def getSequence(blastDb, accession, start=0, end=0, strand='+', padding=0, debug=False):
"""Load a sequence from a BLAST database.
@param blastDb: BLAST database
@param accession: Accession name
@param start: Start coordinate (Default: 0, extract from start of sequence)
@param end: End coordinate (Default: 0, extract to the end of sequence)
@param strand: Strand (Default: '+')
@param padding: Sequence padding (Default: 0)
@returns: (header,seq)
"""
if start>end: start,end = end,start
cmd = 'fastacmd -d %s -s "%s" -L %i,%i' % (blastDb,accession,start,end)
if debug: print cmd
p = os.popen(cmd)
header = p.readline()[1:].strip()
if not header:
raise Exception('BLAST failure')
seq = []
for line in p:
seq.append(line.strip())
seq = ''.join(seq)
if not seq:
print blastDb, accession
raise NotFoundException()
if strand=='-':
seq = sequence.reverseComplement(seq)
return header,seq
def projectOntoString(self, seq):
extracted = []
for tStart,blockSize in zip(self.tStarts, self.blockSizes):
tEnd = tStart+3*blockSize-1
if self.strand=='+':
s = seq[tStart:tEnd+1]
else:
s = sequence.reverseComplement(seq)[tStart:tEnd+1]
extracted.append(s)
return extracted
def projectOntoString(self, seq):
extracted = []
for tStart, blockSize in zip(self.tStarts, self.blockSizes):
tEnd = tStart + 3 * blockSize - 1
if self.strand == '+':
s = seq[tStart:tEnd + 1]
else:
s = sequence.reverseComplement(seq)[tStart:tEnd + 1]
extracted.append(s)
return extracted
def writeSeq(ref, seq, pos, type, strand):
preoffset, postoffset = offsets[type]
ntype = type
if strand == '-':
if ntype == 'ATG': type = 'TGA'
elif ntype == 'TGA': type = 'ATG'
elif ntype == 'GT': type = 'AG'
else: type = 'GT'
postoffset += 2
else:
preoffset += 2
retseq = seq[pos-preoffset:pos+postoffset]
if strand == '-': retseq = reverseComplement(retseq)
head = ref + ':' + str(pos-preoffset) + ':' + str(pos+postoffset-1) + ':' + strand
outfiles[type].write(head, retseq)
def getSequence(blastDb,
accession,
start=0,
end=0,
strand='+',
padding=0,
debug=False):
"""Load a sequence from a BLAST database.
@param blastDb: BLAST database
@param accession: Accession name
@param start: Start coordinate (Default: 0, extract from start of sequence)
@param end: End coordinate (Default: 0, extract to the end of sequence)
@param strand: Strand (Default: '+')
@param padding: Sequence padding (Default: 0)
@returns: (header,seq)
"""
if start > end: start, end = end, start
cmd = 'fastacmd -d %s -s "%s" -L %i,%i' % (blastDb, accession, start, end)
if debug: print cmd
p = os.popen(cmd)
header = p.readline()[1:].strip()
if not header:
raise Exception('BLAST failure')
seq = []
for line in p:
seq.append(line.strip())
seq = ''.join(seq)
if not seq:
print blastDb, accession
raise NotFoundException()
if strand == '-':
seq = sequence.reverseComplement(seq)
return header, seq
def _get_reverse_bases(self):
if self._reverse is None:
self._reverse = sequence.reverseComplement(self.get_bases())
return self._reverse
#!/usr/bin/env python
"""
stops.py
Author: Tony Papenfuss
Date: Mon Apr 17 19:04:42 EST 2006
"""
import os, sys
import sequence
stops = ['TAA', 'TGA', 'TAG', 'taa', 'tga', 'tag']
for stop in stops:
print stop, sequence.reverseComplement(stop)
i = 0
writer = fasta.MfaWriter('ORFs.fa')
filename = sys.argv[1]
header,dna = fasta.load(filename)
header = header.strip()
orfIter = sequence.extractOrfsIter(dna, minLen=minLen, pattern=pattern)
for i,gStart,gEnd,orf in orfIter:
h = '%s.%i.%i-%i Length=%i' % (header,i,gStart,gEnd,len(orf))
writer.write(h, orf)
fasta.pretty(h, orf)
if gStart<gEnd:
s = dna[gStart-1:gEnd]
print gStart, gEnd, len(s), len(s) % 3==0
print sequence.codons(s, remainder=True)
print sequence.translate(s)
else:
gStart,gEnd = gEnd,gStart
s = dna[gStart-1:gEnd]
s = sequence.reverseComplement(s)
print gStart, gEnd, len(s), len(s) % 3==0
print sequence.codons(s, remainder=True)
print sequence.translate(s)
print
writer.close()
import bacillussubtilis168 as bs
import sequence
import unittest
forward = bs.bases
reverse = sequence.reverseComplement(forward)
def find_once(sear, seq):
f, r = seq.find(sear), seq.rfind(sear)
if f == r:
return f
else:
return 'No!'
