name: vcftools
description: A set of tools written in Perl and C++ for working with VCF files
keywords: VCF
  - sort
tools:
  - vcftools:
      description: A set of tools written in Perl and C++ for working with VCF files. This package only contains the C++ libraries whereas the package perl-vcftools-vcf contains the perl libraries
      homepage: http://vcftools.sourceforge.net/
      documentation: http://vcftools.sourceforge.net/man_latest.html
      tool_dev_url: None
      doi:
      licence: ["LGPL"]

input:
  - meta:
      type: map
      description: |
        Groovy Map containing sample information
        e.g. [ id:'test', single_end:false ]
  - variant_file:
      type: file
      description: variant input file which can be vcf, vcf.gz, or bcf format.
  - bed:
      type: file
      description: bed file which can be used with different arguments in vcftools (optional)
  - diff_variant_file:
      type: file
      description: secondary variant file which can be used with the 'diff' suite of tools (optional)

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"
  - vcf:
      type: file
      description: vcf file (optional)
      pattern: "*.vcf"
  - bcf:
      type: file
      description: bcf file (optional)
      pattern: "*.bcf"
  - frq:
      type: file
      description: Allele frequency for each site (optional)
      pattern: "*.frq"
  - frq_count:
      type: file
      description: Allele counts for each site (optional)
      pattern: "*.frq.count"
  - idepth:
      type: file
      description: mean depth per individual (optional)
      pattern: "*.idepth"
  - ldepth:
      type: file
      description: depth per site summed across individuals (optional)
      pattern: "*.ildepth"
  - ldepth_mean:
      type: file
      description: mean depth per site calculated across individuals (optional)
      pattern: "*.ldepth.mean"
  - gdepth:
      type: file
      description: depth for each genotype in vcf file (optional)
      pattern: "*.gdepth"
  - hap_ld:
      type: file
      description: r2, D, and D’ statistics using phased haplotypes (optional)
      pattern: "*.hap.ld"
  - geno_ld:
      type: file
      description: squared correlation coefficient between genotypes encoded as 0, 1 and 2 to represent the number of non-reference alleles in each individual (optional)
      pattern: "*.geno.ld"
  - geno_chisq:
      type: file
      description: test for genotype independence via the chi-squared statistic (optional)
      pattern: "*.geno.chisq"
  - list_hap_ld:
      type: file
      description: r2 statistics of the sites contained in the provided input file verses all other sites (optional)
      pattern: "*.list.hap.ld"
  - list_geno_ld:
      type: file
      description: r2 statistics of the sites contained in the provided input file verses all other sites (optional)
      pattern: "*.list.geno.ld"
  - interchrom_hap_ld:
      type: file
      description: r2 statistics for sites (haplotypes) on different chromosomes (optional)
      pattern: "*.interchrom.hap.ld"
  - interchrom_geno_ld:
      type: file
      description: r2 statistics for sites (genotypes) on different chromosomes (optional)
      pattern: "*.interchrom.geno.ld"
  - tstv:
      type: file
      description: Transition / Transversion ratio in bins of size defined in options (optional)
      pattern: "*.TsTv"
  - tstv_summary:
      type: file
      description: Summary of all Transitions and Transversions (optional)
      pattern: "*.TsTv.summary"
  - tstv_count:
      type: file
      description: Transition / Transversion ratio as a function of alternative allele count (optional)
      pattern: "*.TsTv.count"
  - tstv_qual:
      type: file
      description: Transition / Transversion ratio as a function of SNP quality threshold (optional)
      pattern: "*.TsTv.qual"
  - filter_summary:
      type: file
      description: Summary of the number of SNPs and Ts/Tv ratio for each FILTER category (optional)
      pattern: "*.FILTER.summary"
  - sites_pi:
      type: file
      description: Nucleotide divergency on a per-site basis (optional)
      pattern: "*.sites.pi"
  - windowed_pi:
      type: file
      description: Nucleotide diversity in windows, with window size determined by options (optional)
      pattern: "*windowed.pi"
  - weir_fst:
      type: file
      description: Fst estimate from Weir and Cockerham’s 1984 paper (optional)
      pattern: "*.weir.fst"
  - heterozygosity:
      type: file
      description: Heterozygosity on a per-individual basis (optional)
      pattern: "*.het"
  - hwe:
      type: file
      description: Contains the Observed numbers of Homozygotes and Heterozygotes and the corresponding Expected numbers under HWE (optional)
      pattern: "*.hwe"
  - tajima_d:
      type: file
      description: Tajima’s D statistic in bins with size of the specified number in options (optional)
      pattern: "*.Tajima.D"
  - freq_burden:
      type: file
      description: Number of variants within each individual of a specific frequency in options (optional)
      pattern: "*.ifreqburden"
  - lroh:
      type: file
      description: Long Runs of Homozygosity (optional)
      pattern: "*.LROH"
  - relatedness:
      type: file
