#filePath = argData['dir'] + fileName #IMPORTANT: update this if folder name changes
tmpPath = fileName.split('/')[:-1]
filePath = '/'.join(i for i in tmpPath)
#fetch the saved important features
importance = load_obj(fileName)
#importance = Counter({'R-HSA-927802': 0.31735258141642814, 'hsa04740': 0.2208299216149202, 'hsa05100': 0.1847905733996812, 'hsa04930': 0.10625980494746863, 'hsa04514': 0.047493659101048136, 'hsa04114': 0.03542724660274679, 'hsa04810': 0.03365848585388666, 'hsa04144': 0.030556051003490892})
#access the database to get the description of important features
#dbAdapter = OlegDB()
dbAdapter = TCRD() if argData['db'] == "tcrd" else OlegDB()
#labelMap = convertLabels(importance.keys(),dbAdapter,selectAsDF,type='plot')
if True:
currentGraph = ProteinDiseaseAssociationGraph.load(argData['kgfile'])
# for the graph, we need the original importance
for imp in importance.most_common(numOfFeatures):
print(imp)
Visualize(imp, currentGraph.graph, diseaseName, filePath, dbAdapter=dbAdapter) #g,currentGraph.graph,Disease)
#break
#newSet = {}
#for key in importance.keys():
# newSet[labelMap[key]] = importance[key]
#print('STARTING FEAT VIS')
#AUC = 0.9
#print(newSet,labelMap)
#featureVisualize(Counter(newSet),AUC,"AAA")
# Create a Protein Disease graph from the DB adapter 'OlegDB'
from ProteinGraphML.DataAdapter import OlegDB
from ProteinGraphML.GraphTools import ProteinDiseaseAssociationGraph
## we construct a base map of protein to disease just by creating the ProteinDiseaseAs
dbAdapter = OlegDB()
proteinGraph = ProteinDiseaseAssociationGraph(dbAdapter)
## the 'ProteinDiseaseAssociationGraph' object has helper methods, but we can also access the networkx graph directly it is created with:
print('Total nodes: %d' % len(proteinGraph.graph.nodes))
## we will want to filter by the proteins we are interested in, this list comes from a DB adapter, but any set will do
proteins = dbAdapter.loadTotalProteinList().protein_id
filterByProteins = set(proteins)
# using .attach will add edges from a DB as defined by the adapter,
# with this method we can create a graph of data, which can itself be saved, prevents the
# need from, rebuilding as we work on different diseases, perform analysis
# We've also filter by proteins we care about, in this case it is our original list
proteinGraph.attach(dbAdapter.loadPPI(filterByProteins))
proteinGraph.attach(dbAdapter.loadKegg(filterByProteins))
proteinGraph.attach(dbAdapter.loadReactome(filterByProteins))
proteinGraph.attach(dbAdapter.loadInterpro(filterByProteins))
proteinGraph.attach(dbAdapter.loadGo(filterByProteins))
# networkx provides an api we can nodes from \n",
# here i exploit the unique features of each node to count them\n",
print("running on this disease", disease)
print("")
DEFAULT_GRAPH = "newCURRENT_GRAPH"
# CANT FIND THIS DISEASE
#disease = sys.argv[1]
Procedure = argData['procedure'][0]
print('Procedure', Procedure)
graphString = None
graphString = DEFAULT_GRAPH
# CANT FIND THIS GRAPH
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,
print('HERE ARE LABELS')
#importance = {'hsa01100': 0.31735258141642814, 'hsa04740': 0.2208299216149202, 'hsa05100': 0.1847905733996812, 'hsa04930': 0.10625980494746863, 'hsa04514': 0.047493659101048136, 'hsa04114': 0.03542724660274679, 'hsa04810': 0.03365848585388666, 'hsa04144': 0.030556051003490892}#{"MP_0000180":34,343:1.0,30001:0.3}
#labelMap = convertLabels(importance.keys(),dbAdapter,selectAsDF,type='plot')
#for value[key] in importance.values():
newSet = {}
for key in importance.keys():
newSet[labelMap[key]] = importance[key]
AUC = 0.9
#print(newSet,labelMap)
if False:
currentGraph = ProteinDiseaseAssociationGraph.load("newCURRENT_GRAPH")
# for the graph, we need the original importance
for key in importance.keys():
Visualize((key, importance[key]),
currentGraph.graph,
"MP_0000180",
dbAdapter=dbAdapter) #g,currentGraph.graph,Disease)
break
print('STARTING FEAT VIS')
featureVisualize(Counter(newSet), AUC, "AAA")
#Visualize
#convertLabels([343,30001],dbAdapter,selectAsDF,type="han")
# folder where train and predict data with features will be stored
# outputDir = argData['outputdir']
if not os.path.isdir(args.outputdir):
logging.info('Create the output directory')
os.makedirs(args.outputdir)
logging.info('Output directory for ML data(Training/predict): {0}'.format(
args.outputdir))
# check whether file or disease was given
if args.trainingfile is None and args.disease is None:
parser.error("--disease or -- training file must be specified.")
