annotate protxml_to_gff.xml @ 2:68d8c9e521d7 draft

planemo upload for repository https://github.com/iracooke/protk-galaxytools/blob/master/protk-proteogenomics/.shed.yml commit 24e0fef2496984648a8a5cd5bff4d6b9b634a302-dirty

<tool id="protxml_to_gff" name="Proteomics to GFF" version="1.1.0">
    <description>Export Proteomics Data to GFF</description>
    <requirements>
        <container type="docker">iracooke/protk-1.4.3</container>
        <requirement type="package" version="1.4.3">protk</requirement>
        <requirement type="package" version="2.2.29">blast+</requirement>
    </requirements>
    <stdio>
        <exit_code range="1:"   level="fatal"   description="Failure" />
    </stdio>
    <command>
        protxml_to_gff.rb $protxml_file 
            #if $database.source_select=="built_in":
                -d $database.dbkey
            #else 
                -d $database.fasta_file
            #end if
            -c $gene_file
            #if str( $gffidpattern ):
                --gff-idregex='$gffidpattern'
            #end if

            #if str( $genomeidpattern ):
                --genome-idregex='$genomeidpattern'
            #end if

            #if str( $ignorepattern ):
                --ignore-regex='$ignorepattern'
            #end if
            
            --threshold=$peptide_threshold
            --prot-threshold=$prot_threshold
            $stack_charges
            -o $output
    </command>
    <inputs>
        <conditional name="database">
            <param name="source_select" type="select" label="Database source used for Proteomics Searches" help="Database should be an amino acid fasta file with entry id's that can be parsed to obtain contig or scaffold ids referenced in your gff file">
                <option value="input_ref">Your Upload File</option>
                <option value="built_in">Built-In</option>
            </param>
            <when value="built_in">
                <param name="dbkey" type="select" format="text" >
                    <label>Database</label>
                    <options from_file="pepxml_databases.loc">
                        <column name="name" index="0" />
                        <column name="value" index="2" />
                    </options>
                </param>
            </when>
            <when value="input_ref">
                <param name="fasta_file" type="data" format="fasta" label="Uploaded FASTA file" />
            </when>
        </conditional>
        <param name="protxml_file" type="data" format="protxml" multiple="false" label="Proteomics Search Results" help="A ProtXML file produced by Protein Prophet"/>
        <param name="gene_file" type="data" format="gff3" multiple="false" label="Protein coordinates" help="A gff3 file with coordinates for all protein entries used for proteomics searches. Coordinates should correspond to entries in the genome fasta file"/>
        <param name="peptide_threshold" label="Peptide Probability Threshold" type="float" value="0.95" min="0" max="1" help="Only peptides within accepted proteins and passing this threshold will appear in the output"/>
        <param name="prot_threshold" label="Protein Probability Threshold" type="float" value="0.99" min="0" max="1" help="Only peptides within proteins passing this threshold will appear in the output"/>
        <param name="stack_charges" value="false" type="boolean" label="Peptides with different charges get separate gff entries" help="" truevalue="--stack-charge-states" falsevalue="" />
        <param name="gffidpattern" size="40" type="text" value="lcl\|([^ ]*)" label="gff id regex" help="Regex with capture group for parsing gff ids from protein ids">
            <sanitizer>
            <valid initial="string.printable">
             <remove value="&apos;"/>
            </valid>
            <mapping initial="none">
              <add source="&apos;" target="__sq__"/>
            </mapping>
              </sanitizer>
        </param>

        <param name="genomeidpattern" size="40" type="text" label="genome id regex" help="Regex with capture group for parsing genomic ids from protein ids">
            <sanitizer>
            <valid initial="string.printable">
             <remove value="&apos;"/>
            </valid>
            <mapping initial="none">
              <add source="&apos;" target="__sq__"/>
            </mapping>
              </sanitizer>
        </param>        

        <param name="ignorepattern" size="40" type="text" label="ignore regex" help="Regex to match protein ids that we should ignore completely">
            <sanitizer>
            <valid initial="string.printable">
             <remove value="&apos;"/>
            </valid>
            <mapping initial="none">
              <add source="&apos;" target="__sq__"/>
            </mapping>
              </sanitizer>
        </param>        



    </inputs>
    <outputs>
        <data format="gff3" name="output" />
    </outputs>
    <tests>
      <test>
          <param name="source_select" value="input_ref"/>
          <param name="fasta_file" value="small_prot.fasta" format="fasta"/>

          <param name="protxml_file" value="small.prot.xml" format="protxml"/>
          <param name="gene_file" value="small_combined.gff" format="gff3"/>
          <output name="output" format="gff3">
              <assert_contents>
                  <has_text text="polypeptide" />
              </assert_contents>
          </output>
      </test>
    </tests>
    <help>

**What it does**

Exports peptides and proteins to gff

    </help>
</tool>