doCDS = False
limitNeighbor = True
if '-force':
limitNeighbor = False
hitRDS = readDataset(hitfile, verbose=True, cache=doCache)
readlen = hitRDS.getReadSize()
normalizationFactor = 1.0
if normalizeBins:
totalCount = len(hitRDS)
normalizationFactor = totalCount / 1000000.
hitDict = hitRDS.getReadsDict(doMulti=True, findallOptimize=True)
hg = Genome(genome)
idb = geneinfoDB(cache=doCache)
gidBins = {}
gidLen = {}
geneinfoDict = idb.getallGeneInfo(genome)
if doFlank:
locusByChromDict = getLocusByChromDict(hg,
upstream=upstreamBp,
downstream=downstreamBp,
useCDS=doCDS,
additionalRegionsDict=acceptDict,
keepSense=True,
adjustToNeighbor=limitNeighbor)
else:
locusByChromDict = getLocusByChromDict(hg,
print 'usage: python %s genome GOID1 [GOID2 ....] [-outfile outfilename] [-append] [-restrict genefile]'
sys.exit(1)
genome = sys.argv[1]
writeOut = False
if '-outfile' in sys.argv:
writeOut = True
outfilename = sys.argv[sys.argv.index('-outfile') + 1]
restrict = False
if '-restrict' in sys.argv:
restrictfilename = sys.argv[sys.argv.index('-restrict') + 1]
restrict = True
hg = Genome(genome)
idb = geneinfoDB()
GOIDlist = []
for arg in sys.argv:
if 'GO:' in arg:
GOIDlist.append(arg)
print sys.argv
print GOIDlist
firstGeneList = []
for GOID in GOIDlist:
testList = hg.allGIDsbyGOID(GOID)
print 'GOID: %s (%d)' % (GOID, len(testList))
firstGeneList += testList
pass
#Main program
if len(sys.argv) < 3:
print 'usage: python2.5 %s genome snpsfile nondbsnp_geneinfo_outfile' % sys.argv[
0]
sys.exit(1)
outStr = ""
genome = sys.argv[1]
snpfile = sys.argv[2]
outfilename = sys.argv[3]
infile = file(snpfile, 'r')
hg = Genome(genome)
additionalDict = {}
outS = ""
outfile = open(outfilename, 'w')
outfile.write(
"#Sl\tCl\tchrom\tmis pos\t\tmatch\tuniq_mis\ttot_mis\tbase_chg\tknown_snp\tfunction\tgene\tgeneId\trpkm\n"
)
for line in infile:
if line[0] == '#':
continue
fields = line.split()
if fields[8].find('N\A') == -1:
outfile.write(line)
else:
outS = ''
if '-cache' in sys.argv:
doCache = True
printSeq = False
if '-printseq' in sys.argv:
printSeq = True
maxPvalue = 0.0001
mot = Motif('', motifFile=motfilename)
motLen = len(mot)
bestScore = mot.bestConsensusScore()
if hasMotifExtension:
print "will use cistematic.core.motif C-extension to speed up motif search"
hg = Genome(genome)
# minHits=-1 will force regions to be used regardless
# maxDist= 0 prevents merging of non-overlapping regions
if '-nomerge' in sys.argv:
regions = getMergedRegions(infilename,
maxDist=0,
minHits=-1,
verbose=True,
doMerge=False,
keepPeak=usePeak)
else:
regions = getMergedRegions(infilename,
maxDist=0,
minHits=-1,
verbose=True,
def main(argv):
if len(argv) < 4:
print 'usage: python %s genome gtf outfilename [-polyA length]' % argv[0]
sys.exit(1)
genome = argv[1]
gtf=argv[2]
outputfilename = argv[3]
doPolyA=False
if '-polyA' in argv:
doPolyA=True
tailsize=int(argv[argv.index('-polyA')+1])
tail=''
for i in range(tailsize):
tail=tail+'A'
print 'will add a polyA tail of ', tailsize, 'nt'
outfile = open(outputfilename, 'w')
hg = Genome(genome)
j=0
lineslist = open(gtf)
TranscriptDict={}
for line in lineslist:
j+=1
if j % 100000 == 0:
print j, 'lines processed'
if line.startswith('#'):
continue
fields=line.strip().split('\t')
if fields[2]!='exon':
continue
