Mercurial > repos > vandelj > giant_gsea_format

changeset 1:d72f1bc5ce9e draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
"planemo upload for repository https://github.com/juliechevalier/GIANT/tree/master commit e2b27d6ff2eab66454f984dbf1a519192f41db97"
author vandelj
date Wed, 09 Sep 2020 10:36:26 +0000
parents 3022feec50fe
children 738ed1deed23
files galaxy/wrappers/FormatForGSEA.xml src/General_functions.py
diffstat 2 files changed, 35 insertions(+), 36 deletions(-) [+]
line wrap: on
line diff
--- a/galaxy/wrappers/FormatForGSEA.xml	Fri Jun 26 09:36:46 2020 -0400
+++ b/galaxy/wrappers/FormatForGSEA.xml	Wed Sep 09 10:36:26 2020 +0000
@@ -1,6 +1,7 @@
 <tool name="GIANT-GSEA Formatting" id="giant_gsea_format" version="0.2.0">
   <description>Format input files for GSEA software</description>
   <code file="../../src/General_functions.py"/>
+  <!--<code file="./src/General_functions.py"/> change for Planemo test-->
   <stdio>
     <regex match="Execution halted"
            source="both"
@@ -60,7 +61,7 @@
         </param>
         <param type="data" name="conditionInformation" format="tabular" label="Factor information tabular file" optional="false" multiple="false">
         </param>
-            <param name="factorToInclude" type="select" label="Reference factor" multiple="false" optional="false"  refresh_on_change="true"
+        <param name="factorToInclude" type="select" label="Reference factor" multiple="false" optional="false"  refresh_on_change="true"
               dynamic_options="get_column_names_filteredList(mainCondition['conditionInformation'].file_name,[0])">
         </param>
       </when>
@@ -101,31 +102,27 @@
 
  <tests>
   <test maxseconds="3600" >
-    <param name="selection" value="classicGSEA" />
-    <param name="expressionData" value="./NormalizedData.tabular" />
-    <param name="conditionInformation" value="./conditionGroups.txt" />
-    <param name="factorToInclude" value="Treatment" />
-    <output name="outExpression" file="./GSEA-Formatting/outputExpression.gct" />
-    <output name="outPhenotypes" file="./GSEA-Formatting/outputPhenotypesTreatment.cls" />
-    <output name="log" file="./GSEA-Formatting/outputRanks.log" />
+    <conditional name="mainCondition">
+      <param name="selection" value="classicGSEA" />
+      <param name="expressionData" value="./NormalizedData.tabular" />
+      <param name="conditionInformation" value="./FactorFileGenerator/output/conditionsFile.csv" />
+      <param name="factorToInclude" value="Treatment" />
+    </conditional>    
+    <output name="outExpression" file="./FormatForGSEA/output/outputExpression_A.gct" />
+    <output name="outPhenotypes" file="./FormatForGSEA/output/outputPhenotypes_A.cls" />
+    <output name="log" file="./FormatForGSEA/output/outputLog_A.txt" />
   </test>
+
   <test maxseconds="3600" >
-    <param name="selection" value="classicGSEA" />
-    <param name="expressionData" value="./NormalizedData.tabular" />
-    <param name="conditionInformation" value="./conditionGroups.txt" />
-    <param name="factorToInclude" value="Type" />
-    <output name="outExpression" file="./GSEA-Formatting/outputExpression.gct" />
-    <output name="outPhenotypes" file="./GSEA-Formatting/outputPhenotypesType.cls" />
-    <output name="log" file="./GSEA-Formatting/outputRanks.log" />
-  </test>
-  <test maxseconds="3600" >
-    <param name="selection" value="rankedGSEA" />
-    <param name="differentialAnalysis" value="./LIMMAstatistics.tabular" />
-    <param name="comparisonsToUse" value="WT*Control-KO*Control" />
-    <param name="rankingIndice" value="FC" />
-    <param name="pvalThreshold" value="0.05" />
-    <output name="outRankedGenes" file="./GSEA-Formatting/outputRanks.rnk" />
-    <output name="log" file="./GSEA-Formatting/outputRanks.log" />
+    <conditional name="mainCondition">
+      <param name="selection" value="rankedGSEA" />
+      <param name="differentialAnalysis" value="./DiffExprLimma/output/outputStat.csv" />
+      <param name="comparisonsToUse" value="TreatVsControl" />
+      <param name="rankingIndice" value="absFC" />
+      <param name="pvalThreshold" value="0.05" />
+    </conditional>    
+    <output name="outRankedGenes" file="./FormatForGSEA/output/outputRanks_B.rnk" />
+    <output name="log" file="./FormatForGSEA/output/outputLog_B.txt" />
   </test>
 </tests> 
   <help>
--- a/src/General_functions.py	Fri Jun 26 09:36:46 2020 -0400
+++ b/src/General_functions.py	Wed Sep 09 10:36:26 2020 +0000
@@ -1,5 +1,6 @@
 import re
 import numpy as np
+import galaxy.model
 
