment_ids:
+                    continue # Skip duplicate
+                seen_experiment_ids.add(External_experiment_source_id)
+
+
+                # Match Platform_name and Platform_manufacturer with platform_table
+                platform_name = experiment_row.get('Platform_name')
+                platform_manufacturer = experiment_row.get('Platform_manufacturer')
+
+                # Initialize platform_ids as an empty list
+                platform_ids = []
+
+                # Handle case where we have multiple platforms
+                if platform_name and isinstance(platform_name, list) and len(platform_name) > 0:
+                    # For each platform name, try to find a match
+                    for i, p_name in enumerate(platform_name):
+                        # Get corresponding manufacturer if available
+                        p_manufacturer = ""
+                        if platform_manufacturer and isinstance(platform_manufacturer, list) and i < len(platform_manufacturer):
+                            p_manufacturer = platform_manufacturer[i]
+                        
+                        # Look for a match in platform_table
+                        match = platform_table[
+                            (platform_table['Platform_name'].fillna("") == p_name) &
+                            (platform_table['Platform_manufacturer'].fillna("") == p_manufacturer)
+                        ]
+                        if not match.empty:
+                            platform_ids.append(match['Platform_id'].iloc[0])
+                else:
+                    # Handle non-list values (single string, None, etc.)
+                    p_name = platform_name if platform_name else ""
+                    p_manufacturer = platform_manufacturer if platform_manufacturer else ""
+                    
+                    # If they're strings but not lists, use them directly
+                    match = platform_table[
+                        (platform_table['Platform_name'].fillna("") == p_name) &
+                        (platform_table['Platform_manufacturer'].fillna("") == p_manufacturer)
+                    ]
+                    if not match.empty:
+                        platform_ids.append(match['Platform_id'].iloc[0])
+
+                # Add Platform_id to the row (as a list)
+                experiment_row['Platform_id'] = platform_ids if platform_ids else None
+                # Remove Platform_name and Platform_manufacturer
+                experiment_row.pop('Platform_name', None)
+                experiment_row.pop('Platform_manufacturer', None)
+
+                # Append the row to the experiment data
+                experiment_data.append(experiment_row)
+
+            except Exception as e:
+                print(f"Error processing {csv_file}: {e}")
+                traceback.print_exc()
+                print("Debugging relevant_rows DataFrame:")
+                print(relevant_rows)
+                continue
+
+    # Convert to DataFrame
+    experiment_df = pd.DataFrame(experiment_data)
+
+    # Generate unique Experiment_id
+    experiment_df['Experiment_id'] = [f"GEO-EXPT-{str(i).zfill(5)}" for i in range(len(experiment_df))]
+
+    # Save to CSV
+    output_file = os.path.join(output_path, 'experiment_node.csv')
+    experiment_df.to_csv(output_file, index=False)
+    print(f"Experiment node data saved to {output_file}.")
+    return experiment_df
+
+##################
+# Sample node and ids for mapping relationships
+##################
+def generate_sample_node(input_path, experiment_node_path, output_path):
+    # Load experiment_node.csv
+    experiment_node = pd.read_csv(experiment_node_path)
+
+    # Normalize External_experiment_source_id in experiment_node.csv
+    experiment_node['External_experiment_source_id'] = experiment_node['External_experiment_source_id'].apply(
+        lambda x: eval(x)[0] if isinstance(x, str) and x.startswith('[') else x
+    )
+
+
+    # Initialize a list to store sample data
+    sample_data = []
+    unique_samples = set() # Track unique External_sample_source_id
+    for subfolder in os.listdir(input_path):
+        subfolder_path = os.path.join(input_path, subfolder)
+        if not os.path.isdir(subfolder_path):
+            continue
+
+        for csv_file in os.listdir(subfolder_path):
+            file_path = os.path.join(subfolder_path, csv_file)
+            df = pd.read_csv(file_path)
+
+            try:
+                # Extract External_experiment_source_id
+                experiment_row = df[(df['Primary_category'] == 'Experiment') &
+                                    (df['Attribute'] == 'External_experiment_source_id')]
+                
+                external_experiment_id = eval(experiment_row['Content'].iloc[0])[0]
+                # Filter rows where Primary_category == 'Sample'
+                sample_rows = df[df['Primary_category'] == 'Sample']
+
+                # Determine the length of the External_sample_source_id list
+                external_sample_source_id_row = sample_rows[sample_rows['Attribute'] == 'External_sample_source_id']
+                if not external_sample_source_id_row.empty:
+                    external_sample_source_id_list = eval(external_sample_source_id_row['Content'].iloc[0])
+                    num_samples = len(external_sample_source_id_list)  # Length of the list
+                else:
+                    num_samples = 0  # Default to 0 if no External_sample_source_id is found
+
+
+                # Create a dictionary for each sample
+                sample_dict = {attribute: [] for attribute in sample_rows['Attribute'].unique()}
+                sample_dict['External_experiment_source_id'] = [external_experiment_id] * num_samples# Add the experiment ID
+
+                for _, row in sample_rows.iterrows():
+                    attribute = row['Attribute']
+                    content = (
+                        eval(row['Content'])
+                        if isinstance(row['Content'], str) and row['Content'].startswith('[')
+                        else []
+                    )
+
+                    # Handle None or empty values
+                    if not content:
+                        content = ["" for _ in range(num_samples)]
+                    sample_dict[attribute] = content
+                # Normalize lengths of all attributes
+                max_length = max([len(values) for values in sample_dict.values()])
+                for key in sample_dict:
+                    while len(sample_dict[key]) < max_length:
+                        sample_dict[key].append("")
+
+                # Add data to the sample_data list
+                for i in range(max_length):
+                    external_sample_id = sample_dict.get('External_sample_source_id', [])[i]
+                    if external_sample_id not in unique_samples:
+                        unique_samples.add(external_sample_id)
+                        sample_data.append({key: sample_dict[key][i] for key in sample_dict})
+
+            except Exception as e:
+                print(f"Error processing {csv_file}: {e}")
+                traceback.print_exc()
+                print("Debugging sample_rows DataFrame:")
+                print(sample_rows)
+                continue
+    
+    # Convert to DataFrame
+    sample_df = pd.DataFrame(sample_data)
+
+    # Add Platform_id and Experiment_id by mapping from experiment_node.csv
+    experiment_node['External_experiment_source_id'] = experiment_node['External_experiment_source_id'].fillna("").astype(str)
+    sample_df = sample_df.merge(
+        experiment_node[['External_experiment_source_id', 'Platform_id', 'Experiment_id']],
+        on='External_experiment_source_id',
+        how='left'
+    )
+
+
+    # Generate unique Sample_id
+    sample_df['Sample_id'] = [f"GEO-SAMPLE-{str(i).zfill(5)}" for i in range(len(sample_df))]
+
+    # Save to CSV
+    output_file = os.path.join(output_path, 'sample_node.csv')
+    sample_df.to_csv(output_file, index=False)
+    print(f"Sample node data saved to {output_file}.")
+    return sample_df
+
+##################
+# Project node and ids for mapping relationships
+#1. Use a dictionary project_map instead of a set.
+
+#2. Key it by External_project_source_id.
+
+#3.For each file:
+#   If the project is new, create a new entry with all info, and initialize a list of GardIds.
+#   If the project is already seen, check if the new GardId is not already in the list, and if not, append it.