if 'transcript_name "' in fields[8]:
TranscriptID=fields[8].split('transcript_name "')[1].split('";')[0]
else:
TranscriptID=fields[8].split('transcript_id "')[1].split('";')[0]
if TranscriptDict.has_key(TranscriptID):
pass
else:
TranscriptDict[TranscriptID]=[]
chr=fields[0]
left=int(fields[3])
right=int(fields[4])
orientation=fields[6]
TranscriptDict[TranscriptID].append((chr,left,right,orientation))
g=0
print 'Found', len(TranscriptDict.keys()), 'transcripts'
for transcript in TranscriptDict.keys():
g+=1
if g % 1000 == 0:
print g, 'transcripts sequences processed'
sequence=''
leftEnds=[]
rightEnds=[]
TranscriptDict[transcript].sort()
orientation = TranscriptDict[transcript][0][3]
if orientation=='+' or orientation=='F':
for (chr,left,right,orientation) in TranscriptDict[transcript]:
leftEnds.append(left)
rightEnds.append(right)
try:
sequence=sequence+hg.sequence(chr[3:len(chr)],left,right-left)
print "can't retrieve sequence"
except:
for p in range(left,right-left):
try:
sequence=sequence+hg.sequence(chr[3:len(chr)],p,1)
except:
sequence=sequence+'N'
missed+=1
sense='plus_strand'
if orientation=='-' or orientation=='R':
for (chr,left,right,orientation) in reversed(TranscriptDict[transcript]):
leftEnds.append(left)
rightEnds.append(right)
try:
exonsequence=hg.sequence(chr[3:len(chr)],left-1,right-left+1)
sequence=sequence+getReverseComplement(exonsequence)
except:
for p in range(left-1,right-left+1):
try:
sequence=sequence+getReverseComplement(hg.sequence(chr[3:len(chr)],p,1))
except:
sequence=sequence+'N'
missed+=1
sense='minus_strand'
LeftEnd=min(leftEnds)
RightEnd=max(rightEnds)
outline='>'+transcript+':'+chr+':'+str(LeftEnd)+'-'+str(RightEnd)+'-'+sense
outfile.write(outline+'\n')
if doPolyA:
outfile.write(sequence+tail+'\n')
else:
outfile.write(sequence+'\n')
outfile.close()
from cistematic.genomes import Genome
print '%s: version 1.1' % sys.argv[0]
if len(sys.argv) < 5:
print 'usage: python %s genome merlen chrAny:start-stop outfile' % sys.argv[
0]
sys.exit(1)
genome = sys.argv[1]
merlen = int(sys.argv[2])
location = sys.argv[3]
outfilename = sys.argv[4]
(chrom, pos) = location.split(':')
chrom = chrom[3:]
(start, stop) = pos.split('-')
start = int(start)
regionlength = int(stop) - start + 1
hg = Genome(genome)
seq = hg.sequence(chrom, start, regionlength)
outfile = open(outfilename, 'w')
print 'writing %d %d-mers' % (regionlength - merlen, merlen)
for index in range(regionlength - merlen):
outfile.write(seq[index:index + merlen].upper() + '\n')
outfile.close()
def main(argv):
if len(argv) < 4:
print 'usage: python %s genome gtf outfilename [-polyA length]' % argv[
0]
sys.exit(1)
genome = argv[1]
gtf = argv[2]
outputfilename = argv[3]
doPolyA = False
if '-polyA' in argv:
doPolyA = True
tailsize = int(argv[argv.index('-polyA') + 1])
tail = ''
for i in range(tailsize):
tail = tail + 'A'
print 'will add a polyA tail of ', tailsize, 'nt'
outfile = open(outputfilename, 'w')
hg = Genome(genome)
j = 0
lineslist = open(gtf)
TranscriptDict = {}
for line in lineslist:
j += 1
if j % 100000 == 0:
print j, 'lines processed'
if line.startswith('#'):
continue
fields = line.strip().split('\t')
if fields[2] != 'exon':
continue
if 'transcript_name "' in fields[8]:
TranscriptID = fields[8].split('transcript_name "')[1].split(
