print(p)
if args.schema:
def my_callback(schema):
# adds the source property
schema['category'] = 'hop extention'
schema['properties']['cases'] = {
'$ref': '_definitions.yaml#/to_one'
}
return schema
item_paths = ['output/hop/file.json']
link = {
'name': 'cases',
'backref': 'submitted_file',
'label': 'extends',
'target_type': 'case',
'multiplicity': 'one_to_one',
'required': False
}
schema_path = generate(item_paths,
'submitted_file',
output_dir=args.output_dir,
links=[link],
callback=my_callback)
assert os.path.isfile(p), 'should have an schema file {}'.format(
schema_path)
print(schema_path)
assert os.path.isfile(p), 'should have an output file {}'.format(p)
print(p)
if args.schema:
def my_callback(schema):
# adds the source property
schema['properties']['source'] = {'type': 'string'}
schema['category'] = 'bcc extention'
schema['properties']['demographic'] = {
'$ref': '_definitions.yaml#/to_one'
}
return schema
link = {
'name': 'demographic',
'backref': 'bcc_demographic',
'label': 'extends',
'target_type': 'demographic',
'multiplicity': 'many_to_one',
'required': False
}
schema_path = generate(item_paths,
'bcc_demographic',
output_dir='output/bcc',
links=[link],
callback=my_callback)
assert os.path.isfile(p), 'should have an schema file {}'.format(
schema_path)
print(schema_path)
if args.schema:
def my_callback(schema):
# adds the source property
schema['properties']['source'] = {'type': 'string'}
schema['properties']['diagnosis_name'] = {
'type': ['string', 'null']
}
schema['category'] = 'bcc extention'
schema['properties']['diagnosis'] = {
'$ref': '_definitions.yaml#/to_one'
}
return schema
link = {
'name': 'diagnosis',
'backref': 'bcc_diagnosis',
'label': 'extends',
'target_type': 'diagnosis',
'multiplicity': 'many_to_one',
'required': False
}
schema_path = generate(item_paths,
'bcc_diagnosis',
output_dir='output/bcc',
links=[link],
callback=my_callback)
assert os.path.isfile(p), 'should have an schema file {}'.format(
schema_path)
print(schema_path)
('source/bcc/voncologsurgery.json', 'Surgery', None),
('source/bcc/Radiotherapy.json', 'Radiotherapy', None)
]
treatment_ids = transform_gen3(item_paths, output_dir=args.output_dir, project_id=args.project_id)
# print('\n'.join(treatment_ids))
item_paths = [
('source/bcc/treatment_chemotherapy_ohsu.json', 'Chemotherapy', my_callback),
('source/bcc/treatment_chemotherapy_manually_entered.json', 'Chemotherapy', my_callback),
]
transform_chemotherapy(item_paths, treatment_ids=treatment_ids, output_dir=args.output_dir, project_id=args.project_id)
item_paths = [
'output/bcc/bcc_chemotherapy.json',
]
link = {'name':'treatment', 'backref':'bcc_chemotherapy', 'label':'describes', 'target_type':'treatment', 'multiplicity': 'many_to_one', 'required': False }
schema_path = generate(item_paths,'bcc_chemotherapy', output_dir='output/bcc', links=[link], callback=my_schema_callback)
assert os.path.isfile(schema_path), 'should have an schema file {}'.format(schema_path)
print(schema_path)
item_paths = [
('source/bcc/vResectionDate.json', 'Surgery', my_callback),
('source/bcc/voncologsurgery.json', 'Surgery', my_callback),
]
transform_surgery(item_paths, treatment_ids=treatment_ids, output_dir=args.output_dir, project_id=args.project_id)
item_paths = [
'output/bcc/bcc_surgery.json',
]
link = {'name':'treatment', 'backref':'bcc_surgery', 'label':'describes', 'target_type':'treatment', 'multiplicity': 'many_to_one', 'required': False }
schema_path = generate(item_paths,'bcc_surgery', output_dir='output/bcc', links=[link], callback=my_schema_callback)
assert os.path.isfile(schema_path), 'should have an schema file {}'.format(schema_path)
print(schema_path)
output_dir=args.output_dir,
project_id=args.project_id)
item_paths = [
'source/bcc/lesion_size.json',
]
link = {
'name': 'observation',
'backref': 'bcc_lesion',
'label': 'describes',
'target_type': 'observation',
'multiplicity': 'many_to_one',
'required': False
}
schema_path = generate(item_paths,
'bcc_lesion',
output_dir='output/bcc',
links=[link],
callback=my_schema_callback)
assert os.path.isfile(schema_path), 'should have an schema file {}'.format(
schema_path)
print(schema_path)
item_paths = [
('source/bcc/vWeightMonthly.json', 'Weight', my_callback),
('source/bcc/weight_ohsu.json', 'Weight', my_callback),
]
transform_weight(item_paths,
observation_ids=observation_ids,
output_dir=args.output_dir,
project_id=args.project_id)
item_paths = [
def my_schema_callback(schema):
"""Remove fields that start with _, fix key names with embedded /, fix id lookups """
for k in [k for k in schema['properties'] if k.startswith('_')]:
del schema['properties'][k]
for k in [k for k in schema['properties'] if '/' in k]:
schema['properties'][k.split('/')[1]] = schema['properties'][k]
del schema['properties'][k]
for k in [k for k in schema['properties'] if k.endswith('_id')]:
if k in ['project_id', 'submitter_id']:
continue
schema['properties'][k.replace('_id', '')] = {'type': ['string', "'null'"]} # schema['properties'][k]
del schema['properties'][k]
# adds the source property
schema['category'] = 'bcc extention'
schema['properties']['aliquot'] = {'$ref': '_definitions.yaml#/to_one'}
return schema
return schema
if __name__ == "__main__":
item_paths = ['source/bcc/sample.json']
args = default_parser(DEFAULT_OUTPUT_DIR, DEFAULT_EXPERIMENT_CODE, DEFAULT_PROJECT_ID).parse_args()
transform(item_paths, output_dir=args.output_dir, experiment_code=args.experiment_code, callback=my_callback)
link = {'name':'aliquot', 'backref':'bcc_aliquot', 'label':'derived_from', 'target_type':'aliquot', 'multiplicity': 'many_to_one', 'required': False }
schema_path = generate(item_paths,'bcc_aliquot', output_dir='output/bcc', links=[link], callback=my_schema_callback)
assert os.path.isfile(schema_path), 'should have an schema file {}'.format(schema_path)
print(schema_path)
if args.schema:
def my_callback(schema):
schema['category'] = 'bcc extention'
schema['properties']['case'] = {
'$ref': '_definitions.yaml#/to_one'
}
return schema
item_paths = [
'output/bcc/submitted_file.json',
]
link = {
'name': 'cases',
'backref': 'bcc_submitted_files',
'label': 'extends',
'target_type': 'case',
'multiplicity': 'many_to_one',
'required': False
}
schema_path = generate(item_paths,
'bcc_submitted_file',
output_dir='output/bcc',
links=[link],
callback=my_callback)
assert os.path.isfile(
schema_path), 'should have an schema file {}'.format(schema_path)
print(schema_path)
if __name__ == "__main__":
item_paths = [
'source/bcc/sample_genetrails_copy_number_variant.json',
'source/bcc/sample_genetrails_sequence_variant.json'
]
args = default_parser(DEFAULT_OUTPUT_DIR, DEFAULT_EXPERIMENT_CODE,
DEFAULT_PROJECT_ID).parse_args()
transform(item_paths,
output_dir=args.output_dir,
experiment_code=args.experiment_code,
callback=my_callback)
link = {
'name': 'aliquot',
'backref': 'genetrails',
'label': 'derived_from',
'target_type': 'aliquot',
'multiplicity': 'many_to_one',
'required': False
}
schema_path = generate(item_paths,
'genetrails_variant',
output_dir='output/bcc',
links=[link],
callback=my_schema_callback)
assert os.path.isfile(schema_path), 'should have an schema file {}'.format(
schema_path)
print(schema_path)
schema['properties']['aliquot'] = {'$ref': '_definitions.yaml#/to_one'}
return schema
if __name__ == "__main__":
item_paths = ['source/bcc/WESResults.json']
args = default_parser(DEFAULT_OUTPUT_DIR, DEFAULT_EXPERIMENT_CODE,
DEFAULT_PROJECT_ID).parse_args()
transform(item_paths,
output_dir=args.output_dir,
experiment_code=args.experiment_code,
callback=my_callback)
item_paths = ['output/bcc/wes_result.json']
link = {
'name': 'aliquot',
'backref': 'wes_result',
'label': 'derived_from',
'target_type': 'aliquot',
'multiplicity': 'many_to_one',
'required': False
}
schema_path = generate(item_paths,
'wes_result',
output_dir='output/bcc',
links=[link],
callback=my_schema_callback)
assert os.path.isfile(schema_path), 'should have an schema file {}'.format(
schema_path)
print(schema_path)
item_paths = [
'output/bcc/bcc_biomarker.json',
]
link = {
'name': 'cases',
'backref': 'bcc_biomarkers',
'label': 'extends',
'target_type': 'case',
'multiplicity': 'many_to_one',
'required': False
}
schema_path = generate(item_paths,
'bcc_biomarker',
output_dir='output/bcc',
links=[link],
callback=my_callback)
assert os.path.isfile(
schema_path), 'should have an schema file {}'.format(schema_path)
print(schema_path)
# [
# "CA19 Values After Specimen Collection",
# "Date",
# "ID_Event",
# "Order Proc ID",
# "Participant ID",
# "_not_available_notes",
# "_not_available_reason_id",
# "assay version id",
# diagnosis['*last_known_disease_status'] = disease_status.get(line['Cancer Status'], 'Unknown tumor status')
# diagnosis['*morphology'] = 'tumor_size={}'.format(line['Tumor Size']) # "None is not of type 'string'")
# diagnosis['*primary_diagnosis'] = line['Case_ICD::Transformation']
# diagnosis['*progression_or_recurrence'] = 'unknown' # ['yes', 'no', 'unknown', 'not reported', 'Not Allowed To Collect']
# diagnosis['*site_of_resection_or_biopsy'] = 'unknown'
# diagnosis['*tissue_or_organ_of_origin'] = 'pancrease'
# diagnosis['*tumor_grade'] = 'unknown' # "None is not of type 'string'")
# diagnosis['*tumor_stage'] = 'unknown' # "None is not of type 'string'")
# diagnosis['*vital_status'] = 'unknown'
#
# diagnosis_emitter.write(diagnosis)
cases_emitter.close()
demographics_emitter.close()
if __name__ == "__main__":
item_paths = [
'source/ccle/Individual.Vertex.json.gz',
'source/ccle/maf.Individual.Vertex.json.gz'
]
args = default_parser().parse_args()
transform(item_paths=item_paths, output_dir=args.output_dir)
# glob.glob("output/bcc/*.json")
if args.schema:
schema_path = generate(item_paths,
'case',
output_dir=DEFAULT_OUTPUT_DIR)
print(schema_path)
if 'chromosome' in line:
line['chromosome'] = str(line['chromosome'].replace('chr',''))
return line
def my_pre_processor(schema):
"""Remove fields that start with _, fix key names with embedded /, fix id lookups """
for k in [k for k in schema['properties'] if k.startswith('_')]:
del schema['properties'][k]
for k in [k for k in schema['properties'] if '/' in k]:
schema['properties'][k.split('/')[1]] = schema['properties'][k]
del schema['properties'][k]
for k in [k for k in schema['properties'] if k.endswith('_id')]:
if k in ['submitter_id', 'project_id']:
continue
schema['properties'][k.replace('_id', '')] = {'type': ['string', "'null'"]} # schema['properties'][k]
del schema['properties'][k]
return schema
if __name__ == "__main__":
item_paths = ['source/bcc/sample_genetrails_copy_number_variant.json','source/bcc/sample_genetrails_sequence_variant.json']
args = default_parser(DEFAULT_OUTPUT_DIR, DEFAULT_EXPERIMENT_CODE, DEFAULT_PROJECT_ID).parse_args()
transform(item_paths, project_id=DEFAULT_PROJECT_ID, output_dir=args.output_dir, experiment_code=args.experiment_code, callback=my_callback)
# glob.glob("output/bcc/*.json")
if args.schema:
schema_path = generate(item_paths,'allele', output_dir='output/bcc', callback=my_pre_processor)
print(schema_path)
'answer': answer(row),
}
survey_emitter.write(survey)
survey_emitter.close()
if __name__ == "__main__":
item_paths = [DEFAULT_INPUT_FILE]
args = default_parser(DEFAULT_OUTPUT_DIR, DEFAULT_EXPERIMENT_CODE, DEFAULT_PROJECT_ID).parse_args()
transform(item_paths, output_dir=args.output_dir, experiment_code=args.experiment_code)
p = os.path.join(args.output_dir, 'survey.json')
assert os.path.isfile(p), 'should have an output file {}'.format(p)
print(p)
if args.schema:
def my_callback(schema):
# adds the source property
schema['category'] = 'hop extention'
schema['properties']['cases'] = {'$ref': '_definitions.yaml#/to_one'}
return schema
item_paths = ['output/hop/survey.json']
link = {'name':'cases', 'backref':'hop_survey', 'label':'extends', 'target_type':'case', 'multiplicity': 'one_to_one', 'required': False }
schema_path = generate(item_paths,'hop_survey', output_dir=args.output_dir, links=[link], callback=my_callback)
assert os.path.isfile(p), 'should have an schema file {}'.format(schema_path)
print(schema_path)
print(p)
if args.schema:
def my_callback(schema):
# adds the source property
schema['properties']['source'] = {'type': 'string'}
schema['category'] = 'bcc extention'
schema['properties']['case'] = {
'$ref': '_definitions.yaml#/to_one'
}
return schema
item_paths = ['output/bcc/bcc_participant.json']
link = {
'name': 'case',
'backref': 'bcc_participants',
'label': 'extends',
'target_type': 'case',
'multiplicity': 'many_to_one',
'required': False
}
schema_path = generate(item_paths,
'bcc_participant',
output_dir='output/bcc',
links=[link],
callback=my_callback)
assert os.path.isfile(p), 'should have an schema file {}'.format(
schema_path)
print(schema_path)