def main():
args = read_args()
if args.debug_barcodes:
valid_barcodes = load_barcodes(args)
truth = None
if args.truth is not None:
truth, file_size = read_file(args.truth, args.size)
g = Glass(args.chunk_num,
header_size=args.header_size,
rs=args.rs,
c_dist=args.c_dist,
delta=args.delta,
flag_correct=not (args.no_correction),
gc=args.gc,
max_homopolymer=args.max_homopolymer,
max_hamming=args.max_hamming,
decode=not (args.mock),
exDNA=args.expand_nt,
chunk_size=args.size,
np=args.rand_numpy,
truth=truth,
out=args.out)
line = 0
errors = 0
seen_seeds = defaultdict(int)
#pbar = tqdm(total= args.chunk_num, desc = "Valid oligos")
if args.file_in == '-':
f = sys.stdin
else:
try:
f = open(args.file_in, 'r')
except:
logging.error("%s file not found", args.text_file)
sys.exit(0)
aggressive = None
if args.aggressive:
aggressive = Aggressive(g=g, file_in=f, times=args.aggressive)
######## Main loop
while True:
try:
dna = f.readline().rstrip('\n')
except:
logging.info("Finished reading input file!")
break
if len(dna) == 0:
logging.info("Finished reading input file!")
break
if (args.fasta and re.search(r"^>", dna)):
continue
coverage = 0
#when the file is in the format of coverage \t DNA
if (len(dna.split()) == 2):
coverage, dna = dna.split()
####Aggresive mode
if aggressive is not None and aggressive.turn_on(
int(coverage), seen_seeds):
best_file, value = aggressive.start()
if best_file is not None:
copyfile(best_file, args.out)
logging.info("Done!")
else:
logging.error("Could not decode all file...")
sys.exit(1)
### End of aggressive mode
if 'N' in dna:
continue
line += 1
seed, data = g.add_dna(dna)
if seed == -1: #reed-solomon error!
errors += 1
else:
#pbar.update()
if args.debug_barcodes:
if not dna in valid_barcodes:
logging.error(
"Seed or data %d in line %d are not valid:%s", seed,
line, dna)
else:
seen_seeds[dna] += 1
else:
seen_seeds[seed] += 1
if line % 1000 == 0:
logging.info(
"After reading %d lines, %d chunks are done. So far: %d rejections (%f) %d barcodes",
line, g.chunksDone(), errors, errors / (line + 0.0),
g.len_seen_seed())
pass
if line == args.max_line:
logging.info("Finished reading maximal number of lines")
break
if g.isDone():
logging.info(
"After reading %d lines, %d chunks are done. So far: %d rejections (%f) %d barcodes",
line, g.chunksDone(), errors, errors / (line + 0.0),
g.len_seen_seed())
logging.info("Done!")
break
if not g.isDone():
logging.error("Could not decode all file...")
sys.exit(1)
outstring = g.getString()
f = open(args.out, 'wb')
f.write(outstring)
f.close()
logging.info("MD5 is %s", md5.new(outstring).hexdigest())
json.dump(seen_seeds,
open("seen_barocdes.json", 'w'),
sort_keys=True,
indent=4)
def main():
args = read_args()
if args.debug_barcodes:
valid_barcodes = load_barcodes(args)
comp = None
if args.composite_DNA is not None:
# alphabet is a dict of int->letter including the std 0->A,1->C,2->G,3->T
# the composite alphabet file only contains an ordered list of the *additional* letters
alphabet = read_composite_alphabet(args.composite_DNA[0])
BC_bases = int(args.composite_DNA[1])
# TODO - set max binary block limit somehow, get oligo length from somewhere
if args.composite_encoder is not None:
composite_encoder = create_composite_encoder(
alphabet, int(args.composite_encoder[0]),
int(args.composite_encoder[1]))
else:
composite_encoder = create_optimal_composite_encoder(
alphabet, 10, 136)
comp = {
'alphabet': alphabet,
'BC_bases': BC_bases,
'encoder': composite_encoder
}
truth = None
if args.truth is not None:
truth, file_size = read_file(args.truth, args.size)
g = Glass(args.chunk_num,
header_size=args.header_size,
rs=args.rs,
c_dist=args.c_dist,
delta=args.delta,
flag_correct=not (args.no_correction),
gc=args.gc,
max_homopolymer=args.max_homopolymer,
max_hamming=args.max_hamming,
decode=not (args.mock),
chunk_size=args.size,
np=args.rand_numpy,
truth=truth,
out=args.out,
comp=comp)
line = 0
errors = 0
seen_seeds = defaultdict(int)
# pbar = tqdm(total= args.chunk_num, desc = "Valid oligos")
if args.file_in == '-':
f = sys.stdin
else:
try:
f = open(args.file_in, 'r')
except:
logging.error("%s file not found", args.text_file)
sys.exit(0)
aggressive = None
if args.aggressive:
aggressive = Aggressive(g=g, file_in=f, times=args.aggressive)
######## Main loop
while True:
try:
dna = f.readline().rstrip('\n')
except:
logging.info("Finished reading input file!")
break
if len(dna) == 0:
logging.info("Finished reading input file!")
break
if (args.fasta and re.search(r"^>", dna)):
continue
coverage = 0
# when the file is in the format of coverage \t DNA
if (len(dna.split()) == 2):
coverage, dna = dna.split()
####Aggresive mode
if aggressive is not None and aggressive.turn_on(
int(coverage), seen_seeds):
best_file, value = aggressive.start()
if best_file is not None:
copyfile(best_file, args.out)
logging.info("Done!")
else:
logging.error("Could not decode all file...")
sys.exit(1)
### End of aggressive mode
if 'N' in dna and comp is None:
continue
line += 1
seed, data = g.add_dna(dna)
if seed == -1: # reed-solomon error!
errors += 1
else:
# pbar.update()
if args.debug_barcodes:
if not dna in valid_barcodes:
logging.error(
"Seed or data %d in line %d are not valid:%s", seed,
line, dna)
else:
seen_seeds[dna] += 1
else:
seen_seeds[seed] += 1
if line % 10000 == 0:
logging.info(
"After reading %d lines, %d chunks are done. So far: %d rejections (%f) %d barcodes",
line, g.chunksDone(), errors, errors / (line + 0.0),
g.len_seen_seed())
pass
if line == args.max_line:
logging.info("Finished reading maximal number of lines")
break
if g.isDone():
logging.info(
"After reading %d lines, %d chunks are done. So far: %d rejections (%f) %d barcodes",
line, g.chunksDone(), errors, errors / (line + 0.0),
g.len_seen_seed())
logging.info("Done!")
break
if not g.isDone():
logging.error("Could not decode all file...")
sys.exit(1)
outstring = g.getString()
f = open(args.out, 'wb')
f.write(outstring)
f.close()
logging.info("MD5 is %s", md5.new(outstring).hexdigest())
json.dump(seen_seeds,
open("seen_barocdes.json", 'w'),
sort_keys=True,
indent=4)