'";')[0]
else:
TranscriptID = fields[8].split('transcript_id "')[1].split('";')[0]
if TranscriptDict.has_key(TranscriptID):
pass
else:
TranscriptDict[TranscriptID] = []
chr = fields[0]
left = int(fields[3])
right = int(fields[4])
orientation = fields[6]
TranscriptDict[TranscriptID].append((chr, left, right, orientation))
g = 0
print 'Found', len(TranscriptDict.keys()), 'transcripts'
for transcript in TranscriptDict.keys():
g += 1
if g % 1000 == 0:
print g, 'transcripts sequences processed'
sequence = ''
leftEnds = []
rightEnds = []
TranscriptDict[transcript].sort()
orientation = TranscriptDict[transcript][0][3]
if orientation == '+' or orientation == 'F':
for (chr, left, right, orientation) in TranscriptDict[transcript]:
leftEnds.append(left)
rightEnds.append(right)
try:
sequence = sequence + hg.sequence(chr[3:len(chr)], left,
right - left)
print "can't retrieve sequence"
except:
for p in range(left, right - left):
try:
sequence = sequence + hg.sequence(
chr[3:len(chr)], p, 1)
except:
sequence = sequence + 'N'
missed += 1
sense = 'plus_strand'
if orientation == '-' or orientation == 'R':
for (chr, left, right,
orientation) in reversed(TranscriptDict[transcript]):
leftEnds.append(left)
rightEnds.append(right)
try:
exonsequence = hg.sequence(chr[3:len(chr)], left - 1,
right - left + 1)
sequence = sequence + getReverseComplement(exonsequence)
except:
for p in range(left - 1, right - left + 1):
try:
sequence = sequence + getReverseComplement(
hg.sequence(chr[3:len(chr)], p, 1))
except:
sequence = sequence + 'N'
missed += 1
sense = 'minus_strand'
LeftEnd = min(leftEnds)
RightEnd = max(rightEnds)
outline = '>' + transcript + ':' + chr + ':' + str(
LeftEnd) + '-' + str(RightEnd) + '-' + sense
outfile.write(outline + '\n')
if doPolyA:
outfile.write(sequence + tail + '\n')
else:
outfile.write(sequence + '\n')
outfile.close()
fullOnly = False
if '-fullOnly' in sys.argv:
fullOnly = True
#mot = Motif('',motifFile = motifDir + 'NRSE2.mot')
#motL = Motif('',motifFile = motifDir + 'NRSE2left.mot')
#motR = Motif('',motifFile = motifDir + 'NRSE2right.mot')
mot = Motif('',motifFile = motifDir + 'NRSE3.mot')
motL = Motif('',motifFile = motifDir + 'NRSE3left.mot')
motR = Motif('',motifFile = motifDir + 'NRSE3right.mot')
bestScore = mot.bestConsensusScore()
bestLeft = motL.bestConsensusScore()
bestRight = motR.bestConsensusScore()
hg = Genome(genome)
regions = getMergedRegions(infilename, maxDist=0, minHits=-1, verbose=doVerbose, doMerge=False)
outfile = open(outfilename,'w')
outfile.write('#dataset: %s\tregions:%s\tnormalize: %s\tmarkov1: %s\n' % (chipfilename, infilename, normalize, doMarkov1))
outfile.write('#enforcePeakDist: %s\tpeakdist: %d bp\tfullOnly: %d bp\n' % (enforcePeakDist, maxpeakdist, fullOnly))
outfile.write('#site\tscore\tleftscore\trightscore\tRPM\tpeakDist\ttype\theight\tfractionHeight\tregion\tsense\tseq\n')
countList = []
posList = []
index = 0
regionList = []
for rchrom in regions:
doCache = False
if '-cache' in sys.argv:
doCache = True
bins = 10
standardMinThresh = standardMinDist / bins
hitRDS = readDataset(hitfile, verbose=True, cache=doCache)
readlen = hitRDS.getReadSize()
normalizationFactor = 1.0
if normalize:
totalCount = len(hitRDS)
normalizationFactor = totalCount / 1000000.
