view msgfplus.xml @ 0:dbc77b37e20f draft

planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/msgfplus commit e6dd776a0df16d06df3bd2f230ca80c7420d9125-dirty

<tool id="msgfplus" name="MS-GF+" version="0.1">
    <description>
        Identifies peptides in tandem mass spectra using the MS-GF+ search engine.
    </description>
    <requirements>
        <requirement type="package" version="10089">msgfplus</requirement>
        <environment_variable name="LC_ALL" action="set_to">C</environment_variable>        
    </requirements>
    <stdio>
        <exit_code range="1:" level="fatal" description="Job Failed" />
        <regex match="java.*Exception" level="fatal" description="Java Exception"/> 
        <regex match="Could not create the Java virtual machine" level="fatal" description="JVM Error"/>
    </stdio>
    <command>
<![CDATA[
        #set $db_name = $d.display_name.replace(".fasta", "") + ".fasta"
        #set $input_name = $s.display_name
        #set $output_name = $input_name.replace(".mzML", "") + ".mzid"
        ln -s '$s' '${input_name}' &&
        ln -s '$d' '${db_name}' &&

        java -jar \$(which MSGFPlus.jar)
            -s '$input_name'
            -d '$db_name'
            -thread \${GALAXY_SLOTS:-1}

            -tda $tda
            -t $t$precursor_ion_tol_units
            -ti $advanced.isotope_low,$advanced.isotope_high
            -m $advanced.m
            -inst $inst
            -e $e
            -protocol $advanced.protocol
            -ntt $ntt
            -minLength $advanced.minLength
            -maxLength $advanced.maxLength
            -minCharge $advanced.minCharge
            -maxCharge $advanced.maxCharge
            -n $advanced.n
            -addFeatures $advanced.addFeatures
        &&
        mv '$output_name' output
]]>
    </command>
    <inputs>
        <param argument="-s" type="data" format="mzml" label="Input Raw MS File(s)"/>
        <param argument="-d" type="data" format="fasta" label="Protein Database" help="Select FASTA database from history"/>
        <param argument="-tda" type="boolean" truevalue="1" falsevalue="0" checked="true" label="Search with on-the-fly decoy database?" help="MSGF+ uses XXX_ as an accession prefix to indicate a decoy hit" />
        <param argument="-t" type="float" value="10" label="Precursor mass tolerance" help="Error tolerance for matching peptide mass to precursor ion mass"/>
        <param name="precursor_ion_tol_units" type="select" label="Precursor mass tolerance units" help="Daltons are common for low-res instruments, ppm for high-res instruments">
            <option value="ppm" selected="true">Parts per million (ppm)</option>
            <option value="Da">Daltons</option>
        </param>
        <param argument="-inst" label="Instrument type" type="select" help="The instrument type that generated the MS/MS spectra is used to determine the scoring model">
            <option value="0" selected="true">Low-res (LCQ/LTQ)</option>
            <option value="1" >High-res (LTQ-Orbitrap)</option>
            <option value="2" >Q-TOF</option>
            <option value="3" >Q-Exactive</option>
        </param>
        <param argument="-e" type="select" label="Enzyme" help="Enzyme used to digest proteins in sample preparation; trypsin is the most commonly used enzyme">
            <option value="0">Unspecific cleavage</option>
            <option value="1" selected="true">Trypsin, no P rule</option>
            <option value="2">Chymotrypsin, no P rule (FYWL)</option>
            <option value="3">Lys-C, no P rule</option>
            <option value="4">Lys-N</option>
            <option value="5">Glu-C (glutamyl endopeptidase)</option>
            <option value="6">Arg-C</option>
            <option value="7">Asp-N</option>
            <option value="8">Alpha-lytic protease</option>
            <option value="9">No enzyme</option>
        </param>
        <param argument="-ntt" type="select" format="text" label="Number of tolerable termini" help="Semi-specific requires more time than fully specific; non-specific requires much more.">
            <option value="2" selected="true">Fully specific (both termini match cleavage rules)</option>
            <option value="1">Semi-specific (at least one terminus must match cleavage rules)</option>
            <option value="0">Non-specific (neither terminus is required to match cleavage rules)</option>
        </param>
        <!--
        <param name="fixed_modifications" type="select" label="Fixed Modifications" multiple="true" help="Occurs in known places on peptide sequence. Hold the appropriate key while clicking to select multiple items">
            <options from_file="searchgui_mods.loc">
                <column name="name" index="0" />
                <column name="value" index="0" />
            </options>
        </param>
        <param name="variable_modifications" type="select" label="Variable Modifications" multiple="true" help="Can occur anywhere on the peptide sequence; adds additional error to search score. Hold the appropriate key while clicking to select multiple items">
            <options from_file="searchgui_mods.loc">
                <column name="name" index="0" />
                <column name="value" index="0" />
            </options>
        </param>-->

