comparison encyclopedia_searchtolib.xml @ 1:a7d52df6763f draft

"planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/encyclopedia/tools/encyclopedia commit 81e7c4d3d6066b99ad50374292f340302dc4f02d"

0:683b98838cf0

<tool id="encyclopedia_searchtolib" name="SearchToLib" 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="exit_code"><![CDATA[

        #end if
        @SCAN_INPUTS@
        @FASTA_INPUT@
        @TARGET_FASTA@
        @LIB_INPUT@
        ## @COMMON_OPTIONS@
        ## @MASS_LIBRARY_TOLERANCE@
        ## @PERCOLATOR_OPTIONS@
        ## @PEAK_OPTIONS@
        ## @WINDOW_OPTIONS@
        ## @MODIFICATION_OPTIONS@
        ## @SEARCH_OPTIONS@
        -a $a
        -o chromatogram_library.elib
        | tee -a search2lib.log
    ]]></command>
    <inputs>
        <expand macro="scan_inputs"/>
        <expand macro="lib_input" token_optional="true" token_help="If a prosit dlib is supplied, use EncycopeDIA, else use walnut"/>
        <expand macro="fasta_input"/>
        <expand macro="target_fasta"/>
        <param argument="-a" type="boolean" truevalue="true" falsevalue="false" checked="false" label="match between runs"/>
        <expand macro="common_options"/>
        <expand macro="mass_library_tolerance"/>
        <expand macro="percolator_options"/>
        <expand macro="peak_options"/>
        <expand macro="window_options"/>
        <expand macro="modification_options"/>
        <expand macro="search_options"/>
        <param name="select_outputs" type="select" label="Select outputs" multiple="true">
            <option value="log" selected="true">log</option>
            <option value="elib" selected="true">elib</option>
            <option value="features" selected="true">concatenated_features.txt</option>
            <option value="results" selected="true">concatenated_results.txt</option>
            <option value="decoy" selected="false">concatenated_decoy.txt</option>
            <option value="peptides" selected="true">peptides.txt (requires match between runs)</option>
            <option value="proteins" selected="true">proteins.txt (requires match between runs)</option>
        </param>
    </inputs>
    <outputs>
        <data name="log" format="txt" label="${tool.name} ${on_string} log" from_work_dir="search2lib.log">
            <filter>'log' in select_outputs</filter>

            <filter>'decoy' 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="peptides" format="tabular" label="${tool.name} ${on_string} peptides.txt" from_work_dir="chromatogram_library.peptides.txt">
            <filter>a and peptides' in select_outputs</filter>
            <actions>
                <action name="column_names" type="metadata" default="Peptide,Protein,numFragments" />
            </actions>
        </data>
        <data name="proteins" format="tabular" label="${tool.name} ${on_string} proteins.txt" from_work_dir="chromatogram_library.proteins.txt">
            <filter>a and 'proteins' in select_outputs</filter>
            <actions>
                <action name="column_names" type="metadata" default="Protein,NumPeptides,PeptideSequences" />
            </actions>
        </data>
<!--
-->
    </outputs>
    <help><![CDATA[
SearchToLIB uses EncyclopeDIA, Walnut (Pecan), or XCorDIA to create an DIA Elib for EncyclopeDIA DIA search
Walnut is a FASTA database search engine for DIA data that uses PECAN-style scoring.
You should prefix your arguments with a high memory setting, e.g. "-Xmx8g" for 8gb

Required Parameters: 
	-i	input .DIA or .MZML file
	-f	background FASTA file

Other Parameters: 
	-t	target FASTA file (default: background FASTA file)
	-tp	true/false target FASTA file contains peptides (default: false)
	-o	output report file (default: [input file].pecan.txt)
	-acquisition                          (default: overlapping dia)
	-addDecoysToBackground                (default: false)
	-alpha                                (default: 1.8)
	-beta                                 (default: 0.4)
	-dontRunDecoys                        (default: false)
	-enzyme                               (default: trypsin)
	-filterPeaklists                      (default: false)
	-fixed                                (default: C=57.0214635)
	-foffset                              (default: 0)
	-frag                                 (default: YONLY)
	-ftol                                 (default: 10)
	-ftolunits                            (default: ppm)
	-maxCharge                            (default: 3)
	-maxLength                            (default: 100)
	-maxMissedCleavage                    (default: 1)
	-minCharge                            (default: 2)
	-minEluteTime                         (default: 12)
	-minIntensity                         (default: -1.0)
	-minLength                            (default: 5)
	-minNumOfQuantitativePeaks            (default: 3)
	-minQuantitativeIonNumber             (default: 3)
	-numberOfQuantitativePeaks            (default: 5)
	-numberOfReportedPeaks                (default: 1)
	-numberOfThreadsUsed                  (default: 12)
	-percolatorProteinThreshold           (default: 0.01)
	-percolatorThreshold                  (default: 0.01)
	-percolatorVersionNumber              (default: 3)
	-poffset                              (default: 0)
	-precursorIsolationMargin             (default: 0)
	-precursorWindowSize                  (default: -1)
	-ptol                                 (default: 10)
	-ptolunits                            (default: ppm)
	-requireVariableMods                  (default: false)
	-variable                             (default: -)

