📝 added doc to wf

kids-first · Oct 17, 2024 · ba85e1b · ba85e1b
1 parent 9aae9f5
commit ba85e1b
Showing 1 changed file with 52 additions and 27 deletions.
diff --git a/workflows/kfdrc-gatk-haplotypecaller-ploidy-mod-wf.cwl b/workflows/kfdrc-gatk-haplotypecaller-ploidy-mod-wf.cwl
@@ -2,42 +2,65 @@ cwlVersion: v1.2
 class: Workflow
 id: kfdrc-gatk-haplotypecaller-ploidy-mod-workflow
 label: Kids First DRC GATK HaplotypeCaller Modified Ploidy BETA Workflow
-doc: "This workflow re-runs a subset of regions with a different expected ploidy and re-integrates those results into existing results"
+doc: |
+  # Kids First DRC GATK HaplotypeCaller Modified Ploidy BETA Workflow
+  This is a research workflow for users wishing to modify the ploidy of certain
+  regions of their existing GVCF calls.
+
+  ## Inputs
+
+  - input_cram: Input CRAM file
+  - input_gvcf: GVCF generated in standard workflow
+  - biospecimen_name: String name of biospcimen
+  - output_basename: String to use as the base for output filenames
+  - reference_fasta: FASTA file that was used during alignment. Also need
+    corresponding `.fai` and `.dict` files.
+  - region: Specific region to pull, in format 'chr21' or 'chr3:1-1000'
+  - dbsnp_vcf: dbSNP vcf file
+  - dbsnp_idx: dbSNP vcf index file
+  - contamination: Precalculated contamination value. Providing the value here
+    will skip the run of VerifyBAMID and use the provided value as ground truth.
+  - contamination_sites_bed: .Bed file for markers used in this
+    analysis,format(chr\tpos-1\tpos\trefAllele\taltAllele)
+  - contamination_sites_mu: .mu matrix file of genotype matrix
+  - contamination_sites_ud: .UD matrix file from SVD result of genotype matrix
+  - re_calling_interval_list: Interval list to re-call
+  - wgs_evaluation_interval_list: Target intervals to restrict GVCF metric
+    analysis (for VariantCallingMetrics)
+  - sample_ploidy: If sample/interval is expected to not have ploidy=2, enter expected ploidy
+
+  ## Outputs
+
+  - mixed_ploidy_gvcf: Updated complete GVCF in which the desired region has had its ploidy updated
+
 
