def merge(pair1, pair2, fmt="fq"):
if fmt in ("fq", "fastq"):
from pyngs.biofile.fastq import parse
elif fmt in ("fa", "fna", "fasta", "fsa"):
from pyngs.biofile.fasta import parse
read1s = parse(pair1)
read2s = parse(pair2)
for read1, read2 in izip(read1s, read2s):
print read1
print read2
def _trim_pair(pair1, pair2, method='bwa', qtype='S', qthres=QTHRESHOLD,
lthres=LTHRESHOLD):
_trim = get_method(method)
fq1s = parse(pair1, fmt=qtype)
fq2s = parse(pair2, fmt=qtype)
for fq1, fq2 in izip(fq1s, fq2s):
mark = 0
start1, length1 = _trim(fq1, qthres)
start2, length2 = _trim(fq2, qthres)
if length1 < lthres:
mark |= 1
elif length2 < lthres:
mark |= 2
if mark == GOOD:
yield GOOD, fq1[start1:start1+length1], fq2[start2:start2+length2]
else:
yield mark, fq1, fq2
def split(fname, fmt='fq'):
if fmt in ('fq', 'fastq'):
from pyngs.biofile.fastq import parse
elif fmt in ('fa', 'fna', 'fasta', 'fsa'):
from pyngs.biofile.fasta import parse
for idx, read in enumerate(parse(fname)):
if idx % 2: # read2
print >>sys.stderr, read
else: # read1
print >>sys.stdout, read
def _trim_single(fname, method='bwa', qtype='S', qthres=QTHRESHOLD,
lthres=LTHRESHOLD):
"""trim fastq by quality values
Arguments:
- `fname`: fastq file name
- `method`: the way to trim Fastq object
- `qtype`: the fastq qulity type
- `qthres`: quality cutoff threshold
- `lthres`: length cutoff threshold
"""
_trim = get_method(method=method)
for fq in parse(fname, fmt=qtype):
start, length = _trim(fq, qthres)
if length < lthres:
yield BAD1, fq
else:
yield GOOD, fq[start:start+length]