def transform(output_dir, compresslevel=0):
"""Read bmeg json and writes gen3 json."""
read_groups_emitter = JSONEmitter(os.path.join(output_dir,
'read_group.json'),
compresslevel=0)
read_groups = {}
# [ "_id", "data", "from", "gid", "label", "to" ]
# {"_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()
def transform(output_dir, compresslevel=0):
"""Read bmeg json and writes gen3 json."""
ssm_emitter = JSONEmitter(os.path.join(output_dir, 'submitted_somatic_mutation.json'), compresslevel=0)
read_groups = {}
# [ "_id", "data", "from", "gid", "label", "to" ]
for line in reader('source/ccle/DerivedFrom.Edge.json.gz'):
read_groups[line['from']] = 'read_group-{}'.format(line['to'])
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()
def emitter(type=None, output_dir=DEFAULT_OUTPUT_DIR, **kwargs):
"""Creates a default emitter for type."""
return JSONEmitter(os.path.join(output_dir, '{}.json'.format(type)), compresslevel=0, **kwargs)
def transform(output_dir, compresslevel=0):
"""Read bmeg json and writes gen3 json."""
samples_emitter = JSONEmitter(os.path.join(output_dir, 'samples.json'),
compresslevel=0)
aliquots_emitter = JSONEmitter(os.path.join(output_dir, 'aliquots.json'),
compresslevel=0)
diagnosis_emitter = JSONEmitter(os.path.join(output_dir, 'diagnosis.json'),
compresslevel=0)
samples = {}
diagnoses = {}
for p in [
'source/ccle/BiosampleFor.Edge.json.gz',
'source/ccle/maf.BiosampleFor.Edge.json.gz'
]:
for line in reader(p):
case_submitter_id = line['to']
diagnosis_submitter_id = 'diagnosis-{}'.format(case_submitter_id)
sample = {'type': 'sample', '*cases': {'submitter_id': line['to']}}
sample['*submitter_id'] = line['from']
sample['*diagnoses'] = {'submitter_id': diagnosis_submitter_id}
samples[sample['*submitter_id']] = sample
diagnosis = {
'type': 'diagnosis',
'*submitter_id': diagnosis_submitter_id,
'*cases': {
'submitter_id': case_submitter_id
}
}
diagnoses[sample['*submitter_id']] = diagnosis
for p in [
'source/ccle/maf.AliquotFor.Edge.json.gz',
'source/ccle/AliquotFor.Edge.json.gz'
]:
for line in reader(p):
line = json.loads(line)
# ['type', 'project_id', '*submitter_id', '*cases.submitter_id', 'diagnoses.submitter_id', 'biosample_anatomic_site', 'composition', 'current_weight', 'days_to_collection', 'days_to_sample_procurement', 'diagnosis_pathologically_confirmed', 'freezing_method', 'initial_weight', 'intermediate_dimension', 'is_ffpe', 'longest_dimension', 'method_of_sample_procurement', 'oct_embedded', 'preservation_method', 'sample_type', 'sample_type_id', 'sample_volume', 'shortest_dimension', 'time_between_clamping_and_freezing', 'time_between_excision_and_freezing', 'tissue_type', 'tumor_code', 'tumor_code_id', 'tumor_descriptor',]
aliquot = {
'type': 'aliquot',
'*samples': {
'submitter_id': line['to']
}
}
aliquot['*submitter_id'] = line['from']
aliquots_emitter.write(aliquot)
for p in [
'source/ccle/BioSample.Vertex.json.gz',
'source/ccle/maf.BioSample.Vertex.json.gz'
]:
for line in reader(p):
line = json.loads(line)
# ['type', 'project_id', '*submitter_id', '*cases.submitter_id', 'diagnoses.submitter_id', 'biosample_anatomic_site', 'composition', 'current_weight', 'days_to_collection', 'days_to_sample_procurement', 'diagnosis_pathologically_confirmed', 'freezing_method', 'initial_weight', 'intermediate_dimension', 'is_ffpe', 'longest_dimension', 'method_of_sample_procurement', 'oct_embedded', 'preservation_method', 'sample_type', 'sample_type_id', 'sample_volume', 'shortest_dimension', 'time_between_clamping_and_freezing', 'time_between_excision_and_freezing', 'tissue_type', 'tumor_code', 'tumor_code_id', 'tumor_descriptor',]
sample = samples[line['gid']]
samples_emitter.write(sample)
diagnosis = diagnoses[sample['*submitter_id']]
ccle_attributes = line['data']
diagnosis['*primary_diagnosis'] = ccle_attributes.get(
"Primary Disease",
ccle_attributes.get("Subtype Disease", 'unknown'))
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()