hg = Genome(genome)
idb = geneinfoDB(cache=True)
gidDict = {}
geneinfoDict = idb.getallGeneInfo(genome)
featuresDict = hg.getallGeneFeatures()
#infile = open(infilename)
outfile = open(outfilename, 'w')
gidList = hg.allGIDs()
gidList.sort()
for gid in gidList:
symbol = 'LOC' + gid
geneinfo = ''
featureList = []
altPosList.append(altPos)
posLine[pos] = line
if trackStrand:
if 'RNAFARP' in line:
posStrand[pos] = '+'
posStrand[altPos] = '+'
else:
posStrand[pos] = '-'
posStrand[altPos] = '-'
geneList = []
geneDict = {}
if maxRadius < step:
step = maxRadius - 2
hg = Genome(genome, inRAM=True)
if extendGenome != '':
hg.extendFeatures(extendGenome, replace=replaceModels)
geneannotDict = hg.allAnnotInfo()
#featureTypes = ['CDS'] + hg.getFeatureTypes('UT%')
featureTypes = ['CDS', 'UTR']
for radius in range(1, maxRadius, step):
print 'radius %d' % radius
print len(posList)
if radius == 1:
posDict = genesIntersecting(genome,
posList,
extendGen=extendGenome,
replaceMod=replaceModels)
else:
RDS = readDataset(rdsfile, verbose=True, cache=doCache)
rdsChromList = RDS.getChromosomes()
if doVerbose:
print time.ctime()
distinct = 0
total = 0
outfile = open(outfilename, 'w')
idb = geneinfoDB()
if genome == 'dmelanogaster':
geneinfoDict = idb.getallGeneInfo(genome, infoKey='locus')
else:
geneinfoDict = idb.getallGeneInfo(genome)
hg = Genome(genome)
geneannotDict = hg.allAnnotInfo()
assigned = {}
farConnected = {}
for achrom in rdsChromList:
if achrom == 'chrM':
continue
print achrom
uniqDict = RDS.getReadsDict(fullChrom=True,
chrom=achrom,
noSense=True,
withFlag=True,
withPairID=True,
doUniqs=True,
readIDDict=True)
extendGenome = ''
replaceModels = False
if '-models' in sys.argv:
extendGenome = sys.argv[sys.argv.index('-models') + 1]
if '-replacemodels' in sys.argv:
replaceModels = True
print "will replace gene models with %s" % extendGenome
else:
print "will extend gene models with %s" % extendGenome
doCache = False
cachePages = 0
if '-cache' in sys.argv:
cacheGeneDB(genome)
hg = Genome(genome, dbFile=chooseDB(genome), inRAM=True)
idb = geneinfoDB(cache=True)
print '%s cached' % genome
doCache = True
cachePages = int(sys.argv[sys.argv.index('-cache') + 1])
else:
hg = Genome(genome, inRAM=True)
idb = geneinfoDB()
if extendGenome != '':
hg.extendFeatures(extendGenome, replace=replaceModels)
hitRDS = readDataset(hitfile, verbose=True, cache=doCache)
if cachePages > hitRDS.getDefaultCacheSize():
hitRDS.setDBcache(cachePages)
psyco.full()
except:
pass
from cistematic.genomes import Genome
from math import log
import os.path
import sys
print '%s: version 2.1' % sys.argv[0]
if len(sys.argv) < 6:
print 'usage: python %s genome outimage gofileroot1 title1 cohortsize1 [gofileroot2 title2 cohortsize2 ...] [-fontsize pts] [-length in] [-width in]' % sys.argv[
0]
sys.exit(1)
hg = Genome(sys.argv[1])
allgodesc = hg.allGOterms()
godesc = []
import matplotlib
matplotlib.use('Agg')
from pylab import *
doGray = False
rootdir = './'
