view peptide_prophet.xml @ 16:1b86e378de37 draft

Fix tabular outputs. Export XML_ONLY variable

<tool id="proteomics_search_peptide_prophet_1" name="Peptide Prophet" version="1.1.1">
    <description>Calculate Peptide Prophet statistics on search results</description>
    <requirements>
        <container type="docker">iracooke/protk-1.4.3</container>
        <requirement type="package" version="1.4.3">protk</requirement>
        <requirement type="package" version="4.8.0">trans_proteomic_pipeline</requirement>
    </requirements>
    <command>
        # This should be in the tpp_package.
        # A hack for now
            export XML_ONLY="true";

        peptide_prophet.rb
            --galaxy $input_file
            -o peptide_prophet_output.pep.xml
            -r 
            $glyco 
            $useicat 
            $phospho 
            $usepi
            $usert
            $accurate_mass
            $no_ntt
            $no_nmc
            $use_gamma
            $use_only_expect
            $force_fit
            $allow_alt_instruments
            $maldi
            $usedecoys
            --decoy-prefix $decoy_prefix_string

            #if $experiment_label
                --experiment-label $experiment_label
            #end if

            --p-thresh $p_thresh
            --threads "\${GALAXY_SLOTS:-12}"


    </command>
    <inputs>
        <param name="input_file" type="data" format="pepxml,raw_pepxml" multiple="false" label="Raw Search Results" help="These files will typically be outputs from omssa or xtandem search tools"/>

        <param name="glyco" type="boolean" label="Expect true positives to have a glycocapture motif" truevalue="--glyco" falsevalue=""/>
        <param name="useicat" type="boolean" label="Use icat information" truevalue="--useicat" falsevalue=""/>
        <param name="phospho" type="boolean" label="Use phospho information" truevalue="--phospho" falsevalue=""/>
        <param name="usepi" type="boolean" label="Use pI information" truevalue="--usepi" falsevalue=""/>
        <param name="usert" type="boolean" label="Use hydrophobicity / RT information" truevalue="--usert" falsevalue=""/>
        <param name="accurate_mass" type="boolean" label="Use accurate mass binning" truevalue="--accurate-mass" falsevalue=""/>
        <param name="no_ntt" type="boolean" label="Don't use NTT model" truevalue="--no-ntt" falsevalue=""/>
        <param name="no_nmc" type="boolean" label="Don't use NMC model" truevalue="--no-nmc" falsevalue=""/>
        <param name="use_gamma" type="boolean" label="Use Gamma distribution to model the negatives" help="Applies only to X!Tandem results" truevalue="--usegamma" falsevalue=""/>
        <param name="use_only_expect" type="boolean" label="Only use Expect Score as the discriminant" help="Applies only to X!Tandem results. 
            Helpful for data with homologous top hits e.g. phospho or glyco" truevalue="--use-only-expect" falsevalue=""/>
        <param name="force_fit" type="boolean" label="Force fitting" help="Bypasses automatic mixture model checks and forces fitting of a mixture model" truevalue="--force-fit" falsevalue=""/>
        <param name="allow_alt_instruments" type="boolean" label="Allow multiple instrument types" help="Warning instead of exit with error if instrument types between runs is different" truevalue="--allow-alt-instruments" falsevalue=""/>
        <param name="maldi" type="boolean" label="Maldi data" truevalue="-l" falsevalue=""/>
        <param name="usedecoys" type="boolean" label="Use decoys to pin down the negative distribution" truevalue="" falsevalue="--no-decoy"/>
        <param name="decoy_prefix_string" help="Prefix string for decoy ids" type="text" value="decoy_" label="Decoy Prefix String" size="20"/>    
        <param name="experiment_label" help="Used to commonly label all spectra from one experiment" type="text" value="" label="Experiment Label" size="20"/>
        <param name="p_thresh" help="Peptides scoring less than this value are discarded" type="float" value="0.05" min="0" max="1" label="Probability Threshold"/>
    </inputs>
    <outputs>
        <data format="peptideprophet_pepxml" name="output" metadata_source="input_file" label="peptide_prophet.${input_file.display_name}.pep.xml" from_work_dir="peptide_prophet_output.pep.xml"/>
    </outputs>
    <help>

**What it does**

Given raw search engine scores as inputs this tool estimates the accuracy of peptide assignments.

----

**Citation**

If you use this tool please read and cite the paper describing the statistical model implemented by Peptide Prophet

Keller A., et al. “Empirical Statistical Model to Estimate the Accuracy of Peptide Identifications Made by MS/MS and Database Search” *Anal. Chem.* 74, 5383-5392 (2002).


    </help>


<!--PeptideProphet options [following the 'O']:
                 i [use icat information in PeptideProphet]
                 f [do not use icat information in PeptideProphet]
                 g [use N-glyc motif information in PeptideProphet]
                 H [use Phospho information in PeptideProphet]
                 m [maldi data]
                 I [use pI information in PeptideProphet]
                 R [use Hydrophobicity / RT information in PeptideProphet]
                 F [force the fitting of the mixture model, bypass automatic mixture model checks]
                 A [use accurate mass binning in PeptideProphet]
                 w [warning instead of exit with error if instrument types between runs is different]
                 x [exclude all entries with asterisked score values in PeptideProphet]
                 l [leave alone all entries with asterisked score values in PeptideProphet]
                 n [use hardcoded default initialization parameters of the distributions]
                 P [use Non-parametric model, can only be used with decoy option]
                 N [do not use the NTT model]
                 M [do not use the NMC model]
                 G [use Gamma Distribution to model the Negatives (applies only to X!Tandem data)]
                 E [only use Expect Score as the Discriminant(applies only to X!Tandem data, 
                    helpful for data with homologous top hits e.g. phospho or glyco)]
                 d [report decoy hits with a computed probability based on the model learned]
                 p [run ProteinProphet afterwards]
                 t [do not create png data plot]
                 u [do not assemble protein groups in ProteinProphet analysis]
                 s [do not use Occam's Razor in ProteinProphet analysis to 
                    derive the simplest protein list to explain observed peptides]
-->

</tool>