feat: adding organism specific workflows (#357)

catalog/build/py/iwc_manifest_to_workflows_yaml.py

@@ -16,6 +16,7 @@
     "Transcriptomics": WorkflowCategoryId.TRANSCRIPTOMICS,
     "Epigenetics": WorkflowCategoryId.REGULATION,
     "Genome assembly": WorkflowCategoryId.ASSEMBLY,
+    "SARS-COV-2": WorkflowCategoryId.VARIANT_CALLING
 }
 MANIFEST_SOURCE_OF_TRUTH = ("trs_id", "workflow_name", "categories", "workflow_description")
 

catalog/output/workflows.json

@@ -20,6 +20,22 @@
         "trsId": "#workflow/github.com/iwc-workflows/haploid-variant-calling-wgs-pe/main/versions/v0.1",
         "workflowDescription": "Workflow for variant analysis against a reference genome in GenBank format",
         "workflowName": "Paired end variant calling in haploid system"
+      },
+      {
+        "parameters": [],
+        "ploidy": "HAPLOID",
+        "taxonomyId": "694009",
+        "trsId": "#workflow/github.com/iwc-workflows/sars-cov-2-pe-illumina-artic-variant-calling/COVID-19-PE-ARTIC-ILLUMINA/versions/v0.5.3",
+        "workflowDescription": "The workflow for Illumina-sequenced ARTIC data builds on the RNASeq workflow for paired-end data using the same steps for mapping and variant calling, but adds extra logic for trimming ARTIC primer sequences off reads with the ivar package. In addition, this workflow uses ivar also to identify amplicons affected by ARTIC primer-binding site mutations and tries to exclude reads derived from such tainted amplicons when calculating allele-frequencies of other variants.",
+        "workflowName": "COVID-19: variation analysis on ARTIC PE data"
+      },
+      {
+        "parameters": [],
+        "ploidy": "HAPLOID",
+        "taxonomyId": "694009",
+        "trsId": "#workflow/github.com/iwc-workflows/sars-cov-2-pe-illumina-wgs-variant-calling/COVID-19-PE-WGS-ILLUMINA/versions/v0.2.4",
+        "workflowDescription": "This workflows performs paired end read mapping with bwa-mem followed by sensitive variant calling across a wide range of AFs with lofreq",
+        "workflowName": "COVID-19: variation analysis on WGS PE data"
       }
     ]
   },

