diff encyclopedia_searchtolib.xml.bak @ 1:b4f1a49ff3b5 draft

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

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/encyclopedia_searchtolib.xml.bak	Tue Jun 30 11:39:02 2020 -0400
@@ -0,0 +1,138 @@
+<tool id="encyclopedia_searchtolib" name="SearchToLib" version="@VERSION@.0">
+    <description>Build a Chromatogram Library or quantify samples 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_INPUTS@
+        @LINK_FASTA_INPUT@
+        @LINK_TARGET_FASTA@
+        @LINK_LIB_INPUT@
+        for SCAN_FILE in `ls -1 inputs/*`; do 
+        echo "\$SCAN_FILE" &&
+        EncyclopeDIA -Djava.awt.headless=true -Xmx20g 
+        #if not $l
+            -walnut
+        #end if
+        -i \$SCAN_FILE
+        @FASTA_INPUT@
+        @TARGET_FASTA@
+        @LIB_INPUT@
+        @COMMON_OPTIONS@
+        @MASS_LIBRARY_TOLERANCE@
+        @PERCOLATOR_OPTIONS@
+        @PEAK_OPTIONS@
+        @WINDOW_OPTIONS@
+        @MODIFICATION_OPTIONS@
+        @SEARCH_OPTIONS@ | tee -a search2lib.log
+        ; done && 
+        EncyclopeDIA -Djava.awt.headless=true -Xmx12g -libexport
+        #if not $l
+            -pecan
+        #end if
+        @SCAN_INPUTS@
+        @FASTA_INPUT@
+        @TARGET_FASTA@
+        @LIB_INPUT@
+        -a $a
+        -o chromatogram_library.elib
+        | tee -a search2lib.log
+    ]]></command>
+    <inputs>
+        <expand macro="scan_inputs"/>
+        <expand macro="lib_input" optional="true" libhelp="Use a Chromatogram elib for quantification, or a Prosit dlib spectral library to make a chromatogram elib using EncyclopeDIA, or else leave blank to make a Chromatogram library from just the fasta using Walnut"/>
+        <expand macro="fasta_input"/>
+        <expand macro="target_fasta"/>
+        <param argument="-a" type="boolean" truevalue="true" falsevalue="false" checked="false" label="align between files" help="retention-time alignment of peptides should be enabled when quantifying samples"/>
+        <expand macro="common_options"/>
+        <expand macro="mass_library_tolerance"/>
+        <expand macro="percolator_options"/>
+        <expand macro="peak_options"/>
+        <expand macro="window_options"/>
+        <expand macro="modification_options"/>
+        <expand macro="search_options"/>
+        <param name="select_outputs" type="select" label="Select outputs" multiple="true">
+            <option value="log" selected="true">log</option>
+            <option value="elib" selected="true">elib</option>
+            <option value="features" selected="true">concatenated_features.txt</option>
+            <option value="results" selected="true">concatenated_results.txt</option>
+            <option value="decoy" selected="false">concatenated_decoy.txt</option>
+            <option value="peptides" selected="true">peptides.txt (requires match between runs)</option>
+            <option value="proteins" selected="true">proteins.txt (requires match between runs)</option>
+        </param>
+    </inputs>
+    <outputs>
+        <data name="log" format="txt" label="${tool.name} ${on_string} log" from_work_dir="search2lib.log">
+            <filter>'log' in select_outputs</filter>
+        </data>
+        <data name="elib" format="elib" label="${tool.name} ${on_string} elib" from_work_dir="chromatogram_library.elib">
+            <filter>'elib' in select_outputs</filter>
+        </data>
+        <data name="features" format="tabular" label="${tool.name} ${on_string} concatenated_features.txt" from_work_dir="inputs/chromatogram_library_concatenated_features.txt">
+            <filter>'features' in select_outputs</filter>
+            <actions>
+                <action name="column_names" type="metadata" default="id,TD,ScanNr,topN,rank,peakZScore,peakCalibratedScore,deltaSn,avgIdotp,midIdotp,peakScore,peakWeightedScore,NCI,CIMassErrMean,CIMassErrVar,precursorMassErrMean,precursorMassErrVar,peakSimilarity,sampledTimes,midTime,spectraNorm,pepLength,charge2,charge3,precursorMz,sequence,protein" />
+            </actions>
+        </data>
+        <data name="results" format="tabular" label="${tool.name} ${on_string} concatenated_results.txt" from_work_dir="inputs/chromatogram_library_concatenated_results.txt">
+            <filter>'results' in select_outputs</filter>
+            <actions>
+                <action name="column_names" type="metadata" default="PSMId,score,q-value,posterior_error_prob,peptide,proteinIds" />
+            </actions>
+        </data>
+        <data name="decoy" format="tabular" label="${tool.name} ${on_string} concatenated_decoy.txt" from_work_dir="inputs/chromatogram_library_concatenated_decoy.txt">
+            <filter>'decoy' in select_outputs</filter>
+            <actions>
+                <action name="column_names" type="metadata" default="PSMId,score,q-value,posterior_error_prob,peptide,proteinIds" />
+            </actions>
+        </data>
+        <data name="peptides" format="tabular" label="${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 SearchToLib 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. SearchToLib is then run on the wide-window quantitative replicate mzML files using that chromatogram library, with the *align between files* option, to produce quantification results.
+
+.. image:: SearchToLib_Workflow.png
+  :height: 439
+  :width: 768
+
+.. _Prosit: https://www.proteomicsdb.org/prosit
+
+    ]]></help>
+    <expand macro="citations" />
+</tool>