def main():
args = parse_args()
init_log(args.log)
with open(args.app) as app_file:
# parse and validate the requested data application JSON file
application = Application(app_file)
logging.info("Input data application parsed: {}".format(args.app))
# Create output directory for the results
application_dir = create_app_dir(application)
# check what data types are allowed for this application
allowed_data_types = application.allowed_data_types()
logging.info("Allowed data types: {}".format(
' '.join(allowed_data_types)))
if len(allowed_data_types) > 0:
# Get all the sample metadata for all requested cohorts
requested_cohorts = application.cohorts()
metadata = Metadata(args.data, requested_cohorts)
logging.info("Metadata collected for requested cohorts: {}".format(
' '.join(requested_cohorts)))
metadata_sample_ids = sorted(metadata.get_sample_ids())
logging.info("Metadata for sample IDs: {}".format(
' '.join(metadata_sample_ids)))
# Filter the sample metadata based on patient consent
metadata.filter_consent(args.consent, allowed_data_types)
logging.warning("Consent not handled yet. FIXME")
# Find all the file paths for requested file types for each
# consented sample
requested_file_types = application.file_types()
logging.info("Requested file types: {}".format(
' '.join(requested_file_types)))
fastqs, bams, bais, vcfs = get_files(args.data,
requested_file_types,
metadata)
logging.info("VCF files selected:\n{}".format('\n'.join(vcfs)))
logging.info("BAM files selected:\n{}".format('\n'.join(bams)))
logging.info("BAI files selected:\n{}".format('\n'.join(bais)))
logging.info("FASTQ files selected:\n{}".format('\n'.join(fastqs)))
output_files = []
if 'Anonymised' in allowed_data_types:
# generate random IDs for all output samples
randomised_ids = make_random_ids(args.usedids,
metadata.sample_ids)
metadata.anonymise(randomised_ids)
metadata.write(args.metaout)
logging.info("Anonymised metadata written to: {}".format(
args.metaout))
new_vcfs = anonymise_files(vcfs, randomised_ids,
application_dir, VCF_filename,
vcf_edit)
new_bams = anonymise_files(bams, randomised_ids,
application_dir, BAM_filename,
bam_edit)
# BAIs and FASTQs are just sym-linked to output with randomised name
new_bais = anonymise_files(bais, randomised_ids,
application_dir, BAI_filename)
new_fastqs = anonymise_files(fastqs, randomised_ids,
application_dir, FASTQ_filename)
output_files.extend(new_vcfs + new_bams + new_bais +
new_fastqs)
logging.info("Output files are anonymised")
elif 'Re-identifiable' in allowed_data_types:
new_links = link_files(application_dir,
vcfs + bams + bais + fastqs)
output_files.extend(new_links)
logging.info(
"Files linked in directory: {}".format(application_dir))
metadata.write(args.metaout)
logging.info("Output files are re-identifiable")
else:
print_error(
"Allowed data is neither anonymised nor re-identifiable")
exit(ERROR_BAD_ALLOWED_DATA)
logging.info("Generating MD5 checksums on output files")
md5_files(args.md5, output_files)
else:
logging.warning("No data available for this application")
