def main():
args = get_parser().parse_args()
# add required attributes for loading guppy, but not valid options for
# this script.
args.do_not_use_guppy_server = False
args.output_directory = args.guppy_logs_output_directory
try:
mh.mkdir(args.output_directory, False)
except mh.MegaError:
sys.stderr.write(
'***** WARNING ***** Guppy logs output directory exists. ' +
'Potentially overwriting guppy logs.\n')
sys.stderr.write('Loading model.\n')
backend_params = backends.parse_backend_params(args)
with backends.ModelInfo(backend_params, args.processes) as model_info:
sys.stderr.write('Loading reference.\n')
aligner = mapping.alignerPlus(str(args.reference),
preset=str('map-ont'),
best_n=1)
process_all_reads(args.fast5s_dir, args.num_reads,
args.read_ids_filename, model_info, aligner,
args.processes, args.output, args.suppress_progress,
args.compute_false_reference_scores)
def aligner_validation(args):
logger = logging.get_logger()
if len(mh.ALIGN_OUTPUTS.intersection(args.outputs)) > 0:
if args.reference is None:
logger.error(
('Output(s) requiring reference alignment requested ({}), ' +
'but --reference not provided.').format(', '.join(
mh.ALIGN_OUTPUTS.intersection(args.outputs))))
sys.exit(1)
logger.info('Loading reference.')
if not (os.path.exists(args.reference)
and os.path.isfile(args.reference)):
logger.error('Provided reference file does not exist or is ' +
'not a file.')
sys.exit(1)
aligner = mapping.alignerPlus(str(args.reference),
preset=str('map-ont'),
best_n=1)
setattr(aligner, 'out_fmt', args.mappings_format)
setattr(aligner, 'ref_fn', mh.resolve_path(args.reference))
aligner.add_ref_lens()
mapping.test_open_alignment_out_file(args.output_directory,
aligner.out_fmt,
aligner.ref_names_and_lens,
aligner.ref_fn)
else:
aligner = None
if args.reference is not None:
logger.warning(
'[--reference] provided, but no [--outputs] requiring ' +
'alignment was requested. Argument will be ignored.')
return aligner
def _main(args):
logging.init_logger()
# add required attributes for loading guppy, but not valid options for
# this script.
args.do_not_use_guppy_server = False
args.output_directory = args.guppy_logs_output_directory
try:
mh.mkdir(args.output_directory, False)
except mh.MegaError:
LOGGER.warning(
'Guppy logs output directory exists. Potentially overwriting ' +
'guppy logs.')
LOGGER.info('Loading model.')
backend_params = backends.parse_backend_params(args)
with backends.ModelInfo(backend_params, args.processes) as model_info:
LOGGER.info('Loading reference.')
aligner = mapping.alignerPlus(str(args.reference),
preset=str('map-ont'),
best_n=1)
process_all_reads(args.fast5s_dir, not args.not_recursive,
args.num_reads, args.read_ids_filename, model_info,
aligner, args.processes, args.output,
args.suppress_progress,
args.compute_false_reference_scores)
def _main(args):
logging.init_logger()
LOGGER.info('Loading reference')
aligner = mapping.alignerPlus(str(args.reference),
preset=str('map-ont'),
best_n=1)
aligner.add_ref_lens()
LOGGER.info('Loading variants')
var_data = variants.VarData(args.in_vcf,
args.max_indel_size,
keep_var_fp_open=True,
aligner=aligner)
contigs = var_data.variants_idx.header.contigs.values()
LOGGER.info('Atomizing variants')
with open(args.out_vcf, 'w') as out_vars:
out_vars.write('\n'.join(HEADER + [
CONTIG_HEADER_LINE.format(ctg.name, ctg.length) for ctg in contigs
] + [
variants.CONTEXT_BASE_MI_LINE,
COMMAND_HEADER_LINE.format(' '.join(sys.argv)), FIELDS_LINE
]) + '\n')
for ctg in contigs:
chrm_seq = aligner.seq(ctg.name)
if len(chrm_seq) != ctg.length:
LOGGER.warning(('Mismatched contig lengths ({}) between ' +
'reference ({}) and input VCF ({})').format(
ctg.name, len(chrm_seq), ctg.length))
map_pos = mapping.MAP_POS(chrm=ctg.name,
strand=None,
start=0,
end=len(chrm_seq),
q_trim_start=None,
q_trim_end=None)
for var in var_data.fetch_read_variants(map_pos,
mh.seq_to_int(chrm_seq)):
out_vars.write(
RECORD_LINE.format(chrm=ctg.name,
pos=var.ref_start + 1,
rid=var.id,
ref=var.ref,
alts=','.join(var.alts),
info=variants.HAS_CONTEXT_BASE_TAG
if var.has_context_base else '.'))
LOGGER.info('Indexing output variant file')
variants.index_variants(args.out_vcf)
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 main():
args = get_parser().parse_args()
sys.stderr.write('Loading model.\n')
model_info = backends.ModelInfo(args.taiyaki_model_filename, args.devices,
args.processes, args.chunk_size,
args.chunk_overlap,
args.max_concurrent_chunks)
sys.stderr.write('Loading reference.\n')
aligner = mapping.alignerPlus(str(args.reference),
preset=str('map-ont'),
best_n=1)
process_all_reads(args.fast5s_dir, args.num_reads, args.read_ids_filename,
model_info, aligner, args.processes, args.output,
args.suppress_progress,
args.compute_false_reference_scores)
return