def get_align_parts(data):
data['leftSeqFileName'] = data['alignOutDir'] + '/' + 'Contig.genomedir.fa.left'
data['rightSeqFileName'] = data['alignOutDir'] + '/' + 'Contig.genomedir.fa.right'
data['genomeFragAlignFileName'] = data['alignOutDir'] + '/' + 'genomeFrag.align.fa'
contigSeq = genutils.read_fasta_to_string(data['contigSeqFileName'])
# print data['contigLeftFragAlignBegin'],data['contigLeftFragAlignEnd']
# print data['contigRightFragAlignBegin'],data['contigRightFragAlignEnd']
# print data['genomeFragAlignBegin'],data['genomeFragAlignEnd']
leftSeq = contigSeq[data['contigLeftFragAlignBegin']-1:data['contigLeftFragAlignEnd']]
rightSeq = contigSeq[data['contigRightFragAlignBegin']-1:data['contigRightFragAlignEnd']]
leftSeqStr = genutils.add_breaks_to_line(leftSeq)
outFile= open(data['leftSeqFileName'],'w')
outFile.write('>left\n%s\n' % leftSeqStr)
outFile.close()
rightSeqStr = genutils.add_breaks_to_line(rightSeq)
outFile= open(data['rightSeqFileName'],'w')
outFile.write('>right\n%s\n' % rightSeqStr)
outFile.close()
# the genome part
region = data['chromName'] + ':' + str(data['genomeFragAlignBegin']) + '-' + str(data['genomeFragAlignEnd'])
cmd = 'samtools faidx ' + data['refGenomeFasta'] + ' ' + region + ' > ' + data['genomeFragAlignFileName']
# print cmd
genutils.runCMD(cmd)
def run_align(data):
data['leftAlignFileName'] = data['leftSeqFileName'] + '.align'
data['rightAlignFileName'] = data['rightSeqFileName'] + '.align'
cmd = 'stretcher ' + data['leftSeqFileName'] + ' ' + data['genomeFragAlignFileName'] + ' ' + data['leftAlignFileName']
print cmd
genutils.runCMD(cmd)
cmd = 'stretcher ' + data['rightSeqFileName'] + ' ' + data['genomeFragAlignFileName'] + ' ' + data['rightAlignFileName']
print cmd
genutils.runCMD(cmd)
def get_genome_frag(data):
region = data['chromName'] + ':' + str(data['chromFragStart']) + '-' + str(data['chromFragEnd'])
data['genomeFragFileName'] = data['alignOutDir'] + '/' + 'genomeFrag.fa'
cmd = 'samtools faidx ' + data['refGenomeFasta'] + ' ' + region + ' > ' + data['genomeFragFileName']
print cmd
genutils.runCMD(cmd)
genomeSeq = genutils.read_fasta_to_string(data['genomeFragFileName'])
genomeSeq = genomeSeq.upper()
data['genomeFragSeq'] = genomeSeq
def run_rm(data,run=True):
# change species here
cmd = 'RepeatMasker ' + data['genomeFragFileName']
if run is True:
genutils.runCMD(cmd)
data['genomeFragFileNameRM'] = data['genomeFragFileName'] + '.out'
# change species here
cmd = 'RepeatMasker ' + data['contigSeqFileName']
# print cmd
if run is True:
genutils.runCMD(cmd)
data['contigSeqFileNameRM'] = data['contigSeqFileName'] + '.out'
def novelCoordinates(coord): # Stores coordinates of novel contigs within chrNovel.fa
infofile = '/home/jmkidd/kidd-lab-scratch/feichens-projects/kmer/canFam31/unique_kmers/canFam3.1-withnovel/chromNovel.merge.info'
infoFile = open(infofile, 'r')
for line in infoFile:
line = line.rstrip()
line = line.split()
