def transcriptOverlaps(self, tccs):
'''return list of overlapping transcripts'''
if not isinstance(tccs, type([])):
print 'transcript overlaps: NEED TCC LIST, not a single tcc!'
return 1
print 'num of tccs being compared', len(tccs)
#gather all transcript tccs(make tcc --> id).
tccDict = {}
for gene in self.genes:
for transcript in gene.transcripts:
if transcript.tcc in tccDict:
tccDict[transcript.tcc].append(transcript.id)
else:
tccDict[transcript.tcc] = [transcript.id]
print 'num of tcc transcript tccs', len(tccDict.keys())
overlapped = compare.compareTwoTcc(tccDict.keys(), tccs, 1)
tList = []
for gene in self.genes:
for transcript in gene.transcripts:
if transcript.tcc in overlapped:
tList.append(transcript)
return tList
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 = cgDB.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 transcriptOverlaps(self, tccs):
'''return list of overlapping transcripts'''
if not isinstance(tccs, type([])):
print 'transcript overlaps: NEED TCC LIST, not a single tcc!'
return 1
print 'num of tccs being compared', len(tccs)
#gather all transcript tccs(make tcc --> id).
tccDict = {}
for gene in self.genes:
for transcript in gene.transcripts:
if transcript.tcc in tccDict:
tccDict[transcript.tcc].append(transcript.id)
else:
tccDict[transcript.tcc] = [transcript.id]
print 'num of tcc transcript tccs', len(tccDict.keys())
overlapped = compare.compareTwoTcc(tccDict.keys(), tccs, 1)
tList = []
for gene in self.genes:
for transcript in gene.transcripts:
if transcript.tcc in overlapped:
tList.append(transcript)
return tList
def compareMouseHuman(mFN, hFNLift):
aDC = cgNexusFlat.Nexus(mFN, cgOriginRNAFlat.OriginRNA)
aDC.load(['tcc'])
bTccs = []
f = open(hFNLift, 'r')
for line in f:
ls = line.strip().split('\t')
bTccs.append(ls[0])
aTccs = []
for id in aDC.tcc:
aTccs.append(aDC.tcc[id])
print compareTwoTcc(aTccs, bTccs, amount=True)
def compareTwoMouse(aFN, bFN):
aDC = cgNexusFlat.Nexus(aFN, cgOriginRNAFlat.OriginRNA)
aDC.load(['tcc'])
bDC = cgNexusFlat.Nexus(bFN, cgOriginRNAFlat.OriginRNA)
bDC.load(['tcc'])
aTccs = []
bTccs = []
for id in aDC.tcc:
aTccs.append(aDC.tcc[id])
for id in bDC.tcc:
bTccs.append(bDC.tcc[id])
print compareTwoTcc(aTccs, bTccs, amount=True)
def compareMouseHuman(mFN, hFNLift):
aDC = cgNexusFlat.Nexus(mFN, cgOriginRNAFlat.OriginRNA)
aDC.load(['tcc'])
bTccs = []
f = open(hFNLift, 'r')
for line in f:
ls = line.strip().split('\t')
bTccs.append(ls[0])
aTccs = []
for id in aDC.tcc:
aTccs.append(aDC.tcc[id])
print compareTwoTcc(aTccs, bTccs, amount = True)
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 = cgDB.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 = cgDB.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 compareTwoMouse(aFN, bFN):
aDC = cgNexusFlat.Nexus(aFN, cgOriginRNAFlat.OriginRNA)
aDC.load(['tcc'])
bDC = cgNexusFlat.Nexus(bFN, cgOriginRNAFlat.OriginRNA)
bDC.load(['tcc'])
aTccs = []
bTccs = []
for id in aDC.tcc:
aTccs.append(aDC.tcc[id])
for id in bDC.tcc:
bTccs.append(bDC.tcc[id])
print compareTwoTcc(aTccs, bTccs, amount = True)
def splitExonsIntrons(cName = None):
mConf = c.cgConfig('Main.conf')
conf = c.getConfig(cName)
#init
organism = conf.conf['organism']
minOverlap = 50
cHairs = getHairpins.getHairpins() #CID: HAIRPIN
exonList = compare.tccFileToList('%sExons.tcc' % organism, 0)
hairpins = []
for CID in cHairs:
hairpins.append(cHairs[CID])
print 'checking overlaps'
#check which hairpins overlap exons and by how much
exonOverlapped = compare.compareTwoTcc(hairpins, exonList, 1, amount = True)
print ' ', len(exonOverlapped)
print 'removing partial introns'
#remove the ones that didn't overlap more than X:
remList = []
for tcc, oAmount in exonOverlapped:
if oAmount < minOverlap:
remList.append([tcc, oAmount])
for item in remList:
exonOverlapped.remove(item)
print ' ', len(exonOverlapped), 'out of', len(cHairs.keys())
#get CIDs of exons
exonCIDs = []
for tcc, oAmount in exonOverlapped:
for CID in cHairs:
if cHairs[CID] == tcc:
exonCIDs.append(str(CID))
#Open sorted predictions and write lines with CIDs to respective files
predFile = open(conf.conf['resultsSorted'], 'r')
exonFile = open(conf.conf['resultsSorted'] + '.exons', 'w')
intronFile = open(conf.conf['resultsSorted'] + '.introns', 'w')
for line in predFile:
if line.split('\t')[7] in exonCIDs:
exonFile.write(line)
else:
intronFile.write(line)
predFile.close()
exonFile.close()
intronFile.close()
def splitExonsIntrons(cName=None):
mConf = c.cgConfig('Main.conf')
conf = c.getConfig(cName)
#init
organism = conf.conf['organism']
minOverlap = 50
cHairs = getHairpins.getHairpins() #CID: HAIRPIN
exonList = compare.tccFileToList('%sExons.tcc' % organism, 0)
hairpins = []
for CID in cHairs:
hairpins.append(cHairs[CID])
print 'checking overlaps'
#check which hairpins overlap exons and by how much
exonOverlapped = compare.compareTwoTcc(hairpins, exonList, 1, amount=True)
print ' ', len(exonOverlapped)
print 'removing partial introns'
#remove the ones that didn't overlap more than X:
remList = []
for tcc, oAmount in exonOverlapped:
if oAmount < minOverlap:
remList.append([tcc, oAmount])
for item in remList:
exonOverlapped.remove(item)
print ' ', len(exonOverlapped), 'out of', len(cHairs.keys())
#get CIDs of exons
exonCIDs = []
for tcc, oAmount in exonOverlapped:
for CID in cHairs:
if cHairs[CID] == tcc:
exonCIDs.append(str(CID))
#Open sorted predictions and write lines with CIDs to respective files
predFile = open(conf.conf['resultsSorted'], 'r')
exonFile = open(conf.conf['resultsSorted'] + '.exons', 'w')
intronFile = open(conf.conf['resultsSorted'] + '.introns', 'w')
for line in predFile:
if line.split('\t')[7] in exonCIDs:
exonFile.write(line)
else:
intronFile.write(line)
predFile.close()
exonFile.close()
intronFile.close()
def reportDifference(oldFN, newFN):
f = open(oldFN, 'r')
oldList = [x for x in f]
oldCoords = [x.strip().split('\t')[0] for x in oldList]
f.close()
f = open(newFN, 'r')
newList = [x for x in f]
newCoords = [x.strip().split('\t')[0] for x in newList]
f.close()
bothList = []
bothList.extend(newList)
bothList.extend(oldList)
bothCoords = compareData.compareTwoTcc(oldCoords, newCoords, 1)
onlyOld = []
for x in oldCoords:
if x not in bothCoords:
onlyOld.append(x)
onlyNew = []
for x in newCoords:
if x not in bothCoords:
onlyNew.append(x)
print 'Both'
knownList = []
for x in bothCoords:
for y in bothList:
if x in y:
print y.strip()
knownList.append(y)
break
print 'old'
for y in oldList:
if y not in knownList:
print y.strip()
print 'new'
for y in newList:
if y not in knownList:
print y.strip()
def reportDifference(oldFN, newFN):
f = open(oldFN, 'r')
oldList = [x for x in f]
oldCoords = [x.strip().split('\t')[0] for x in oldList]
f.close()
f = open(newFN, 'r')
newList = [x for x in f]
newCoords = [x.strip().split('\t')[0] for x in newList]
f.close()
bothList = []
bothList.extend(newList)
bothList.extend(oldList)
bothCoords = compareData.compareTwoTcc(oldCoords, newCoords, 1)
onlyOld = []
for x in oldCoords:
if x not in bothCoords:
onlyOld.append(x)
onlyNew = []
for x in newCoords:
if x not in bothCoords:
onlyNew.append(x)
print 'Both'
knownList = []
for x in bothCoords:
for y in bothList:
if x in y:
print y.strip()
knownList.append(y)
break
print 'old'
for y in oldList:
if y not in knownList:
print y.strip()
print 'new'
for y in newList:
if y not in knownList:
print y.strip()
def overlapWithDegradome(dFN, eFN):
eSites = cgEdit.loadEditingSites(eFN)
degTccs = []
f = open(dFN, 'r')
for line in f:
ls = line.strip().split('\t')
chrom, strand, start, end = bioLibCG.tccSplit(ls[1])
start = start - 3
end = end + 3
degTccs.append(bioLibCG.makeTcc(chrom, strand, start, end))
print degTccs[0:5]
eTccs = [eSite.tcc for eSite in eSites]
overlaps = compareData.compareTwoTcc(eTccs, degTccs, 1)
print len(overlaps)
def overlapWithDegradome(dFN, eFN):
eSites = cgEdit.loadEditingSites(eFN)
degTccs = []
f = open(dFN, "r")
for line in f:
ls = line.strip().split("\t")
chrom, strand, start, end = bioLibCG.tccSplit(ls[1])
start = start - 3
end = end + 3
degTccs.append(bioLibCG.makeTcc(chrom, strand, start, end))
print degTccs[0:5]
eTccs = [eSite.tcc for eSite in eSites]
overlaps = compareData.compareTwoTcc(eTccs, degTccs, 1)
print len(overlaps)
def countWithBins(dFN, binDir, type = 'INTRON'):
print 'loading degradome'
dNX = cgNexusFlat.Nexus(dFN, cgDegPeak.Peak)
dNX.load(['tcc'])
print 'loading bins'
bins = []
for i in range(50):
bins.append([])
for chrom in bioLibCG.humanChromosomes:
for strand in ('1', '-1'):
f = open(binDir + '/%s.%s.%s.bins' % (type, chrom, strand), 'r')
for line in f:
ls = line.strip().split('\t')
tccs = ls[1:51]
for i in range(0,50):
bins[i].append(tccs[i])
#collect dTtcs in list
dTccs = []
for dID in dNX.tcc:
tcc = dNX.tcc[dID]
c, s, st, en = bioLibCG.tccSplit(tcc)
if s == '1':
s = '-1'
en = st
else:
s = '1'
st = en
dTccs.append(bioLibCG.makeTcc(c,s,st,en))
print len(dTccs), len(bins[0])
for i in range(0, 50):
print i
overlaps = compareData.compareTwoTcc(dTccs, bins[i], 1)
print len(overlaps)
print overlaps
def compareTccs(humanFN, liftCoords, rn = None, tn = None):
'''compare if there is an overlap between a mouse alignment and any human'''
mouseList = []
f = open(liftCoords, 'r')
for line in f:
ls = line.strip().split('\t')
mouseList.append(ls[0])
humanList = []
DC = cgNexusFlat.Nexus(humanFN, cgOriginRNAFlat.OriginRNA)
DC.load(['tcc'], [rn, tn])
for id in DC.tcc:
humanList.append(DC.tcc[id])
mouseList = list(set(mouseList))
humanList = list(set(humanList))
x = compareData.compareTwoTcc(humanList, mouseList)
for i in x:
print i
def compareTccs(humanFN, liftCoords, rn=None, tn=None):
'''compare if there is an overlap between a mouse alignment and any human'''
mouseList = []
f = open(liftCoords, 'r')
for line in f:
ls = line.strip().split('\t')
mouseList.append(ls[0])
humanList = []
DC = cgNexusFlat.Nexus(humanFN, cgOriginRNAFlat.OriginRNA)
DC.load(['tcc'], [rn, tn])
for id in DC.tcc:
humanList.append(DC.tcc[id])
mouseList = list(set(mouseList))
humanList = list(set(humanList))
x = compareData.compareTwoTcc(humanList, mouseList)
for i in x:
print i
def updateMicroRNAOverlap(aDir, microFN):
oRNA_DC = cgDB.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 countWithBins(dFN, binDir, type='INTRON'):
print 'loading degradome'
dNX = cgNexusFlat.Nexus(dFN, cgDegPeak.Peak)
dNX.load(['tcc'])
print 'loading bins'
bins = []
for i in range(50):
bins.append([])
for chrom in bioLibCG.humanChromosomes:
for strand in ('1', '-1'):
f = open(binDir + '/%s.%s.%s.bins' % (type, chrom, strand), 'r')
for line in f:
ls = line.strip().split('\t')
tccs = ls[1:51]
for i in range(0, 50):
bins[i].append(tccs[i])
#collect dTtcs in list
dTccs = []
for dID in dNX.tcc:
tcc = dNX.tcc[dID]
c, s, st, en = bioLibCG.tccSplit(tcc)
if s == '1':
s = '-1'
en = st
else:
s = '1'
st = en
dTccs.append(bioLibCG.makeTcc(c, s, st, en))
print len(dTccs), len(bins[0])
for i in range(0, 50):
print i
overlaps = compareData.compareTwoTcc(dTccs, bins[i], 1)
print len(overlaps)
print overlaps
def transcriptSetOverlapDegFile(degFile):
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
degTccs = []
f = open(degFile, 'r')
for line in f:
ls = line.strip().split('\t')
degTccs.append(ls[1])
f.close()
degTccs = [cg.convertToAS(x) for x in degTccs]
#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)
f = open(degFile, 'r')
newLines = []
for line in f:
degTcc = cg.convertToAS(ls[1])
inTran = '0'
if degTcc in overlappingDegTccs:
inTran = '1'
#update newLines
newLine = cg.appendToLine(line, inTran, 3)
f.close()
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 transcriptSetOverlapDegFile(degFile):
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
degTccs = []
f = open(degFile, 'r')
for line in f:
ls = line.strip().split('\t')
degTccs.append(ls[1])
f.close()
degTccs = [cg.convertToAS(x) for x in degTccs]
#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)
f = open(degFile, 'r')
newLines = []
for line in f:
degTcc = cg.convertToAS(ls[1])
inTran = '0'
if degTcc in overlappingDegTccs:
inTran = '1'
#update newLines
newLine = cg.appendToLine(line, inTran, 3)
f.close()
def getOverlappingTranscriptList(self, tccs):
"""given tccs, return the transcripts that overlap with them in a single list"""
if not isinstance(tccs, type([])):
# print 'transcript overlaps: NEED TCC LIST, not a single tcc!'
return 1
# print 'num of tccs being compared', len(tccs)
# gather all transcript tccs(make tcc --> id).
tccDict = {}
for gene in self.genes:
for transcript in gene.transcripts:
tccDict[transcript.tcc] = 1
# print 'num of tcc transcript tccs', len(tccDict.keys())
overlapped = compare.compareTwoTcc(tccDict.keys(), tccs, 1)
tList = []
for gene in self.genes:
for transcript in gene.transcripts:
if transcript.tcc in overlapped:
tList.append(transcript)
return tList
def getOverlappingTranscriptList(self, tccs):
'''given tccs, return the transcripts that overlap with them in a single list'''
if not isinstance(tccs, type([])):
#print 'transcript overlaps: NEED TCC LIST, not a single tcc!'
return 1
#print 'num of tccs being compared', len(tccs)
#gather all transcript tccs(make tcc --> id).
tccDict = {}
for gene in self.genes:
for transcript in gene.transcripts:
tccDict[transcript.tcc] = 1
#print 'num of tcc transcript tccs', len(tccDict.keys())
overlapped = compare.compareTwoTcc(tccDict.keys(), tccs, 1)
tList = []
for gene in self.genes:
for transcript in gene.transcripts:
if transcript.tcc in overlapped:
tList.append(transcript)
return tList
#get results that are only noncoding
import bioLibCG as cg
import compareData as compare
predName = '/home/chrisgre/projects/NoncodingMouse/results/NCmouse-s3k8b17.bothNCandC.results'
keepList = compare.tccFileToList('keepNoncoding.tcc', 0)
predList = compare.tccFileToList(predName, 1)
keepers = compare.compareTwoTcc(predList, keepList, 1)
print len(keepers)
#now go back through pred file and create a new file with only lines that have noncoding in them
predFile = open(predName, 'r')
outFile = open('NCmouse.noncoding.results', 'w')
predLines = predFile.readlines()
predFile.close()
newLines = {}
for keeper in keepers:
for line in predLines:
if keeper in line:
newLines[line] = 1
for line in newLines:
outFile.write(line)
frameLength = 200
frameShift = 1
for cluster in sortedClusters:
#grab first and last coordinate from cluster, for each cluster deduce how many theoretical microRNAs were in hitScope
clusterChrom = cluster[0].split(":")[0]
clusterStrand = cluster[0].split(":")[1]
firstCoord = int(cluster[0].split(":")[2])
#print cluster[-1]
lastCoord = int(cluster[-1].split(":")[3])
startCoord = firstCoord
while startCoord < lastCoord:
#count how many hits there are in this range
rangeStart = startCoord - (frameLength/2)
rangeEnd = startCoord + (frameLength/2)
rangeTcc = '%s:%s:%s:%s' % (clusterChrom, clusterStrand, rangeStart, rangeEnd)
overlappedList = compare.compareTwoTcc([rangeTcc], cluster, 2)
hitCount = len(overlappedList)
#output
outputFile.write('%s\t%s\n' % (rangeTcc, hitCount))
startCoord = startCoord + frameShift #check overlap with range
outputFile.close()
print 'Output Hits per Frame:', timer.split()
print 'Overall Time:', timer.report()
def defineClusters(cName=None):
#Start Timer
timer = cg.cgTimer()
timer.start()
#Get list of mature tccs
conf = cgConfig.getConfig(cName) #passed or default
finalMirFileName = conf.conf['resultsRaw']
matureTccs = compare.tccFileToList(finalMirFileName,
1) # list of all mature micro in tcc
print 'List getting', timer.split()
#make connections dict
matureConnections = compare.makeConnectionsDict(matureTccs)
print 'Make connections:', timer.split()
#Now have to define Clusters...
clusters = []
addedList = []
#I don't think python passes by reference? also I think this function is in the middle because it uses a global variable :P
def createClusters(item=None, mode=None):
if item in addedList:
return 0
elif mode == "top":
clusters.append([item])
addedList.append(
item) ##creates new cluster with the item already stored in it
for connectedItem in matureConnections[item]:
createClusters(connectedItem, "neighbor")
elif mode == "neighbor":
clusters[-1].append(
item) #add this item to the last cluster created
addedList.append(item)
for connectedItem in matureConnections[item]:
createClusters(connectedItem, "neighbor")
for tcc in matureTccs:
createClusters(tcc, "top")
print 'Make Clusters', timer.split()
#Sort Clusters.
sortedClusters = []
for cluster in clusters:
sortedClusters.append(cg.sortTccList(cluster))
print 'Sort Clusters:', timer.split()
#Output sorted cluster file
clusterFileName = conf.conf['sortedClusters']
clusterFile = open(clusterFileName, 'w')
for cluster in sortedClusters:
for hit in cluster:
clusterFile.write('%s,' % hit)
clusterFile.write('\n')
clusterFile.close()
'''
#re-create sortedClusters list:
clusterFileName = 'sortedClusters.data'
clusterFile = open(clusterFileName, 'r')
sortedClusters = []
for line in clusterFile:
sortedClusters.append([])
line = line.strip()[0:-1] #take off last comma ;P
for hit in (line.strip().split(',')):
sortedClusters[-1].append(hit)
'''
print 'Store intermediate data:', timer.split()
#output hitsAround file
outputFile = open(conf.conf['hitsPerFrame'], 'w')
frameLength = 200
frameShift = 1
for cluster in sortedClusters:
#grab first and last coordinate from cluster, for each cluster deduce how many theoretical microRNAs were in hitScope
clusterChrom = cluster[0].split(":")[0]
clusterStrand = cluster[0].split(":")[1]
firstCoord = int(cluster[0].split(":")[2])
#print cluster[-1]
lastCoord = int(cluster[-1].split(":")[3])
startCoord = firstCoord
while startCoord < lastCoord:
#count how many hits there are in this range
rangeStart = startCoord - (frameLength / 2)
rangeEnd = startCoord + (frameLength / 2)
rangeTcc = '%s:%s:%s:%s' % (clusterChrom, clusterStrand,
rangeStart, rangeEnd)
overlappedList = compare.compareTwoTcc([rangeTcc], cluster, 2)
hitCount = len(overlappedList)
#output
outputFile.write('%s\t%s\n' % (rangeTcc, hitCount))
startCoord = startCoord + frameShift #check overlap with range
outputFile.close()
print 'Output Hits per Frame:', timer.split()
print 'Overall Time:', timer.report()
def defineClusters(cName = None):
#Start Timer
timer = cg.cgTimer()
timer.start()
#Get list of mature tccs
conf = cgConfig.getConfig(cName) #passed or default
finalMirFileName = conf.conf['resultsRaw']
matureTccs = compare.tccFileToList(finalMirFileName, 1) # list of all mature micro in tcc
print 'List getting', timer.split()
#make connections dict
matureConnections = compare.makeConnectionsDict(matureTccs)
print 'Make connections:', timer.split()
#Now have to define Clusters...
clusters = []
addedList = []
#I don't think python passes by reference? also I think this function is in the middle because it uses a global variable :P
def createClusters(item = None, mode = None):
if item in addedList:
return 0
elif mode == "top":
clusters.append([item])
addedList.append(item) ##creates new cluster with the item already stored in it
for connectedItem in matureConnections[item]:
createClusters(connectedItem, "neighbor")
elif mode == "neighbor":
clusters[-1].append(item) #add this item to the last cluster created
addedList.append(item)
for connectedItem in matureConnections[item]:
createClusters(connectedItem, "neighbor")
for tcc in matureTccs:
createClusters(tcc, "top")
print 'Make Clusters', timer.split()
#Sort Clusters.
sortedClusters = []
for cluster in clusters:
sortedClusters.append(cg.sortTccList(cluster))
print 'Sort Clusters:', timer.split()
#Output sorted cluster file
clusterFileName = conf.conf['sortedClusters']
clusterFile = open(clusterFileName, 'w')
for cluster in sortedClusters:
for hit in cluster:
clusterFile.write('%s,' % hit)
clusterFile.write('\n')
clusterFile.close()
'''
#re-create sortedClusters list:
clusterFileName = 'sortedClusters.data'
clusterFile = open(clusterFileName, 'r')
sortedClusters = []
for line in clusterFile:
sortedClusters.append([])
line = line.strip()[0:-1] #take off last comma ;P
for hit in (line.strip().split(',')):
sortedClusters[-1].append(hit)
'''
print 'Store intermediate data:', timer.split()
#output hitsAround file
outputFile = open(conf.conf['hitsPerFrame'], 'w')
frameLength = 200
frameShift = 1
for cluster in sortedClusters:
#grab first and last coordinate from cluster, for each cluster deduce how many theoretical microRNAs were in hitScope
clusterChrom = cluster[0].split(":")[0]
clusterStrand = cluster[0].split(":")[1]
firstCoord = int(cluster[0].split(":")[2])
#print cluster[-1]
lastCoord = int(cluster[-1].split(":")[3])
startCoord = firstCoord
while startCoord < lastCoord:
#count how many hits there are in this range
rangeStart = startCoord - (frameLength/2)
rangeEnd = startCoord + (frameLength/2)
rangeTcc = '%s:%s:%s:%s' % (clusterChrom, clusterStrand, rangeStart, rangeEnd)
overlappedList = compare.compareTwoTcc([rangeTcc], cluster, 2)
hitCount = len(overlappedList)
#output
outputFile.write('%s\t%s\n' % (rangeTcc, hitCount))
startCoord = startCoord + frameShift #check overlap with range
outputFile.close()
print 'Output Hits per Frame:', timer.split()
print 'Overall Time:', timer.report()
