def ECUnitTest(Nin,G, Lin, foldername = "", bridgingDepth = 20, msaWidth = 20 ):
dummyParameters = logging.parameterObj()
dummyParameters.bridgingDepth = bridgingDepth
dummyParameters.msaWidth = msaWidth
dummyParameters.N, dummyParameters.G, dummyParameters.L, dummyParameters.p = Nin, G,Lin, 0.015
dummyParameters.indel = True
dummyParameters.defaultFolder = foldername
dummyParameters.threshold = 5
dummyParameters.liid = 48
snpRate, typeOfGen, detail = 0.001 ,'m', "500-200-50"
G,N,L = dummyParameters.G, dummyParameters.N, dummyParameters.L,
motherGen, reads, noisyReads = logging.rawDataLoad(foldername+"UnitTest",G,N,L, "dn")
f2= logging.fmapfusedLoad(foldername+'clusteredGroup2.csv')
G2 = logging.loadGraph(foldername+'basicMapping.csv', foldername+'seqMapping.txt', 'simple')
checkCondensingBasic(G2, [G2[0]], "simple")
G3 = bridgeResolve.resolveRepeats(f2,G2,dummyParameters)
checkCondensingBasic(G3, [G3[0]], "MB")
G4 = alignmentBridge.MSAresolve(f2, G3, noisyReads, snpRate,dummyParameters)
#G4 = G3
#checkCondensingBasic(G4, [G4[0]], "MB")
recovSeq = eulerCycle.findEC(G4)
recovGen = readAns.reportRecovSeq(recovSeq, f2, noisyReads,dummyParameters)
numMistakes, success = compare.subAlignCompare(recovGen, motherGen,dummyParameters)
return numMistakes, success
def dataGenUnitTest():
print "dataGenUnitTest"
dummyParameters = logging.parameterObj()
dummyParameters.N, dummyParameters.G, dummyParameters.L, dummyParameters.p, typeOfGen, detail = 100, 10000,100, 0.01, 't', "500"
dummyParameters.indel = True
motherGen, reads, noisyReads = dataGen.generateData(typeOfGen,detail,dummyParameters)
def batchProcessingGenomeSegTest():
print "Batch Processing LNK Test"
headerName = "largeScaleTest/"
os.system("mkdir " + headerName)
logging.savingGenomeSegmentFile(headerName)
listOfNLKDataPts = logging.loadingGenomeSegmentFile(headerName)
numberOfRounds = 1
for testPoint, roundNum in zip(listOfNLKDataPts,
range(len(listOfNLKDataPts))):
folderName = headerName + "sample_point_" + str(roundNum)
os.system("mkdir " + folderName)
[
G, N, L, p, epsilon, K, liid, threshold, NKcov, Nbridge, Ncov,
ratio, numberOfClusterRounds, brachingDepth, bridgingDepth,
msaWidth, clusterRounds, fingerPrint, clusterRatio, startindex,
endindex
] = testPoint
print "G", G
parameterRobot = logging.parameterObj(
G, N, L, p, epsilon, K, liid, threshold, NKcov, Nbridge, Ncov,
ratio, numberOfClusterRounds, brachingDepth, bridgingDepth,
msaWidth, folderName, clusterRounds, fingerPrint, clusterRatio)
snpRate, typeOfGen, detail = 0.001, 'd', "genome.fasta-" + str(
startindex) + "-" + str(endindex)
parameterRobot.indel = True
temptime = time.time()
batchProcessingUnitTest(numberOfRounds, parameterRobot, snpRate,
typeOfGen, detail)
print "time per sample point ", time.time() - temptime
def batchProcessingLNKTest():
print "Batch Processing LNK Test"
headerName = "synthetic_reads/"
os.system("mkdir " + headerName)
logging.savingLNKFile(headerName)
listOfNLKDataPts = logging.loadingLNKFile(headerName)
numberOfRounds = 1
listOfNLKDataPts = [listOfNLKDataPts[0]]
for testPoint, roundNum in zip(listOfNLKDataPts,
range(len(listOfNLKDataPts))):
folderName = headerName + "sample_point_" + str(roundNum)
os.system("mkdir " + folderName)
snpRate, typeOfGen, detail = 0.001, 'm', "500-200-50"
[
G, N, L, p, epsilon, K, liid, threshold, NKcov, Nbridge, Ncov,
ratio, numberOfClusterRounds, brachingDepth, bridgingDepth,
msaWidth, clusterRounds, fingerPrint, clusterRatio
] = testPoint
parameterRobot = logging.parameterObj(
G, N, L, p, epsilon, K, liid, threshold, NKcov, Nbridge, Ncov,
ratio, numberOfClusterRounds, brachingDepth, bridgingDepth,
msaWidth, folderName, clusterRounds, fingerPrint, clusterRatio)
parameterRobot.indel = True
batchProcessingUnitTest(numberOfRounds, parameterRobot, snpRate,
typeOfGen, detail)
def branchClearingUnitTest(G,
N,
L,
K,
liid,
threshold,
foldername="",
branchingDepth=20):
