def plotPatternBeyondRepeat(genomeSource1, genomeSource2, startpt1, endpt1,
startpt2, endpt2, plotRange):
f1 = open(genomeSource1, 'r')
f2 = open(genomeSource2, 'r')
pointerLocation1 = endpt1
pointerLocation2 = endpt2
windowSize = 10
distanceList = []
for index in range(plotRange):
f1.seek(pointerLocation1)
f2.seek(pointerLocation2)
str1 = f1.read(windowSize)
str2 = f2.read(windowSize)
pointerLocation1 = pointerLocation1 + windowSize
pointerLocation2 = pointerLocation2 + windowSize
distance = distanceComputeLib.hammingDistance(
str1, str2, min(windowSize, len(str1), len(str2)))
distanceList.append(distance)
plt.subplot(211)
plt.plot(range(0,
len(distanceList) * windowSize, windowSize), distanceList)
windowSize = 10
distanceList = []
pointerLocation1 = startpt1 - windowSize
pointerLocation2 = startpt2 - windowSize
# for index in range(plotRange):
# f1.seek(pointerLocation1)
# f2.seek(pointerLocation2)
# str1 = f1.read(windowSize)
# str2 = f2.read(windowSize)
# pointerLocation1 = pointerLocation1 - windowSize
# pointerLocation2 = pointerLocation2 - windowSize
# distance = hammingDistance(str1, str2, windowSize)
# distanceList.append(distance)
# plt.subplot(212)
# plt.plot(range(0,len(distanceList)*windowSize,windowSize), distanceList)
#plt.show()
f1.close()
f2.close()
def plotPatternBeyondRepeat(genomeSource1,genomeSource2, startpt1, endpt1, startpt2, endpt2,plotRange):
f1 = open(genomeSource1,'r')
f2 = open(genomeSource2,'r')
pointerLocation1 = endpt1
pointerLocation2 = endpt2
windowSize = 10
distanceList = []
for index in range(plotRange):
f1.seek(pointerLocation1)
f2.seek(pointerLocation2)
str1 = f1.read(windowSize)
str2 = f2.read(windowSize)
pointerLocation1 = pointerLocation1 + windowSize
pointerLocation2 = pointerLocation2 + windowSize
distance = distanceComputeLib.hammingDistance(str1, str2, min(windowSize,len(str1),len(str2)))
distanceList.append(distance)
plt.subplot(211)
plt.plot(range(0,len(distanceList)*windowSize,windowSize), distanceList)
windowSize = 10
distanceList = []
pointerLocation1 = startpt1 - windowSize
pointerLocation2 = startpt2 - windowSize
# for index in range(plotRange):
# f1.seek(pointerLocation1)
# f2.seek(pointerLocation2)
# str1 = f1.read(windowSize)
# str2 = f2.read(windowSize)
# pointerLocation1 = pointerLocation1 - windowSize
# pointerLocation2 = pointerLocation2 - windowSize
# distance = hammingDistance(str1, str2, windowSize)
# distanceList.append(distance)
# plt.subplot(212)
# plt.plot(range(0,len(distanceList)*windowSize,windowSize), distanceList)
#plt.show()
f1.close()
f2.close()
def effectOfInterleaving(genomeSource1, Lrepeat, Liid):
f1 = open(genomeSource1, 'r')
G = len(f1.read())
print G
oldh = Liid
totalNumberOfRounds = 100000
for numberOfRounds in range(totalNumberOfRounds):
i = random.randint(0, G - Lrepeat - Liid - 1)
j = random.randint(i + 1, G - Lrepeat - Liid)
f1.seek(i)
substring1 = f1.read(Liid)
f1.seek(j)
substring2 = f1.read(Liid)
h1 = distanceComputeLib.hammingDistance(substring1, substring2,
len(substring1))
f1.seek(i + Lrepeat)
substring1 = f1.read(Liid)
