Mercurial > repos > galaxyp > feature_alignment

changeset 0:7b4d70c9a139 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author galaxyp
date Mon, 11 May 2015 12:20:44 -0400
parents
children 25f43048bff3
files .shed.yml feature_alignment.xml tool_dependencies.xml
diffstat 3 files changed, 116 insertions(+), 0 deletions(-) [+]
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/.shed.yml	Mon May 11 12:20:44 2015 -0400
@@ -0,0 +1,3 @@
+# repository published to https://toolshed.g2.bx.psu.edu/repos/galaxyp/feature_alignment
+owner: galaxyp
+name: feature_alignment
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/feature_alignment.xml	Mon May 11 12:20:44 2015 -0400
@@ -0,0 +1,107 @@
+<tool id="feature_alignment" name="Feature Alignment" version="0.1">
+    <description>of peakgroups below a FDR</description>
+    <stdio>
+        <exit_code level="fatal" range="1:"/>
+    </stdio>
+    <version_command>feature_alignment.py --version</version_command>
+    <command interpreter="python">
+<![CDATA[
+    feature_alignment.py 
+        --in #'" "'.join([ $file for $file in $inputs ])#
+        --file_format $oformat
+        #if str($out) == "openswath":
+            --out $out
+        #end if
+        --out_matrix out_matrix.tsv
+        --out_ids $out_ids
+        --fdr_cutoff $fdr_cutoff
+        #if $max_fdr_quality and $max_fdr_quality is not None:
+            --max_fdr_quality "$max_fdr_quality"
+        #end if
+        --max_rt_diff $max_rt_diff
+        --iso_max_rt_diff $iso_max_rt_diff
+        --frac_selected $frac_selected
+        --method $method
+        --matrix_output_method $matrix_output_method
+        --realign_method $realign_method
+
+        &&
+        mv out_matrix.tsv $out_matrix
+
+]]></command>
+    <inputs>
+
+        <param name="inputs" type="data" multiple="True"
+            label="A list of mProphet output files containing all peakgroups" help="(--in)"/>
+        <param name="oformat" type="select" label="Which input file format is used" help="(--file_format)">
+            <option value="openswath">OpenSwath</option>
+            <option value="peakview" selected="True">Peakview</option>
+        </param>
+
+        <param name="fdr_cutoff" type="float" value="0.01" label="Seeding score cutoff" help="(--fdr_cutoff)" />
+        <param name="max_fdr_quality" type="text" default="-1.0"
+            label="Extension score cutoff"
+            help="During the extension phase of the algorithm, peakgroups of this quality will still be considered for alignment (in FDR) - it is possible to give a range in the format lower,higher+stepsize,stepsize - e.g. 0,0.31,0.01 (-1 will set it to fdr_cutoff) (--max_fdr_quality)"/>
+        <param name="max_rt_diff" type="integer" default="30"
+            label="Maximal difference in RT for two aligned features" help="(--max_rt_diff)"/>
+        <param name="iso_max_rt_diff" type="text" default="10"
+            label="Maximal difference in RT for two isotopic channels in the same run" help="(--iso_max_rt_diff)" />
+        <param name="frac_selected" type="float" value="0.0" min="0" max="1"
+            label="Do not write peakgroup if selected in less than this fraction of runs" help="(--frac_selected)"/>
+
+        <param name="method" type="select"
+            label="Which method to use for the clustering"
+            help="Note that the MST options will perform a local, MST guided alignment while the other options will use a reference-guided alignment. The global option will also move peaks which are below the selected FDR threshold. (--method)" />
+            <option value='best_overall' selected="True">best_overall</option>
+            <option value='best_cluster_score'>best_cluster_score</option>
+            <option value='global_best_cluster_score'>global_best_cluster_score</option>
+            <option value='global_best_overall'>global_best_overall</option>
+            <option value='LocalMST'>LocalMST</option>
+            <option value='LocalMSTAllCluster'>LocalMSTAllCluster</option>
+        </param>
+
+        <param name="matrix_output_method" type="select"
+            label="Which columns are written besides Intensity" help="(--matrix_output_method)">
+            <option value='none' selected="True">None</option>
+            <option value='RT'>RT</option>
+            <option value='score'>Score</option>
+            <option value='source'>Source</option>
+            <option value='full'>Full</option>
+        </param>
+        <param name="realign_method" type="select" label="How to re-align runs in retention time" help="(--realign_method)">
+            <option value='diRT' selected="True">Use only deltaiRT from the input file</option>
+            <option value='linear'>Perform a linear regression using best peakgroups</option>
+            <!--option value='splineR'>Perform a spline fit using R</option-->
+            <!--option value='splineR_external'>Perform a spline fit using R</option-->
+            <option value='splinePy'>Use Python native spline from scikits.datasmooth (slow!)</option>
+            <option value='lowess'>Use Robust locally weighted regression (lowess smoother)</option>
+            <option value='CVSpline'>Splines with cross-validation</option>
+            <option value='nonCVSpline'>Splines without cross-validation</option>
+            <option value='earth' >Use Multivariate Adaptive Regression Splines using py-earth</option>
+        </param>
+    </inputs>
+    <outputs>
+        <!-- Matrix containing one peak group per row -->
+        <data format="tabular" name="out_matrix"/>
+        <!-- Id file only containing the ids -->
+        <data format="tabular" name="out_ids"/>
+        <!-- Output file with filtered peakgroups for quantification (only works for OpenSWATH) -->
+        <data format="text" name="out">
+            <filter>oformat == 'openswath'</filter>
+        </data>
+    </outputs>
+    <help>
+<![CDATA[
+
+**What it does**
+
+This program will select all peakgroups below the FDR cutoff in all files and try to align them to each other.
+If only one file is given, it will act as peakgroup selector (best by m_score)
+and will apply the provided FDR cutoff.
+]]>
+    </help>
+    <citations>
+        <citation type="doi"></citation>
+    </citations>
+</tool>
+
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/tool_dependencies.xml	Mon May 11 12:20:44 2015 -0400
@@ -0,0 +1,6 @@
+<?xml version="1.0"?>
+<tool_dependency>
+  <package name="msproteomicstools" version="0.3.2">
+    <repository changeset_revision="a523661475a2" name="package_msproteomicstools_0_3_2" owner="iuc" toolshed="https://testtoolshed.g2.bx.psu.edu" />
+  </package>
+</tool_dependency>