comparison msgfplus_search.xml @ 15:6c751c59ce18 draft

Docker support and update for protk 1.4

14:32365fec702c

<tool id="proteomics_search_msgfplus_1" name="MSGF+ MSMS Search" version="1.0.3">
    <description>Run an MSGF+ Search</description>
    <requirements>
        <requirement type="package" version="1.3">protk</requirement>
        <requirement type="package" version="20140210">msgfplus</requirement>
        <requirement type="package" version="3_0_4388">proteowizard</requirement>
    </requirements>
    <command>
        msgfplus_search.rb

        --max-pep-len=$max_pep_len
        --max-pep-charge=$max_pep_charge
        --min-pep-charge=$min_pep_charge
        --num-reported-matches=$num_reported_matches
        --java-mem=$java_mem
        #if $pepxml_output_use:
        --pepxml
        #end if
    </command>

        </repeat>
        <param name="missed_cleavages" type="select" format="text" help="Allow peptides to contain up to this many missed enzyme cleavage sites">
            <label>Missed Cleavages Allowed</label>
            <option value="0">0</option>
            <option value="1">1</option>
            <option value="2">2</option>
        </param>
        
        <param name="cleavage_semi" type="boolean" label="Allow semi-cleaved peptides" help="This can increase search time dramatically" truevalue="--cleavage-semi" falsevalue="" />

        <param name="enzyme" type="select" format="text">

        </param>
        
        <param name="instrument" type="select" format="text">
            <label>Instrument Type</label>
            <option value="2">TOF</option>
            <option value="0">Low-res LCQ/LTQ</option>
            <option value="1">High-res LTQ</option>
        </param>

        <param name="fragment_method" type="select" format="text">
            <label>Fragmentation Method</label>

            <option value="1">Phosphorylation</option>
            <option value="2">iTRAQ</option>
            <option value="3">iTRAQPhospho</option>
        </param>

        <param name="precursor_ion_tol" help="Precursor Ion Tolerance (Da or ppm)" type="float" value="100" min="0" max="10000" label="Precursor ion tolerance"/>
        <param name="precursor_tolu" type="select" format="text">
            <label>Precursor Ion Tolerance Units</label>
            <option value="ppm">ppm</option>
            <option value="Da">Da</option>
        </param>

        <param name="max_pep_len" help="" type="integer" value="40" label="Maximum Peptide Length"/>
        <param name="min_pep_charge" help="" type="integer" value="2" label="Minimum Peptide Charge"/>
        <param name="max_pep_charge" help="" type="integer" value="3" label="Maximum Peptide Charge"/>
        <param name="num_reported_matches" help="Number of matches per spectrum to be reported" type="integer" value="1" label="Num reported matches"/>
        <param name="java_mem" help="Increase this value if you get out of memory errors" type="text" size="80" value="3500M" label="Java Memory Limit"/>
        <param name="pepxml_output_use" type="boolean" label="Convert results to pepXML" help="" truevalue="true" falsevalue="false" />
    </inputs>
    <outputs>
        <data format="mzid" name="output" metadata_source="input_file" label="MSGF+_vs_${database.dbkey if $database.has_key('dbkey') else $database.fasta_file.display_name}.${input_file.display_name}.${input_file.display_name}">
            <change_format>
                <when input="pepxml_output_use" value="true" format="raw_pepxml" metadata_source="input_file" 
                    label="MSGF+_vs_${database.dbkey if $database.has_key('dbkey') else $database.fasta_file.display_name}.${input_file.display_name}.${input_file.display_name}"/>
            </change_format>
        </data>
    </outputs>
    <tests>
        <test>
            <param name="source_select" value="input_ref"/>
              <param name="fasta_file" value="bsa.fasta"/>
                  <param name="input_file" value="bsa.mzML"/>
              <output name="output" file="bsa.mzid" compare="sim_size" delta="600" /> 
        </test>
    </tests>
    <help>

**What it does**

Runs an MS/MS database search using the MSGFPlus search engine. Output is in the form of a pepXML file containing identified peptides along with their raw search scores.

