<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
        #if $database.source_select=="built_in":
         --galaxy -d $database.dbkey
        #else
        --galaxy -d $database.fasta_file
        #end if

        --var-mods='
        $variable_mods
        #for $custom_variable_mod in $custom_variable_mods:
        ,${custom_variable_mod.custom_mod}
        #end for
        '

        --fix-mods='
        $fixed_mods
        #for $custom_fix_mod in $custom_fix_mods:
        ,${custom_fix_mod.custom_mod}
        #end for
        '

        $input_file 
        -o $output 
        -r 
        --enzyme=$enzyme 
        --precursor-ion-tol-units=$precursor_tolu 
        -v $missed_cleavages
        $cleavage_semi
        -p $precursor_ion_tol 
        --instrument=$instrument
        --isotope-error-range=$isotope_error_range
        --fragment-method=$fragment_method
        --protocol=$protocol
        --min-pep-len=$min_pep_len
        --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>

    <inputs>
        <conditional name="database">
            <param name="source_select" type="select" label="Database source">
                <option value="built_in">Built-In</option>
                <option value="input_ref" selected="true">Your Upload File</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="input_file" type="data" format="mzml" multiple="false" label="MSMS File" help="An mzML file with MS/MS data"/>
        <param name="variable_mods" format="text" type="select" multiple="true" label="Variable Modifications" help="Multiple Selection Allowed">
            <options from_file="msgfplus_mods.loc">
                <column name="name" index="0" />
                <column name="value" index="2" />
            </options>
        </param>
        <repeat name="custom_variable_mods" title="Custom Variable Modifications" 
            help="See https://bix-lab.ucsd.edu/pages/viewpage.action?pageId=13533355 for details on how to create these">
            <param name="custom_mod" type="text" />
        </repeat>
        <param name="fixed_mods" format="text" type="select" multiple="true" label="Fixed Modifications" help="Multiple Selection Allowed">
            <options from_file="msgfplus_mods.loc">
                <column name="name" index="0" />
                <column name="value" index="2" />
            </options>
        </param>
        <repeat name="custom_fix_mods" title="Custom Fixed Modifications" help="See https://bix-lab.ucsd.edu/pages/viewpage.action?pageId=13533355 for details on how to create these">
            <param name="custom_mod" type="text">
            </param>
        </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">
            <label>Enzyme</label>
            <option value="0">unspecific cleavage</option>
            <option value="1" selected="true">Trypsin</option>
            <option value="2">Chymotrypsin</option>
            <option value="3">Lys-C</option>
            <option value="4">Lys-N</option>
            <option value="5">glutamyl endopeptidase</option>
            <option value="6">Arg-C</option>
            <option value="7">Asp-N</option>
            <option value="8">alphaLP</option>
            <option value="9">no cleavage</option>
        </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="0">Respect Input File</option>
            <option value="1">CID</option>
            <option value="2">ETD</option>
            <option value="3">HCD</option>
            <option value="4">Merge spectra from same precursor</option>
        </param>

        <param name="protocol" type="select" format="text">
            <label>Protocol</label>
            <option value="0">NoProtocol</option>
            <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="isotope_error_range" help="Takes into account of the error introduced by chooosing a non-monoisotopic peak for fragmentation." type="text" size="80" value="0,1" label="Isotope Error Range"/>
        <param name="min_pep_len" help="" type="integer" value="6" label="Minimum Peptide Length"/>
        <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.

----

**References**

Please see http://proteomics.ucsd.edu/Software/MSGFPlus.html for details of the MSGFPlus search engine and references describing its algorithm

    </help>
</tool>