Update Denoising results

CHANGELOG.md

@@ -1,5 +1,11 @@
 # openproblems.bio unreleased
 
+## MAJOR CHANGES
+
+* Update Denoising task to OpenProblems v2 results (PR #325)
+
+# openproblems.bio v2.3.6
+
 ## NEW CONTENT
 
 * Add an event page for the Weekly wednesday work meeting (PR #299).

results/denoising/data/dataset_info.json

@@ -1,38 +1,138 @@
 [
-    {
-        "dataset_name": "Pancreas (inDrop)",
-        "image": "openproblems-python-pytorch",
-        "data_url": "https://ndownloader.figshare.com/files/36086813",
-        "data_reference": "luecken2022benchmarking",
-        "dataset_summary": "Human pancreatic islet scRNA-seq data from 6 datasets across technologies (CEL-seq, CEL-seq2, Smart-seq2, inDrop, Fluidigm C1, and SMARTER-seq). Here we just use the inDrop1 batch, which includes1937 cells \u00d7 15502 genes.",
-        "task_id": "denoising",
-        "commit_sha": "9d1665076cf6215a31f89ed2be8be20a02502887",
-        "dataset_id": "pancreas",
-        "source_dataset_id": "openproblems_v1/pancreas",
-        "implementation_url": "https://github.com/openproblems-bio/openproblems/blob/main/openproblems/tasks/denoising/datasets/pancreas.py"
-    },
-    {
-        "dataset_name": "1k Peripheral blood mononuclear cells",
-        "image": "openproblems-python-pytorch",
-        "data_url": "https://ndownloader.figshare.com/files/36088667",
-        "data_reference": "10x2018pbmc",
-        "dataset_summary": "1k Peripheral Blood Mononuclear Cells (PBMCs) from a healthy donor. Sequenced on 10X v3 chemistry in November 2018 by 10X Genomics.",
-        "task_id": "denoising",
-        "commit_sha": "9d1665076cf6215a31f89ed2be8be20a02502887",
-        "dataset_id": "pbmc",
-        "source_dataset_id": "openproblems_v1/tenx_1k_pbmc",
-        "implementation_url": "https://github.com/openproblems-bio/openproblems/blob/main/openproblems/tasks/denoising/datasets/pbmc.py"
-    },
-    {
-        "dataset_name": "Tabula Muris Senis Lung",
-        "image": "openproblems-python-pytorch",
-        "data_url": "https://tabula-muris-senis.ds.czbiohub.org/",
-        "data_reference": "tabula2020single",
-        "dataset_summary": "All lung cells from Tabula Muris Senis, a 500k cell-atlas from 18 organs and tissues across the mouse lifespan. Here we use just 10x data from lung. 24540 cells \u00d7 16160 genes across 3 time points.",
-        "task_id": "denoising",
-        "commit_sha": "9d1665076cf6215a31f89ed2be8be20a02502887",
-        "dataset_id": "tabula_muris_senis_lung_random",
-        "source_dataset_id": "openproblems_v1/tabula_muris_senis_droplet_lung",
-        "implementation_url": "https://github.com/openproblems-bio/openproblems/blob/main/openproblems/tasks/denoising/datasets/tabula_muris_senis.py"
-    }
-]
+  {
+    "task_id": "denoising",
+    "dataset_id": "cellxgene_census/dkd",
+    "dataset_name": "Diabetic Kidney Disease",
+    "dataset_summary": "Multimodal single cell sequencing implicates chromatin accessibility and genetic background in diabetic kidney disease progression",
+    "data_reference": "wilson2022multimodal",
+    "data_url": "https://cellxgene.cziscience.com/collections/b3e2c6e3-9b05-4da9-8f42-da38a664b45b"
+  },
+  {
+    "task_id": "denoising",
+    "dataset_id": "cellxgene_census/tabula_sapiens",
+    "dataset_name": "Tabula Sapiens",
+    "dataset_summary": "A multiple-organ, single-cell transcriptomic atlas of humans",
+    "data_reference": "consortium2022tabula",
+    "data_url": "https://cellxgene.cziscience.com/collections/e5f58829-1a66-40b5-a624-9046778e74f5"
+  },
+  {
+    "task_id": "denoising",
+    "dataset_id": "cellxgene_census/hcla",
+    "dataset_name": "Human Lung Cell Atlas",
+    "dataset_summary": "An integrated cell atlas of the human lung in health and disease (core)",
+    "data_reference": "sikkema2023integrated",
+    "data_url": "https://cellxgene.cziscience.com/collections/6f6d381a-7701-4781-935c-db10d30de293"
+  },
+  {
+    "task_id": "denoising",
+    "dataset_id": "cellxgene_census/mouse_pancreas_atlas",
+    "dataset_name": "Mouse Pancreatic Islet Atlas",
+    "dataset_summary": "Mouse pancreatic islet scRNA-seq atlas across sexes, ages, and stress conditions including diabetes",
+    "data_reference": "hrovatin2023delineating",
+    "data_url": "https://cellxgene.cziscience.com/collections/296237e2-393d-4e31-b590-b03f74ac5070"
+  },
+  {
+    "task_id": "denoising",
+    "dataset_id": "openproblems_v1/cengen",
+    "dataset_name": "CeNGEN",