dummyParameters = logging.parameterObj()
dummyParameters.defaultFolder = foldername
dummyParameters.brachingDepth = branchingDepth
dummyParameters.K, dummyParameters.liid, dummyParameters.threshold = K, liid, threshold
dummyParameters.G, dummyParameters.N, dummyParameters.L = G, N, L
motherGen, reads, noisyReads = logging.rawDataLoad(foldername + "UnitTest",
G, N, L, "dn")
returnfmapping = logging.fmappingLoad(foldername + 'clusteredGroup.csv')
G1, startList, fmapping = graphForm.getSeqGraph(returnfmapping, noisyReads,
dummyParameters)
#checkCondensingBasic(G1, startList, "simple")
returnfmapping, G1 = branchClear.clearResidual(returnfmapping, G1,
dummyParameters)
G2 = G1
graphForm.debugSeqGraph(G2)
#G2 = G1
checkCondensingBasic2(G2, [G2[0]], "simple")
def branchClearingUnitTest(G, N, L,K, liid, threshold, foldername = "",branchingDepth= 20):
dummyParameters = logging.parameterObj()
dummyParameters.defaultFolder = foldername
dummyParameters.brachingDepth = branchingDepth
dummyParameters.K, dummyParameters.liid, dummyParameters.threshold = K, liid, threshold
dummyParameters.G, dummyParameters.N, dummyParameters.L = G, N, L
motherGen, reads, noisyReads = logging.rawDataLoad(foldername+"UnitTest",G,N,L, "dn")
returnfmapping= logging.fmappingLoad(foldername+'clusteredGroup.csv')
G1,startList, fmapping = graphForm.getSeqGraph(returnfmapping,noisyReads, dummyParameters)
#checkCondensingBasic(G1, startList, "simple")
returnfmapping, G1= branchClear.clearResidual(returnfmapping,G1,dummyParameters)
G2 = G1
graphForm.debugSeqGraph(G2)
#G2 = G1
checkCondensingBasic2(G2, [G2[0]], "simple")
def dataGenUnitTest():
print "dataGenUnitTest"
dummyParameters = logging.parameterObj()
dummyParameters.N, dummyParameters.G, dummyParameters.L, dummyParameters.p, typeOfGen, detail = 100, 10000, 100, 0.01, 't', "500"
dummyParameters.indel = True
motherGen, reads, noisyReads = dataGen.generateData(
typeOfGen, detail, dummyParameters)
def overallTestRun():
#"oneLine.fasta-0-1440371"
G, N, L, p, epsilon, K, liid, threshold,NKcov, Nbridge, Ncov, ratio, numberOfClusterRounds,brachingDepth,bridgingDepth,msaWidth,folderName =10000 ,83 , 1189, 0.01 , 0.1 , 600 , 32, 8 , 508 , 377 , 417 , 1.21822542 , 0, 0, 0 , 0 , ""
parameterRobot = logging.parameterObj(G, N, L, p, epsilon, K, liid, threshold,NKcov, Nbridge, Ncov, ratio, numberOfClusterRounds,brachingDepth,bridgingDepth,msaWidth,folderName )
snpRate, typeOfGen, detail = 0.001 ,'d', "genome.fasta-50000-60000"
parameterRobot.clusterRounds , parameterRobot.fingerPrint, parameterRobot.clusterRatio = 2 , 6, 1
#snpRate, typeOfGen , detail = 0.001,'m', "500-200-50"
numMistakes, success = assemblerMain.runAssembler(snpRate, typeOfGen, detail, parameterRobot)
return numMistakes, success
def graphFormUnitTest2(N, G, L, folderName = ""):
dummyParameters = logging.parameterObj()
dummyParameters.defaultFolder = folderName
returnfmapping= logging.fmappingLoad(dummyParameters.defaultFolder+'clusteredGroup.csv')
dummyParameters.N, dummyParameters.G, dummyParameters.L, dummyParameters.p, typeOfGen, detail = N, G, L, 0.015, 'm', "500-200-50"
motherGen, reads, noisyReads = logging.rawDataLoad(dummyParameters.defaultFolder+"UnitTest",dummyParameters.G,dummyParameters.N,dummyParameters.L, "dn")
G1,startList,fmapping = graphForm.getSeqGraph(returnfmapping,noisyReads, dummyParameters )
def clusteringTestingOfK(G, N, L, folderName, K, threshold, liid):
motherGen, reads, noisyReads = logging.rawDataLoad(folderName + "UnitTest",G,N,L,'a')
dummyParameters = logging.parameterObj()
dummyParameters.brachingDepth = 20
dummyParameters.clusterRounds , dummyParameters.fingerPrint, dummyParameters.clusterRatio = 2, 6, 2
dummyParameters.N, dummyParameters.L, dummyParameters.K, dummyParameters.G, dummyParameters.threshold, dummyParameters.liid = N, L, K, G, threshold, liid
cluster.groupNoisyKmers(noisyReads,dummyParameters, 'fast' )
