annotate encyclopedia_encyclopedia.xml @ 2:eac99effe86f draft default tip

planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/encyclopedia/tools/encyclopedia commit 0bb79ebbaf73fe6e902f6ef20cc9c9741063bf34

<tool id="encyclopedia_encyclopedia" name="EncyclopeDIA" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@">
    <description>Library Searching Directly from Data-Independent Acquisition (DIA) MS/MS Data</description>
    <macros>
        <import>macros.xml</import>
    </macros>
    <expand macro="requirements" />
    <command detect_errors="exit_code"><![CDATA[
        @CMD_IMPORTS@
        @LINK_SCAN_INPUT@
        @LINK_FASTA_INPUT@
        @LINK_LIB_INPUT@
        EncyclopeDIA -Djava.awt.headless=true -Duser.language=en-US -Duser.region=US
            -Xmx\$[ \${GALAXY_MEMORY_MB:-20480} / 1024 ]g
            -numberOfThreadsUsed "\${GALAXY_SLOTS:-4}"
        @SCAN_INPUT@
        @FASTA_INPUT@
        @LIB_INPUT@
        @COMMON_OPTIONS@
        @MASS_LIBRARY_TOLERANCE@
        @PERCOLATOR_OPTIONS@
        @PEAK_OPTIONS@
        @WINDOW_OPTIONS@
        @MODIFICATION_OPTIONS@
        -o gxpedia
    ]]></command>
    <inputs>
        <expand macro="scan_input"/>
        <expand macro="fasta_input"/>
        <expand macro="lib_input" optional="false" libhelp="Chromatogram elib from SearchToLib on pooled samples"/>
        <expand macro="options_section"/>
        <param name="select_outputs" type="select" label="Select outputs" multiple="true">
            <option value="log" selected="true">log</option>
            <option value="elib" selected="true">elib</option>
            <option value="first_delta_rt_pdf" selected="false">Initial Delta Retention Time Plot</option>
            <option value="first_rt_fit_pdf" selected="false">Initial Fitted Retention Time Plot</option>
            <option value="first_rt_fit_txt" selected="false">Initial Fitted Retention Time Table</option>
            <option value="final_delta_rt_pdf" selected="false">Final Delta Retention Time Plot</option>
            <option value="final_rt_fit_pdf" selected="false">Final Fitted Retention Time Plot</option>
            <option value="final_rt_fit_txt" selected="false">Final Fitted Retention Time Table</option>
            <option value="features" selected="false">features</option>
            <option value="encyclopedia" selected="true">encyclopedia results</option>
            <option value="encyclopedia_decoy" selected="false">encyclopedia decoy results</option>
        </param>
    </inputs>
    <outputs>
        <data name="log" format="txt" label="${tool.name} ${on_string} log" from_work_dir="gxpedia.log">
            <filter>'log' in select_outputs</filter>
        </data>
        <data name="elib" format="elib" label="${tool.name} ${on_string} elib" from_work_dir="gxpedia.elib">
            <filter>'elib' in select_outputs</filter>
        </data>
        <data name="first_delta_rt_pdf" format="pdf" label="${tool.name} ${on_string} encyclopedia.txt.first.delta_rt.pdf" from_work_dir="gxpedia.encyclopedia.txt.first.delta_rt.pdf">
            <filter>'first_delta_rt_pdf' in select_outputs</filter>
        </data>
        <data name="first_rt_fit_pdf" format="pdf" label="${tool.name} ${on_string} encyclopedia.txt.first.rt_fit.pdf" from_work_dir="gxpedia.encyclopedia.txt.first.rt_fit.pdf">
            <filter>'first_rt_fit_pdf' in select_outputs</filter>
        </data>
        <data name="first_rt_fit_txt" format="tabular" label="${tool.name} ${on_string} encyclopedia.txt.first.rt_fit.txt" from_work_dir="gxpedia.encyclopedia.txt.first.rt_fit.txt">
            <filter>'first_rt_fit_txt' in select_outputs</filter>
            <actions>
                <action name="column_names" type="metadata" default="library,actual,warpToActual,delta,fitProb,isDecoy,sequence" />
            </actions>
        </data>
        <data name="final_delta_rt_pdf" format="pdf" label="${tool.name} ${on_string} encyclopedia.txt.final.delta_rt.pdf" from_work_dir="gxpedia.encyclopedia.txt.final.delta_rt.pdf">
            <filter>'final_delta_rt_pdf' in select_outputs</filter>
        </data>
