def testNbSeq(self):
nb_seq = FastaIO.nbSeq(self.tmp_mono_line)
self.assertEqual(4, nb_seq)
nb_seq = FastaIO.nbSeq(self.tmp_multi_line)
self.assertEqual(4, nb_seq)
nb_seq = FastaIO.nbSeq(self.tmp_multi_line_gz)
self.assertEqual(4, nb_seq)
args = parser.parse_args()
# Logger initialisation
logging.basicConfig(
level=logging.DEBUG,
format=
'%(asctime)s -- [%(filename)s][pid:%(process)d][%(levelname)s] -- %(message)s'
)
log = logging.getLogger(os.path.basename(__file__))
log.info(" ".join(sys.argv))
log.info("Random seed used: {}".format(args.random_seed))
# Get number of duplications by reads
log.info("Get duplication count for each read")
random.seed(args.random_seed)
nb_reads = FastaIO.nbSeq(args.input_R1)
if nb_reads < 10000:
log.error(
"The number of reads in {} is unsufficient to simulate duplication (found: {} ; expected: {})."
.format(args.input_R1, nb_reads, 10000))
nb_occurences = getNbOccur(args.duplication_profile, nb_reads)
# Witre reads
log.info("Write reads")
with FastaIO(args.output_R1, "w") as FH_out_R1:
with FastaIO(args.output_R2, "w") as FH_out_R2:
with FastaIO(args.input_R1) as FH_in_R1:
with FastaIO(args.input_R2) as FH_in_R2:
for curr_nb_occur, R1, R2 in zip(nb_occurences, FH_in_R1,
FH_in_R2):
description = "dupCount={}".format(curr_nb_occur)