Arvados-DCO-1.1-Signed-off-by: Sarah Wait Zaranek <swz@curii.com>
no issue #
cwlVersion: v1.1
class: Workflow
cwlVersion: v1.1
class: Workflow
+label: WGS processing workflow for single sample
requirements:
- class: SubworkflowFeatureRequirement
inputs:
requirements:
- class: SubworkflowFeatureRequirement
inputs:
- fastq1: File
- fastq2: File
+ fastq1:
+ type: File
+ format: edam:format_1930 # FASTQ
+ label: One of set of pair-end FASTQs (R1)
+ fastq2:
+ type: File
+ format: edam:format_1930 # FASTQ
+ label: One of set of pair-end FASTQs (R2)
+ format: edam:format_1929 # FASTA
+ label: Reference genome
secondaryFiles:
- .amb
- .ann
secondaryFiles:
- .amb
- .ann
+ sample:
+ type: string
+ label: Sample Name
+ format: edam:format_3016 # VCF
+ label: VCF of known polymorphic sites for BQSR
- scattercount: string
- clinvarvcf: File
- reportfunc: File
- headhtml: File
- tailhtml: File
+ scattercount:
+ type: string
+ label: Desired split for variant calling
+ clinvarvcf:
+ type: File
+ format: edam:format_3016 # VCF
+ label: Reference VCF for ClinVar
+ reportfunc:
+ type: File
+ label: Function used to create HTML report
+ headhtml:
+ type: File
+ format: edam:format_1964 # HTML
+ label: Header for HTML report
+ tailhtml:
+ type: File
+ format: edam:format_1964 # HTML
+ label: Footer for HTML report
outputs:
qc-html:
type: File[]
outputs:
qc-html:
type: File[]
+ label: FASTQ QC report
+ format: edam:format_1964 # HTML
outputSource: fastqc/out-html
qc-zip:
type: File[]
outputSource: fastqc/out-html
qc-zip:
type: File[]
+ label: Zip file of FASTQ QC report and associated data
outputSource: fastqc/out-zip
gvcf:
type: File
outputSource: haplotypecaller/gatheredgvcf
outputSource: fastqc/out-zip
gvcf:
type: File
outputSource: haplotypecaller/gatheredgvcf
+ format: edam:format_3016 # GVCF
+ label: GVCF generated from GATK
report:
type: File
outputSource: generate-report/report
report:
type: File
outputSource: generate-report/report
+ format: edam:format_1964 # HTML
+ label: ClinVar variant report
+
steps:
fastqc:
run: fastqc.cwl
steps:
fastqc:
run: fastqc.cwl
headhtml: headhtml
tailhtml: tailhtml
out: [report]
headhtml: headhtml
tailhtml: tailhtml
out: [report]
+
+s:codeRepository: https://github.com/arvados/arvados-tutorial
+s:license: https://www.gnu.org/licenses/agpl-3.0.en.html
+
+$namespaces:
+ s: https://schema.org/
+ edam: http://edamontology.org/
+
+$schemas:
+ - https://schema.org/version/latest/schema.rdf
+ - http://edamontology.org/EDAM_1.18.owl
-$namespaces:
- arv: "http://arvados.org/cwl#"
- cwltool: "http://commonwl.org/cwltool#"
class: ExpressionTool
cwlVersion: v1.1
class: ExpressionTool
cwlVersion: v1.1
-label: Create array of gvcfs to process
+label: Find matching FASTQ pairs
requirements:
InlineJavascriptRequirement: {}
requirements:
InlineJavascriptRequirement: {}
inputs:
fastqdir:
type: Directory
inputs:
fastqdir:
type: Directory
- label: Input directory of fastqs
+ label: Input directory of FASTQs
loadListing: 'shallow_listing'
loadListing: 'shallow_listing'
outputs:
fastq1:
type: File[]
outputs:
fastq1:
type: File[]
+ format: edam:format_1930 # FASTQ
+ label: Half set of pair-end FASTQs (R1)
+ format: edam:format_1930 # FASTQ
+ label: Half set of pair-end FASTQs (R2)
expression: |
${function compare(a, b) {
var baseA = a.basename;
expression: |
${function compare(a, b) {
var baseA = a.basename;
return {"fastq1": fastq1, "fastq2": fastq2, "sample": sample};
}
return {"fastq1": fastq1, "fastq2": fastq2, "sample": sample};
}
+
+
+s:codeRepository: https://github.com/arvados/arvados-tutorial
+s:license: https://www.gnu.org/licenses/agpl-3.0.en.html
+
+$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
- sample:
- type: string
- label: Sample name
knownsites:
type: File
format: edam:format_3016 # VCF
knownsites:
type: File
format: edam:format_3016 # VCF
type: File[]
outputSource: bwamem-gatk-report/gvcf
format: edam:format_3016 # GVCF
type: File[]
outputSource: bwamem-gatk-report/gvcf
format: edam:format_3016 # GVCF
- label: GVCFs generated from sets of fastqs
+ label: GVCFs generated from GATK