def transcriptSetOverlap(aDir, AS):
AS = bool(AS)
geneSetFN = '/home/chrisgre/dataSources/known/Human/geneSets/ensemblAllTranscripts.tsv'
allExons = cgGenes.createGeneSetFromFile(geneSetFN)
#get degradome TCCS
#note that you need to test the AS peaks, this is the location of the targetted transcript
oRNA_DC = cgNexusFlat.dataController(aDir, cgOriginRNA.OriginRNA)
id_oRNA = oRNA_DC.load()
if AS == True:
degTccs = [cg.convertToAS(x.tcc) for x in id_oRNA.values()]
else:
degTccs = [x.tcc for x in id_oRNA.values()]
#find all overlapping exons/transcripts, then all results sequences that overlap exons
overlappingExons = allExons.transcriptOverlaps(degTccs)
#print len(overlappingExons), "num of overlapping exons"
overlappingExonTccs = [x.tcc for x in overlappingExons]
overlappingDegTccs = compare.compareTwoTcc(degTccs, overlappingExonTccs, 1)
#write new file
for obj in id_oRNA.values():
if AS:
degTcc = cg.convertToAS(obj.tcc)
else:
degTcc = obj.tcc
if degTcc in overlappingDegTccs:
obj.transcriptOverlap = True
else:
obj.transcriptOverlap = False
oRNA_DC.commit(id_oRNA)
def transcriptSetOverlap(aDir, AS):
AS = bool(AS)
geneSetFN = '/home/chrisgre/dataSources/known/Human/geneSets/ensemblAllTranscripts.tsv'
allExons = cgGenes.createGeneSetFromFile(geneSetFN)
#get degradome TCCS
#note that you need to test the AS peaks, this is the location of the targetted transcript
oRNA_DC = cgNexusFlat.dataController(aDir, cgOriginRNA.OriginRNA)
id_oRNA = oRNA_DC.load()
if AS == True:
degTccs = [cg.convertToAS(x.tcc) for x in id_oRNA.values()]
else:
degTccs = [x.tcc for x in id_oRNA.values()]
#find all overlapping exons/transcripts, then all results sequences that overlap exons
overlappingExons = allExons.transcriptOverlaps(degTccs)
#print len(overlappingExons), "num of overlapping exons"
overlappingExonTccs = [x.tcc for x in overlappingExons]
overlappingDegTccs = compare.compareTwoTcc(degTccs, overlappingExonTccs, 1)
#write new file
for obj in id_oRNA.values():
if AS:
degTcc = cg.convertToAS(obj.tcc)
else:
degTcc = obj.tcc
if degTcc in overlappingDegTccs:
obj.transcriptOverlap = True
else:
obj.transcriptOverlap = False
oRNA_DC.commit(id_oRNA)
def transcriptSetOverlapTargets(aDir):
geneSetFN = '/home/chrisgre/dataSources/known/Human/geneSets/ensemblAllTranscripts.tsv'
allExons = cgGenes.createGeneSetFromFile(geneSetFN)
#get degradome TCCS
#note that you need to test the AS peaks, this is the location of the targetted transcript
aDC = cgNexusFlat.dataController(aDir, cgAlignment.cgAlignment)
id_alignment = aDC.load()
#create list of unique tccs.
uniqTccs = []
for alignment in id_alignment.values():
chrom, strand, start, end = cg.tccSplit(alignment.tTcc)
offset = alignment.tStart
sLen = alignment.sLength
if strand == '1':
start = start - 19 + offset
end = start + sLen
else:
end = end + 19 - offset
start = end - sLen
tcc = cg.makeTcc(chrom, strand, start, end)
if tcc not in uniqTccs: uniqTccs.append(tcc)
degTccs = [cg.convertToAS(x) for x in uniqTccs]
#find all overlapping exons/transcripts, then all results sequences that overlap exons
overlappingExons = allExons.transcriptOverlaps(degTccs)
overlappingExonTccs = [x.tcc for x in overlappingExons]
overlappingDegTccs = compare.compareTwoTcc(degTccs, overlappingExonTccs, 1)
#update
for obj in id_alignment.values():
chrom, strand, start, end = cg.tccSplit(alignment.tTcc)
offset = alignment.tStart
sLen = alignment.sLength
if strand == '1':
start = start - 19 + offset
end = start + sLen
else:
end = end + 19 - offset
start = end - sLen
tcc = cg.makeTcc(chrom, strand, start, end)
degTcc = cg.convertToAS(tcc)
if degTcc in overlappingDegTccs:
obj.transcriptOverlap = True
else:
obj.transcriptOverlap = False
aDC.commit(id_alignment)
def transcriptSetOverlapTargets(aDir):
geneSetFN = '/home/chrisgre/dataSources/known/Human/geneSets/ensemblAllTranscripts.tsv'
allExons = cgGenes.createGeneSetFromFile(geneSetFN)
#get degradome TCCS
#note that you need to test the AS peaks, this is the location of the targetted transcript
aDC = cgNexusFlat.dataController(aDir, cgAlignment.cgAlignment)
id_alignment = aDC.load()
#create list of unique tccs.
