From 9aae9f56992a537642be29220404672b80d4d3a9 Mon Sep 17 00:00:00 2001
From: Miguel Brown <miguel.a.brown@gmail.com>
Date: Wed, 16 Oct 2024 15:19:07 -0400
Subject: [PATCH] :broom: cleared ou a premature prod wf update and removed
 extra input :pencil: added readme

---
 docs/KFDRC_GATK_HC_MOD_PLOIDY_README.md       | 29 +++++++++++++++++++
 ...drc-gatk-haplotypecaller-ploidy-mod-wf.cwl |  8 ++---
 workflows/kfdrc-gatk-haplotypecaller-wf.cwl   |  2 --
 3 files changed, 33 insertions(+), 6 deletions(-)
 create mode 100644 docs/KFDRC_GATK_HC_MOD_PLOIDY_README.md

diff --git a/docs/KFDRC_GATK_HC_MOD_PLOIDY_README.md b/docs/KFDRC_GATK_HC_MOD_PLOIDY_README.md
new file mode 100644
index 0000000..8195762
--- /dev/null
+++ b/docs/KFDRC_GATK_HC_MOD_PLOIDY_README.md
@@ -0,0 +1,29 @@
+# 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
diff --git a/workflows/kfdrc-gatk-haplotypecaller-ploidy-mod-wf.cwl b/workflows/kfdrc-gatk-haplotypecaller-ploidy-mod-wf.cwl
index 70a74ab..37263f3 100644
--- a/workflows/kfdrc-gatk-haplotypecaller-ploidy-mod-wf.cwl
+++ b/workflows/kfdrc-gatk-haplotypecaller-ploidy-mod-wf.cwl
@@ -1,7 +1,7 @@
 cwlVersion: v1.2
 class: Workflow
 id: kfdrc-gatk-haplotypecaller-ploidy-mod-workflow
-label: Kids First DRC GATK HaplotypeCaller Modified Ploidy 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"
 
 requirements:
@@ -17,8 +17,6 @@ inputs:
       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']} 
-  reference_dict: {type: 'File?', "sbg:suggestedValue": {class: File, path: 60639019357c3a53540ca7e7,
-      name: Homo_sapiens_assembly38.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}}
@@ -80,7 +78,9 @@ steps:
       output_basename: output_basename
       dbsnp_vcf: dbsnp_vcf
       dbsnp_idx: dbsnp_idx
-      reference_dict: reference_dict
+      reference_dict:
+        source: reference_fasta
+        valueFrom: "${self.secondaryFiles.filter(function(e) {return e.nameext == '.dict'})[0])}"
       wgs_calling_interval_list: re_calling_interval_list
       wgs_evaluation_interval_list: wgs_evaluation_interval_list
       conditional_run:
diff --git a/workflows/kfdrc-gatk-haplotypecaller-wf.cwl b/workflows/kfdrc-gatk-haplotypecaller-wf.cwl
index b7d61be..97c282d 100644
--- a/workflows/kfdrc-gatk-haplotypecaller-wf.cwl
+++ b/workflows/kfdrc-gatk-haplotypecaller-wf.cwl
@@ -113,7 +113,6 @@ inputs:
       class: File, path: 60639017357c3a53540ca7d3, name: wgs_evaluation_regions.hg38.interval_list}}
   run_sex_metrics: {type: 'boolean?', default: false, doc: "idxstats will be collected\
       \ and X/Y ratios calculated"}
-  sample_ploidy: { type: 'int?', doc: "If sample/interval is expected to not have ploidy=2, enter expected ploidy" }
 outputs:
   gvcf: {type: File, outputSource: generate_gvcf/gvcf}
   gvcf_calling_metrics: {type: 'File[]', outputSource: generate_gvcf/gvcf_calling_metrics}
@@ -159,7 +158,6 @@ steps:
         valueFrom: $(1)
       contamination: contamination
       biospecimen_name: biospecimen_name
-      sample_ploidy: sample_ploidy
     out: [verifybamid_output, gvcf, gvcf_calling_metrics]
 $namespaces:
   sbg: https://sevenbridges.com