tmp = line[0]
if re.match(r">(\S+)", tmp) is not None:
match = re.match(r">(\S+)", tmp)
data['contigID'] = match.group(1)
data['offset'] = int(line[3]) - 1
# chrom start[0] end[1] chrom[2] offset[3]
coordTable[data['contigID']] = [line[3],line[4], data['contigID'], data['offset']]
novelfile = '/home/ampend/kidd-lab/ampend-projects/CGH_Array_Design_Dog/CGH_Array_Analysis/inputData/ProbeBEDFiles/NocanFam3Coords/novelContigs.probesel.pass.bed'
novelFile = open(novelfile, 'r')
correctednovel = novelfile + '.corrected'
correctedNovel = open(correctednovel, 'w')
for line in novelFile:
line = line.rstrip()
line = line.split()
data['novelChromID'] = line[0]
data['probeID'] = line[3]
if data['novelChromID'] in coordTable:
if data['novelChromID'] == 'zoey-scaffold-686':
continue
data['novelChrom'] = 'chrNovel'
#data['novelChrom'] = coordTable[data['novelChromID']][2]
data['novelStart'] = int(coordTable[data['novelChromID']][3]) + int(line[1])
data['novelEnd'] = int(coordTable[data['novelChromID']][3]) + int(line[2])
data['novelProbeID'] = data['probeID']
novelTable[data['novelProbeID']] = (data['novelChrom'], data['novelStart'], data['novelEnd'],data['novelProbeID'])
correctedNovel.write('%s\t%s\t%s\t%s\n' % (data['novelChrom'],data['novelStart'],data['novelEnd'],data['novelProbeID']))
cmd = 'cat %s../inputData/ProbeBEDFiles/Mappable/* %s../inputData/ProbeBEDFiles/NocanFam3Coords/ChrY.probesel.pass.bed %s../inputData/ProbeBEDFiles/NocanFam3Coords/LINEs_RefInsertions.probesel.bed.pass.bed.sorted %s../inputData/ProbeBEDFiles/NocanFam3Coords/novelContigs.probesel.pass.bed.corrected %s../inputData/ProbeBEDFiles/NocanFam3Coords/SINEs_ReferenceInsertions.probesel.pass.bed.sorted > %s../inputData/ProbeBEDFiles/TOTAL_Probes_FINALCoordinates_all.bed' % (options.directory, options.directory, options.directory, options.directory, options.directory, options.directory)
print cmd
genutils.runCMD(cmd)
def run_pear(myData):
# PEAR aligns/merges overlapping read pairs, which is the case that we have here
myData['pearBase'] = myData['outDir'] + myData['sampleName'] + '.pear'
cmd = 'pear --nbase -f %s -r %s -o %s' % (myData['r1fq'],myData['r2fq'],myData['pearBase'])
myData['assembledFQ'] = myData['pearBase'] + '.assembled.fastq'
myData['discardedFQ'] = myData['pearBase'] + '.discarded.fastq'
myData['notAssemF'] = myData['pearBase'] + '.unassembled.forward.fastq'
myData['notAssemR'] = myData['pearBase'] + '.unassembled.reverse.fastq'
# check to see if should run
outgz = myData['assembledFQ'] + '.gz'
if os.path.isfile(outgz) is True:
print 'found gzip output already, will not rerun'
myData['assembledFQ'] += '.gz'
myData['discardedFQ'] += '.gz'
myData['notAssemF'] += '.gz'
myData['notAssemR'] += '.gz'
else:
print cmd
genutils.runCMD(cmd)
cmd = 'gzip ' + myData['assembledFQ']
print cmd
genutils.runCMD(cmd)
myData['assembledFQ'] += '.gz'
cmd = 'gzip ' + myData['discardedFQ']
print cmd
genutils.runCMD(cmd)
