def extractOrfsIter(seq, minLen=20, pattern='\*|X{200,}', verbose=False):
"""Returns an ORF extracting iterator
@param seq: DNA sequence
@param minLen: Minimum ORF length (default=20)
@param pattern: Stop and break pattern (default="*|X{200,}")
@return: Iterator yielding (i,gStart,gEnd,ORF)
"""
L = len(seq)
regex = re.compile(pattern)
i = 0
sixFrameIter = sixFrameTranslationIter(seq)
for frame,p in sixFrameIter:
if verbose: print frame
matchIter = regex.finditer(p)
# As though there is a stop to the left of 0
start = -1
for match in matchIter:
end = match.start()
orf = p[start+1:end]
if len(orf)>=minLen:
i += 1
gStart,gEnd = hmmer.convertSixFrameToGenomic(start+2, end, frame, L)
yield i, gStart, gEnd, orf
start = copy.copy(end)
# As though there is a stop to the right of len(p)-1
end = len(p)
orf = p[start+1:end]
if len(orf)>=minLen:
i += 1
gStart,gEnd = hmmer.convertSixFrameToGenomic(start+2, end, frame, L)
yield i, gStart, gEnd, orf
frame = hmmer.hmmer2frame[hmmerFrame]
print >> sys.stderr, 'Frame:', frame
if frame>0:
strand = '+'
else:
strand = '-'
matchIter = pattern.finditer(p)
match = matchIter.next()
start = match.start()
for match in matchIter:
end = match.start()
orf = p[start+1:end]
length = len(orf)
if length>=minLen:
gStart,gEnd = hmmer.convertSixFrameToGenomic(start+2, end, frame, L)
i += 1
h = '%s.%i.%i-%i length %i' % (hstart, i, gStart, gEnd, length)
writer.write(h, orf + '\n')
# if strand=='+':
# print orf
# print [x for x in sequence.codonIterator(seq[gStart-1:gEnd], remainder=True)]
# print sequence.translate(seq[gStart-1:gEnd])
# else:
# start,end = gEnd,gStart
# print orf
# print [x for x in sequence.codonIterator(sequence.reverseComplement(seq[start-1:end]), remainder=True)]
# print sequence.translate(sequence.reverseComplement(seq[start-1:end]))
# print
frame = hmmer.hmmer2frame[hmmerFrame]
print >> sys.stderr, 'Frame:', frame
if frame > 0:
strand = '+'
else:
strand = '-'
matchIter = pattern.finditer(p)
match = matchIter.next()
start = match.start()
for match in matchIter:
end = match.start()
orf = p[start + 1:end]
length = len(orf)
if length >= minLen:
gStart, gEnd = hmmer.convertSixFrameToGenomic(
start + 2, end, frame, L)
i += 1
h = '%s.%i.%i-%i length %i' % (hstart, i, gStart, gEnd, length)
writer.write(h, orf + '\n')
# if strand=='+':
# print orf
# print [x for x in sequence.codonIterator(seq[gStart-1:gEnd], remainder=True)]
# print sequence.translate(seq[gStart-1:gEnd])
# else:
# start,end = gEnd,gStart
# print orf
# print [x for x in sequence.codonIterator(sequence.reverseComplement(seq[start-1:end]), remainder=True)]
# print sequence.translate(sequence.reverseComplement(seq[start-1:end]))
# print