+##################
+def generate_project_node(input_path, output_path):
+    # Dictionary to store unique projects with GardId as list
+    project_map = {}
+
+    for subfolder in os.listdir(input_path):
+        subfolder_path = os.path.join(input_path, subfolder)
+        if not os.path.isdir(subfolder_path):
+            continue
+
+        for csv_file in os.listdir(subfolder_path):
+            if not csv_file.endswith('.csv'):
+                continue
+
+            file_path = os.path.join(subfolder_path, csv_file)
+            df = pd.read_csv(file_path)
+
+            try:
+                # Extract project-related rows
+                project_rows = df[df['Primary_category'] == 'Project']
+                if project_rows.empty:
+                    print(f"No Project data in {csv_file}. Skipping...")
+                    continue
+
+                # Create a dictionary for the project
+                project_dict = {}
+                for _, row in project_rows.iterrows():
+                    attribute = row['Attribute']
+                    content = row['Content']
+
+                    # Handle empty or NaN content
+                    if isinstance(content, str) and content.startswith('['):
+                        try:
+                            content_list = eval(content)
+                            content = content_list[0] if content_list else ""
+                        except Exception:
+                            content = ""
+                    else:
+                        content = ""
+                    project_dict[attribute] = content
+                
+                external_project_id = project_dict.get('External_project_source_id', "")
+                if not external_project_id:
+                    print(f"Missing External_project_source_id in {csv_file}. Skipping...")
+                    continue
+
+                # Extract GardId from Condition
+                gard_id = None
+                condition_row = df[(df['Primary_category'] == 'Condition') & (df['Attribute'] == 'GardId')]
+                if not condition_row.empty:
+                    gard_content = condition_row['Content'].iloc[0]
+                    if isinstance(gard_content, str) and gard_content.startswith('['):
+                        gard_list = eval(gard_content)
+                        gard_id = gard_list[0] if gard_list else None
+
+                #Add or update project
+                if external_project_id in project_map:
+                    if gard_id and gard_id not in project_map[external_project_id]['GardId']:
+                        project_map[external_project_id]['GardId'].append(gard_id)
+                else:
+                    project_dict['GardId'] = [gard_id] if gard_id else []
+                    project_map[external_project_id] = project_dict
+
+
+            except Exception as e:
+                print(f"Error processing {csv_file}: {e}")
+                traceback.print_exc()
+                print("Debugging project_rows DataFrame:")
+                print(project_rows)
+                continue
+
+    # Convert to DataFrame
+    project_data = list(project_map.values())
+    project_df = pd.DataFrame(project_data)
+
+    # Generate unique Project_id
+    project_df['Project_id'] = [f"GEO-PROJ-{str(i).zfill(5)}" for i in range(len(project_df))]
+
+    # Save to CSV
+    output_file = os.path.join(output_path, 'project_node.csv')
+    project_df.to_csv(output_file, index=False)
+    print(f"Project node data saved to {output_file}.")
+    return project_df
+    
+##################
+# Update experiment_node.csv
+##################
+def update_experiment_node(experiment_node_path, project_node_path, output_path):
+    try:
+        # Read experiment_node.csv and project_node.csv
+        experiment_node = pd.read_csv(experiment_node_path)
+        project_node = pd.read_csv(project_node_path)
+        
+
+        # Check if required columns exist
+        if 'External_project_source_id' not in experiment_node.columns:
+            raise ValueError("Experiment table must contain 'External_project_source_id' column.")
+        if 'External_project_source_id' not in project_node.columns or 'Project_id' not in project_node.columns:
+            raise ValueError("Project table must contain 'External_project_source_id' and 'Project_id' columns.")
+
+        # Normalize External_project_source_id in experiment_node
+        def normalize_external_project_id(value):
+            if isinstance(value, str) and value.startswith('['):
+                try:
+                    value_list = eval(value)
+                    return value_list[0] if value_list else ""
+                except Exception as e:
+                    print(f"Error normalizing value: {value}. Exception: {e}")
+                    return ""
+            return value
+
+        experiment_node['External_project_source_id'] = experiment_node['External_project_source_id'].apply(
+            normalize_external_project_id
+        )
+
+        # Normalize External_project_source_id in project_node
+        project_node['External_project_source_id'] = project_node['External_project_source_id'].astype(str)
+
+
+        # Simplify Sequencing_type and Sequencing_library
+        for column in ['Sequencing_type', 'Sequencing_library']:
+            if column in experiment_node.columns:
+                experiment_node[column] = experiment_node[column].apply(
+                    lambda x: simplify_list_column(x)
+                )
+        # Remove any existing Project_id_x or Project_id_y columns to avoid confusion
+        #if 'Project_id_x' in experiment_node.columns:
+        #    experiment_node.drop(columns=['Project_id_x'], inplace=True)
+        #if 'Project_id_y' in experiment_node.columns:
+        #    experiment_node.drop(columns=['Project_id_y'], inplace=True)
+        # Merge Project_id into experiment_node
+        experiment_node = experiment_node.merge(
+            project_node[['External_project_source_id', 'Project_id']],
+            on='External_project_source_id',
+            how='left'
+        )
+
+        # Save the updated experiment_node.csv
+        output_file = os.path.join(output_path, 'experiment_node.csv')
+        experiment_node.to_csv(output_file, index=False)
+        print(f"Updated experiment_node.csv saved to {output_file}.")
+        return experiment_node
+
+    except Exception as e:
+        print(f"Error updating experiment_node.csv with Project_id: {e}")
+        traceback.print_exc()
+
+# Helper function to simplify list columns
+def simplify_list_column(value):
+    try:
+        if isinstance(value, str) and value.startswith('['):
+            value_list = eval(value)
+            # Deduplicate elements and convert back to a string
+            unique_values = sorted(set(value_list))
+            if len(unique_values) == 1:
+                return unique_values[0]  # If all elements are the same, keep one
+            return str(unique_values)  # If different, keep unique elements as a list
+        return value
+    except Exception as e:
+        print(f"Error simplifying column value: {value}. Exception: {e}")
+        return value
+
+##################
+# Generate Condition node
+##################
+def generate_condition_node(input_path, output_path):
+    try:
+        # Initialize a list to store condition data
+        condition_data = []
+        unique_conditions = set()  # Track unique GardId values to avoid duplicates
+
+        for subfolder in os.listdir(input_path):
+            subfolder_path = os.path.join(input_path, subfolder)
+            if not os.path.isdir(subfolder_path):
+                continue
+
+            for csv_file in os.listdir(subfolder_path):
+                if not csv_file.endswith('.csv'):
+                    continue
+
+                file_path = os.path.join(subfolder_path, csv_file)
+                df = pd.read_csv(file_path)
+
+                try:
+                    # Extract condition-related rows
+                    condition_rows = df[df['Primary_category'] == 'Condition']
+                    if condition_rows.empty:
+                        print(f"No Condition data in {csv_file}. Skipping...")
+                        continue
+
+                    # Create a dictionary for each condition
+                    condition_dict = {}
+                    for _, row in condition_rows.iterrows():
+                        attribute = row['Attribute']
+                        content = row['Content']
+
+                        # Handle list-like content
+                        if isinstance(content, str) and content.startswith('['):
+                            try:
+                                content_list = eval(content)
+                                content = content_list[0] if content_list else ""
+                            except Exception as e:
+                                print(f"Error processing content: {content}. Exception: {e}")
+                                content = ""
+
+                        condition_dict[attribute] = content
+
+                    # Ensure GardId is present and unique
+                    gard_id = condition_dict.get('GardId', "")
+                    if gard_id in unique_conditions:
+                        print(f"Duplicate GardId '{gard_id}' found in {csv_file}. Skipping...")