def clusteringTestingOfK(G, N, L, folderName, K, threshold, liid):
motherGen, reads, noisyReads = logging.rawDataLoad(folderName + "UnitTest",
G, N, L, 'a')
dummyParameters = logging.parameterObj()
dummyParameters.brachingDepth = 20
dummyParameters.clusterRounds, dummyParameters.fingerPrint, dummyParameters.clusterRatio = 2, 6, 2
dummyParameters.N, dummyParameters.L, dummyParameters.K, dummyParameters.G, dummyParameters.threshold, dummyParameters.liid = N, L, K, G, threshold, liid
cluster.groupNoisyKmers(noisyReads, dummyParameters, 'fast')
def graphFormUnitTest2(N, G, L, folderName=""):
dummyParameters = logging.parameterObj()
dummyParameters.defaultFolder = folderName
returnfmapping = logging.fmappingLoad(dummyParameters.defaultFolder +
'clusteredGroup.csv')
dummyParameters.N, dummyParameters.G, dummyParameters.L, dummyParameters.p, typeOfGen, detail = N, G, L, 0.015, 'm', "500-200-50"
motherGen, reads, noisyReads = logging.rawDataLoad(
dummyParameters.defaultFolder + "UnitTest", dummyParameters.G,
dummyParameters.N, dummyParameters.L, "dn")
G1, startList, fmapping = graphForm.getSeqGraph(returnfmapping, noisyReads,
dummyParameters)
def overallTestRun():
#"oneLine.fasta-0-1440371"
G, N, L, p, epsilon, K, liid, threshold, NKcov, Nbridge, Ncov, ratio, numberOfClusterRounds, brachingDepth, bridgingDepth, msaWidth, folderName = 10000, 83, 1189, 0.01, 0.1, 600, 32, 8, 508, 377, 417, 1.21822542, 0, 0, 0, 0, ""
parameterRobot = logging.parameterObj(G, N, L, p, epsilon, K, liid,
threshold, NKcov, Nbridge, Ncov,
ratio, numberOfClusterRounds,
brachingDepth, bridgingDepth,
msaWidth, folderName)
snpRate, typeOfGen, detail = 0.001, 'd', "genome.fasta-50000-60000"
parameterRobot.clusterRounds, parameterRobot.fingerPrint, parameterRobot.clusterRatio = 2, 6, 1
#snpRate, typeOfGen , detail = 0.001,'m', "500-200-50"
numMistakes, success = assemblerMain.runAssembler(snpRate, typeOfGen,
detail, parameterRobot)
return numMistakes, success
def resolveRepeatsUnitTest(foldername= ""):
var = raw_input("Enter something: ")
print "you entered ", var
f2= logging.fmapfusedLoad(foldername+'clusteredGroup2.csv')
G2 = logging.loadGraph(foldername+'basicMapping.csv', foldername+'seqMapping.txt', 'simple')
checkCondensingBasic(G2, [G2[0]], "simple")
dummyParameters = logging.parameterObj()
dummyParameters.bridgingDepth = 10
G3 = bridgeResolve.resolveRepeats(f2,G2,dummyParameters)
checkCondensingBasic(G3, [G3[0]], "MB")
def resolveRepeatsUnitTest(foldername=""):
var = raw_input("Enter something: ")
print "you entered ", var
f2 = logging.fmapfusedLoad(foldername + 'clusteredGroup2.csv')
G2 = logging.loadGraph(foldername + 'basicMapping.csv',
foldername + 'seqMapping.txt', 'simple')
checkCondensingBasic(G2, [G2[0]], "simple")
dummyParameters = logging.parameterObj()
dummyParameters.bridgingDepth = 10
G3 = bridgeResolve.resolveRepeats(f2, G2, dummyParameters)
checkCondensingBasic(G3, [G3[0]], "MB")
def graphFormUnitTest(N, G, L, folderName =""):
print "dataGenUnitTest"
dummyParameters = logging.parameterObj()
dummyParameters.defaultFolder = folderName
dummyParameters.liid = 40
dummyParameters.K = 40
dummyParameters.threshold = 6
dummyParameters.p = 0.015
dummyParameters.indel = True
dummyParameters.N, dummyParameters.G, dummyParameters.L, dummyParameters.p, typeOfGen, detail = N, G, L, 0.015, 'm', "500-200-50"
# motherGen, reads, noisyReads = dataGen.generateData( typeOfGen,detail,dummyParameters)
motherGen, reads, noisyReads = logging.rawDataLoad(dummyParameters.defaultFolder+"UnitTest",dummyParameters.G,dummyParameters.N,dummyParameters.L, "dn")
returnfmapping= cluster.groupIndelNoisyKmers(noisyReads, dummyParameters, "fast")
def testBandedClustering():
dummyParameters = logging.parameterObj()
#dummyParameters.defaultFolder = ""
dummyParameters.liid = 40
dummyParameters.K = 40
dummyParameters.threshold = 6
dummyParameters.p = 0.015
dummyParameters.indel = True