myData['discardedFQ'] += '.gz'
cmd = 'gzip ' + myData['notAssemF']
print cmd
genutils.runCMD(cmd)
myData['notAssemF'] += '.gz'
cmd = 'gzip ' + myData['notAssemR']
print cmd
genutils.runCMD(cmd)
myData['notAssemR'] += '.gz'
line = line.split()
siteID = line[0]
if siteID == 'siteID':
continue
if line[1] == 'NO_CANDIDATE':
continue
print line
data = {}
data['tmpDir'] = options.tmpDir
if os.path.isdir(data['tmpDir']) is False:
cmd = 'mkdir ' + data['tmpDir']
print 'making tmp dir'
print cmd
genutils.runCMD(cmd)
data['refGenomeFasta'] = refGenomeFasta
data['siteID'] = siteID
chrom = siteID.split('_')
chrom = chrom[0:-1]
chrom = '_'.join(chrom)
p = int(siteID.split('_')[-1])
startBp = p - regDelta
endBp = p + regDelta
data['chromName'] = chrom
data['chromFragStart'] =startBp
data['chromFragEnd'] = endBp
def print_pretty_alignment(data):
#left end is blue, right start is red
data['3wayAlignFilePrettyName'] = data['genomeFragFileName'] + '.3wayalign.pretty'
data['3wayAlignFilePrettyNamePS'] = data['alignOutDir'] + '/' + data['siteID'] + '.3wayalign.pretty.ps'
data['3wayAlignFilePrettyNamePDF'] = data['alignOutDir'] + '/' + data['siteID'] + '.3wayalign.pretty.pdf'
outFile = open(data['3wayAlignFilePrettyName'],'w')
outFile.write('Site ID: %s\n' % (data['siteID']))
outFile.write('%s\t%s\n' % (data['contigName'],data['contigDir']))
outFile.write('%s:%i-%i\n' % (data['chromName'],data['genomeFragAlignBegin'],data['genomeFragAlignEnd']))
# left BP in chromFrag and Contig
outFile.write('~color{0 0 1}end left match~color{default} chromFrag %i Contig %i\n' % (data['leftBpGenomeFragCoords'],data['leftBpContigCoord']))
# right BP in chromFrag and Contig
outFile.write('~color{1 0 0}start right match~color{default} chromFrag %i Contig %i\n' % (data['rightBpGenomeFragCoords'],data['rightBpContigCoord']))
#go through and add in the colors
# do the colors individually
print 'ready to start'
print data['leftBpContigCoord'],data['leftBpGenomeFragCoords']
print data['rightBpContigCoord'],data['rightBpGenomeFragCoords']
for i in range(0,len(data['genome3way'])):
if data['left3wayPos'][i] == (data['leftBpContigCoord'] - data['contigLeftFragAlignBegin'] + 1):
if data['left3way'][i] == '-':
print 'left is -'
else:
data['left3way'][i] = '~color{0 0 1}' + data['left3way'][i] + '~color{default}'
data['3wayParse'][i] = '~color{0 0 1}' + data['3wayParse'][i] + '~color{default}'
print 'LEFT contig',i,data['left3wayPos'][i]
if data['genome3wayPos'][i] == data['leftBpGenomeFragCoords'] and data['genome3way'][i] != '-':
data['genome3way'][i] = '~color{0 0 1}' + data['genome3way'][i] + '~color{default}'
print 'LEFT GENOME',i,data['genome3wayPos'][i]
if data['right3wayPos'][i] == (data['rightBpContigCoord'] - data['contigRightFragAlignBegin'] +1):
if data['right3way'][i] == '-':
print i,'right is -'
else:
data['right3way'][i] = '~color{1 0 0}' + data['right3way'][i] + '~color{default}'