+                        continue
+
+                    # Add the condition to the data and mark it as processed
+                    unique_conditions.add(gard_id)
+                    condition_data.append(condition_dict)
+
+                except Exception as e:
+                    print(f"Error processing {csv_file}: {e}")
+                    traceback.print_exc()
+                    print("Debugging condition_rows DataFrame:")
+                    print(condition_rows)
+                    
+
+        # Convert to DataFrame
+        condition_df = pd.DataFrame(condition_data)
+
+        # Generate unique Condition_id
+        #condition_df['Condition_id'] = [f"GEO-COND-{str(i).zfill(5)}" for i in range(len(condition_df))]
+
+        # Save to CSV
+        output_file = os.path.join(output_path, 'condition_node.csv')
+        condition_df.to_csv(output_file, index=False)
+        print(f"Condition node data saved to {output_file}.")
+        return condition_df
+
+    except Exception as e:
+        print(f"Error generating condition_node.csv: {e}")
+        traceback.print_exc()
+
+##################
+# Generate publication node
+##################
+def generate_publication_node(input_path, project_node_path, output_path):
+    try:
+        # Initialize a list to store publication data
+        publication_data = []
+        unique_pubmed_ids = set()  # Track unique Pubmed_id to avoid duplicates
+
+        # Read project node data
+        project_node = pd.read_csv(project_node_path)
+
+        for subfolder in os.listdir(input_path):
+            subfolder_path = os.path.join(input_path, subfolder)
+            if not os.path.isdir(subfolder_path):
+                continue
+
+            for csv_file in os.listdir(subfolder_path):
+                if not csv_file.endswith('.csv'):
+                    continue
+
+                file_path = os.path.join(subfolder_path, csv_file)
+                df = pd.read_csv(file_path)
+
+                try:
+                    # Extract publication-related rows
+                    publication_rows = df[df['Primary_category'] == 'Publication']
+                    project_row = df[(df['Primary_category'] == 'Project') & (df['Attribute'] == 'External_project_source_id')]
+
+                    if publication_rows.empty or project_row.empty:
+                        print(f"No Publication or External_project_source_id data in {csv_file}. Skipping...")
+                        continue
+
+                    # Extract External_project_source_id
+                    external_project_id = project_row['Content'].iloc[0]
+                    if isinstance(external_project_id, str) and external_project_id.startswith('['):
+                        try:
+                            external_project_id_list = eval(external_project_id)
+                            external_project_id = external_project_id_list[0] if external_project_id_list else ""
+                        except Exception as e:
+                            print(f"Error processing External_project_source_id: {external_project_id}. Exception: {e}")
+                            external_project_id = ""
+
+                    # Create a dictionary for each publication
+                    publication_dict = {}
+                    for _, row in publication_rows.iterrows():
+                        attribute = row['Attribute']
+                        content = row['Content']
+
+                        # Handle list-like content
+                        if isinstance(content, str) and content.startswith('['):
+                            try:
+                                content_list = eval(content)
+                                content = content_list[0] if content_list else ""
+                            except Exception as e:
+                                print(f"Error processing content: {content}. Exception: {e}")
+                                content = ""
+
+                        publication_dict[attribute] = content
+
+                    # Add External_project_source_id to the publication dictionary
+                    publication_dict['External_project_source_id'] = external_project_id
+
+                    # Exclude empty Pubmed_id rows
+                    pubmed_id = publication_dict.get('Pubmed_id', "")
+                    if not pubmed_id:
+                        continue
+
+                    # Handle multiple Pubmed_id and Project_id
+                    pubmed_ids = [x.strip() for x in pubmed_id.split(",")]
+                    if len(pubmed_ids) > 1:
+                        for pid in pubmed_ids:
+                            if pid in unique_pubmed_ids:
+                                continue
+                            unique_pubmed_ids.add(pid)
+                            publication_data.append({
+                                'Pubmed_id': pid,
+                                'Authors': publication_dict.get('Authors', ""),
+                                'Title': publication_dict.get('Title', ""),
+                                'Journal': publication_dict.get('Journal', ""),
+                                'Abstract': publication_dict.get('Abstract', ""),
+                                'External_project_source_id': [external_project_id]
+                            })
+                    else:
+                        if pubmed_ids[0] in unique_pubmed_ids:
+                            # Update existing entry's Project_id list
+                            for pub_entry in publication_data:
+                                if pub_entry['Pubmed_id'] == pubmed_ids[0]:
+                                    pub_entry['External_project_source_id'].append(external_project_id)
+                                    break
+                        else:
+                            unique_pubmed_ids.add(pubmed_ids[0])
+                            publication_data.append({
+                                'Pubmed_id': pubmed_ids[0],
+                                'Authors': publication_dict.get('Authors', ""),
+                                'Title': publication_dict.get('Title', ""),
+                                'Journal': publication_dict.get('Journal', ""),
+                                'Abstract': publication_dict.get('Abstract', ""),
+                                'External_project_source_id': [external_project_id]
+                            })
+
+                except Exception as e:
+                    print(f"Error processing {csv_file}: {e}")
+                    traceback.print_exc()
+                    print("Debugging publication_rows DataFrame:")
+                    print(publication_rows)
+                    continue
+
+        # Convert to DataFrame
+        publication_df = pd.DataFrame(publication_data)
+        
+        # Explode External_project_source_id to handle lists
+        publication_df = publication_df.explode('External_project_source_id')
+
+        # Ensure all External_project_source_id are strings
+        publication_df['External_project_source_id'] = publication_df['External_project_source_id'].astype(str)
+
+        # Merge with project_node to get Project_id
+        publication_df = publication_df.merge(
+            project_node[['External_project_source_id', 'Project_id']],
+            how='left',
+            on='External_project_source_id'
+        )
+        # Group by Pubmed_id and combine Project_id lists
+        publication_df = publication_df.groupby('Pubmed_id', as_index=False).agg({
+            'Authors': 'first',
+            'Title': 'first',
+            'Journal': 'first',
+            'Abstract': 'first',
+            'Project_id': lambda x: sorted(set(str(i) for i in x if pd.notna(i)))
+        })
+
+        # Drop External_project_source_id after merging
+        #publication_df = publication_df.drop(columns=['External_project_source_id'])
+
+        # Combine Project_id lists into unique, sorted lists
+        #publication_df['Project_id'] = publication_df['Project_id'].apply(lambda x: sorted(set(x)) if isinstance(x, list) else x)
+
+        # Generate unique Publication_id
+        #publication_df['Publication_id'] = [f"PUB-{str(i).zfill(5)}" for i in range(len(publication_df))]
+
+        # Save to CSV
+        output_file = os.path.join(output_path, 'publication_node.csv')
+        publication_df.to_csv(output_file, index=False)
+        print(f"Publication node data saved to {output_file}.")
+        return publication_df
+
+    except Exception as e:
+        print(f"Error generating publication_node.csv: {e}")
+        traceback.print_exc()
+
+
+##################
+# Generate mapping relationships csv
+##################
+def generate_mapping_relationships(experiment_node_path, sample_node_path, project_node_path, publication_node_path, output_path):
+    try:
+        
+        # Read the experiment table
+        experiment_node = pd.read_csv(experiment_node_path)
+
+        # Check if the required columns exist in experiment_node
+        if 'Experiment_id' not in experiment_node.columns or 'Platform_id' not in experiment_node.columns:
+            raise ValueError("Experiment table must contain 'Experiment_id' and 'Platform_id' columns.")
