name: "vsearch_usearchglobal"
description: Compare target sequences to fasta-formatted query sequences using global pairwise alignment.
keywords:
  - vsearch
  - usearch
  - alignment
  - fasta
tools:
  - "vsearch":
      description: "VSEARCH is a versatile open-source tool for microbiome analysis, including chimera detection, clustering, dereplication and rereplication, extraction, FASTA/FASTQ/SFF file processing, masking, orienting, pair-wise alignment, restriction site cutting, searching, shuffling, sorting, subsampling, and taxonomic classification of amplicon sequences for metagenomics, genomics, and population genetics. (USEARCH alternative)"
      homepage: "https://github.com/torognes/vsearch"
      documentation: "None"
      tool_dev_url: "https://github.com/torognes/vsearch"
      doi: "doi: 10.7717/peerj.2584"
      licence: "['GPL v3-or-later OR BSD-2-clause']"

input:
  - meta:
      type: map
      description: Groovy Map containing sample information e.g. [ id:'test' ]
  - queryfasta:
      type: file
      description: Query sequences in FASTA format
      pattern: "*.{fasta,fa,fna,faa}"
  - db:
      type: file
      description: Reference database file in FASTA or UDB format
      pattern: "*"
  - idcutoff:
      type: real
      description: Reject the sequence match if the pairwise identity is lower than the given id cutoff value (value ranging from 0.0 to 1.0 included)
  - outoption:
      type: string
      description: Specify the type of output file to be generated by selecting one of the vsearch output file options
      pattern: "alnout|biomout|blast6out|mothur_shared_out|otutabout|samout|uc|userout|lcaout"
  - user_columns:
      type: string
      description: If using the `userout` option, specify which columns to include in output, with fields separated with `+` (e.g. query+target+id). See USEARCH manual for valid options. For other output options, use an empty string.

output:
  - aln:
      type: file
      description: Results in pairwise alignment format
      pattern: "*.{aln}"
  - biom:
      type: file
      description: Results in an OTU table in the biom version 1.0 file format
      pattern: "*.{biom}"
  - lca:
      type: file
      description: Last common ancestor (LCA) information about the hits of each query in tab-separated format
      pattern: "*.{lca}"
  - mothur:
      type: file
      description: Results in an OTU table in the mothur ’shared’ tab-separated plain text file format
      pattern: "*.{mothur}"
  - otu:
      type: file
      description: Results in an OTU table in the classic tab-separated plain text format
      pattern: "*.{otu}"
  - sam:
      type: file
      description: Results written in sam format
      pattern: "*.{sam}"
  - tsv:
      type: file
      description: Results in tab-separated output, columns defined by user
      pattern: "*.{tsv}"
  - txt:
      type: file
      description: Tab delimited results in blast-like tabular format
      pattern: "*.{txt}"
  - uc:
      type: file
      description: Tab delimited results in a uclust-like format with 10 columns
      pattern: "*.{uc}"
  - versions:
      type: file
      description: File containing software versions
      pattern: "versions.yml"

authors:
  - "@jtangrot"