Merge pull request #2 from mr-c/flexi_runtime

Use biocontainers, when possible

topmed-workflows/TOPMed_RNAseq_pipeline/checker-workflows/check_bams_wf.cwl

@@ -1,3 +1,4 @@
+#!/usr/bin/env cwl-runner
 doc: |
     Compare 2 input BAM files and report results.
     Exit 0 if sucess.

topmed-workflows/TOPMed_RNAseq_pipeline/checker-workflows/check_md5_wf.cwl

@@ -1,3 +1,4 @@
+#!/usr/bin/env cwl-runner
 doc: |
     Calculates the MD5 hash of the input file and compares it to the input MD5 hash.
     If hashes match: Exit 0

topmed-workflows/TOPMed_RNAseq_pipeline/checker-workflows/components/calc_md5.cwl

@@ -1,3 +1,4 @@
+#!/usr/bin/env cwl-runner
 doc: |
     Calculate the MD5 hash for the input file.
 

topmed-workflows/TOPMed_RNAseq_pipeline/checker-workflows/components/compare_bams.cwl

@@ -1,3 +1,4 @@
+#!/usr/bin/env cwl-runner
 doc: |
     Compare 2 input BAM files using [BamUtil diff](https://genome.sph.umich.edu/wiki/BamUtil:_diff)
 

topmed-workflows/TOPMed_RNAseq_pipeline/checker-workflows/components/read_file.cwl

@@ -1,3 +1,4 @@
+#!/usr/bin/env cwl-runner
 cwlVersion: v1.0
 class: ExpressionTool
 

topmed-workflows/TOPMed_RNAseq_pipeline/checker-workflows/components/string_comparison.cwl

@@ -1,3 +1,4 @@
+#!/usr/bin/env cwl-runner
 cwlVersion: v1.0
 class: CommandLineTool
 baseCommand: []

topmed-workflows/TOPMed_RNAseq_pipeline/checker-workflows/components/untar_dir.cwl

@@ -1,3 +1,4 @@
+#!/usr/bin/env cwl-runner
 doc: |
     Extract all files from archive.tar and filter through gzip
 

topmed-workflows/TOPMed_RNAseq_pipeline/checker-workflows/rnaseq_pipeline_fastq_checker-tar.cwl

@@ -1,3 +1,4 @@
+#!/usr/bin/env cwl-runner
 doc: |
     A workflow to verify the proper execution of [TOPMed RNA-seq Workflow](https://github.com/heliumdatacommons/cwl_workflows/blob/master/topmed-workflows/TOPMed_RNAseq_pipeline/rnaseq_pipeline_fastq.cwl)
 
@@ -20,29 +21,23 @@ inputs:
     type: File[]
   prefix_str:
     type: string
-  threads:
-    type: int
-  memory:
-    type: int
   rsem_ref_dir_tar:
     type: File
   max_frag_len:
     type: int
   estimate_rspd:
-    type: string
+    type: boolean
   is_stranded:
-    type: string
+    type: boolean
   paired_end:
-    type: string
+    type: boolean
   genes_gtf:
     type: File
   genome_fasta:
     type: File
     secondaryFiles:
       - .fai
       - ^.dict
-  java_path:
-    type: string
   rnaseqc_flags:
     type: string[]
   # gatk_flags:
@@ -72,8 +67,6 @@ inputs:
   #   type: string
   # hash_exon_counts:
   #   type: string
-  hash_count_metrics:
-    type: string
   # hash_count_outputs:
   #   type: string
   checker_star_output_bam:
@@ -157,16 +150,13 @@ steps:
       star_index: untar_star_index/untarred_dir
       fastqs: fastqs
       prefix_str: prefix_str
-      threads: threads
-      memory: memory
       rsem_ref_dir: untar_rsem_reference/untarred_dir
       max_frag_len: max_frag_len
       estimate_rspd: estimate_rspd
       is_stranded: is_stranded
       paired_end: paired_end
       genes_gtf: genes_gtf
       genome_fasta: genome_fasta
-      java_path: java_path
       rnaseqc_flags: rnaseqc_flags
       # gatk_flags: gatk_flags
     out:
@@ -310,7 +300,7 @@ steps:
   #   out: [out_hash_string]
 
 $namespaces:
-  s: https://schema.org/
+  s: http://schema.org/
 
 $schemas:
 - http://dublincore.org/2012/06/14/dcterms.rdf

topmed-workflows/TOPMed_RNAseq_pipeline/checker-workflows/rnaseq_pipeline_fastq_checker.cwl