+
+        # Extract the Experiment-Platform mapping
+        experiment_platform_mapping = []
+        
+        for _, row in experiment_node.iterrows():
+            experiment_id = row['Experiment_id']
+            platform_ids = row['Platform_id']
+            
+            # Parse the Platform_id column which might be stored as a string representation of a list
+            if isinstance(platform_ids, str):
+                try:
+                    # This handles cases like "[id1, id2, id3]"
+                    platform_ids = ast.literal_eval(platform_ids)
+                except (ValueError, SyntaxError):
+                    # If it's not a valid list representation, treat as a single value
+                    platform_ids = [platform_ids] if pd.notna(platform_ids) else []
+            elif not isinstance(platform_ids, list):
+                # Handle non-string, non-list values
+                platform_ids = [platform_ids] if pd.notna(platform_ids) else []
+            
+            # Create a mapping entry for each Platform_id
+            for platform_id in platform_ids:
+                if pd.notna(platform_id) and platform_id != "":  # Skip empty or NaN values
+                    experiment_platform_mapping.append({
+                        'Experiment_id': experiment_id,
+                        'Platform_id': platform_id
+                    })
+        
+        # Convert to DataFrame
+        experiment_platform_mapping = pd.DataFrame(experiment_platform_mapping)
+        
+        # Save the Experiment-Platform mapping
+        experiment_platform_file = os.path.join(output_path, 'experiment_platform_mapping.csv')
+        experiment_platform_mapping.to_csv(experiment_platform_file, index=False)
+        print(f"Experiment-Platform mapping saved to {experiment_platform_file}.")
+
+        # Read the sample table
+        sample_node = pd.read_csv(sample_node_path)
+
+        # Check if the required columns exist in sample_node
+        if 'Sample_id' not in sample_node.columns or 'Experiment_id' not in sample_node.columns or 'Platform_id' not in sample_node.columns:
+            raise ValueError("Sample table must contain 'Sample_id', 'Experiment_id', and 'Platform_id' columns.")
+
+        # Extract the Sample-Experiment mapping
+        sample_experiment_mapping = sample_node[['Sample_id', 'Experiment_id']].dropna(subset=['Sample_id', 'Experiment_id'])
+
+        # Save the Sample-Experiment mapping
+        sample_experiment_file = os.path.join(output_path, 'sample_experiment_mapping.csv')
+        sample_experiment_mapping.to_csv(sample_experiment_file, index=False)
+        print(f"Sample-Experiment mapping saved to {sample_experiment_file}.")
+
+        # Extract the Sample-Platform mapping
+        sample_platform_mapping = sample_node[['Sample_id', 'Platform_id']].dropna(subset=['Sample_id', 'Platform_id'])
+
+        # Save the Sample-Platform mapping
+        sample_platform_file = os.path.join(output_path, 'sample_platform_mapping.csv')
+        sample_platform_mapping.to_csv(sample_platform_file, index=False)
+        print(f"Sample-Platform mapping saved to {sample_platform_file}.")
+        
+
+        # Read the project table
+        project_node = pd.read_csv(project_node_path)
+
+        # Check if the required columns exist in project_node
+        if 'GardId' not in project_node.columns or 'Project_id' not in project_node.columns:
+            raise ValueError("Project table must contain 'GardId' and 'Project_id' columns.")
+
+        # Extract the Condition-Project mapping
+        #condition_project_mapping = project_node[['GardId', 'Project_id']].dropna(subset=['GardId', 'Project_id'])
+        # Handle GardId as a list by creating a row for each GardId-Project_id pair
+        condition_project_mapping = []
+        for _, row in project_node.iterrows():
+            project_id = row['Project_id']
+            gard_ids = row['GardId']
+            
+            # Parse the GardId column which is stored as a string representation of a list
+            if isinstance(gard_ids, str):
+                try:
+                    # This handles cases like "[123, 456]" or "[]"
+                    gard_ids = ast.literal_eval(gard_ids)
+                except (ValueError, SyntaxError):
+                    # If it's not a valid list representation, treat as a single value
+                    gard_ids = [gard_ids] if pd.notna(gard_ids) else []
+            elif not isinstance(gard_ids, list):
+                # Handle non-string, non-list values (like a single integer)
+                gard_ids = [gard_ids] if pd.notna(gard_ids) else []
+                
+            # Create a mapping entry for each GardId
+            for gard_id in gard_ids:
+                if pd.notna(gard_id) and gard_id != "":  # Skip empty or NaN values
+                    condition_project_mapping.append({
+                        'GardId': gard_id,
+                        'Project_id': project_id
+                    })
+        # Convert to DataFrame
+        condition_project_mapping = pd.DataFrame(condition_project_mapping)
+
+        # Save the Condition-Project mapping
+        condition_project_file = os.path.join(output_path, 'condition_project_mapping.csv')
+        condition_project_mapping.to_csv(condition_project_file, index=False)
+        print(f"Condition-Project mapping saved to {condition_project_file}.")
+        
+        experiment_node = pd.read_csv(experiment_node_path)
+
+        # Extract the Project-Experiment mapping
+        project_experiment_mapping = experiment_node[['Project_id', 'Experiment_id']].dropna(subset=['Project_id', 'Experiment_id'])
+
+        # Save the Project-Experiment mapping
+        project_experiment_file = os.path.join(output_path, 'project_experiment_mapping.csv')
+        project_experiment_mapping.to_csv(project_experiment_file, index=False)
+        print(f"Project-Experiment mapping saved to {project_experiment_file}.")
+        
+
+
+        # Read the publication table
+        publication_node = pd.read_csv(publication_node_path)
+
+        # Check if the required columns exist in publication_node
+        if 'Pubmed_id' not in publication_node.columns or 'Project_id' not in publication_node.columns:
+            raise ValueError("Publication table must contain 'Pubmed_id' and 'Project_id' columns.")
+
+        # Expand Project_id lists to 1-to-1 mapping
+        publication_project_mapping = []
+        for _, row in publication_node.iterrows():
+            pubmed_id = row['Pubmed_id']
+            project_ids = eval(row['Project_id']) if isinstance(row['Project_id'], str) else []
+            for project_id in project_ids:
+                publication_project_mapping.append({'Pubmed_id': pubmed_id, 'Project_id': project_id})
+
+        # Convert to DataFrame
+        publication_project_df = pd.DataFrame(publication_project_mapping)
+
+        # Save the Publication-Project mapping
+        publication_project_file = os.path.join(output_path, 'publication_project_mapping.csv')
+        publication_project_df.to_csv(publication_project_file, index=False)
+        print(f"Publication-Project mapping saved to {publication_project_file}.")
