From: Sarah Wait Zaranek Date: Tue, 7 Jul 2020 00:36:13 +0000 (+0000) Subject: Updating yml for formats X-Git-Url: https://git.arvados.org/arvados-tutorial.git/commitdiff_plain/5080fcfd4a95af83c57b7a386b7ae9e0d38ef7c5 Updating yml for formats Arvados-DCO-1.1-Signed-off-by: Sarah Wait Zaranek no issue # --- diff --git a/WGS-processing/cwl/helper/annotate-vcf.cwl b/WGS-processing/cwl/helper/annotate-vcf.cwl index bb4989e..1e028c4 100644 --- a/WGS-processing/cwl/helper/annotate-vcf.cwl +++ b/WGS-processing/cwl/helper/annotate-vcf.cwl @@ -3,9 +3,9 @@ class: CommandLineTool label: Annotate and filter VCF requirements: - - class: DockerRequirement + DockerRequirement: dockerPull: curii/clinvar-report - - class: ShellCommandRequirement + ShellCommandRequirement: {} hints: ResourceRequirement: @@ -32,7 +32,6 @@ inputs: outputs: reporttxt: stdout - label: Annotated text from VCF arguments: - bcftools diff --git a/WGS-processing/cwl/helper/bwamem-gatk-report-wf.cwl b/WGS-processing/cwl/helper/bwamem-gatk-report-wf.cwl index ee8ae4f..ea5b93b 100644 --- a/WGS-processing/cwl/helper/bwamem-gatk-report-wf.cwl +++ b/WGS-processing/cwl/helper/bwamem-gatk-report-wf.cwl @@ -3,7 +3,7 @@ class: Workflow label: WGS processing workflow for single sample requirements: - - class: SubworkflowFeatureRequirement + SubworkflowFeatureRequirement: {} inputs: fastq1: @@ -119,7 +119,7 @@ steps: run: report-wf.cwl in: gvcf: haplotypecaller/gatheredgvcf - samplename: sample + sample: sample clinvarvcf: clinvarvcf reportfunc: reportfunc headhtml: headhtml @@ -133,6 +133,6 @@ $namespaces: s: https://schema.org/ edam: http://edamontology.org/ -$schemas: - - https://schema.org/version/latest/schema.rdf - - http://edamontology.org/EDAM_1.18.owl +#$schemas: +# - https://schema.org/version/latest/schema.rdf +# - http://edamontology.org/EDAM_1.18.owl diff --git a/WGS-processing/cwl/helper/gather-array-vcf.cwl b/WGS-processing/cwl/helper/gather-array-vcf.cwl new file mode 100644 index 0000000..1e7d705 --- /dev/null +++ b/WGS-processing/cwl/helper/gather-array-vcf.cwl @@ -0,0 +1,103 @@ +cwlVersion: v1.1 +class: CommandLineTool +label: Gather GVCFs + +requirements: + DockerRequirement: + dockerPull: broadinstitute/gatk:4.1.7.0 + ShellCommandRequirement: {} + InlineJavascriptRequirement: {} + +hints: + ResourceRequirement: + ramMin: 20000 + coresMin: 4 + arv:RuntimeConstraints: + outputDirType: keep_output_dir + +inputs: + gvcfarray: + type: File[] + format: edam:format_3016 # GVCF + label: GVCFs for given intervals + sample: + type: string + label: Sample Name + reference: + type: File + format: edam:format_1929 # FASTA + label: Reference genome + secondaryFiles: + - .amb + - .ann + - .bwt + - .pac + - .sa + - .fai + - ^.dict +outputs: + gatheredgvcf: + type: File + format: edam:format_3016 # GVCF + label: Gathered GVC + secondaryFiles: + - .tbi + outputBinding: + glob: "*.g.vcf.gz" + +baseCommand: /gatk/gatk + +arguments: + - "--java-options" + - "-Xmx8G" + - MergeVcfs + - shellQuote: false + valueFrom: | + ${function compare(a, b) { + var baseA = a.basename; + var baseB = b.basename; + + var comparison = 0; + if (baseA > baseB) { + comparison = 1; + } else if (baseA < baseB) { + comparison = -1; + } + return