45653db5fb11364034e3ead3a1c5d8fc508afe3b
[arvados-tutorial.git] / WGS-processing / cwl / helper / scatter-gatk-wf-with-interval.cwl
1 cwlVersion: v1.1
2 class: Workflow
3 label: Scattered variant calling workflow  
4
5 requirements:
6   - class: SubworkflowFeatureRequirement
7   - class: ScatterFeatureRequirement
8
9 inputs:
10   bam:
11     type: File
12     format: edam:format_2572 # BAM
13     label: Indexed sorted BAM with labeled duplicates
14     secondaryFiles:
15       - .bai
16   reference:
17     type: File
18     format: edam:format_1929 # FASTA
19     label: Reference genome
20     secondaryFiles:
21       - .amb
22       - .ann
23       - .bwt
24       - .pac
25       - .sa
26       - .fai
27       - ^.dict
28   sample: 
29     type: string
30     label: Sample Name
31   knownsites1:
32     type: File
33     format: edam:format_3016 # VCF
34     label: VCF of known polymorphic sites for BQSR
35     secondaryFiles:
36       - .tbi
37   scattercount: 
38     type: string
39     label: Desired split for variant calling
40
41 outputs:
42   gatheredgvcf:
43     type: File
44     format: edam:format_3016 # GVCF
45     label: Gathered GVCF 
46     secondaryFiles: 
47       - .tbi
48     outputSource: gather-GVCFs/gatheredgvcf
49     
50 steps:
51   splitintervals:
52     run: gatk-splitintervals.cwl
53     in:
54       reference: reference
55       sample: sample
56       scattercount: scattercount
57     out: [intervalfiles]
58       
59   recal-haplotypecaller: 
60     run: gatk-wf-with-interval.cwl
61     scatter: intervallist
62     in:
63       bam: bam
64       reference: reference
65       sample: sample
66       knownsites1: knownsites1
67       intervallist: splitintervals/intervalfiles
68     out: [gvcf]
69
70   gather-GVCFs:
71     run: gather-array-vcf.cwl
72     in:
73       gvcfarray: recal-haplotypecaller/gvcf
74       sample: sample
75       reference: reference
76     out: [gatheredgvcf] 
77
78 s:codeRepository: https://github.com/arvados/arvados-tutorial
79 s:license: https://www.gnu.org/licenses/agpl-3.0.en.html
80
81 $namespaces:
82  s: https://schema.org/
83  edam: http://edamontology.org/
84
85 $schemas:
86  - https://schema.org/version/latest/schema.rdf
87  - http://edamontology.org/EDAM_1.18.owl