def name(fN):
if __name__ == "__main__":
import sys
if sys.argv[1] == "help":
bioLibCG.gd(sys.argv[0])
else:
bioLibCG.submitArgs(globals()[sys.argv[1]], sys.argv[1:])
import bioLibCG
import cgDB
import cgOriginRNA
def probeMicro(oDir):
oDC = cgDB.dataController(oDir, cgOriginRNA.OriginRNA)
id_oRNA = oDC.load()
for oRNA in id_oRNA.values():
if oRNA.passedFilter:
print oRNA.id, oRNA.sequence, oRNA.tcc, oRNA.tccs
if __name__ == "__main__":
import sys
bioLibCG.submitArgs(probeMicro, sys.argv)
import bioLibCG
def parseTargets(fN):
f = open(fN, 'r')
for line in f:
ls = line.strip().split('\t')
micro = ls[3].split(',')
micro.extend(ls[4].split(','))
done = []
for m in micro:
if m != 'None' and (m not in done):
print m
done.append(m)
if __name__ == "__main__":
import sys
bioLibCG.submitArgs(parseTargets, sys.argv)
for line in f:
lChrom, start, end, val = (line.strip().split('\t'))
start, end, val = int(start), int(end), int(val)
if val < 1: continue
#print start, end, val
for i in range(start, end):
try:
hitDict[lChrom][strand][i] += val
except (KeyError,TypeError):
if not lChrom in hitDict:
hitDict[lChrom] = {}
if not strand in hitDict[lChrom]:
hitDict[lChrom][strand] = {}
hitDict[lChrom][strand][i] = val
#write results to wig file
writeWigFromHitDict(hitDict, assembly, name, directory)
if __name__ == "__main__":
import sys
cg.submitArgs(makeWigMem, sys.argv)
#cg.submitArgs(mixWig, sys.argv)
import bioLibCG
def createResultsFile(peakFN, outFN):
f = open(peakFN, 'r')
peaks = [x.strip() for x in f]
f.close()
outF = open(outFN, 'w')
for i, peak in enumerate(peaks):
outF.write('%s\t%s\n' % (i, peak))
if __name__ == "__main__":
import sys
bioLibCG.submitArgs(createResultsFile, sys.argv)
import bioLibCG
def filterDups(fN, oFN):
outF = open(oFN, 'w')
knownSeqs = []
f = open(fN, 'r')
for line in f:
ls = line.strip().split('\t')
seq = ls[1]
if seq not in knownSeqs:
outF.write(line)
knownSeqs.append(seq)
f.close()
outF.close()
if __name__ == "__main__":
import sys
bioLibCG.submitArgs(filterDups, sys.argv)
import bioLibCG
import GenomeFetch
def peakToSeq(peakFN, extend, outFN, assembly):
#extend is +25 for degradome and -6/-4 for oRNA
extend = int(extend)
gf = GenomeFetch.GenomeFetch(assembly)
outF = open(outFN, 'w')
f = open(peakFN, 'r')
for line in f:
ls = line.strip().split('\t')
chrom, strand, start, end = bioLibCG.tccSplit(ls[0])
start, end = start - extend, end + extend
newTcc = bioLibCG.makeTcc(chrom, strand, start, end)
outF.write(gf.getSequence(newTcc) + '\n')
if __name__ == "__main__":
import sys
bioLibCG.submitArgs(peakToSeq, sys.argv)
longestT = transcript
# Get the coordinate ends/etc
starts, ends = [], []
if longestUTR is None:
continue
for utrPair in longestUTR:
starts.append(utrPair[0])
ends.append(utrPair[1])
starts.sort()
ends.sort()
startS = ",".join([str(x) for x in starts])
endS = ",".join([str(x) for x in ends])
print "%s\t%s\t%s\t%s\t%s\t%s" % (
transcript.id,
transcript.parent,
transcript.chromosome,
transcript.strand,
startS,
endS,
)
if __name__ == "__main__":
import sys
bioLibCG.submitArgs(getCoords, sys.argv)
for each duplicate sequence
make set of targets for each oID --> set each oid's targets'''
oNX = cgNexusFlat.Nexus(oFN, cgOriginRNAFlat.OriginRNA)
oNX.load(['sequence', 'filteredTargets'], [rn, tn])
knownSeq_targets = {}
#create oID groups and target sets.
for oID in oNX.sequence:
currSeq = oNX.sequence[oID]
#add targets to set
for tID in oNX.filteredTargets[oID]:
knownSeq_targets.setdefault(currSeq, set()).add(tID)
for oID in oNX.sequence:
currSeq = oNX.sequence[oID]
newTargets = list(knownSeq_targets.get(currSeq, set()))
oNX.filteredTargets[oID] = newTargets
oNX.save()
if __name__ == "__main__":
import sys
bioLibCG.submitArgs(updateSeqDuplicateMultiTcc, sys.argv)
import bioLibCG
import GenomeFetch
def getPeakSequences(peakFN, extend=0):
extend = int(extend)
f = open(peakFN, 'r')
peaks = [x.strip() for x in f]
f.close()
gf = GenomeFetch.GenomeFetch('hg19')
for peak in peaks:
chrom, strand, start, end = bioLibCG.tccSplit(peak)
start = start - extend
end = end + extend
print gf.get_seq_from_to(chrom, start, end, strand)
if __name__ == "__main__":
import sys
bioLibCG.submitArgs(getPeakSequences, sys.argv)
import bioLibCG
def parseTargets(fN):
f = open(fN, 'r')
for line in f:
ls = line.strip().split('\t')
micro = ls[3].split(',')
micro.extend(ls[4].split(','))
done = []
for m in micro:
if m != 'None' and (m not in done):
print m
done.append(m)
if __name__ == "__main__":
import sys
bioLibCG.submitArgs(parseTargets, sys.argv)
ls = line.strip().split('\t')
'''
for i, text in enumerate(ls):
print i, text
'''
tID = ls[0]
chr = 'chr' + ls[1]
strand = ls[4]
tss, tse = ls[2], ls[3]
css, cse = tss, tss
exons = getBracketList(ls[18])
numExons = len(exons)
exonStarts = ','.join([x[0] for x in exons])
exonEnds = ','.join([x[1] for x in exons])
geneName = ls[8]
geneName = ensID_gID.get(geneName, geneName)
stat5 = 'none'
stat3 = 'none'
tCoding = 'pseudogene_noncoding'
unused = 'none'
gCoding = 'pseudogene_noncoding'
print '%s\t%s\t%s\t%s\t%s\t%s\t%s\t%s\t%s\t%s\t%s\t%s\t%s\t%s\t%s\t%s' % (
tID, chr, strand, tss, tse, css, cse, numExons, exonStarts,
exonEnds, geneName, stat5, stat3, tCoding, unused, gCoding)
if __name__ == "__main__":
import sys
bioLibCG.submitArgs(convertPsuedo, sys.argv)
cLength = 1
letters = list(seq)
for i, letter in enumerate(letters):
if i == 0: continue
if letters[i] == letters[i - 1]:
cLength += 1
if cLength > highestLength:
highestLength = cLength
else:
cLength = 1
return highestLength
def filterContigs(fN, outFN):
fOut = open(outFN, 'w')
f = open(fN, 'r')
for line in f:
ls = line.strip().split('\t')
seq = ls[1]
if getContigLength(seq) < 7:
fOut.write(line)
if __name__ == "__main__":
import sys
bioLibCG.submitArgs(filterContigs, sys.argv)
import subprocess
import bioLibCG
import os
def parRun(numParts, memoryAmount, scriptName, *args):
numParts = int(numParts)
for i in xrange(1, numParts + 1):
#specific the correct qJob with correct memory
qJobX = '%s/exec/qJob%s.sh' % (os.environ['HOME'], memoryAmount)
qDo = '%s/exec/qDo.sh' % (os.environ['HOME'])
#construct command to pass
com = [qJobX, qDo, scriptName]
for arg in args:
com.append(arg)
com.append(str(i))
com.append(str(numParts))
#run each job
subprocess.Popen(com).wait()
if __name__ == "__main__":
import sys
bioLibCG.submitArgs(parRun, sys.argv)
codingFlag = None
tTypes = [ x[1] for x in transcript.getOverlappingElements(eSite.tcc)]
if '3UTR' in tTypes:
tType = '3UTR'
elif '5UTR' in tTypes:
tType = '5UTR'
else:
tType = tTypes[0] #has to be one thing...exon or intron
#This only works because UTR takes precedence over EXON in TYPE.
if tType == 'EXON':
if codingTranscript:
codingFlag = 'C'
else:
codingFlag = 'NC'
else:
codingFlag = 'NC'
fOut.write('%s\t%s\t%s\t%s\t%s\t%s\n' % (eSite.ID, transcript.parent, transcript.id, tType, codingFlag, transcript.tType))
#fOut.write('%s:%s:%s\t%s\t%s\t%s\t%s\n' % (eSite.chromosome, eSite.strand, eSite.coordinate, transcript.parent, transcript.id, tType, codingFlag))
fOut.close()
if __name__ == "__main__":
import sys
bioLibCG.submitArgs(updateContext, sys.argv)
complexities = []
seqNumTargets = []
for line in f:
ls = line.strip().split('\t')
id = int(ls[0])
complexity = id_comp[id]
numTargets = float(ls[1])
complexities.append(complexity)
seqNumTargets.append(numTargets)
plt.plot(complexities,
seqNumTargets,
'bo',
label='simulated sRNA',
color='blue')
plt.legend()
plt.ylabel(
'Number of targets per small RNA (filter: O >0-NoMicroTran, T YesTran4Mis > .55 6bp'
)
plt.xlabel('Complexity of smallRNA')
plt.title('Origin RNA Target simulation')
plt.show()
f.close()
if __name__ == "__main__":
import sys
bioLibCG.submitArgs(plotEntropyTargets, sys.argv)
import bioLibCG
from siRnaPredict import getEntropy
def filterEntropy(fN, outFN, minEntropy = 1.15):
minEntropy = float(minEntropy)
fOut = open(outFN, 'w')
f = open(fN, 'r')
for line in f:
ls = line.strip().split('\t')
seq = ls[1]
ent = getEntropy(seq)
if ent > minEntropy:
fOut.write(line)
if __name__ == "__main__":
import sys
bioLibCG.submitArgs(filterEntropy, sys.argv)
import bioLibCG
def numTargets(fN):
f = open(fN, 'r')
for line in f:
ls = line.strip().split('\t')
id, targets = ls[0], ls[4].split(',')
uniq = []
for target in targets:
if target not in uniq:
uniq.append(target)
print id, ','.join(uniq)
if __name__ == "__main__":
import sys
bioLibCG.submitArgs(numTargets, sys.argv)
for line in f:
ls = line.strip().split(' ')
sID = int(ls[0])
tID = int(ls[1])
sOffset = int(ls[4])
try:
mismatchPositions = [(int(x) + sOffset) for x in ls[9].split(',')]
except IndexError:
mismatchPositions = []
ss = id_qSeq[sID]
ts = id_dSeq[tID]
sSpaces = ''.join([' ' for i in list(range(0,sOffset))])
tSpaces = [' ' for i in list(ts)]
for i in mismatchPositions:
tSpaces[i] = 'X'
#graphically display
print ts
print ''.join(tSpaces)
print '%s%s' % (sSpaces, ss)
print
if __name__ == "__main__":
import sys
bioLibCG.submitArgs(checkAlignment, sys.argv)
compareList = zip(mCodonList, emCodonList)
codonNumber = ePositionInMRNA // 3
codonPair = compareList[codonNumber]
bCodon = codonPair[0]
aCodon = codonPair[1]
baa = cgSeqMod.translateRNA(bCodon, map)
aaa = cgSeqMod.translateRNA(aCodon, map)
synFlag = 'SYN'
if baa != aaa:
synFlag = 'NON'
bCodonList = list(bCodon)
aCodonList = list(aCodon)
matchedLetters = zip(bCodonList, aCodonList)
for pair in matchedLetters:
if pair[0] != 'A':
if pair[1] == 'G' and pair[0] != 'G':
print 'messed up codon switch', bCodonList, aCodonList
print t.parent, '%s:%s' % (
eSite.chromosome, eSite.coordinate
), eSite.strand, bCodon, aCodon, baa, aaa
outF.write('\t'.join([
str(eSite.ID), transcript.parent, transcript.id, synFlag,
bCodon, aCodon, baa, aaa
]) + '\n')
if __name__ == "__main__":
import sys
bioLibCG.submitArgs(betterSynonymous, sys.argv)
import bioLibCG
import cgAlign
def createDatabases(targetsFN, wordSize, runName):
wordSize = int(wordSize)
# make sequence list out of targets, make db, write to file
f = open(targetsFN, "r")
seqList = []
print "obtaining sequences"
i = 0
for line in f:
seqList.append(cgAlign.cgSeq(i, line.strip()))
i += 1
f.close()
print "making word db"
wordDB = cgAlign.createWordDatabase(seqList, wordSize)
cgAlign.writeWordDatabase(wordDB, runName)
print "making seq db"
seqDB = cgAlign.createSequenceDatabase(seqList)
cgAlign.writeSequenceDatabase(seqDB, runName)
if __name__ == "__main__":
import sys
bioLibCG.submitArgs(createDatabases, sys.argv)
print a.tTcc, a.id
aDC.commit(id_alignment)
def appendTranInfo(aDir, degSmallFN):
aDC = cgDB.dataController(aDir, cgAlignment)
id_alignment = aDC.load()
tID_tranVal = {}
f = open(degSmallFN, 'r')
for line in f:
ls = line.strip().split('\t')
val = int(ls[3])
if val == 1: val = True
if val == 0: val = False
tID_tranVal[int(ls[0])] = val
for alignment in id_alignment.values():
transcriptOverlap = tID_tranVal[alignment.tID]
alignment.transcriptOverlap = transcriptOverlap
aDC.commit(id_alignment)
if __name__ == "__main__":
import sys
bioLibCG.submitArgs(loadAlignments, sys.argv)
import bioLibCG
import compareData
import cgEdit
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)
if __name__ == "__main__":
import sys
bioLibCG.submitArgs(overlapWithDegradome, sys.argv)
import bioLibCG
def uniqueColumn(fN, column, whole=False):
u = {}
f = open(fN, 'r')
for line in f:
ls = line.strip().split('\t')
u[ls[int(column)]] = line.strip()
if whole:
for i in u:
print u[i]
else:
for i in u:
print i
if __name__ == "__main__":
import sys
bioLibCG.submitArgs(uniqueColumn, sys.argv)
import bioLibCG
import cgEdit
def getEditInfo(fN, idList):
eSites = cgEdit.loadEditingSites(fN)
idDict = {}
for eSite in eSites:
idDict[eSite.ID] = eSite
list = []
f = open(idList, 'r')
for line in f:
ls = line.strip().split('\t')
list.append(int(ls[0]))
for id in list:
eSite = idDict[id]
print eSite.ID, '%s:%s' % (eSite.chromosome, eSite.coordinate), eSite.gene, eSite.eRatio
if __name__ == "__main__":
import sys
bioLibCG.submitArgs(getEditInfo, sys.argv)
def plotContextPie(oDir, contextFN):
oDC = cgDB.dataController(oDir, cgOriginRNA.OriginRNA)
id_oRNA = oDC.load()
oID_tTypes = {}
f = open(contextFN, 'r')
for line in f:
ls = line.strip().split('\t')
id = int(ls[0])
tType = ls[5]
oID_tTypes.setdefault(id, []).append(tType)
tType_count = {}
for oRNA in id_oRNA.values():
if not oRNA.passedFilter:
continue
for tType in oID_tTypes[oRNA.id]:
num = tType_count.get(tType, 0)
tType_count[tType] = num + 1
for tType, count in tType_count.items():
print tType, count
if __name__ == "__main__":
import sys
bioLibCG.submitArgs(plotContextPie, sys.argv)
import subprocess
import bioLibCG
import os
def parRun(numParts, memoryAmount, scriptName, *args):
numParts = int(numParts)
for i in xrange(1, numParts + 1):
#specific the correct qJob with correct memory
qJobX = '%s/exec/qJob%s.sh' % (os.environ['HOME'], memoryAmount)
qDo = '%s/exec/qDo.sh' % (os.environ['HOME'])
#construct command to pass
com = [qJobX, qDo, scriptName]
for arg in args:
com.append(arg)
com.append(str(i))
com.append(str(numParts))
#run each job
subprocess.Popen(com).wait()
if __name__ == "__main__":
import sys
bioLibCG.submitArgs(parRun, sys.argv)
if gType == t:
#totalNum += 1.0/lg
#theSum += 1.0/lg
totalNum += 1.0
theSum += 1
fracs.append(totalNum)
labels = [
'Introns (%s)' % fracs[0],
'Intergenic(%s)' % fracs[1],
'Exons (%s)' % fracs[2],
'3\'UTR (%s)' % fracs[3],
'5\'UTR (%s)' % fracs[4]
]
fracs = [float(x) / theSum for x in fracs]
explode = (0.1, 0.1, 0.2, 0.1, 0.1)
pie(fracs, explode=explode, labels=labels, autopct='%1.1f%%', shadow=True)
title('Editing Site Genomic Location',
bbox={
'facecolor': '1.0',
'pad': 10
})
show()
if __name__ == "__main__":
import sys
bioLibCG.submitArgs(makeContextPieBetter, sys.argv)
import bioLibCG
import matplotlib.pyplot as plt
import siRnaPredict as si
def makeComplexityHist(fN):
f = open(fN, 'r')
histVals = []
for line in f:
ls = line.strip().split('\t')
name = ls[3]
seq = ls[4]
if 'hsa' in name:
histVals.append(si.getEntropy(seq))
plt.hist(histVals, 30)
plt.show()
if __name__ == "__main__":
import sys
bioLibCG.submitArgs(makeComplexityHist, sys.argv)
import bioLibCG
def addIDs(fN, outFN):
fOut = open(outFN, 'w')
i = 0
f = open(fN, 'r')
for line in f:
fOut.write('%s\t%s\n' % (i, line.strip()))
i += 1
fOut.close()
if __name__ == "__main__":
import sys
bioLibCG.submitArgs(addIDs, sys.argv)
newLines = []
for line in f:
ls = line.strip().split('\t')
degTcc = cg.convertToAS(ls[1])
chrom, strand, start, end = cg.tccSplit(degTcc)
if chrom != runningChrom:
continue
if strand != runningStrand:
continue
inTran = '0'
for i in xrange(start, end + 1):
if i in coordSet:
inTran = '1'
break
#update newLines
newLine = cg.appendToLine(line, inTran, 3)
newLines.append(newLine)
f.close()
f = open(degFile + '.%s.%s' % (runningChrom, runningStrand), 'w')
f.writelines(newLines)
f.close()
if __name__ == "__main__":
import sys
cg.submitArgs(globals()[sys.argv[1]], sys.argv[1:])
def subtractTwoTccLists(tccListKeep, tccListOther):
#Both Lists should already be COLLAPSED!!!
if checkIfOverlaps(tccListKeep):
print 'THE KEEPER LIST HAS OVERLAPS (SUBTRACTION)'
if checkIfOverlaps(tccListOther):
print 'THE OTHER LIST HAS OVERLAPS (SUBTRACTION)'
overlapKeep = compareTwoTcc(tccListKeep, tccListOther, 1)
overlapOther = compareTwoTcc(tccListKeep, tccListOther, 2)
subList = recurseSubtract(overlapKeep, overlapOther)
#print 'subList:', subList
#for those that didn't overlap return them
newSeqs = [] # make a new list so as to not overwrite the other.
newSeqs.extend(tccListKeep)
for tcc in overlapKeep:
newSeqs.remove(tcc)
newSeqs.extend(subList)
return newSeqs
if __name__ == "__main__":
import sys
bioLibCG.submitArgs(getIndividualOverlaps, sys.argv)
pRuns
--run.00
----oRNA (slave: pRuns/run.00/oRNA)
----aDir
--run.01
'''
mDC = cgDB.dataController(masterDir, cgAlignment.cgAlignment)
id_masterObj = mDC.load()
#recurse through all the runs
masterBN = bioLibCG.getBaseFileName(masterDir)
for slaveDir in bioLibCG.recursePaths(parDir, end = masterBN):
oDC = cgDB.dataController(slaveDir, cgAlignment.cgAlignment)
id_slaveObj = oDC.load()
id_masterObj = cgDB.mergeTwoObjects(id_masterObj, id_slaveObj, cgOriginRNA.OriginRNA)
mDC.commit(id_masterObj)
def mergeDir(dirName):
cgDB.mergeDirectory(dirName, cgOriginRNA.OriginRNA)
if __name__ == "__main__":
import sys
bioLibCG.submitArgs(mergeDir, sys.argv)
import bioLibCG
def formatFile(fN):
f = open(fN, 'r')
for line in f:
ls = line.strip().split('\t')
newList = []
newList.extend(ls[1:11])
newList.extend(ls[12:])
print '\t'.join(newList)
if __name__ == "__main__":
import sys
bioLibCG.submitArgs(formatFile, sys.argv)
midCheck = 0
highCheck = 0
#check mismatches
for i in lowRange:
if i in alignment.mismatchPositions:
lowCheck = 1
break
for i in midRange:
if i in alignment.mismatchPositions:
midCheck = 1
break
for i in highRange:
if i in alignment.mismatchPositions:
highCheck = 1
break
fOut.write('%s\t%s\t%s\t%s\t%s\n' % (sID, tID, lowCheck, midCheck, highCheck))
f.close()
if __name__ == "__main__":
import sys
#bioLibCG.submitArgs(markMismatchedPairs, sys.argv)
bioLibCG.submitArgs(markCenterExpression, sys.argv)
import bioLibCG
def blankIDs(fN, outFN, numIDs=None):
'''Make a file with X number of blank IDs, or as many as there is lines in a file'''
if numIDs:
numIDs = int(numIDs)
else:
numIDs = bioLibCG.getNumFileLines(fN)
newLines = []
for i in xrange(0, numIDs):
newLines.append('%s\n' % i)
f = open(outFN, 'w')
f.writelines(newLines)
f.close()
if __name__ == "__main__":
import sys
bioLibCG.submitArgs(blankIDs, sys.argv)
fracs = []
theSum = 0.0
for t in types:
totalNum = 0.0
for gene in geneDict:
lg = len(geneDict[gene])
for gType in geneDict[gene]:
if gType == t:
#totalNum += 1.0/lg
#theSum += 1.0/lg
totalNum += 1.0
theSum += 1
fracs.append(totalNum)
labels = ['Introns (%s)' % fracs[0], 'Intergenic(%s)' % fracs[1], 'Exons (%s)' % fracs[2], '3\'UTR (%s)' % fracs[3], '5\'UTR (%s)' % fracs[4]]
fracs = [float(x)/theSum for x in fracs]
explode=(0.1, 0.1, 0.2, 0.1, 0.1)
pie(fracs, explode=explode, labels=labels, autopct='%1.1f%%', shadow=True)
title('Editing Site Genomic Location', bbox={'facecolor':'1.0', 'pad':10})
show()
if __name__ == "__main__":
import sys
bioLibCG.submitArgs(makeContextPieBetter, sys.argv)
import bioLibCG
import cgEdit
import GenomeFetch
def getFolded(fN):
eSites = cgEdit.loadEditingSites(fN)
gf = GenomeFetch.GenomeFetch('hg19')
for eSite in eSites:
#Get +/- 200 bp of eSite
chrom, strand, coord = eSite.chromosome, eSite.strand, eSite.coordinate
start, end = coord - 200, coord + 200
seq = gf.get_seq_from_to(chrom, start, end, strand)
print '>', eSite.ID
print seq
if __name__ == "__main__":
import sys
bioLibCG.submitArgs(getFolded, sys.argv)
import bioLibCG
def countUniqueID(fN):
f = open(fN, 'r')
countDict = {}
for line in f:
id = line.strip().split('\t')[0]
countDict[id] = line.strip()
f.close()
print len(countDict)
for i in countDict:
print countDict[i]
if __name__ == "__main__":
import sys
bioLibCG.submitArgs(countUniqueID, sys.argv)
----oRNA (slave: pRuns/run.00/oRNA)
----aDir
--run.01
'''
mDC = cgDB.dataController(masterDir, cgAlignment.cgAlignment)
id_masterObj = mDC.load()
#recurse through all the runs
masterBN = bioLibCG.getBaseFileName(masterDir)
for slaveDir in bioLibCG.recursePaths(parDir, end=masterBN):
oDC = cgDB.dataController(slaveDir, cgAlignment.cgAlignment)
id_slaveObj = oDC.load()
id_masterObj = cgDB.mergeTwoObjects(id_masterObj, id_slaveObj,
cgOriginRNA.OriginRNA)
mDC.commit(id_masterObj)
def mergeDir(dirName):
cgDB.mergeDirectory(dirName, cgOriginRNA.OriginRNA)
if __name__ == "__main__":
import sys
bioLibCG.submitArgs(mergeDir, sys.argv)
f.readline()
for line in f:
ls = line.strip().split('\t')
'''
for i, text in enumerate(ls):
print i, text
'''
tID = ls[0]
chr = 'chr' + ls[1]
strand = ls[4]
tss, tse = ls[2], ls[3]
css, cse = tss, tss
exons = getBracketList(ls[18])
numExons = len(exons)
exonStarts = ','.join([x[0] for x in exons])
exonEnds = ','.join([x[1] for x in exons])
geneName = ls[8]
geneName = ensID_gID.get(geneName, geneName)
stat5 = 'none'
stat3 = 'none'
tCoding = 'pseudogene_noncoding'
unused = 'none'
gCoding = 'pseudogene_noncoding'
print '%s\t%s\t%s\t%s\t%s\t%s\t%s\t%s\t%s\t%s\t%s\t%s\t%s\t%s\t%s\t%s' % (tID, chr, strand, tss, tse, css, cse, numExons, exonStarts, exonEnds, geneName, stat5, stat3, tCoding, unused, gCoding)
if __name__ == "__main__":
import sys
bioLibCG.submitArgs(convertPsuedo, sys.argv)
codingTranscript = '_coding' in transcript.tType
tType = None
codingFlag = None
tTypes = [x[1] for x in transcript.getOverlappingElements(oRNA.tcc)]
#categorize border types
tType = ds.spotItem(tTypes)
if tType == 'EXON' or 'EXON_INTRON':
if codingTranscript:
codingFlag = 'C'
else:
codingFlag = 'NC'
else:
codingFlag = 'NC'
oRNA.transcriptIDs.append(transcript.id)
oRNA.transcriptContexts.append(tType)
oRNA.transcriptTypes.append(transcript.tType)
oRNA.transcriptCodingTypes.append(codingFlag)
oDC.commit(id_oRNA)
if __name__ == "__main__":
import sys
bioLibCG.submitArgs(updateContext, sys.argv)
import bioLibCG
import cgDB
import cgOriginRNA
def getSeqs(oDir):
oDC = cgDB.dataController(oDir, cgOriginRNA.OriginRNA)
id_oRNA = oDC.load()
for id, oRNA in id_oRNA.items():
if oRNA.sequenceDuplicate:
continue
if oRNA.totalContigLength > 6:
continue
if oRNA.endContigLength > 6:
continue
print "%s" % id
if __name__ == "__main__":
import sys
bioLibCG.submitArgs(getSeqs, sys.argv)
import bioLibCG
import cgDB
import cgAlignment
def probeAlignments(aDir):
probePairs = [[6, 35934]]
aDC = cgDB.dataController(aDir, cgAlignment.cgAlignment)
id_alignment = aDC.load()
for alignment in id_alignment.values():
for sID, tID in probePairs:
if alignment.sID == sID and alignment.tID == tID:
print alignment.id, alignment.sID, alignment.tID, alignment.centerExpression, alignment.mismatchStatus, alignment.numMismatches, alignment.transcriptOverlap
if __name__ == "__main__":
import sys
bioLibCG.submitArgs(probeAlignments, sys.argv)
rects1 = ax.bar(ind, menMeans, width, color='r')
womenMeans = (49344, 43652, 40213, 36490, 25724, 6236, 5237, 4639, 4108, 2774)
womenStd = (220,209,202,191,152,13,12,11,11,9)
rects2 = ax.bar(ind+width, womenMeans, width, color='y', yerr=womenStd)
# add some
ax.set_ylabel('Total Number of Targets')
ax.set_xlabel('descriptor (a:b:c)\n a = # bp from center where NO mismatches allowed\n b = # of bp from center where at least c% of degradome expression must be found')
ax.set_title('Total SNR')
ax.set_xticks(ind+width)
ax.set_xticklabels( ('4.6.30', '4.6.50', '4.6.60', '4.6.70', '4.6.90', '6.6.30', '6.6.50', '6.6.60', '6.6.70', '6.6.90'))
ax.axis([0,10,0,70000])
ax.legend( (rects1[0], rects2[0]), ('Observed', 'Simulated') )
def autolabel(rects):
# attach some text labels
for rect in rects:
height = rect.get_height()
ax.text(rect.get_x()+rect.get_width()/2., 1.05*height, '%d'%int(height), ha='center', va='bottom')
autolabel(rects1)
autolabel(rects2)
plt.show()
if __name__ == "__main__":
import sys
bioLibCG.submitArgs(plotBarSNR, sys.argv)
import bioLibCG
import compareData
import cgEdit
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)
if __name__ == "__main__":
import sys
bioLibCG.submitArgs(overlapWithDegradome, sys.argv)
import bioLibCG
def targetCount(fN):
targetDict = {}
f = open(fN, 'r')
for line in f:
ls = line.strip().split('\t')
targets = ls[4].split(',')
for target in targets:
if target in targetDict:
targetDict[target] += 1
else:
targetDict[target] = 1
for target in targetDict:
print target + '\t' + str(targetDict[target])
if __name__ == "__main__":
import sys
bioLibCG.submitArgs(targetCount, sys.argv)
f = open(degFile, 'r')
newLines = []
for line in f:
ls = line.strip().split('\t')
degTcc = cg.convertToAS(ls[1])
chrom, strand, start, end = cg.tccSplit(degTcc)
if chrom != runningChrom:
continue
if strand != runningStrand:
continue
inTran = '0'
for i in xrange(start, end + 1):
if i in coordSet:
inTran = '1'
break
#update newLines
newLine = cg.appendToLine(line, inTran, 3)
newLines.append(newLine)
f.close()
f = open(degFile + '.%s.%s' % (runningChrom, runningStrand), 'w')
f.writelines(newLines)
f.close()
if __name__ == "__main__":
import sys
cg.submitArgs(globals()[sys.argv[1]], sys.argv[1:])
for i,letter in enumerate(seq):
if i == 0: continue
if seq[i] == seq[i-1]:
cLength5 += 1
else:
break
#3'
cLength = 1
revSeq = [x for x in reversed(seq)]
for i,letter in enumerate(revSeq):
if i == 0: continue
if revSeq[i] == revSeq[i-1]:
cLength += 1
else:
break
highest = cLength5
if cLength > cLength5:
highest = cLength
oRNA.endContigLength = highest
oDC.commit(id_oRNA)
if __name__ == "__main__":
import sys
bioLibCG.submitArgs(updateEndContig, sys.argv)
bioLibCG.submitArgs(updateTotalContig, sys.argv)
highRange = range(7, 15)
lowCheck = 0
midCheck = 0
highCheck = 0
#check mismatches
for i in lowRange:
if i in alignment.mismatchPositions:
lowCheck = 1
break
for i in midRange:
if i in alignment.mismatchPositions:
midCheck = 1
break
for i in highRange:
if i in alignment.mismatchPositions:
highCheck = 1
break
fOut.write('%s\t%s\t%s\t%s\t%s\n' %
(sID, tID, lowCheck, midCheck, highCheck))
f.close()
if __name__ == "__main__":
import sys
#bioLibCG.submitArgs(markMismatchedPairs, sys.argv)
bioLibCG.submitArgs(markCenterExpression, sys.argv)
mmVal = mmDict[sID][tID]
if mmVal == 1:
continue
#check center Expression
centerVal = centerDict[sID][tID]
if centerVal < minCenterLevel:
continue
newTargetList.append(str(tID))
if len(newTargetList) < 1: continue
newTargets = ','.join(newTargetList)
#update newLines
newLines.append(bioLibCG.appendToLine(line, newTargets, int(updatePosition)))
f.close()
#update file
f = open(outFN, 'w')
f.writelines(newLines)
f.close()
if __name__ == "__main__":
import sys
bioLibCG.submitArgs(filterTargets, sys.argv)
if fChrom != chrom: continue
print ' ', fN, fChrom
f = open(fN, 'r')
f.readline() #header
strand = cg.getBaseFileName(fN).strip().split('.')[-2]
for line in f:
lChrom, start, end, val = (line.strip().split('\t'))
start, end, val = int(start), int(end), int(val)
if val < 1: continue
#print start, end, val
for i in range(start, end):
try:
hitDict[lChrom][strand][i] += val
except (KeyError, TypeError):
if not lChrom in hitDict:
hitDict[lChrom] = {}
if not strand in hitDict[lChrom]:
hitDict[lChrom][strand] = {}
hitDict[lChrom][strand][i] = val
#write results to wig file
writeWigFromHitDict(hitDict, assembly, name, directory)
if __name__ == "__main__":
import sys
cg.submitArgs(makeWigMem, sys.argv)
#cg.submitArgs(mixWig, sys.argv)
import cgDB
import cgOriginRNA
import bioLibCG
def probeORNA(oDir):
oDC = cgDB.dataController(oDir, cgOriginRNA.OriginRNA)
id_oRNA = oDC.load()
for oRNA in id_oRNA.values():
if oRNA.passedFilter:
cgOriginRNA.prettyPrint(oRNA)
if __name__ == "__main__":
import sys
bioLibCG.submitArgs(probeORNA, sys.argv)
for i,letter in enumerate(seq):
if i == 0: continue
if seq[i] == seq[i-1]:
cLength5 += 1
else:
break
#3'
cLength = 1
revSeq = [x for x in reversed(seq)]
for i,letter in enumerate(revSeq):
if i == 0: continue
if revSeq[i] == revSeq[i-1]:
cLength += 1
else:
break
highest = cLength5
if cLength > cLength5:
highest = cLength
oNX.endContigLength[oID] = highest
oNX.save()
if __name__ == "__main__":
import sys
bioLibCG.submitArgs(updateEndContig, sys.argv)
bioLibCG.submitArgs(updateTotalContig, sys.argv)
import bioLibCG
def fixup(eFN, tableFN):
coord_gName = {}
coord_eRatio = {}
f = open(eFN, 'r')
for line in f:
ls = line.strip().split('\t')
coord = '%s:%s' % (ls[0], ls[1])
gName = ls[3]
eRatio = ls[6]
coord_gName[coord] = gName
coord_eRatio[coord] = eRatio
f = open(tableFN, 'r')
for line in f:
ls = line.strip().split('\t')
coord = 'chr%s:%s' % (ls[0], ls[1])
ls.append(coord_eRatio[coord])
if ls[3] == 'NONE':
ls[3] = coord_gName[coord]
print '\t'.join(ls)
if __name__ == "__main__":
import sys
bioLibCG.submitArgs(fixup, sys.argv)
def createDatabases(targetsFN, wordSize, runName, hasIDs=False):
wordSize = int(wordSize)
hasIDs = (hasIDs == "True")
print 'using IDs', hasIDs
#make sequence list out of targets, make db, write to file
f = open(targetsFN, 'r')
seqList = []
print 'obtaining sequences'
i = 0
for line in f:
if hasIDs:
theID, seq = line.strip().split('\t')
else:
theID, seq = i, line.strip()
seqList.append(cgAlign.cgSeq(theID, seq))
i += 1
f.close()
print 'making word db'
wordDB = cgAlign.createWordDatabase(seqList, wordSize)
cgAlign.writeWordDatabase(wordDB, runName)
print 'making seq db'
seqDB = cgAlign.createSequenceDatabase(seqList)
cgAlign.writeSequenceDatabase(seqDB, runName)
if __name__ == "__main__":
import sys
bioLibCG.submitArgs(createDatabases, sys.argv)
import bioLibCG
import cgGenes3
import cgSeqMod
def testit(gFN):
geneSet = cgGenes3.createGeneSetEditing(gFN)
map = cgSeqMod.loadCodonMap('hg19')
for gene in geneSet.genes:
for transcript in gene.transcripts:
try:
print ''
mRNA = transcript.getMRNA(coding = True)
i = transcript.getRelativePositionMRNA(35872409)
if i == -1:
continue
print transcript.id
print i
print mRNA[:i], mRNA[i], mRNA[i + 1:]
print cgSeqMod.translateRNA(mRNA, map)
except:
pass
if __name__ == "__main__":
import sys
bioLibCG.submitArgs(testit, sys.argv)
#error checks
if len(c) > (keyPositions[-1] + 1):
raise NameError("non-keyword arguments can not follow kw args")
if continuityCheck(keyPositions):
raise NameError("two keyword designations in a row!")
for kw in possibleKeywords:
if c.count(kw) > 1:
raise NameError("keyword was used twice!")
#update nonkw
newNonkw = [x for x in nonkw[:keyPositions[0]]]
#update kw
for position in keyPositions:
key, val = nonkw[position], nonkw[position + 1]
kw[key] = val
return dFxn(*newNonkw, **kw)
return wrapped
if __name__ == "__main__":
import sys
if sys.argv[1] == "help":
bioLibCG.gd(sys.argv[0])
else:
bioLibCG.submitArgs(globals()[sys.argv[1]], sys.argv[1:])
#3UTR
if strand == '1':
if cEnd + 1 == tStart or cEnd + 1 == tEnd + 1:
p.tell('3 is none')
c += 1
if codingStatus:
e += 1
range3 = ()
else:
range3 = (cEnd + 1, tEnd)
else:
if cStart == tStart or cStart == tEnd + 1:
p.tell('3 is none')
c += 1
if codingStatus:
e += 1
range3 = ()
else:
range3 = (tStart, cStart - 1)
a += 1
print a, b, c, d, e
if __name__ == "__main__":
import sys
if sys.argv[1] == "help":
bioLibCG.gd(sys.argv[0])
else:
bioLibCG.submitArgs(globals()[sys.argv[1]], sys.argv[1:])
import bioLibCG
import cgEdit
def getEditInfo(fN, idList):
eSites = cgEdit.loadEditingSites(fN)
idDict = {}
for eSite in eSites:
idDict[eSite.ID] = eSite
list = []
f = open(idList, 'r')
for line in f:
ls = line.strip().split('\t')
list.append(int(ls[0]))
for id in list:
eSite = idDict[id]
print eSite.ID, '%s:%s' % (eSite.chromosome,
eSite.coordinate), eSite.gene, eSite.eRatio
if __name__ == "__main__":
import sys
bioLibCG.submitArgs(getEditInfo, sys.argv)
