def testIter(genomeLen, numReads, readLen, mutFreq, errors, errorFreq, prop=1):
# Initialize the reference gene
t = ['$']
for i in range(genomeLen):
t = [random.choice(['A', 'C', 'T', 'G'])] + t
# constuct the fm index
alphabet = ['$', 'A', 'C', 'G', 'T']
b = 5
fm = bwt.constructFM(t, b, alphabet)
startsOrig = []
for i in range(numReads):
start = random.randint(0, genomeLen - readLen - 1)
startsOrig += [start]
starts = startsOrig[:]
# mutate the reference genome to get new genome
t2 = t[:]
for i in range(int(round(mutFreq * genomeLen))):
base = random.randint(0, len(t2) - 1)
mutType = random.randint(0, 2)
# substitution
if mutType == 0:
t2[base] = random.choice(['A', 'C', 'T', 'G'])
# insertion
elif mutType == 1:
t2 = t2[:base] + [random.choice(['A', 'C', 'T', 'G'])] + t2[base:]
for s in xrange(len(starts)):
if starts[s] >= base:
starts[s] += 1
# deletion
else:
t2 = t2[:base] + t2[base + 1:]
for s in xrange(len(starts)):
if starts[s] >= base:
starts[s] -= 1
# generate reads from new genome
reads = []
for i in xrange(len(starts)):
reads += [t2[starts[i]:starts[i] + readLen]]
# introduce substitution errors with 1% chance at each base
for j in xrange(readLen):
if random.random() < errorFreq:
reads[i][j] = random.choice(['A', 'C', 'T', 'G'])
return iu.iterativeUpdateError(fm, b, alphabet, reads, startsOrig, errors,
5, True, readLen, genomeLen, prop)
def testIter(genomeLen, numReads, readLen, mutFreq, errors, errorFreq):
# Initialize the reference gene
t = ['$']
for i in range(genomeLen):
t = [random.choice(['A', 'C', 'T', 'G'])] + t
# constuct the fm index
alphabet = ['$', 'A', 'C', 'G', 'T']
b = 5
fm = bwt.constructFM(t, b, alphabet)
startsOrig = []
for i in range(numReads):
start = random.randint(0, genomeLen-readLen-1)
startsOrig += [start]
starts = startsOrig[:]
# mutate the reference genome to get new genome
t2 = t[:]
for i in range(int(round(mutFreq*genomeLen))):
base = random.randint(2*readLen, len(t2)-2*readLen)
mutType = random.randint(0,2)
# substitution
if mutType == 0:
t2[base] = random.choice(['A', 'C', 'T', 'G'])
# insertion
elif mutType == 1:
t2 = t2[:base] + [random.choice(['A', 'C', 'T', 'G'])] + t2[base:]
for s in xrange(len(starts)):
if starts[s] >= base:
starts[s] += 1
# deletion
else:
t2 = t2[:base] + t2[base+1:]
for s in xrange(len(starts)):
if starts[s] >= base:
starts[s] -= 1
# generate reads from new genome
reads = []
for i in xrange(len(starts)):
reads += [t2[starts[i]:starts[i]+readLen]]
# introduce substitution errors with 1% chance at each base
for j in xrange(readLen):
if random.random() < errorFreq:
reads[i][j] = random.choice(['A', 'C', 'T', 'G'])
return iu.iterativeUpdateError(fm, b, alphabet, reads, startsOrig, errors, 5, True, readLen, genomeLen)
def iterEM(genomeLen, numReads, readLen, mutFreq, errors, errorFreq):
''' Prop = proportion of reads to contribute to mutations '''
# Initialize the reference gene
t = ['$']
for i in range(genomeLen):
t = [random.choice(['A', 'C', 'T', 'G'])] + t
# constuct the fm index
alphabet = ['$', 'A', 'C', 'G', 'T']
b = 5
fm = bwt.constructFM(t, b, alphabet)
startsOrig = []
for i in range(numReads):
start = random.randint(0, genomeLen-readLen-1)
