view dfast.xml @ 0:6ddc8a6503e7 draft default tip

planemo upload for repository https://github.com/quadram-institute-bioscience/galaxy-tools/tree/master/tools/dfast

<tool id="dfast" name="dfast" version="@VERSION@">
  <description>prokaryotic genome annotation</description>
    <macros>
        <import>macros.xml</import>
    </macros>
    <expand macro="requirements" />
    <expand macro="version_command" />
    <command detect_errors="exit_code"><![CDATA[
    #import re
    #if $ortho.use
      #set $ref_set_str = ''
      #set $divisor = ''  
      #for $i_file in $ortho.refs:
        #set $ref_set_str = $ref_set_str + $divisor + "{}".format($i_file)
        #set $divisor = ';'  ### will create "A ; B ; C "
      #end for
    #end if
    #if $genome_input.is_of_type('fasta'):
      ln -s ${genome_input}  in.fasta && 
    #elif $genome_input.is_of_type('fasta.gz'):
      gunzip -c ${genome_input} > in.fasta &&
    #elif $genome_input.is_of_type('fasta.bz2'):
      bunzip2 -c ${genome_input} > in.fasta &&
    #end if
    dfast -g in.fasta 
      -o OUT
      --cpu \${GALAXY_SLOTS:-1}
      --aligner ${aligner} 
      --gcode ${gcode} 
      --use_original_name ${use_orig_name}
      --sort_sequence ${sort_sequence}
      --use_separate_tags ${separate_tags}
      #if str($min_length) != ""
        --minimum_length ${min_length}
      #end if
      #if $ortho.use
        --references "${ref_set_str}"
      #end if
      ${fix_origin}
    ]]></command>
  <inputs>
    <param name="genome_input" multiple="false" format="fasta, fasta.gz, fasta.bz2" type="data" label="Genome to be annotated, in fasta format (can be zipped)"/>

    <param name="aligner" type="select" label="Aligner" help="Safer to leave the default (ghostx)">
        <option value="ghostx" selected="true">ghostx (default)</option>
        <option value="blastp">blastp (experimental, since didn't pass local tests) </option>
    </param>

    <param name="gcode" type="select" label="Genetic code">
        <option value="11" selected="true">Default</option>
        <option value="4">Mycoplasma</option>
    </param>

    <param name="use_orig_name" type="boolean" truevalue="t" falsevalue="f" checked="false" help="--use_original_name" label="Use original sequence names in a query FASTA file"/>

    <param name="sort_sequence" type="boolean" truevalue="t" falsevalue="f" checked="true" help="--sort_sequence" label="Sort sequences by length"/>

    <param name="min_length" type="integer" label="Minimum sequence length (default:200)" help="--minimum_length" optional="true" />

    <param name="separate_tags" type="boolean" truevalue="t" falsevalue="f" checked="true" help="--use_separate_tags" label="Use separate tags according to feature types"/>

    <param name="fix_origin" type="boolean" truevalue="--fix_origin" falsevalue="" checked="false" help="--fix_origin"
      label="Rotate/flip the chromosome so that the dnaA gene comes first. (ONLY FOR A FINISHED GENOME)" />

    <conditional name="ortho">
      <param name="use" type="boolean" checked="false" help="--references" label="orthologous gene assignment with OrthoSearch"/>
      <when value="true">
        <param name="refs" type="data" multiple="true" format="genbank,embl,asn1" label="One or more genbank reference genomes">
          <help><![CDATA[
            OrthoSearch conducts all-against-all protein alignments between the given reference genomes to infer orthologous genes.
          ]]></help>
        </param>
      </when>
      <when value="false"> </when>
    </conditional>
  </inputs>
  <outputs>
    <data name="g_embl" format="embl" label="Annotated genome in EMBL format" from_work_dir="OUT/genome.embl"/>
    <data name="g_gbk" format="genbank" label="Annotated genome in GENBANK format" from_work_dir="OUT/genome.gbk"/>
    <data name="g_gff" format="gff"   label="Annotated genome in GFF format" from_work_dir="OUT/genome.gff"/>
    <data name="e_fsa" format="fasta" label="fsa file for Genbank submission" from_work_dir="OUT/genbank/genbank.fsa"/>
    <data name="e_tbl" format="txt"   label="tbl file for Genbank submission" from_work_dir="OUT/genbank/genbank.tbl"/>
    <data name="e_fsa" format="fasta" label="fasta file for DDBJ submission" from_work_dir="OUT/ddbj/mss.fasta"/>
    <data name="e_fsa" format="txt"   label="ann file for DDBJ submission" from_work_dir="OUT/ddbj/mss.ann"/>
    <data name="g_fna" format="fasta" label="Genome sequences in fasta format" from_work_dir="OUT/genome.fna"/>
    <data name="p_faa" format="fasta" label="Predicted proteins (fasta)" from_work_dir="OUT/protein.faa"/>
    <data name="r_fna" format="fasta" label="Predicted RNAs (fasta)" from_work_dir="OUT/rna.fna"/>
    <data name="c_fna" format="fasta" label="Predicted CDs (fasta)" from_work_dir="OUT/cds.fna"/>
    <data name="stats" format="tabular" label="overall statistics" from_work_dir="OUT/statistics.txt"/>
  </outputs>
  <tests>
    <test>
      <param name="genome_input" value="test.genome.fna"/>
      <param name="fast" value="true"/>
      <param name="inputtre" value="HOG1.tre,HOG2.tre,HOG3.tre,HOG4.tre,HOG5.tre"/>
      <output name="stats" file="statistics.txt"/>
    </test>
  </tests>
    <help><![CDATA[
      DFAST is a flexible and customizable pipeline for prokaryotic genome annotation as well as data submission to the
      INSDC. It is originally developed as the background engine for the DFAST web service and is also available as a
      stand-alone command-line tool.

      DFAST can annotate a typical-sized bacterial genome within several minutes. In addition to the conventional
      homology search, it features unique functions such as orthologous gene assignment between reference genomes,
      pseudo/frameshifted gene prediction, and conserved domain search.

      This galaxy tool may be incomplete, please let us know if there is any missing functionality. 
    ]]></help>
    <expand macro="citations" />
</tool>