Mercurial > repos > vandelj > giant_aptsummarize
changeset 1:2762a2622e0d draft
"planemo upload for repository https://github.com/juliechevalier/GIANT/tree/master commit e2b27d6ff2eab66454f984dbf1a519192f41db97"
| author | vandelj |
|---|---|
| date | Wed, 09 Sep 2020 10:43:27 +0000 |
| parents | 708f43bda2b6 |
| children | 41f95153ce4b |
| files | galaxy/wrappers/ArrayNormalization.xml src/General_functions.py |
| diffstat | 2 files changed, 23 insertions(+), 31 deletions(-) [+] |
line wrap: on
line diff
--- a/galaxy/wrappers/ArrayNormalization.xml Fri Jun 26 09:35:11 2020 -0400 +++ b/galaxy/wrappers/ArrayNormalization.xml Wed Sep 09 10:43:27 2020 +0000 @@ -1,7 +1,7 @@ <tool name="GIANT-Normalization with APT Summarize" id="giant_aptsummarize" version="0.1.1"> <description>Apply Affymetrix Power Tool summarize function to .CEL collection</description> <requirements> - <requirement type="package" version="2.10.1">apt-probeset-summarize</requirement> + <requirement type="package" version="2.10.2">apt-probeset-summarize</requirement> </requirements> <stdio> <regex match="Execution halted" @@ -11,11 +11,8 @@ <exit_code range="10" level="fatal" description="Error in post-treatments, see log file for more information." /> <exit_code range="1:9" level="fatal" description="Error during apt command execution, see log file for more information." /> </stdio> - - - - <command> <![CDATA[ - ##ONLY FOR LOCAL TEST PURPOSE, COMMENT OTHERWISE + <command> <![CDATA[ + ##only for local test, comment otherwise ##set $pathToApt='/mnt/galaxy/home/galaxy/Software/ThermoFischer/apt-1.20.6-x86_64-intel-linux/bin' mkdir ./apt_output/; @@ -104,8 +101,6 @@ ]]> </command> - - <configfiles> <configfile name="scriptFormat"> <![CDATA[ @@ -176,8 +171,6 @@ </configfile> </configfiles> - - <inputs> <param type="text" name="title" value="APT_toPersonalize" label="Title for output"/> @@ -253,13 +246,11 @@ </conditional> </inputs> - - <outputs> <data format="tabular" name="outputData" label="${title}_NormalizedData"/> <data format="txt" name="log" label="${title}_Log" /> </outputs> - + <tests> @@ -268,16 +259,15 @@ <param name="commandLine" value="rma-gc-scale" /> <param name="normLevel" value="core" /> <param name="arraySelection" value="other" /> - <param name="CDFfile" value="./Mouse430_2.cdf" /> - <param name="annotationFile" value="./formatedAnnotation.csv" /> + <param name="CDFfile" value="./APT-summarize/input/Mouse430_2.cdf" /> + <param name="annotationFile" value="./APT-summarize/input/formatedAnnotation.csv" /> <param name="addAnnotation" value="true" /> <param name="keepAnnotated" value="false" /> <param name="mergingMethod" value="mean" /> - <output name="outputData" file="./APT-summarize/expressionOutput.csv" /> - <output name="log" file="./APT-summarize/output.log" lines_diff="2" /> + <output name="outputData" file="./APT-summarize/output/outputExpression.csv" /> + <output name="log" file="./APT-summarize/output/outputLog.txt" compare="sim_size" delta_frac="0.15" /> </test> -</tests> - + </tests>
--- a/src/General_functions.py Fri Jun 26 09:35:11 2020 -0400 +++ b/src/General_functions.py Wed Sep 09 10:43:27 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")