class PetersTest(unittest.TestCase):
def setUp(self):
pass
def test_length(self):
self.assertEqual(len(forward), len(reverse))
def test_find_once(self):
self.assertEqual('No!', find_once('A', forward))
length += coord[1] - coord[0] + 1
if gene.strand == '-': frame = str(swap((length-1)%3))
if (coord[0] == gene.min) and (coord[1] == gene.max):
split.addFeature(Feature(gene.ref+'_inter', gene.source, ['inter'], [[prev+1, coord[0]-1]], gene.score, '+', '.', gene.name))
split.addFeature(Feature(gene.ref+'_esing', gene.source, ['esing'], [coord], gene.score, gene.strand, frame, gene.name))
elif coord[0] == gene.min:
split.addFeature(Feature(gene.ref+'_inter', gene.source, ['inter'], [[prev+1, coord[0]-1]], gene.score, '+', '.', gene.name))
split.addFeature(Feature(gene.ref+'_'+forward, gene.source, [forward], [coord], gene.score, gene.strand, frame, gene.name))
elif coord[1] == gene.max:
split.addFeature(Feature(gene.ref+'_intrn', gene.source, ['intrn'], [[prev+1, coord[0]-1]], gene.score, gene.strand, '.', gene.name))
split.addFeature(Feature(gene.ref+'_'+backward, gene.source, [backward], [coord], gene.score, gene.strand, frame, gene.name))
else:
split.addFeature(Feature(gene.ref+'_intrn', gene.source, ['intrn'], [[prev+1, coord[0]-1]], gene.score, gene.strand, '.', gene.name))
split.addFeature(Feature(gene.ref+'_eintn', gene.source, ['eintn'], [coord], gene.score, gene.strand, frame, gene.name))
prev = coord[1]
split.addFeature(Feature(gene.ref+'_inter', gene.source, ['inter'], [[prev+1, endref]], gene.score, '+', '.', gene.name))
for typeref in split:
type = typeref.split('_')[-1]
if outfiles.has_key(type):
split.writeGff(outfiles[type][0], typeref)
for generef in split[typeref]:
gene = split[typeref][generef]
for a in range(len(gene.coords)):
start = gene.coords[a][0]
end = gene.coords[a][1]
ref = gene.ref
strand = gene.strand
outhead = gene.ref + ':' + str(start) + ':' + str(end) + ':' + strand + ':' + gene.frame[a]
outseq = seq[start-startref:end-startref+1]
if strand == '-': outseq = reverseComplement(outseq)
outfiles[gene.type[0]][1].write(outhead, outseq)
def selfSW(s):
"""Return the self-alignment, i.e. the sequence to the
reverse complement sequence.
The better the alignment the more secondary structure.
"""
return SW(s,sequence.reverseComplement(s))
def blastEnergy(qrySeq,subjSeq,findGaps=True,debug=False):
"""Return the energy for the association of the query and subject
sequences. The gaps are found by SW algnment.
"""
if debug:
dbOut=file('beDebug.log','w')
dbOut=sys.stdout
if findGaps:
swAlign,swScore = SW(qrySeq,subjSeq)
#debug=False
qrySw,subjSw = [line.strip().replace(' ','x')
for line in swAlign.split('\n')]
if 'x' in qrySw or 'x' in subjSw :
debug=True
if debug:
print >> dbOut, "\ninput:"
print >> dbOut, qrySeq
print >> dbOut, subjSeq
print >> dbOut, "SW:"
print >> dbOut, qrySw
print >> dbOut, subjSw
print >> dbOut, swScore
# add x to right end if necessary
# this should not happen
qrySw=qrySw.rstrip('.')
subjSw=subjSw.rstrip('.')
