def removeRedundantRefvsQuery(folderName, mummerLink, fileR, fileQ,
outputFileName):
thres = 10
if True:
alignerRobot.useMummerAlignBatch(mummerLink, folderName,
[["redundantRvsQ", fileR, fileQ, ""]],
houseKeeper.globalParallel)
dataList = alignerRobot.extractMumData(folderName, "redundantRvsQOut")
lenDicR = IORobot.obtainLength(folderName, fileR)
lenDicQ = IORobot.obtainLength(folderName, fileQ)
isRedundantList = []
for eachitem in dataList:
match1, match2, name1, name2 = eachitem[4], eachitem[5], eachitem[
7], eachitem[8]
l1, l2 = lenDicR[name1], lenDicQ[name2]
if abs(l2 - match2) < thres:
isRedundantList.append(name2)
#print lenDicQ
nonRedundantList = obtainComplement(lenDicQ, isRedundantList)
print nonRedundantList
IORobot.putListToFileO(folderName, fileQ, outputFileName, nonRedundantList)
os.system("cp " + folderName + "SC_n_tmp.fasta " + folderName +
"SC_n.fasta")
def removeRedundantRefvsQuery(folderName, mummerLink, fileR, fileQ, outputFileName):
thres = 10
if True:
alignerRobot.useMummerAlignBatch(
mummerLink, folderName, [["redundantRvsQ", fileR, fileQ, ""]], houseKeeper.globalParallel
)
dataList = alignerRobot.extractMumData(folderName, "redundantRvsQOut")
lenDicR = IORobot.obtainLength(folderName, fileR)
lenDicQ = IORobot.obtainLength(folderName, fileQ)
isRedundantList = []
for eachitem in dataList:
match1, match2, name1, name2 = eachitem[4], eachitem[5], eachitem[7], eachitem[8]
l1, l2 = lenDicR[name1], lenDicQ[name2]
if abs(l2 - match2) < thres:
isRedundantList.append(name2)
# print lenDicQ
nonRedundantList = obtainComplement(lenDicQ, isRedundantList)
print nonRedundantList
IORobot.putListToFileO(folderName, fileQ, outputFileName, nonRedundantList)
os.system("cp " + folderName + "SC_n_tmp.fasta " + folderName + "SC_n.fasta")
def removeRedundantWithFile(folderName, mummerLink, inputFilename,
mummerTmpName, outputFileName):
thres = 10
os.system("sed -e 's/|//g' " + folderName + inputFilename + ".fasta > " +
folderName + inputFilename + "2.fasta")
os.system("cp " + folderName + inputFilename + "2.fasta " + folderName +
inputFilename + ".fasta")
if True:
alignerRobot.useMummerAlignBatch(mummerLink, folderName, [[
mummerTmpName, inputFilename + ".fasta", inputFilename + ".fasta",
""
]], houseKeeper.globalParallel)
# alignerRobot.useMummerAlign(mummerLink, folderName, "self", "contigs.fasta", "contigs.fasta")
# outputName, referenceName, queryName, specialName
dataList = alignerRobot.extractMumData(folderName, mummerTmpName + "Out")
dataList = alignerRobot.transformCoor(dataList)
lenDic = IORobot.obtainLength(folderName, inputFilename + '.fasta')
removeList = []
shortEmbedClusterDic = {}
for eachitem in lenDic:
shortEmbedClusterDic[eachitem] = clusterElem(eachitem)
for eachitem in dataList:
match1, match2, name1, name2 = eachitem[4], eachitem[5], eachitem[
7], eachitem[8]
if name1 != name2:
l1, l2 = lenDic[name1], lenDic[name2]
if abs(l1 - match1) < thres and abs(l2 - match2) > thres:
removeList.append(name1)
elif abs(l1 - match1) > thres and abs(l2 - match2) < thres:
removeList.append(name2)
elif abs(l1 - match1) < thres and abs(l2 - match2) < thres:
print "Both shortembedd", eachitem
union(shortEmbedClusterDic[name1], shortEmbedClusterDic[name2])
nameList = obtainComplement(lenDic, removeList)
returnList = []
for eachitem in nameList:
if find(shortEmbedClusterDic[eachitem]).id == eachitem:
returnList.append(eachitem)
print "len(nameList), len(returnList)", len(nameList), len(returnList)
IORobot.putListToFileO(folderName, inputFilename + ".fasta",
outputFileName, returnList)
def removeRedundantWithFile(folderName, mummerLink, inputFilename, mummerTmpName, outputFileName):
thres = 10
os.system("sed -e 's/|//g' " + folderName + inputFilename + ".fasta > " + folderName + inputFilename + "2.fasta")
os.system("cp " + folderName + inputFilename + "2.fasta " + folderName + inputFilename + ".fasta")
if True:
alignerRobot.useMummerAlignBatch(
mummerLink,
folderName,
[[mummerTmpName, inputFilename + ".fasta", inputFilename + ".fasta", ""]],
houseKeeper.globalParallel,
)
# alignerRobot.useMummerAlign(mummerLink, folderName, "self", "contigs.fasta", "contigs.fasta")
# outputName, referenceName, queryName, specialName
dataList = alignerRobot.extractMumData(folderName, mummerTmpName + "Out")
dataList = alignerRobot.transformCoor(dataList)
lenDic = IORobot.obtainLength(folderName, inputFilename + ".fasta")
removeList = []
shortEmbedClusterDic = {}
for eachitem in lenDic:
shortEmbedClusterDic[eachitem] = clusterElem(eachitem)
for eachitem in dataList:
match1, match2, name1, name2 = eachitem[4], eachitem[5], eachitem[7], eachitem[8]
if name1 != name2:
l1, l2 = lenDic[name1], lenDic[name2]
if abs(l1 - match1) < thres and abs(l2 - match2) > thres:
removeList.append(name1)
elif abs(l1 - match1) > thres and abs(l2 - match2) < thres:
removeList.append(name2)
elif abs(l1 - match1) < thres and abs(l2 - match2) < thres:
print "Both shortembedd", eachitem
union(shortEmbedClusterDic[name1], shortEmbedClusterDic[name2])
nameList = obtainComplement(lenDic, removeList)
returnList = []
for eachitem in nameList:
if find(shortEmbedClusterDic[eachitem]).id == eachitem:
returnList.append(eachitem)
print "len(nameList), len(returnList)", len(nameList), len(returnList)
IORobot.putListToFileO(folderName, inputFilename + ".fasta", outputFileName, returnList)
def alignWithName(leftSeg, rightSeg, folderName, mummerLink, nameOfOut):
overlap = [0, 0]
lLen = 0
f = open(folderName + nameOfOut + "leftSeg.fasta", 'w')
f.write(">SegL\n")
if len(leftSeg) < 50000:
f.write(leftSeg)
lLen = len(leftSeg)
else:
f.write(leftSeg[-50000:])
lLen = 50000
f.close()
rLen = 0
f = open(folderName + nameOfOut + "rightSeg.fasta", 'w')
f.write(">SegR\n")
if len(rightSeg) < 50000:
f.write(rightSeg)
rLen = len(rightSeg)
else:
f.write(rightSeg[0:50000])
rLen = 50000
f.close()
#alignerRobot.useMummerAlign(mummerLink, folderName, "overlap", "leftSeg.fasta", "rightSeg.fasta", False)
alignerRobot.useMummerAlign(mummerLink,
folderName,
nameOfOut,
nameOfOut + "leftSeg.fasta",
nameOfOut + "rightSeg.fasta",
specialForRaw=False,
specialName="",
refinedVersion=True)
dataList = alignerRobot.extractMumData(folderName, nameOfOut + "Out")
thres = 10
if len(dataList) == 0:
overlap = [0, 0]
else:
myMax = [0, 0]