@@ -1,3 +1,4 @@
+#!/usr/bin/env cwl-runner
 doc: |
     A workflow to verify the proper execution of [TOPMed RNA-seq Workflow](https://github.com/heliumdatacommons/cwl_workflows/blob/master/topmed-workflows/TOPMed_RNAseq_pipeline/rnaseq_pipeline_fastq.cwl)
 
@@ -18,29 +19,23 @@ inputs:
     type: File[]
   prefix_str:
     type: string
-  threads:
-    type: int
-  memory:
-    type: int
   rsem_ref_dir:
     type: Directory
   max_frag_len:
     type: int
   estimate_rspd:
-    type: string
+    type: boolean
   is_stranded:
-    type: string
+    type: boolean
   paired_end:
-    type: string
+    type: boolean
   genes_gtf:
     type: File
   genome_fasta:
     type: File
     secondaryFiles:
       - .fai
       - ^.dict
-  java_path:
-    type: string
   rnaseqc_flags:
     type: string[]
   # gatk_flags:
@@ -70,8 +65,6 @@ inputs:
   #   type: string
   # hash_exon_counts:
   #   type: string
-  hash_count_metrics:
-    type: string
   # hash_count_outputs:
   #   type: string
   checker_star_output_bam:
@@ -143,16 +136,13 @@ steps:
       star_index: star_index
       fastqs: fastqs
       prefix_str: prefix_str
-      threads: threads
-      memory: memory
       rsem_ref_dir: rsem_ref_dir
       max_frag_len: max_frag_len
       estimate_rspd: estimate_rspd
       is_stranded: is_stranded
       paired_end: paired_end
       genes_gtf: genes_gtf
       genome_fasta: genome_fasta
-      java_path: java_path
       rnaseqc_flags: rnaseqc_flags
       # gatk_flags: gatk_flags
     out:
@@ -296,7 +286,7 @@ steps:
   #   out: [out_hash_string]
 
 $namespaces:
-  s: https://schema.org/
+  s: http://schema.org/
 
 $schemas:
 - http://dublincore.org/2012/06/14/dcterms.rdf

topmed-workflows/TOPMed_RNAseq_pipeline/indexbam.cwl

@@ -1,25 +1,25 @@
+#!/usr/bin/env cwl-runner
 doc: |
     A wrapper for running `samtools index <bam>`.
 
 cwlVersion: v1.0
 class: CommandLineTool
-id: "run-index-bam"
 label: "run-index-bam"
-baseCommand: ["samtools", "index"]
+baseCommand: [ samtools, index ]
 
 requirements:
-- class: InlineJavascriptRequirement
-- class: DockerRequirement
-  dockerPull: heliumdatacommons/topmed-rnaseq:latest
-- class: InitialWorkDirRequirement
-  listing:
-    - $(inputs.input_bam)
+  DockerRequirement:
+    dockerPull: quay.io/biocontainers/samtools:1.8--4
+  InitialWorkDirRequirement:
+    listing:
+      - $(inputs.input_bam)
 
 inputs:
   input_bam:
     type: File
     inputBinding:
       position: 1
+      valueFrom: $(self.basename)
 
 outputs:
   bam_index:

topmed-workflows/TOPMed_RNAseq_pipeline/input-examples/rnaseq_pipeline_fastq-example.yml

@@ -11,9 +11,9 @@ rsem_ref_dir:
     class: Directory
     location: /rsem_ref/
 max_frag_len: 1000
-estimate_rspd: "true"
-is_stranded: "true"
-paired_end: "true"
+estimate_rspd: true
+is_stranded: true
+paired_end: true
 genes_gtf: {
     class: File,
     path: gencode.v26.annotation.withTranscriptID.gtf
@@ -22,9 +22,6 @@ genome_fasta: {
     class: File,
     path: Homo_sapiens_assembly38_noALT_noHLA_noDecoy_ERCC.fasta
 }
-java_path: /usr/lib/jvm/java-1.7.0-openjdk-amd64/bin/java
-memory: 8
 rnaseqc_flags: ["noDoC", "strictMode"]
 # gatk_flags: []
 prefix_str: "LC_C13_cRNA"
-threads: 4

topmed-workflows/TOPMed_RNAseq_pipeline/input-examples/rsem-example.yml

@@ -7,7 +7,7 @@ transcriptome_bam: {
 }
 prefix_str: "LC_C13_cRNA"
 max_frag_len: 1000
-estimate_rspd: "true"
-is_stranded: "true"
-paired_end: "true"
+estimate_rspd: true
+is_stranded: true
+paired_end: true
 threads: 4

topmed-workflows/TOPMed_RNAseq_pipeline/markduplicates.cwl

@@ -1,3 +1,4 @@
+#!/usr/bin/env cwl-runner
 doc: |
     A CWL wrapper for [run_MarkDuplicates.py](https://github.com/broadinstitute/gtex-pipeline/blob/master/rnaseq/src/run_MarkDuplicates.py)
 