        <data name="final_rt_fit_pdf" format="pdf" label="${tool.name} ${on_string} encyclopedia.txt.final.rt_fit.pdf" from_work_dir="gxpedia.encyclopedia.txt.final.rt_fit.pdf">
            <filter>'final_rt_fit_pdf' in select_outputs</filter>
        </data>
        <data name="final_rt_fit_txt" format="tabular" label="${tool.name} ${on_string} encyclopedia.txt.final.rt_fit.txt" from_work_dir="gxpedia.encyclopedia.txt.final.rt_fit.txt">
            <filter>'final_rt_fit_txt' in select_outputs</filter>
            <actions>
                <action name="column_names" type="metadata" default="library,actual,warpToActual,delta,fitProb,isDecoy,sequence" />
            </actions>
        </data>
        <data name="features" format="tabular" label="${tool.name} ${on_string} features.txt" from_work_dir="gxpedia.features.txt">
            <filter>'features' in select_outputs</filter>
            <actions>
                <action name="column_names" type="metadata" default="id,TD,ScanNr,topN,deltaCN,primary,xCorrLib,xCorrModel,LogDotProduct,logWeightedDotProduct,sumOfSquaredErrors,weightedSumOfSquaredErrors,numberOfMatchingPeaks,numberOfMatchingPeaksAboveThreshold,averageAbsFragmentDeltaMass,averageFragmentDeltaMasses,isotopeDotProduct,averageAbsParentDeltaMass,averageParentDeltaMass,eValue,deltaRT,pepLength,charge2,charge3,precursorMz,RTinMin,sequence,protein" />
            </actions>
        </data>
        <data name="encyclopedia" format="tabular" label="${tool.name} ${on_string} encyclopedia.txt" from_work_dir="gxpedia.encyclopedia.txt">
            <filter>'encyclopedia' in select_outputs</filter>
            <actions>
                <action name="column_names" type="metadata" default="PSMId,score,q-value,posterior_error_prob,peptide,proteinIds" />
            </actions>
        </data>
        <data name="encyclopedia_decoy" format="tabular" label="${tool.name} ${on_string} encyclopedia.decoy.txt" from_work_dir="gxpedia.encyclopedia.decoy.txt">
            <filter>'encyclopedia_decoy' in select_outputs</filter>
            <actions>
                <action name="column_names" type="metadata" default="PSMId,score,q-value,posterior_error_prob,peptide,proteinIds" />
            </actions>
        </data>
    </outputs>
    <tests>
        <test>
            <param name="scan_input" ftype="mzml" value="BCS_hela_wide_500_900_1.mzML"/>
            <param name="library" ftype="elib" value="BCS_hela.elib"/>
            <param name="fasta" ftype="fasta" value="uniprot_human.fasta"/>
            <param name="select_outputs" value="log,features,encyclopedia"/>
            <output name="features" ftype="tabular">
                <assert_contents>
                    <has_text text="ESYDDVSSFR"/>
                </assert_contents>
            </output>
            <output name="encyclopedia" ftype="tabular">
                <assert_contents>
                    <has_text text="ESYDDVSSFR"/>
                </assert_contents>
            </output>
        </test>
    </tests>

    <help><![CDATA[
**EncyclopeDIA**

@ENCYCLOPEDIA_WIKI@

EncyclopeDIA extracts peptide fragmentation chromatograms from MZML files, matches them to spectra in libraries, and calculates various scoring features. These features are interpreted by Percolator to identify peptides.


**Inputs**

  - A spectrum file in mzML format
  - A chromatogram library that can be generated by SearchToLib 
  - A protein data base in fasta format


@MSCONVERT_HELP@

**Outputs**

  - A log file
  - A Chromatogram Library (.elib)
  - The identified features in tabular format
    Feature values of scans that are used by percolator to determine matches.
  - The identified Peptide Spectral Match results in tabular format
    Columns: PSMId, score, q-value, posterior_error_prob, peptide, proteinIds
  - The identified peptides in tabular format
    Per peptide: the normalized intensity for each scan file.
    Columns: Peptide, Protein, numFragments, intensity_in_file1, intensity_in_file2, ...
  - The identified proteins in tabular format
    Per protein: the normalized intensity for each scan file.
    Columns: Protein, NumPeptides, PeptideSequences, intensity_in_file1, intensity_in_file2, ...

    ]]></help>
    <expand macro="citations" />
</tool>