 requirements:
 - class: ScatterFeatureRequirement
 - class: MultipleInputFeatureRequirement
 - class: SubworkflowFeatureRequirement
 inputs:
   input_cram: {type: 'File', doc: "Input CRAM file"}
-  input_gvcf: { type: File, secondaryFiles: ['.tbi'], doc: "gVCF generated in standard workflow"}
+  input_gvcf: {type: File, secondaryFiles: ['.tbi'], doc: "gVCF generated in standard workflow"}
   biospecimen_name: {type: 'string', doc: "String name of biospecimen"}
   output_basename: {type: 'string', doc: "String to use as the base for output filenames"}
-  reference_fasta: {type: 'File', "sbg:suggestedValue": {class: File, path: 60639014357c3a53540ca7a3,
-      name: Homo_sapiens_assembly38.fasta, secondaryFiles: [{class: File, path: 60639016357c3a53540ca7af, name: Homo_sapiens_assembly38.fasta.fai}, {class: File, path: 60639019357c3a53540ca7e7,
-      name: Homo_sapiens_assembly38.dict}]},
-    secondaryFiles: ['.fai', '^.dict']} 
-  region: { type: 'string?', doc: "Specific region to pull, in format 'chr21' or 'chr3:1-1000'" }
-  dbsnp_vcf: {type: 'File', doc: "dbSNP vcf file", "sbg:suggestedValue": {class: File,
-      path: 6063901f357c3a53540ca84b, name: Homo_sapiens_assembly38.dbsnp138.vcf}}
-  dbsnp_idx: {type: 'File?', doc: "dbSNP vcf index file", "sbg:suggestedValue": {
-      class: File, path: 6063901e357c3a53540ca834, name: Homo_sapiens_assembly38.dbsnp138.vcf.idx}}
-  contamination: {type: 'float?', doc: "Precalculated contamination value. Providing\
-      \ the value here will skip the run of VerifyBAMID and use the provided value\
-      \ as ground truth."}
-  contamination_sites_bed: {type: 'File?', doc: ".Bed file for markers used in this\
-      \ analysis,format(chr\tpos-1\tpos\trefAllele\taltAllele)", "sbg:suggestedValue": {
-      class: File, path: 6063901e357c3a53540ca833, name: Homo_sapiens_assembly38.contam.bed}}
-  contamination_sites_mu: {type: 'File?', doc: ".mu matrix file of genotype matrix",
-    "sbg:suggestedValue": {class: File, path: 60639017357c3a53540ca7cd, name: Homo_sapiens_assembly38.contam.mu}}
-  contamination_sites_ud: {type: 'File?', doc: ".UD matrix file from SVD result of\
-      \ genotype matrix", "sbg:suggestedValue": {class: File, path: 6063901f357c3a53540ca84f,
-      name: Homo_sapiens_assembly38.contam.UD}}
-  re_calling_interval_list: {type: 'File', doc: "Interval list to re-call" }
-  wgs_evaluation_interval_list: {type: 'File', doc: "Target intervals to restrict\
-      \ gvcf metric analysis (for VariantCallingMetrics)", "sbg:suggestedValue": {
-      class: File, path: 60639017357c3a53540ca7d3, name: wgs_evaluation_regions.hg38.interval_list}}
-  sample_ploidy: { type: 'int?', doc: "If sample/interval is expected to not have ploidy=2, enter expected ploidy" }
+  reference_fasta: {type: 'File', "sbg:suggestedValue": {class: File, path: 60639014357c3a53540ca7a3, name: Homo_sapiens_assembly38.fasta,
+      secondaryFiles: [{class: File, path: 60639016357c3a53540ca7af, name: Homo_sapiens_assembly38.fasta.fai}, {class: File, path: 60639019357c3a53540ca7e7,
+          name: Homo_sapiens_assembly38.dict}]}, secondaryFiles: ['.fai', '^.dict']}
+  region: {type: 'string?', doc: "Specific region to pull, in format 'chr21' or 'chr3:1-1000'"}
+  dbsnp_vcf: {type: 'File', doc: "dbSNP vcf file", "sbg:suggestedValue": {class: File, path: 6063901f357c3a53540ca84b, name: Homo_sapiens_assembly38.dbsnp138.vcf}}
+  dbsnp_idx: {type: 'File?', doc: "dbSNP vcf index file", "sbg:suggestedValue": {class: File, path: 6063901e357c3a53540ca834, name: Homo_sapiens_assembly38.dbsnp138.vcf.idx}}
+  contamination: {type: 'float?', doc: "Precalculated contamination value. Providing the value here will skip the run of VerifyBAMID
+      and use the provided value as ground truth."}
+  contamination_sites_bed: {type: 'File?', doc: ".Bed file for markers used in this analysis,format(chr\tpos-1\tpos\trefAllele\taltAllele)",
+    "sbg:suggestedValue": {class: File, path: 6063901e357c3a53540ca833, name: Homo_sapiens_assembly38.contam.bed}}
+  contamination_sites_mu: {type: 'File?', doc: ".mu matrix file of genotype matrix", "sbg:suggestedValue": {class: File, path: 60639017357c3a53540ca7cd,
+      name: Homo_sapiens_assembly38.contam.mu}}
+  contamination_sites_ud: {type: 'File?', doc: ".UD matrix file from SVD result of genotype matrix", "sbg:suggestedValue": {class: File,
+      path: 6063901f357c3a53540ca84f, name: Homo_sapiens_assembly38.contam.UD}}
+  re_calling_interval_list: {type: 'File', doc: "Interval list to re-call"}
+  wgs_evaluation_interval_list: {type: 'File', doc: "Target intervals to restrict gvcf metric analysis (for VariantCallingMetrics)",
+    "sbg:suggestedValue": {class: File, path: 60639017357c3a53540ca7d3, name: wgs_evaluation_regions.hg38.interval_list}}
+  sample_ploidy: {type: 'int?', doc: "If sample/interval is expected to not have ploidy=2, enter expected ploidy"}
 
 outputs:
   mixed_ploidy_gvcf: {type: File, outputSource: picard_mergevcfs_python_renamesample/output}
@@ -103,3 +126,5 @@ $namespaces:
 hints:
 - class: 'sbg:maxNumberOfParallelInstances'
   value: 4
+sbg:license: Apache License 2.0
+sbg:publisher: KFDRC