f1.seek(j + Lrepeat)
substring2 = f1.read(Liid)
h2 = distanceComputeLib.hammingDistance(substring1, substring2,
len(substring1))
h = max(h1, h2)
print i, j, h
if h < oldh:
oldh = h
print "Minimum hamming distance over ", totalNumberOfRounds, " is ", oldh, "\n"
f1.close()
def effectOfInterleaving(genomeSource1,Lrepeat, Liid):
f1 = open(genomeSource1, 'r')
G = len(f1.read())
print G
oldh = Liid
totalNumberOfRounds = 100000
for numberOfRounds in range(totalNumberOfRounds):
i = random.randint(0,G- Lrepeat - Liid -1)
j = random.randint(i+1, G- Lrepeat - Liid)
f1.seek(i)
substring1 = f1.read(Liid)
f1.seek(j)
substring2= f1.read(Liid)
h1= distanceComputeLib.hammingDistance(substring1,substring2, len(substring1))
f1.seek(i + Lrepeat)
substring1 = f1.read(Liid)
f1.seek(j+ Lrepeat)
substring2= f1.read(Liid)
h2= distanceComputeLib.hammingDistance(substring1,substring2, len(substring1))
h = max(h1,h2)
print i,j, h
if h < oldh:
oldh = h
print "Minimum hamming distance over " ,totalNumberOfRounds, " is ", oldh, "\n"
f1.close()
def checking(temp,genomeSource1,genomeSource2 ):
print temp
f1 = open(genomeSource1,'r')
f2 = open(genomeSource2,'r')
f1.seek(temp[0]-1)
f2.seek(temp[1]-1)
str1 = f1.read(temp[2])
str2 = f2.read(temp[2])
print "Hamming distance", distanceComputeLib.hammingDistance(str1,str2, len(str1))
f1.seek(temp[0]-2)
f2.seek(temp[1]-2)
str1 = f1.read(temp[2]+2)
str2 = f2.read(temp[2]+2)
print "Hamming distance", distanceComputeLib.hammingDistance(str1,str2, len(str1))
f1.close()
f2.close()
def reportPatternBeyondRepeat(genomeSource1, genomeSource2, startpt1, endpt1,
startpt2, endpt2, plotRange, outputResult):
Gchecker = open(genomeSource1, 'r')
G = len(Gchecker.read())
print G
Gchecker.close()
f1 = open(genomeSource1, 'r')
f2 = open(genomeSource2, 'r')
pointerLocation1 = endpt1
pointerLocation2 = endpt2
windowSize = 10
distanceList = []
for index in range(plotRange):
if pointerLocation1 < G and pointerLocation2 < G:
f1.seek(pointerLocation1)
f2.seek(pointerLocation2)
str1 = f1.read(windowSize)
str2 = f2.read(windowSize)
pointerLocation1 = pointerLocation1 + windowSize
pointerLocation2 = pointerLocation2 + windowSize
distance = distanceComputeLib.hammingDistance(
str1, str2, windowSize)
distanceList.append(distance)
f = open(outputResult, 'w')
for eachitem in distanceList:
f.write(str(eachitem) + "\n")
f.close()
f1.close()
f2.close()
def reportPatternBeyondRepeat(genomeSource1,genomeSource2, startpt1, endpt1, startpt2, endpt2,plotRange,outputResult):
Gchecker = open(genomeSource1,'r')
G = len(Gchecker.read())
print G
Gchecker.close()
f1 = open(genomeSource1,'r')
f2 = open(genomeSource2,'r')
pointerLocation1 = endpt1
pointerLocation2 = endpt2
windowSize = 10
distanceList = []
for index in range(plotRange):
if pointerLocation1 < G and pointerLocation2 < G:
f1.seek(pointerLocation1)
f2.seek(pointerLocation2)
str1 = f1.read(windowSize)
str2 = f2.read(windowSize)
pointerLocation1 = pointerLocation1 + windowSize
pointerLocation2 = pointerLocation2 + windowSize
