def _main(args):
log_suffix = ('aggregation' if args.output_suffix is None else
'aggregation.' + args.output_suffix)
logging.init_logger(args.megalodon_directory, out_suffix=log_suffix)
LOGGER.debug('Command: """' + ' '.join(sys.argv) + '"""')
if args.mod_aggregate_method == mh.MOD_EM_NAME:
mod_agg_info = mods.AGG_INFO(mh.MOD_EM_NAME, None)
elif args.mod_aggregate_method == mh.MOD_BIN_THRESH_NAME:
mod_agg_info = mods.AGG_INFO(
mh.MOD_BIN_THRESH_NAME, args.mod_binary_threshold)
valid_read_ids = mh.parse_read_ids(args.read_ids_filename)
aggregate.aggregate_stats(
args.outputs, args.megalodon_directory, args.processes,
args.write_vcf_log_probs, args.heterozygous_factors,
variants.HAPLIOD_MODE if args.haploid else variants.DIPLOID_MODE,
mod_agg_info, args.write_mod_log_probs, args.mod_output_formats,
args.suppress_progress, valid_read_ids, args.output_suffix,
args.aggregate_batch_size)
if mh.VAR_NAME in args.outputs:
LOGGER.info('Sorting output variant file')
variant_fn = mh.add_fn_suffix(
mh.get_megalodon_fn(args.megalodon_directory, mh.VAR_NAME),
args.output_suffix)
sort_variant_fn = mh.add_fn_suffix(variant_fn, 'sorted')
variants.sort_variants(variant_fn, sort_variant_fn)
LOGGER.info('Indexing output variant file')
variants.index_variants(sort_variant_fn)
def main():
args = get_parser().parse_args()
log_suffix = ('aggregation' if args.output_suffix is None else
'aggregation.' + args.output_suffix)
logging.init_logger(args.output_directory, out_suffix=log_suffix)
logger = logging.get_logger()
mod_agg_info = mods.AGG_INFO(mods.BIN_THRESH_NAME,
args.mod_binary_threshold)
mod_names = []
if mh.MOD_NAME in args.outputs:
logger.info('Loading model.')
mod_names = backends.ModelInfo(
mh.get_model_fn(args.taiyaki_model_filename)).mod_long_names
if args.reference is not None: logger.info('Loading reference.')
aligner = mapping.alignerPlus(str(args.reference),
preset=str('map-ont'),
best_n=1)
if args.reference is not None:
aligner.add_ref_lens()
valid_read_ids = None
if args.read_ids_filename is not None:
with open(args.read_ids_filename) as read_ids_fp:
valid_read_ids = set(line.strip() for line in read_ids_fp)
aggregate.aggregate_stats(
args.outputs, args.output_directory, args.processes,
args.write_vcf_log_probs, args.heterozygous_factors,
snps.HAPLIOD_MODE if args.haploid else snps.DIPLOID_MODE, mod_names,
mod_agg_info, args.write_mod_log_probs, args.mod_output_formats,
args.suppress_progress, aligner.ref_names_and_lens, valid_read_ids,
args.output_suffix)
# note reference is required in order to annotate contigs for VCF writing
if mh.SNP_NAME in args.outputs and args.reference is not None:
logger.info('Sorting output variant file')
variant_fn = mh.add_fn_suffix(
mh.get_megalodon_fn(args.output_directory, mh.SNP_NAME),
args.output_suffix)
sort_variant_fn = mh.add_fn_suffix(variant_fn, 'sorted')
snps.sort_variants(variant_fn, sort_variant_fn)
logger.info('Indexing output variant file')
index_var_fn = snps.index_variants(sort_variant_fn)
return
def index_variants(variant_fn):
try:
return pysam.tabix_index(variant_fn,
force=True,
preset='vcf',
keep_original=True)
except OSError:
# file likely not sorted
sort_variant_fn = mh.add_fn_suffix(variant_fn, 'sorted')
sort_variants(variant_fn, sort_variant_fn)
return pysam.tabix_index(sort_variant_fn,
force=True,
preset='vcf',
keep_original=True)
def _main():
args = get_parser().parse_args()
mkdir(args.output_directory, args.overwrite)
logging.init_logger(args.output_directory)
logger = logging.get_logger()
logger.debug('Command: """' + ' '.join(sys.argv) + '"""')
if _DO_PROFILE:
args = profile_validation(args)
args, pr_ref_filts = parse_pr_ref_output(args)
tai_model_fn = mh.get_model_fn(args.taiyaki_model_filename)
model_info = backends.ModelInfo(tai_model_fn, args.devices, args.processes,
args.chunk_size, args.chunk_overlap,
args.max_concurrent_chunks)
args, mods_info = mods_validation(args, model_info)
aligner = aligner_validation(args)
args, snps_data = snps_validation(args, model_info.is_cat_mod,
model_info.output_size, aligner)
process_all_reads(args.fast5s_dir, not args.not_recursive, args.num_reads,
args.read_ids_filename, model_info, args.outputs,
args.output_directory, args.basecalls_format, aligner,
snps_data, args.processes, args.verbose_read_progress,
args.suppress_progress, mods_info, args.database_safety,
args.edge_buffer, pr_ref_filts)
if mh.MAP_NAME in args.outputs:
logger.info('Spawning process to sort mappings')
map_p = post_process_mapping(args.output_directory, aligner.out_fmt,
aligner.ref_fn)
if mh.WHATSHAP_MAP_NAME in args.outputs:
logger.info('Spawning process to sort whatshap mappings')
whatshap_sort_fn, whatshap_p = post_process_whatshap(
args.output_directory, aligner.out_fmt, aligner.ref_fn)
if mh.SNP_NAME in args.outputs or mh.MOD_NAME in args.outputs:
post_process_aggregate(
mods_info, args.outputs, args.mod_binary_threshold,
args.output_directory, args.processes, args.write_vcf_log_probs,
args.heterozygous_factors, snps_data, args.write_mod_log_probs,
args.suppress_progress, aligner.ref_names_and_lens)
if mh.SNP_NAME in args.outputs:
logger.info('Sorting output variant file')
variant_fn = mh.get_megalodon_fn(args.output_directory, mh.SNP_NAME)
sort_variant_fn = mh.add_fn_suffix(variant_fn, 'sorted')
snps.sort_variants(variant_fn, sort_variant_fn)
logger.info('Indexing output variant file')
index_variant_fn = snps.index_variants(sort_variant_fn)
if mh.WHATSHAP_MAP_NAME in args.outputs:
if whatshap_p.is_alive():
logger.info('Waiting for whatshap mappings sort')
while whatshap_p.is_alive():
sleep(0.1)
logger.info(
snps.get_whatshap_command(index_variant_fn, whatshap_sort_fn,
mh.add_fn_suffix(variant_fn, 'phased')))
if mh.MAP_NAME in args.outputs:
if map_p.is_alive():
logger.info('Waiting for mappings sort')
while map_p.is_alive():
sleep(0.1)
return