dummyParameters.N, dummyParameters.G, dummyParameters.L, dummyParameters.p, typeOfGen, detail = 600, 10000,200, 0.015, 'm', "500-200-50"
startFingerPrint, endFingerPrint, read1, read2 = [] , [] , [] , []
read1= np.zeros(200, dtype= np.int64)
read2 = np.zeros(200, dtype= np.int64)
for i in range(200):
read1[i] = random.randint(1,4)
read2[i] = random.randint(1,4)
for i in range(50):
read2[i] = 4
read1[150+i] = 4
print read1, read2
startFingerPrint, endFingerPrint = [160,8] ,[ 190,40]
score , returnalignedSeq1, returnalignedSeq2 , starti, startj , endi, endj =cluster.SWAlignmentBanded(startFingerPrint, endFingerPrint,read1 ,read2 , dummyParameters)
print "score", score
cluster.printSeq(returnalignedSeq1)
cluster.printSeq(returnalignedSeq2)
print "starti, startj, endi , endj : ", starti, startj, endi , endj
score , returnalignedSeq1, returnalignedSeq2 , starti, startj , endi, endj =cluster.SWAlignment(read1, read2 , dummyParameters)
print "score", score
cluster.printSeq(returnalignedSeq1)
cluster.printSeq(returnalignedSeq2)
print "starti, startj, endi , endj : ", starti, startj, endi , endj
def clusterUnitTest2():
# Unit Test 1 : Generate 30 reads with 10 copies with noise , length being 20
motherGen, reads, noisyReads = logging.rawDataLoad("clusterReadsUnitTest",
10, 300, 40, "dn")
parameterRobot = logging.parameterObj()
parameterRobot.N = 300
parameterRobot.L = 40
parameterRobot.G = 10000
parameterRobot.liid = 30
parameterRobot.K = 30
parameterRobot.threshold = 5
parameterRobot.p = 0.01
parameterRobot.indel = True
cluster.groupIndelNoisyKmers(noisyReads, parameterRobot, "fast")
def MSAResolverEpeatUnitTest(Nin, Lin, foldername = ""):
f2= logging.fmapfusedLoad('clusteredGroup2.csv')
G2 = logging.loadGraph(foldername+'basicMapping.csv', foldername+'seqMapping.txt', 'simple')
#checkCondensingBasic(G2, [G2[0]], "simple")
dummyParameters = logging.parameterObj()
dummyParameters.bridgingDepth = 5
dummyParameters.msaWidth = 20
G3 = bridgeResolve.resolveRepeats(f2,G2,dummyParameters)
#checkCondensingBasic(G3, [G3[0]], "MB")
N, G, L, p,snpRate, typeOfGen, detail = Nin, 10000,Lin, 0.015, 0.001 ,'m', "500-300-50"
motherGen, reads, noisyReads = logging.rawDataLoad(foldername+"UnitTest",G,N,L,"dn")
alignmentBridge.MSAresolve(f2, G3, noisyReads, snpRate,dummyParameters)
def clusterUnitTest2():
# Unit Test 1 : Generate 30 reads with 10 copies with noise , length being 20
motherGen, reads, noisyReads = logging.rawDataLoad("clusterReadsUnitTest",10,300,40,"dn")
parameterRobot = logging.parameterObj()
parameterRobot.N = 300
parameterRobot.L = 40
parameterRobot.G = 10000
parameterRobot.liid = 30
parameterRobot.K = 30
parameterRobot.threshold = 5
parameterRobot.p = 0.01
parameterRobot.indel = True
cluster.groupIndelNoisyKmers(noisyReads, parameterRobot, "fast")
def segmentChopAndTestTest(Nin,G, Lin, foldername = "", bridgingDepth = 20, msaWidth = 20):
dummyParameters = logging.parameterObj()
dummyParameters.bridgingDepth = bridgingDepth
dummyParameters.msaWidth = msaWidth
dummyParameters.N, dummyParameters.G, dummyParameters.L, dummyParameters.p = Nin, G,Lin, 0.015
dummyParameters.indel = True
dummyParameters.defaultFolder = foldername
dummyParameters.threshold = 5
dummyParameters.liid = 48
snpRate, typeOfGen, detail = 0.001 ,'m', "500-200-50"
G,N,L = dummyParameters.G, dummyParameters.N, dummyParameters.L,
motherGen, reads, noisyReads = logging.rawDataLoad(foldername+"UnitTest",G,N,L, "dn")
#G3, f2 = interactiveNodeRemoval(folderName, "skip")
G3, f2 = interactiveNodeRemoval(folderName, "desiredOpt")
chopAndAlign(G3, f2 , noisyReads, motherGen, dummyParameters)
def graphFormUnitTest(N, G, L, folderName=""):
print "dataGenUnitTest"
dummyParameters = logging.parameterObj()
dummyParameters.defaultFolder = folderName
dummyParameters.liid = 40
dummyParameters.K = 40
dummyParameters.threshold = 6
dummyParameters.p = 0.015
dummyParameters.indel = True
