name: gtdbtk_classifywf
description: GTDB-Tk is a software toolkit for assigning objective taxonomic classifications to bacterial and archaeal genomes based on the Genome Database Taxonomy GTDB.
keywords:
  - GTDB taxonomy
  - taxonomic classification
tools:
  - gtdbtk:
      description: GTDB-Tk is a software toolkit for assigning objective taxonomic classifications to bacterial and archaeal genomes based on the Genome Database Taxonomy GTDB.
      homepage: https://ecogenomics.github.io/GTDBTk/
      documentation: https://ecogenomics.github.io/GTDBTk/
      tool_dev_url: https://github.com/Ecogenomics/GTDBTk
      doi: "10.1093/bioinformatics/btz848"
      licence: ['GNU General Public v3 (GPL v3)']

input:
  - meta:
      type: map
      description: |
        Groovy Map containing sample information
        e.g. [ id:'test', single_end:false,  assembler:'spades' ]
  - bins:
      type: The binned fasta files from the assembler
      description: Fasta files
      pattern: "*.{fasta,fa}"
  - database:
      type: The local copy of the taxonomic database used by GTDB-tk
      description: The unzipped copy of the database
      pattern: "*"

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"
  - summary:
      type: file
      description: A TSV summary file for the classification
      pattern: "*.{summary.tsv}"
  - tree:
      type: file
      description: NJ or UPGMA tree in Newick format produced from a multiple sequence alignment
      pattern: "*.{classify.tree.gz}"
  - markers:
      type: file
      description: A TSV summary file lineage markers used for the classification.
      pattern: "*.{markers_summary.tsv}"
  - msa:
      type: file
      description: Multiple sequence alignments file.
      pattern: "*.{msa.fasta.gz}"
  - user_msa:
      type: file
      description: Multiple sequence alignments file for the user-provided files.
      pattern: "*.{user_msa.fasta.gz}"
  - filtered:
      type: file
      description: A list of genomes with an insufficient number of amino acids in MSA..
      pattern: "*.{filtered.tsv}"
  - log:
      type: file
      description: GTDB-tk log file
      pattern: "*.{log}"
  - warnings:
      type: file
      description: GTDB-tk warnings log file
      pattern: "*.{warnings.log}"
  - failed:
      type: file
      description: A TSV summary of the genomes which GTDB-tk failed to classify.
      pattern: "*.{failed_genomes.tsv}"
authors:
  - "@skrakau"
  - "@abhi18av"