Mercurial > repos > melissacline > ucsc_cancer_utilities

changeset 41:9806198df91f

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
fix
author jingchunzhu
date Thu, 06 Aug 2015 00:27:05 -0700
parents 72dc9215623d
children 03b7b1cf78ce
files mergeGenomicFiles.xml mergeMutationDatasets.xml mergeXenaMutation.py
diffstat 3 files changed, 23 insertions(+), 18 deletions(-) [+]
line wrap: on
line diff
--- a/mergeGenomicFiles.xml	Fri Jul 31 21:29:17 2015 -0700
+++ b/mergeGenomicFiles.xml	Thu Aug 06 00:27:05 2015 -0700
@@ -1,4 +1,4 @@
-<tool id="mergeGenomicFiles" description="Merge two genomic datasets into a new dataset" name="Merge Genomic Datasets" version="0.0.1">
+<tool id="mergeGenomicFiles" description="Merge two genomic matrices into a new dataset" name="Merge Genomic Matrix Datasets" version="0.0.1">
   <description>
     Given two genomic datasets, merge them to create a larger dataset with the row and column identifiers from both datasets. Output this larger dataset, along with a 2-column matrix indicating the source file of each sample
   </description>
@@ -6,20 +6,24 @@
       mergeGenomicMatrixFiles.py $inputA $inputB $outputC $outputSourceMatrix
       #if $labelForDatasetA
           --aLabel "${labelForDatasetA}"
+      #else
+          --aLabel "${inputA.name}"
       #end if
       #if $labelForDatasetB
           --bLabel "${labelForDatasetB}"
+      #else
+          --bLabel "${inputB.name}"
       #end if
   </command>
   <inputs>
-    <param name="inputA" format="tabular" type="data" label="Genomic Dataset A"/>
-    <param type="text" name="labelForDatasetA"  label="Dataset A Label (optional)" optional="true"/>
-    <param name="inputB" format="tabular" type="data" label="Genomic Dataset B"/> 
-    <param type="text" name="labelForDatasetB"  label="Dataset B Label (optional)" optional="true"/>
+    <param name="inputA" format="tabular" type="data" label="Genomic Matrix A"/>
+    <param type="text" name="labelForDatasetA"  label="Dataset A Label (eg. A)" value="dataset A"/>
+    <param name="inputB" format="tabular" type="data" label="Genomic Matrix B"/> 
+    <param type="text" name="labelForDatasetB"  label="Dataset B Label (eg. B)" value="dataset B"/>
  </inputs>
   <outputs>
-    <data name="outputSourceMatrix" format="tabular" label="Genomic Data Sources"/>
-    <data name="outputC" format="tabular" label="Merged Genomic Data"/>
+    <data name="outputSourceMatrix" format="tabular" label="Data Source ${labelForDatasetB}+${labelForDatasetA}"/>
+    <data name="outputC" format="tabular" label="Genomic Matrix ${labelForDatasetB}+${labelForDatasetA}"/>
   </outputs>
   <help>
     ***Merge Genomic Datasets***
--- a/mergeMutationDatasets.xml	Fri Jul 31 21:29:17 2015 -0700
+++ b/mergeMutationDatasets.xml	Thu Aug 06 00:27:05 2015 -0700
@@ -1,26 +1,27 @@
-<tool id="mergeMutationDatasets" description="Merge two Xena positional mutation datasets into a new dataset" name="Merge Positional Mutation Data" 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>
+<tool id="mergeMutationDatasets" description="Merge two Xena positional mutation datasets into a new dataset" name="Merge Xena Mutation by Position Data" version="0.0.1">
   <command interpreter="python">
       mergeXenaMutation.py $outputC $outputSourceMatrix $errorLog  $inputA $inputB 
       #if $labelForDatasetA
           --aLabel "${labelForDatasetA}"
+      #else
+          --aLabel "${inputA.name}"
       #end if
       #if $labelForDatasetB
           --bLabel "${labelForDatasetB}"
+      #else
+          --bLabel "${inputB.name}"
       #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"/>
+    <param name="inputA" format="tabular" type="data" label="Xena Mutation by Position Dataset A"/>
+    <param type="text" name="labelForDatasetA"  label="Dataset A Label (eg. A)" value="dataset A"/>
+    <param name="inputB" format="tabular" type="data" label="Xena Mutation by Position Dataset B"/> 
+    <param type="text" name="labelForDatasetB"  label="Dataset B Label (eg. B)" value="dataset B"/>
  </inputs>
   <outputs>
     <data name="errorLog" format="data" label="Execution Log"/>
-    <data name="outputSourceMatrix" format="tabular" label="Mutation Data Sources"/> 
-    <data name="outputC" format="tabular" label="Merged Mutation Data"/>
+    <data name="outputSourceMatrix" format="tabular" label="Data Source ${labelForDatasetB}+${labelForDatasetA}"/> 
+    <data name="outputC" format="tabular" label="Mutation by Position ${labelForDatasetB}+${labelForDatasetA}"/>
   </outputs>
   <help>
     ***Merge Xena Positional Mutation Datasets***
--- a/mergeXenaMutation.py	Fri Jul 31 21:29:17 2015 -0700
+++ b/mergeXenaMutation.py	Thu Aug 06 00:27:05 2015 -0700
@@ -117,7 +117,7 @@
     sample = string.split(line,'\t')[0]
     if sample not in sampleDic:
       sampleDic[sample]=[]
-    if inFile not in sampleDic[sample]:
+    if label not in sampleDic[sample]:
       sampleDic[sample].append(label)
   fin.close()
   return