startsOrig += [start]
starts = startsOrig[:]
# mutate the reference genome to get new genome
t2 = t[:]
for i in range(int(round(mutFreq*genomeLen))):
base = random.randint(0, len(t2)-1)
mutType = random.randint(0,2)
# substitution
if mutType == 0:
t2[base] = random.choice(['A', 'C', 'T', 'G'])
# insertion
elif mutType == 1:
t2 = t2[:base] + [random.choice(['A', 'C', 'T', 'G'])] + t2[base:]
for s in xrange(len(starts)):
if starts[s] >= base:
starts[s] += 1
# deletion
else:
t2 = t2[:base] + t2[base+1:]
for s in xrange(len(starts)):
if starts[s] >= base:
starts[s] -= 1
# generate reads from new genome
reads = []
for i in xrange(len(starts)):
reads += [t2[starts[i]:starts[i]+readLen]]
# introduce substitution errors with 1% chance at each base
for j in xrange(readLen):
if random.random() < errorFreq:
reads[i][j] = random.choice(['A', 'C', 'T', 'G'])
tempReads = reads[:]
tempFM = copy.deepcopy(fm)
tempStarts = startsOrig[:]
accuracyOrig, sizeOrig = iterativeEM.iterativeEM(tempFM, b, alphabet, tempReads, tempStarts, errors, 5, readLen, genomeLen, 1)
tempFM = copy.deepcopy(fm)
tempReads = reads[:]
tempStarts = startsOrig[:]
accuracyRed, sizeRed = iterativeEM.iterativeEM(tempFM, b, alphabet, tempReads, tempStarts, errors, 5, readLen, genomeLen, 0.1)
tempFM = copy.deepcopy(fm)
tempReads = reads[:]
tempStarts = startsOrig[:]
accuracyDist1, sizeDist1 = iterativeEMDist.iterativeEMDist(tempFM, b, alphabet, tempReads, tempStarts, errors, 5, readLen, genomeLen, 1, 1)
tempFM = copy.deepcopy(fm)
tempReads = reads[:]
tempStarts = startsOrig[:]
accuracyDist2, sizeDist2 = iterativeEMDist.iterativeEMDist(tempFM, b, alphabet, tempReads, tempStarts, errors, 5, readLen, genomeLen, 2, 1)
tempFM = copy.deepcopy(fm)
tempReads = reads[:]
tempStarts = startsOrig[:]
accuracyDistChunk2, sizeDistChunk2 = iterativeEMDist.iterativeEMDist(tempFM, b, alphabet, tempReads, tempStarts, errors, 5, readLen, genomeLen, 2, 50)
return (accuracyOrig, accuracyRed, accuracyDist1, accuracyDist2, accuracyDistChunk2), (sizeOrig, sizeRed, sizeDist1, sizeDist2, sizeDistChunk2)
def countCorrect(genomeLen, numReads, readLen, mutFreq, errors):
# Initialize the reference gene
t = ['$']
for i in range(genomeLen):
t = [random.choice(['A', 'C', 'T', 'G'])] + t
# constuct the fm index
alphabet = ['$', 'A', 'C', 'G', 'T']
b = 5
fm = bwt.constructFM(t, b, alphabet)
startsOrig = []
for i in range(numReads):
start = random.randint(0, genomeLen-readLen-1)
startsOrig += [start]
starts = startsOrig[:]
# mutate the reference genome to get new genome
t2 = t[:]
for i in range(int(round(mutFreq*genomeLen))):
base = random.randint(0, len(t2)-1)
mutType = random.randint(0,2)
# substitution
if mutType == 0:
t2[base] = random.choice(['A', 'C', 'T', 'G'])
# insertion
elif mutType == 1:
t2 = t2[:base] + [random.choice(['A', 'C', 'T', 'G'])] + t2[base:]
for s in xrange(len(starts)):
if starts[s] >= base:
starts[s] += 1
# deletion
else:
t2 = t2[:base] + t2[base+1:]
for s in xrange(len(starts)):
if starts[s] >= base:
starts[s] -= 1
# generate reads from new genome
reads = []
for i in xrange(len(starts)):
reads += [t2[starts[i]:starts[i]+readLen]]