+    "dataset_summary": "Complete Gene Expression Map of an Entire Nervous System",
+    "data_reference": "hammarlund2018cengen",
+    "data_url": "https://www.cengen.org"
+  },
+  {
+    "task_id": "denoising",
+    "dataset_id": "openproblems_v1/zebrafish",
+    "dataset_name": "Zebrafish embryonic cells",
+    "dataset_summary": "Single-cell mRNA sequencing of zebrafish embryonic cells.",
+    "data_reference": "wagner2018single",
+    "data_url": "https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE112294"
+  },
+  {
+    "task_id": "denoising",
+    "dataset_id": "openproblems_v1/tenx_5k_pbmc",
+    "dataset_name": "5k PBMCs",
+    "dataset_summary": "5k peripheral blood mononuclear cells from a healthy donor",
+    "data_reference": "10x2019pbmc",
+    "data_url": "https://www.10xgenomics.com/resources/datasets/5-k-peripheral-blood-mononuclear-cells-pbm-cs-from-a-healthy-donor-with-cell-surface-proteins-v-3-chemistry-3-1-standard-3-1-0"
+  },
+  {
+    "task_id": "denoising",
+    "dataset_id": "openproblems_v1/mouse_hspc_nestorowa2016",
+    "dataset_name": "Mouse HSPC",
+    "dataset_summary": "Haematopoeitic stem and progenitor cells from mouse bone marrow",
+    "data_reference": "nestorowa2016single",
+    "data_url": "https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE81682"
+  },
+  {
+    "task_id": "denoising",
+    "dataset_id": "cellxgene_census/gtex_v9",
+    "dataset_name": "GTEX v9",
+    "dataset_summary": "Single-nucleus cross-tissue molecular reference maps to decipher disease gene function",
+    "data_reference": "eraslan2022singlenucleus",
+    "data_url": "https://cellxgene.cziscience.com/collections/a3ffde6c-7ad2-498a-903c-d58e732f7470"
+  },
+  {
+    "task_id": "denoising",
+    "dataset_id": "openproblems_v1/immune_cells",
+    "dataset_name": "Human immune",
+    "dataset_summary": "Human immune cells dataset from the scIB benchmarks",
+    "data_reference": "luecken2022benchmarking",
+    "data_url": "https://theislab.github.io/scib-reproducibility/dataset_immune_cell_hum.html"
+  },
+  {
+    "task_id": "denoising",
+    "dataset_id": "openproblems_v1/tenx_1k_pbmc",
+    "dataset_name": "1k PBMCs",
+    "dataset_summary": "1k peripheral blood mononuclear cells from a healthy donor",
+    "data_reference": "10x2018pbmc",
+    "data_url": "https://www.10xgenomics.com/resources/datasets/1-k-pbm-cs-from-a-healthy-donor-v-3-chemistry-3-standard-3-0-0"
+  },
+  {
+    "task_id": "denoising",
+    "dataset_id": "openproblems_v1/mouse_blood_olsson_labelled",
+    "dataset_name": "Mouse myeloid",
+    "dataset_summary": "Myeloid lineage differentiation from mouse blood",
+    "data_reference": "olsson2016single",
+    "data_url": "https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE70245"
+  },
+  {
+    "task_id": "denoising",
+    "dataset_id": "openproblems_v1/pancreas",
+    "dataset_name": "Human pancreas",
+    "dataset_summary": "Human pancreas cells dataset from the scIB benchmarks",
+    "data_reference": "luecken2022benchmarking",
+    "data_url": "https://theislab.github.io/scib-reproducibility/dataset_pancreas.html"
+  },
+  {
+    "task_id": "denoising",
+    "dataset_id": "cellxgene_census/immune_cell_atlas",
+    "dataset_name": "Immune Cell Atlas",
+    "dataset_summary": "Cross-tissue immune cell analysis reveals tissue-specific features in humans",
+    "data_reference": "dominguez2022crosstissue",
+    "data_url": "https://cellxgene.cziscience.com/collections/62ef75e4-cbea-454e-a0ce-998ec40223d3"
+  },
+  {
+    "task_id": "denoising",
+    "dataset_id": "openproblems_v1/allen_brain_atlas",
+    "dataset_name": "Mouse Brain Atlas",
+    "dataset_summary": "Adult mouse primary visual cortex",
+    "data_reference": "tasic2016adult",
+    "data_url": "http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE71585"
+  },
+  {
+    "task_id": "denoising",
+    "dataset_id": "openproblems_v1/tnbc_wu2021",
+    "dataset_name": "Triple-Negative Breast Cancer",
+    "dataset_summary": "1535 cells from six fresh triple-negative breast cancer tumors.",
+    "data_reference": "wu2021single",
+    "data_url": "https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE118389"
+  },
+  {
+    "task_id": "denoising",
+    "dataset_id": "cellxgene_census/hypomap",
+    "dataset_name": "HypoMap",
+    "dataset_summary": "A unified single cell gene expression atlas of the murine hypothalamus",
+    "data_reference": "steuernagel2022hypomap",
+    "data_url": "https://cellxgene.cziscience.com/collections/d86517f0-fa7e-4266-b82e-a521350d6d36"
+  }
+]