15:6c751c59ce18

<tool id="proteomics_search_msgfplus_1" name="MSGF+ MSMS Search" version="1.1.0">
    <description>Run an MSGF+ Search</description>
    <requirements>
        <container type="docker">iracooke/protk-1.4.1</container>
        <requirement type="package" version="1.4">protk</requirement>
        <requirement type="package" version="20140210">msgfplus</requirement>
        <requirement type="package" version="3_0_4388">proteowizard</requirement>
    </requirements>
    <command>
        msgfplus_search.rb

        --max-pep-len=$max_pep_len
        --max-pep-charge=$max_pep_charge
        --min-pep-charge=$min_pep_charge
        --num-reported-matches=$num_reported_matches
        --java-mem=$java_mem

        --threads $threads

        #if $pepxml_output_use:
        --pepxml
        #end if
    </command>

        </repeat>
        <param name="missed_cleavages" type="select" format="text" help="Allow peptides to contain up to this many missed enzyme cleavage sites">
            <label>Missed Cleavages Allowed</label>
            <option value="0">0</option>
            <option value="1">1</option>
            <option selected="true" value="2">2</option>
        </param>
        
        <param name="cleavage_semi" type="boolean" label="Allow semi-cleaved peptides" help="This can increase search time dramatically" truevalue="--cleavage-semi" falsevalue="" />

        <param name="enzyme" type="select" format="text">

        </param>
        
        <param name="instrument" type="select" format="text">
            <label>Instrument Type</label>
            <option value="2">TOF</option>
            <option value="0" selected="true">Low-res LCQ/LTQ</option>
            <option value="1">High-res LTQ</option>
        </param>

        <param name="fragment_method" type="select" format="text">
            <label>Fragmentation Method</label>

            <option value="1">Phosphorylation</option>
            <option value="2">iTRAQ</option>
            <option value="3">iTRAQPhospho</option>
        </param>

        <param name="precursor_ion_tol" help="Precursor Ion Tolerance (Da or ppm)" type="float" value="10" min="0" max="10000" label="Precursor ion tolerance"/>
        <param name="precursor_tolu" type="select" format="text">
            <label>Precursor Ion Tolerance Units</label>
            <option value="ppm">ppm</option>
            <option value="Da">Da</option>
        </param>

        <param name="max_pep_len" help="" type="integer" value="40" label="Maximum Peptide Length"/>
        <param name="min_pep_charge" help="" type="integer" value="2" label="Minimum Peptide Charge"/>
        <param name="max_pep_charge" help="" type="integer" value="3" label="Maximum Peptide Charge"/>
        <param name="num_reported_matches" help="Number of matches per spectrum to be reported" type="integer" value="1" label="Num reported matches"/>
        <param name="java_mem" help="Increase this value if you get out of memory errors" type="text" size="80" value="3500M" label="Java Memory Limit"/>
        <param name="threads" type="integer" value="1" label="Threads" help="Number of threads to use for search."/>        
        <param name="pepxml_output_use" checked="true" type="boolean" label="Convert results to pepXML" help="" truevalue="true" falsevalue="false" />
    </inputs>
    <outputs>
        <data format="mzid" name="output" metadata_source="input_file" label="MSGF+_vs_${database.dbkey if $database.has_key('dbkey') else $database.fasta_file.display_name}.${input_file.display_name}.${input_file.display_name}.${'pepXML' if $pepxml_output_use else 'mzid'}">
            <change_format>
                <when input="pepxml_output_use" value="true" format="raw_pepxml" metadata_source="input_file"/>
            </change_format>
        </data>
    </outputs>

    <tests>
        <!-- Just test that the tool runs and produces vaguely correct output -->
        <test>
            <param name="source_select" value="input_ref"/>
            <param name="fasta_file" value="testdb.fasta" format="fasta"/>
            <param name="input_file" value="tiny.mzML" format="mzml"/>
            <param name="precursor_ion_tol" value="200"/>
            <param name="pepxml_output_use" value="true"/>
            <output name="output" format="raw_pepxml">
                <assert_contents>
                    <has_text text="FALPQYLKTVYQHQKAMKPWIQPKTKVIPYVRYL" />
                </assert_contents>
            </output>
        </test>
    </tests>

    <help>

**What it does**

Runs an MS/MS database search using the MSGFPlus search engine. Output is in the form of a pepXML file containing identified peptides along with their raw search scores.