diff percolator.xml @ 0:3a49065a05d6 draft

planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/percolator commit b4871f9659a924a68430aed3a93f4f9bad733fd6
author galaxyp
date Wed, 07 Dec 2016 16:43:51 -0500
parents
children 86770eea5b09
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/percolator.xml	Wed Dec 07 16:43:51 2016 -0500
@@ -0,0 +1,86 @@
+<tool id="percolator" name="Percolator" version="3.0">
+    <description>accurate peptide identification</description>
+    <requirements>
+        <requirement type="package" version="3.0">percolator</requirement>
+    </requirements>
+    <stdio>
+        <exit_code range="1:"/>
+    </stdio>
+    <command>
+    percolator -j '$input'
+    #if $output_type == "xml"
+        -X '$percoout' --decoy-xml-output
+    #else
+        -J '$percoout'
+    #end if
+    #if $cpos
+        -p $cpos
+    #end if
+    #if $cneg
+        -n $cneg
+    #end if
+    #if $testfdr
+        -t $testfdr
+    #end if
+    #if $trainfdr
+        -F $trainfdr
+    #end if
+    #if $maxiter
+        -i $maxiter
+    #end if
+    #if $seed
+        -S $seed
+    #end if
+    #if $default_direction
+        -V $default_direction
+    #end if
+    $quickval $unitnorm $override $onlypsms
+    </command>
+    <inputs>
+        <param name="output_type" label="What filetype to output" type="select" display="radio">
+            <option value="xml" selected="true">percolator XML (for further processing)</option>
+	        <option value="tsv">Tab-separated</option>
+        </param>
+        <param name="input" type="data" format="percin" label="Percolator input data" />
+        <param name="cpos" label="Penalty for mistakes on positive examples" type="float" optional="true" />
+        <param name="cneg" label="Penalty for mistakes on negative examples" type="float" optional="true" />
+        <param name="trainfdr" label="FDR threshold to define positive examples" type="float" optional="true" help="Set by cross validation if 0."/>
+        <param name="testfdr" label="FDR threshold for evaluating best cross validation result" type="float" optional="true" />
+        <param name="maxiter" label="Maximal number of iterations" type="integer" optional="true" />
+        <param name="quickval" label="Quicker execution by reduced internal cross-validation" type="boolean" truevalue="-x" falsevalue=""/>
+        <param name="default_direction" label="Most informative feature given as feature number" type="integer" optional="true" />
+        <param name="unitnorm" type="boolean" label="Unit normalization instead of standard deviation" truevalue="-u" falsevalue=""/>
+        <param name="override" label="Override error check?" help="and no fallback on default score vector in case of suspect score vector" type="boolean" truevalue="-O" falsevalue=""/>
+        <param name="seed" label="Seed of random number generator" type="integer" optional="true" />
+        <!--<param name="klammer" label="Retention time features calculated as in Klammer et al?" type="boolean" />  TODO: this param goes together with the doc param which I havent figured out how to use yet. -->
+        <param name="onlypsms" label="Skip all outputs except PSMs" type="boolean" truevalue="-U" falsevalue=""/>
+    </inputs>
+    <outputs>
+        <data format="percout" name="percoout">
+		    <change_format>
+			    <when input="output_type" value="tsv" format="tsv" />
+		    </change_format>
+	    </data>
+    </outputs>
+    <tests>
+        <test>
+            <param name="input" value="percolatorTab" />
+            <param name="output_type" value="xml" />
+            <output name="percoout" value="percolatorOut.xml" lines_diff="2" />
+        </test>
+        <test>
+            <param name="input" value="percolatorTab" />
+            <param name="output_type" value="tsv" />
+            <output name="percoout" value="percolatorOut.txt" />
+        </test>
+    </tests>
+    <help>The first step in analyzing an mass spectrometry assay is to match the harvested spectra against a target database using database search engines such as Sequest and Mascot, a process that renders list of peptide-spectrum matches. However, it is not trivial to assess the accuracy of these identifications.
+
+Percolator uses a semi-supervised machine learning to discriminate correct from incorrect peptide-spectrum matches, and calculates accurate statistics such as q-value (FDR) and posterior error probabilities. 
+    </help>
+    <citations>
+        <citation type="doi">10.1038/nmeth1113</citation>
+        <citation type="doi">10.1021/pr700600n</citation>
+        <citation type="doi">10.1093/bioinformatics/btn294</citation>
+    </citations>
+</tool>