        <!-- MS-GF+ ADVANCED PARAMETERS -->
        <section name="advanced" title="Advanced Options">
            <param argument="-minCharge" label="Minimum precursor charge" value="2" type="integer" help="Minimum precursor charge to consider if charges are not specified in the spectrum file"/>
            <param argument="-maxCharge" label="Maximum precursor charge" value="3" type="integer" help="Maximum precursor charge to consider if charges are not specified in the spectrum file"/>
            <param argument="-minLength" label="Minimum peptide length" value="6" type="integer" help="Minimum peptide length to consider"/>
            <param argument="-maxLength" label="Maximum peptide length" value="40" type="integer" help="Maximum peptide length to consider"/>
            <param name="num_ptms" label="Maximum modifications allowed per peptide" type="integer" value="2" />
            <param argument="-m" label="Fragmentation type" type="select" help="Fragmentation method identifier (used to determine the scoring model)">
                <option value="0" selected="True">As written in the spectrum or CID if no info</option>
                <option value="1" >CID</option>
                <option value="2" >ETD</option>
                <option value="3" >HCD</option>
            </param>
            <param argument="-protocol" label="Protocol type" type="select" help="Protocols are used to enable scoring parameters for enriched and/or labeled samples">
                <option value="0" selected="True">Automatic</option>
                <option value="1" >Phosphorylation</option>
                <option value="2" >iTRAQ</option>
                <option value="3" >iTRAQPhospho</option>
                <option value="4" >TMT</option>
                <option value="5" >Standard</option>
            </param>
            <param argument="-n" label="Maximum matches per spectrum" type="integer" value="1" help="Number of peptide matches per spectrum to report" />
            <param argument="-addFeatures" label="Calculate additional scoring features?" type="boolean" truevalue="1" falsevalue="0" help="If true, several extra derivative scores are calculated for each match" />
            <param name="isotope_low" label="Lower isotope error range" type="integer" value="0" help="Takes into account of the error introduced by chooosing a non-monoisotopic peak for fragmentation (-ti)" />
            <param name="isotope_high" label="Upper isotope error range" type="integer" value="1" /> 
        </section>
    </inputs>
    <outputs>
        <data name="output" format="mzid" from_work_dir="output" />
    </outputs>
    <tests>
        <test>
            <param name="s" value="input/201208-378803.mzML" />
            <param name="d" value="input/cow.protein.PRG2012-subset.fasta" />
            <output name="output" file="201208-378803-msgf.mzid" lines_diff="12" />
        </test>
        <test>
            <param name="s" value="input/201208-378803.mzML" />
            <param name="d" value="input/cow.protein.PRG2012-subset.fasta" />
            <param name="tda" value="1" />
            <param name="t" value="0.02" />
            <param name="precursor_ion_tol_units" value="Da" />
            <param name="isotope_low" value="-1" />
            <param name="isotope_high" value="0" />
            <param name="m" value="1" />
            <param name="inst" value="1" />
            <param name="e" value="3" />
            <param name="ntt" value="1" />
            <param name="protocol" value="2" />
            <param name="minLength" value="10" />
            <param name="maxLength" value="20" />
            <param name="minCharge" value="2" />
            <param name="maxCharge" value="6" />
            <param name="n" value="2" />
            <param name="addFeatures" value="1" />
            <output name="output" file="201208-378803-msgf-2mmu-semi-tryptic.mzid" lines_diff="12" />
        </test>
    </tests>
    <help>
**What it does**

Performs protein identification via database search using MS-GF+.

    </help>
    <citations>
        <citation type="doi">10.1038/ncomms6277</citation>
        <citation type="doi">10.1021/pr8001244</citation>
        <citation type="bibtex">@misc{toolsGalaxyP, author = {Chilton, J, Gruening, B, Chambers, MC, et al.}, title = {Galaxy Proteomics Tools}, publisher = {GitHub}, journal = {GitHub repository},
                                      year = {2015}, url = {https://github.com/galaxyproteomics/tools-galaxyp}}</citation> <!-- TODO: fix substitution of commit ", commit = {$sha1$}" -->
    </citations>
</tool>