# Match reads against t2
correct = 0
incorrect = 0
for i in range(numReads):
#print 'Read ' + str(i+1)
#print ' ' + ''.join(reads[i])
m = bwt.findApproximate(fm, b, alphabet, ''.join(reads[i]), errors)
found = False
#print 'Searching for ' + str(startsOrig[i])
#print m
#print ''.join(reads[i])
#print ''.join(t[starts[i]:starts[i]+readLen])
for j in xrange(-errors, errors+1):
if startsOrig[i]+j in m.keys() and not found:
#print 'Found!\n'
correct += 1
found = True
if not found:
#print 'Not found\n'
incorrect += 1
print ' Accuracy: ' + str(correct) + ' / ' + str(correct+incorrect) + ' = ' + str(float(correct)/(incorrect+correct))
return float(correct) / (incorrect+correct)
#!/usr/bin/env python3
import bwt
import random
alpha = ['A', 'C', 'G', 'T']
t = ['$'] + [random.choice(alpha) for x in range(10000)]
alphabet = alpha + ['$']
b = 5
print('OldRow, First, Checkpt, NewRow, SA, Checkpt, Reord')
fm = bwt.constructFM(t, b, alphabet)
bwt.insert(fm, b, alphabet, 1, random.choice(alpha), timing=True)
bwt.insert(fm, b, alphabet, 5, random.choice(alpha), timing=True)
bwt.insert(fm, b, alphabet, 10, random.choice(alpha), timing=True)
bwt.insert(fm, b, alphabet, 50, random.choice(alpha), timing=True)
bwt.insert(fm, b, alphabet, 100, random.choice(alpha), timing=True)
bwt.insert(fm, b, alphabet, 500, random.choice(alpha), timing=True)
bwt.insert(fm, b, alphabet, 1000, random.choice(alpha), timing=True)
bwt.insert(fm, b, alphabet, 5000, random.choice(alpha), timing=True)
print()
fm = bwt.constructFM(t, b, alphabet)
bwt.insert(fm, b, alphabet, 1, 'A', timing=True)
bwt.insert(fm, b, alphabet, 5, 'A', timing=True)
bwt.insert(fm, b, alphabet, 10, 'A', timing=True)
bwt.insert(fm, b, alphabet, 50, 'A', timing=True)
bwt.insert(fm, b, alphabet, 100, 'A', timing=True)
bwt.insert(fm, b, alphabet, 500, 'A', timing=True)
bwt.insert(fm, b, alphabet, 1000, 'A', timing=True)
bwt.insert(fm, b, alphabet, 5000, 'A', timing=True)
bwt.insert(fm, b, alphabet, 10000, 'A', timing=True)
print()
def iterEM(genomeLen, numReads, readLen, mutFreq, errors, errorFreq):
''' Prop = proportion of reads to contribute to mutations '''
# Initialize the reference gene
t = ['$']
for i in range(genomeLen):
t = [random.choice(['A', 'C', 'T', 'G'])] + t
# constuct the fm index
alphabet = ['$', 'A', 'C', 'G', 'T']
b = 5
fm = bwt.constructFM(t, b, alphabet)
startsOrig = []
for i in range(numReads):
start = random.randint(0, genomeLen - readLen - 1)
startsOrig += [start]
starts = startsOrig[:]
# mutate the reference genome to get new genome
t2 = t[:]
for i in range(int(round(mutFreq * genomeLen))):
base = random.randint(0, len(t2) - 1)
mutType = random.randint(0, 2)
# substitution
if mutType == 0:
t2[base] = random.choice(['A', 'C', 'T', 'G'])
# insertion
elif mutType == 1:
t2 = t2[:base] + [random.choice(['A', 'C', 'T', 'G'])] + t2[base:]
for s in xrange(len(starts)):
if starts[s] >= base:
starts[s] += 1
# deletion
else:
t2 = t2[:base] + t2[base + 1:]
for s in xrange(len(starts)):
if starts[s] >= base:
starts[s] -= 1
# generate reads from new genome
reads = []
for i in xrange(len(starts)):
reads += [t2[starts[i]:starts[i] + readLen]]