for eachitem in dataList:
if eachitem[1] > lLen - thres and eachitem[2] < thres:
if eachitem[5] > myMax[1]:
myMax[0] = eachitem[4]
myMax[1] = eachitem[5]
overlap = myMax
return overlap
def removeEmbedded(folderName, mummerLink):
print "removeEmbedded"
thres = 10
os.system("sed -e 's/|//g' " + folderName + "contigs.fasta > " +
folderName + "contigs2.fasta")
os.system("cp " + folderName + "contigs2.fasta " + folderName +
"contigs.fasta")
if True:
print "removeEmbedded: Aligning contigs.fasta to contigs.fasta, outputs are self*.delta"
alignerRobot.useMummerAlignBatch(
mummerLink, folderName,
[["self", "contigs.fasta", "contigs.fasta", ""]],
houseKeeper.globalParallel)
# alignerRobot.useMummerAlign(mummerLink, folderName, "self", "contigs.fasta", "contigs.fasta")
# outputName, referenceName, queryName, specialName
print "removeEmbedded: Extracting MUMmer data from delta files to selfOut"
dataList = alignerRobot.extractMumData(folderName, "selfOut")
dataList = alignerRobot.transformCoor(dataList)
lenDic = IORobot.obtainLength(folderName, 'contigs.fasta')
removeList = []
for eachitem in dataList:
match1, match2, name1, name2 = eachitem[4], eachitem[5], eachitem[
7], eachitem[8]
if name1 != name2:
l1, l2 = lenDic[name1], lenDic[name2]
if abs(l1 - match1) < thres and abs(l2 - match2) > thres:
removeList.append(name1)
elif abs(l1 - match1) > thres and abs(l2 - match2) < thres:
removeList.append(name2)
elif abs(l1 - match1) < thres and abs(l2 - match2) < thres:
print "Both shortembedd", eachitem
nameList = []
for eachitem in lenDic:
nameList.append(eachitem)
print len(nameList)
for eachitem in removeList:
if eachitem in nameList:
nameList.remove(eachitem)
print len(nameList)
print "removeEmbedded: Outputting non-contained contigs to noEmbed.fasta"
IORobot.putListToFileO(folderName, "contigs.fasta", "noEmbed", nameList)
def removeEmbedded(folderName, mummerLink):
print "removeEmbedded"
thres = 10
command = r'''perl -pe 's/>[^\$]*$/">Seg" . ++$n ."\n"/ge' ''' + folderName + "raw_reads.fasta > " + folderName + houseKeeper.globalReadName
os.system(command)
command = r'''perl -pe 's/>[^\$]*$/">Seg" . ++$n ."\n"/ge' ''' + folderName + "contigs.fasta > " + folderName + houseKeeper.globalContigName
os.system(command)
if True:
alignerRobot.useMummerAlignBatch(mummerLink, folderName, [[
"self", houseKeeper.globalContigName, houseKeeper.globalContigName,
""
]], houseKeeper.globalParallel)
# alignerRobot.useMummerAlign(mummerLink, folderName, "self", "contigs.fasta", "contigs.fasta")
# outputName, referenceName, queryName, specialName
dataList = alignerRobot.extractMumData(folderName, "selfOut")
dataList = alignerRobot.transformCoor(dataList)
lenDic = IORobot.obtainLength(folderName, houseKeeper.globalContigName)
removeList = []
for eachitem in dataList:
match1, match2, name1, name2 = eachitem[4], eachitem[5], eachitem[
7], eachitem[8]
if name1 != name2:
l1, l2 = lenDic[name1], lenDic[name2]
if abs(l1 - match1) < thres and abs(l2 - match2) > thres:
removeList.append(name1)
elif abs(l1 - match1) > thres and abs(l2 - match2) < thres:
removeList.append(name2)
elif abs(l1 - match1) < thres and abs(l2 - match2) < thres:
print "Both shortembedd", eachitem
nameList = []
for eachitem in lenDic:
nameList.append(eachitem)
print len(nameList)
for eachitem in removeList:
if eachitem in nameList:
nameList.remove(eachitem)
print len(nameList)
IORobot.putListToFileO(folderName, houseKeeper.globalContigName, "noEmbed",
nameList)
def removeEmbedded(folderName , mummerLink):
print "removeEmbedded"
thres = 10
command= r'''perl -pe 's/>[^\$]*$/">Seg" . ++$n ."\n"/ge' ''' + folderName + "raw_reads.fasta > " + folderName + houseKeeper.globalReadName
os.system(command)
command= r'''perl -pe 's/>[^\$]*$/">Seg" . ++$n ."\n"/ge' ''' + folderName + "contigs.fasta > " + folderName + houseKeeper.globalContigName
os.system(command)
if True:
alignerRobot.useMummerAlignBatch(mummerLink, folderName, [["self", houseKeeper.globalContigName, houseKeeper.globalContigName, ""]], houseKeeper.globalParallel)
# alignerRobot.useMummerAlign(mummerLink, folderName, "self", "contigs.fasta", "contigs.fasta")
# outputName, referenceName, queryName, specialName
dataList = alignerRobot.extractMumData(folderName, "selfOut")
dataList = alignerRobot.transformCoor(dataList)
lenDic = IORobot.obtainLength(folderName, houseKeeper.globalContigName)
removeList = []
for eachitem in dataList:
match1, match2, name1, name2 = eachitem[4], eachitem[5], eachitem[7], eachitem[8]
if name1 != name2:
l1, l2 = lenDic[name1], lenDic[name2]
if abs(l1 - match1) < thres and abs(l2 - match2) > thres:
removeList.append(name1)
elif abs(l1 - match1) > thres and abs(l2 - match2) < thres:
removeList.append(name2)
elif abs(l1 - match1) < thres and abs(l2 - match2) < thres:
print "Both shortembedd", eachitem
nameList = []
for eachitem in lenDic:
nameList.append(eachitem)
print len(nameList)
for eachitem in removeList:
if eachitem in nameList:
nameList.remove(eachitem)
print len(nameList)
IORobot.putListToFileO(folderName, houseKeeper.globalContigName, "noEmbed", nameList)
def removeEmbedded(folderName, mummerLink):
print "removeEmbedded"
thres = 10
os.system("sed -e 's/|//g' " + folderName + "contigs.fasta > " + folderName + "contigs2.fasta")
os.system("cp " + folderName + "contigs2.fasta " + folderName + "contigs.fasta")
if True:
print "removeEmbedded: Aligning contigs.fasta to contigs.fasta, outputs are self*.delta"
alignerRobot.useMummerAlignBatch(
mummerLink, folderName, [["self", "contigs.fasta", "contigs.fasta", ""]], houseKeeper.globalParallel
)
# alignerRobot.useMummerAlign(mummerLink, folderName, "self", "contigs.fasta", "contigs.fasta")
# outputName, referenceName, queryName, specialName
print "removeEmbedded: Extracting MUMmer data from delta files to selfOut"
dataList = alignerRobot.extractMumData(folderName, "selfOut")
dataList = alignerRobot.transformCoor(dataList)
lenDic = IORobot.obtainLength(folderName, "contigs.fasta")
removeList = []
for eachitem in dataList:
match1, match2, name1, name2 = eachitem[4], eachitem[5], eachitem[7], eachitem[8]
if name1 != name2:
l1, l2 = lenDic[name1], lenDic[name2]
if abs(l1 - match1) < thres and abs(l2 - match2) > thres:
removeList.append(name1)
elif abs(l1 - match1) > thres and abs(l2 - match2) < thres:
removeList.append(name2)
elif abs(l1 - match1) < thres and abs(l2 - match2) < thres:
print "Both shortembedd", eachitem
nameList = []
for eachitem in lenDic:
nameList.append(eachitem)
print len(nameList)
for eachitem in removeList:
if eachitem in nameList:
nameList.remove(eachitem)
print len(nameList)
print "removeEmbedded: Outputting non-contained contigs to noEmbed.fasta"
IORobot.putListToFileO(folderName, "contigs.fasta", "noEmbed", nameList)
def alignWithName(leftSeg, rightSeg, folderName, mummerLink, nameOfOut):
overlap = [0, 0 ]
lLen = 0
f = open(folderName + nameOfOut+"leftSeg.fasta", 'w')
f.write(">SegL\n")
if len(leftSeg) < 50000:
f.write(leftSeg)
lLen = len(leftSeg)
else:
f.write(leftSeg[-50000:])
lLen = 50000
f.close()
rLen = 0
f = open(folderName + nameOfOut+"rightSeg.fasta", 'w')
f.write(">SegR\n")
if len(rightSeg) < 50000:
f.write(rightSeg)
rLen = len(rightSeg)
else:
f.write(rightSeg[0:50000])
rLen = 50000
f.close()
#alignerRobot.useMummerAlign(mummerLink, folderName, "overlap", "leftSeg.fasta", "rightSeg.fasta", False)
alignerRobot.useMummerAlign(mummerLink, folderName, nameOfOut, nameOfOut+"leftSeg.fasta", nameOfOut+"rightSeg.fasta", specialForRaw = False, specialName = "", refinedVersion= True)
dataList = alignerRobot.extractMumData(folderName , nameOfOut+"Out")
thres = 10
if len(dataList) == 0:
overlap = [0, 0 ]
else:
myMax = [0, 0]
for eachitem in dataList:
if eachitem[1] > lLen - thres and eachitem[2] < thres:
if eachitem[5] > myMax[1]:
myMax[0] = eachitem[4]
myMax[1] = eachitem[5]
overlap = myMax
return overlap
def align(leftSeg, rightSeg, folderName, mummerLink):
overlap = [0, 0]
lLen = 0
f = open(folderName + "leftSeg.fasta", "w")
f.write(">SegL\n")
if len(leftSeg) < 50000:
f.write(leftSeg)
lLen = len(leftSeg)
else:
f.write(leftSeg[-50000:])
lLen = 50000
f.close()
rLen = 0
f = open(folderName + "rightSeg.fasta", "w")
f.write(">SegR\n")
if len(rightSeg) < 50000:
f.write(rightSeg)
rLen = len(rightSeg)
else:
f.write(rightSeg[0:50000])
rLen = 50000
f.close()
alignerRobot.useMummerAlign(mummerLink, folderName, "overlap", "leftSeg.fasta", "rightSeg.fasta", False)
dataList = alignerRobot.extractMumData(folderName, "overlapOut")
thres = 10
if len(dataList) == 0:
overlap = [0, 0]
else:
myMax = [0, 0]
for eachitem in dataList:
if eachitem[1] > lLen - thres and eachitem[2] < thres:
if eachitem[5] > myMax[1]:
myMax[0] = eachitem[4]
myMax[1] = eachitem[5]
overlap = myMax
return overlap
def observeOverlap(folderName):
dataList = alignerRobot.extractMumData(folderName, "selfOut")
dataList = alignerRobot.transformCoor(dataList)
lenDic = IORobot.obtainLength(folderName, 'contigs.fasta')
matchThres = 10000
nonMatchThres = 500
count = 0
newDataList = []
for eachitem in dataList:
name1, name2 = eachitem[-2], eachitem[-1]
matchLen1, matchLen2 = eachitem[4], eachitem[5]
start1, end1, start2, end2 = eachitem[0], eachitem[1], eachitem[
2], eachitem[3]
# if name1!= name2 and min(lenDic[name1] - end1, lenDic[name2] - end2 ) > nonMatchThres \
# and min(start1, start2) > nonMatchThres \
if name1!= name2 and ( min(lenDic[name1] - end1, lenDic[name2] - end2 ) > nonMatchThres \