imagename = sys.argv[2]
options = 0
fontSize = 5
extendGenome = ''
replaceModels = False
if '-models' in sys.argv:
extendGenome = sys.argv[sys.argv.index('-models') + 1]
if '-replacemodels' in sys.argv:
replaceModels = True
print "will replace gene models with %s" % extendGenome
else:
print "will extend gene models with %s" % extendGenome
doCache = False
if '-cache' in sys.argv:
doCache = True
cacheGeneDB(genome)
hg = Genome(genome, dbFile=chooseDB(genome), inRAM=True)
print '%s cached' % genome
else:
hg = Genome(genome, inRAM=True)
if extendGenome != '':
hg.extendFeatures(extendGenome, replace=replaceModels)
RDS = readDataset(hitfile, verbose=True, cache=doCache, reportCount=False)
uniqcount = RDS.getUniqsCount()
print '%d unique reads' % uniqcount
splicecount = 0
countDict = {}
gidList = []
farList = []
for line in infile:
if line[0] == '#':
continue
fields = line.split('\t')
chrom = fields[2][3:]
start = int(fields[3])
pos = (chrom, start)
posList.append(pos)
posLine[pos] = line
geneList = []
geneDict = {}
geneSense = {}
hg = Genome(genome)
#featureTypes = ['CDS'] + hg.getFeatureTypes('UT%')
featureTypes = ['CDS', 'UTR']
for ftype in featureTypes:
if flankBP > 0:
posDict = genesIntersecting(genome, posList, flank=flankBP)
else:
posDict = genesIntersecting(genome, posList)
for pos in posDict:
#print pos
geneID = posDict[pos][0][0]
try:
symbol = geneinfoDict[geneID][0][0]
except:
symbol = 'LOC' + geneID
try:
outfilename = sys.argv[3]
# maxBorder should be readlen - 4
maxBorder = int(sys.argv[4])
doVerbose = False
if '-verbose' in sys.argv:
doVerbose = True
spacer = 2
if '-spacer' in sys.argv:
spacer = int(sys.argv[sys.argv.index('-spacer') + 1])
spacerseq = 'N' * spacer
datafile = open(datafilename)
#seqfile = open('knownGeneMrna.txt')
hg = Genome(genome)
spliceCountDict = {}
exonStartDict = {}
exonStopDict = {}
exonLengthDict = {}
nameToChromDict = {}
nameToComplementDict = {}
alreadySeen = {}
counter = 0
for line in datafile:
fields = line.split()
name = fields[0]
spliceCount = int(fields[7]) - 1
if spliceCount < 1:
doDataset = False
if '-dataset' in sys.argv:
if usePeaks:
print "ignoring dataset and relying on peak data"
else:
hitfile = sys.argv[sys.argv.index('-dataset') + 1]
doDataset = True
hitRDS = readDataset(hitfile, verbose=True, cache=doCache)
readlen = hitRDS.getReadSize()
doCompact = False
if '-compact' in sys.argv:
doCompact = True
hg = Genome(genome)
outfile = open(outfilename, 'w')
#readlen = readSize(hitfile)
#hitDict = getReadDict(hitfile)
if doCompact:
regionDict = getMergedRegions(regionfile,
minHits=minHitThresh,
verbose=True,
chromField=0,
compact=True,
keepPeak=usePeaks,
returnTop=topRegions)
else:
regionDict = getMergedRegions(regionfile,
def main(argv):
if len(argv) < 3:
print 'usage: python %s genome gtf outfilename [-spliced] [-class_code symbol]' % argv[0]
print ' this script will output the translation of all three possible reading frames; stop codons will be converted to a .'