comparison; + } + + var sortedarray = []; + sortedarray = inputs.gvcfarray.sort(compare) + + var samples = []; + for (var i = 0; i < sortedarray.length; i++) { + var name = sortedarray[i]; + if (name.nameext ==='.gz' ) { + samples.push(name.path); + } + } + + var sampleinput = ""; + + for (var i = 0; i < samples.length; i++) { + var s1 = samples[i]; + sampleinput = sampleinput + "-I " + s1 + " " + } + + return sampleinput; + } + - prefix: "-O" + valueFrom: $(inputs.sample).g.vcf.gz + +s:codeRepository: https://github.com/arvados/arvados-tutorial +s:license: https://www.gnu.org/licenses/agpl-3.0.en.html + +$namespaces: + s: https://schema.org/ + edam: http://edamontology.org/ + arv: "http://arvados.org/cwl#" + cwltool: "http://commonwl.org/cwltool#" + +#$schemas: +# - https://schema.org/version/latest/schema.rdf +# - http://edamontology.org/EDAM_1.18.owl diff --git a/WGS-processing/cwl/helper/gather-vcf.cwl b/WGS-processing/cwl/helper/gather-vcf.cwl index b59fc35..4f79669 100644 --- a/WGS-processing/cwl/helper/gather-vcf.cwl +++ b/WGS-processing/cwl/helper/gather-vcf.cwl @@ -2,10 +2,6 @@ cwlVersion: v1.1 class: CommandLineTool label: Gather GVCF using Picard -$namespaces: - arv: "http://arvados.org/cwl#" - cwltool: "http://commonwl.org/cwltool#" - requirements: DockerRequirement: dockerPull: broadinstitute/gatk:4.1.7.0 diff --git a/WGS-processing/cwl/helper/gatk-wf-with-interval.cwl b/WGS-processing/cwl/helper/gatk-wf-with-interval.cwl index a5d1993..de4a648 100644 --- a/WGS-processing/cwl/helper/gatk-wf-with-interval.cwl +++ b/WGS-processing/cwl/helper/gatk-wf-with-interval.cwl @@ -3,7 +3,7 @@ class: Workflow label: Variant calling workflow for given interval requirements: - - class: SubworkflowFeatureRequirement + SubworkflowFeatureRequirement: {} inputs: bam: diff --git a/WGS-processing/cwl/helper/gvcf-to-vcf.cwl b/WGS-processing/cwl/helper/gvcf-to-vcf.cwl index 4df5fd8..7df5fe2 100644 --- a/WGS-processing/cwl/helper/gvcf-to-vcf.cwl +++ b/WGS-processing/cwl/helper/gvcf-to-vcf.cwl @@ -3,9 +3,9 @@ class: CommandLineTool label: Convert GVCF to VCF requirements: - - class: DockerRequirement + DockerRequirement: dockerPull: curii/clinvar-report - - class: ShellCommandRequirement + ShellCommandRequirement: {} hints: ResourceRequirement: diff --git a/WGS-processing/cwl/helper/scatter-gatk-wf-with-interval.cwl b/WGS-processing/cwl/helper/scatter-gatk-wf-with-interval.cwl index 75c605b..9752edb 100644 --- a/WGS-processing/cwl/helper/scatter-gatk-wf-with-interval.cwl +++ b/WGS-processing/cwl/helper/scatter-gatk-wf-with-interval.cwl @@ -3,8 +3,8 @@ class: Workflow label: Scattered variant calling workflow requirements: - - class: SubworkflowFeatureRequirement - - class: ScatterFeatureRequirement + SubworkflowFeatureRequirement: {} + ScatterFeatureRequirement: {} inputs: bam: diff --git a/WGS-processing/cwl/wgs-processing-wf.cwl b/WGS-processing/cwl/wgs-processing-wf.cwl index 474a5e3..9459a3f 100644 --- a/WGS-processing/cwl/wgs-processing-wf.cwl +++ b/WGS-processing/cwl/wgs-processing-wf.cwl @@ -90,6 +90,6 @@ $namespaces: s: https://schema.org/ edam: http://edamontology.org/ -$schemas: - - https://schema.org/version/latest/schema.rdf - - http://edamontology.org/EDAM_1.18.owl +#$schemas: +# - https://schema.org/version/latest/schema.rdf +# - http://edamontology.org/EDAM_1.18.owl diff --git a/WGS-processing/yml/helper/annotate-vcf.yml b/WGS-processing/yml/helper/annotate-vcf.yml index 74f0856..e25dc7f 100644 --- a/WGS-processing/yml/helper/annotate-vcf.yml +++ b/WGS-processing/yml/helper/annotate-vcf.yml @@ -1,7 +1,9 @@ vcf: class: File + format: edam:format_3016 location: keep:542f0989c5ee117e20d293ef82311192+114145/hu34D5B9_var-GS000015891-ASM.vcf.gz clinvarvcf: class: File + format: edam:format_3016 location: keep:80aadf801bccd1e1d838b07d46d4de63+1712/37/clinvar.vcf.gz diff --git a/WGS-processing/yml/helper/bwamem-gatk-report-wf.yml b/WGS-processing/yml/helper/bwamem-gatk-report-wf.yml index 074d16a..5e5be2c 100644 --- a/WGS-processing/yml/helper/bwamem-gatk-report-wf.yml +++ b/WGS-processing/yml/helper/bwamem-gatk-report-wf.yml @@ -2,18 +2,22 @@ sample: ERR1726424 reference: class: File + format: edam:format_1929 location: keep:a3af04432df3d71d22f2fe8be549ba96+5974/hg38.fa fastq1: class: File + format: edam:format_1930 location: keep:c96565a96cd428fe92bf70e97488bd80+21857/ERR1726424_1.fastq/ERR1726424_1.fastq.gz fastq2: class: File + format: edam:format_1930 location: keep:0ea6e3aaa6ead18a2cc4ba67a22939e9+25007/ERR1726424_2.fastq/ERR1726424_2.fastq.gz clinvarvcf: class: File + format: edam:format_3016 location: keep:242ba3b9049aee86ab2c72db4f3b2822+223/38/clinvar.vcf.gz reportfunc: @@ -22,14 +26,17 @@ reportfunc: headhtml: class: File + format: edam:format_1964 location: /data-sdd/pgp/arvados-tutorial/src/annotation/head.html tailhtml: class: File + format: edam:format_1964 location: /data-sdd/pgp/arvados-tutorial/src/annotation/tail.html scattercount: '32' knownsites: class: File + format: edam:format_3016 location: keep:7c0b13bda857fa15d88c1039182f69d5+8052/Homo_sapiens_assembly38.known_indels.vcf.gz diff --git a/WGS-processing/yml/helper/fastqc.yml b/WGS-processing/yml/helper/fastqc.yml index 53f4d7e..36bf7e1 100644 --- a/WGS-processing/yml/helper/fastqc.yml +++ b/WGS-processing/yml/helper/fastqc.yml @@ -1,7 +1,9 @@ fastq1: class: File + format: edam:format_1930 location: keep:c96565a96cd428fe92bf70e97488bd80+21857/ERR1726424_1.fastq/ERR1726424_1.fastq.gz fastq2: class: File + format: edam:format_1930 location: keep:0ea6e3aaa6ead18a2cc4ba67a22939e9+25007/ERR1726424_2.fastq/ERR1726424_2.fastq.gz diff --git a/WGS-processing/yml/helper/gatk-applyBQSR-with-interval.yml b/WGS-processing/yml/helper/gatk-applyBQSR-with-interval.yml index 6259b09..c992b4f 100644 --- a/WGS-processing/yml/helper/gatk-applyBQSR-with-interval.yml +++ b/WGS-processing/yml/helper/gatk-applyBQSR-with-interval.yml @@ -1,9 +1,11 @@ bam: class: File + format: edam:format_2572 location: keep:79407f4f0d46a44fcc9c377461ee85fc+53752/marked_dupsERR1726424.sorted.bam reference: class: File + format: edam:format_1929 location: keep:a3af04432df3d71d22f2fe8be549ba96+5974/hg38.fa sample: ERR1726424 diff --git a/WGS-processing/yml/helper/gatk-haplotypecaller-with-interval.yml b/WGS-processing/yml/helper/gatk-haplotypecaller-with-interval.yml index 4c42573..b46c700 100644 --- a/WGS-processing/yml/helper/gatk-haplotypecaller-with-interval.yml +++ b/WGS-processing/yml/helper/gatk-haplotypecaller-with-interval.yml @@ -1,10 +1,15 @@ bam: class: File + format: edam:format_2572 location: keep:377c02de508dff9e4474f9a48d754933+53821/marked_dupsERR1726424.sorted.bam + reference: class: File + format: edam:format_1929 location: keep:a3af04432df3d71d22f2fe8be549ba96+5974/hg38.fa + intervallist: class: File location: keep:4d4947f6637f0acec32580e09d991967+815/0000-scattered.interval_list + sample: ERR1726424 diff --git a/WGS-processing/yml/helper/gatk-selectvariants.yml b/WGS-processing/yml/helper/gatk-selectvariants.yml index 972459b..49d918c 100644 --- a/WGS-processing/yml/helper/gatk-selectvariants.yml +++ b/WGS-processing/yml/helper/gatk-selectvariants.yml @@ -1,9 +1,11 @@ gvcf: class: File + format: edam:format_3016 location: keep:3b34d300671c8dc8d1b2327f6ddab140+587/ERR1726424.g.vcf.gz reference: class: File + format: edam:format_1929 location: keep:a3af04432df3d71d22f2fe8be549ba96+5974/hg38.fa sample: ERR1726424 diff --git a/WGS-processing/yml/helper/gatk-splitintervals.yml b/WGS-processing/yml/helper/gatk-splitintervals.yml index 68dbcc4..6c1c24a 100644 --- a/WGS-processing/yml/helper/gatk-splitintervals.yml +++ b/WGS-processing/yml/helper/gatk-splitintervals.yml @@ -1,5 +1,6 @@ reference: class: File + format: edam:format_1929 location: keep:a3af04432df3d71d22f2fe8be549ba96+5974/hg38.fa sample: ERR1726424 diff --git a/WGS-processing/yml/helper/gatk-wf-with-interval.yml b/WGS-processing/yml/helper/gatk-wf-with-interval.yml index e1e2b94..22a9af5 100644 --- a/WGS-processing/yml/helper/gatk-wf-with-interval.yml +++ b/WGS-processing/yml/helper/gatk-wf-with-interval.yml @@ -1,9 +1,11 @@ bam: class: File + format: edam:format_2572 location: keep:377c02de508dff9e4474f9a48d754933+53821/marked_dupsERR1726424.sorted.bam reference: class: File + format: edam:format_1929 location: keep:a3af04432df3d71d22f2fe8be549ba96+5974/hg38.fa intervallist: @@ -14,4 +16,5 @@ sample: ERR1726424 knownsites: class: File + format: edam:format_3016 location: keep:7c0b13bda857fa15d88c1039182f69d5+8052/Homo_sapiens_assembly38.known_indels.vcf.gz diff --git a/WGS-processing/yml/helper/gvcf-to-vcf.yml b/WGS-processing/yml/helper/gvcf-to-vcf.yml index 270836e..36186d5 100644 --- a/WGS-processing/yml/helper/gvcf-to-vcf.yml +++ b/WGS-processing/yml/helper/gvcf-to-vcf.yml @@ -1,5 +1,6 @@ gvcf: class: File + format: edam:format_3016 location: keep:02615a79bbe37b48629db97ab43147ae+1123/hu297A5D_AE2CH6SK4DG.gatk.g.vcf -samplename: hu297A5D_AE2CH6SK4DG +sample: hu297A5D_AE2CH6SK4DG diff --git a/WGS-processing/yml/helper/mark-duplicates.yml b/WGS-processing/yml/helper/mark-duplicates.yml index 5e68b88..cc55782 100644 --- a/WGS-processing/yml/helper/mark-duplicates.yml +++ b/WGS-processing/yml/helper/mark-duplicates.yml @@ -1,3 +1,4 @@ bam: class: File + format: edam:format_2572 location: keep:713b093318f16861084d17a252eef710+12715/WGC069888D.bam diff --git a/WGS-processing/yml/helper/samtools-index.yml b/WGS-processing/yml/helper/samtools-index.yml index 72a01f7..3f77479 100644 --- a/WGS-processing/yml/helper/samtools-index.yml +++ b/WGS-processing/yml/helper/samtools-index.yml @@ -1,3 +1,4 @@ bam: class: File + format: edam:format_2572 location: keep:a0ca1f68836aac0bcefaed9cf5c63200+68/out.sorted.bam