Mercurial > repos > melissacline > ucsc_xena_platform
changeset 35:d8dc482ef970
add functionality to import probeMap
| author | jingchunzhu <jingchunzhu@gmail.com> |
|---|---|
| date | Thu, 23 Jul 2015 16:14:33 -0700 |
| parents | a3fbe077a14c |
| children | d64a002c3b0c |
| files | xena_import.py xena_import.xml |
| diffstat | 2 files changed, 109 insertions(+), 102 deletions(-) [+] |
line wrap: on
line diff
--- a/xena_import.py Thu Jul 23 01:02:24 2015 -0700 +++ b/xena_import.py Thu Jul 23 16:14:33 2015 -0700 @@ -53,6 +53,7 @@ parser.add_argument("--dataSubType", type=str, default=None) parser.add_argument("--label", type=str, default=None) parser.add_argument("--colNormalization", type=bool, default=False) + parser.add_argument("--probeMap", type=str, default=None) args = parser.parse_args() fp2 = open(args.outfile, "w") @@ -62,6 +63,10 @@ jsonMetadataTargetPathname = "%s/%s.json" % (xenaFileDir, genomicDataFile) + if args.probeMap is not None: + probeMapDataFile = args.probeMap.split("/")[-1] + jsonProbeMapMetadataTargetPathname = "%s/%s.json" % (xenaFileDir, + probeMapDataFile) # The metadata either came as the name of a JSON file or a series of # command line arguments. @@ -83,13 +88,27 @@ metadata['colNormalization'] = "true" else: updateColNormalization(metadata) + if args.probeMap is not None: + metadata[':probeMap'] = probeMapDataFile + jsonMetadata = json.dumps(metadata, indent=2) fp = open(jsonMetadataTargetPathname, "w") fp.write("%s\n" % (jsonMetadata)) fp.close() + if args.probeMap is not None: + probeMapMetadata={"type":"probeMap"} + jsonProbeMapMetadata = json.dumps(probeMapMetadata, indent=2) + jsonProbeMapMetadataTargetPathname = "%s/%s.json" % (xenaFileDir, + probeMapDataFile) + fp = open(jsonProbeMapMetadataTargetPathname, "w") + fp.write("%s\n" % ( jsonProbeMapMetadata)) + fp.close() + # Finally, copy the genomic data into the Xena directory shutil.copy(args.genomicDataPath, xenaFileDir) + if args.probeMap is not None: + shutil.copy(args.probeMap, xenaFileDir) # Set up the xena load comamnd and try to execute it. If an exception # is generated, output a traceback and exit with nonzero status. If @@ -99,6 +118,16 @@ xenaFileDir, genomicDataFile, xena.port()) + loadInToXena (xenaLoadCmd, fp2) + if args.probeMap is not None: + xenaLoadCmd = "java -jar %s -l --force %s/%s -p %s" % (xena.jarPath(), + xenaFileDir, + probeMapDataFile, + xena.port()) + loadInToXena (xenaLoadCmd, fp2) + + +def loadInToXena (xenaLoadCmd, fp2): try: subprocess.call(xenaLoadCmd, shell=True) except: @@ -113,6 +142,5 @@ fp2.close() sys.exit(0) - if __name__ == "__main__": main()
--- a/xena_import.xml Thu Jul 23 01:02:24 2015 -0700 +++ b/xena_import.xml Thu Jul 23 16:14:33 2015 -0700 @@ -1,124 +1,103 @@ -<tool id="xenaImport" description="Import into XENA from Galaxy" name="XENA Import" version="0.0.1"> +<tool id="xenaImport" name="XENA Import" version="0.0.1"> <description>Import from Galaxy into the Xena VM</description> <requirements> <requirement type="package" version="1.0">installXena</requirement> </requirements> <command interpreter="python"> xena_import.py ${xenaInputData} $outfile - #if $source.metadataSource == "json" - --json ${source.xenaMetadata} - #else - --cohort "${source.cohort}" --type ${source.format.metadataType} - #if $source.format.metadataType == "genomicMatrix" or $source.format.metadataType == "clinicalMatrix": - #if $source.format.isCustom.dataSubType == "custom" - #if $source.format.isCustom.customSubType - --dataSubType "${source.format.isCustom.customSubType}" - #end if - #else - --dataSubType "${source.format.isCustom.dataSubType}" + --cohort "${cohort}" --type ${format.metadataType} + #if $format.metadataType == "genomicMatrix" or $format.metadataType == "clinicalMatrix": + #if $format.isCustom.dataSubType == "custom" + #if $format.isCustom.customSubType + --dataSubType "${format.isCustom.customSubType}" #end