def generate_donor_organism_json(data, output_dir, donor_number, bundle_uuid):
file_name = f'donor_organism_{donor_number}.json'
donor_organism_json = create_donor_organism_json(data=data,
file_uuid=generate_file_uuid(bundle_uuid, file_name),
i=donor_number)
with open(f'{output_dir}/{file_name}', 'w') as f:
f.write(json.dumps(donor_organism_json, indent=4))
print(f'"{output_dir}/{file_name}" successfully written.')
def generate_cell_suspension_json(wb, output_dir, cell_count, bundle_uuid):
file_name = 'cell_suspension_0.json'
cell_suspension_data = parse_cell_suspension_data_from_xlsx(wb)
cell_json = create_cell_suspension_jsons(data=cell_suspension_data,
cell_count=cell_count,
file_uuid=generate_file_uuid(bundle_uuid, file_name))
with open(f'{output_dir}/{file_name}', 'w') as f:
f.write(json.dumps(cell_json, indent=4))
print(f'"{output_dir}/{file_name}" successfully written.')
def generate_library_preparation_protocol_json(wb, output_dir, bundle_uuid):
file_name = 'library_preparation_protocol_0.json'
library_preparation_protocol_data = parse_library_preparation_protocol_data_from_xlsx(wb)
library_preparation_protocol_json = create_library_preparation_protocol_json(
data=library_preparation_protocol_data,
file_uuid=generate_file_uuid(bundle_uuid, file_name)
)
with open(f'{output_dir}/{file_name}', 'w') as f:
f.write(json.dumps(library_preparation_protocol_json, indent=4))
print(f'"{output_dir}/{file_name}" successfully written.')
def generate_sequencing_protocol_json(wb, output_dir, bundle_uuid):
sequencing_protocol_data = parse_sequencing_protocol_data_from_xlsx(wb)
lengths = set(map(len, sequencing_protocol_data.values()))
for i in range(one(lengths)):
file_name = f'sequencing_protocol_{i}.json'
sequencing_protocol_json = create_sequencing_protocol_json(
data=sequencing_protocol_data,
file_uuid=generate_file_uuid(bundle_uuid, file_name),
i=i
)
with open(f'{output_dir}/{file_name}', 'w') as f:
json.dump(sequencing_protocol_json, f, indent=4)
print(f'"{output_dir}/{file_name}" successfully written.')
def file_uuid_callback(file_path: str):
file_path = Path(file_path)
file_name = file_path.name
file_uuid = generate_file_uuid(bundle_uuid, file_name)
log.info('Allocated UUID %s for file %s', file_uuid, file_path)
if file_name.endswith('.json'):
with file_path.open('rt') as f:
document = json.load(f)
if file_name == 'links.json':
pass
elif file_name == 'project_0.json':
assert document['provenance'][
'document_id'] == bundle_uuid
else:
assert document['provenance'][
'document_id'] == file_uuid
return file_uuid
def generate_analysis_json(bundle_uuid, output_dir):
file_name = 'analysis_file_0.json'
version = timestamp()
analysis_json = {
"describedBy": "https://schema.humancellatlas.org/type/file/6.0.0/analysis_file",
"file_core": {
"file_name": "matrix.mtx.zip",
"format": "mtx"
},
"schema_type": "file",
"provenance": {
"document_id": generate_file_uuid(bundle_uuid, file_name),
"submission_date": version, # TODO: Fetch from DSS if it exists
"update_date": version
}
}
with open(f'{output_dir}/{file_name}', 'w') as f:
f.write(json.dumps(analysis_json, indent=4))
print(f'"{output_dir}/{file_name}" successfully written.')
def generate_analysis_protocol_json(output_dir, bundle_uuid):
# TODO: Hard-coded and not sure where this data should come from... ???
file_name = 'analysis_protocol_0.json'
version = timestamp()
analysis_protocol_json = {
"computational_method": "SmartSeq2SingleCell",
"describedBy": "https://schema.humancellatlas.org/type/protocol/analysis/9.0.0/analysis_protocol",
"protocol_core": {
"protocol_id": "smartseq2_v2.3.0"
},
"schema_type": "protocol",
"type": {
"text": "analysis"
},
"provenance": {
"document_id": generate_file_uuid(bundle_uuid, file_name),
"submission_date": version, # TODO: Fetch from DSS if it exists
"update_date": version
}
}
with open(f'{output_dir}/{file_name}', 'w') as f:
f.write(json.dumps(analysis_protocol_json, indent=4))
print(f'"{output_dir}/{file_name}" successfully written.')