name: gatk4_splitncigarreads
description: Splits reads that contain Ns in their cigar string
keywords:
  - vcf
  - merge
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
params:
  - outdir:
      type: string
      description: |
        The pipeline's output directory. By default, the module will
        output files into `$params.outdir/<SOFTWARE>`
  - publish_dir_mode:
      type: string
      description: |
        Value for the Nextflow `publishDir` mode parameter.
        Available: symlink, rellink, link, copy, copyNoFollow, move.
  - enable_conda:
      type: boolean
      description: |
        Run the module with Conda using the software specified
        via the `conda` directive
  - singularity_pull_docker_container:
      type: boolean
      description: |
        Instead of directly downloading Singularity images for use with Singularity,
        force the workflow to pull and convert Docker containers instead.
input:
  - meta:
      type: map
      description: |
        Groovy Map containing sample information
        e.g. [ id:'test']
  - bam:
      type: list
      description: BAM/SAM/CRAM file containing reads
      pattern: "*.{bam,sam,cram}"
  - fasta:
      type: file
      description: Reference sequence file
      pattern: "*.fasta"
output:
  - bam:
      type: file
      description: Output file with split reads (BAM/SAM/CRAM)
      pattern: "*.{bam,sam,cram}"
  - version:
      type: file
      description: File containing software version
      pattern: "*.version.txt"
authors:
  - "@kevinmenden"