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_rankAndMerge(self):
contigList = []
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")
SeqIO.write([SeqRecord(Seq("CCCGGGCCC", generic_dna), id="ReadDummy", description="")], self.folderName + self.readsFilename , "fasta")
scoreList = [ ['ContigDummyL_R~ContigDummyR_L~1' , 1 , 1] ]
contigGapReadLookUpDic = {}
contigDummyLRecord, contigDummyRRecord = [4, 6, 1, 3, 3, 3, 100.0, 6, 9, 'ContigDummyL', 'ReadDummy'], [1, 3, 7, 9, 3, 3, 100.0, 7, 9, 'ContigDummyR', 'ReadDummy']
contigGapReadLookUpDic['ContigDummyL_p-ContigDummyR_p'] = [[contigDummyLRecord, contigDummyRRecord]]
contigsNamesList = alignmentLib.findContigsNames(self.folderName, self.contigsFilename)
dummyNodeDataRobot = setCoverLib.dummyNodeController()
dummyNodeDataRobot.realToDummyDic = {'ContigDummyL': 'ContigDummyL','ContigDummyR': 'ContigDummyR'}
dummyNodeDataRobot.dummyToRealDic = {'ContigDummyL': 'ContigDummyL','ContigDummyR': 'ContigDummyR'}
rankingLib.rankAndMerge(self.folderName,contigsNamesList, self.contigsFilename, self.readsFilename, scoreList, contigGapReadLookUpDic, 1, 0.95, "scoreList.json", "improved.fasta", dummyNodeDataRobot)
expectedContig= "AAACCC" + "GGG" + "CCCTTTT"
records = list(SeqIO.parse(self.folderName + "improved.fasta", "fasta"))
assert(expectedContig == str(records[0].seq))
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_rankAndMerge(self):
contigList = []
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")
SeqIO.write(
[SeqRecord(Seq("CCCGGGCCC", generic_dna), id="ReadDummy", description="")],
self.folderName + self.readsFilename,
"fasta",
)
scoreList = [["ContigDummyL_R~ContigDummyR_L~1", 1, 1]]
contigGapReadLookUpDic = {}
contigDummyLRecord, contigDummyRRecord = (
[4, 6, 1, 3, 3, 3, 100.0, 6, 9, "ContigDummyL", "ReadDummy"],
[1, 3, 7, 9, 3, 3, 100.0, 7, 9, "ContigDummyR", "ReadDummy"],
)
contigGapReadLookUpDic["ContigDummyL_p-ContigDummyR_p"] = [[contigDummyLRecord, contigDummyRRecord]]
contigsNamesList = alignmentLib.findContigsNames(self.folderName, self.contigsFilename)
dummyNodeDataRobot = setCoverLib.dummyNodeController()
dummyNodeDataRobot.realToDummyDic = {"ContigDummyL": "ContigDummyL", "ContigDummyR": "ContigDummyR"}
dummyNodeDataRobot.dummyToRealDic = {"ContigDummyL": "ContigDummyL", "ContigDummyR": "ContigDummyR"}
rankingLib.rankAndMerge(
self.folderName,
contigsNamesList,
self.contigsFilename,
self.readsFilename,
scoreList,
contigGapReadLookUpDic,
1,
0.95,
"scoreList.json",
"improved.fasta",
dummyNodeDataRobot,
)
expectedContig = "AAACCC" + "GGG" + "CCCTTTT"
records = list(SeqIO.parse(self.folderName + "improved.fasta", "fasta"))
assert expectedContig == str(records[0].seq)
def test_findContigsNames(self):
self.createSimpleFasta()
contigsNamesList = alignmentLib.findContigsNames(self.folderName, self.contigsFilename)
assert(contigsNamesList == ['ContigDummy'] )
def test_findContigsNames(self):
self.createSimpleFasta()
contigsNamesList = alignmentLib.findContigsNames(self.folderName, self.contigsFilename)
assert contigsNamesList == ["ContigDummy"]