def read_cnv_data(self):
"""
Returns
-------
mapping of patient to mutations by entrez ids
"""
# Real Data #
# process Copy Number Variation data
patients = {}
ENTREZ_COL_NAME = 'Entrez Gene ID'
with open(config.get_safe_data_file(
self.args.cnv_patient_data)) as csvfile:
for row in csv.DictReader(csvfile):
ent_id = row[ENTREZ_COL_NAME]
for k, v in row.items():
if k == ENTREZ_COL_NAME or v == '0':
continue
pat_id = k
if pat_id not in patients:
patients[pat_id] = {'loss': [], 'gain': []}
if v == '1':
patients[pat_id]['loss'].append(ent_id)
else:
patients[pat_id]['gain'].append(ent_id)
return collections.OrderedDict(sorted(patients.items()))
def read_som_data(self):
# Real Data #
# process RNA-seq expression data
patients = {}
with open(config.get_safe_data_file(args.som_patient_data)) as csv_file:
reader = csv.DictReader(csv_file)
for row in reader:
pat_id = row['Patient ID']
ent_id = row['Entrez Gene ID']
if pat_id not in patients:
patients[pat_id] = {ent_id}
else:
patients[pat_id].add(ent_id)
return collections.OrderedDict(sorted(patients.items()))
def read_data(self):
# Real Data #
# process RNA-seq expression data
patients = {}
with open(config.get_safe_data_file(args.patient_data)) as csvfile:
reader = csv.DictReader(csvfile)
for row in reader:
pat_id = row['Patient ID']
ent_id = row['Entrez Gene ID']
if pat_id not in patients:
patients[pat_id] = {ent_id}
else:
patients[pat_id].add(ent_id)
return patients