distance = distanceComputeLib.hammingDistance(str1, str2, windowSize)
distanceList.append(distance)
f = open(outputResult,'w')
for eachitem in distanceList:
f.write(str(eachitem) + "\n" )
f.close()
f1.close()
f2.close()
def findapproxrepeatLength(filename1, filename2, start1, start2,
lengthOfExactRepeat):
f1 = open(filename1, 'r')
f2 = open(filename2, 'r')
totalNumberOfError = 0
windowSize = 100
threshold = 25
### Decision rule : if > 50 error in the latest window of 100, then stop counting
numberOfError = 0
### Compute the RHS
f1.seek(start1 + lengthOfExactRepeat - windowSize - 1)
f2.seek(start2 + lengthOfExactRepeat - windowSize - 1)
temp1 = f1.read(windowSize)
temp2 = f2.read(windowSize)
lastPosition1 = start1 + lengthOfExactRepeat - windowSize - 1
lastPosition2 = start2 + lengthOfExactRepeat - windowSize - 1
print "CheckPoint 1 : ", distanceComputeLib.hammingDistance(
temp1, temp2, len(temp1))
numberOfError = distanceComputeLib.hammingDistance(temp1, temp2,
len(temp1))
totalNumberOfError = totalNumberOfError + numberOfError
while (numberOfError < threshold):
f1.seek(lastPosition1)
char1 = f1.read(1)
f2.seek(lastPosition2)
char2 = f2.read(1)
if char1 != char2:
numberOfError = numberOfError - 1
f1.seek(lastPosition1 + windowSize)
f2.seek(lastPosition2 + windowSize)
char1 = f1.read(1)
char2 = f2.read(1)
if char1 != char2:
numberOfError = numberOfError + 1
totalNumberOfError = totalNumberOfError + 1
lastPosition1 = lastPosition1 + 1
lastPosition2 = lastPosition2 + 1
endIndex1 = lastPosition1 + windowSize - int(threshold * 1.3333)
endIndex2 = lastPosition2 + windowSize - int(threshold * 1.3333)
numberOfError = 0
### Compute the LHS
f1.seek(start1)
f2.seek(start2)
temp1 = f1.read(windowSize)
temp2 = f2.read(windowSize)
lastPosition1 = start1 + windowSize - 1
lastPosition2 = start2 + windowSize - 1
numberOfError = distanceComputeLib.hammingDistance(temp1, temp2,
len(temp1))
print "checkPoint2 :", distanceComputeLib.hammingDistance(
temp1, temp2, len(temp1))
totalNumberOfError = totalNumberOfError + numberOfError
while (numberOfError < threshold):
f1.seek(lastPosition1)
char1 = f1.read(1)
f2.seek(lastPosition2)
char2 = f2.read(1)
if char1 != char2:
numberOfError = numberOfError - 1
f1.seek(lastPosition1 - windowSize)
f2.seek(lastPosition2 - windowSize)
char1 = f1.read(1)
char2 = f2.read(1)
if char1 != char2:
numberOfError = numberOfError + 1
totalNumberOfError = totalNumberOfError + 1
lastPosition1 = lastPosition1 - 1
lastPosition2 = lastPosition2 - 1
startIndex1 = lastPosition1 - windowSize + int(threshold * 1.3333)
startIndex2 = lastPosition2 - windowSize + int(threshold * 1.3333)
lapprox = endIndex1 - startIndex1
print lapprox, totalNumberOfError, threshold, lengthOfExactRepeat
mutationRate = (totalNumberOfError - 2 * threshold) / float(lapprox)
if mutationRate == 0:
mutationRate = 1 / float(lapprox)
print "mutationRate", mutationRate, (totalNumberOfError - 2 * threshold)
if startIndex1 > startIndex2:
dummy = startIndex1
startIndex1 = startIndex2
startIndex2 = dummy
if lapprox <= lengthOfExactRepeat:
return start1, start2, lengthOfExactRepeat + 1, 1 / float(