data['3wayParse'][i] = '~color{1 0 0}' + data['3wayParse'][i] + '~color{default}'
print i,'right contig',i,data['right3wayPos'][i]
if data['genome3wayPos'][i] == data['rightBpGenomeFragCoords'] and data['genome3way'][i] != '-' :
data['genome3way'][i] = '~color{1 0 0}' + data['genome3way'][i] + '~color{default}'
print i,'RIGHT GENOME',i,data['genome3wayPos'][i]
leftName = 'left '
rightName = 'right '
chromName = 'chrom '
passeName = ' '
outFile.write('\n\n')
# do it in runs of 50
width = 70
sliceS = 0
sliceE = sliceS + width
while True:
if sliceS >= len(data['genome3way']):
break
if sliceE > len(data['genome3way']):
sliceE = len(data['genome3way'])
l = data['left3way'][sliceS:sliceE]
g = data['genome3way'][sliceS:sliceE]
r = data['right3way'][sliceS:sliceE]
p = data['3wayParse'][sliceS:sliceE]
l = leftName + ''.join(l)
g = chromName + ''.join(g)
r = rightName + ''.join(r)
p = passeName + ''.join(p)
outFile.write('%s\n%s\n%s\n%s\n\n' % (l,g,r,p))
sliceS = sliceE
sliceE = sliceS + width
outFile.close()
print 'Clean up PS and PDF'
cmd = 'rm ' + data['3wayAlignFilePrettyNamePS']
print cmd
genutils.runCMDNoFail(cmd)
cmd = 'rm ' + data['3wayAlignFilePrettyNamePDF']
print cmd
genutils.runCMDNoFail(cmd)
cmd = 'enscript %s -o %s -e~ -B -2r' % (data['3wayAlignFilePrettyName'],data['3wayAlignFilePrettyNamePS'])
print cmd
genutils.runCMD(cmd)
cmd = 'ps2pdf ' + data['3wayAlignFilePrettyNamePS'] + ' ' + data['3wayAlignFilePrettyNamePDF']
print cmd
genutils.runCMD(cmd)
def run_miropeats(data):
if 'miropeatSValue' in data:
s = data['miropeatSValue']
else:
s = 80
s = 40 # for the dogs...
data['miropeatSValue'] = s
data['miroOutPS'] = data['alignOutDir'] + '/' + 'miropeats.' + str(s) + '.ps'
data['miroOutInfo'] = data['alignOutDir'] + '/' + 'miropeats.' + str(s) + '.out'
if 'tmpDir' in data:
tmpDir = data['tmpDir']
else:
tmpDir = '/home/jmkidd/kidd-lab-scratch/jmkidd-projects/tmp/'
tmpGenome = tmpDir + 'genome.fa'
tmpContig = tmpDir + 'contig.fa'
tmpMRPS = tmpDir + 'tmp.MRPS'
tmpMROUT = tmpDir + 'tmp.MROUT'
cmd = 'cp %s %s' % (data['genomeFragFileName'],tmpGenome)
print cmd
genutils.runCMD(cmd)
cmd = 'cp %s %s' % (data['contigSeqFileName'],tmpContig)
print cmd
genutils.runCMD(cmd)
cmd = 'miropeats -s %i -onlyinter -o %s -seq %s -seq %s > %s' % (s,tmpMRPS,tmpGenome,tmpContig,tmpMROUT)
print cmd
genutils.runCMD(cmd)
#cp
if os.path.isfile(tmpMRPS) is True:
cmd = 'cp %s %s' % (tmpMRPS,data['miroOutPS'])
print cmd
genutils.runCMD(cmd)
else:
data['miroOutPS'] = 'FAILURE'
cmd = 'cp %s %s' % (tmpMROUT,data['miroOutInfo'])
print cmd
genutils.runCMD(cmd)
# clean up
cmd = 'rm %s %s' % (tmpGenome,tmpContig)
print cmd
genutils.runCMD(cmd)
if os.path.isfile(tmpMRPS) is True:
cmd = 'rm ' + tmpMRPS
print cmd
genutils.runCMD(cmd)
if os.path.isfile(tmpMROUT) is True:
cmd = 'rm ' + tmpMROUT
print cmd
genutils.runCMD(cmd)
def get_genome_gaps(data,run=True):
data['genomeFragGapsFileName'] = data['genomeFragFileName'] + '.gaps'
cmd = 'get_gaps.pl ' + data['genomeFragFileName'] + ' > ' + data['genomeFragGapsFileName']
if run is True:
genutils.runCMD(cmd)
def get_contig_gaps(data,run=True):
data['contigSeqGapsFileName'] = data['contigSeqFileName'] + '.gaps'
cmd = 'get_gaps.pl ' + data['contigSeqFileName'] + ' > ' + data['contigSeqGapsFileName']
if run is True:
genutils.runCMD(cmd)
get_genome_gaps(data,run)
def bwa_index_alleles(data):
cmd = 'bwa-0.5.9 index %s' % (data['alleleFa'])
# print cmd
genutils.runCMD(cmd)
def make_alternative_seqs(data,bpOutTable,allelesBaseDir,fragmentExtension):
alleleDir = allelesBaseDir + data['siteID']
if os.path.isdir(alleleDir) is False:
cmd = 'mkdir ' + alleleDir
print cmd
genutils.runCMD(cmd)
alleleDir += '/'
genomeLeftFa = alleleDir + 'genomeLeft.fa'
genomeRightFa = alleleDir + 'genomeRight.fa'
genomeWholeFa = alleleDir + 'genomeWhole.fa'
alleleFa = alleleDir + 'alleles.fa'
data['alleleFa'] = alleleFa
data['alleleDir'] = alleleDir
gTSDs = data['rightBpChromCoords']
gTSDe = data['leftBpChromCoords']
gTSDl = gTSDe - gTSDs + 1
data['gTSDl'] = gTSDl
if gTSDl <= -1: # deletion in chromosome
print 'deletion of %i in genome' % gTSDl
leftChromBp = data['leftBpChromCoords']
leftChromStart = leftChromBp - fragmentExtension + 1
rightChromBp = data['rightBpChromCoords']
rightChromEnd = rightChromBp + fragmentExtension - 1
data['insSite'] = leftChromBp
# print leftChromBp,leftChromStart,rightChromBp,rightChromEnd
region = data['chromName'] + ':' + str(leftChromStart) + '-' + str(leftChromBp)
cmd = 'samtools faidx ' + data['refGenomeFasta'] + ' ' + region + ' > ' + genomeLeftFa
genutils.runCMD(cmd)
genomeLeftSeq = genutils.read_fasta_to_string(genomeLeftFa)
genomeLeftSeq = genomeLeftSeq.upper()
region = data['chromName'] + ':' + str(rightChromBp) + '-' + str(rightChromEnd)
cmd = 'samtools faidx ' + data['refGenomeFasta'] + ' ' + region + ' > ' + genomeRightFa
genutils.runCMD(cmd)
genomeRightSeq = genutils.read_fasta_to_string(genomeRightFa)
genomeRightSeq = genomeRightSeq.upper()
# get the chrom sequence
region = data['chromName'] + ':' + str(leftChromStart) + '-' + str(rightChromEnd)
cmd = 'samtools faidx ' + data['refGenomeFasta'] + ' ' + region + ' > ' + genomeWholeFa
genutils.runCMD(cmd)
genomeWholeSeq = genutils.read_fasta_to_string(genomeWholeFa)
genomeWholeSeq = genomeWholeSeq.upper()
data['mapFragStart'] = leftChromStart
data['mapFragEnd'] = rightChromEnd
# since that BP is in contig
contigStart = data['leftBpContigCoord'] # already last bp
contigEnd = data['rightBpContigCoord']
contigSeq = data['contigSeqGenomeDir'][contigStart:contigEnd-1]
# print out genome
outFile = open(alleleFa,'w')
outFile.write('>%s\n' % (data['siteID']+'_genome'))
gSeq = genomeWholeSeq
gSeq = genutils.add_breaks_to_line(gSeq)
outFile.write('%s\n' % gSeq)
outFile.write('>%s\n' % (data['siteID']+'_insertion'))
iSeq = genomeLeftSeq + contigSeq + genomeRightSeq
iSeq = genutils.add_breaks_to_line(iSeq)
outFile.write('%s\n' % iSeq)
outFile.close()
# print 'left',genomeLeftSeq
# print 'right',genomeRightSeq
# print 'contig',contigSeq
# print len(contigSeq)
elif gTSDl >= 1: # has TSD
# print 'has TSD len %i' % gTSDl
# note that they cross
leftChromBp = data['rightBpChromCoords']
leftChromStart = leftChromBp - fragmentExtension + 1
rightChromBp = data['leftBpChromCoords']
rightChromEnd = rightChromBp + fragmentExtension - 1
data['insSite'] = leftChromBp
# print leftChromBp,leftChromStart,rightChromBp,rightChromEnd
region = data['chromName'] + ':' + str(leftChromStart) + '-' + str(leftChromBp)
cmd = 'samtools faidx ' + data['refGenomeFasta'] + ' ' + region + ' > ' + genomeLeftFa
genutils.runCMD(cmd)
genomeLeftSeq = genutils.read_fasta_to_string(genomeLeftFa)
genomeLeftSeq = genomeLeftSeq.upper()
region = data['chromName'] + ':' + str(rightChromBp) + '-' + str(rightChromEnd)
cmd = 'samtools faidx ' + data['refGenomeFasta'] + ' ' + region + ' > ' + genomeRightFa
genutils.runCMD(cmd)
genomeRightSeq = genutils.read_fasta_to_string(genomeRightFa)
genomeRightSeq = genomeRightSeq.upper()
# get the chrom sequence
region = data['chromName'] + ':' + str(leftChromStart) + '-' + str(rightChromEnd)
cmd = 'samtools faidx ' + data['refGenomeFasta'] + ' ' + region + ' > ' + genomeWholeFa
genutils.runCMD(cmd)
data['mapFragStart'] = leftChromStart
data['mapFragEnd'] = rightChromEnd
genomeWholeSeq = genutils.read_fasta_to_string(genomeWholeFa)
genomeWholeSeq = genomeWholeSeq.upper()
# since that BP is in contig
contigStart = data['leftBpContigCoord'] - gTSDl + 1 # to get over to right size, include the TSD
contigEnd = data['rightBpContigCoord'] + gTSDl - 1 # to get over to the right size, include the TSD
contigSeq = data['contigSeqGenomeDir'][contigStart:contigEnd-1]
# print out genome
outFile = open(alleleFa,'w')
outFile.write('>%s\n' % (data['siteID']+'_genome'))
gSeq = genomeWholeSeq
gSeq = genutils.add_breaks_to_line(gSeq)
outFile.write('%s\n' % gSeq)
outFile.write('>%s\n' % (data['siteID']+'_insertion'))
iSeq = genomeLeftSeq + contigSeq + genomeRightSeq
iSeq = genutils.add_breaks_to_line(iSeq)
outFile.write('%s\n' % iSeq)
outFile.close()
# print 'left',genomeLeftSeq
# print 'right',genomeRightSeq
# print 'contig',contigSeq
# print len(contigSeq)
elif gTSDl == 0: # has no TSD
# print 'has TSD len %i' % gTSDl
# note that they cross
leftChromBp = data['leftBpChromCoords']
leftChromStart = leftChromBp - fragmentExtension + 1
rightChromBp = data['rightBpChromCoords']
rightChromEnd = rightChromBp + fragmentExtension - 1
data['insSite'] = leftChromBp
# print leftChromBp,leftChromStart,rightChromBp,rightChromEnd
region = data['chromName'] + ':' + str(leftChromStart) + '-' + str(leftChromBp)
cmd = 'samtools faidx ' + data['refGenomeFasta'] + ' ' + region + ' > ' + genomeLeftFa
genutils.runCMD(cmd)
genomeLeftSeq = genutils.read_fasta_to_string(genomeLeftFa)
genomeLeftSeq = genomeLeftSeq.upper()
region = data['chromName'] + ':' + str(rightChromBp) + '-' + str(rightChromEnd)
cmd = 'samtools faidx ' + data['refGenomeFasta'] + ' ' + region + ' > ' + genomeRightFa
genutils.runCMD(cmd)
genomeRightSeq = genutils.read_fasta_to_string(genomeRightFa)
genomeRightSeq = genomeRightSeq.upper()
# get the chrom sequence
region = data['chromName'] + ':' + str(leftChromStart) + '-' + str(rightChromEnd)
cmd = 'samtools faidx ' + data['refGenomeFasta'] + ' ' + region + ' > ' + genomeWholeFa
genutils.runCMD(cmd)
data['mapFragStart'] = leftChromStart
data['mapFragEnd'] = rightChromEnd
genomeWholeSeq = genutils.read_fasta_to_string(genomeWholeFa)
genomeWholeSeq = genomeWholeSeq.upper()
# since that BP is in contig
contigStart = data['leftBpContigCoord']
contigEnd = data['rightBpContigCoord']
contigSeq = data['contigSeqGenomeDir'][contigStart:contigEnd-1]
# print out genome
outFile = open(alleleFa,'w')
outFile.write('>%s\n' % (data['siteID']+'_genome'))
gSeq = genomeWholeSeq
gSeq = genutils.add_breaks_to_line(gSeq)
outFile.write('%s\n' % gSeq)
outFile.write('>%s\n' % (data['siteID']+'_insertion'))
iSeq = genomeLeftSeq + contigSeq + genomeRightSeq
iSeq = genutils.add_breaks_to_line(iSeq)
outFile.write('%s\n' % iSeq)
outFile.close()
# print 'left',genomeLeftSeq
# print 'right',genomeRightSeq
# print 'contig',contigSeq
# print len(contigSeq)
else:
print 'What TSD size?'
print gTSDl
sys.exit()
# make out file
nl = [data['siteID'],data['chromName'],data['insSite'],gTSDl,data['mapFragStart'],data['mapFragEnd'] ]
nl = [str(i) for i in nl]
nl = '\t'.join(nl) + '\n'
bpOutTable.write(nl)
bwa_index_alleles(data)
######## NOVEL CONTIGS ##########
#################################
print 'Now annotating novel contigs in fosmid...\n'
#novelContigFasta = '~/kidd-lab/ampend-projects/Novel_Sequence_Analysis/NovelSequence/novel.v2.fa.masked'
#New non-reundant Fasta
novelContigFasta = '~/kidd-lab/ampend-projects/Novel_Sequence_Analysis/RedundantNovelContigs/Final_chrNovel_Fasta/novelContigs_NonRedundant.fa.masked'
bottomRM = options.bottomRM
masked_bottomRM = bottomRM.replace(".out",".masked")
contigfile = 'BLAT_novelContigs_vs_fosmid.blat'
#cmd = 'blat -fine -minMatch=1 -minScore=10 -out=blast9 %s %s %s' % (novelContigFasta,masked_bottomRM,contigfile)
cmd = 'blat -noHead %s %s %s' % (novelContigFasta,masked_bottomRM,contigfile)
print cmd
genutils.runCMD(cmd)
n = 0
#ypos = bottomLine - 0.25
exon_pos = gap_pos - 0.03
ypos = exon_pos
contigFile = open('BLAT_novelContigs_vs_fosmid.blat','r')
contigList = []
print 'NOVEL CONTIG start ypos', ypos
for b in contigFile:
b = b.rstrip()
b = b.split()
if b[0].isdigit() is False:
def run_repeatmasker(fastaFile):
cmd = 'RepeatMasker --species human %s ' % (fastaFile)
# change this to use other species or libraries
# cmd = 'RepeatMasker --species dog %s ' % (fastaFile)
if os.path.isfile(fastaFile) is True:
genutils.runCMD(cmd)
