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 runAssembler(snpRate, typeOfGen, detail, parameterRobot):
#N, G, L, p,K,snpRate, typeOfGen, detail = 100, 100, 10000, 0.01,30,0.001, 'r', "1000"
motherGen, reads, noisyReads = dataGen.generateData(
typeOfGen, detail, parameterRobot)
motherGen, reads, noisyReads = logging.rawDataLoad(
parameterRobot.defaultFolder + "UnitTest", parameterRobot.G,
parameterRobot.N, parameterRobot.L, "dn")
f1 = cluster.groupIndelNoisyKmers(noisyReads, parameterRobot)
G1, startList, f1 = graphForm.getSeqGraph(f1, noisyReads, parameterRobot)
f2, G2 = branchClear.clearResidual(f1, G1, parameterRobot)
G3 = bridgeResolve.resolveRepeats(f2, G2, parameterRobot)
G4 = alignmentBridge.MSAresolve(f2, G3, noisyReads, snpRate,
parameterRobot)
#G4 = G3
recovSeq = eulerCycle.findEC(G4)
recovGen = readAns.reportRecovSeq(recovSeq, f2, noisyReads, parameterRobot)
numMistakes, success = compare.subAlignCompare(recovGen, motherGen,
parameterRobot)
#numMistakes, success = 0 , 0
return numMistakes, success
# Target of the new code : Fast Assemble and assembly in optimal amount of information
#t0 = time.time()
#N, G, L, p,snpRate, typeOfGen, detail = 1000, 10000,200, 0.015, 0.001 ,'m', "500-300-50"
#runAssembler(N, G, L, p,snpRate, typeOfGen, detail)
#print "Time (sec) :", time.time() - t0
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 runAssembler(snpRate, typeOfGen, detail,parameterRobot):
#N, G, L, p,K,snpRate, typeOfGen, detail = 100, 100, 10000, 0.01,30,0.001, 'r', "1000"
motherGen, reads, noisyReads = dataGen.generateData(typeOfGen, detail,parameterRobot)
motherGen, reads, noisyReads = logging.rawDataLoad(parameterRobot.defaultFolder+"UnitTest",parameterRobot.G,parameterRobot.N,parameterRobot.L, "dn")
f1 = cluster.groupIndelNoisyKmers(noisyReads,parameterRobot)
G1,startList, f1 = graphForm.getSeqGraph(f1,noisyReads, parameterRobot)
f2, G2 = branchClear.clearResidual(f1, G1,parameterRobot)
G3 = bridgeResolve.resolveRepeats(f2, G2,parameterRobot)
G4 = alignmentBridge.MSAresolve(f2, G3, noisyReads, snpRate,parameterRobot )
#G4 = G3
recovSeq = eulerCycle.findEC(G4)
recovGen = readAns.reportRecovSeq(recovSeq, f2, noisyReads,parameterRobot)
numMistakes, success = compare.subAlignCompare(recovGen, motherGen,parameterRobot)
#numMistakes, success = 0 , 0
return numMistakes, success
# Target of the new code : Fast Assemble and assembly in optimal amount of information
#t0 = time.time()
#N, G, L, p,snpRate, typeOfGen, detail = 1000, 10000,200, 0.015, 0.001 ,'m', "500-300-50"
#runAssembler(N, G, L, p,snpRate, typeOfGen, detail)
#print "Time (sec) :", time.time() - t0
