def orientate(self, seq):
ret = self.wu.search_text(seq)
if ret is not None:
if self.conserved_sequences[ret[1]].rc:
return reverse_complement(seq)
else:
return seq
else:
logging.error('cannot identify any 16S conserved sequences'\
'in:\n%s\nReturning original sequence',
(seq,))
return seq
def _sam_to_fastx2(self, cluster, prefix, fasta=True, qual=True, fastq=False,
pairs=False, sep12=False):
"""Take a pysam AlignedRead and convert it into a fasta, qual or fastq
cluster: A Cluster object which contains lists of paired and single
reads
prefix: file path prefix
"""
if fasta and fastq:
raise RuntimeError("cannot output both fasta and fastq at the same time, choose one or the other")
#logging.debug("requrested the following read"
# "outputs:\nfasta=%s\nfastq=%s\npairs=%s\nsep12=%s\n",
# str(fasta), str(fastq), str(pairs), str(sep12))
#logging.debug("cluster reads: first = %d, second = %d, singles = %d",
# len(cluster.first), len(cluster.second), len(cluster.singles))
written_files = {}
# for seqs - fasta, fastq
fp1 = None
fp2 = None
fps = None
fpp = None
# for quals
qfp1 = None
qfp2 = None
qfps = None
qfpp = None
if len(cluster.first):
# we have reads in pairs
if fasta:
if pairs:
if sep12:
suffix1 = "_R1.fasta"
suffix2 = "_R2.fasta"
fp1 = open(prefix+suffix1, 'w')
fp2 = open(prefix+suffix2, 'w')
written_files['r1'] = suffix1
written_files['r2'] = suffix2
else:
suffix12 = "_R12.fasta"
fpp = open(prefix+suffix12, 'w')
written_files['r12'] = suffix12
else:
suffixs = "_s.fasta"
fps = open(prefix+suffixs, 'w')
written_files['s'] = suffixs
if qual:
if pairs:
if sep12:
suffix1 = "_R1.fasta.qual"
suffix2 = "_R2.fasta.qual"
qfp1 = open(prefix+suffix1, 'w')
qfp2 = open(prefix+suffix2, 'w')
written_files['q1'] = suffix1
written_files['q2'] = suffix2
else:
suffix12 = "_R12.fasta.qual"
qfpp = open(prefix+suffix12, 'w')
written_files['q12'] = suffix12
else:
suffixs = "_s.fasta.qual"
qfps = open(prefix+suffixs, 'w')
written_files['qs'] = suffixs
if fastq:
if pairs:
if sep12:
suffix1 = "_R1.fastq"
suffix2 = "_R2.fastq"
fp1 = open(prefix+suffix1, 'w')
fp2 = open(prefix+suffix2, 'w')
written_files['r1'] = suffix1
written_files['r2'] = suffix2
else:
suffix12 = "_R12.fastq"
fpp = open(prefix+suffix12, 'w')
written_files['r12'] = suffix12
else:
suffixs = "_s.fastq"
fps = open(prefix+suffixs, 'w')
written_files['s'] = suffixs
for ar1, ar2 in zip(cluster.first, cluster.second):
name1 = ar1.qname
seq1 = ar1.seq
quality1 = ar1.qual
name2 = ar2.qname
seq2 = ar2.seq
quality2 = ar2.qual
if ar1.is_reversed():
seq1 = reverse_complement(seq1)
quality1 = quality1[::-1]
if ar2.is_reversed():
seq2 = reverse_complement(seq2)
quality2 = quality2[::-1]
if fp1 is not None and fp2 is not None:
if fasta:
fp1.write(">%s\n%s\n" % (name1, seq1))
fp2.write(">%s\n%s\n" % (name2, seq2))
if fastq:
fp1.write('@%s\n%s\n+\n%s\n' % (name1,seq1,quality1))
fp2.write('@%s\n%s\n+\n%s\n' % (name2,seq2,quality2))
if qual:
quality = amplishot.parse.fastx.decode_quality(quality1)
quality = ' '.join(str(x) for x in quality)
qfp1.write('>%s\n%s\n' %(name1, quality))
quality = amplishot.parse.fastx.decode_quality(quality2)
quality = ' '.join(str(x) for x in quality)
qfp2.write('>%s\n%s\n' %(name2, quality))
elif fpp is not None:
if fasta:
fpp.write(">%s\n%s\n" % (name1, seq1))
fpp.write(">%s\n%s\n" % (name2, seq2))
if fastq:
fpp.write('@%s\n%s\n+\n%s\n' % (name1,seq1,quality1))
fpp.write('@%s\n%s\n+\n%s\n' % (name2,seq2,quality2))
if qual:
quality = amplishot.parse.fastx.decode_quality(quality1)
quality = ' '.join(str(x) for x in quality)
qfpp.write('>%s\n%s\n' %(name1, quality))
quality = amplishot.parse.fastx.decode_quality(quality2)
quality = ' '.join(str(x) for x in quality)
qfpp.write('>%s\n%s\n' %(name2, quality))
elif fps is not None:
if fasta:
fps.write(">%s\n%s\n" % (name1, seq1))
fps.write(">%s\n%s\n" % (name2, seq2))
if fastq:
fps.write('@%s\n%s\n+\n%s\n' % (name1,seq1,quality1))
fps.write('@%s\n%s\n+\n%s\n' % (name2,seq2,quality2))
if qual:
quality = amplishot.parse.fastx.decode_quality(quality1)
quality = ' '.join(str(x) for x in quality)
qfps.write('>%s\n%s\n' %(name1, quality))
quality = amplishot.parse.fastx.decode_quality(quality2)
quality = ' '.join(str(x) for x in quality)
qfps.write('>%s\n%s\n' %(name2, quality))
if len(cluster.singles):
# only reads in singles
if fasta:
suffixs = "_s.fasta"
if fps is None:
fps = open(prefix+suffixs, 'w')
written_files['s'] = suffixs
if qual:
if qfps is None:
qfps = open(prefix+"_s.fasta.qual", 'w')
written_files['qs'] = "_s.fasta.qual"
if fastq:
if fps is None:
fps = open(prefix+"_s.fastq",'w')
written_files['s'] = "_s.fastq"
for ar in cluster.singles:
name = ar.qname
seq = ar.seq
quality = ar.qual
if ar.is_reversed():
seq = reverse_complement(seq)
quality = quality[::-1]
if fasta:
fps.write(">%s\n%s\n" % (name, seq))
if fastq:
fps.write('@%s\n%s\n+\n%s\n' % (name,seq,quality))
if qual:
quality = amplishot.parse.fastx.decode_quality(quality)
quality = ' '.join(str(x) for x in quality)
qfps.write('>%s\n%s\n' %(name, quality))
if fp1:
fp1.close()
if fp2:
fp2.close()
if fpp:
fpp.close()
if fps:
fps.close()
if qfp1:
qfp1.close()
if qfp2:
qfp2.close()
if qfpp:
qfpp.close()
if qfps:
qfps.close()
return written_files