INNER CODE UNIT · Python
generate_sequence_features_multi
BigDataBiology/SemiBin · SemiBin/main.py:894
def generate_sequence_features_multi(logger, args):
"""
Generate data.csv and data_split.csv for every sample of multi-sample binning mode.
data.csv has the features(kmer and abundance) for original contigs.
data_split.csv has the features(kmer and abundace) for contigs that are breaked up as must-link pair.
"""
import pandas as pd
if not args.bams and not args.abundances:
logger.error(
"You need to specify input BAM files or abundance files.")
sys.exit(1)
n_sample = len(args.bams) if args.bams else len(args.abundances)
if args.abundances and n_sample < 5:
logger.error(
"Abundances from strobealign-aemb can only be used when at least 5 samples are used.")
sys.exit(1)