sys.exit(1)
genome = argv[1]
gtf=argv[2]
outputfilename = argv[3]
doSpliced=False
if '-spliced' in argv:
doSpliced=True
print 'will only look at transciprs with more than one exon'
doClassCode=False
if '-class_code' in argv:
doClassCode=True
class_code=argv[argv.index('-class_code')+1]
print 'will only look at transciprs if class code', class_code
CodonDict={'GCU':'A', 'GCC':'A', 'GCA':'A', 'GCG':'A',
'UUA':'L', 'UUG':'L', 'CUU':'L', 'CUC':'L', 'CUA':'L', 'CUG':'L',
'CGU':'R', 'CGC':'R', 'CGA':'R', 'CGG':'R', 'AGA':'R', 'AGG':'R',
'AAA':'K', 'AAG':'K',
'AAU':'N', 'AAC':'N',
'AUG':'M',
'GAU':'D', 'GAC':'D',
'UUU':'F', 'UUC':'F',
'UGU':'C', 'UGC':'C',
'CCU':'P', 'CCC':'P', 'CCA':'P', 'CCG':'P',
'CAA':'Q', 'CAG':'Q',
'UCU':'S', 'UCC':'S', 'UCA':'S', 'UCG':'S', 'AGU':'S', 'AGC':'S',
'GAA':'E', 'GAG':'E',
'ACU':'T', 'ACC':'T', 'ACA':'T', 'ACG':'T',
'GGU':'G', 'GGC':'G', 'GGA':'G', 'GGG':'G',
'UGG':'W',
'CAU':'H', 'CAC':'H',
'UAU':'Y', 'UAC':'Y',
'AUU':'I', 'AUC':'I', 'AUA':'I',
'GUU':'V', 'GUC':'V', 'GUA':'V', 'GUG':'V',
'START':'AUG',
'UAA':'.',
'UGA':'.',
'UAG':'.'}
outfile = open(outputfilename, 'w')
hg = Genome(genome)
j=0
lineslist = open(gtf)
TranscriptDict={}
for line in lineslist:
j+=1
if j % 100000 == 0:
print j, 'lines processed'
if line.startswith('#'):
continue
fields=line.strip().split('\t')
if fields[2]!='exon':
continue
if doClassCode:
if 'class_code "' in fields[8]:
cc = fields[8].split('class_code "')[1].split('";')[0]
if cc != class_code:
continue
else:
continue
if 'transcript_name "' in fields[8]:
TranscriptID=fields[8].split('transcript_name "')[1].split('";')[0]
else:
TranscriptID=fields[8].split('transcript_id "')[1].split('";')[0]
if TranscriptDict.has_key(TranscriptID):
pass
else:
TranscriptDict[TranscriptID]=[]
chr=fields[0]
left=int(fields[3])
right=int(fields[4])
orientation=fields[6]
TranscriptDict[TranscriptID].append((chr,left,right,orientation))
g=0
print 'Found', len(TranscriptDict.keys()), 'transcripts'
for transcript in TranscriptDict.keys():
g+=1
if g % 1000 == 0:
print g, 'transcripts sequences processed'
TranscriptDict[transcript] = list(Set(TranscriptDict[transcript]))
if doSpliced:
if len(TranscriptDict[transcript]) == 1:
del TranscriptDict[transcript]
continue
sequence=''
leftEnds=[]
rightEnds=[]
orientation = TranscriptDict[transcript][0][3]
TranscriptDict[transcript].sort()
if orientation=='+':
for (chr,left,right,orientation) in TranscriptDict[transcript]:
try:
sequence=sequence+hg.sequence(chr[3:len(chr)],left,right-left)
except:
print "can't retrieve sequence", chr,left,right,orientation
for p in range(left,right-left):
try:
sequence=sequence+hg.sequence(chr[3:len(chr)],p,1)
except:
sequence=sequence+'N'
missed+=1
sense='plus_strand'
if orientation=='-':
for (chr,left,right,orientation) in reversed(TranscriptDict[transcript]):
try:
exonsequence=hg.sequence(chr[3:len(chr)],left-1,right-left+1)
sequence=sequence+getReverseComplement(exonsequence)
except:
print "can not retrieve sequence", chr,left,right,orientation
for p in range(left-1,right-left+1):
try:
sequence=sequence+getReverseComplement(hg.sequence(chr[3:len(chr)],p,1))
except:
sequence=sequence+'N'
missed+=1
sense='minus_strand'
if orientation=='.':
for (chr,left,right,orientation) in TranscriptDict[transcript]:
try:
sequence=sequence+hg.sequence(chr[3:len(chr)],left,right-left)
except:
print "can not retrieve sequence", chr,left,right,orientation
for p in range(left,right-left):
try:
sequence=sequence+hg.sequence(chr[3:len(chr)],p,1)
except:
sequence=sequence+'N'
missed+=1
sense='unknown_strand'
LeftEnd=TranscriptDict[transcript][0][1]
RightEnd=TranscriptDict[transcript][-1][2]
if orientation == '+' or orientation == '-':
sequence = sequence.upper().replace('T','U')
max_protein_length = len(sequence)
outline='>'+transcript+':'+chr+':'+str(LeftEnd)+'-'+str(RightEnd)+'-'+sense+'::frame1'
outfile.write(outline+'\n')
protein = ''
for i in range(0,max_protein_length-3,3):
if 'N' in sequence[i:i+3]:
protein = protein + '.'
