<tool id="proteinpilot_group_extractor" name="ProteinPilot - GroupFileExtractor" version="5.0.0">
  <description>convert group file to tabular reports, mzIndentML, and MGF</description>
  <command>
<![CDATA[
    #if $quant.use
    #set $denom = str($quant.dtype)
    #else
    #set $denom = ""
    #end if
    #set $ptypes = str($ptype).split(',')
    #set $cmd = []
    #if 'PROTEIN' in $ptypes:
    #set $cmd = $cmd + ['GroupFileExtractor.exe PROTEIN ' + str($input) + ' protein_report.txt ' + $denom]
    #end if
    #if 'PEPTIDE' in $ptypes:
    #set $cmd = $cmd + ['GroupFileExtractor.exe PEPTIDE ' + str($input) + ' peptide_report.txt ' + $denom]
    #end if
    #if 'DISTINCT_PEPTIDE' in $ptypes:
    #set $cmd = $cmd + ['GroupFileExtractor.exe DISTINCT_PEPTIDE ' + str($input) + ' distinct_peptide_report.txt ' + $denom]
    #end if
    #if 'SPECTRUM' in $ptypes:
    #set $cmd = $cmd + ['GroupFileExtractor.exe SPECTRUM ' + str($input) + ' spectrum_report.txt ' + $denom]
    #end if
    #if 'FEATURES' in $ptypes:
    #set $cmd = $cmd + ['GroupFileExtractor.exe FEATURES ' + str($input) + ' features_report.txt ' + $denom]
    #end if
    #if 'MZIDENTML' in $ptypes:
    #set $cmd = $cmd + ['GroupFileExtractor.exe MZIDENTML ' + str($input) + ' mzidentml.mzid ' + $denom]
    #end if
    #if 'MGF' in $ptypes:
    #set $cmd = $cmd + ['GroupFileExtractor.exe MGF ' + str($input) + ' output.mgf ' + $denom]
    #end if
    #if 'XML' in $ptypes:
    #set $cmd = $cmd + ['GroupFileExtractor.exe XML ' + str($input) + ' results.xml ' + $denom]
    #end if
    #if 'METADATAXML' in $ptypes:
    #set $cmd = $cmd + ['GroupFileExtractor.exe METADATAXML ' + str($input) + ' metadata.xml ' + $denom]
    #end if
    #if 'METADATACSV' in $ptypes:
    #set $cmd = $cmd + ['GroupFileExtractor.exe METADATACSV ' + str($input) + ' metadata.csv ' + $denom]
    #end if
    #echo ' && '.join($cmd)
]]>
  </command>
  <inputs>
    <param format="group" name="input" type="data" label="ProteinPilot Group Data" help=""/>
    <param name="ptype" type="select" multiple="true" optional="false" label="Select Summary Reports">
      <option value="PROTEIN">PROTEIN</option>
      <option value="PEPTIDE">PEPTIDE</option>
      <option value="DISTINCT_PEPTIDE">DISTINCT_PEPTIDE</option>
      <option value="SPECTRUM">SPECTRUM</option>
      <option value="FEATURES">FEATURES</option>
      <option value="MZIDENTML">MZIDENTML</option>
      <option value="MGF">MGF</option>
      <option value="XML">XML</option>
      <option value="METADATAXML">METADATAXML</option>
      <option value="METADATACSV">METADATACSV</option>
    </param>
    <conditional name="quant">
      <param name="use" type="boolean" label="Include quantitation results" truevalue="true" falsevalue="false" />
      <when value="true">
        <param name="dtype" type="select" label="Denominator">
          <option value="IT113">IT113</option>
          <option value="IT114" selected="true">IT114</option>
          <option value="IT115">IT115</option>
          <option value="IT116">IT116</option>
          <option value="IT117">IT117</option>
          <option value="IT118">IT118</option>
          <option value="IT119">IT119</option>
          <option value="IT121">IT121</option>
          <option value="Light">Light</option>
          <option value="Heavy">Heavy</option>
          <option value="Medium">Medium</option>
        </param>
      </when>
      <when value="false"/>
    </conditional>
  </inputs>
  <outputs>
    <data format="tabular" name="protein_report" label="PROTEIN report for ${on_string}" from_work_dir="protein_report.txt">
        <filter>'PROTEIN' in ptype</filter>
    </data>
    <data format="tabular" name="peptide_report" label="PEPTIDE report for ${on_string}" from_work_dir="peptide_report.txt">
        <filter>'PEPTIDE' in ptype</filter>
    </data>
    <data format="tabular" name="distinct_peptide_report" label="DISTINCT_PEPTIDE report for ${on_string}" from_work_dir="distinct_peptide_report.txt">
        <filter>'DISTINCT_PEPTIDE' in ptype</filter>
    </data>
    <data format="tabular" name="spectrum_report" label="SPECTRUM report for ${on_string}" from_work_dir="spectrum_report.txt">
        <filter>'SPECTRUM' in ptype</filter>
    </data>
    <data format="tabular" name="features_report" label="FEATURES report for ${on_string}" from_work_dir="features_report.txt">
        <filter>'FEATURES' in ptype</filter>
    </data>
    <data format="mzid" name="mzidentml" label="mzIdentML for ${on_string}" from_work_dir="mzidentml.mzid">
        <filter>'MZIDENTML' in ptype</filter>
    </data>
    <data format="mgf" name="mgf" label="mgf for ${on_string}" from_work_dir="output.mgf">
        <filter>'MGF' in ptype</filter>
    </data>
    <data format="xml" name="results_xml" label="Results.xml for ${on_string}" from_work_dir="results.xml">
        <filter>'XML' in ptype</filter>
    </data>
    <data format="xml" name="metadata_xml" label="Metadata.xml for ${on_string}" from_work_dir="metadata.xml">
        <filter>'METADATAXML' in ptype</filter>
    </data>
    <data format="csv" name="metadata_csv" label="Metadata.csv for ${on_string}" from_work_dir="metadata.csv">
        <filter>'METADATACSV' in ptype</filter>
    </data>
  </outputs>
  <help>
<![CDATA[
**ProteinPilot GroupFileExtractor**

