INNER CODE UNIT · Python
multi_easy_binning
BigDataBiology/SemiBin · SemiBin/main.py:1330
def multi_easy_binning(logger, args, device):
"""
contain `generate_cannot_links`, `generate_sequence_features_multi`, `train`, `bin` in one command for multi-sample binning
"""
logger.info('Performing multi-sample binning')
logger.info('Generating training data...')
sample_list = generate_sequence_features_multi(logger, args)
for sample_index, sample in enumerate(sample_list):
sample_fasta = os.path.join(
args.output, 'samples', f'{sample}.fa')
sample_data = os.path.join(args.output, 'samples', sample, 'data.csv')
sample_data_split = os.path.join(
args.output, 'samples', sample, 'data_split.csv')
c_min_len, must_link_threshold, contig_dict = load_fasta(sample_fasta, args.ratio)