Merge pull request #26 from mskcc/develop

Release - 1.1.3
mskcc · Jul 29, 2022 · cf4867f · cf4867f
2 parents 54c9e02 + f442bf1
commit cf4867f
Show file tree

Hide file tree

Showing 16 changed files with 421 additions and 288 deletions.
diff --git a/.gitmodules b/.gitmodules
@@ -1,3 +0,0 @@
-[submodule "modules/pair/helix_filters_01"]
-	path = modules/pair/helix_filters_01
-	url = https://github.com/mskcc/helix_filters_01

diff --git a/modules/pair/alignment-pair.cwl b/modules/pair/alignment-pair.cwl
@@ -10,26 +10,6 @@ requirements:
 
 inputs:
 
-  pair:
-    type:
-      type: array
-      items:
-        type: record
-        fields:
-          CN: string
-          LB: string
-          ID: string
-          PL: string
-          PU: string[]
-          R1: File[]
-          R2: File[]
-          zR1: File[]
-          zR2: File[]
-          bam: File[]
-          RG_ID: string[]
-          adapter: string
-          adapter2: string
-          bwa_output: string
   genome: string
   intervals: string[]
   opt_dup_pix_dist: string
@@ -76,6 +56,42 @@ inputs:
       - .fai
       - ^.dict
   conpair_markers_bed: string
+  tumor:
+    type:
+      type: record
+      fields:
+        CN: string
+        LB: string
+        ID: string
+        PL: string
+        PU: string[]
+        R1: File[]
+        R2: File[]
+        zR1: File[]
+        zR2: File[]
+        bam: File[]
+        RG_ID: string[]
+        adapter: string
+        adapter2: string
+        bwa_output: string
+  normal:
+    type:
+      type: record
+      fields:
+        CN: string
+        LB: string
+        ID: string
+        PL: string
+        PU: string[]
+        R1: File[]
+        R2: File[]
+        zR1: File[]
+        zR2: File[]
+        bam: File[]
+        RG_ID: string[]
+        adapter: string
+        adapter2: string
+        bwa_output: string
 
 outputs:
 
@@ -148,7 +164,9 @@ steps:
   sample_alignment:
     run: ../../workflows/sample-workflow.cwl
     in:
-      sample: pair
+      sample:
+        source: [tumor, normal]
+        linkMerge: merge_flattened
       genome: genome
       opt_dup_pix_dist: opt_dup_pix_dist
       gatk_jar_path: gatk_jar_path
@@ -164,7 +182,6 @@ steps:
   realignment:
     run: realignment.cwl
     in:
-      pair: pair
       bams: sample_alignment/bam
       hapmap: hapmap
       dbsnp: dbsnp
@@ -175,4 +192,10 @@ steps:
       ref_fasta: ref_fasta
       intervals: intervals
       abra_ram_min: abra_ram_min
+      tumor: tumor
+      normal: normal
+      normal_name:
+        valueFrom: ${ return inputs.normal.ID; }
+      tumor_name:
+        valueFrom: ${ return inputs.tumor.ID; }
     out: [outbams, covint_list, covint_bed, qual_metrics, qual_pdf]
diff --git a/modules/pair/helix_filters_01 b/modules/pair/helix_filters_01
diff --git a/modules/pair/maf-processing-pair.cwl b/modules/pair/maf-processing-pair.cwl
@@ -11,26 +11,43 @@ requirements:
 
 inputs:
 
-    pair:
+    tumor:
         type:
-          type: array
-          items:
             type: record
             fields:
-              CN: string
-              LB: string
-              ID: string
-              PL: string
-              PU: string[]
-              R1: File[]
-              R2: File[]
-              zR1: File[]
-              zR2: File[]
-              bam: File[]
-              RG_ID: string[]
-              adapter: string
-              adapter2: string
-              bwa_output: string
+                CN: string
+                LB: string
+                ID: string
+                PL: string
+                PU: string[]
+                R1: File[]
+                R2: File[]
+                zR1: File[]
+                zR2: File[]
+                bam: File[]
+                RG_ID: string[]
+                adapter: string
+                adapter2: string
+                bwa_output: string
+    normal:
+        type:
+            type: record
+            fields:
+                CN: string
+                LB: string
+                ID: string
+                PL: string
+                PU: string[]
+                R1: File[]
+                R2: File[]
+                zR1: File[]
+                zR2: File[]
+                bam: File[]
+                RG_ID: string[]
+                adapter: string
+                adapter2: string
+                bwa_output: string
+
     bams:
         type: File[]
         secondaryFiles:
@@ -72,9 +89,10 @@ outputs:
 steps:
     create_pairing_file:
         in:
-            pair: pair
+            tumor: tumor
+            normal: normal
             echoString:
-                valueFrom: ${ return inputs.pair[1].ID + "\t" + inputs.pair[0].ID; }
+                valueFrom: ${ return inputs.normal.ID + "\t" + inputs.tumor.ID; }
             output_filename:
                 valueFrom: ${ return "tn_pairing_file.txt"; }
         out: [ pairfile ]
@@ -89,13 +107,16 @@ steps:
                 DockerRequirement:
                     dockerPull: alpine:3.8
             inputs:
-                pair:
+                tumor:
+                    type:
+                        type: record
+                        fields:
+                            ID: string
+                normal:
                     type:
-                        type: array
-                        items:
-                            type: record
-                            fields:
-                                ID: string
+                        type: record
+                        fields:
+                            ID: string
                 echoString:
                     type: string
                     inputBinding:

diff --git a/modules/pair/realignment.cwl b/modules/pair/realignment.cwl
@@ -13,26 +13,8 @@ inputs:
         type: File[]
         secondaryFiles:
             - ^.bai
-    pair:
-        type:
-          type: array
-          items:
-            type: record
-            fields:
-              CN: string
-              LB: string
-              ID: string
-              PL: string
-              PU: string[]
-              R1: File[]
-              R2: File[]
-              zR1: File[]
-              zR2: File[]
-              bam: File[]
-              RG_ID: string[]
-              adapter: string
-              adapter2: string
-              bwa_output: string
+    normal_name: string
+    tumor_name: string
     ref_fasta:
         type: File
         secondaryFiles:
@@ -116,7 +98,6 @@ steps:
     gatk_find_covered_intervals:
         run: ../../tools/gatk.FindCoveredIntervals/3.3-0/gatk.FindCoveredIntervals.cwl
         in:
-            pair: pair
             intervals_list: intervals
             reference_sequence: ref_fasta
             coverage_threshold:
@@ -132,9 +113,10 @@ steps:
     combine_intervals:
         in:
             files: gatk_find_covered_intervals/fci_list
-            pair: pair
+            normal_name: normal_name
+            tumor_name: tumor_name
             output_filename:
-                valueFrom: ${ return inputs.pair[0].ID + "." + inputs.pair[1].ID + ".fci.list"; }
+                valueFrom: ${ return inputs.tumor_name + "." + inputs.normal_name + ".fci.list"; }
         out: [mergedfile]
         run:
             class: CommandLineTool

diff --git a/project-workflow-sv.cwl b/project-workflow-sv.cwl
@@ -105,28 +105,46 @@ inputs:
         abra_ram_min: int
         scripts_bin: string
         gatk_jar_path: string
-  pairs:
+  tumors:
     type:
       type: array
       items:
-        type: array
-        items:
-          type: record
-          fields:
-            CN: string
-            LB: string
-            ID: string
-            PL: string
-            PU: string[]
-            R1: File[]
-            R2: File[]
-            zR1: File[]
-            zR2: File[]
-            bam: File[]
-            RG_ID: string[]
-            adapter: string
-            adapter2: string
-            bwa_output: string
+        type: record
+        fields:
+          CN: string
+          LB: string
+          ID: string
+          PL: string
+          PU: string[]
+          R1: File[]
+          R2: File[]
+          zR1: File[]
+          zR2: File[]
+          bam: File[]
+          RG_ID: string[]
+          adapter: string
+          adapter2: string
+          bwa_output: string
+  normals:
+    type:
+      type: array
+      items:
+        type: record
+        fields:
+          CN: string
+          LB: string
+          ID: string
+          PL: string
+          PU: string[]
+          R1: File[]
+          R2: File[]
+          zR1: File[]
+          zR2: File[]
+          bam: File[]
+          RG_ID: string[]
+          adapter: string
+          adapter2: string
+          bwa_output: string
 
 outputs:
 
@@ -257,11 +275,12 @@ steps:
       exac_filter: exac_filter
       curated_bams: curated_bams
       cosmic: cosmic
-      pair: pairs
+      tumor: tumors
+      normal: normals
       ref_fasta: ref_fasta
       mouse_fasta: mouse_fasta
     out: [normal_bam,tumor_bam,clstats1,clstats2,md_metrics,as_metrics,hs_metrics,insert_metrics,insert_pdf,per_target_coverage,qual_metrics,qual_pdf,doc_basecounts,gcbias_pdf,gcbias_metrics,gcbias_summary,conpair_pileups,mutect_vcf,mutect_callstats,vardict_vcf,combine_vcf,annotate_vcf,vardict_norm_vcf,mutect_norm_vcf,snp_pileup,merged_file_unfiltered,merged_file,maf_file,portal_file,maf,genome,assay,pi,pi_email,project_prefix,normal_sample_name,tumor_sample_name]
-    scatter: [pair]
+    scatter: [tumor, normal]
     scatterMethod: dotproduct
 
   generate_qc: