def default_parser(output_dir, experiment_code, project_id):
parser = default_argument_parser(
output_dir=output_dir,
description='Reads bcc json and writes gen3 json ({}).'.format(output_dir)
)
parser.add_argument('--experiment_code', type=str,
default=experiment_code,
help='Name of gen3 experiment ({}).'.format(experiment_code))
parser.add_argument('--project_id', type=str,
default=project_id,
help='Name of gen3 program-project ({}).'.format(project_id))
parser.add_argument('--schema', type=bool,
default=True,
help='generate schemas (true).'.format(experiment_code))
return parser
def default_parser():
parser = default_argument_parser(
output_dir=DEFAULT_OUTPUT_DIR,
description='Reads bcc json and writes gen3 json ({}).'.format(
DEFAULT_OUTPUT_DIR))
parser.add_argument('--experiment_code',
type=str,
default=DEFAULT_EXPERIMENT_CODE,
help='Name of existing gen3 experiment ({}).'.format(
DEFAULT_EXPERIMENT_CODE))
parser.add_argument(
'--schema',
type=bool,
default=True,
help='generate schemas (true).'.format(DEFAULT_EXPERIMENT_CODE))
return parser
python3 load/gen3_query_generator.py $PP $EP --node_type slide_image
python3 load/gen3_query_generator.py $PP $EP --node_type submitted_aligned_reads
python3 load/gen3_query_generator.py $PP $EP --node_type submitted_copy_number
python3 load/gen3_query_generator.py $PP $EP --node_type submitted_file
python3 load/gen3_query_generator.py $PP $EP --node_type submitted_methylation
python3 load/gen3_query_generator.py $PP $EP --node_type submitted_somatic_mutation
python3 load/gen3_query_generator.py $PP $EP --node_type submitted_unaligned_reads
python3 load/gen3_query_generator.py $PP $EP --node_type hop_survey
python3 load/gen3_query_generator.py $PP $EP --node_type aliquot
"""
if __name__ == "__main__":
parser = default_argument_parser(
output_dir=DEFAULT_OUTPUT_DIR,
description='Reads gen3 json ({}), creates psql tsv .'.format(
DEFAULT_INPUT_DIR))
parser.add_argument(
'--program',
type=str,
default=DEFAULT_PROGRAM,
help='Name of existing gen3 program ({}).'.format(DEFAULT_PROGRAM))
parser.add_argument(
'--project',
type=str,
default=DEFAULT_PROJECT,
required=True,
help='Name of existing gen3 project ({}).'.format(DEFAULT_PROJECT))
parser.add_argument(
'--node_type',
diagnosis['*age_at_diagnosis'] = None
diagnosis['*classification_of_tumor'] = 'Unknown'
diagnosis['*days_to_last_follow_up'] = None
diagnosis['*days_to_last_known_disease_status'] = None
diagnosis['*days_to_recurrence'] = None
diagnosis['*last_known_disease_status'] = 'Unknown tumor status'
diagnosis['*morphology'] = 'unknown'
diagnosis['*progression_or_recurrence'] = 'unknown'
diagnosis['*site_of_resection_or_biopsy'] = 'unknown'
diagnosis['*tissue_or_organ_of_origin'] = 'unknown'
diagnosis['*tumor_grade'] = 'unknown'
diagnosis['*tumor_stage'] = 'unknown'
diagnosis['*vital_status'] = 'unknown'
diagnosis_emitter.write(diagnosis)
samples_emitter.close()
aliquots_emitter.close()
diagnosis_emitter.close()
if __name__ == "__main__":
parser = default_argument_parser(
output_dir=DEFAULT_OUTPUT_DIR,
description='Reads bcc tsv and writes gen3 json ({}).'.format(
DEFAULT_OUTPUT_DIR))
args = parser.parse_args()
transform(output_dir=args.output_dir)
if not deleted and delete_first:
delete_all(submission_client, program, project, types=[nodes[0]['type']])
deleted = True
collect_result(create_node(submission_client, program, project, nodes))
# pool.apply_async(create_node, args=(submission_client, program, project, nodes), callback=collect_result)
# logger.info(f'pool.close/join')
# pool.close()
# pool.join() # postpones the execution of next line of code until all processes in the queue are done
if __name__ == "__main__":
parser = default_argument_parser(
description='Reads gen3 json ({}).'.format(DEFAULT_INPUT_DIR)
)
parser.add_argument('--path', type=str,
default=DEFAULT_PATH,
help='Match these files ({}).'.format(DEFAULT_PATH))
parser.add_argument('--program', type=str,
default=DEFAULT_PROGRAM,
help='Name of existing gen3 program ({}).'.format(DEFAULT_PROGRAM))
parser.add_argument('--project', type=str,
default=DEFAULT_PROJECT,
required=True,
help='Name of existing gen3 project ({}).'.format(DEFAULT_PROJECT))
parser.add_argument('--batch_size', type=int,
default=DEFAULT_BATCH_SIZE,
help='Number of records to send to gen3 at a time({}).'.format(DEFAULT_BATCH_SIZE))
# {"_id": "(Callset:ccle:ACH-001270:None)--CallsetFor->(Aliquot:ACH-001270)", "gid": "(Callset:ccle:ACH-001270:None)--CallsetFor->(Aliquot:ACH-001270)", "label": "CallsetFor", "from": "Callset:ccle:ACH-001270:None", "to": "Aliquot:ACH-001270", "data": {}}
for line in reader('source/ccle/maf.CallsetFor.Edge.json.gz'):
# *type project_id *submitter_id *aliquots.submitter_id RIN adapter_name adapter_sequence barcoding_applied base_caller_name base_caller_version experiment_name flow_cell_barcode includes_spike_ins instrument_model is_paired_end library_name library_preparation_kit_catalog_number library_preparation_kit_name library_preparation_kit_vendor library_preparation_kit_version library_selection library_strand library_strategy platform read_group_name read_length sequencing_center sequencing_date size_selection_range spike_ins_concentration spike_ins_fasta target_capture_kit_catalog_number target_capture_kit_name target_capture_kit_target_region target_capture_kit_vendor target_capture_kit_version to_trim_adapter_sequence ]
read_group_submitter_id = 'read_group-{}'.format(line['from'])
if read_group_submitter_id in read_groups:
continue
read_group = {
'type': 'read_group',
'*aliquots': {
'submitter_id': line['to']
}
}
read_group['*submitter_id'] = read_group_submitter_id
read_groups[read_group_submitter_id] = read_group
for read_group in read_groups:
read_groups_emitter.write(read_groups[read_group])
read_groups_emitter.close()
if __name__ == "__main__":
parser = default_argument_parser(
output_dir=DEFAULT_OUTPUT_DIR,
description=
'Reads bmeg callset json and writes gen3 read_group json ({}).'.format(
DEFAULT_OUTPUT_DIR))
args = parser.parse_args()
transform(output_dir=args.output_dir)
for line in reader('source/ccle/File.Vertex.json.gz'):
ssm_submitter_id = line['gid']
read_group_submitter_id = read_groups[ssm_submitter_id]
ssm = {
'type': 'submitted_somatic_mutation',
'*read_groups': {
'submitter_id': read_group_submitter_id
}
}
ssm['*submitter_id'] = ssm_submitter_id
ssm['md5sum'] = line['data']['md5']
ssm['file_size'] = line['data']['size']
ssm['file_name'] = line['data']['path']
ssm['experimental_strategy'] = 'etl'
ssm['data_type'] = 'maf like'
ssm['data_format'] = 'tsv'
ssm['data_category'] = 'omics'
ssm_emitter.write(ssm)
ssm_emitter.close()
if __name__ == "__main__":
parser = default_argument_parser(
output_dir=DEFAULT_OUTPUT_DIR,
description='Reads bmeg Files json and writes gen3 submitted_somatic_mutation json ({}).'.format(DEFAULT_OUTPUT_DIR)
)
args = parser.parse_args()
transform(output_dir=args.output_dir)
types=types,
batch_size=batch_size)
try:
if drop_project:
print(submission_client.delete_project(program, project),
file=sys.stderr)
except Exception as e:
print(e)
# try:
# print(submission_client.delete_program(program), file=sys.stderr)
# except Exception as e:
# print(e)
if __name__ == "__main__":
parser = default_argument_parser(
description='deletes all content for project')
parser.add_argument(
'--program',
type=str,
default=DEFAULT_PROGRAM,
help='Name of existing gen3 program ({}).'.format(DEFAULT_PROGRAM))
parser.add_argument(
'--project',
type=str,
default=DEFAULT_PROJECT,
help='Name of existing gen3 project ({}).'.format(DEFAULT_PROJECT))
parser.add_argument(
'--credentials_path',
type=str,
default=DEFAULT_CREDENTIALS_PATH,
help='Location of gen3 path ({}).'.format(DEFAULT_CREDENTIALS_PATH))