or min(start1, start2) > nonMatchThres ) \
and matchLen1> matchThres:
print "eachitem ", eachitem, lenDic[name1], lenDic[name2]
count = count + 1
newDataList.append(eachitem)
print "Count: " + str(count)
blkDic = getBreakPointFromDataList(folderName, newDataList)
LCList = IORobot.loadContigsFromFile(folderName, "contigs.fasta")
contigList = []
for eachcontig in LCList:
#print eachcontig
if not eachcontig in blkDic:
contigList = contigList + [LCList[eachcontig]]
else:
contigList = contigList + tmpBreakAcBkPts(LCList[eachcontig],
blkDic[eachcontig])
print "len(contigList)", len(contigList)
IORobot.writeSegOut(contigList, folderName, "breakChains.fasta")
def fillInMissed(folderName, mummerLink, filerefname, filequeryname, fileoutname):
os.system("mv " + folderName + fileoutname + " " + folderName + filequeryname )
alignerRobot.useMummerAlignBatch(mummerLink, folderName, [[fileoutname+"fillmiss", filerefname, filequeryname, ""]], houseKeeper.globalParallel)
dataList = alignerRobot.extractMumData(folderName, fileoutname+"fillmissOut")
lenDic = obtainLength(folderName, filerefname)
### Check if there is any missing parts
# Format of the dataList : 1 765 | 11596 10822 | 765 775 | 84.25 | ref_NC_001133_ scf7180000000702"
dataList.sort(key = itemgetter(-2))
thres = 100
extraList = []
for key, items in groupby(dataList, itemgetter(-2)):
isFound = False
for eachitem in items:
if abs(int(eachitem[4]) - lenDic[key]) < thres:
isFound = True
break
if not isFound:
extraList.append(key)
### Fill in any missing items
referenceDic = loadContigsFromFile(folderName, filerefname)
queryDic = loadContigsFromFile(folderName, filequeryname)
ctgList = [referenceDic[eachitem] for eachitem in extraList] + [queryDic[eachitem] for eachitem in queryDic]
writeSegOut(ctgList, folderName, fileoutname)
print "fileoutname: len(extraList)",fileoutname, len(extraList), len(ctgList)
def obtainLinkInfo(folderName, mummerLink, inputFile, mummerFile):
thres = 5
minLen = 400
# thres = 10
# minLen = 200
writeToFile_Double1(folderName, inputFile + ".fasta",
inputFile + "_Double.fasta", "contig")
fmyFile = open(folderName + inputFile + "_Double.fasta", 'r')
fSmaller = open(folderName + inputFile + "_contigs_Double.fasta", 'w')
tmp = fmyFile.readline().rstrip()
maxSize = 50000
myName = ""
while len(tmp) > 0:
if tmp[0] == '>':
fSmaller.write(tmp + '\n')
myName = tmp[1:]
else:
component = tmp[0:min(len(tmp), maxSize)]
countComp = len(component)
fSmaller.write(component)
component = tmp[max(0, len(tmp) - maxSize):len(tmp)]
fSmaller.write(component)
countComp = countComp + len(component)
print "DebugName", myName, countComp
fSmaller.write('\n')
tmp = fmyFile.readline().rstrip()
fSmaller.close()
fmyFile.close()
if True:
alignerRobot.useMummerAlignBatch(mummerLink, folderName, [[
mummerFile, inputFile + "_contigs_Double.fasta",
inputFile + "_contigs_Double.fasta", ""
]], houseKeeper.globalParallel)
# alignerRobot.useMummerAlign(mummerLink, folderName, mummerFile, inputFile + "_contigs_Double.fasta", inputFile + "_contigs_Double.fasta")
lengthDic = obtainLength(folderName, inputFile + "_contigs_Double.fasta")
