def get(self, key: Any) -> Optional[FileLike]:
"""Get the file object associated with a path. If the file is not
already open, it is first opened with `xopen`.
Args:
key: The file name/key.
Returns:
The opened file.
"""
fileobj = self._files.get(key, None)
if fileobj is None:
if isinstance(key, int) and len(self) > key:
key = list(self.keys)[key]
fileobj = self._files[key]
else:
return None
if isinstance(fileobj, dict):
path = self._paths[key]
fileobj["context_wrapper"] = True
fileobj = xopen(path, **fileobj)
if self.header and fileobj.writable():
fileobj.write(self.header)
self._files[key] = fileobj
return fileobj
def main():
parser = argparse.ArgumentParser()
parser.add_argument("-1", "--fastq1")
parser.add_argument("-2", "--fastq2")
parser.add_argument("-o", "--output", default="-")
args = parser.parse_args()
with xopen(args.fastq1) as fq1, xopen(args.fastq2) as fq2:
hists = make_hists(fq1, fq2)
with xopen(args.output, 'w') as o:
w = csv.writer(o, delimiter="\t")
w.writerow(('read', 'side', 'pos', 'base', 'count'))
for i, h in enumerate(hists, 1):
for j in range(2):
for b in nuc:
for k, count in enumerate(h[j][b], 1):
w.writerow((i, j, k, b, count))
def main():
parser = argparse.ArgumentParser()
parser.add_argument("-1", "--fastq1")
parser.add_argument("-2", "--fastq2")
parser.add_argument("-o", "--output", default="-")
args = parser.parse_args()
with xopen(args.fastq1) as fq1, xopen(args.fastq2) as fq2:
hists = make_hists(fq1, fq2)
with xopen(args.output, 'w') as o:
w = csv.writer(o, delimiter="\t")
w.writerow(('read', 'side', 'pos', 'base', 'count'))
for i, h in enumerate(hists, 1):
for j in range(2):
for b in nuc:
for k, count in enumerate(h[j][b], 1):
w.writerow((i, j, k, b, count))
def translate(fasta):
dbf = os.path.basename(rreplace(fasta, 'fasta', 'fasta.db', 1))
print('Translating...')
with xopen(dbf, 'wt') as db:
parser = SeqIO.parse(xopen(fasta, 'rt'), 'fasta')
for sequence in parser:
id, seq = sequence.description, Seq(
str(sequence.seq).upper().replace('X', 'N'))
f = (-3, -2, -1, 1, 2, 3)
for i in f:
if i < 0:
db.write('>%s\n%s\n' %
('%s_%d' % (id, i),
seq.reverse_complement()[-(i + 1):].translate(
stop_symbol='X')))
elif i > 0:
db.write('>%s\n%s\n' %
('%s_+%d' %
(id, i), seq[i - 1:].translate(stop_symbol='X')))
def main():
parser = argparse.ArgumentParser()
parser.add_argument("-a", "--adapter1", default=ADAPTER1)
parser.add_argument("-A", "--adapter2", default=ADAPTER2)
parser.add_argument("-1", "--fastq1")
parser.add_argument("-2", "--fastq2")
parser.add_argument("-o", "--output", default="-")
args = parser.parse_args()
with xopen(args.fastq1) as fq1, xopen(args.fastq2) as fq2:
metrics = estimate_metrics(fq1, fq2, args.adapter1, args.adapter2)
with xopen(args.output, 'w') as o:
print("Avg error prob: {}".format(metrics[0]), file=o)
print("Read 1 with full-length adapters: {}".format(metrics[1]),
file=o)
print("Read 1 full-length adapter bases: {}".format(metrics[2]),
file=o)
print("Read 2 with full-length adapters: {}".format(metrics[3]),
file=o)
print("Read 2 full-length adapter bases: {}".format(metrics[4]),
file=o)
def main(args):
with xopen(args.Tumor_Normal_mpileup, 'rt') as TN, open(args.Candidate_somatic_sites, 'wt') as Cs:
combi = pairwise(enumerate(TN))
for line, line_pair in combi:
# look at a genomic site and its next number_of_columns site
line_content = line[1].rstrip('\n').split('\t')
line_pair_content = line_pair[1].rstrip('\n').split('\t')
if line_content[0] == line_pair_content[0] and (int(line_pair_content[1]) - int(line_content[1]) == args.number_of_columns):
process_line(line_content, line, Cs)
else:
# ignore the genomic site if its next number_of_columns site does not exist
next(itertools.islice(combi, 2*args.number_of_columns-1, 2*args.number_of_columns-1), None)
def main(args):
with xopen(args.Tumor_Normal_mpileup, 'rt') as TN, open(args.Candidate_validated_somatic_sites, 'rt') as Cs, open(args.Mapping_information_file, 'wt') as Mi:
n = 110
enume_Cs = enumerate(Cs)
enume_TN = enumerate(TN)
for line in enume_Cs:
holder = []
# creating input for training or inference
if args.indicator == 'training':
label = []
else:
pass
base = ['A', 'T', 'G', 'C', 'N']
line_content = line[1].rstrip('\n').split('\t')
# encoding for bases
encoding = ['00001', '00010', '00100', '01000', '10000']
# process the first line
if line[0] == 0:
for col in itertools.islice(enume_TN, int(line_content[0]) - n, int(line_content[0]) + n +1):
holder = generate_mapping_infor_reads(col, holder)
keep = int(line_content[0])
# creating input for training or inference
if args.indicator == 'training':
for i in range(2805):
label.append(line_content[3])
holder.append(label)
overlap = holder[:-1]
else:
overlap = holder
# write to a file in row order
for row in zip(*holder):
Mi.write('\t'.join(row) + '\n')
# process the rest lines
else:
# the distance between two candidate or validated genomic sites
gap = int(line_content[0]) - keep
# the distance larger than the window size of 2*n
if gap > 2*n:
for col in itertools.islice(enume_TN, gap - 2*n -1, gap):
holder = generate_mapping_infor_reads(col, holder)
# creating input for training or inference
if args.indicator == 'training':
for i in range(2805):
label.append(line_content[3])
holder.append(label)
overlap = holder[:-1]
else:
overlap = holder
for row in zip(*holder):
Mi.write('\t'.join(row) + '\n')
keep = int(line_content[0])
# the distance smaller than the window size of 2*n
else:
# copy the information of overlapping window from last column
for infor in overlap[gap:]:
holder.append(infor)
overlap = []
for col in itertools.islice(enume_TN, 0, gap):
holder = generate_mapping_infor_reads(col, holder)
# creating input for training or inference
if args.indicator == 'training':
for i in range(2805):
label.append(line_content[3])
holder.append(label)
overlap = holder[:-1]
else:
overlap = holder
for row in zip(*holder):
Mi.write('\t'.join(row) + '\n')
keep = int(line_content[0])
def open(self) -> None:
"""Opens the reader.
"""
self._reader = xopen(self.path, "rb", context_wrapper=True)
def __init__(self, file1, file2=None, **kwargs):
self.paired = file2 is not None
self.file1 = xopen(file1, 'wt', **kwargs)
if self.paired:
self.file2 = xopen(file2, 'wt', **kwargs)