+
+
+
+
+    except Exception as e:
+        print(f"Error generating mapping relationships: {e}")
+        traceback.print_exc()
+
+
+
+     
+
+
+
+
+# Total tables: 2675
+def count_total_files(input_path):
+    count = 0
+    for subfolder in os.listdir(input_path):
+        subfolder_path = os.path.join(input_path, subfolder)
+        if not os.path.isdir(subfolder_path):
+            continue
+
+        for csv_file in os.listdir(subfolder_path):
+            file_path = os.path.join(subfolder_path, csv_file)
+            count += 1
+    print("Total tables:", count)
+    
+
+
+
+
+# Main processing function
+def process_all_nodes(input_path, output_path):
+    os.makedirs(output_path, exist_ok=True)
+    
+    # Generate Platform node
+    platform_table = pd.DataFrame(columns=['Platform_name', 'Platform_manufacturer'])
+    platform_table = generate_platform_node(input_path, platform_table, output_path)
+    
+    # Generate Experiment node
+    platform_table_path = os.path.join(output_path, 'platform_node.csv')
+    platform_table = pd.read_csv(platform_table_path)
+    generate_experiment_node(input_path, platform_table, output_path)
+
+    # Generate Sample node
+    experiment_node_path = os.path.join(output_path, 'experiment_node.csv')
+    generate_sample_node(input_path, experiment_node_path, output_path)
+
+    # Generate Project node
+    generate_project_node(input_path, output_path)
+
+    # Updating the Experiment node & get Project-Experiemtn mapping
+    # 1.Replace External_project_source_id with Project_id from Project node. 2.Shortening the list of sequencing type and library by deduplicates.
+    project_node_path = os.path.join(output_path, 'project_node.csv')
+    update_experiment_node(experiment_node_path, project_node_path, output_path)
+
+    # Generate Condition node
+    generate_condition_node(input_path, output_path)
+
+    # Generate Publication node & Publication-Project mapping
+    generate_publication_node(input_path, project_node_path, output_path) 
+    sample_node_path = os.path.join(output_path, 'sample_node.csv')
+    publication_node_path = os.path.join(output_path, 'publication_node.csv')
+
+    generate_mapping_relationships(experiment_node_path, sample_node_path, project_node_path, publication_node_path, output_path)
+    # Node cleaning
+
+    print(f"All nodes and mappings generated successfully in {output_path}.")
+    
diff --git a/RDAS_RDOMICS/scripts/step6_import_to_neo4j.py b/RDAS_RDOMICS/scripts/step6_import_to_neo4j.py
new file mode 100644
index 0000000..5776951
--- /dev/null
+++ b/RDAS_RDOMICS/scripts/step6_import_to_neo4j.py
@@ -0,0 +1,483 @@
+import os
+import pandas as pd
+import json
+import pickle
+from neo4j import GraphDatabase
+import traceback
+import ast
+
+def process_import(csv_path, json_path):
+    """
+    Main processing function to transform CSV to JSON and import data into Neo4j.
+    """
+    neo4j_uri = os.environ.get("NEO4J_URI")
+    neo4j_user = os.environ.get("NEO4J_USER")
+    neo4j_password = os.environ.get("NEO4J_PASSWORD")
+    if not all([neo4j_uri, neo4j_user, neo4j_password]):
+        raise ValueError("Set NEO4J_URI, NEO4J_USER, and NEO4J_PASSWORD before running this step.")
+
+    try:
+        # Step 1: Transform all CSV files to JSON
+        #to_json(csv_path, json_path)
+
+        # Step 2: Import data into Neo4j
+        import_to_memgraph(json_path, neo4j_uri, neo4j_user, neo4j_password)
+
+    except Exception as e:
+        print(f"Error in process_import: {e}")
+        raise
+
+SCHEMA = {
+    "publication_node.csv": "Pubmed_id",
+    "project_node.csv": "Project_id",
+    "experiment_node.csv": "Experiment_id",
+    "sample_node.csv": "Sample_id",
+    "platform_node.csv": "Platform_id",
+    "condition_node.csv": "GardId"
+}
+
+def to_json(csv_path, json_path):
+    """
+    Convert all CSV files under 'csv_path' to JSON and save them in 'json_path'.
+    Handle node files and mapping files appropriately.
+    """
+    try:
+        os.makedirs(json_path, exist_ok=True)
+
+        for file_name in os.listdir(csv_path):
+            if file_name.endswith('.csv'):
+                csv_file = os.path.join(csv_path, file_name)
+                json_file = os.path.join(json_path, file_name.replace('.csv', '.json'))
+
+                # Check if the file is a mapping file
+                if "mapping" in file_name:
+                    # Transform mapping file to include 'start' and 'end'  
+                    # Mapping files don't require primary keys
+                    df = pd.read_csv(csv_file)
+                    mapping_data = []
+
+                    if "sample_platform_mapping" in file_name:
+                        for _, row in df.iterrows():
+                            sample_id = row[0]  # First column is Sample_id
+                            platform_ids = row[1]  # Second column is Platform_id(s)
+                            
+                            # Parse the platform_ids if it's a string representation of a list
+                            if isinstance(platform_ids, str) and platform_ids.startswith('[') and platform_ids.endswith(']'):
+                                try:
+                                    platform_ids = ast.literal_eval(platform_ids)
+                                except:
+                                    platform_ids = [platform_ids]
+                            elif not isinstance(platform_ids, list):
+                                platform_ids = [platform_ids]
+                            
+                            # Create a mapping entry for each platform ID
+                            for platform_id in platform_ids:
+                                mapping_data.append({
+                                    "start": {"label": "Sample", "key": "Sample_id", "value": sample_id},
+                                    "end": {"label": "Platform", "key": "Platform_id", "value": platform_id}
+                                })
+                    elif "condition_project_mapping" in file_name:
+                        for _, row in df.iterrows():
+                            mapping_data.append({
+                                "start": {"label": "Condition", "key": "GardId", "value": row["GardId"] },
+                                "end": { "label": "Project", "key": "Project_id", "value": row["Project_id"] }
+                            })
+                    elif "publication_project_mapping" in file_name:
+                        for _, row in df.iterrows():
+                            mapping_data.append({
+                                "start": {"label": "Publication", "key":"Pubmed_id", "value": row["Pubmed_id"]},
+                                "end": {"label": "Project", "key": "Project_id", "value": row["Project_id"]}
+                            })
+                    elif "project_experiment_mapping" in file_name:
+                        for _, row in df.iterrows():
+                            mapping_data.append({
+                                "start": {"label": "Project", "key": "Project_id", "value": row["Project_id"]},
+                                "end": {"label": "Experiment", "key": "Experiment_id", "value": row["Experiment_id"]}
+                            })
+                    elif "experiment_platform_mapping" in file_name:
+                        for _, row in df.iterrows():
+                            mapping_data.append({
+                                "start": {"label": "Experiment", "key": "Experiment_id", "value": row["Experiment_id"]},
+                                "end": {"label": "Platform", "key": "Platform_id", "value": row["Platform_id"]}
+                            })
+                    elif "sample_experiment_mapping" in file_name:
+                        for _, row in df.iterrows():
+                            mapping_data.append({
+                                "start": {"label": "Sample", "key": "Sample_id", "value": row["Sample_id"]},
+                                "end": {"label": "Experiment", "key": "Experiment_id", "value": row["Experiment_id"]},
+                            })
+                    else:
+                        # Generic handling for other mapping files
+                        for _, row in df.iterrows():
+                            # Assume first column is start and second is end
+                            start_id = row.iloc[0]
+                            end_id = row.iloc[1]
+                            
+                            # Determine labels and keys from filename
+                            parts = file_name.replace('_mapping.csv', '').split('_')
+                            if len(parts) >= 2:
+                                start_label = parts[0].capitalize()
+                                end_label = parts[1].capitalize()
+                                
+                                # Determine keys based on labels
+                                start_key = f"{start_label}_id"
+                                end_key = f"{end_label}_id"
+                                
+                                mapping_data.append({
+                                    "start": {"label": start_label, "key": start_key, "value": start_id},
+                                    "end": {"label": end_label, "key": end_key, "value": end_id}
+                                })
+
+                    with open(json_file, "w") as f:
+                        json.dump(mapping_data, f, indent=4)
+
+                else:
+                    # Node files require primary keys
+                    primary_key = SCHEMA.get(file_name)
+                    if primary_key is None:
+                        raise ValueError(f"Primary key not defined for {file_name}")
+
+                    # Read CSV
+                    df = pd.read_csv(csv_file)
+
+                    # Ensure primary key exists
+                    if primary_key not in df.columns:
+                        raise ValueError(f"Primary key '{primary_key}' not found in {file_name}")
+
+                    # Convert to JSON
+                    df.to_json(json_file, orient='records', indent=4)
+
+                print(f"Converted {file_name} to JSON at {json_file}")
+
+    except Exception as e:
+        print(f"Error in to_json: {e}")
+        raise
+
+def create_node(session, file_path, batch_size=500, checkpoint_file=None):
+    """
+    Import nodes from a JSON file into Memgraph using batch transactions with checkpointing.