dataSetRaw = alignerRobot.extractMumData(folderName, mummerFile + "Out")
# ## Format [ helperStart, helperEnd , readStart, readEnd,matchLen1,matchLen2,percentMatch,helperName,readName]
dataSet = []
for eachitem in dataSetRaw:
helperStart, helperEnd, readStart, readEnd, matchLen1, matchLen2, percentMatch, helperName, readName = eachitem
detailHelper = helperName.split('_')
detailRead = readName.split('_')
if detailHelper[0] != detailRead[0] and helperName != readName and max(
matchLen1, matchLen2) > minLen and readStart < readEnd and min(
helperStart, readStart) < thres and min(
lengthDic[helperName] - helperEnd,
lengthDic[readName] - readEnd) + 1 < thres:
conditionForMatch = True
else:
conditionForMatch = False
if conditionForMatch:
if helperStart < thres:
dataSet.append((max(matchLen1,
matchLen2), readName, helperName))
dataSet.sort(reverse=True)
numberOfContig = len(lengthDic)
return numberOfContig, dataSet
def obtainLinkInfo(folderName, mummerLink, inputFile, mummerFile):
# minLen = 200
minLen = 400
if houseKeeper.globalRelaxThres == False:
thres = 5
elif houseKeeper.globalRelaxThres == True:
thres = 10
writeToFile_Double1(folderName, inputFile + ".fasta", inputFile + "_Double.fasta", "contig")
fmyFile = open(folderName + inputFile + "_Double.fasta", 'r')
fSmaller = open(folderName + inputFile + "_contigs_Double.fasta", 'w')
tmp = fmyFile.readline().rstrip()
maxSize = 50000
myName = ""
while len(tmp) > 0:
if tmp[0] == '>':
fSmaller.write(tmp + '\n')
myName = tmp[1:]
else:
component = tmp[0:min(len(tmp), maxSize)]
countComp = len(component)
fSmaller.write(component)
component = tmp[max(0, len(tmp) - maxSize):len(tmp)]
fSmaller.write(component)
countComp = countComp + len(component)
print "DebugName", myName, countComp
fSmaller.write('\n')
tmp = fmyFile.readline().rstrip()
fSmaller.close()
fmyFile.close()
if True:
alignerRobot.useMummerAlignBatch(mummerLink, folderName, [[mummerFile, inputFile + "_contigs_Double.fasta", inputFile + "_contigs_Double.fasta", ""]], houseKeeper.globalParallel )
# alignerRobot.useMummerAlign(mummerLink, folderName, mummerFile, inputFile + "_contigs_Double.fasta", inputFile + "_contigs_Double.fasta")
lengthDic = obtainLength(folderName, inputFile + "_contigs_Double.fasta")
dataSetRaw = alignerRobot.extractMumData(folderName, mummerFile + "Out")
# ## Format [ helperStart, helperEnd , readStart, readEnd,matchLen1,matchLen2,percentMatch,helperName,readName]
dataSet = []
for eachitem in dataSetRaw:
helperStart, helperEnd , readStart, readEnd, matchLen1, matchLen2, percentMatch, helperName, readName = eachitem
detailHelper = helperName.split('_')
detailRead = readName.split('_')
if detailHelper[0] != detailRead[0] and helperName != readName and max(matchLen1, matchLen2) > minLen and readStart < readEnd and min(helperStart, readStart) < thres and min(lengthDic[helperName] - helperEnd, lengthDic[readName] - readEnd) + 1 < thres:
conditionForMatch = True
else:
conditionForMatch = False
if conditionForMatch :
if helperStart < thres:
dataSet.append((max(matchLen1, matchLen2), readName, helperName))
dataSet.sort(reverse=True)
numberOfContig = len(lengthDic)
return numberOfContig, dataSet
