def mainFlow(folderName, mummerLink, inputContigsFilename, inputReadsFilename, useSpades, noAlignment, scoreListOutputName, outputContigsFilename, mScoreThres, conScoreThres, setCoverOption):
outputHeader, splitNum, parallelNum = "readToContigHeader", 20, 20
contigsFilename, readsFilename= "tmp" + inputContigsFilename , "tmp" + inputReadsFilename
targetToSourceContigsNamesDic = houseKeeperLib.transformFileHeaders(folderName, inputContigsFilename, contigsFilename, noAlignment)
targetToSourceReadsNamesDic = houseKeeperLib.transformFileHeaders(folderName, inputReadsFilename, readsFilename, noAlignment)
dataList = alignmentLib.extractRead2Contig(folderName, mummerLink, readsFilename, contigsFilename, splitNum, outputHeader, parallelNum, noAlignment )
connectingReadsList = readConnectivityLib.findConnectingReadsList(dataList)
spanReadsList, contigGapReadLookUpDic = readConnectivityLib.findSpanReadsList(connectingReadsList)
contigsNamesList = alignmentLib.findContigsNames(folderName, contigsFilename)
G = graphLib.formContigGraph(spanReadsList, contigsNamesList)
condenseCandidatesList = G.findCondenseCandidatesList()
multiplicityDic = G.findEdgeMultiplicity()
potentialMergesList = setCoverLib.extendConnectivityFromReads(condenseCandidatesList, connectingReadsList, contigsNamesList, setCoverOption, multiplicityDic)
if useSpades == True:
cTestLib.assignCoverageFromHeader(G, folderName, contigsFilename, targetToSourceContigsNamesDic)
else:
cTestLib.assignCoverageFromDataList(G, dataList,folderName, contigsFilename)
scoreStructList = cTestLib.calculateConfidenceScore(G, potentialMergesList)
scoreListWithDummy, dummyNodeDataRobot = setCoverLib.assignRepeatedNodesToDummy(scoreStructList)
rankingLib.rankAndMerge(folderName,contigsNamesList, contigsFilename, readsFilename, scoreListWithDummy, contigGapReadLookUpDic, mScoreThres, conScoreThres, scoreListOutputName, outputContigsFilename, dummyNodeDataRobot)
def mainFlow(folderName, mummerLink, inputContigsFilename, inputReadsFilename,
useSpades, noAlignment, scoreListOutputName,
outputContigsFilename, mScoreThres, conScoreThres,
setCoverOption):
outputHeader, splitNum, parallelNum = "readToContigHeader", 20, 20
contigsFilename, readsFilename = "tmp" + inputContigsFilename, "tmp" + inputReadsFilename
targetToSourceContigsNamesDic = houseKeeperLib.transformFileHeaders(
folderName, inputContigsFilename, contigsFilename, noAlignment)
targetToSourceReadsNamesDic = houseKeeperLib.transformFileHeaders(
folderName, inputReadsFilename, readsFilename, noAlignment)
dataList = alignmentLib.extractRead2Contig(folderName, mummerLink,
readsFilename, contigsFilename,
splitNum, outputHeader,
parallelNum, noAlignment)
connectingReadsList = readConnectivityLib.findConnectingReadsList(dataList)
spanReadsList, contigGapReadLookUpDic = readConnectivityLib.findSpanReadsList(
connectingReadsList)
contigsNamesList = alignmentLib.findContigsNames(folderName,
contigsFilename)
G = graphLib.formContigGraph(spanReadsList, contigsNamesList)
condenseCandidatesList = G.findCondenseCandidatesList()
multiplicityDic = G.findEdgeMultiplicity()
potentialMergesList = setCoverLib.extendConnectivityFromReads(
condenseCandidatesList, connectingReadsList, contigsNamesList,
setCoverOption, multiplicityDic)
if useSpades == True:
cTestLib.assignCoverageFromHeader(G, folderName, contigsFilename,
targetToSourceContigsNamesDic)
else:
cTestLib.assignCoverageFromDataList(G, dataList, folderName,
contigsFilename)
scoreStructList = cTestLib.calculateConfidenceScore(G, potentialMergesList)
scoreListWithDummy, dummyNodeDataRobot = setCoverLib.assignRepeatedNodesToDummy(
scoreStructList)
rankingLib.rankAndMerge(folderName, contigsNamesList, contigsFilename,
readsFilename, scoreListWithDummy,
contigGapReadLookUpDic, mScoreThres, conScoreThres,
scoreListOutputName, outputContigsFilename,
dummyNodeDataRobot)
def test_assignCoverageFromDataList(self):