# introduce substitution errors with 1% chance at each base
for j in xrange(readLen):
if random.random() < errorFreq:
reads[i][j] = random.choice(['A', 'C', 'T', 'G'])
tempReads = reads[:]
tempFM = copy.deepcopy(fm)
tempStarts = startsOrig[:]
accuracyOrig, sizeOrig = iterativeEM.iterativeEM(tempFM, b, alphabet,
tempReads, tempStarts,
errors, 5, readLen,
genomeLen, 1)
tempFM = copy.deepcopy(fm)
tempReads = reads[:]
tempStarts = startsOrig[:]
accuracyRed, sizeRed = iterativeEM.iterativeEM(tempFM, b, alphabet,
tempReads, tempStarts,
errors, 5, readLen,
genomeLen, 0.1)
tempFM = copy.deepcopy(fm)
tempReads = reads[:]
tempStarts = startsOrig[:]
accuracyDist1, sizeDist1 = iterativeEMDist.iterativeEMDist(
tempFM, b, alphabet, tempReads, tempStarts, errors, 5, readLen,
genomeLen, 1, 1)
tempFM = copy.deepcopy(fm)
tempReads = reads[:]
tempStarts = startsOrig[:]
accuracyDist2, sizeDist2 = iterativeEMDist.iterativeEMDist(
tempFM, b, alphabet, tempReads, tempStarts, errors, 5, readLen,
genomeLen, 2, 1)
tempFM = copy.deepcopy(fm)
tempReads = reads[:]
tempStarts = startsOrig[:]
accuracyDistChunk2, sizeDistChunk2 = iterativeEMDist.iterativeEMDist(
tempFM, b, alphabet, tempReads, tempStarts, errors, 5, readLen,
genomeLen, 2, 50)
return (accuracyOrig, accuracyRed, accuracyDist1, accuracyDist2,
accuracyDistChunk2), (sizeOrig, sizeRed, sizeDist1, sizeDist2,
sizeDistChunk2)
def iterEM(genomeLen, numReads, readLen, mutFreq, errors, errorFreq):
""" Prop = proportion of reads to contribute to mutations """
# Initialize the reference gene
t = ["$"]
for i in range(genomeLen):
t = [random.choice(["A", "C", "T", "G"])] + t
# constuct the fm index
alphabet = ["$", "A", "C", "G", "T"]
b = 5
fm = bwt.constructFM(t, b, alphabet)
# initialize starting points for reads
# reads are twice as likely to originate from the first half of the genome
startsOrig = []
for i in range(numReads):
start = random.randint(0, round(1.5 * (genomeLen - readLen - 1)))
if start > genomeLen / 2:
start -= genomeLen / 2
startsOrig += [int(start)]
starts = startsOrig[:]
# mutate the reference genome to get new genome
t2 = t[:]
for i in range(int(round(mutFreq * genomeLen))):
base = random.randint(0, len(t2) - 1)
mutType = random.randint(0, 2)
# substitution
if mutType == 0:
t2[base] = random.choice(["A", "C", "T", "G"])
# insertion
elif mutType == 1:
t2 = t2[:base] + [random.choice(["A", "C", "T", "G"])] + t2[base:]
for s in xrange(len(starts)):
if starts[s] >= base:
starts[s] += 1
# deletion
else:
t2 = t2[:base] + t2[base + 1 :]
for s in xrange(len(starts)):
if starts[s] >= base:
starts[s] -= 1
# generate reads from new genome
reads = []
for i in xrange(len(starts)):
reads += [t2[starts[i] : starts[i] + readLen]]
# introduce substitution errors with 1% chance at each base
for j in xrange(readLen):
if random.random() < errorFreq:
reads[i][j] = random.choice(["A", "C", "T", "G"])
tempReads = reads[:]
tempFM = copy.deepcopy(fm)
tempStarts = startsOrig[:]
accuracyOrig, sizeOrig = iterativeEM.iterativeEM(
tempFM, b, alphabet, tempReads, tempStarts, errors, 5, readLen, genomeLen, 1
)
tempFM = copy.deepcopy(fm)
tempReads = reads[:]
tempStarts = startsOrig[:]