dummyParameters.N, dummyParameters.G, dummyParameters.L, dummyParameters.p, typeOfGen, detail = N, G, L, 0.015, 'm', "500-200-50"
# motherGen, reads, noisyReads = dataGen.generateData( typeOfGen,detail,dummyParameters)
motherGen, reads, noisyReads = logging.rawDataLoad(
dummyParameters.defaultFolder + "UnitTest", dummyParameters.G,
dummyParameters.N, dummyParameters.L, "dn")
returnfmapping = cluster.groupIndelNoisyKmers(noisyReads, dummyParameters,
"fast")
def MSAResolverEpeatUnitTest(Nin, Lin, foldername=""):
f2 = logging.fmapfusedLoad('clusteredGroup2.csv')
G2 = logging.loadGraph(foldername + 'basicMapping.csv',
foldername + 'seqMapping.txt', 'simple')
#checkCondensingBasic(G2, [G2[0]], "simple")
dummyParameters = logging.parameterObj()
dummyParameters.bridgingDepth = 5
dummyParameters.msaWidth = 20
G3 = bridgeResolve.resolveRepeats(f2, G2, dummyParameters)
#checkCondensingBasic(G3, [G3[0]], "MB")
N, G, L, p, snpRate, typeOfGen, detail = Nin, 10000, Lin, 0.015, 0.001, 'm', "500-300-50"
motherGen, reads, noisyReads = logging.rawDataLoad(foldername + "UnitTest",
G, N, L, "dn")
alignmentBridge.MSAresolve(f2, G3, noisyReads, snpRate, dummyParameters)
def testBandedClustering():
dummyParameters = logging.parameterObj()
#dummyParameters.defaultFolder = ""
dummyParameters.liid = 40
dummyParameters.K = 40
dummyParameters.threshold = 6
dummyParameters.p = 0.015
dummyParameters.indel = True
dummyParameters.N, dummyParameters.G, dummyParameters.L, dummyParameters.p, typeOfGen, detail = 600, 10000, 200, 0.015, 'm', "500-200-50"
startFingerPrint, endFingerPrint, read1, read2 = [], [], [], []
read1 = np.zeros(200, dtype=np.int64)
read2 = np.zeros(200, dtype=np.int64)
for i in range(200):
read1[i] = random.randint(1, 4)
read2[i] = random.randint(1, 4)
for i in range(50):
read2[i] = 4
read1[150 + i] = 4
print read1, read2
startFingerPrint, endFingerPrint = [160, 8], [190, 40]
score, returnalignedSeq1, returnalignedSeq2, starti, startj, endi, endj = cluster.SWAlignmentBanded(
startFingerPrint, endFingerPrint, read1, read2, dummyParameters)
print "score", score
cluster.printSeq(returnalignedSeq1)
cluster.printSeq(returnalignedSeq2)
print "starti, startj, endi , endj : ", starti, startj, endi, endj
score, returnalignedSeq1, returnalignedSeq2, starti, startj, endi, endj = cluster.SWAlignment(
read1, read2, dummyParameters)
print "score", score
cluster.printSeq(returnalignedSeq1)
cluster.printSeq(returnalignedSeq2)
print "starti, startj, endi , endj : ", starti, startj, endi, endj
def batchProcessingGenomeSegTest():
print "Batch Processing LNK Test"
headerName = "largeScaleTest/"
os.system("mkdir "+headerName)
logging.savingGenomeSegmentFile(headerName)
listOfNLKDataPts = logging.loadingGenomeSegmentFile(headerName)
numberOfRounds = 1
for testPoint,roundNum in zip(listOfNLKDataPts, range(len(listOfNLKDataPts))):
folderName = headerName+"sample_point_" + str(roundNum)
os.system("mkdir " + folderName )
[G, N, L, p, epsilon, K, liid, threshold,NKcov, Nbridge, Ncov, ratio, numberOfClusterRounds,brachingDepth,bridgingDepth,msaWidth,clusterRounds, fingerPrint, clusterRatio, startindex, endindex ] = testPoint
print "G", G
parameterRobot = logging.parameterObj(G, N, L, p, epsilon, K, liid, threshold,NKcov, Nbridge, Ncov, ratio, numberOfClusterRounds,brachingDepth,bridgingDepth,msaWidth,folderName,clusterRounds, fingerPrint, clusterRatio )
snpRate, typeOfGen , detail = 0.001,'d', "genome.fasta-"+str(startindex)+"-"+str(endindex)
parameterRobot.indel = True
temptime = time.time()
batchProcessingUnitTest(numberOfRounds,parameterRobot,snpRate, typeOfGen , detail)
print "time per sample point ", time.time() - temptime
def ECUnitTest(Nin, G, Lin, foldername="", bridgingDepth=20, msaWidth=20):
dummyParameters = logging.parameterObj()
dummyParameters.bridgingDepth = bridgingDepth
dummyParameters.msaWidth = msaWidth
dummyParameters.N, dummyParameters.G, dummyParameters.L, dummyParameters.p = Nin, G, Lin, 0.015
