name: gatk4_getpileupsummaries
description: |
  Summarizes counts of reads that support reference, alternate and other alleles for given sites. Results can be used with CalculateContamination. Requires a common germline variant sites file, such as from gnomAD.
keywords:
  - gatk4
  - getpileupsumaries
  - readcountssummary
  - germlinevariantsites
tools:
  - gatk4:
      description: |
        Developed in the Data Sciences Platform at the Broad Institute, the toolkit offers a wide variety of tools
        with a primary focus on variant discovery and genotyping. Its powerful processing engine
        and high-performance computing features make it capable of taking on projects of any size.
      homepage: https://gatk.broadinstitute.org/hc/en-us
      documentation: https://gatk.broadinstitute.org/hc/en-us/categories/360002369672s
      doi: 10.1158/1538-7445.AM2017-3590

input:
  - meta:
      type: map
      description: |
        Groovy Map containing sample information
        e.g. [ id:'test' ]
  - bam:
      type: file
      description: BAM file to be summarised.
      pattern: "*.bam"
  - bai:
      type: file
      description: BAM file index.
      pattern: "*.bam.bai"
  - variants:
      type: file
      description: Population vcf of germline sequencing, containing allele fractions. Is also used as sites file if no separate sites file is specified.
      pattern: "*.vcf.gz"
  - variants_idx:
      type: file
      description: Index file for the germline resource.
      pattern: "*.vcf.gz.tbi"
  - sites:
      type: file
      description: File containing specified sites to be used for the summary. If this option is not specified, variants file is used instead automatically.
      pattern: "*.interval_list"

output:
  - pileup:
      type: file
      description: File containing the pileup summary table.
      pattern: "*.pileups.table"
  - versions:
      type: file
      description: File containing software versions
      pattern: "versions.yml"

authors:
  - "@GCJMackenzie"