accuracyRed, sizeRed = iterativeEM.iterativeEM(
tempFM, b, alphabet, tempReads, tempStarts, errors, 5, readLen, genomeLen, 0.1
)
tempFM = copy.deepcopy(fm)
tempReads = reads[:]
tempStarts = startsOrig[:]
accuracyChunk50, sizeChunk50 = iterativeEMDist.iterativeEMDist(
tempFM, b, alphabet, tempReads, tempStarts, errors, 5, readLen, genomeLen, 2, 50
)
tempFM = copy.deepcopy(fm)
tempReads = reads[:]
tempStarts = startsOrig[:]
accuracyChunk100, sizeChunk100 = iterativeEMDist.iterativeEMDist(
tempFM, b, alphabet, tempReads, tempStarts, errors, 5, readLen, genomeLen, 2, 100
)
return (
(accuracyOrig, accuracyRed, accuracyChunk50, accuracyChunk100),
(sizeOrig, sizeRed, sizeChunk50, sizeChunk100),
)
length = lengths[i]
numRuns = runLens[i]
for n in xrange(numRuns):
# Generate a long random string of random length
t = ['$']
for i in range(length):
t = [random.choice(['A', 'C', 'T', 'G'])] + t
alphabet = ['$', 'A', 'C', 'G', 'T']
b = 50
# Construct the fm index
startBuild = time.time()
fm = bwt.constructFM(t, b, alphabet)
buildTime += time.time() - startBuild
letters = set(t)
letters.remove('$')
# Substitution of a character
subId = random.randint(0,length-1)
newChar = random.choice(list(letters))
t2 = t[:subId] + [newChar] + t[subId+1:]
startUpdate = time.time()
fm_new = bwt.substitute(fm, b, alphabet, subId, newChar)
timeUpdate = time.time() - startUpdate
updateTimes[0] += timeUpdate
def countCorrect(genomeLen, numReads, readLen, mutFreq, errors):
# Initialize the reference gene
t = ['$']
for i in range(genomeLen):
t = [random.choice(['A', 'C', 'T', 'G'])] + t
# constuct the fm index
alphabet = ['$', 'A', 'C', 'G', 'T']
b = 5
fm = bwt.constructFM(t, b, alphabet)
startsOrig = []
for i in range(numReads):
start = random.randint(0, genomeLen - readLen - 1)
startsOrig += [start]
starts = startsOrig[:]
# mutate the reference genome to get new genome
t2 = t[:]
for i in range(int(round(mutFreq * genomeLen))):
base = random.randint(0, len(t2) - 1)
mutType = random.randint(0, 2)
# substitution
if mutType == 0:
t2[base] = random.choice(['A', 'C', 'T', 'G'])
# insertion
elif mutType == 1:
t2 = t2[:base] + [random.choice(['A', 'C', 'T', 'G'])] + t2[base:]
for s in xrange(len(starts)):
if starts[s] >= base:
starts[s] += 1
# deletion
else:
t2 = t2[:base] + t2[base + 1:]
for s in xrange(len(starts)):
if starts[s] >= base:
starts[s] -= 1
# generate reads from new genome
reads = []
for i in xrange(len(starts)):
reads += [t2[starts[i]:starts[i] + readLen]]
# Match reads against t2
correct = 0
incorrect = 0
for i in range(numReads):
#print 'Read ' + str(i+1)
#print ' ' + ''.join(reads[i])
m = bwt.findApproximate(fm, b, alphabet, ''.join(reads[i]), errors)
found = False
#print 'Searching for ' + str(startsOrig[i])
#print m
#print ''.join(reads[i])
#print ''.join(t[starts[i]:starts[i]+readLen])
for j in xrange(-errors, errors + 1):
if startsOrig[i] + j in m.keys() and not found:
#print 'Found!\n'
correct += 1
found = True
if not found:
#print 'Not found\n'
incorrect += 1
print ' Accuracy: ' + str(correct) + ' / ' + str(
correct + incorrect) + ' = ' + str(
float(correct) / (incorrect + correct))
return float(correct) / (incorrect + correct)