def retriveDataForIds(ids,datasetCollectionName): raise Exception, " Error: Not completed" datasetsIndexFile = getMainDatasetIndexFileName(datasetCollectionName) datasets = readDatasetDescriptions.readDatasets(datasetsIndexFile,datasetCollectionName) for datasetKey in datasets.keys(): dataset = datasets[datasetKey] if cgsAS.getFeatureDatasetProperty(datasetKey,"hasFeatures") == False: continue dataset.openDBDataConnection(cgsAS) regionData = {} for id in ids: regionData[id] = {} for datasetKey in datasets.keys(): dataset = datasets[datasetKey] for id in ids: raise Exception, "Error: Not completed"
def exportDataInitializeStructures(datasets,regionSet,exportGenome): raise GDMException, "openDBDataConnection was changed" initializadDatasets = {} cgsAS = CGSAnnotationsSettings.CGSAnnotationsSettings(regionSet,exportGenome,{},{}) datasetsIndexFile = getMainDatasetIndexFileName(exportGenome) defaultDatasets = readDatasetDescriptions.readDatasets(datasetsIndexFile) #fullyProcessedDefaultDatasets = readSettingsFile(settings.fullyProcessedDefaultDatasetsFile) for datasetKey in defaultDatasets.keys(): if not datasetKey in datasets or cgsAS.getFeatureDatasetProperty(datasetKey,"hasFeatures") == False: log_CSEngine("exportDataInitializeStructures: Skipping "+datasetKey) continue log_CSEngine("exportDataInitializeStructures: Loading "+datasetKey) defaultDatasets[datasetKey].init(False) defaultDatasets[datasetKey].openDBDataConnection(cgsAS) initializadDatasets[datasetKey] = defaultDatasets[datasetKey] if datasetKey == regionSet: cgsAS.addRegionDataset({datasetKey:{}}) cgsAS.addFeatureDataset({datasetKey:{}}) return initializadDatasets
genome = sys.argv[1] directParam = "computeAll" if len(sys.argv) > 2: directParam = sys.argv[2] print "Genome:", genome datasetCollectionName = genome + "_ucsc_cpg_islands_test" cgsAS = CGSAnnotationsSettings.CGSAnnotationsSettings(datasetCollectionName, genome, {}, {}) if directParam == "computeAll": datasetsIndexFile = getMainDatasetIndexFileName(cgsAS.genome + "_test") #=============================================================================== # #Step 1 Read all datasets #=============================================================================== import readDatasetDescriptions datasets = readDatasetDescriptions.readDatasets(datasetsIndexFile) #=============================================================================== # #Step 2 Download and process datasets #=============================================================================== #datasets = {"broad_histones_CTCF":datasets["broad_histones_CTCF"], # datasetCollectionName:datasets[datasetCollectionName]} for dataset in datasets: datasets[dataset].init() cgsAS.addFeatureDataset( {dataset: datasets[dataset].getDefaultAnnotationSettings()}) if dataset == "hg18_ensembl_gene_genes": cgsAS.addFeatureDataset({ "hg18_ensembl_gene_genes": { "includeGO": True, "includeGeneDescriptions": True,
#=============================================================================== genome = sys.argv[1] directParam = "computeAll" if len(sys.argv) > 2: directParam = sys.argv[2] print "Genome:",genome datasetCollectionName = genome+"_ucsc_cpg_islands_test" cgsAS = CGSAnnotationsSettings.CGSAnnotationsSettings(datasetCollectionName,genome,{},{}) if directParam == "computeAll": datasetsIndexFile = getMainDatasetIndexFileName(cgsAS.genome+"_test") #=============================================================================== # #Step 1 Read all datasets #=============================================================================== import readDatasetDescriptions datasets = readDatasetDescriptions.readDatasets(datasetsIndexFile) #=============================================================================== # #Step 2 Download and process datasets #=============================================================================== #datasets = {"broad_histones_CTCF":datasets["broad_histones_CTCF"], # datasetCollectionName:datasets[datasetCollectionName]} for dataset in datasets: datasets[dataset].init() cgsAS.addFeatureDataset({dataset:datasets[dataset].getDefaultAnnotationSettings()}) if dataset == "hg18_ensembl_gene_genes": cgsAS.addFeatureDataset({"hg18_ensembl_gene_genes":{"includeGO":True, "includeGeneDescriptions": True, "includeOMIM": True, "includeGeneTranscripts":False, "includeGenesUpTo":10000}})