def export_patients(bot, patient_ids, study, owner, out_file, progress_callback):
start_time = time.time()
count = 0
n_exported = 0
prop_names = bot.list_patient_class_properties()
writer = csv.writer(out_file)
writer.writerow(prop_names)
for patient_id in patient_ids:
progress_callback(count)
count += 1
if study != None:
patient_study = bot.get_study(patient_id)
if patient_study != study and not (study == '' and patient_study == None):
continue
if owner:
patient_owner = bot.get_owner(patient_id)
if PhenoTipsBot.qualify(patient_owner) != PhenoTipsBot.qualify(owner):
continue
patient = bot.get(patient_id)
patient['identifier'] = 'P' + patient['identifier'].zfill(7)
row = []
for prop_name in prop_names:
row.append(patient[prop_name])
writer.writerow(row)
n_exported += 1
return n_exported, timedelta(seconds=time.time() - start_time)
def get_clinvar_data(bot, patient_ids, study, owner, gene, progress_callback):
start_time = time.time()
count = 0
clinvar_data = OrderedDict()
for patient_id in patient_ids:
count += 1
progress_callback(count)
if study != None:
patient_study = bot.get_study(patient_id)
if study != patient_study.lower() and not (study == '' and patient_study == None):
continue
if owner:
patient_owner = bot.get_owner(patient_id)
if PhenoTipsBot.qualify(patient_owner) != PhenoTipsBot.qualify(owner):
continue
clinvar_variant_nums = bot.list_objects(patient_id, 'Main.ClinVarVariant')
if len(clinvar_variant_nums) == 0:
continue
patient_obj = bot.get(patient_id)
for clinvar_variant_num in clinvar_variant_nums:
clinvar_variant_obj = bot.get_object(patient_id, 'Main.ClinVarVariant', clinvar_variant_num)
gene_symbol = clinvar_variant_obj.get('gene_symbol')
if gene and (not gene_symbol or not gene in gene_symbol.upper().split(';')):
continue
#we aggregate all fields except for these
clinvar_data_key = (
clinvar_variant_obj['reference_sequence'] if 'reference_sequence' in clinvar_variant_obj else None,
clinvar_variant_obj['hgvs'] if 'hgvs' in clinvar_variant_obj else None,
clinvar_variant_obj['cis_or_trans'] if 'cis_or_trans' in clinvar_variant_obj else None,
clinvar_variant_obj['location'] if 'location' in clinvar_variant_obj else None,
patient_obj['omim_id'] if 'omim_id' in patient_obj else None,
clinvar_variant_obj['condition_category'] if 'condition_category' in clinvar_variant_obj else None,
clinvar_variant_obj['clinical_significance'] if 'clinical_significance' in clinvar_variant_obj else None,
clinvar_variant_obj['collection_method'] if 'collection_method' in clinvar_variant_obj else None,
clinvar_variant_obj['allele_origin'] if 'allele_origin' in clinvar_variant_obj else None,
clinvar_variant_obj['tissue'] if 'tissue' in clinvar_variant_obj else None,
patient_obj ['case_or_control'] if 'case_or_control' in patient_obj else None,
)
if not clinvar_data_key in clinvar_data:
clinvar_data[clinvar_data_key] = []
clinvar_data[clinvar_data_key].append((patient_obj, clinvar_variant_obj))
return clinvar_data, timedelta(seconds=time.time() - start_time)
writer = csv.writer(sys.stdout, delimiter='\t')
fid = study if study else '0'
for patient_id in patient_ids:
stderr.write(str(count) + '\r')
count += 1
if study != None:
patient_study = bot.get_study(patient_id)
if patient_study != study and not (study == '' and patient_study == None):
continue
if owner:
patient_owner = bot.get_owner(patient_id)
if PhenoTipsBot.qualify(patient_owner) != PhenoTipsBot.qualify(owner):
continue
patient = bot.get(patient_id)
iid = patient['external_id']
pat = '0'
mat = '0'
if patient.get('gender') == 'M':
sex = 1
elif patient.get('gender') == 'F':
sex = 2
else:
sex = 0
if patient.get('case_or_control') == 'case':
phenotype = 2
elif patient.get('case_or_control') == 'control':