      description: Relatedness statistic based on the method of Yang et al, Nature Genetics 2010 (doi:10.1038/ng.608) (optional)
      pattern: "*.relatedness"
  - relatedness2:
      type: file
      description: Relatedness statistic based on the method of Manichaikul et al., BIOINFORMATICS 2010 (doi:10.1093/bioinformatics/btq559) (optional)
      pattern: "*.relatedness2"
  - lqual:
      type: file
      description: per-site SNP quality (optional)
      pattern: "*.lqual"
  - missing_individual:
      type: file
      description: Missingness on a per-individual basis (optional)
      pattern: "*.imiss"
  - missing_site:
      type: file
      description: Missingness on a per-site basis (optional)
      pattern: "*.lmiss"
  - snp_density:
      type: file
      description: Number and density of SNPs in bins of size defined by option (optional)
      pattern: "*.snpden"
  - kept_sites:
      type: file
      description: All sites that have been kept after filtering (optional)
      pattern: "*.kept.sites"
  - removed_sites:
      type: file
      description: All sites that have been removed after filtering (optional)
      pattern: "*.removed.sites"
  - singeltons:
      type: file
      description: Location of singletons, and the individual they occur in (optional)
      pattern: "*.singeltons"
  - indel_hist:
      type: file
      description: Histogram file of the length of all indels (including SNPs) (optional)
      pattern: "*.indel_hist"
  - hapcount:
      type: file
      description: Unique haplotypes within user specified bins (optional)
      pattern: "*.hapcount"
  - mendel:
      type: file
      description: Mendel errors identified in trios (optional)
      pattern: "*.mendel"
  - format:
      type: file
      description: Extracted information from the genotype fields in the VCF file relating to a specfied FORMAT identifier (optional)
      pattern: "*.FORMAT"
  - info:
      type: file
      description: Extracted information from the INFO field in the VCF file (optional)
      pattern: "*.INFO"
  - genotypes_matrix:
      type: file
      description: |
        Genotypes output as large matrix.
        Genotypes of each individual on a separate line.
        Genotypes are represented as 0, 1 and 2, where the number represent that number of non-reference alleles.
        Missing genotypes are represented by -1 (optional)
      pattern: "*.012"
  - genotypes_matrix_individual:
      type: file
      description: Details the individuals included in the main genotypes_matrix file (optional)
      pattern: "*.012.indv"
  - genotypes_matrix_position:
      type: file
      description: Details the site locations included in the main genotypes_matrix file (optional)
      pattern: "*.012.pos"
  - impute_hap:
      type: file
      description: Phased haplotypes in IMPUTE reference-panel format (optional)
      pattern: "*.impute.hap"
  - impute_hap_legend:
      type: file
      description: Impute haplotype legend file (optional)
      pattern: "*.impute.hap.legend"
  - impute_hap_indv:
      type: file
      description: Impute haplotype individuals file (optional)
      pattern: "*.impute.hap.indv"
  - ldhat_sites:
      type: file
      description: Output data in LDhat format, sites (optional)
      pattern: "*.ldhat.sites"
  - ldhat_locs:
      type: file
      description: output data in LDhat format, locations (optional)
      pattern: "*.ldhat.locs"
  - beagle_gl:
      type: file
      description: Genotype likelihoods for biallelic sites (optional)
      pattern: "*.BEAGLE.GL"
  - beagle_pl:
      type: file
      description: Genotype likelihoods for biallelic sites (optional)
      pattern: "*.BEAGLE.PL"
  - ped:
      type: file
      description: output the genotype data in PLINK PED format (optional)
      pattern: "*.ped"
  - map_:
      type: file
      description: output the genotype data in PLINK PED format (optional)
      pattern: "*.map"
  - tped:
      type: file
      description: output the genotype data in PLINK PED format (optional)
      pattern: "*.tped"
  - tfam:
      type: file
      description: output the genotype data in PLINK PED format (optional)
      pattern: "*.tfam"
  - diff_sites_in_files:
      type: file
      description: Sites that are common / unique to each file specified in optional inputs (optional)
      pattern: "*.diff.sites.in.files"
  - diff_indv_in_files:
      type: file
      description: Individuals that are common / unique to each file specified in optional inputs (optional)
      pattern: "*.diff.indv.in.files"
  - diff_sites:
      type: file
      description: Discordance on a site by site basis, specified in optional inputs (optional)
      pattern: "*.diff.sites"
  - diff_indv:
      type: file
      description: Discordance on a individual by individual basis, specified in optional inputs (optional)
      pattern: "*.diff.indv"
  - diff_discd_matrix:
      type: file
      description: Discordance matrix between files specified in optional inputs (optional)
      pattern: "*.diff.discordance.matrix"
  - diff_switch_error:
      type: file
      description: Switch errors found between sites (optional)
      pattern: "*.diff.switch"

authors:
  - "@Mark-S-Hill"