comparison msgfplus.xml @ 2:058a2ab1d462 draft

planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/msgfplus commit b4871f9659a924a68430aed3a93f4f9bad733fd6

1:797c755b9e74

<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="v10089">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}' &&

        echo \\#Mods > Mods.txt &&
        #set $common_mods = str($common_fixed_modifications) + "," + str($common_variable_modifications)
        #for $mod in $common_mods.split(",")
          echo '$mod.replace("_", ",")' >> Mods.txt &&

        #for $mod in $custom_mods
          echo '${mod.formula_or_mass},${mod.aa_specificity},${mod.fix_or_opt},${mod.position_specificity},${mod.mod_name}' >> Mods.txt &&
        #end for

        msgfjar=\$(which MSGFPlus.jar) &&
        ( [ -f "\$msgfjar" ] || (echo MSGFPlus.jar not found && exit 1)) &&

        java -jar \$msgfjar
            -s '$input_name'
            -d '$db_name'
            -thread \${GALAXY_SLOTS:-1}
            -mod Mods.txt
            -tda $tda

        &&
        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>

    <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" />
            <param name="tda" value="1" />
            <param name="ntt" value="1" />
            <param name="t" value="50" />
            <param name="precursor_ion_tol_units" value="ppm" />            
            <param name="common_fixed_modifications" value="" />
            <param name="common_variable_modifications" value="" />
            <output name="output" file="201208-378803-msgf-50ppm-semitryptic-no_mods.mzid" lines_diff="6" />
        </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="custom_mods_0|fix_or_opt" value="opt" />
            <param name="custom_mods_0|position_specificity" value="c-term" />
            <param name="custom_mods_0|mod_name" value="Gly-loss+Amide" />

            <param name="custom_mods_1|formula_or_mass" value="C10H10N5O7P" />
            <param name="custom_mods_1|aa_specificity" value="CS" />
            <param name="custom_mods_1|fix_or_opt" value="opt" />
            <param name="custom_mods_1|position_specificity" value="any" />
            <param name="custom_mods_1|mod_name" value="cGMP" />

            <output name="output" file="201208-378803-msgf-2mmu-tryptic-many_mods.mzid" lines_diff="6" />
        </test>
    </tests>
    <help>
**What it does**

2:058a2ab1d462

<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="2016.10.26">msgf_plus</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[
        #if $msgf_input.intype_selector == "single"
        #set $db_name = $msgf_input.d.display_name.replace(".fasta", "") + ".fasta"
        #set $input_name = $msgf_input.s.display_name
        ln -s '$msgf_input.s' '${input_name}' &&
        ln -s '$msgf_input.d' '${db_name}' &&
        #else if $msgf_input.intype_selector == "fractions"
        #set $db_name = $msgf_input.db_spectra.reverse.display_name.replace(".fasta", "") + ".fasta"
        #set $input_name = $msgf_input.db_spectra.forward.display_name
        ln -s '$msgf_input.db_spectra.forward' '${input_name}' &&
        ln -s '$msgf_input.db_spectra.reverse' '${db_name}' &&
        #end if
        #set $output_name = $input_name.replace(".mzML", "") + ".mzid"

        echo \\#Mods > Mods.txt &&
        #set $common_mods = str($common_fixed_modifications) + "," + str($common_variable_modifications)
        #for $mod in $common_mods.split(",")
          echo '$mod.replace("_", ",")' >> Mods.txt &&

        #for $mod in $custom_mods
          echo '${mod.formula_or_mass},${mod.aa_specificity},${mod.fix_or_opt},${mod.position_specificity},${mod.mod_name}' >> Mods.txt &&
        #end for

	msgf_plus
            -s '$input_name'
            -d '$db_name'
            -thread \${GALAXY_SLOTS:-1}
            -mod Mods.txt
            -tda $tda

        &&
        mv '$output_name' output
]]>
    </command>
    <inputs>
        <conditional name="msgf_input">
          <param name="intype_selector" type="select" label="Type of MSGF+ analysis">
            <option value="single">Single database</option>
            <option value="fractions">Prefractionated database</option>
          </param>
          <when value="single">
            <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"/>
          </when>
          <when value="fractions">
		  <param name="db_spectra" type="data_collection" collection_type="paired" 
			  label="Collection: Pairs of FASTA database (forward) and spectra (reverse)"/>
          </when>
        </conditional>
        <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>

    <outputs>
        <data name="output" format="mzid" from_work_dir="output" />
    </outputs>
    <tests>
        <test>
	    <param name="msgf_input.intype_selector" value="single" />
            <param name="msgf_input.s" value="input/201208-378803.mzML" />
            <param name="msgf_input.d" value="input/cow.protein.PRG2012-subset.fasta" />
            <param name="tda" value="1" />
            <param name="ntt" value="1" />
            <param name="t" value="50" />
            <param name="precursor_ion_tol_units" value="ppm" />            
            <param name="common_fixed_modifications" value="" />
            <param name="common_variable_modifications" value="" />
            <output name="output" file="201208-378803-msgf_20161026-50ppm-semitryptic-no_mods.mzid" compare="sim_size" delta="20" />
        </test>
        <test>
	    <param name="msgf_input.intype_selector" value="fractions" />
            <param name="msgf_input.db_spectra.forward" value="input/201208-378803.mzML" />
            <param name="msgf_input.db_spectra.reverse" value="input/cow.protein.PRG2012-subset.fasta" />
            <param name="tda" value="1" />
            <param name="ntt" value="1" />
            <param name="t" value="50" />
            <param name="precursor_ion_tol_units" value="ppm" />            
            <param name="common_fixed_modifications" value="" />
            <param name="common_variable_modifications" value="" />
            <output name="output" file="201208-378803-msgf-50ppm-semitryptic-no_mods.mzid" lines_diff="6" />
        </test>
        <test>
	    <param name="msgf_input.intype_selector" value="single" />
            <param name="msgf_input.s" value="input/201208-378803.mzML" />
            <param name="msgf_input.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="custom_mods_0|fix_or_opt" value="opt" />
            <param name="custom_mods_0|position_specificity" value="c-term" />
            <param name="custom_mods_0|mod_name" value="Gly-loss+Amide" />

            <param name="custom_mods_1|formula_or_mass" value="C10H10N5O7P" />
            <param name="custom_mods_1|aa_specificity" value="C,S" />
            <param name="custom_mods_1|fix_or_opt" value="opt" />
            <param name="custom_mods_1|position_specificity" value="any" />
            <param name="custom_mods_1|mod_name" value="cGMP" />

            <output name="output" file="201208-378803-msgf_20161026-2mmu-tryptic-many_mods.mzid" lines_diff="6" />
        </test>
    </tests>
    <help>
**What it does**