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

1:a7d52df6763f

<tool id="encyclopedia_searchtolib" name="SearchToLib" version="@VERSION@.0">
    <description>Build a Chromatogram Library from Data-Independent Acquisition (DIA) MS/MS Data</description>
    <macros>
        <import>macros.xml</import>
    </macros>
    <expand macro="requirements" />
    <command detect_errors="exit_code"><![CDATA[

        #end if
        @SCAN_INPUTS@
        @FASTA_INPUT@
        @TARGET_FASTA@
        @LIB_INPUT@
        -a $a
        -o chromatogram_library.elib
        | tee -a search2lib.log
    ]]></command>
    <inputs>
        <expand macro="scan_inputs"/>
        <expand macro="lib_input" optional="true" libhelp="Use a Prosit dlib spectral library to make a chromatogram elib using EncyclopeDIA, or else leave blank to make a Chromatogram library from just the fasta using Walnut"/>
        <expand macro="fasta_input"/>
        <expand macro="target_fasta"/>
        <param argument="-a" type="boolean" truevalue="true" falsevalue="false" checked="false" label="align between files" help="retention-time alignment of peptides is generally not needed when using narrow-window spectrums"/>
        <expand macro="common_options"/>
        <expand macro="mass_library_tolerance"/>
        <expand macro="percolator_options"/>
        <expand macro="peak_options"/>
        <expand macro="window_options"/>
        <expand macro="modification_options"/>
        <expand macro="search_options"/>
        <param name="select_outputs" type="select" label="Select outputs" multiple="true">
            <option value="log" selected="true">log</option>
            <option value="elib" selected="true">elib</option>
            <option value="features" selected="false">concatenated_features.txt</option>
            <option value="results" selected="false">concatenated_results.txt</option>
            <option value="decoy" selected="false">concatenated_decoy.txt</option>
            <!--
            <option value="peptides" selected="false">peptides.txt (requires align between files)</option>
            <option value="proteins" selected="false">proteins.txt (requires align between files)</option>
            -->
        </param>
    </inputs>
    <outputs>
        <data name="log" format="txt" label="${tool.name} ${on_string} log" from_work_dir="search2lib.log">
            <filter>'log' in select_outputs</filter>

            <filter>'decoy' 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="peptides" format="tabular" label="${tool.name} ${on_string} peptides.txt" from_work_dir="chromatogram_library.peptides.txt">
            <filter>a and 'peptides' in select_outputs</filter>
            <actions>
                <action name="column_names" type="metadata" default="Peptide,Protein,numFragments" />
            </actions>
        </data>
        <data name="proteins" format="tabular" label="${tool.name} ${on_string} proteins.txt" from_work_dir="chromatogram_library.proteins.txt">
            <filter>a and 'proteins' in select_outputs</filter>
            <actions>
                <action name="column_names" type="metadata" default="Protein,NumPeptides,PeptideSequences" />
            </actions>
        </data>
        -->
    </outputs>
    <help><![CDATA[

**SearchToLIB**

@ENCYCLOPEDIA_WIKI@

SearchToLIB uses the EncyclopeDIA algorithm, or the Walnut (Pecan) algorithm to search Data-Independent Acquisition (DIA) MS/MS spectrum files and creates a DIA elib chromatogram library for EncyclopeDIA DIA quantitation search. 

SearchToLIB can also quantify peptides from the chromatogram library. 

@MSCONVERT_HELP@

**Typical DIA Workflow**

Two sets of Mass Spec MS/MS DIA data are collected for the experiment.  In addition to collecting wide-window DIA experiments on each quantitative replicate, a pool containing peptides from every condition is measured using several staggered narrow-window DIA experiments.

  1. SearchToLib is first run with the pooled narrow-window mzML files to create a combined DIA elib chromatogram library.   
     If a Spectral library argument is provided, for example from **Prosit**, SearchToLIB uses EncyclopeDIA to search each input spectrum mzML file.  
     Otherwise, SearchToLIB uses Walnut, a FASTA database search engine for DIA data that uses PECAN-style scoring.


       * Prosit_ generates a predicted spectrum library of fragmentation patterns and retention times for every +2H and +3H tryptic peptide in a FASTA database, with up to one missed cleavage.


  2. EncyclopeDIA Quantify is then run on the wide-window quantitative replicate mzML files using that chromatogram library to produce quantification results.

.. image:: SearchToLib_Workflow.png
  :height: 439
  :width: 768

.. _Prosit: https://www.proteomicsdb.org/prosit

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