dummyParameters.indel = True
dummyParameters.defaultFolder = foldername
dummyParameters.threshold = 5
dummyParameters.liid = 48
snpRate, typeOfGen, detail = 0.001, 'm', "500-200-50"
G, N, L = dummyParameters.G, dummyParameters.N, dummyParameters.L,
motherGen, reads, noisyReads = logging.rawDataLoad(foldername + "UnitTest",
G, N, L, "dn")
f2 = logging.fmapfusedLoad(foldername + 'clusteredGroup2.csv')
G2 = logging.loadGraph(foldername + 'basicMapping.csv',
foldername + 'seqMapping.txt', 'simple')
checkCondensingBasic(G2, [G2[0]], "simple")
G3 = bridgeResolve.resolveRepeats(f2, G2, dummyParameters)
checkCondensingBasic(G3, [G3[0]], "MB")
G4 = alignmentBridge.MSAresolve(f2, G3, noisyReads, snpRate,
dummyParameters)
#G4 = G3
#checkCondensingBasic(G4, [G4[0]], "MB")
recovSeq = eulerCycle.findEC(G4)
recovGen = readAns.reportRecovSeq(recovSeq, f2, noisyReads,
dummyParameters)
numMistakes, success = compare.subAlignCompare(recovGen, motherGen,
dummyParameters)
return numMistakes, success
def testChecking(folderName, N, L, G ):
#N, L, G = 1345, 1000, 50000
f2 = open(folderName+"rec.txt", 'r')
temp2 = f2.read()
recov = np.zeros(len(temp2), dtype = np.int32)
j =0
while j <len(temp2):
if temp2[j] != '-':
recov[j] = int(temp2[j])
j = j+1
else:
recov[j] = -1
j = j+2
f2.close()
dummyParameters = logging.parameterObj()
dummyParameters.defaultFolder = folderName
dummyParameters.G = G
motherGen, reads, noisyReads = logging.rawDataLoad(folderName+"UnitTest",G,N,L, 'd')
print len(recov) , len(motherGen)
numberMistakes, success = compare.subAlignCompare(recov, motherGen,dummyParameters)
def dataGenUnitTest2():
print "dataGenUnitTest2"
dummyParameters = logging.parameterObj()
dummyParameters.N, dummyParameters.G, dummyParameters.L, dummyParameters.p, typeOfGen, detail = 100, 10000,100, 0.01, 't', "500"
G,N,L = dummyParameters.G, dummyParameters.N, dummyParameters.L
motherGen, reads, noisyReads = logging.rawDataLoad("UnitTest",G,N,L, 'd')
print reads
print noisyReads
baseList = []
for indexN in range(N):
for indexL in range(L):
if reads[indexN][indexL] == noisyReads[indexN][indexL]:
baseList.append(0)
else:
baseList.append(1)
print "Error Probability", np.mean(baseList)
print "numberOfBasesGet ", len(baseList)
def dataGenUnitTest2():
print "dataGenUnitTest2"
dummyParameters = logging.parameterObj()
dummyParameters.N, dummyParameters.G, dummyParameters.L, dummyParameters.p, typeOfGen, detail = 100, 10000, 100, 0.01, 't', "500"
G, N, L = dummyParameters.G, dummyParameters.N, dummyParameters.L
motherGen, reads, noisyReads = logging.rawDataLoad("UnitTest", G, N, L,
'd')
print reads
print noisyReads
baseList = []
for indexN in range(N):
for indexL in range(L):
if reads[indexN][indexL] == noisyReads[indexN][indexL]:
baseList.append(0)
else:
baseList.append(1)
print "Error Probability", np.mean(baseList)
print "numberOfBasesGet ", len(baseList)
def batchProcessingLNKTest():
print "Batch Processing LNK Test"
headerName = "synthetic_reads/"
os.system("mkdir "+headerName)
logging.savingLNKFile(headerName)
listOfNLKDataPts = logging.loadingLNKFile(headerName)
numberOfRounds = 1
listOfNLKDataPts = [listOfNLKDataPts[0]]
for testPoint,roundNum in zip(listOfNLKDataPts, range(len(listOfNLKDataPts))):
folderName = headerName+"sample_point_" + str(roundNum)
os.system("mkdir " + folderName )
snpRate, typeOfGen , detail = 0.001,'m', "500-200-50"
[G, N, L, p, epsilon, K, liid, threshold,NKcov, Nbridge, Ncov, ratio, numberOfClusterRounds,brachingDepth,bridgingDepth,msaWidth,clusterRounds, fingerPrint, clusterRatio ] = testPoint
parameterRobot = logging.parameterObj(G, N, L, p, epsilon, K, liid, threshold,NKcov, Nbridge, Ncov, ratio, numberOfClusterRounds,brachingDepth,bridgingDepth,msaWidth,folderName,clusterRounds, fingerPrint, clusterRatio )
parameterRobot.indel = True
batchProcessingUnitTest(numberOfRounds,parameterRobot,snpRate, typeOfGen , detail)