dataList, contigList = [ [1, 6, 1, 6, 6, 6, 100.0, 6, 6, 'ContigDummyL', 'ReadDummy'] ], []
contigList.append(SeqRecord(Seq("AAACCC", generic_dna), id="ContigDummyL", description=""))
contigList.append(SeqRecord(Seq("CCCTTTT", generic_dna), id="ContigDummyR", description=""))
SeqIO.write(contigList, self.folderName + self.contigsFilename , "fasta")
spanReadsList, contigsNamesList = [['ContigDummyL_p', 'ContigDummyR_p', 'ReadDummy']], ['ContigDummyL', 'ContigDummyR']
G = graphLib.formContigGraph(spanReadsList, contigsNamesList)
cTestLib.assignCoverageFromDataList(G, dataList, self.folderName, self.contigsFilename)
assert(G.dicOfContigNodes['ContigDummyL'].contigLength == 6)
assert(G.dicOfContigNodes['ContigDummyR'].contigLength == 7)
assert(G.dicOfContigNodes['ContigDummyL'].readToContigCount == 1)
assert(G.dicOfContigNodes['ContigDummyR'].readToContigCount == 0)
def test_calculateConfidenceScore(self):
condenseCandidatesList = [[['ContigDummyL_R~ContigDummyR_L~1'], False]]
spanReadsList, contigsNamesList = [['ContigDummyL_p', 'ContigDummyR_p', 'ReadDummy']], ['ContigDummyL', 'ContigDummyR']
dataList, contigList = [ [1, 6, 1, 6, 6, 6, 100.0, 6, 6, 'ContigDummyL', 'ReadDummy'] ], []
contigList.append(SeqRecord(Seq("AAACCC", generic_dna), id="ContigDummyL", description=""))
contigList.append(SeqRecord(Seq("CCCTTTT", generic_dna), id="ContigDummyR", description=""))
SeqIO.write(contigList, self.folderName + self.contigsFilename , "fasta")
G = graphLib.formContigGraph(spanReadsList, contigsNamesList)
cTestLib.assignCoverageFromDataList(G, dataList, self.folderName, self.contigsFilename)
scoreStructList = cTestLib.calculateConfidenceScore(G, condenseCandidatesList)
assert(scoreStructList[0][0][0][0] == 'ContigDummyL_R~ContigDummyR_L~1' )
assert(abs(scoreStructList[0][0][0][1] - 0.53846153846153844) < 0.01)
assert(scoreStructList[0][0][0][2] == 1)
assert(scoreStructList[0][1] == False)
def test_assignCoverageFromDataList(self):
dataList, contigList = [[1, 6, 1, 6, 6, 6, 100.0, 6, 6, "ContigDummyL", "ReadDummy"]], []
contigList.append(SeqRecord(Seq("AAACCC", generic_dna), id="ContigDummyL", description=""))
contigList.append(SeqRecord(Seq("CCCTTTT", generic_dna), id="ContigDummyR", description=""))
SeqIO.write(contigList, self.folderName + self.contigsFilename, "fasta")
spanReadsList, contigsNamesList = (
[["ContigDummyL_p", "ContigDummyR_p", "ReadDummy"]],
["ContigDummyL", "ContigDummyR"],
)
G = graphLib.formContigGraph(spanReadsList, contigsNamesList)
cTestLib.assignCoverageFromDataList(G, dataList, self.folderName, self.contigsFilename)
assert G.dicOfContigNodes["ContigDummyL"].contigLength == 6
assert G.dicOfContigNodes["ContigDummyR"].contigLength == 7
assert G.dicOfContigNodes["ContigDummyL"].readToContigCount == 1
assert G.dicOfContigNodes["ContigDummyR"].readToContigCount == 0
def test_calculateConfidenceScore(self):
condenseCandidatesList = [[["ContigDummyL_R~ContigDummyR_L~1"], False]]
spanReadsList, contigsNamesList = (
[["ContigDummyL_p", "ContigDummyR_p", "ReadDummy"]],
["ContigDummyL", "ContigDummyR"],
)
dataList, contigList = [[1, 6, 1, 6, 6, 6, 100.0, 6, 6, "ContigDummyL", "ReadDummy"]], []
contigList.append(SeqRecord(Seq("AAACCC", generic_dna), id="ContigDummyL", description=""))
contigList.append(SeqRecord(Seq("CCCTTTT", generic_dna), id="ContigDummyR", description=""))
SeqIO.write(contigList, self.folderName + self.contigsFilename, "fasta")
G = graphLib.formContigGraph(spanReadsList, contigsNamesList)
cTestLib.assignCoverageFromDataList(G, dataList, self.folderName, self.contigsFilename)
scoreStructList = cTestLib.calculateConfidenceScore(G, condenseCandidatesList)
assert scoreStructList[0][0][0][0] == "ContigDummyL_R~ContigDummyR_L~1"
assert abs(scoreStructList[0][0][0][1] - 0.53846153846153844) < 0.01
assert scoreStructList[0][0][0][2] == 1
assert scoreStructList[0][1] == False