+    """
+    try:
+        # Load the JSON file
+        with open(file_path, 'r') as f:
+            nodes = json.load(f)
+
+        # Determine the label for the nodes based on the file name
+        label = os.path.basename(file_path).replace('_node.json', '').capitalize()
+        print(f"  -> Importing nodes with label: {label} from {file_path}")
+        
+        # Initialize checkpoint data
+        start_index = 0
+        checkpoint_path = checkpoint_file or f"{file_path}.checkpoint"
+        
+        # Check if checkpoint exists and load it
+        if os.path.exists(checkpoint_path):
+            try:
+                with open(checkpoint_path, 'rb') as cp:
+                    checkpoint_data = pickle.load(cp)
+                    start_index = checkpoint_data.get('last_processed_index', 0) + 1
+                    print(f"  -> Resuming from checkpoint at index {start_index}")
+            except Exception as e:
+                print(f"  -> Error loading checkpoint, starting from beginning: {e}")
+                start_index = 0
+
+        # Process nodes in batches
+        total_nodes = len(nodes)
+        for i in range(start_index, total_nodes, batch_size):
+            # Create a batch of nodes
+            batch = nodes[i:min(i+batch_size, total_nodes)]
+            
+            # Use an explicit transaction for the batch
+            with session.begin_transaction() as tx:
+                for node in batch:
+                    cypher_query = f"""
+                    CREATE (n:{label})
+                    SET n = $properties
+                    """
+                    tx.run(cypher_query, properties=node)
+                
+                # Commit the transaction for this batch
+                tx.commit()
+            
+            # Save checkpoint after each batch
+            with open(checkpoint_path, 'wb') as cp:
+                pickle.dump({'last_processed_index': min(i+batch_size, total_nodes)-1}, cp)
+            
+            # Log progress
+            print(f"    -> Imported {min(i+batch_size, total_nodes)}/{total_nodes} nodes for label {label}")
+        
+        # Remove checkpoint file when done
+        if os.path.exists(checkpoint_path):
+            os.remove(checkpoint_path)
+            
+        print(f"  -> Finished importing nodes for label {label}")
+
+    except Exception as e:
+        print(f"Error in create_node for {file_path}: {e}")
+        traceback.print_exc()    
+        raise
+
+def create_relationships(session, file_path, batch_size=500, checkpoint_file=None):
+    """
+    Import relationships from a JSON file into Memgraph using batch transactions with checkpointing.
+    """
+    try:
+        # Load the JSON file
+        with open(file_path, 'r') as f:
+            relationships = json.load(f)
+
+        # Determine the relationship type based on the file name
+        relationship_type = os.path.basename(file_path).replace('_mapping.json', '').upper()
+        print(f"  -> Importing relationships of type: {relationship_type} from {file_path}")
+        
+        # Initialize checkpoint data
+        start_index = 0
+        checkpoint_path = checkpoint_file or f"{file_path}.checkpoint"
+        
+        # Check if checkpoint exists and load it
+        if os.path.exists(checkpoint_path):
+            try:
+                with open(checkpoint_path, 'rb') as cp:
+                    checkpoint_data = pickle.load(cp)
+                    start_index = checkpoint_data.get('last_processed_index', 0) + 1
+                    print(f"  -> Resuming from checkpoint at index {start_index}")
+            except Exception as e:
+                print(f"  -> Error loading checkpoint, starting from beginning: {e}")
+                start_index = 0
+
+        # Verify current count in database
+        with session.begin_transaction() as tx:
+            count_query = f"""
+            MATCH ()-[r:{relationship_type}]->() 
+            RETURN count(r) as rel_count
+            """
+            result = tx.run(count_query)
+            current_count = result.single()["rel_count"]
+            print(f"  -> Current count of {relationship_type} relationships in database: {current_count}")
+
+        # Process relationships in batches
+        total_rels = len(relationships)
+        successful_imports = 0
+        
+        for i in range(start_index, total_rels, batch_size):
+            # Create a batch of relationships
+            batch = relationships[i:min(i+batch_size, total_rels)]
+            batch_success = 0
+            
+            # Use an explicit transaction for the batch
+            with session.begin_transaction() as tx:
+                for rel in batch:
+                    # Validate the structure of each relationship
+                    if not rel.get('start') or not rel.get('end'):
+                        print(f"  -> Skipping invalid relationship in {file_path}: {rel}")
+                        continue
+
+                    # Extract details for the relationship
+                    start_label = rel['start']['label']
+                    start_key = rel['start']['key']
+                    start_value = rel['start']['value']
+
+                    end_label = rel['end']['label']
+                    end_key = rel['end']['key']
+                    end_value = rel['end']['value']
+                    
+                    # Handle case where value is a list - extract the first element
+                    if isinstance(start_value, list) and len(start_value) > 0:
+                        start_value = start_value[0]
+                    if isinstance(end_value, list) and len(end_value) > 0:
+                        end_value = end_value[0]
+                    
+                    # Handle stringified list case
+                    if isinstance(start_value, str) and start_value.startswith('[') and start_value.endswith(']'):
+                        try:
+                            start_value = ast.literal_eval(start_value)[0]
+                        except:
+                            # Keep as is if parsing fails
+                            pass
+
+                    if isinstance(end_value, str) and end_value.startswith('[') and end_value.endswith(']'):
+                        try:
+                            end_value = ast.literal_eval(end_value)[0]
+                        except:
+                            # Keep as is if parsing fails
+                            pass
+
+                    # Safety check to avoid inserting None accidentally
+                    if start_value is None or end_value is None:
+                        print(f"  -> Skipping relationship due to missing start or end value: Start={start_value}, End={end_value}")
+                        continue
+
+                    cypher_query = f"""
+                    MATCH (a:{start_label} {{ {start_key}: $start_value }}),
+                          (b:{end_label} {{ {end_key}: $end_value }})
+                    MERGE (a)-[r:{relationship_type}]->(b)
+                    RETURN count(r) as rel_count
+                    """
+                    result = tx.run(
+                        cypher_query,
+                        start_value=start_value,
+                        end_value=end_value
+                    )
+                    
+                    # Check if relationship was created or already existed
+                    summary = result.consume()
+                    if summary.counters.relationships_created > 0:
+                        batch_success += 1
+                    elif summary.counters.relationships_created == 0:
+                        # Check if nodes exist
+                        check_query = f"""
+                        MATCH (a:{start_label} {{ {start_key}: $start_value }})
+                        RETURN count(a) as start_count
+                        """
+                        start_result = tx.run(check_query, start_value=start_value)
+                        start_count = start_result.single()["start_count"]
+                        
+                        check_query = f"""
