def test(r=1, **kw):
S = make_dna_scoring_dict(10, -1, -8)
seq2 = DNA.makeSequence('AAAATGCTTA' * r)
seq1 = DNA.makeSequence('AATTTTGCTG' * r)
t0 = time.time()
aln = classic_align_pairwise(seq1, seq2, S, 10, 2, local=False, **kw)
t = time.time() - t0
return (len(seq1) * len(seq2)) / t
print t
def test(r=1, **kw):
S = make_dna_scoring_dict(10, -1, -8)
seq2 = DNA.makeSequence("AAAATGCTTA" * r)
seq1 = DNA.makeSequence("AATTTTGCTG" * r)
t0 = time.time()
aln = classic_align_pairwise(seq1, seq2, S, 10, 2, local=False, **kw)
t = time.time() - t0
return (len(seq1) * len(seq2)) / t
print t
def group_to_reference(fulldict, reference, nonref, structscore, norefseq=False):
nogroup = []
score_structures = ScoreStructures()
for currstruct in nonref:
strscore = structscore
seqscore = 0
bestref = ""
#remove gaps from majority and set as seq1
seq = fulldict[currstruct].majorityConsensus()
seq1 = RnaSequence(''.join(seq).replace('-', ''))
for teststruct in reference:
holdscore = score_structures(currstruct, teststruct)
if holdscore <= strscore:
#remove gaps from majority and set as seq2
seq = fulldict[teststruct].majorityConsensus()
seq2 = RnaSequence(''.join(seq).replace('-', ''))
#compare alignment score. subtract so lower is still better
aln, alnscore = classic_align_pairwise(seq1, seq2, alnscores, -10, -10, False, return_score=True)
if alnscore > seqscore:
strscore = holdscore
seqscore = alnscore
bestref = teststruct
if bestref != "":
#combine the two alignments into one alignment using reference sequence as guide
#refseq must be ungapped to do this without realigning, hence the checks
if norefseq:
#realign all sequences since no refseq available
combinedseqs = fulldict[bestref].degap().addSeqs(fulldict[currstruct].degap())
fulldict[bestref] = align_unaligned_seqs(combinedseqs, RNA, params={"-maxiters": 2, "-diags": True})
continue
#if one refseq is gapless, can easily combine them without realigning
if not fulldict[currstruct].getGappedSeq("refseq").isGapped():
fulldict[bestref].addFromReferenceAln(fulldict[currstruct])
elif not fulldict[bestref].getGappedSeq("refseq").isGapped():
fulldict[currstruct].addFromReferenceAln(fulldict[bestref])
fulldict[bestref] = fulldict[currstruct]
else:
#realign all sequences since both refseqs have gaps
#hacky but it works, need to fix later
fulldict[bestref].Names.remove("refseq")
combinedseqs = fulldict[bestref].degap().addSeqs(fulldict[currstruct].degap())
fulldict[bestref] = align_unaligned_seqs(combinedseqs, RNA)
fulldict[bestref].Names.remove("refseq")
fulldict[bestref].Names.insert(0, "refseq")
fulldict.pop(currstruct)
else:
nogroup.append(currstruct)
score_structures.end()
return fulldict, nogroup
def test(r=1, **kw):
S = make_dna_scoring_dict(10, -1, -8)
seq2 = DNA.makeSequence('AAAATGCTTA' * r)
seq1 = DNA.makeSequence('AATTTTGCTG' * r)
t0 = time.clock()
try:
# return_alignment is False in order to emphasise the quadratic part of the work.
aln = classic_align_pairwise(seq1, seq2, S, 10, 2, local=False, return_alignment=False, **kw)
except ArithmeticError:
return '*'
else:
t = time.clock() - t0
return int ( (len(seq1)*len(seq2))/t/1000 )
def group_denovo(fulldict, keys, structscore, norefseq=False):
topop = []
score_structures = ScoreStructures()
for pos, currstruct in enumerate(keys):
strscore = structscore
seqscore = 0
bestref = ""
#remove gaps from majority and set as seq1
seq = fulldict[currstruct].majorityConsensus()
seq1 = RnaSequence(''.join(seq).replace('-', ''))
for secpos in range(pos+1, len(keys)):
holdscore = score_structures(currstruct, keys[secpos])
if holdscore <= strscore:
#remove gaps from majority and set as seq2
seq = fulldict[keys[secpos]].majorityConsensus()
seq2 = RnaSequence(''.join(seq).replace('-', ''))
#compare alignment score. Higher is better.
aln, alnscore = classic_align_pairwise(seq1, seq2, alnscores, -10, -10, False, return_score=True)
if alnscore > seqscore:
strscore = holdscore
seqscore = alnscore
bestref = keys[secpos]
if bestref != "":
if norefseq:
#realign all sequences since no refseq available
combinedseqs = fulldict[bestref].degap().addSeqs(fulldict[currstruct].degap())
fulldict[bestref] = align_unaligned_seqs(combinedseqs, RNA)
continue
if not fulldict[currstruct].getGappedSeq("refseq").isGapped():
fulldict[bestref].addFromReferenceAln(fulldict[currstruct])
elif not fulldict[bestref].getGappedSeq("refseq").isGapped():
fulldict[currstruct].addFromReferenceAln(fulldict[bestref])
fulldict[bestref] = fulldict[currstruct]
else:
#realign all sequences since both refseqs have gaps
#hacky but it works, need to fix later
fulldict[bestref].Names.remove("refseq")
combinedseqs = fulldict[bestref].degap().addSeqs(fulldict[currstruct].degap())
fulldict[bestref] = align_unaligned_seqs(combinedseqs, RNA)
fulldict[bestref].Names.remove("refseq")
fulldict[bestref].Names.insert(0, "refseq")
fulldict.pop(currstruct)
topop.append(pos)
topop.sort(reverse=True)
for pos in topop:
keys.pop(pos)
score_structures.end()
return fulldict, keys
def test(r=1, **kw):
S = make_dna_scoring_dict(10, -1, -8)
seq2 = DNA.makeSequence('AAAATGCTTA' * r)
seq1 = DNA.makeSequence('AATTTTGCTG' * r)
t0 = time.clock()
try:
# return_alignment is False in order to emphasise the quadratic part of the work.
aln = classic_align_pairwise(seq1,
seq2,
S,
10,
2,
local=False,
return_alignment=False,
**kw)
except ArithmeticError:
return '*'
else:
t = time.clock() - t0
return int((len(seq1) * len(seq2)) / t / 1000)
def _aligned_both_ways(self, seq1, seq2, **kw):
S = make_dna_scoring_dict(10, -1, -8)
a1 = classic_align_pairwise(seq1, seq2, S, 10, 2, **kw)
a2 = classic_align_pairwise(seq2, seq1, S, 10, 2, **kw)
return [a1, a2]
def _aligned_both_ways(self, seq1, seq2, **kw):
S = make_dna_scoring_dict(10, -1, -8)
a1 = classic_align_pairwise(seq1, seq2, S, 10, 2, **kw)
a2 = classic_align_pairwise(seq2, seq1, S, 10, 2, **kw)
return [a1, a2]
