# HG changeset patch
# User melissacline
# Date 1426889355 14400
# Node ID 371579dd9bc65418d04e43445c9294762656675e
# Parent  15cb5a49cdbcaf236c21b19996ff312052c6648c
Uploaded

diff -r 15cb5a49cdbc -r 371579dd9bc6 mergeMutationDatasets.xml
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/mergeMutationDatasets.xml	Fri Mar 20 18:09:15 2015 -0400
@@ -0,0 +1,31 @@
+<tool id="mergeMutationDatasets" description="Merge two mutation datasets into a new dataset" name="mergeMutationData" version="0.0.1">
+  <description>
+    Given two mutation datasets, merge them to create a larger dataset with the mutations from both datasets. Output this larger dataset, along with a 2-column matrix indicating the source of each mutation
+  </description>
+  <command interpreter="python">
+      mergeXenaMutation.py $outputC $outputSourceMatrix $errorLog  $inputA $inputB 
+      #if $labelForDatasetA
+          --aLabel "${labelForDatasetA}"
+      #end if
+      #if $labelForDatasetB
+          --bLabel "${labelForDatasetB}"
+      #end if
+  </command>
+  <inputs>
+    <param name="inputA" format="tabular" type="data" label="Mutation Dataset A"/>
+    <param type="text" name="labelForDatasetA"  label="Dataset A Label (optional)" optional="true"/>
+    <param name="inputB" format="tabular" type="data" label="Mutation Dataset B"/> 
+    <param type="text" name="labelForDatasetB"  label="Dataset B Label (optional)" optional="true"/>
+ </inputs>
+  <outputs>
+    <data name="outputC" format="tabular" label="Merged Mutation Data"/>
+    <data name="outputSourceMatrix" format="tabular" label="Mutation Data Sources"/> 
+    <data name="errorLog" format="data" label="Execution Log"/>
+  </outputs>
+  <help>
+    ***Merge Xena Mutation Datasets***
+
+    Given two datasets of mutation data as formatted for the UCSC Xena Browser, merge them to produce a third dataset that is the union of the first two.  The new dataset will contain all mutations from either dataset. 
+
+    To maintain provenance, this script also outputs a second matrix, with one row for each sample ID that appears in the output dataset, and two columns per row indicating which input dataset(s) contained some mutation data for that sample.  By default, the input dataset name is used to indicate which input file each column came from.  Optionally, the user can specify descriptive labels to be used in place of the dataset names.   </help>
+</tool>