@@ -9,35 +10,42 @@ doc: |
 
 cwlVersion: v1.0
 class: CommandLineTool
-id: "run-MarkDuplicates"
 label: "run-MarkDuplicates"
-baseCommand: ["python3", "-u", "/src/run_MarkDuplicates.py"]
+baseCommand: [java]
 
-requirements:
-  - class: DockerRequirement
-    dockerPull: heliumdatacommons/topmed-rnaseq:latest
+requirements: # turn back into a hint when the biocontainer has its classpath
+              #   updated
+  EnvVarRequirement:
+    envDef:
+      CLASSPATH: /usr/local/share/picard-2.9.2-2/picard.jar
+  DockerRequirement:
+    dockerPull: quay.io/biocontainers/picard:2.9.2--2
 
 inputs:
   input_bam:
     type: File
-    inputBinding:
-      position: 1
   prefix_str:
     type: string
-    inputBinding:
-      position: 2
-  memory:
-    type: int
-    inputBinding:
-      position: 3
-      prefix: --memory
+
+arguments:
+  - prefix: -Xmx
+    valueFrom: $(runtime.ram)M
+    separate: false
+  - picard.cmdline.PicardCommandLine
+  - MarkDuplicates
+  - I=$(inputs.input_bam.path)
+  - O=$(runtime.outdir)/$(inputs.input_bam.nameroot).md.bam
+  - M=$(runtime.outdir)/$(inputs.prefix_str).marked_dup_metrics.txt
+  - ASSUME_SORT_ORDER=coordinate
+  - OPTICAL_DUPLICATE_PIXEL_DISTANCE=100
 
 outputs:
   bam_file:
     type: File
     outputBinding:
-      glob: "*.md.bam"
+      glob: $(inputs.input_bam.nameroot).md.bam
   metrics:
     type: File
     outputBinding:
-      glob: "*.marked_dup_metrics.txt"
+      glob: $(inputs.prefix_str).marked_dup_metrics.txt
+

topmed-workflows/TOPMed_RNAseq_pipeline/rna_seqc.cwl

@@ -1,3 +1,4 @@
+#!/usr/bin/env cwl-runner
 doc: |
     A CWL wrapper for [run_rnaseqc.py](https://github.com/heliumdatacommons/cwl_workflows/blob/master/topmed-workflows/TOPMed_RNAseq_pipeline/src/run_rnaseqc.py) duplicated from [run_rnaseqc.py](https://github.com/broadinstitute/gtex-pipeline/blob/master/rnaseq/src/run_rnaseqc.py) with minor modifications.
 
@@ -9,12 +10,12 @@ doc: |
 
 cwlVersion: v1.0
 class: CommandLineTool
-id: "run-seqc"
 label: "run-seqc"
 # run_rnaseqc.py is not an executable file in the docker container.
 baseCommand: ["python3", "/src/run_rnaseqc.py"]
 
 requirements:
+  InlineJavascriptRequirement: {}
   DockerRequirement:
     dockerPull: heliumdatacommons/topmed-rnaseq:latest
 
@@ -40,16 +41,6 @@ inputs:
     type: string
     inputBinding:
       position: 4
-  java_path:
-    type: string
-    inputBinding:
-      position: 5
-      prefix: --java
-  memory:
-    type: int
-    inputBinding:
-      position: 6
-      prefix: --memory
   rnaseqc_flags:
     type:
       type: array
@@ -70,6 +61,11 @@ inputs:
   #     position: 8
   #     prefix: --gatk_flags
 
+arguments:
+  - prefix: --memory
+    valueFrom: $(runtime.ram / 1024)
+  - prefix: --java
+    valueFrom: /usr/lib/jvm/java-1.7.0-openjdk-amd64/bin/java
 outputs:
   gene_rpkm:
     type: File