def _dnapi_prediction(fn, out_dir):
end_file = _prepare_file(fn, out_dir)
iterative_result = iterative_adapter_prediction(end_file, [1.2, 1.3, 1.4, 1.7, 2], [7, 11], 500000)
max_score = iterative_result[1][1]
adapters = list()
for a in iterative_result:
if a[1] > max_score * 0.40:
logger.debug("Adding adapter to the list: %s with score %s" % (a[0], a[1]))
adapters.append(a[0])
return adapters
def _dnapi_prediction(fn, out_dir):
end_file = _prepare_file(fn, out_dir)
iterative_result = iterative_adapter_prediction(end_file, [1.2, 1.3, 1.4, 1.7, 2], [7, 11], 500000)
max_score = iterative_result[1][1]
adapters = list()
for a in iterative_result:
if a[1] > max_score * 0.40:
logger.debug("Adding adapter to the list: %s with score %s" % (a[0], a[1]))
adapters.append(a[0])
return adapters
def _dnapi_prediction(fn):
iterative_result = iterative_adapter_prediction(fn, [1.2, 1.3, 1.4],
[9, 11], 50000)
return [a[0] for a in iterative_result]
def _dnapi_prediction(fn):
iterative_result = iterative_adapter_prediction(fn, [1.2, 1.3, 1.4], [9, 11], 50000)
return [a[0] for a in iterative_result]
def main():
args = parse_args()
fastq = args.FASTQ
Ks = convert_interval(args.k, "-k", int)
Rs = convert_interval(args.r, "-r", float)
if not MAP_TO_GENOME:
if len(Ks) > 1 or len(Rs) > 1:
adapts = iterative_adapter_prediction(fastq, Rs, Ks, SAMPLE_NUM)
else:
adapts = adapter_prediction(fastq, Rs[0], Ks[0], SAMPLE_NUM)
if args.show_all:
for x in adapts:
print("{}\tscore={:.2f}".format(*x))
else:
print(adapts[0][0])
else:
global TEMP_DIR
TEMP_DIR = "{}/DNApi_tmp_{}".format(args.temp_dir, str(uuid.uuid4()))
subprocess.call(("mkdir {}".format(TEMP_DIR)).split())
original_fastq = fastq
fastq, total_read, sd = fastq_input_prep(fastq, args.subsample_rate,
TEMP_DIR)
if args.seq:
adapts = set(args.seq)
setstr = ["user-input" for i in range(len(adapts))]
else:
msg = "warning: predicted adapter is too short (<{0}): '{1}'\n" \
+ "warning: '{1}' will not be further investigated\n"
params = {}
for k in Ks:
for r in Rs:
aout = adapter_prediction(fastq, r, k, SAMPLE_NUM)[0][0]
if len(aout) < args.prefix_match:
sys.stderr.write(msg.format(l, s))
continue
aseq = aout[:args.prefix_match + 5]
params.setdefault(aseq,
[]).append("{}:{:.1f}".format(k, r))
adapts = list(params.keys())
setstr = [';'.join(s) for s in params.values()]
adapts.append("RAW_INPUT")
setstr.append("NO_TREATMENT")
if not adapts:
raise Exception("no valid adapters to further process")
table = []
for i, aseq in enumerate(adapts):
cnts = map_clean_reads(fastq, aseq[:args.prefix_match],
args.trim_5p, args.trim_3p, args.min_len,
args.max_len, args.map_command, TEMP_DIR)
read_stats = [c / total_read * 100 for c in cnts]
table.append([
aseq, cnts[0], read_stats[0], cnts[1], read_stats[1], setstr[i]
])
make_stats_report(table, total_read, args.subsample_rate,
args.prefix_match, sd, original_fastq,
args.output_dir, TEMP_DIR, args.no_output_files)
def main():
args = parse_args()
fastq = args.FASTQ
Ks = convert_interval(args.k, "-k", int)
Rs = convert_interval(args.r, "-r", float)
if not MAP_TO_GENOME:
if len(Ks) > 1 or len(Rs) > 1:
adapts = iterative_adapter_prediction(fastq, Rs, Ks, SAMPLE_NUM)
else:
adapts = adapter_prediction(fastq, Rs[0], Ks[0], SAMPLE_NUM)
if args.show_all:
for x in adapts:
print("{}\tscore={:.2f}".format(*x))
else:
print(adapts[0][0])
else:
global TEMP_DIR
TEMP_DIR = "{}/DNApi_tmp_{}".format(
args.temp_dir, str(uuid.uuid4()))
subprocess.call(("mkdir {}".format(TEMP_DIR)).split())
original_fastq = fastq
fastq, total_read, sd = fastq_input_prep(
fastq, args.subsample_rate, TEMP_DIR)
if args.seq:
adapts = set(args.seq)
setstr = ["user-input" for i in range(len(adapts))]
else:
msg = "warning: predicted adapter is too short (<{0}): '{1}'\n" \
+ "warning: '{1}' will not be further investigated\n"
params = {}
for k in Ks:
for r in Rs:
aout = adapter_prediction(fastq, r, k, SAMPLE_NUM)[0][0]
if len(aout) < args.prefix_match:
sys.stderr.write(msg.format(l, s))
continue
aseq = aout[: args.prefix_match+5]
params.setdefault(aseq,[]).append("{}:{:.1f}".format(k,r))
adapts = list(params.keys())
setstr = [';'.join(s) for s in params.values()]
adapts.append("RAW_INPUT")
setstr.append("NO_TREATMENT")
if not adapts:
raise Exception("no valid adapters to further process")
table = []
for i, aseq in enumerate(adapts):
cnts = map_clean_reads(
fastq, aseq[:args.prefix_match], args.trim_5p,
args.trim_3p, args.min_len, args.max_len,
args.map_command, TEMP_DIR)
read_stats = [c / total_read * 100 for c in cnts]
table.append([aseq, cnts[0], read_stats[0],
cnts[1], read_stats[1], setstr[i]])
make_stats_report(
table, total_read, args.subsample_rate, args.prefix_match,
sd, original_fastq, args.output_dir, TEMP_DIR, args.no_output_files)