name: "gatk4_collectsvevidence"
description: Gathers paired-end and split read evidence files for use in the GATK-SV pipeline. Output files are a file containing the location of and orientation of read pairs marked as discordant, and a file containing the clipping location of all soft clipped reads and the orientation of the clipping.
keywords:
  - gatk4
  - collectsvevidence
  - structural variants
  - metrics
tools:
  - "gatk4":
      description: "Genome Analysis Toolkit (GATK4)"
      homepage: "https://gatk.broadinstitute.org/hc/en-us"
      documentation: "None"
      tool_dev_url: "https://github.com/broadinstitute/gatk"
      doi: "10.1158/1538-7445.AM2017-3590"
      licence: "['BSD-3-clause']"

input:
  - meta:
      type: map
      description: |
        Groovy Map containing sample information
        e.g. [ id:'test', single_end:false ]
  - input:
      type: file
      description: BAM/CRAM/SAM file
      pattern: "*.{bam,cram,sam}"
  - input_index:
      type: file
      description: Index of the BAM/CRAM/SAM file
      pattern: "*.{bai,crai,sai}"
  - allele_count_vcf:
      type: file
      description: Optional - input VCF of SNPs marking loci for allele counts, needed for the allele counts output
      pattern: "*.vcf.gz"
  - allele_count_vcf_index:
      type: file
      description: Optional - index of the VCF file, needed for the allele counts output
      pattern: "*.tbi"
  - fasta:
      type: file
      description: Optional - reference FASTA file needed when the input is a CRAM file
      pattern: "*.{fasta,fa}"
  - fasta_fai:
      type: file
      description: Optional - index of the reference FASTA file needed when the input is a CRAM file
      pattern: "*.fai"
  - dict:
      type: file
      description: Optional - sequence dictionary of the reference FASTA file needed when the input is a CRAM file
      pattern: "*.dict"

output:
  - meta:
      type: map
      description: |
        Groovy Map containing sample information
        e.g. [ id:'test', single_end:false ]
  - versions:
      type: file
      description: File containing software versions
      pattern: "versions.yml"
  - split_read_evidence:
      type: file
      description: Output file for split read evidence
      pattern: "*.sr.txt.gz"
  - split_read_evidence_index:
      type: file
      description: Index of the output file for split read evidence
      pattern: "*.sr.txt.gz.tbi"
  - paired_end_evidence:
      type: file
      description: Output file for paired end evidence
      pattern: "*.pe.txt.gz"
  - paired_end_evidence_index:
      type: file
      description: Index of the output file for paired end evidence
      pattern: "*.pe.txt.gz.tbi"
  - allele_counts:
      type: file
      description: Output file for allele counts
      pattern: "*.ld.txt.gz"
  - allele_counts_index:
      type: file
      description: Index of the output file for allele counts
      pattern: "*.ld.txt.gz.tbi"

authors:
  - "@nvnieuwk"