catalog/source/workflows.yml

@@ -685,6 +685,194 @@ workflows:
       - key: GTF file of annotation
         variable: GENE_MODEL_URL
     active: true
+  - trs_id: "#workflow/github.com/iwc-workflows/sars-cov-2-consensus-from-variation/COVID-19-CONSENSUS-CONSTRUCTION/versions/v0.4.2"
+    categories:
+      - VARIANT_CALLING
+    workflow_name: "COVID-19: consensus construction"
+    workflow_description:
+      "Build a consensus sequence from FILTER PASS variants with
+      intrasample allele-frequency above a configurable consensus threshold.
+
+      Hard-mask regions with low coverage (but not consensus variants within them) and
+      ambiguous sites."
+    ploidy: ANY
+    parameters:
+      - key: Variant calls
+        type_guide:
+          class: Collection
+      - key: min-AF for consensus variant
+        type_guide:
+          class: float
+      - key: min-AF for failed variants
+        type_guide:
+          class: float
+      - key: aligned reads data for depth calculation
+        type_guide:
+          class: Collection
+          ext: bam
+      - key: Depth-threshold for masking
+        type_guide:
+          class: integer
+      - key: Reference genome
+        type_guide:
+          class: File
+    active: false
+  - trs_id: "#workflow/github.com/iwc-workflows/sars-cov-2-ont-artic-variant-calling/COVID-19-ARTIC-ONT/versions/v0.3.2"
+    categories:
+      - VARIANT_CALLING
+    workflow_name: "COVID-19: variation analysis of ARTIC ONT data"
+    workflow_description:
+      This workflow for ONT-sequenced ARTIC data is modeled after
+      the alignment/variant-calling steps of the [ARTIC pipeline](https://artic.readthedocs.io/en/latest/).
+      It performs, essentially, the same steps as that pipeline’s minion command, i.e.
+      read mapping with minimap2 and variant calling with medaka. Like the Illumina
+      ARTIC workflow it uses ivar for primer trimming. Since ONT-sequenced reads have
+      a much higher error rate than Illumina-sequenced reads and are therefor plagued
+      more by false-positive variant calls, this workflow does make no attempt to handle
+      amplicons affected by potential primer-binding site mutations.
+    ploidy: ANY
+    parameters:
+      - key: ONT-sequenced reads
+        type_guide:
+          class: Collection
+          ext:
+            - fastqsanger
+            - fastqsanger.gz
+      - key: Minimum read length
+        type_guide:
+          class: integer
+      - key: Maximum read length
+        type_guide:
+          class: integer
+      - key: NC_045512.2 FASTA sequence of SARS-CoV-2
+        type_guide:
+          class: File
+          ext:
+            - fasta
+            - fasta.gz
+      - key: Primer binding sites info in BED format
+        type_guide:
+          class: File
+          ext: bed
+    active: false
+  - trs_id: "#workflow/github.com/iwc-workflows/sars-cov-2-pe-illumina-artic-variant-calling/COVID-19-PE-ARTIC-ILLUMINA/versions/v0.5.3"
+    categories:
+      - VARIANT_CALLING
+    workflow_name: "COVID-19: variation analysis on ARTIC PE data"
+    workflow_description:
+      The workflow for Illumina-sequenced ARTIC data builds on the
+      RNASeq workflow for paired-end data using the same steps for mapping and variant
+      calling, but adds extra logic for trimming ARTIC primer sequences off reads with
+      the ivar package. In addition, this workflow uses ivar also to identify amplicons
+      affected by ARTIC primer-binding site mutations and tries to exclude reads derived
+      from such tainted amplicons when calculating allele-frequencies of other variants.
+    ploidy: HAPLOID
+    taxonomy_id: 694009
+    parameters:
+      - key: Paired Collection
+        type_guide:
+          class: Collection
+          ext:
+            - fastqsanger
+            - fastqsanger.gz
+      - key: NC_045512.2 FASTA sequence of SARS-CoV-2
+        variable: ASSEMBLY_ID
+      - key: ARTIC primer BED
+        type_guide:
+          class: File
+          ext: bed
+      - key: ARTIC primers to amplicon assignments
+        type_guide:
+          class: File
+          ext: tabular
+      - key: Read removal minimum AF
+        type_guide:
+          class: float
+      - key: Read removal maximum AF
+        type_guide:
+          class: float
+      - key: Minimum DP required after amplicon bias correction
+        type_guide:
+          class: integer
+      - key: Minimum DP_ALT required after amplicon bias correction
+        type_guide:
+          class: integer
+    active: true
+  - trs_id: "#workflow/github.com/iwc-workflows/sars-cov-2-pe-illumina-wgs-variant-calling/COVID-19-PE-WGS-ILLUMINA/versions/v0.2.4"
+    categories:
+      - VARIANT_CALLING
+    workflow_name: "COVID-19: variation analysis on WGS PE data"
+    workflow_description:
+      This workflows performs paired end read mapping with bwa-mem
+      followed by sensitive variant calling across a wide range of AFs with lofreq
+    ploidy: HAPLOID
+    taxonomy_id: 694009
+    parameters:
+      - key: Paired Collection
+        type_guide:
+          class: Collection
+          ext:
+            - fastqsanger
+            - fastqsanger.gz
+      - key: NC_045512.2 FASTA sequence of SARS-CoV-2
+        variable: ASSEMBLY_ID
+    active: true
+  - trs_id: "#workflow/github.com/iwc-workflows/sars-cov-2-se-illumina-wgs-variant-calling/COVID-19-SE-WGS-ILLUMINA/versions/v0.1.5"
+    categories:
+      - VARIANT_CALLING
+    workflow_name: "COVID-19: variation analysis on WGS SE data"
+    workflow_description:
+      This workflows performs single end read mapping with bowtie2
+      followed by sensitive variant calling across a wide range of AFs with lofreq
+    ploidy: ANY
+    parameters:
+      - key: Single End Collection
+        type_guide:
+          class: Collection
+          ext:
+            - fastqsanger
+            - fastqsanger.gz
+      - key: NC_045512.2 FASTA sequence of SARS-CoV-2
+        type_guide:
+          class: File
+          ext:
+            - fasta
+            - fasta.gz
+    active: false
+  - trs_id: "#workflow/github.com/iwc-workflows/sars-cov-2-variation-reporting/COVID-19-VARIATION-REPORTING/versions/v0.3.4"
+    categories:
+      - VARIANT_CALLING
+    workflow_name: "COVID-19: variation analysis reporting"
+    workflow_description:
+      This workflow takes a VCF dataset of variants produced by
+      any of the *-variant-calling workflows in https://github.com/galaxyproject/iwc/tree/main/workflows/sars-cov-2-variant-calling
+      and generates tabular lists of variants by Samples and by Variant, and an overview
+      plot of variants and their allele-frequencies.
+    ploidy: ANY
+    parameters:
+      - key: Variation data to report
+        type_guide:
+          class: Collection
+          ext:
+            - vcf
+            - vcf_bgzip
+      - key: AF Filter
+        type_guide:
+          class: float
+      - key: DP Filter
+        type_guide:
+          class: integer
+      - key: DP_ALT Filter
+        type_guide:
+          class: integer
+      - key: gene products translations
+        type_guide:
+          class: File
+          ext: tabular
+      - key: Number of Clusters
+        type_guide:
+          class: integer
+    active: false
   - trs_id: "#workflow/github.com/iwc-workflows/variation-reporting/main/versions/v0.1.1"
     categories:
       - VARIANT_CALLING