def testChecking(folderName, N, L, G):
#N, L, G = 1345, 1000, 50000
f2 = open(folderName + "rec.txt", 'r')
temp2 = f2.read()
recov = np.zeros(len(temp2), dtype=np.int32)
j = 0
while j < len(temp2):
if temp2[j] != '-':
recov[j] = int(temp2[j])
j = j + 1
else:
recov[j] = -1
j = j + 2
f2.close()
dummyParameters = logging.parameterObj()
dummyParameters.defaultFolder = folderName
dummyParameters.G = G
motherGen, reads, noisyReads = logging.rawDataLoad(folderName + "UnitTest",
G, N, L, 'd')
print len(recov), len(motherGen)
numberMistakes, success = compare.subAlignCompare(recov, motherGen,
dummyParameters)
def segmentChopAndTestTest(Nin,
G,
Lin,
foldername="",
bridgingDepth=20,
msaWidth=20):
dummyParameters = logging.parameterObj()
dummyParameters.bridgingDepth = bridgingDepth
dummyParameters.msaWidth = msaWidth
dummyParameters.N, dummyParameters.G, dummyParameters.L, dummyParameters.p = Nin, G, Lin, 0.015
dummyParameters.indel = True
dummyParameters.defaultFolder = foldername
dummyParameters.threshold = 5
dummyParameters.liid = 48
snpRate, typeOfGen, detail = 0.001, 'm', "500-200-50"
G, N, L = dummyParameters.G, dummyParameters.N, dummyParameters.L,
motherGen, reads, noisyReads = logging.rawDataLoad(foldername + "UnitTest",
G, N, L, "dn")
#G3, f2 = interactiveNodeRemoval(folderName, "skip")
G3, f2 = interactiveNodeRemoval(folderName, "desiredOpt")
chopAndAlign(G3, f2, noisyReads, motherGen, dummyParameters)
def interactiveNodeRemoval(foldername, modeOfOpt = "skip"):
'''
delnode 1002
deledge 1004, 1028
addedge 1023 , 3434
'''
G2 = []
if modeOfOpt == "skip":
varList = ["start none", ""]
elif modeOfOpt == "desiredOpt":
varList = ["start none", "delnode 734288", "delnode 1716432", "fusenode 1438104", "fusenode 1166060" , "view", ""]
var = varList.pop(0)
while len(var) > 0 :
command = var.split()
if command[0] == "start":
print "Start"
G2 = logging.loadGraph(foldername+'basicMapping.csv', foldername+'seqMapping.txt', 'simple')
elif command[0] == "delnode":
print "To delete node"
currentNodeIndex = int(command[1])
print "currentNodeIndex", currentNodeIndex
for eachnode in G2:
if eachnode.nodeIndex == currentNodeIndex:
currentNode = eachnode
for eachitem in currentNode.listOfPrevNodes:
eachitem.listOfNextNodes.remove(currentNode)
currentNode.listOfPrevNodes = []
for eachitem in currentNode.listOfNextNodes:
eachitem.listOfPrevNodes.remove(currentNode)
currentNode.listOfNextNodes = []
currentNode.nodeIndexList = []
graphForm.condenseGraph(G2)
elif command[0] == "deledge":
node1 = int(command[1])
node2 = int(command[2])
startNode, endNode = [] , []
for eachnode in G2:
if eachnode.nodeIndex == node1:
startNode = eachnode
if eachnode.nodeIndex == node2:
endNode = eachnode
startNode.listOfNextNodes.remove(endNode)
endNode.listOfPrevNodes.remove(startNode)
print "To insert nodes"
elif command[0] == "addedge" :
node1 = int(command[1])
node2 = int(command[2])
startNode, endNode = [] , []
for eachnode in G2:
if eachnode.nodeIndex == node1:
startNode = eachnode
if eachnode.nodeIndex == node2:
endNode = eachnode
startNode.listOfNextNodes.append(endNode)
endNode.listOfPrevNodes.append(startNode)
elif command[0] == "fusenode":
myNodeIndex = int(command[1])
for eachnode in G2:
if eachnode.nodeIndex == myNodeIndex:
currentNode = eachnode
if len(currentNode.listOfPrevNodes) == 1:
prevNode = currentNode.listOfPrevNodes[0]
for eachnextnode in currentNode.listOfNextNodes:
eachnextnode.listOfPrevNodes.remove(currentNode)
eachnextnode.listOfPrevNodes.append(prevNode)
prevNode.listOfNextNodes.append(eachnextnode)
prevNode.listOfNextNodes.remove(currentNode)
currentNode.listOfNextNodes = []
currentNode.listOfPrevNodes =[]
currentNode.nodeIndexList = []
elif len(currentNode.listOfNextNodes) ==1 :
nextNode = currentNode.listOfNextNodes[0]
for eachprevnode in currentNode.listOfPrevNodes:
eachprevnode.listOfNextNodes.remove(currentNode)
eachprevnode.listOfNextNodes.append(nextNode)