if - #end if - #if $source.label - --label "${source.label}" #else - --label "${xenaInputData.name}" + --dataSubType "${format.isCustom.dataSubType}" #end if #end if + + #if $label + --label "${label}" + #else + --label "${xenaInputData.name}" + #end if + + #if $format.withProbeMap.probeMap =="select" + --probeMap "${format.withProbeMap.probeMapFile}" + #end if + #if $colNormalization: --colNormalization 1 #end if </command> <inputs> <param format="data" type="data" name="xenaInputData" label="Data to import to Xena" optional="false"/> - <conditional name="source"> - <param type="select" name="metadataSource" label="Metadata entry"> - <option value="entry">Enter your own</option> - <option value="json">Specify json metadata file</option> + <param format="str" type="text" name="cohort" label="Cohort" optional="false"/> + <conditional name="format"> + <param type="select" name="metadataType" label="File Format"> + <option value="genomicMatrix">Rows (Identifiers) by Columns (Samples) (often genomic data)</option> + <option value="clinicalMatrix">Rows (Samples) by Columns (Identifiers) (often clinical data)</option> + <option value="mutationVector">Mutation By Position</option> </param> - <when value="json"> - <param format="data" type="data" name="xenaMetadata" label="Metadata file" optional="false"/> + <when value="genomicMatrix"> + <conditional name="withProbeMap"> + <param type="select" name="probeMap" label="Identifier to Gene Mapping"> + <option value="none">No id to gene mapping file</option> + <option value="select">Select a id to gene mapping file</option> + </param> + <when value="none"/> + <when value="select"> + <param type="data" format="tabular" multiple="false" name="probeMapFile" optional="false"/> + </when> + </conditional> + + <conditional name="isCustom"> + <param type="select" name="dataSubType" label="Type of data"> + <option value="custom">Enter your own</option> + <option value="copy number">copy number</option> + <option value="DNA methylation">DNA methylation</option> + <option value="exon expression">exon expression</option> + <option value="gene expression">gene expression</option> + <option value="gene expression RNAseq">gene expression RNAseq</option> + <option value="gene expression Array">gene expression Array</option> + <option value="mRNA expression">mRNA expression</option> + <option value="somatic mutation (SNP and small INDELs)">somatic mutation (SNP and small INDELs)</option> + <option value="somatic mutation (gene level)">somatic mutation (gene level)</option> + <option value="protein expression RPPA">protein expression RPPA</option> + <option value="PARADIGM pathway activity">PARADIGM pathway activity</option> + </param> + <when value="custom"> + <param type="text" name="customSubType" label="Type of data" optional="true"/> + </when> + <when value="copy number"/> + <when value="DNA methylation"/> + <when value="exon expression"/> + <when value="gene expression"/> + <when value="gene expression RNAseq"/> + <when value="gene expression Array"/> + <when value="mRNA expression"/> + <when value="somatic mutation (SNP and small INDELs)"/> + <when value="somatic mutation (gene level)"/> + <when value="protein expression RPPA"/> + <when value="PARADIGM pathway activity"/> + </conditional> + </when> - <when value="entry"> - <param format="str" type="text" name="cohort" label="Cohort" optional="false"/> - <conditional name="format"> - <param type="select" name="metadataType" label="File Format"> - <option value="genomicMatrix">Rows (Identifiers) by Columns (Samples) (often genomic data)</option> - <option value="clinicalMatrix">Rows (Samples) by Columns (Identifiers) (often clinical data)</option> - <option value="mutationVector">Mutation By Position</option> - </param> - <when value="genomicMatrix"> - <conditional name="isCustom"> - <param type="select" name="dataSubType" label="Type of data"> - <option