Bugfix .bai secondary file for ApplyBSQR behavior
[arvados-tutorial.git] / WGS-processing / cwl / helper / mark-duplicates.cwl
index 3d7cba6fa17d2a208e75fdaeabe83361dfe02dfd..1a39c1280c830d77867ef9b76f73365be3874f28 100644 (file)
@@ -1,9 +1,6 @@
 cwlVersion: v1.1
 class: CommandLineTool
-label: Marking Duplicates using Picard 
-$namespaces:
-  arv: "http://arvados.org/cwl#"
-  cwltool: "http://commonwl.org/cwltool#"
+label: Mark duplicates using GATK (Picard)
 
 requirements:
   DockerRequirement:
@@ -12,21 +9,31 @@ requirements:
 hints:
   ResourceRequirement:
     ramMin: 20000
-    coresMin: 4    
+    coresMin: 4
   arv:RuntimeConstraints:
     outputDirType: keep_output_dir
+  SoftwareRequirement:
+    packages:
+      GATK:
+        specs: [ "https://identifiers.org/rrid/RRID:SCR_001876" ]
+        version: [ "4.1.7" ]
 
 inputs:
   bam:
     type: File
+    format: edam:format_2572 # BAM
+    label: Sorted BAM
 
 outputs:
   dupbam:
     type: File
+    format: edam:format_2572 # BAM
+    label: Sorted BAM with labeled duplicates
     outputBinding:
       glob: "*.bam"
   dupmetrics:
     type: File
+    label: Duplication metrics file
     outputBinding:
       glob: "*.txt"
 
@@ -34,11 +41,24 @@ baseCommand: /gatk/gatk
 
 arguments:
   - "--java-options"
-  - "-Xmx8G" 
+  - "-Xmx8G"
   - MarkDuplicates
   - prefix: "-I"
     valueFrom: $(inputs.bam.path)
   - prefix: "-O"
     valueFrom: marked_dups$(inputs.bam.basename)
   - prefix: "-M"
-    valueFrom: "metrics.txt" 
+    valueFrom: "metrics.txt"
+
+s:codeRepository: https://github.com/arvados/arvados-tutorial
+s:license: https://www.gnu.org/licenses/agpl-3.0.en.html
+
+$namespaces:
+ s: https://schema.org/
+ edam: http://edamontology.org/
+ arv: "http://arvados.org/cwl#"
+ cwltool: "http://commonwl.org/cwltool#"
+
+#$schemas:
+# - https://schema.org/version/latest/schema.rdf
+# - http://edamontology.org/EDAM_1.18.owl