view gtdbtk.xml @ 2:c22501876284 draft

planemo upload

<tool id="gtdbtk" name="GTDB-tk" version="@VERSION@">
  <description>A toolkit for assigning objective taxonomic classifications to bacterial and archaeal genomes</description>
    <macros>
        <import>macros.xml</import>
    </macros>
    <expand macro="requirements" />
    <expand macro="version_command" />
    <command detect_errors="exit_code"><![CDATA[
      #import re
      #set $bool_unz = ''
      #set $bool_zip = ''
      mkdir ./input && 
      #for $counter, $i_file in enumerate($inputseq):
        #if $i_file.is_of_type('fasta'):
          #set $bool_unz = "true"
          #set $ext = '.fasta'
        #elif $i_file.is_of_type('fasta.gz'):
          #set $bool_zip = "true"
          #set $ext = '.gz'
        #end if
        #set $_input_file = "./input/" + $i_file.element_identifier + $ext
        ln -s '${i_file}' ${_input_file} &&
      #end for
      mkdir ./output ./output_zip &&
      #if str($bool_unz) == "true"
        GTDBTK_DATA_PATH='$gtdbtk_databases.fields.path'  gtdbtk classify_wf -x fasta --genome_dir ./input --cpus  \${GALAXY_SLOTS:-4} --out_dir ./output &&
      #end if
      #if str($bool_zip) == "true"
        GTDBTK_DATA_PATH='$gtdbtk_databases.fields.path'  gtdbtk classify_wf -x gz --genome_dir ./input --cpus  \${GALAXY_SLOTS:-4} --out_dir ./output_zip &&
      #end if
      grep -h  user_genome ./output*/gtdbtk.*.summary.tsv | head -1 > output/summary.tsv &&
      grep -hv user_genome ./output*/gtdbtk.*.summary.tsv >> output/summary.tsv &&
      if [ -f ./output/gtdbtk.ar122.user_msa.fasta ]; then mv ./output/gtdbtk.ar122.user_msa.fasta ./output/archaea.fasta; fi &&
      if [ -f ./output_zip/gtdbtk.ar122.user_msa.fasta ]; then cat ./output_zip/gtdbtk.ar122.user_msa.fasta >> ./output/archaea.fasta; fi &&
      if [ -f ./output/gtdbtk.bac120.user_msa.fasta ]; then mv ./output/gtdbtk.bac120.user_msa.fasta ./output/bacteria.fasta; fi &&
      if [ -f ./output_zip/gtdbtk.bac120.user_msa.fasta ]; then cat ./output_zip/gtdbtk.bac120.user_msa.fasta >> ./output/bacteria.fasta; fi 
    ]]></command>
  <inputs>
    <param name="inputseq" multiple="true" type="data" format="fasta, fasta.gz" label="input genomes in fasta format (can be gzipped)">
      <help><![CDATA[
        Unlike the standalone program, where the output removes the suffixes, this Galaxy tools preserves the suffix (i.e. will output <i>genome1.fas</i> instead of <i>genome1</i>).
        This is to allow for mixing compressed and uncompressed files (while avoiding overwritting similarly-named ones).
        Here we also merge results from <i>gtdbtk.ar122.summary.tsv</i> and <i>gtdbtk.bac120.summary.tsv</i> files. 
        ]]></help>
    </param>

    <param label="Select a GTDB database" name="gtdbtk_databases" type="select">
      <options from_data_table="gtdbtk_databases">
        <validator message="No database is available" type="no_options" />
      </options>
    </param>

  </inputs>
  <outputs>
    <data name="summary_out" format="tabular" label="summarised taxon classification" from_work_dir="output/summary.tsv" />
    <data name="bact_out" format="fasta" label="MSA of submitted genomes inferred as bacterial" from_work_dir="output/bacteria.fasta" />
    <data name="arch_out" format="fasta" label="MSA of submitted genomes inferred as archaeal" from_work_dir="output/archaea.fasta" />
  </outputs>

  <tests>
    <test>
      <param name="inputseq" value="genome_3.fna"/>
      <param name="gtdbtk_databases" value="default_db"/>
      <output name='summary_out' file="gtdbtk.ar122.summary.tsv"/>
    </test>
  </tests>

    <help><![CDATA[
      The classify workflow consists of three steps: identify, align, and classify. The identify step calls genes using Prodigal, 
      and uses HMM models and the HMMER package to identify the 120 bacterial and 122 archaeal marker genes used for phylogenetic inference. 
      Multiple sequence alignments (MSA) are obtained by aligning marker genes to their respective HMM model. The
      align step concatenates the aligned marker genes and filters the concatenated MSA to approximately 5,000 amino
      acids. Finally, the classify step uses pplacer to find the maximum-likelihood placement of each genome in the
      GTDB-Tk reference tree. GTDB-Tk classifies each genome based on its placement in the reference tree, its
      relative evolutionary divergence, and/or average nucleotide identity (ANI) to reference genomes.  

      It will process all genomes in the directory <my_genomes> using both bacterial and archaeal marker sets and place
      the results in <output_dir>. Genomes must be in FASTA format (gzip with the extension .gz is acceptable). The
      location of genomes can also be specified using a batch file with the --batchfile flag. The batch file is a
      two column file indicating the location of each genome and the desired genome identifier (i.e., a Newick
      compatible alphanumeric string). These fields must be separated by a tab.
    ]]></help>
    <expand macro="citations" />
</tool>