def countBySeed(editFN, microFN, flankAmount, outFN):
'''FlankF amount should be +/- 6'''
flankAmount = int(flankAmount)
eSites = cgEdit.loadEditingSites(editFN)
micros = cgMicroRNA.loadMicroRNAFromTargetScan(microFN, 'hsa')
gf = GenomeFetch.GenomeFetch('hg19')
for eSite in eSites:
chrom = eSite.chromosome
coord = eSite.coordinate
strand = eSite.strand
flankingSeq = gf.get_seq_from_to(chrom, coord - flankAmount, coord + flankAmount, strand)
eFlankingSeq = flankingSeq[:flankAmount] + 'G' + flankingSeq[flankAmount + 1:]
flankingSeq.replace('T', 'U')
eFlankingSeq.replace('T','U')
checkID = 'hsa-miR-330-5p'
for microRNA in micros:
comSeed = cgSeqMod.reverseComplementSequence(microRNA.seed, True)
if comSeed in flankingSeq:
eSite.microTargets.append(microRNA.id)
if microRNA.id == checkID:
print '%s:%s' % (eSite.chromosome, eSite.coordinate), eSite.strand, eSite.gene
microRNA.numBefore += 1
#print '@', 'flank', eSite.ID, microRNA.id, flankingSeq, comSeed
if comSeed in eFlankingSeq:
microRNA.numAfter += 1
if microRNA.id == checkID:
print '%s:%s' % (eSite.chromosome, eSite.coordinate), eSite.strand, eSite.gene
eSite.eMicroTargets.append(microRNA.id)
#print '@', 'eFlank', eSite.ID, microRNA.id, eFlankingSeq, comSeed
for micro in micros:
if micro.numBefore > 0 or micro.numAfter > 0:
#print micro.id, micro.numBefore, micro.numAfter
pass
#write contents to file...
outF = open(outFN, 'w')
for eSite in eSites:
if len(eSite.microTargets) == 0:
targets = 'None'
else:
targets = ','.join(eSite.microTargets)
if len(eSite.eMicroTargets) == 0:
eTargets = 'None'
else:
eTargets = ','.join(eSite.eMicroTargets)
outF.write('%s\t%s:%s\t%s\t%s\t%s\n' % (eSite.ID, eSite.chromosome, eSite.coordinate, eSite.strand, targets, eTargets))
def updateMicroTargets(editFN, microFN, flankAmount, outFN):
'''FlankF amount should be +/- 6'''
flankAmount = int(flankAmount)
eSites = cgEdit.loadEditingSites(editFN)
micros = cgMicroRNA.loadMicroRNAFromTargetScan(microFN, 'hsa')
gf = GenomeFetch.GenomeFetch('hg19')
for eSite in eSites:
chrom = eSite.chromosome
coord = eSite.coordinate
strand = eSite.strand
flankingSeq = gf.get_seq_from_to(chrom, coord - flankAmount, coord + flankAmount, strand)
eFlankingSeq = flankingSeq[:flankAmount] + 'G' + flankingSeq[flankAmount + 1:]
for microRNA in micros:
comSeed = cgSeqMod.reverseComplementSequence(microRNA.seed, True)
if comSeed in flankingSeq:
eSite.microTargets.append(microRNA.id)
print '@', 'flank', eSite.ID, microRNA.id, flankingSeq, comSeed
if comSeed in eFlankingSeq:
eSite.eMicroTargets.append(microRNA.id)
print '@', 'eFlank', eSite.ID, microRNA.id, eFlankingSeq, comSeed
#write contents to file...
