def estimate_frequency(motif,k,samples=100000,thresh=0.7):
#Build sequences
estimate = -30
total = 0
totalcount = 0
for i in range(40):
long_string = 'ACGT'*(int(float(samples)*k/4))
long_string = list(long_string)
random.shuffle(long_string)
random.shuffle(long_string)
random.shuffle(long_string)
long_string = ''.join(long_string)
seqD = {}
for i in range(samples):
offset = k*i
seqD[i] = long_string[offset:offset+k]
P = ProbeSet(genome=seqD)
count = P.count_matching_probes(motif,thresh=thresh)
total += float(samples)
totalcount += float(count)
f = totalcount/total
d = math.fabs(f-estimate)/(estimate+0.00000001)
estimate = f
if d < 1e-4: break
if i > 2 and totalcount > 100: break
#print '%10d %10d %12.3e %12.3e'%(totalcount, total, f, d)
return estimate
def estimate_frequency(motif, k, samples=100000, thresh=0.7):
#Build sequences
estimate = -30
total = 0
totalcount = 0
for i in range(40):
long_string = 'ACGT' * (int(float(samples) * k / 4))
long_string = list(long_string)
random.shuffle(long_string)
random.shuffle(long_string)
random.shuffle(long_string)
long_string = ''.join(long_string)
seqD = {}
for i in range(samples):
offset = k * i
seqD[i] = long_string[offset:offset + k]
P = ProbeSet(genome=seqD)
count = P.count_matching_probes(motif, thresh=thresh)
total += float(samples)
totalcount += float(count)
f = totalcount / total
d = math.fabs(f - estimate) / (estimate + 0.00000001)
estimate = f
if d < 1e-4: break
if i > 2 and totalcount > 100: break
#print '%10d %10d %12.3e %12.3e'%(totalcount, total, f, d)
return estimate
def probOvlpBinomial(A,B,thresh=0.7,verbose=None):
if A.width >= B.width:
Wide, Narrow = A, B
else:
Wide, Narrow = B, A
RC = MotifTools.revcomplement
newWide = Wide[-1,Wide.width+1]
if Wide.__dict__.has_key('bestWide'):
bestWide = Wide.bestWide
else:
bestWideD = {}
for x in newWide.bestseqs(thresh*newWide.maxscore):
bestWideD[x[1]] = 1
for x in bestWideD.keys():
bestWideD[RC(x)] = 1
Wide.bestWide = bestWideD.keys()
bestWide = Wide.bestWide
Wide = newWide
D={}
for i in range(len(bestWide)):
D[i] = bestWide[i]
P = ProbeSet(genome=D)
matchNarrow = P.count_matching_probes(Narrow,thresh=thresh)
if matchNarrow == 0:
p = 1.0
return p
if not Narrow.__dict__.has_key('probNarrow'): Narrow.probNarrow = {}
if Narrow.probNarrow.has_key(Wide.width):
probNarrow = Narrow.probNarrow[Wide.width]
else:
probNarrow = estimate_frequency(Narrow,Wide.width,thresh=thresh)
Narrow.probNarrow[Wide.width] = probNarrow
p = Arith.binomialsumtail(probNarrow,len(bestWide),matchNarrow)
print '\nD= %7.3f %9.4e %8d %7d %-14s %-20s %-14s %-20s'%(
Arith.nlog10(p),probNarrow,len(bestWide),matchNarrow,
A.family,A,B.family,B)
return p
def probOvlpBinomial(A, B, thresh=0.7, verbose=None):
if A.width >= B.width:
Wide, Narrow = A, B
else:
Wide, Narrow = B, A
RC = MotifTools.revcomplement
newWide = Wide[-1, Wide.width + 1]
if Wide.__dict__.has_key('bestWide'):
bestWide = Wide.bestWide
else:
bestWideD = {}
for x in newWide.bestseqs(thresh * newWide.maxscore):
bestWideD[x[1]] = 1
for x in bestWideD.keys():
bestWideD[RC(x)] = 1
Wide.bestWide = bestWideD.keys()
bestWide = Wide.bestWide
Wide = newWide
D = {}
for i in range(len(bestWide)):
D[i] = bestWide[i]
P = ProbeSet(genome=D)
matchNarrow = P.count_matching_probes(Narrow, thresh=thresh)
if matchNarrow == 0:
p = 1.0
return p
if not Narrow.__dict__.has_key('probNarrow'): Narrow.probNarrow = {}
if Narrow.probNarrow.has_key(Wide.width):
probNarrow = Narrow.probNarrow[Wide.width]
else:
probNarrow = estimate_frequency(Narrow, Wide.width, thresh=thresh)
Narrow.probNarrow[Wide.width] = probNarrow
p = Arith.binomialsumtail(probNarrow, len(bestWide), matchNarrow)
print '\nD= %7.3f %9.4e %8d %7d %-14s %-20s %-14s %-20s' % (Arith.nlog10(
p), probNarrow, len(bestWide), matchNarrow, A.family, A, B.family, B)
return p