<tool id="encyclopedia_walnut" name="Walnut" version="@VERSION@.0">
    <description>PeCAn-based Peptide Detection Directly from Data-Independent Acquisition (DIA) MS/MS Data</description>
    <macros>
        <import>macros.xml</import>
    </macros>
    <expand macro="requirements" />
    <command detect_errors="aggressive"><![CDATA[
        @CMD_IMPORTS@
        @LINK_SCAN_INPUT@
        @LINK_FASTA_INPUT@
        @LINK_TARGET_FASTA@
        EncyclopeDIA -Djava.awt.headless=true -Duser.language=en-US -Duser.region=US
            -Xmx\$[ \${GALAXY_MEMORY_MB:-20480} / 1024 ]g -walnut
            -numberOfThreadsUsed "\${GALAXY_SLOTS:-4}"
        @SCAN_INPUT@
        @FASTA_INPUT@
        @TARGET_FASTA@
        @COMMON_OPTIONS@
        @MASS_LIBRARY_TOLERANCE@
        @PERCOLATOR_OPTIONS@
        @PEAK_OPTIONS@
        @WINDOW_OPTIONS@
        @MODIFICATION_OPTIONS@
        @SEARCH_OPTIONS@
        -o gxpedia
    ]]></command>
    <inputs>
        <expand macro="scan_input"/>
        <expand macro="fasta_input"/>
        <expand macro="target_fasta"/>
        <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="features" selected="false">features.txt</option>
            <option value="pecan" selected="true">pecan.txt</option>
            <option value="pecan_decoy" selected="false">pecan.decoy.txt</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} ${on_string} elib" from_work_dir="gxpedia.elib">
            <filter>'elib' in select_outputs</filter>
        </data>
        <data name="features" format="tabular" label="${tool.name} ${on_string} features.txt" from_work_dir="gxpedia.features.txt">
            <filter>'features' in select_outputs</filter>
            <actions>
                <action name="column_names" type="metadata" default="id,TD,ScanNr,topN,rank,peakZScore,peakCalibratedScore,deltaSn,avgIdotp,midIdotp,peakScore,peakWeightedScore,NCI,CIMassErrMean,CIMassErrVar,precursorMassErrMean,precursorMassErrVar,peakSimilarity,sampledTimes,midTime,spectraNorm,pepLength,charge2,charge3,precursorMz,sequence,protein" />
            </actions>
        </data>
        <data name="pecan" format="tabular" label="${tool.name} ${on_string} pecan.txt" from_work_dir="gxpedia.pecan.txt">
            <filter>'pecan' in select_outputs</filter>
            <actions>
                <action name="column_names" type="metadata" default="PSMId,score,q-value,posterior_error_prob,peptide,proteinIds" />
            </actions>
        </data>
        <data name="pecan_decoy" format="tabular" label="${tool.name} ${on_string} pecan.decoy.txt" from_work_dir="gxpedia.pecan.decoy.txt">
            <filter>'pecan_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_narrow_3_1.mzML"/>
            <param name="fasta" ftype="fasta" value="uniprot_tiny_human.fasta"/>
            <param name="select_outputs" value="log,features,pecan"/>
            <output name="features" ftype="tabular">
                <assert_contents>
                    <has_text text="LHYNEGLNIK"/>
                </assert_contents>
            </output>
        </test>
    </tests>
    <help><![CDATA[
**Walnut**

@ENCYCLOPEDIA_WIKI@

Walnut is a FASTA database search engine for Data-Independent Acquisition (DIA) MS/MS data.
Walnut uses PeCAn-style scoring to extract peptide fragmentation chromatograms from MZML files, assign peaks, and calculate various peak features. These features are interpreted by Percolator to identify peptides.



**Inputs**

  - A spectrum file in mzML format
  - 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>