currentGraph = ProteinDiseaseAssociationGraph.load(graphString)
# SOME DISEASES CAUSE "DIVIDE BY 0 error"
print("GRAPH {0} LOADED".format(graphString))
nodes = [ProteinInteractionNode, KeggNode, ReactomeNode, GoNode, InterproNode]
staticFeatures = []
print("--- USING {0} METAPATH FEATURE SETS".format(len(nodes)))
print("--- USING {0} STATIC FEATURE SETS".format(len(staticFeatures)))
if fileData is not None:
#print("FOUND {0} POSITIVE LABELS".format(len(fileData[True])))
#print("FOUND {0} NEGATIVE LABELS".format(len(fileData[False])))
trainData = metapathFeatures(disease,
currentGraph,
nodes,
staticFeatures,
loadedLists=fileData).fillna(0)
else:
trainData = metapathFeatures(disease, currentGraph, nodes,
staticFeatures).fillna(0)
d = BinaryLabel()
d.loadData(trainData)
#XGBCrossVal(d)
#print('calling function...', locals()[Procedure])
locals()[Procedure](d)
#print("FEATURES CREATED, STARTING ML")
#d = BinaryLabel()
#d.loadData(trainData)
logging.info("--- METAPATH FEATURE SETS: {0}".format(len(nodes)))
logging.info("--- STATIC FEATURE SETS: {0}".format(len(staticFeatures)))
logging.info("--- STATIC FEATURE DIR: {0}".format(args.static_dir))
# fetch the description of proteins
idDescription = dbAdapter.fetchPathwayIdDescription(
) # fetch the description
# generate features
if fileData is not None:
# logging.info("FOUND {0} POSITIVE LABELS".format(len(fileData[True])))
# logging.info("FOUND {0} NEGATIVE LABELS".format(len(fileData[False])))
allData = metapathFeatures(args.disease,
currentGraph,
nodes,
idDescription,
staticFeatures,
args.static_dir,
loadedLists=fileData).fillna(0)
else:
logging.error('fileData should not be None')
exit()
# Divide allData into training/predict set and save them
saveTrainPredictSet(allData, args.outputdir, args.disease,
args.trainingfile, args.predictfile)
logging.info('{0}: elapsed time: {1}'.format(
os.path.basename(sys.argv[0]),
time.strftime('%Hh:%Mm:%Ss', time.gmtime(time.time() - t0))))