+                        MATCH (b:{end_label} {{ {end_key}: $end_value }})
+                        RETURN count(b) as end_count
+                        """
+                        end_result = tx.run(check_query, end_value=end_value)
+                        end_count = end_result.single()["end_count"]
+                        
+                        if start_count == 0 or end_count == 0:
+                            print(f"    -> Warning: Could not create relationship - Start node exists: {start_count > 0}, End node exists: {end_count > 0}")
+                            print(f"       Start: {start_label}({start_key}={start_value}), End: {end_label}({end_key}={end_value})")
+                            
+                            # If end node doesn't exist but should, print more details
+                            if end_count == 0:
+                                print(f"       Original end value in mapping: {rel['end']['value']}")
+                                # Try to find similar nodes
+                                similar_query = f"""
+                                MATCH (b:{end_label})
+                                RETURN b.{end_key} as id LIMIT 5
+                                """
+                                similar_result = tx.run(similar_query)
+                                similar_ids = [record["id"] for record in similar_result]
+                                print(f"       Sample of existing {end_label} IDs: {similar_ids}")
+                
+                # Commit the transaction for this batch
+                tx.commit()
+                successful_imports += batch_success
+            
+            # Save checkpoint after each batch
+            with open(checkpoint_path, 'wb') as cp:
+                pickle.dump({'last_processed_index': min(i+batch_size, total_rels)-1}, cp)
+            
+            # Log progress with actual success count
+            print(f"    -> Processed {min(i+batch_size, total_rels)}/{total_rels} relationships, successfully imported {successful_imports} relationships of type {relationship_type}")
+            
+            # Verify count in database periodically
+            if i % (batch_size * 10) == 0:
+                with session.begin_transaction() as tx:
+                    count_query = f"""
+                    MATCH ()-[r:{relationship_type}]->() 
+                    RETURN count(r) as rel_count
+                    """
+                    result = tx.run(count_query)
+                    current_count = result.single()["rel_count"]
+                    print(f"    -> Current count of {relationship_type} relationships in database: {current_count}")
+        
+        # Final count verification
+        with session.begin_transaction() as tx:
+            count_query = f"""
+            MATCH ()-[r:{relationship_type}]->() 
+            RETURN count(r) as rel_count
+            """
+            result = tx.run(count_query)
+            final_count = result.single()["rel_count"]
+            print(f"  -> Final count of {relationship_type} relationships in database: {final_count}")
+            print(f"  -> Successfully imported {successful_imports} relationships of type {relationship_type}")
+        
+        # Remove checkpoint file when done
+        if os.path.exists(checkpoint_path):
+            os.remove(checkpoint_path)
+            
+        print(f"  -> Finished importing relationships of type {relationship_type}")
+
+    except Exception as e:
+        print(f"Error in create_relationships for {file_path}: {e}")
+        traceback.print_exc()
+        raise
+
+def import_to_memgraph(json_path, uri, user, password, batch_size=500):
+    """
+    Connect to Memgraph and import nodes and relationships from JSON files with checkpointing.
+    """
+    driver = GraphDatabase.driver(uri, auth=(user, password))
+    
+    # Create checkpoint directory
+    checkpoint_dir = os.path.join(json_path, "checkpoints")
+    os.makedirs(checkpoint_dir, exist_ok=True)
+    
+    # Track overall progress
+    progress_file = os.path.join(checkpoint_dir, "import_progress.pkl")
+    processed_files = set()
+    
+    # Load progress if exists
+    if os.path.exists(progress_file):
+        try:
+            with open(progress_file, 'rb') as f:
+                processed_files = pickle.load(f)
+            print(f"Resuming import. {len(processed_files)} files already processed.")
+        except Exception as e:
+            print(f"Error loading progress file, starting from beginning: {e}")
+            processed_files = set()
+
+    try:
+        with driver.session() as session:
+            """
+            # Step 1: Import all nodes
+            print("Step 1: Importing all nodes...")
+            node_files = [f for f in os.listdir(json_path) if f.endswith('.json') and "mapping" not in f]
+            for file_name in node_files:
+                if file_name in processed_files:
+                    print(f"  -> Skipping already processed file: {file_name}")
+                    continue
+                    
+                file_path = os.path.join(json_path, file_name)
+                checkpoint_path = os.path.join(checkpoint_dir, f"{file_name}.checkpoint")
+                print(f"  -> Processing node file: {file_name}")
+                create_node(session, file_path, batch_size, checkpoint_path)
+                
+                # Mark file as processed
+                processed_files.add(file_name)
+                with open(progress_file, 'wb') as f:
+                    pickle.dump(processed_files, f)
+            """
+            # Step 2: Import all relationships
+            print("Step 2: Importing all relationships...")
+            rel_files = [f for f in os.listdir(json_path) if f.endswith('.json') and "mapping" in f]
+            for file_name in rel_files:
+                if file_name in processed_files:
+                    print(f"  -> Skipping already processed file: {file_name}")
+                    continue
+                    
+                file_path = os.path.join(json_path, file_name)
+                checkpoint_path = os.path.join(checkpoint_dir, f"{file_name}.checkpoint")
+                print(f"  -> Processing relationship file: {file_name}")
+                create_relationships(session, file_path, batch_size, checkpoint_path)
+                
+                # Mark file as processed
+                processed_files.add(file_name)
+                with open(progress_file, 'wb') as f:
+                    pickle.dump(processed_files, f)
+
+        # Clean up checkpoint directory when everything is done
+        if os.path.exists(checkpoint_dir):
+            import shutil
+            shutil.rmtree(checkpoint_dir)
+            print("Import completed successfully. Checkpoint files removed.")
+
+    except Exception as e:
+        print(f"Error in import_to_memgraph: {e}")
+        print("Checkpoint files preserved for resuming import later.")
+        traceback.print_exc()
+        raise
+
+    finally:
+        driver.close()
+
+
+
+
+
diff --git a/RDAS_RDOMICS/scripts/step7_1_import_normalized_experiment_properties.py b/RDAS_RDOMICS/scripts/step7_1_import_normalized_experiment_properties.py
new file mode 100644
index 0000000..fb81794
--- /dev/null
+++ b/RDAS_RDOMICS/scripts/step7_1_import_normalized_experiment_properties.py
@@ -0,0 +1,79 @@
+"""Import normalized experiment properties into the graph database."""
+
+import argparse
+import os
+from pathlib import Path
+import sys
+
+import pandas as pd
+from neo4j import GraphDatabase
+
+CURRENT_DIR = Path(__file__).resolve().parent
+if str(CURRENT_DIR) not in sys.path:
+    sys.path.insert(0, str(CURRENT_DIR))
+
+from utils import load_paths
+
+
+def import_normalized_properties(config_path: str | None = None) -> None:
+    neo4j_uri = os.environ.get("NEO4J_URI")
+    neo4j_user = os.environ.get("NEO4J_USER")
+    neo4j_password = os.environ.get("NEO4J_PASSWORD")
+    if not all([neo4j_uri, neo4j_user, neo4j_password]):
+        raise ValueError("Set NEO4J_URI, NEO4J_USER, and NEO4J_PASSWORD before running this step.")