outF = open(outFN, 'w')
for eSite in eSites:
if len(eSite.microTargets) == 0:
targets = 'None'
else:
targets = ','.join(eSite.microTargets)
if len(eSite.eMicroTargets) == 0:
eTargets = 'None'
else:
eTargets = ','.join(eSite.eMicroTargets)
outF.write('%s\t%s:%s\t%s\t%s\t%s\n' % (eSite.ID, eSite.chromosome, eSite.coordinate, eSite.strand, targets, eTargets))
def getMRNA(self, coding=False):
gf = GenomeFetch.GenomeFetch('hg19')
if self.strand == '1':
mRNAList = []
#Get CDS START/END
try:
cdsStart = self.utr5[-1][
1] + 1 #start of coding is right after utr
except IndexError:
cdsStart = int(bioLibCG.tccSplit(self.tcc)[2])
try:
cdsEnd = self.utr3[-1][
0] - 1 #Check if this is how you added Elements to the UTR
except IndexError:
cdsEnd = int(bioLibCG.tccSplit(self.tcc)[3])
if not coding:
chrom, strand, start, end = bioLibCG.tccSplit(self.tcc)
cdsStart = start
cdsEnd = end
coordinates = []
coordinates.extend([cdsStart, cdsEnd])
for exon in self.exonList:
for exonCoord in exon:
if cdsStart < exonCoord < cdsEnd:
coordinates.append(exonCoord)
#now start at cdsStart and make exon pair for each region till cdsEnd
coordinates.sort()
tccStarts = [(coordinates[i * 2])
for i in range(len(coordinates) // 2)]
tccEnds = [
coordinates[1 + i * 2] for i in range(len(coordinates) // 2)
]
tccPairs = zip(tccStarts, tccEnds)
for tccPair in tccPairs:
mRNAList.append(
gf.get_seq_from_to(self.chromosome, tccPair[0] + 1,
tccPair[1] + 1)) #gf is 1-based...
mRNA = ''.join(mRNAList)
return mRNA.replace('T', 'U')
if self.strand == '-1':
'''This this differs in that: 1) the UTR coordinates have to be retrieved differently, 2) The
exon coordinates that will be kept have to be checked with signs reversed, 3) have to revComp it'''
mRNAList = []
try:
cdsStart = self.utr5[-1][0] - 1
except IndexError:
cdsStart = int(bioLibCG.tccSplit(self.tcc)[3])
try:
cdsEnd = self.utr3[-1][
1] + 1 #Check if this is how you added Elements to the UTR
except IndexError:
cdsEnd = int(bioLibCG.tccSplit(self.tcc)[2])
if not coding:
chrom, strand, start, end = bioLibCG.tccSplit(self.tcc)
cdsStart = end
cdsEnd = start
coordinates = []
coordinates.extend([cdsStart, cdsEnd])
for exon in self.exonList:
for exonCoord in exon:
if cdsStart > exonCoord > cdsEnd: #switched signs for negative
coordinates.append(exonCoord)
#now start at cdsStart and make tccs for each region till cdsEnd
coordinates.sort()
#print coordinates
#print len(coordinates)
tccStarts = [(coordinates[i * 2])
for i in range(len(coordinates) // 2)]
tccEnds = [
coordinates[1 + i * 2] for i in range(len(coordinates) // 2)
]
tccPairs = zip(tccStarts, tccEnds)
#print tccPairs
for tccPair in tccPairs:
mRNAList.append(
gf.get_seq_from_to(self.chromosome, tccPair[0] + 1,
tccPair[1] + 1)) #gf is 1-based
mRNA = ''.join(mRNAList)
mRNA = cgSeqMod.reverseComplementSequence(mRNA, False)
return mRNA.replace('T', 'U')
def getMRNA(self, coding=False):
gf = GenomeFetch.GenomeFetch("hg19")
if self.strand == "1":
mRNAList = []
# Get CDS START/END
try:
cdsStart = self.utr5[-1][1] + 1 # start of coding is right after utr
except IndexError:
cdsStart = int(bioLibCG.tccSplit(self.tcc)[2])
try:
cdsEnd = self.utr3[-1][0] - 1 # Check if this is how you added Elements to the UTR
except IndexError:
cdsEnd = int(bioLibCG.tccSplit(self.tcc)[3])
if not coding:
chrom, strand, start, end = bioLibCG.tccSplit(self.tcc)
cdsStart = start
cdsEnd = end
coordinates = []
coordinates.extend([cdsStart, cdsEnd])
for exon in self.exonList:
for exonCoord in exon:
if cdsStart < exonCoord < cdsEnd:
coordinates.append(exonCoord)
# now start at cdsStart and make exon pair for each region till cdsEnd
coordinates.sort()
tccStarts = [(coordinates[i * 2]) for i in range(len(coordinates) // 2)]
tccEnds = [coordinates[1 + i * 2] for i in range(len(coordinates) // 2)]
tccPairs = zip(tccStarts, tccEnds)
for tccPair in tccPairs:
mRNAList.append(gf.get_seq_from_to(self.chromosome, tccPair[0] + 1, tccPair[1] + 1)) # gf is 1-based...
mRNA = "".join(mRNAList)
return mRNA.replace("T", "U")
if self.strand == "-1":
"""This this differs in that: 1) the UTR coordinates have to be retrieved differently, 2) The
exon coordinates that will be kept have to be checked with signs reversed, 3) have to revComp it"""
mRNAList = []
try:
cdsStart = self.utr5[-1][0] - 1
except IndexError:
cdsStart = int(bioLibCG.tccSplit(self.tcc)[3])
try:
cdsEnd = self.utr3[-1][1] + 1 # Check if this is how you added Elements to the UTR
except IndexError:
cdsEnd = int(bioLibCG.tccSplit(self.tcc)[2])
if not coding:
chrom, strand, start, end = bioLibCG.tccSplit(self.tcc)
cdsStart = end
cdsEnd = start
coordinates = []
coordinates.extend([cdsStart, cdsEnd])
for exon in self.exonList:
for exonCoord in exon:
if cdsStart > exonCoord > cdsEnd: # switched signs for negative
coordinates.append(exonCoord)
# now start at cdsStart and make tccs for each region till cdsEnd
coordinates.sort()
# print coordinates
# print len(coordinates)
tccStarts = [(coordinates[i * 2]) for i in range(len(coordinates) // 2)]
tccEnds = [coordinates[1 + i * 2] for i in range(len(coordinates) // 2)]
tccPairs = zip(tccStarts, tccEnds)
# print tccPairs
for tccPair in tccPairs:
mRNAList.append(gf.get_seq_from_to(self.chromosome, tccPair[0] + 1, tccPair[1] + 1)) # gf is 1-based
mRNA = "".join(mRNAList)
mRNA = cgSeqMod.reverseComplementSequence(mRNA, False)
return mRNA.replace("T", "U")
def checkSeeds(editFN, contextFN, miLocationFN, miSequenceFN, gFN):
eSites = cgEdit.loadEditingSites(editFN)
cgEdit.updateContextEditingSites(eSites, contextFN) #puts the UTR, EXON in eSite.context
geneSet = cgGenes3.createGeneSetEditing(gFN)
tName_t = {}
for t in geneSet.transcripts:
tName_t[t.id] = t
miName_miSequence = {}
f = open(miSequenceFN, 'r')
for line in f:
ls = line.strip().split('\t')
name = ls[0]
seq = ls[1]
name = 'hsa-' + name
miName_miSequence[name] = seq
tName_miInfo = {}
f = open(miLocationFN, 'r')
for line in f:
ls = line.strip().split('\t')
tName = ls[0]
miName = ls[1]
loc = int(ls[2])
tName_miInfo.setdefault(tName, []).append([miName, loc])
foundIt = []
notFoundIt = []
for tName in tName_miInfo:
try:
t = tName_t[tName]
except:
continue
checkSeq = get3UTRSeq(t)
try:
mRNA = t.getMRNA()
except:
continue
for miInfo in tName_miInfo[tName]:
miName = miInfo[0]
loc = miInfo[1]
try:
miSequence = miName_miSequence[miName]
miSeed = miSequence[1:8]
except:
continue
rcMiSeed = cgSeqMod.reverseComplementSequence(miSeed, True)
newLoc = loc - (len(mRNA) - len(checkSeq))
finding = checkSeq.find(rcMiSeed, newLoc - 25)
if finding != -1:
if (0 < newLoc - finding < 30):
newResult = '%s\t%s\t%s\t%s\t%s' % (miName, tName, finding, newLoc, loc)
if newResult not in foundIt: foundIt.append(newResult)
else:
if miName == 'hsa-miR-21':
print loc, len(checkSeq), len(mRNA)
print mRNA
print checkSeq
newResult = '%s\t%s\t%s\t%s\t%s' % (miName, tName, finding, newLoc, loc)
if newResult not in notFoundIt: notFoundIt.append(newResult)
print len(foundIt)
print len(notFoundIt)
print ''
for i in foundIt:
print i
print ''
for i in notFoundIt:
print i
