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_assignRepeatedNodesToDummy(self):
scoreList = [[[["ContigDummyL_R~ContigDummyR_L~1", 1, 1]], False]]
scoreListWithDummy, dummyNodeDataRobot = setCoverLib.assignRepeatedNodesToDummy(scoreList)
expectedScoreListWithDummy = [["Dummy0_R~Dummy1_L~1", 1, 1]]
assert "ContigDummyL" == dummyNodeDataRobot.D2RLookUp("Dummy0")
assert "ContigDummyR" == dummyNodeDataRobot.D2RLookUp("Dummy1")
assert ["Dummy0"] == dummyNodeDataRobot.R2DLookUp("ContigDummyL")
assert ["Dummy1"] == dummyNodeDataRobot.R2DLookUp("ContigDummyR")
assert expectedScoreListWithDummy == scoreListWithDummy
def test_assignRepeatedNodesToDummy(self):
scoreList = [[[['ContigDummyL_R~ContigDummyR_L~1' , 1 , 1]], False ] ]
scoreListWithDummy, dummyNodeDataRobot = setCoverLib.assignRepeatedNodesToDummy(scoreList)
expectedScoreListWithDummy = [['Dummy0_R~Dummy1_L~1', 1, 1]]
assert( "ContigDummyL" == dummyNodeDataRobot.D2RLookUp("Dummy0"))
assert( "ContigDummyR" == dummyNodeDataRobot.D2RLookUp("Dummy1"))
assert( ["Dummy0"] == dummyNodeDataRobot.R2DLookUp("ContigDummyL"))
assert( ["Dummy1"] == dummyNodeDataRobot.R2DLookUp("ContigDummyR"))
assert(expectedScoreListWithDummy == scoreListWithDummy)
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)