# fetch KG data
# graphString = args.kgfile
currentGraph = ProteinDiseaseAssociationGraph.load(args.kgfile)
logging.info("GRAPH {0} LOADED".format(args.kgfile))
# Access the db adaptor. Make TCRD as the default DB
dbAdapter = OlegDB() if args.db == "olegdb" else TCRD()
if args.trainingfile is not None and args.disease is None:
# trainingPklFile = trainingfile
logging.info('Input training file: {0}'.format(args.trainingfile))
try:
with open(args.trainingfile, 'rb') as f:
fileData = pickle.load(f)
except:
logging.error('Invalid pickled training set file')
exit()
dbAdapter = OlegDB()
# CANT FIND THIS DISEASE(?)
# disease = "MP_0000180"
disease = "MP_0000184"
with db_session:
dname = dbAdapter.db.get("SELECT name FROM mp_onto WHERE mp_term_id = '" +
disease + "'")
logging.info("disease: {0}: \"{1}\"".format(disease, dname))
fileData = None
pickleFile = "ProteinDisease_GRAPH.pickle"
# CANT FIND THIS GRAPH(?)
currentGraph = ProteinDiseaseAssociationGraph.load(pickleFile)
# SOME DISEASES CAUSE "DIVIDE BY 0 error"
logging.info("GRAPH LOADED: {0}".format(pickleFile))
nodes = [ProteinInteractionNode, KeggNode, ReactomeNode, GoNode, InterproNode]
staticFeatures = [] # ALL OPTIONS HERE... ["gtex","lincs","hpa","ccle"]
logging.info("USING {0} METAPATH FEATURE SETS".format(len(nodes)))
logging.info("USING {0} STATIC FEATURE SETS".format(len(staticFeatures)))
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])))
trainData = metapathFeatures(disease,
currentGraph,
args = parser.parse_args()
logging.basicConfig(
format='%(asctime)s %(levelname)s:%(message)s',
level=(logging.DEBUG if args.verbose > 1 else logging.INFO))
t0 = time.time()
## Construct base protein-disease map from ProteinDiseaseAssociationGraph.
## Db is PonyORM db (https://docs.ponyorm.org/api_reference.html).
# Make TCRD as the default DB
dbad = OlegDB() if args.db == "olegdb" else TCRD()
pdg = ProteinDiseaseAssociationGraph(dbad)
## ProteinDiseaseAssociationGraph object has helper methods, but
## NetworkX methods also available.
## https://networkx.github.io/documentation/stable/reference/
logging.info('Total nodes: %d; edges: %d' %
(pdg.graph.order(), pdg.graph.size()))
## Filter by proteins of interest; this list comes from a DB adapter, but any set will do.
proteins = dbad.loadTotalProteinList().protein_id
proteinSet = set(proteins)
logging.info('Protein set: %d' % (len(proteinSet)))
# Using attach() add edges from DB.
# With this method create graph, which can be saved, avoiding