+
+    paths = load_paths(config_path)
+    experiment_file_path = paths["experiment_node_normalized"]
+
+    print("Reading experiment data from CSV file...")
+    exp_df = pd.read_csv(experiment_file_path)
+
+    print("Connecting to Memgraph database...")
+    driver = GraphDatabase.driver(neo4j_uri, auth=(neo4j_user, neo4j_password))
+    batch_size = 500
+    total_updated = 0
+
+    with driver.session() as session:
+        for i in range(0, len(exp_df), batch_size):
+            batch = exp_df.iloc[i:i+batch_size]
+            batch_updated = 0
+
+            for _, row in batch.iterrows():
+                experiment_id = row['Experiment_id']
+                omics_type_norm = row['Omics_type_norm'] if pd.notna(row['Omics_type_norm']) else ""
+                sequencing_type_norm = row['Sequencing_type_norm'] if pd.notna(row['Sequencing_type_norm']) else ""
+
+                if not omics_type_norm and not sequencing_type_norm:
+                    continue
+
+                query = """
+                MATCH (e:Experiment {Experiment_id: $experiment_id})
+                SET e.Omics_type_norm = $omics_type_norm,
+                    e.Sequencing_type_norm = $sequencing_type_norm
+                RETURN count(e) as updated
+                """
+
+                result = session.run(
+                    query,
+                    experiment_id=experiment_id,
+                    omics_type_norm=omics_type_norm,
+                    sequencing_type_norm=sequencing_type_norm
+                )
+                batch_updated += result.single()["updated"]
+
+            total_updated += batch_updated
+            print(f"Processed batch {i//batch_size + 1}, updated {batch_updated} nodes")
+
+    driver.close()
+    print(f"Import complete. Updated {total_updated} Experiment nodes with normalized properties.")
+
+
+def _parse_args() -> argparse.Namespace:
+    parser = argparse.ArgumentParser(description="Import normalized experiment properties.")
+    parser.add_argument("--config", help="Optional path to a YAML config file.")
+    return parser.parse_args()
+
+
+if __name__ == "__main__":
+    args = _parse_args()
+    import_normalized_properties(args.config)
diff --git a/RDAS_RDOMICS/scripts/step7_experiment_normalization.py b/RDAS_RDOMICS/scripts/step7_experiment_normalization.py
new file mode 100644
index 0000000..4105b42
--- /dev/null
+++ b/RDAS_RDOMICS/scripts/step7_experiment_normalization.py
@@ -0,0 +1,59 @@
+"""Normalize experiment properties using the configured mapping table."""
+
+import argparse
+import os
+from pathlib import Path
+import sys
+
+import pandas as pd
+
+CURRENT_DIR = Path(__file__).resolve().parent
+if str(CURRENT_DIR) not in sys.path:
+    sys.path.insert(0, str(CURRENT_DIR))
+
+from utils import ensure_parent_dir, load_paths
+
+
+def normalize_experiment_data(config_path: str | None = None) -> None:
+    paths = load_paths(config_path)
+    norm_file_path = paths["experiment_normalization_rules"]
+    experiment_file_path = os.path.join(paths["node_csv_files"], "experiment_node.csv")
+    normalized_experiment_file_path = paths["experiment_node_normalized"]
+
+    norm_df = pd.read_csv(norm_file_path)
+    exp_df = pd.read_csv(experiment_file_path)
+
+    exp_df['Omics_type_norm'] = ''
+    exp_df['Sequencing_type_norm'] = ''
+
+    assay_type_column = "Assay_type_norm" if "Assay_type_norm" in norm_df.columns else "Sequencing_type_norm"
+    norm_dict = {}
+    for _, row in norm_df.iterrows():
+        key = (str(row['Omics_type']), str(row['Sequencing_type']), str(row['Sequencing_library']))
+        value = (row['Omics_type_norm'], row[assay_type_column])
+        norm_dict[key] = value
+
+    for idx, row in exp_df.iterrows():
+        key = (str(row['Omics_type']), str(row['Sequencing_type']), str(row['Sequencing_library']))
+        if key in norm_dict:
+            omics_norm, seq_norm = norm_dict[key]
+            exp_df.at[idx, 'Omics_type_norm'] = omics_norm
+            exp_df.at[idx, 'Sequencing_type_norm'] = seq_norm
+
+    ensure_parent_dir(normalized_experiment_file_path)
+    exp_df.to_csv(normalized_experiment_file_path, index=False)
+    print(f"Normalization complete. Updated {sum(exp_df['Omics_type_norm'] != '')} rows.")
+    print(f"Total rows in experiment_node.csv: {len(exp_df)}")
+    print(f"Rows with normalized Omics type: {sum(exp_df['Omics_type_norm'] != '')}")
+    print(f"Rows with normalized Sequencing type: {sum(exp_df['Sequencing_type_norm'] != '')}")
+
+
+def _parse_args() -> argparse.Namespace:
+    parser = argparse.ArgumentParser(description="Normalize experiment node properties.")
+    parser.add_argument("--config", help="Optional path to a YAML config file.")
+    return parser.parse_args()
+
+
+if __name__ == "__main__":
+    args = _parse_args()
+    normalize_experiment_data(args.config)
diff --git a/RDAS_RDOMICS/scripts/utils.py b/RDAS_RDOMICS/scripts/utils.py
new file mode 100644
index 0000000..02c10a4
--- /dev/null
+++ b/RDAS_RDOMICS/scripts/utils.py
@@ -0,0 +1,54 @@
+from __future__ import annotations
+
+import os
+from pathlib import Path
+
+import yaml
+
+
+REPO_ROOT = Path(__file__).resolve().parents[1]
+DEFAULT_CONFIG_PATH = Path(__file__).resolve().parent / "config" / "paths.yaml"
+
+
+def load_config(config_path: str | None = None) -> dict:
+    """Load the full YAML configuration."""
+    selected_config = config_path or os.environ.get("RDAS_RDOMICS_CONFIG")
+    config_file = Path(selected_config).expanduser() if selected_config else DEFAULT_CONFIG_PATH
+
+    if not config_file.exists():
+        raise FileNotFoundError(f"Path config not found: {config_file}")
+
+    with config_file.open("r", encoding="utf-8") as handle:
+        return yaml.safe_load(handle) or {}
+
+
+def resolve_repo_path(path_value: str | os.PathLike[str]) -> str:
+    """Resolve a config path against the repo root unless already absolute."""
+    candidate = Path(path_value).expanduser()
+    if not candidate.is_absolute():
+        candidate = REPO_ROOT / candidate
+    return str(candidate)
+
+
+def load_paths(config_path: str | None = None) -> dict[str, str]:
+    """Load configured paths and resolve relative entries from the repo root."""
+    config = load_config(config_path)
+
+    raw_paths = config.get("paths", config)
+    resolved_paths: dict[str, str] = {}
+
+    for key, value in raw_paths.items():
+        resolved_paths[key] = resolve_repo_path(value)
+
+    return resolved_paths
+
+
+def load_settings(config_path: str | None = None) -> dict:
+    """Load non-path settings from the YAML configuration."""
+    config = load_config(config_path)
+    return config.get("settings", {})
+
+
+def ensure_parent_dir(path_value: str | os.PathLike[str]) -> None:
+    """Create the parent directory for a file path if needed."""
+    Path(path_value).expanduser().resolve().parent.mkdir(parents=True, exist_ok=True)