def add_arguments(self, parser):
parser.add_argument(dest='inputs', nargs='+', help="Input sequence file path (FASTA, GenBank, Pfam CSV).")
parser.add_argument('-o', '--output', required=False, help="Custom output directory path.")
parser.add_argument('--limit-to-record', action='append', help="Process only specific record ID. Can be provided multiple times.")
parser.add_argument('--minimal-output', dest='is_minimal_output', action='store_true', default=False,
help="Produce minimal output with just the GenBank sequence file.")
group = parser.add_argument_group('BGC detection options', '')
no_models_message = 'run "deepbgc download" to download models'
detector_names = util.get_available_models('detector')
group.add_argument('-d', '--detector', dest='detectors', action='append', default=[],
help="Trained detection model name ({}). "
"Can be provided multiple times (-d first -d second).".format(', '.join(detector_names) or no_models_message))
group.add_argument('--no-detector', action='store_true', help="Disable BGC detection.")
group.add_argument('-l', '--label', dest='labels', action='append', default=[], help="Label for detected clusters (equal to --detector by default). "
"If multiple detectors are provided, a label should be provided for each one.")
group.add_argument('-s', '--score', default=0.5, type=float,
help="Average protein-wise DeepBGC score threshold for extracting BGC regions from Pfam sequences.")
group.add_argument('--merge-max-protein-gap', default=0, type=int, help="Merge detected BGCs within given number of proteins.")
group.add_argument('--merge-max-nucl-gap', default=0, type=int, help="Merge detected BGCs within given number of nucleotides.")
group.add_argument('--min-nucl', default=1, type=int, help="Minimum BGC nucleotide length.")
group.add_argument('--min-proteins', default=1, type=int, help="Minimum number of proteins in a BGC.")
group.add_argument('--min-domains', default=1, type=int, help="Minimum number of protein domains in a BGC.")
group.add_argument('--min-bio-domains', default=0, type=int, help="Minimum number of known biosynthetic protein domains in a BGC (from antiSMASH ClusterFinder).")
group = parser.add_argument_group('BGC classification options', '')
classifier_names = util.get_available_models('classifier')
group.add_argument('-c', '--classifier', dest='classifiers', action='append', default=[],
help="Trained classification model name ({}). "
"Can be provided multiple times (-c first -c second).".format(', '.join(classifier_names) or no_models_message))
group.add_argument('--no-classifier', action='store_true', help="Disable BGC classification.")
group.add_argument('--classifier-score', default=0.5, type=float,
help="DeepBGC classification score threshold for assigning classes to BGCs (inclusive).")
def run(self):
ok = True
custom_dir = os.environ.get(util.DEEPBGC_DOWNLOADS_DIR)
if custom_dir:
logging.info('Using custom downloads dir: %s', custom_dir)
data_dir = util.get_downloads_dir(versioned=False)
if not os.path.exists(data_dir):
logging.warning('Data downloads directory does not exist yet: %s',
data_dir)
logging.warning(
'Run "deepbgc download" to download all dependencies or set %s env var',
util.DEEPBGC_DOWNLOADS_DIR)
ok = False
else:
logging.info('Available data files: %s', os.listdir(data_dir))
versioned_dir = util.get_downloads_dir(versioned=True)
if not os.path.exists(versioned_dir):
logging.info(
'Downloads directory for current version does not exist yet: %s',
versioned_dir)
logging.info('Run "deepbgc download" to download current models')
return
detectors = util.get_available_models('detector')
logging.info('=' * 80)
logging.info('Available detectors: %s', detectors)
if not detectors:
logging.warning(
'Run "deepbgc download" to download current detector models')
ok = False
for name in detectors:
model_path = util.get_model_path(name, 'detector')
ok = self.print_model(name, model_path) and ok
classifiers = util.get_available_models('classifier')
logging.info('=' * 80)
logging.info('Available classifiers: %s', classifiers)
for name in classifiers:
model_path = util.get_model_path(name, 'classifier')
ok = self.print_model(name, model_path) and ok
if not classifiers:
logging.warning(
'Run "deepbgc download" to download current classifier models')
ok = False
logging.info('=' * 80)
if ok:
logging.info('All OK')
else:
logging.warning('Some warnings detected, check the output above')