def arrangeSeqBasedOnRef(motherGenome, reconstructedGenome, parameterRobot):
# 1) Extract components and sort
G = parameterRobot.G
fingerPrint = 20
searchNumber = 1000
allFingerPrint = np.zeros(( G-fingerPrint+1) *(fingerPrint+1) , dtype= np.int32).reshape(G-fingerPrint+1, fingerPrint+1)
for i in range(G-fingerPrint +1 ):
allFingerPrint[i][0:-1] = motherGenome[i:i+fingerPrint]
allFingerPrint[i][-1] = i
allFingerPrint = sorted(allFingerPrint,key = itemgetterkk(range(0, fingerPrint+1)))
# 2) Search for appropriate hash items
searchItemList = []
starterIndex = -1
oneItemList = []
hashSearch = np.zeros(fingerPrint+1 , dtype = np.int32)
for i in range(searchNumber):
foundIndex = int( min(i*len(reconstructedGenome)/float(searchNumber), len(reconstructedGenome)- fingerPrint -1 ) )
hashSearch[0:fingerPrint+1] = reconstructedGenome[foundIndex: foundIndex +fingerPrint+1]
hashSearch[-1] = -10
indexInFPList = bridgeResolve.bisectkk(allFingerPrint, hashSearch) -1
tmpItem = []
#print indexInFPList
while (0<=indexInFPList < len(allFingerPrint) and np.array_equal(allFingerPrint[indexInFPList][0:-1],hashSearch[0:-1])):
tmpItem.append(allFingerPrint[indexInFPList][-1])
indexInFPList = indexInFPList - 1
print "tmpItem", tmpItem
searchItemList.append(tmpItem)
if len(tmpItem) == 1 :
oneItemList.append(i)
#else:
# print len(tmpItem)
starterIndexList = []
print "oneItemList",oneItemList
print "searchItemList", searchItemList
for dummyIndex in oneItemList:
tmp = int(searchItemList[dummyIndex][0] - dummyIndex*len(reconstructedGenome)/float(searchNumber))
#print tmp
if tmp < 0 :
tmp = tmp + G
starterIndexList.append(tmp)
print "starterIndexList", starterIndexList
starterIndex = int(np.median(starterIndexList))
starterIndex = G - starterIndex
print starterIndex
# 3) Arrange the starter of reconstructed guy
newArranged = np.zeros(len(reconstructedGenome))
newArranged[0:len(reconstructedGenome)-starterIndex] = reconstructedGenome[starterIndex:len(reconstructedGenome)]
newArranged[len(reconstructedGenome)-starterIndex:len(reconstructedGenome)]= reconstructedGenome[0:starterIndex]
return newArranged
def arrangeSeqBasedOnRef(motherGenome, reconstructedGenome, parameterRobot):
# 1) Extract components and sort
G = parameterRobot.G
fingerPrint = 20
searchNumber = 1000
allFingerPrint = np.zeros((G - fingerPrint + 1) * (fingerPrint + 1),
dtype=np.int32).reshape(G - fingerPrint + 1,
fingerPrint + 1)
for i in range(G - fingerPrint + 1):
allFingerPrint[i][0:-1] = motherGenome[i:i + fingerPrint]
allFingerPrint[i][-1] = i
allFingerPrint = sorted(allFingerPrint,
key=itemgetterkk(range(0, fingerPrint + 1)))
# 2) Search for appropriate hash items
searchItemList = []
starterIndex = -1
oneItemList = []
hashSearch = np.zeros(fingerPrint + 1, dtype=np.int32)
for i in range(searchNumber):
foundIndex = int(
min(i * len(reconstructedGenome) / float(searchNumber),
len(reconstructedGenome) - fingerPrint - 1))
hashSearch[0:fingerPrint +
1] = reconstructedGenome[foundIndex:foundIndex +
fingerPrint + 1]
hashSearch[-1] = -10
indexInFPList = bridgeResolve.bisectkk(allFingerPrint, hashSearch) - 1
tmpItem = []
#print indexInFPList
while (0 <= indexInFPList < len(allFingerPrint) and np.array_equal(
allFingerPrint[indexInFPList][0:-1], hashSearch[0:-1])):
tmpItem.append(allFingerPrint[indexInFPList][-1])
indexInFPList = indexInFPList - 1
print "tmpItem", tmpItem
searchItemList.append(tmpItem)
if len(tmpItem) == 1:
oneItemList.append(i)
#else:
# print len(tmpItem)
starterIndexList = []
print "oneItemList", oneItemList
print "searchItemList", searchItemList
for dummyIndex in oneItemList:
tmp = int(searchItemList[dummyIndex][0] -
dummyIndex * len(reconstructedGenome) / float(searchNumber))
#print tmp
if tmp < 0:
tmp = tmp + G
starterIndexList.append(tmp)
print "starterIndexList", starterIndexList
starterIndex = int(np.median(starterIndexList))
starterIndex = G - starterIndex
print starterIndex
# 3) Arrange the starter of reconstructed guy
newArranged = np.zeros(len(reconstructedGenome))
newArranged[0:len(reconstructedGenome) -
starterIndex] = reconstructedGenome[
starterIndex:len(reconstructedGenome)]
newArranged[len(reconstructedGenome) -
starterIndex:len(reconstructedGenome
)] = reconstructedGenome[0:starterIndex]
return newArranged
def searchFromRO(readSortedf2,searchitem):
searchIndex = bridgeResolve.bisectkk(readSortedf2, searchitem)
#print "searchitem, searchresult", searchitem, readSortedf2[searchIndex-1]
newKmerIndex = readSortedf2[searchIndex-1][2]
return newKmerIndex