sizeDiff = len(qrySw)-len(subjSw)
if sizeDiff > 0:
subjSw+=['x']*sizeDiff
elif sizeDiff < 0:
qrySw+=['x']*abs(sizeDiff)
qrySw=list(qrySw)
subjSw=list(subjSw)
#put mismatches back in
for i in range(len(qrySw)):
if qrySw[i] == '.':
#print >> dbOut, qrySw[:i].count('x')]
qrySw[i]=qrySeq[i-qrySw[:i].count('x')]
for i in range(len(subjSw)):
if subjSw[i] == '.':
subjSw[i]=subjSeq[i-subjSw[:i].count('x')]
# go back to strings
qrySw=''.join(qrySw)
subjSw=''.join(subjSw)
if debug:
print >> dbOut, "e-mangle:"
print >> dbOut, qrySw
print >> dbOut, subjSw
else:
qrySw=qrySw.replace('U','T')
subjSw=subjSw.replace('U','T')
qrySw=qrySw
subjSw=subjSeq
try:
e= energy(qrySw,sequence.reverseComplement(subjSw))
except:
print ("""energy calculation failed:
Query:\t%s\t%s
Subj:\t%s\t%s
""" % (qrySeq,qrySw,subjSeq,subjSw))
raise
return e
def getSequenceFromString(self, seq):
s = seq[self.sStart-1:self.sEnd]
if self.strand=='-':
s = sequence.reverseComplement(s)
return s
i = 0
writer = fasta.MfaWriter('ORFs.fa')
filename = sys.argv[1]
header, dna = fasta.load(filename)
header = header.strip()
orfIter = sequence.extractOrfsIter(dna, minLen=minLen, pattern=pattern)
for i, gStart, gEnd, orf in orfIter:
h = '%s.%i.%i-%i Length=%i' % (header, i, gStart, gEnd, len(orf))
writer.write(h, orf)
fasta.pretty(h, orf)
if gStart < gEnd:
s = dna[gStart - 1:gEnd]
print gStart, gEnd, len(s), len(s) % 3 == 0
print sequence.codons(s, remainder=True)
print sequence.translate(s)
else:
gStart, gEnd = gEnd, gStart
s = dna[gStart - 1:gEnd]
s = sequence.reverseComplement(s)
print gStart, gEnd, len(s), len(s) % 3 == 0
print sequence.codons(s, remainder=True)
print sequence.translate(s)
print
writer.close()
if False:
domains = hmmer4.load_domains('hmmer/6frames.txt')
for d in domains:
p = hmmer4.parseSixFrameHeader(d.accession)
print d
print p.name, p.frame
gStart,gEnd,strand = hmmer4.convert6FrameToGenomic(d.sStart,d.sEnd,p.frame,L)
print gStart,gEnd,strand
if strand=='+':
dna = s[gStart-1:gEnd]
print len(dna), len(dna) % 3==0
print sequence.codons(dna, remainder=True)
print sequence.translate(dna)
else:
gStart,gEnd = gEnd,gStart
dna = sequence.reverseComplement(s[gStart-1:gEnd])
print len(dna), len(dna) % 3==0
print sequence.codons(dna, remainder=True)
print sequence.translate(dna)
print
else:
domains = hmmer4.load_domains('hmmer/ORFs.txt')
for d in domains:
o = hmmer4.parseOrfHeader(d.accession)
print d
print o
gStart,gEnd = hmmer4.convertOrfToGenomic(d.sStart,d.sEnd,o.strand,o.start)
if o.strand=='+':
dna = s[gStart-1:gEnd]
else:
gStart,gEnd = gEnd,gStart
def getSequenceFromString(self, seq):
s = seq[self.sStart - 1:self.sEnd]
if self.strand == '-':
s = sequence.reverseComplement(s)
return s
#!/usr/bin/env python
"""
stops.py
Author: Tony Papenfuss
Date: Mon Apr 17 19:04:42 EST 2006
"""
import os, sys
import sequence
stops = ['TAA','TGA','TAG','taa','tga','tag']
for stop in stops:
print stop, sequence.reverseComplement(stop)
Date: Tue Aug 22 20:14:57 EST 2006
"""
import os, sys
import fasta, sequence
header,seq = fasta.load('NKC.fa')
orfIterator = fasta.load_iter('ORFs.fa')
writer = fasta.MfaWriter('ORFs2.fa')
for h,orf in orfIterator:
chrom,block,orfId,limits = h.split()[0].split('.')
start,end = limits.split('-')
start = int(start)
end = int(end)
if start>end:
strand = '-'
start,end = end,start
s = sequence.translate(sequence.reverseComplement(seq[start-1:end]))
else:
strand = '+'
s = sequence.translate(seq[start-1:end])
if s!=orf: print h
writer.write(h,s + '\n')
writer.close()