 def get_column_names( file_path, toNotConsider=-1, each=1):
 	options=[]
@@ -76,7 +77,7 @@
 
 def get_condition_file_names( file_list, toNotConsider=-1, each=1):
 	options=[]
-	if not isinstance(file_list,list):#if input file is a tabular file, act as get_column_names
+	if not (isinstance(file_list,list) or isinstance(file_list,galaxy.model.HistoryDatasetCollectionAssociation) or isinstance(file_list,galaxy.model.DatasetCollection)) :#if input file is a tabular file, act as get_column_names
 		inputfile = open(file_list.file_name)
 		firstLine = next(inputfile).strip().split("\t")
 		cpt=0
@@ -88,13 +89,17 @@
 				if cpt==each:
 					cpt=0
 		inputfile.close()
-	else:#if input file is a .cel file list or a collection
-		if not hasattr(file_list[0],'collection'):#if it is not a collection, get name easily
-			for i, field_component in enumerate( file_list ):
-				options.append( ( field_component.name, field_component.name, False ) )
-		else:#if the file is a collection, have to get deeper in the corresponding HistoryDatasetCollectionAssociation object
-			for i, field_component in enumerate( file_list[0].collection.elements ):
-				options.append( ( field_component.element_identifier, field_component.element_identifier, False ) )
+	else:#if input file is a .cel file list, a DatasetCollection or a HistoryDatasetCollectionAssociation
+			if isinstance(file_list,list):#if it is a list, retrieve names easily
+				for i, field_component in enumerate( file_list ):
+					options.append( ( field_component.name, field_component.name, False ) )
+			else:#if the file is a DatasetCollection, have to get deeper in the corresponding DatasetCollection object
+				if isinstance(file_list,galaxy.model.DatasetCollection):#if it is a list, retrieve names easily
+					for i, field_component in enumerate( file_list.elements ):
+						options.append( ( field_component.element_identifier, field_component.element_identifier, False ) )
+				else:#if the file is a HistoryDatasetCollectionAssociation, have to get a little bit deeper in the corresponding HistoryDatasetCollectionAssociation object
+					for i, field_component in enumerate( file_list.collection.elements ):
+						options.append( ( field_component.element_identifier, field_component.element_identifier, False ) )
 	return options
 
 def generateFactorFile( file_list, factor_list, outputFileName, logFile):
@@ -102,10 +107,7 @@
 	outputfile = open(outputFileName, 'w')
 	outputLog = open(logFile, 'w')
 	sampleList=[]
-	if not isinstance(file_list,list):
-		conditionNames=get_condition_file_names(file_list,0) #unique expression file, remove the first column (index=0)
-	else :
-		conditionNames=get_condition_file_names(file_list) #.CEL files
+	conditionNames=get_condition_file_names(file_list,0) #if it's a unique expression file, remove the first column (index=0)
 	for iSample, sample_component in enumerate (conditionNames):
 		sampleList.append(str(sample_component[1]))
 	outputLog.write("[INFO] "+str(len(sampleList))+" sample are detected as input\n")