lengthOfExactRepeat)
else:
return startIndex1, startIndex2, lapprox, mutationRate
def findapproxrepeatLength(filename1, filename2, start1, start2, lengthOfExactRepeat):
f1 = open(filename1, 'r')
f2 = open(filename2, 'r')
totalNumberOfError = 0
windowSize = 100
threshold = 25
### Decision rule : if > 50 error in the latest window of 100, then stop counting
numberOfError= 0
### Compute the RHS
f1.seek(start1+ lengthOfExactRepeat- windowSize-1)
f2.seek(start2+ lengthOfExactRepeat- windowSize-1)
temp1 = f1.read(windowSize)
temp2 = f2.read(windowSize)
lastPosition1 = start1+ lengthOfExactRepeat- windowSize-1
lastPosition2 = start2+ lengthOfExactRepeat- windowSize-1
print "CheckPoint 1 : ", distanceComputeLib.hammingDistance(temp1, temp2, len(temp1))
numberOfError = distanceComputeLib.hammingDistance(temp1, temp2, len(temp1))
totalNumberOfError = totalNumberOfError + numberOfError
while (numberOfError < threshold):
f1.seek(lastPosition1)
char1 = f1.read(1)
f2.seek(lastPosition2)
char2 = f2.read(1)
if char1 != char2 :
numberOfError = numberOfError - 1
f1.seek(lastPosition1 + windowSize)
f2.seek(lastPosition2 + windowSize)
char1 = f1.read(1)
char2 = f2.read(1)
if char1 != char2:
numberOfError = numberOfError + 1
totalNumberOfError= totalNumberOfError + 1
lastPosition1 = lastPosition1 + 1
lastPosition2 = lastPosition2 + 1
endIndex1 = lastPosition1 + windowSize - int(threshold* 1.3333)
endIndex2 = lastPosition2 + windowSize - int(threshold* 1.3333)
numberOfError= 0
### Compute the LHS
f1.seek(start1)
f2.seek(start2)
temp1 = f1.read(windowSize)
temp2 = f2.read(windowSize)
lastPosition1 = start1 + windowSize -1
lastPosition2 = start2 + windowSize -1
numberOfError = distanceComputeLib.hammingDistance(temp1, temp2, len(temp1))
print "checkPoint2 :", distanceComputeLib.hammingDistance(temp1, temp2, len(temp1))
totalNumberOfError = totalNumberOfError + numberOfError
while (numberOfError < threshold):
f1.seek(lastPosition1)
char1 = f1.read(1)
f2.seek(lastPosition2)
char2 = f2.read(1)
if char1 != char2 :
numberOfError = numberOfError - 1
f1.seek(lastPosition1 - windowSize)
f2.seek(lastPosition2 - windowSize)
char1 = f1.read(1)
char2 = f2.read(1)
if char1 != char2:
numberOfError = numberOfError + 1
totalNumberOfError = totalNumberOfError +1
lastPosition1 = lastPosition1 - 1
lastPosition2 = lastPosition2 - 1
startIndex1 = lastPosition1 - windowSize + int(threshold* 1.3333)
startIndex2 = lastPosition2 - windowSize + int(threshold* 1.3333)
lapprox = endIndex1-startIndex1
print lapprox, totalNumberOfError ,threshold,lengthOfExactRepeat
mutationRate = (totalNumberOfError - 2* threshold )/float(lapprox)
if mutationRate == 0:
mutationRate = 1/float(lapprox)
print "mutationRate", mutationRate, (totalNumberOfError - 2* threshold )
if startIndex1 > startIndex2 :
dummy = startIndex1
startIndex1 = startIndex2
startIndex2 = dummy
if lapprox <= lengthOfExactRepeat:
return start1, start2, lengthOfExactRepeat+1, 1/ float(lengthOfExactRepeat)
else:
return startIndex1, startIndex2, lapprox, mutationRate