nextNode.listOfPrevNodes.append(eachprevnode)
nextNode.listOfPrevNodes.remove(currentNode)
currentNode.listOfNextNodes = []
currentNode.listOfPrevNodes = []
currentNode.nodeIndexList = []
elif command[0] == "view":
G2 = graphForm.newCondensingStep(G2)
G2 = G2[0]
checkCondensingBasic(G2, [G2[0]], "simple")
#var = raw_input("Enter Operations: ")
var = varList.pop(0)
dummyParameters = logging.parameterObj()
dummyParameters.bridgingDepth = 20
print "Loading fmap and graph "
f2= logging.fmapfusedLoad(foldername+'clusteredGroup2.csv')
G3 = bridgeResolve.resolveRepeats(f2,G2,dummyParameters)
assert(1==2)
G3 = G2
print "Done Loading the fmap and graph"
#checkCondensingBasic(G3, [G3[0]], "MB")
return G3,f2
def interactiveNodeRemoval(foldername, modeOfOpt="skip"):
'''
delnode 1002
deledge 1004, 1028
addedge 1023 , 3434
'''
G2 = []
if modeOfOpt == "skip":
varList = ["start none", ""]
elif modeOfOpt == "desiredOpt":
varList = [
"start none", "delnode 734288", "delnode 1716432",
"fusenode 1438104", "fusenode 1166060", "view", ""
]
var = varList.pop(0)
while len(var) > 0:
command = var.split()
if command[0] == "start":
print "Start"
G2 = logging.loadGraph(foldername + 'basicMapping.csv',
foldername + 'seqMapping.txt', 'simple')
elif command[0] == "delnode":
print "To delete node"
currentNodeIndex = int(command[1])
print "currentNodeIndex", currentNodeIndex
for eachnode in G2:
if eachnode.nodeIndex == currentNodeIndex:
currentNode = eachnode
for eachitem in currentNode.listOfPrevNodes:
eachitem.listOfNextNodes.remove(currentNode)
currentNode.listOfPrevNodes = []
for eachitem in currentNode.listOfNextNodes:
eachitem.listOfPrevNodes.remove(currentNode)
currentNode.listOfNextNodes = []
currentNode.nodeIndexList = []
graphForm.condenseGraph(G2)
elif command[0] == "deledge":
node1 = int(command[1])
node2 = int(command[2])
startNode, endNode = [], []
for eachnode in G2:
if eachnode.nodeIndex == node1:
startNode = eachnode
if eachnode.nodeIndex == node2:
endNode = eachnode
startNode.listOfNextNodes.remove(endNode)
endNode.listOfPrevNodes.remove(startNode)
print "To insert nodes"
elif command[0] == "addedge":
node1 = int(command[1])
node2 = int(command[2])
startNode, endNode = [], []
for eachnode in G2:
if eachnode.nodeIndex == node1:
startNode = eachnode
if eachnode.nodeIndex == node2:
endNode = eachnode
startNode.listOfNextNodes.append(endNode)
endNode.listOfPrevNodes.append(startNode)
elif command[0] == "fusenode":
myNodeIndex = int(command[1])
for eachnode in G2:
if eachnode.nodeIndex == myNodeIndex:
currentNode = eachnode
if len(currentNode.listOfPrevNodes) == 1:
prevNode = currentNode.listOfPrevNodes[0]
for eachnextnode in currentNode.listOfNextNodes:
eachnextnode.listOfPrevNodes.remove(currentNode)
eachnextnode.listOfPrevNodes.append(prevNode)
prevNode.listOfNextNodes.append(eachnextnode)
prevNode.listOfNextNodes.remove(currentNode)
currentNode.listOfNextNodes = []
currentNode.listOfPrevNodes = []
currentNode.nodeIndexList = []
elif len(currentNode.listOfNextNodes) == 1:
nextNode = currentNode.listOfNextNodes[0]
for eachprevnode in currentNode.listOfPrevNodes:
eachprevnode.listOfNextNodes.remove(currentNode)
eachprevnode.listOfNextNodes.append(nextNode)
nextNode.listOfPrevNodes.append(eachprevnode)
nextNode.listOfPrevNodes.remove(currentNode)
currentNode.listOfNextNodes = []
currentNode.listOfPrevNodes = []
currentNode.nodeIndexList = []
elif command[0] == "view":
G2 = graphForm.newCondensingStep(G2)
G2 = G2[0]
checkCondensingBasic(G2, [G2[0]], "simple")
#var = raw_input("Enter Operations: ")
var = varList.pop(0)
dummyParameters = logging.parameterObj()
dummyParameters.bridgingDepth = 20
print "Loading fmap and graph "
f2 = logging.fmapfusedLoad(foldername + 'clusteredGroup2.csv')
G3 = bridgeResolve.resolveRepeats(f2, G2, dummyParameters)
assert (1 == 2)
G3 = G2
print "Done Loading the fmap and graph"
#checkCondensingBasic(G3, [G3[0]], "MB")
return G3, f2
