def test_Test2(self):
dataList = []
dataList.append([
1001, 2001, 2001, 1001, 1000, 1000, 100.0, 8000, 8000, 'Contig1',
'Contig2'
])
repeatIntervalDic = breakPointFinding.returnBkPtBoolSat(dataList)
expectedOutput = {'Contig2': [[1001, 1016]], 'Contig1': [[2001, 2016]]}
assert (repeatIntervalDic == expectedOutput)
def repeatFinder(folderName, inputName):
'''
Input : dataList
Output : repeatIntervalDic
'''
dataList = alignerRobot.extractMumData(folderName,
"self" + inputName + "Out")
#dataList = alignerRobot.transformCoor(dataList)
lenDic = IORobot.obtainLength(folderName, inputName + '.fasta')
matchThres = 8000
nonMatchThres = 2
separationThres = 1000
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], min(
eachitem[2:4]), max(eachitem[2:4])
if name1 != name2 and (min(lenDic[name1] - end1, lenDic[name2] - end2)
> nonMatchThres or min(start1, start2) >
nonMatchThres) and matchLen1 > matchThres:
newDataList.append(eachitem)
elif name1 == name2 and abs(
start1 - start2
) > matchLen1 + separationThres and matchLen1 > matchThres:
#print eachitem
newDataList.append(eachitem)
#print len(newDataList), newDataList[0]
# 351 [1, 17852, 1, 17842, 17852, 17842, 98.11, 'Segkk0', 'Segkk128']
# assert(False)
newDataList.sort(key=itemgetter(-2))
if False:
### Old method
repeatIntervalDic = {}
count = 0
for key, items in groupby(newDataList, itemgetter(-2)):
listOfIntervals = []
for eachsub in items:
listOfIntervals.append([eachsub[0], eachsub[1]])
if True:
thres = 30
B = intervalunion.intervalCover(listOfIntervals, thres)
rangeList = intervalunion.reportMisAssemblyIntervals2(
B, lenDic[key], thres, key)
count += len(rangeList)
if len(rangeList) > 0:
repeatIntervalDic[key] = rangeList
print "Count", count
print repeatIntervalDic
else:
repeatIntervalDic = breakPointFinding.returnBkPtBoolSat(newDataList)
return repeatIntervalDic