Mercurial > repos > vandelj > giant_volcano_plot

changeset 1:75505421bcf3 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 10:38:06 +0000
parents c9a38c1eadf1
children 866eec4605b0
files galaxy/wrappers/VolcanoPlotTool.xml src/General_functions.py
diffstat 2 files changed, 55 insertions(+), 29 deletions(-) [+]
line wrap: on
line diff
--- a/galaxy/wrappers/VolcanoPlotTool.xml	Fri Jun 26 09:45:41 2020 -0400
+++ b/galaxy/wrappers/VolcanoPlotTool.xml	Wed Sep 09 10:38:06 2020 +0000
@@ -1,4 +1,4 @@
-<tool name="GIANT-Plot volcanos" id="giant_volcano_plot" version="0.3.3">
+<tool name="GIANT-Plot volcanos" id="giant_volcano_plot" version="0.3.4">
   <description>Plot volcano from tabular file</description>
   <requirements>
     <requirement type="package" version="1.7.1">r-r.methodss3</requirement>
@@ -8,6 +8,7 @@
     <requirement type="package" version="1.3.1">r-stringr</requirement>
   </requirements>
   <code file="../../src/General_functions.py"/>
+  <!--<code file="./src/General_functions.py"/> change for Planemo test-->
   <stdio>
     <regex match="Execution halted"
            source="both"
@@ -25,6 +26,8 @@
     #import imp
     #set $runIdentifier=str($outputData).rsplit("/")[-1].rsplit(".")[0]
     #set $general_functions=$imp.load_source('General_functions', $__tool_directory__+'/../../src/General_functions.py')
+    ##change for Planemo test
+    ##set $general_functions=$imp.load_source('General_functions', $__tool_directory__+'/src/General_functions.py')
     #set $ret_code=$general_functions.selectSubSetTable($inputSection['inputData'].file_name,$inputSection['headerNumber'].value,[0],$volcanoSection['volcanoList'],$__new_file_path__+'/'+$__user_id__+'_'+$runIdentifier+'_statisticsFormated.csv',$log.file_name)
 
     if [ $ret_code != 0 ]; then
@@ -44,6 +47,8 @@
 
 
     Rscript '$__tool_directory__/../../src/VolcanoPlotsScript.R' -i 'statisticsFormated.csv' -l '$log' -o '$outputData' -f 'pdf'
+    ##change for Planemo test
+    ##Rscript '$__tool_directory__/src/VolcanoPlotsScript.R' -i 'statisticsFormated.csv' -l '$log' -o '$outputData' -f 'pdf'
       #for $i, $s in enumerate( $volcanoSection.volcanoList )
         -n '${s.volcanoName}'
         -p '${s.pvalColumn}'
@@ -324,25 +329,44 @@
   </outputs>
 
 
-  
+
  <tests>
   <test maxseconds="3600">
-    <param name="wfile" value="wiggle.wig" />
-    <param name="bfile" value="bedfile.bed" />
-    <param name="span" value="3000" />
-    <param name="pfres" value="50" />
-    <param name="lowersize" value="1000" />
-    <param name="middlesize" value="2000" />
-    <param name="uppersize" value="3000" />
-    <param name="lowerbisize" value="2500" />
-    <param name="upperbisize" value="5000" />
-    <param name="reldist" value="3000" />
-    <param name="genome" value="hg18" />
-    <param name="imagetype" value="PDF" />
-    <param name="enable" value="no" />
-    <output name="outputData" file="ceas_1/ceas_1.pdf" />
+    <section name="inputSection">
+      <param name="inputData" value="./DiffExprLimma/output/outputStat.csv" />
+      <param name="headerNumber" value="2" />
+    </section>
+    <section name="volcanoSection" >
+      <repeat name="volcanoList" >
+        <param name="volcanoName" value="TreatVsControl" />
+        <param name="pvalColumn" value="TreatVsControl_p-val" />
+        <param name="fdrColumn" value="TreatVsControl_FDR.p-val" />
+        <param name="fcColumn" value="TreatVsControl_log2(FC)" />
+      </repeat>
+      <repeat name="volcanoList" >
+        <param name="volcanoName" value="WTvsKO" />
+        <param name="pvalColumn" value="WTvsKO_p-val" />
+        <param name="fdrColumn" value="WTvsKO_FDR.p-val" />
+        <param name="fcColumn" value="WTvsKO_log2(FC)" />
+      </repeat>
+    </section>
+    <section name="plotSection" >
+      <param name="fcKind" value="log2(FC)" />
+      <param name="FDRthreshold" value="0.05" />
+      <param name="FCthreshold" value="2.0" />
+      <conditional name="geneInformation">
+        <param name="addGeneInfo" value="false" />
+      </conditional>
+      <param type="select" value="png" />
+    </section>
+    <output name="outputData" file="./VolcanoPlotTool/output/outputResults.csv" />
+    <output name="html_file" file="./VolcanoPlotTool/output/outputHTML.zip" decompress="true" />
+    <output name="log" file="./VolcanoPlotTool/output/outputLog.txt" compare="sim_size" delta_frac="0.10" />
   </test>
-</tests> 
+ </tests> 
+
+
+
   <help>
 <![CDATA[
 **What it does ?**
--- a/src/General_functions.py	Fri Jun 26 09:45:41 2020 -0400
+++ b/src/General_functions.py	Wed Sep 09 10:38:06 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")