value="custom">Enter your own</option> - <option value="phenotype">phenotype</option> - <option value="copy number">copy number</option> - <option value="DNA methylation">DNA methylation</option> - <option value="exon expression">exon expression</option> - <option value="gene expression">gene expression</option> - <option value="gene expression RNAseq">gene expression RNAseq</option> - <option value="gene expression Array">gene expression Array</option> - <option value="mRNA expression">mRNA expression</option> - <option value="somatic mutation (SNP and small INDELs)">somatic mutation (SNP and small INDELs)</option> - <option value="somatic mutation (gene level)">somatic mutation (gene level)</option> - <option value="protein expression RPPA">protein expression RPPA</option> - <option value="PARADIGM pathway activity">PARADIGM pathway activity</option> - </param> - <when value="custom"> - <param type="text" name="customSubType" label="Type of data" optional="true"/> - </when> - <when value="phenotype"/> - <when value="copy number"/> - <when value="DNA methylation"/> - <when value="exon expression"/> - <when value="gene expression"/> - <when value="gene expression RNAseq"/> - <when value="gene expression Array"/> - <when value="mRNA expression"/> - <when value="somatic mutation (SNP and small INDELs)"/> - <when value="somatic mutation (gene level)"/> - <when value="protein expression RPPA"/> - <when value="PARADIGM pathway activity"/> - </conditional> - </when> - <when value="clinicalMatrix"> - <conditional name="isCustom"> - <param type="select" name="dataSubType" label="Type of data"> - <option value="custom">Enter your own</option> - <option value="phenotype">phenotype</option> - <option value="copy number">copy number</option> - <option value="DNA methylation">DNA methylation</option> - <option value="exon expression">exon expression</option> - <option value="gene expression">gene expression</option> - <option value="gene expression RNAseq">gene expression RNAseq</option> - <option value="gene expression Array">gene expression Array</option> - <option value="mRNA expression">mRNA expression</option> - <option value="somatic mutation (SNP and small INDELs)">somatic mutation (SNP and small INDELs)</option> - <option value="somatic mutation (gene level)">somatic mutation (gene level)</option> - <option value="protein expression RPPA">protein expression RPPA</option> - <option value="PARADIGM pathway activity">PARADIGM pathway activity</option> - </param> - <when value="custom"> - <param type="text" name="customSubType" label="Type of data" optional="true"/> - </when> - <when value="phenotype"/> - <when value="copy number"/> - <when value="DNA methylation"/> - <when value="exon expression"/> - <when value="gene expression"/> - <when value="gene expression RNAseq"/> - <when value="gene expression Array"/> - <when value="mRNA expression"/> - <when value="somatic mutation (SNP and small INDELs)"/> - <when value="somatic mutation (gene level)"/> - <when value="protein expression RPPA"/> - <when value="PARADIGM pathway activity"/> - </conditional> - </when> - <when value="mutationVector"/> - </conditional> - <param type="text" name="label" label="Display Name (Optional)" optional="true"/> + <when value="clinicalMatrix"> + <conditional name="isCustom"> + <param type="select" name="dataSubType" label="Type of data"> + <option value="custom">Enter your own</option> + <option value="phenotype">phenotype</option> + </param> + <when value="custom"> + <param type="text" name="customSubType" label="Type of data" optional="true"/> + </when> + <when value="phenotype"/> + </conditional> </when> + <when value="mutationVector"/> </conditional> + <param type="text" name="label" label="Display Name (Optional)" optional="true"/> <param type="boolean" name="colNormalization" label="Apply Column Normalization" checked="false"/> </inputs> <outputs>