uniqTccs = []
for alignment in id_alignment.values():
chrom, strand, start, end = cg.tccSplit(alignment.tTcc)
offset = alignment.tStart
sLen = alignment.sLength
if strand == '1':
start = start - 19 + offset
end = start + sLen
else:
end = end + 19 - offset
start = end - sLen
tcc = cg.makeTcc(chrom, strand, start, end)
if tcc not in uniqTccs: uniqTccs.append(tcc)
degTccs = [cg.convertToAS(x) for x in uniqTccs]
#find all overlapping exons/transcripts, then all results sequences that overlap exons
overlappingExons = allExons.transcriptOverlaps(degTccs)
overlappingExonTccs = [x.tcc for x in overlappingExons]
overlappingDegTccs = compare.compareTwoTcc(degTccs, overlappingExonTccs, 1)
#update
for obj in id_alignment.values():
chrom, strand, start, end = cg.tccSplit(alignment.tTcc)
offset = alignment.tStart
sLen = alignment.sLength
if strand == '1':
start = start - 19 + offset
end = start + sLen
else:
end = end + 19 - offset
start = end - sLen
tcc = cg.makeTcc(chrom, strand, start, end)
degTcc = cg.convertToAS(tcc)
if degTcc in overlappingDegTccs:
obj.transcriptOverlap = True
else:
obj.transcriptOverlap = False
aDC.commit(id_alignment)
def updateMicroRNAOverlap(aDir, microFN):
oRNA_DC = cgNexusFlat.dataController(aDir, cgOriginRNA.OriginRNA)
id_oRNA = oRNA_DC.load()
#Put micro and small coords into lists
microCoords = []
smallCoords = []
f = open(microFN, 'r')
microCoords = [x.strip() for x in f]
f.close()
smallCoords = [x.tcc for x in id_oRNA.values()]
#overlap them
smallOverlaps = compare.compareTwoTcc(microCoords, smallCoords, 2)
#For each sRNA, save overlap value.
for oRNA in id_oRNA.values():
oRNA.microOverlap = oRNA.tcc in smallOverlaps
oRNA_DC.commit(id_oRNA)
def countForError(oDir, filteredFile):
fList = []
f = open(filteredFile, 'r')
for line in f:
ls = line.strip().split('\t')
fList.append(int(line.strip()))
oID_numTargets = {}
for i in range(0, 10):
print i
simDirRNA = '/home/chrisgre/scripts/simulations/simsk50Filtered/simulation.%s/oRNA' % i
oDC = cgNexusFlat.dataController(simDirRNA, cgOriginRNA.OriginRNA)
id_sRNA = oDC.load()
groupTotal = 0
for id, sRNA in id_sRNA.items():
if not id in fList:
continue
groupTotal += len(sRNA.filteredTargets)
print groupTotal
def countForError(oDir, filteredFile):
fList = []
f = open(filteredFile, 'r')
for line in f:
ls = line.strip().split('\t')
fList.append(int(line.strip()))
oID_numTargets = {}
for i in range(0,10):
print i
simDirRNA = '/home/chrisgre/scripts/simulations/simsk50Filtered/simulation.%s/oRNA' % i
oDC = cgNexusFlat.dataController(simDirRNA, cgOriginRNA.OriginRNA)
id_sRNA = oDC.load()
groupTotal = 0
for id, sRNA in id_sRNA.items():
if not id in fList:
continue
groupTotal += len(sRNA.filteredTargets)
print groupTotal
def updateMicroRNAOverlap(aDir, microFN):
oRNA_DC = cgNexusFlat.dataController(aDir, cgOriginRNA.OriginRNA)
id_oRNA = oRNA_DC.load()
#Put micro and small coords into lists
microCoords = []
smallCoords = []
f = open(microFN, 'r')
microCoords = [x.strip() for x in f]
f.close()
smallCoords = [x.tcc for x in id_oRNA.values()]
#overlap them
smallOverlaps = compare.compareTwoTcc(microCoords, smallCoords, 2)
#For each sRNA, save overlap value.
for oRNA in id_oRNA.values():
oRNA.microOverlap = oRNA.tcc in smallOverlaps
oRNA_DC.commit(id_oRNA)
