def peptideEncoding(dna, protein):
"""
Find motifs in the positions dna which generate the protein
"""
reverseLookup = defaultdict(list)
for k, v in rnaCoding.iteritems():reverseLookup[v].append(k.replace('U', 'T'))
motifs = [ "".join(prod) for prod in product(*[reverseLookup[p] for p in protein])]
motifs += [reverseComplement(m) for m in motifs]
motifLength = 3 * len(protein)
return [dna[i:i + motifLength] for i in range(len(dna) - motifLength) if dna[i:i + motifLength] in motifs]
def syntegenyBlockConstruction(kLength, sequence1, sequence2):
kmerPos = defaultdict(list)
for i in range(len(sequence1) - kLength + 1):
kmer = sequence1[i:i + kLength]
kmerPos[kmer].append(i)
kmerPos[reverseComplement(kmer)].append(i)
for i in range(len(sequence2) - kLength + 1):
kmer = sequence2[i:i + kLength]
for pos in kmerPos[kmer]:
yield(pos, i)
def syntegenyBlockConstruction(kLength, sequence1, sequence2):
kmerPos = defaultdict(list)
for i in range(len(sequence1) - kLength + 1):
kmer = sequence1[i:i + kLength]
kmerPos[kmer].append(i)
kmerPos[reverseComplement(kmer)].append(i)
for i in range(len(sequence2) - kLength + 1):
kmer = sequence2[i:i + kLength]
for pos in kmerPos[kmer]:
yield (pos, i)
def peptideEncoding(dna, protein):
"""
Find motifs in the positions dna which generate the protein
"""
reverseLookup = defaultdict(list)
for k, v in rnaCoding.iteritems():
reverseLookup[v].append(k.replace('U', 'T'))
motifs = [
"".join(prod) for prod in product(*[reverseLookup[p] for p in protein])
]
motifs += [reverseComplement(m) for m in motifs]
motifLength = 3 * len(protein)
return [
dna[i:i + motifLength] for i in range(len(dna) - motifLength)
if dna[i:i + motifLength] in motifs
]
def testReverseComplement2(self):
self.assertEqual(hw.reverseComplement("CCCGGG"), "CCCGGG")
def testReverseComplement1(self):
self.assertEqual(hw.reverseComplement("GATTACA"), "TGTAATC")
def testReverseComplement(self):
dna = 'AAAACCCGGT'
self.assertEqual('ACCGGGTTTT', reverseComplement(dna))
def testReverseComplement(self):
dna = 'AAAACCCGGT'
self.assertEqual('ACCGGGTTTT', reverseComplement(dna))
def Find(self, sequence):
length = len(sequence)
rc = reverseComplement(sequence)
fwd = [(m.start(), m.end(), 0) for m in re.finditer(self.regularExpression, sequence)]
rev = [(length-m.end(), length-m.start(), 1) for m in re.finditer(self.regularExpression, rc)]
return fwd + rev
