name: ngscheckmate_ncm
description: Determining whether sequencing data comes from the same individual by using SNP matching. Designed for humans on vcf or bam files.
keywords:
  - ngscheckmate
  - matching
  - snp
tools:
  - ngscheckmate:
      description: NGSCheckMate is a software package for identifying next generation sequencing (NGS) data files from the same individual, including matching between DNA and RNA.
      homepage: https://github.com/parklab/NGSCheckMate
      documentation: https://github.com/parklab/NGSCheckMate
      tool_dev_url: https://github.com/parklab/NGSCheckMate
      doi: "doi:/10.1093/nar/gkx193"
      licence: ["MIT"]

input:
  - files:
      type: file
      description: VCF or BAM files for each sample, in a merged channel (possibly gzipped). BAM files require an index too.
      pattern: "*.{vcf,vcf.gz,bam,bai}"

  - snp_bed:
      type: file
      description: BED file containing the SNPs to analyse
      pattern: "*.{bed}"

  - fasta:
      type: file
      description: fasta file for the genome, only used in the bam mode
      pattern: "*.{bed}"

output:
  - versions:
      type: file
      description: File containing software versions
      pattern: "versions.yml"

  - pdf:
      type: file
      description: A pdf containing a dendrogram showing how the samples match up
      pattern: "*.{pdf}"

  - corr_matrix:
      type: file
      description: A text file containing the correlation matrix between each sample
      pattern: "*corr_matrix.txt"

  - matched:
      type: file
      description: A txt file containing only the samples that match with each other
      pattern: "*matched.txt"

  - all:
      type: file
      description: A txt file containing all the sample comparisons, whether they match or not
      pattern: "*all.txt"

  - vcfs:
      type: file
      description: If ran in bam mode, vcf files for each sample giving the SNP calls
      pattern: "*.vcf"

authors:
  - "@sppearce"