def read_length_histogram(in_fastq, out_hist):
"""draw histogram of read lengths"""
length_count = defaultdict(int)
for header, seq, qual in parseFastq(gzip.open(in_fastq)):
length_count[len(seq)] += 1
pyplot.figure()
pyplot.bar(range(1,max(length_count)+1),
[length_count[l] for l in range(1, max(length_count)+1)],
align='center')
pyplot.savefig(out_hist)
def read_length_histogram(in_fastq, out_hist):
"""draw histogram of read lengths"""
length_count = defaultdict(int)
for header, seq, qual in parseFastq(gzip.open(in_fastq)):
length_count[len(seq)] += 1
pyplot.figure()
pyplot.bar(range(1,
max(length_count) + 1),
[length_count[l] for l in range(1,
max(length_count) + 1)],
align='center')
pyplot.savefig(out_hist)
def trim_regex(in_fastq, out_fastq, trim_pattern):
"""Search the reads for a regex, and trim everything matching the pattern
and all succeeding sequence.
"""
pattern = re.compile(trim_pattern)
with gzip.open(in_fastq) as infile:
with gzip.open(out_fastq, 'w') as outfile:
for header, seq, qual in parseFastq(infile):
matches = [m.span() for m in pattern.finditer(seq)]
if len(matches) > 0:
# match to re found--
# trim the right-most hit and add the trimmed sequence to the read ID
m = matches[-1]
header = seq[m[0]:] + '_' + header
seq = seq[:m[0]]
qual = qual[:m[0]]
if len(matches) > 0 or not cfg.getboolean('filtering', 'require_regex'):
if len(seq) >= 10: # TODO: add adjustable min length
outfile.write('@%s\n%s\n+%s\n%s\n' % (header, seq,
header, qual))
def trim_regex(in_fastq, out_fastq, trim_pattern):
"""Search the reads for a regex, and trim everything matching the pattern
and all succeeding sequence.
"""
pattern = re.compile(trim_pattern)
with gzip.open(in_fastq) as infile:
with gzip.open(out_fastq, 'w') as outfile:
for header, seq, qual in parseFastq(infile):
matches = [m.span() for m in pattern.finditer(seq)]
if len(matches) > 0:
# match to re found--
# trim the right-most hit and add the trimmed sequence to the read ID
m = matches[-1]
header = seq[m[0]:] + '_' + header
seq = seq[:m[0]]
qual = qual[:m[0]]
if len(matches) > 0 or not cfg.getboolean(
'filtering', 'require_regex'):
if len(seq) >= 10: # TODO: add adjustable min length
outfile.write('@%s\n%s\n+%s\n%s\n' %
(header, seq, header, qual))