else:
protein = protein + CodonDict[sequence[i:i+3]]
outfile.write(protein+'\n')
outline='>'+transcript+':'+chr+':'+str(LeftEnd)+'-'+str(RightEnd)+'-'+sense+'::frame2'
outfile.write(outline+'\n')
protein = ''
for i in range(1,max_protein_length-4,3):
if 'N' in sequence[i:i+3]:
protein = protein + '.'
else:
protein = protein + CodonDict[sequence[i:i+3]]
outfile.write(protein+'\n')
outline='>'+transcript+':'+chr+':'+str(LeftEnd)+'-'+str(RightEnd)+'-'+sense+'::frame3'
outfile.write(outline+'\n')
protein = ''
for i in range(2,max_protein_length-5,3):
if 'N' in sequence[i:i+3]:
protein = protein + '.'
else:
protein = protein + CodonDict[sequence[i:i+3]]
outfile.write(protein+'\n')
else:
sequence1 = sequence.upper().replace('T','U')
sequence2 = getReverseComplement(sequence).upper().replace('T','U')
max_protein_length = len(sequence1)
outline='>'+transcript+':'+chr+':'+str(LeftEnd)+'-'+str(RightEnd)+'-'+sense+'::frame1'
outfile.write(outline+'\n')
protein = ''
for i in range(0,max_protein_length-3,3):
if 'N' in sequence1[i:i+3]:
protein = protein + '.'
else:
protein = protein + CodonDict[sequence1[i:i+3]]
outfile.write(protein+'\n')
outline='>'+transcript+':'+chr+':'+str(LeftEnd)+'-'+str(RightEnd)+'-'+sense+'::frame2'
outfile.write(outline+'\n')
protein = ''
for i in range(1,max_protein_length-4,3):
if 'N' in sequence1[i:i+3]:
protein = protein + '.'
else:
protein = protein + CodonDict[sequence1[i:i+3]]
outfile.write(protein+'\n')
outline='>'+transcript+':'+chr+':'+str(LeftEnd)+'-'+str(RightEnd)+'-'+sense+'::frame3'
outfile.write(outline+'\n')
protein = ''
for i in range(2,max_protein_length-5,3):
if 'N' in sequence1[i:i+3]:
protein = protein + '.'
else:
protein = protein + CodonDict[sequence1[i:i+3]]
outfile.write(protein+'\n')
outline='>'+transcript+':'+chr+':'+str(LeftEnd)+'-'+str(RightEnd)+'-'+sense+'::frame4'
outfile.write(outline+'\n')
protein = ''
for i in range(0,max_protein_length-3,3):
if 'N' in sequence2[i:i+3]:
protein = protein + '.'
else:
protein = protein + CodonDict[sequence2[i:i+3]]
outfile.write(protein+'\n')
outline='>'+transcript+':'+chr+':'+str(LeftEnd)+'-'+str(RightEnd)+'-'+sense+'::frame5'
outfile.write(outline+'\n')
protein = ''
for i in range(1,max_protein_length-4,3):
if 'N' in sequence2[i:i+3]:
protein = protein + '.'
else:
protein = protein + CodonDict[sequence2[i:i+3]]
outfile.write(protein+'\n')
outline='>'+transcript+':'+chr+':'+str(LeftEnd)+'-'+str(RightEnd)+'-'+sense+'::frame6'
outfile.write(outline+'\n')
protein = ''
for i in range(2,max_protein_length-5,3):
if 'N' in sequence2[i:i+3]:
protein = protein + '.'
else:
protein = protein + CodonDict[sequence2[i:i+3]]
outfile.write(protein+'\n')
outfile.close()