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')
def __init__(self, classifier, score_threshold=0.5):
if classifier is None or not isinstance(classifier, six.string_types):
raise ValueError(
'Expected classifier name, got {}'.format(classifier))
self.classifier_name = classifier
self.score_threshold = score_threshold
classifier_path = util.get_model_path(self.classifier_name,
'classifier')
self.model = SequenceModelWrapper.load(classifier_path)
self.total_class_counts = pd.Series()
def __init__(self, classifier, score_threshold=0.5):
if classifier is None or not isinstance(classifier, six.string_types):
raise ValueError('Expected classifier name or path, got {}'.format(classifier))
if (os.path.exists(classifier) or os.path.sep in classifier) and not os.path.isdir(classifier):
classifier_path = classifier
# Set classifier name to filename without suffix
classifier, _ = os.path.splitext(os.path.basename(classifier))
else:
classifier_path = util.get_model_path(classifier, 'classifier')
self.classifier_name = classifier
self.score_threshold = score_threshold
self.model = SequenceModelWrapper.load(classifier_path)
self.total_class_counts = pd.Series()
def __init__(self, detector, label=None, score_threshold=0.5, merge_max_protein_gap=0,
merge_max_nucl_gap=0, min_nucl=1, min_proteins=1, min_domains=1, min_bio_domains=0):
self.score_threshold = score_threshold
if detector is None or not isinstance(detector, six.string_types):
raise ValueError('Expected detector name, got {}'.format(detector))
self.detector_name = detector
self.detector_label = label or self.detector_name
self.score_column = util.format_bgc_score_column(self.detector_name)
self.merge_max_protein_gap = merge_max_protein_gap
self.merge_max_nucl_gap = merge_max_nucl_gap
self.min_nucl = min_nucl
self.min_proteins = min_proteins
self.min_domains = min_domains
self.min_bio_domains = min_bio_domains
model_path = util.get_model_path(self.detector_name, 'detector')
self.model = SequenceModelWrapper.load(model_path)
self.num_detected = 0
def __init__(self, detector, label=None, score_threshold=0.5, merge_max_protein_gap=0,
merge_max_nucl_gap=0, min_nucl=1, min_proteins=1, min_domains=1, min_bio_domains=0):
self.score_threshold = score_threshold
if detector is None or not isinstance(detector, six.string_types):
raise ValueError('Expected detector name or path, got {}'.format(detector))
if (os.path.exists(detector) or os.path.sep in detector) and not os.path.isdir(detector):
model_path = detector
# Set detector name to filename without suffix
detector, _ = os.path.splitext(os.path.basename(detector))
else:
model_path = util.get_model_path(detector, 'detector')
self.detector_name = detector
self.detector_label = label or self.detector_name
self.score_column = util.format_bgc_score_column(self.detector_name)
self.merge_max_protein_gap = merge_max_protein_gap
self.merge_max_nucl_gap = merge_max_nucl_gap
self.min_nucl = min_nucl
self.min_proteins = min_proteins
self.min_domains = min_domains
self.min_bio_domains = min_bio_domains
self.model = SequenceModelWrapper.load(model_path)
self.num_detected = 0