  Requires ProteinPilot version 5


**INPUT** 

  A ProteinPilot .group file

**OUTPUTS**

  Data can now be exported in the following formats:

    (1) **Protein Summary**
  
      A tabular report of detected proteins.
  
    (2) **Peptide Summary**
  
      A tabular report of detected proteins.
  
    (3) **Distinct Peptide Summary**
  
      The Distinct Peptide Summary export provides a summary of all peptide groups for each group that has at least one hypotheses with at least 15% confidence. The purpose is to report a list of all distinct physical peptides that have been detected. Each physical peptide can have multiple precursor charge states observed as detected, separate LCMS map features. To attempt to identify the peptide, each of these LCMS features can have MS/MS spectra triggered.
  
      The process of identification does not always result in a clear single answer, so ambiguity in identification can occur. The purpose of the peptide group is to group all competitive hypotheses for a given physical peptide arising from the following three levels:
  
        - multiple precursor charge states,
        - multiple MS/MS spectra of a given charge state, and
        - multiple answers for a given MS/MS spectrum.
  
      The Distinct Peptide Summary export is unlike the previous Peptide Summary export, which exported information only about the peptides claimed by reported proteins. The Distinct Peptide Summary export shows all hypotheses that are within the margin of error of being the right answer, regardless of whether they are attached to reported proteins, making this export useful for peptide-centric workflows.
  
    (4) **Spectrum Summary**
  
      The spectrum export includes all of the top hits to each spectrum, making it spectrum- centric, rather than protein-peptide ID-centric. This gives the user a way to access all of the information, rather than just the protein-filtered information as is done with the existing Peptide Summary export.
  
    (5) **mzIDentML**
  
      The ProteinPilot software now exports search results in mzIDentML version 1.2 candidate format.* This is a standardized format developed by the Human Proteome Organizations (HUPO) Proteomics Standards Initiative (PSI) for reporting parameters and results from mass spectrometric database search engines. Users can most easily export to mzIDentML format from the export options available in the software, but exports can also be done programmatically.
  
      http://onlinelibrary.wiley.com/doi/10.1002/pmic.201400080/abstract Seymour, Sean et al. "A standardized framing for reporting protein identifications in mzIdentML 1.2." Proteomics. doi: 10.1002/pmic.201400080.
  
    (6) **MGF Peak list**
  
      Recalibrated MGF (Mascot Generic File) peak lists can now be exported programmatically. 
  
    (7) **Metadata**
  
      This is a new export option that provides metadata based on search criteria (for example, search date, time, other search parameters). Metadata can be exported in .txt or .xml file format.
  
    (8) **Features**
  
      The Features export contains all of the detected protein features (for example, post-translational modifications and sequence variants).
      Confidence Interval (CI) columns added to Proteins Detected table
      The ProteinPilot software now reports a confidence interval for SILAC and other MS- based quantitation workflows, such as SCIEX mTRAQ. Four new column options are hidden by default but can be shown on the Protein Quant tab in the Proteins Detected table: Upper CI M:L, Lower CI M:L, Upper CI H:L, and Lower CI H:L. Upper and Lower CI column headings reflect whether the user selected a Heavy (H) or Light (L) denominator.
      N-15 universal labeling SILAC support
      Quantitation of universally N-15 labeled SILAC duplex samples was introduced in ProteinPilot software 4.2 Beta but required some special configuration. This feature is now available by default and no longer requires any additional steps to perform this type of quantitation analysis.

]]>
  </help>
</tool>