def main():
args = get_parser().parse_args()
worker_kwarg_names = ['back_prob', 'localpen', 'minscore', 'trim']
model = helpers.load_model(args.model)
fast5_reads = fast5utils.iterate_fast5_reads(
args.read_dir, limit=args.limit, strand_list=args.input_strand_list,
recursive=args.recursive)
with helpers.open_file_or_stdout(args.output) as fh:
for res in imap_mp(
squiggle_match.worker, fast5_reads, threads=args.jobs,
fix_kwargs=helpers.get_kwargs(args, worker_kwarg_names),
unordered=True, init=squiggle_match.init_worker,
initargs=[model, args.references]):
if res is None:
continue
read_id, sig, score, path, squiggle, bases = res
bases = bases.decode('ascii')
fh.write('#{} {}\n'.format(read_id, score))
for i, (s, p) in enumerate(zip(sig, path)):
fh.write('{}\t{}\t{}\t{}\t{}\t{}\t{}\t{}\n'.format(
read_id, i, s, p, bases[p], squiggle[p, 0], squiggle[p, 1],
squiggle[p, 2]))
def main(argv):
"""Main function to process mapping for each read using functions in prepare_mapping_funcs"""
args = parser.parse_args()
print("Running prepare_mapping using flip-flop remapping")
if not args.overwrite:
if os.path.exists(args.output):
print("Cowardly refusing to overwrite {}".format(args.output))
sys.exit(1)
# Make an iterator that yields all the reads we're interested in.
fast5_reads = fast5utils.iterate_fast5_reads(
args.input_folder,
limit=args.limit,
strand_list=args.input_strand_list)
# Set up arguments (kwargs) for the worker function for each read
kwargs = helpers.get_kwargs(args,
['alphabet', 'collapse_alphabet', 'device'])
kwargs[
'per_read_params_dict'] = prepare_mapping_funcs.get_per_read_params_dict_from_tsv(
args.input_per_read_params)
kwargs['references'] = helpers.fasta_file_to_dict(args.references)
kwargs['model'] = helpers.load_model(args.model)
workerFunction = prepare_mapping_funcs.oneread_remap # remaps a single read using flip-flip network
results = imap_mp(workerFunction,
fast5_reads,
threads=args.jobs,
fix_kwargs=kwargs,
unordered=True)
# results is an iterable of dicts
# each dict is a set of return values from a single read
prepare_mapping_funcs.generate_output_from_results(results, args)
def main():
"""Main function to process mapping for each read using functions in prepare_mapping_funcs"""
args = parser.parse_args()
print("Running prepare_mapping using flip-flop remapping")
if not args.overwrite:
if os.path.exists(args.output):
print("Cowardly refusing to overwrite {}".format(args.output))
sys.exit(1)
# Create alphabet and check for consistency
modified_bases = [elt[0] for elt in args.mod]
canonical_bases = [elt[1] for elt in args.mod]
for b in modified_bases:
assert len(
b
) == 1, "Modified bases must be a single character, got {}".format(b)
assert b not in args.alphabet, "Modified base must not be a canonical base, got {}".format(
b)
for b in canonical_bases:
assert len(
b
) == 1, "Canonical coding for modified bases must be a single character, got {}".format(
b)
assert b in args.alphabet, "Canonical coding for modified base must be a canonical base, got {}".format(
b)
full_alphabet = args.alphabet + ''.join(modified_bases)
flat_alphabet = args.alphabet + ''.join(canonical_bases)
modification_names = [elt[2] for elt in args.mod]
alphabet_info = alphabet.AlphabetInfo(full_alphabet,
flat_alphabet,
modification_names,
do_reorder=True)
print("Converting references to labels using {}".format(
str(alphabet_info)))
# Make an iterator that yields all the reads we're interested in.
fast5_reads = fast5utils.iterate_fast5_reads(
args.input_folder,
limit=args.limit,
strand_list=args.input_strand_list,
recursive=args.recursive)
# Set up arguments (kwargs) for the worker function for each read
kwargs = helpers.get_kwargs(args, ['device'])
kwargs[
'per_read_params_dict'] = prepare_mapping_funcs.get_per_read_params_dict_from_tsv(
args.input_per_read_params)
kwargs['references'] = helpers.fasta_file_to_dict(args.references,
alphabet=full_alphabet)
kwargs['model'] = helpers.load_model(args.model)
kwargs['alphabet_info'] = alphabet_info
# remaps a single read using flip-flip network
workerFunction = prepare_mapping_funcs.oneread_remap
results = imap_mp(workerFunction,
fast5_reads,
threads=args.jobs,
fix_kwargs=kwargs,
unordered=True,
chunksize=50)
# results is an iterable of dicts
# each dict is a set of return values from a single read
prepare_mapping_funcs.generate_output_from_results(results, args.output,
alphabet_info)
action=FileExists,
help='Directory for fast5 reads')
if __name__ == '__main__':
args = parser.parse_args()
worker_kwarg_names = ['back_prob', 'localpen', 'minscore', 'trim']
model = helpers.load_model(args.model)
fast5_reads = fast5utils.iterate_fast5_reads(
args.read_dir, limit=args.limit, strand_list=args.input_strand_list)
for res in imap_mp(squiggle_match.worker,
fast5_reads,
threads=args.jobs,
fix_kwargs=helpers.get_kwargs(args, worker_kwarg_names),
unordered=True,
init=squiggle_match.init_worker,
initargs=[model, args.references]):
if res is None:
continue
read_id, sig, score, path, squiggle, bases = res
bases = bases.decode('ascii')
print('#{} {}'.format(read_id, score))
for i, (s, p) in enumerate(zip(sig, path)):
print('{}\t{}\t{}\t{}\t{}\t{}\t{}'.format(read_id, i, s, p,
bases[p], squiggle[p, 0],
squiggle[p, 1],
squiggle[p, 2]))