name: "multivcfanalyzer"
description: SNP table generator from GATK UnifiedGenotyper with functionality geared for aDNA
keywords:
  - vcf
  - ancient DNA
  - aDNA
  - SNP
  - GATK UnifiedGenotyper
  - SNP table
tools:
  - "multivcfanalyzer":
      description: "MultiVCFAnalyzer is a VCF file post-processing tool tailored for aDNA. License on Github repository."
      homepage: "https://github.com/alexherbig/MultiVCFAnalyzer"
      documentation: "https://github.com/alexherbig/MultiVCFAnalyzer"
      tool_dev_url: "https://github.com/alexherbig/MultiVCFAnalyzer"
      doi: "10.1038/nature13591"
      licence: "['GPL >=3']"

input:
  - vcfs:
      type: file
      description: One or a list of uncompressed VCF file
      pattern: "*.vcf"
  - fasta:
      type: file
      description: Reference genome VCF was generated against
      pattern: "*.{fasta,fna,fa}"
  - snpeff_results:
      type: file
      description: Results from snpEff in txt format (Optional)
      pattern: "*.txt"
  - gff:
      type: file
      description: GFF file corresponding to reference genome fasta (Optional)
      pattern: "*.gff"
  - allele_freqs:
      type: boolean
      description: |
        Whether to include the percentage of reads a given allele is
        present in in the SNP table.
  - genotype_quality:
      type: integer
      description: |
        Minimum GATK genotyping threshold threshold of which a SNP call
        falling under is 'discarded'
  - coverage:
      type: integer
      description: |
        Minimum number of a reads that a position must be covered by to be
        reported
  - homozygous_freq:
      type: number
      description: Fraction of reads a base must have to be called 'homozygous'
  - heterozygous_freq:
      type: mumber
      description: |
        Fraction of which whereby if a call falls above this value, and lower
        than the homozygous threshold, a base will be called 'heterozygous'.
  - gff_exclude:
      type: file
      description: |
        file listing positions that will be 'filtered' (i.e. ignored)
        (Optional)
      pattern: "*.vcf"

output:
  - versions:
      type: file
      description: File containing software versions
      pattern: "versions.yml"
  - bam:
      type: file
      description: Sorted BAM/CRAM/SAM file
      pattern: "*.{bam,cram,sam}"

  - full_alignment:
      type: file
      description: Fasta a fasta file of all positions contained in the VCF files i.e. including ref calls
      pattern: ".fasta.gz"
  - info_txt:
      type: file
      description: Information about the run
      pattern: ".txt"
  - snp_alignment:
      type: file
      description: A fasta file of just SNP positions with samples only
      pattern: ".fasta.gz"
  - snp_genome_alignment:
      type: file
      description: A fasta file of just SNP positions with reference genome
      pattern: ".fasta.gz"
  - snpstatistics:
      type: file
      description: Some basic statistics about the SNP calls of each sample
      pattern: ".tsv"
  - snptable:
      type: file
      description: Basic SNP table of combined positions taken from each VCF file
      pattern: ".tsv"
  - snptable_snpeff:
      type: file
      description: Input file for SnpEff
      pattern: ".tsv"
  - snptable_uncertainty:
      type: file
      description: Same as above, but with lower case characters indicating uncertain calls
      pattern: ".tsv"
  - structure_genotypes:
      type: file
      description: Input file for STRUCTURE
      pattern: ".tsv"
  - structure_genotypes_nomissing:
      type: file
      description: Alternate input file for STRUCTURE
      pattern: ".tsv"
  - json:
      type: file
      description: Summary statistics in MultiQC JSON format
      pattern: ".json"

authors:
  - "@jfy133"