def main():
'''
main run call
'''
debug = False
from optparse import OptionParser
usage = "usage: %prog [options] -g [INPUT_GENOME] -i [INPUT_REGION_GFF] -r [RANKBY_BAM_FILE] -o [OUTPUT_FOLDER] [OPTIONAL_FLAGS]"
parser = OptionParser(usage = usage)
#required flags
parser.add_option("-i","--i", dest="input",nargs = 1, default=None,
help = "Enter a .gff or .bed file of binding sites used to make enhancers")
parser.add_option("-r","--rankby", dest="rankby",nargs = 1, default=None,
help = "bamfile to rank enhancer by")
parser.add_option("-o","--out", dest="out",nargs = 1, default=None,
help = "Enter an output folder")
parser.add_option("-g","--genome", dest="genome",nargs = 1, default=None,
help = "Reference genome file: example- hg18_refseq.ucsc")
#optional flags
parser.add_option("-b","--bams", dest="bams",nargs = 1, default=None,
help = "Enter a comma separated list of additional bam files to map to")
parser.add_option("-c","--control", dest="control",nargs = 1, default=None,
help = "bamfile to rank enhancer by")
parser.add_option("-s","--stitch", dest="stitch",nargs = 1, default=12500,
help = "Enter a max linking distance for stitching")
parser.add_option("-t","--tss", dest="tss",nargs = 1, default=0,
help = "Enter a distance from TSS to exclude. 0 = no TSS exclusion")
#RETRIEVING FLAGS
(options,args) = parser.parse_args()
if not options.input or not options.rankby or not options.out or not options.genome:
print('hi there')
parser.print_help()
exit()
#making the out folder if it doesn't exist
outFolder = ROSE_utils.formatFolder(options.out,True)
#figuring out folder schema
gffFolder = ROSE_utils.formatFolder(outFolder+'gff/',True)
mappedFolder = ROSE_utils.formatFolder(outFolder+ 'mappedGFF/',True)
#GETTING INPUT FILE
if options.input.split('.')[-1] == 'bed':
#CONVERTING A BED TO GFF
inputGFFName = options.input.split('/')[-1][0:-4]
inputGFFFile = '%s%s.gff' % (gffFolder,inputGFFName)
ROSE_utils.bedToGFF(options.input,inputGFFFile)
elif options.input.split('.')[-1] =='gff':
#COPY THE INPUT GFF TO THE GFF FOLDER
inputGFFFile = options.input
os.system('cp %s %s' % (inputGFFFile,gffFolder))
else:
print('WARNING: INPUT FILE DOES NOT END IN .gff or .bed. ASSUMING .gff FILE FORMAT')
#COPY THE INPUT GFF TO THE GFF FOLDER
inputGFFFile = options.input
os.system('cp %s %s' % (inputGFFFile,gffFolder))
#GETTING THE LIST OF BAMFILES TO PROCESS
if options.control:
bamFileList = [options.rankby,options.control]
else:
bamFileList = [options.rankby]
if options.bams:
bamFileList += options.bams.split(',')
bamFileLIst = ROSE_utils.uniquify(bamFileList)
#optional args
#Stitch parameter
stitchWindow = int(options.stitch)
#tss options
tssWindow = int(options.tss)
if tssWindow != 0:
removeTSS = True
else:
removeTSS = False
#GETTING THE BOUND REGION FILE USED TO DEFINE ENHANCERS
print('USING %s AS THE INPUT GFF' % (inputGFFFile))
inputName = inputGFFFile.split('/')[-1].split('.')[0]
#GETTING THE GENOME
genome = options.genome
print('USING %s AS THE GENOME' % genome)
#GETTING THE CORRECT ANNOT FILE
cwd = os.getcwd()
## genomeDict = {
## 'HG18':'%s/annotation/hg18_refseq.ucsc' % (cwd),
## 'MM9': '%s/annotation/mm9_refseq.ucsc' % (cwd),
## 'HG19':'%s/annotation/hg19_refseq.ucsc' % (cwd),
## 'MM8': '%s/annotation/mm8_refseq.ucsc' % (cwd),
## 'MM10':'%s/annotation/mm10_refseq.ucsc' % (cwd),
## }
annotFile = genome
## annotFile = genomeDict[upper(genome)]
#MAKING THE START DICT
print('MAKING START DICT')
startDict = ROSE_utils.makeStartDict(annotFile)
#LOADING IN THE BOUND REGION REFERENCE COLLECTION
print('LOADING IN GFF REGIONS')
referenceCollection = ROSE_utils.gffToLocusCollection(inputGFFFile)
#CHECKING INPUT REGIONS FOR FORMATTING
print('CHECKING INPUT TO MAKE SURE EACH REGION HAS A UNIQUE IDENTIFIER')
checkRefCollection(referenceCollection) #makes sure that all input regions have a unique ID
#NOW STITCH REGIONS
print('STITCHING REGIONS TOGETHER')
stitchedCollection,debugOutput = regionStitching(inputGFFFile,stitchWindow,tssWindow,annotFile,removeTSS)
#NOW MAKE A STITCHED COLLECTION GFF
print('MAKING GFF FROM STITCHED COLLECTION')
stitchedGFF=ROSE_utils.locusCollectionToGFF(stitchedCollection)
if not removeTSS:
stitchedGFFFile = '%s%s_%sKB_STITCHED.gff' % (gffFolder,inputName,stitchWindow/1000)
stitchedGFFName = '%s_%sKB_STITCHED' % (inputName,stitchWindow/1000)
debugOutFile = '%s%s_%sKB_STITCHED.debug' % (gffFolder,inputName,stitchWindow/1000)
else:
stitchedGFFFile = '%s%s_%sKB_STITCHED_TSS_DISTAL.gff' % (gffFolder,inputName,stitchWindow/1000)
stitchedGFFName = '%s_%sKB_STITCHED_TSS_DISTAL' % (inputName,stitchWindow/1000)
debugOutFile = '%s%s_%sKB_STITCHED_TSS_DISTAL.debug' % (gffFolder,inputName,stitchWindow/1000)
#WRITING DEBUG OUTPUT TO DISK
if debug:
print('WRITING DEBUG OUTPUT TO DISK AS %s' % (debugOutFile))
ROSE_utils.unParseTable(debugOutput,debugOutFile,'\t')
#WRITE THE GFF TO DISK
print('WRITING STITCHED GFF TO DISK AS %s' % (stitchedGFFFile))
ROSE_utils.unParseTable(stitchedGFF,stitchedGFFFile,'\t')
#SETTING UP THE OVERALL OUTPUT FILE
outputFile1 = outFolder + stitchedGFFName + '_ENHANCER_REGION_MAP.txt'
print('OUTPUT WILL BE WRITTEN TO %s' % (outputFile1))
#MAPPING TO THE NON STITCHED (ORIGINAL GFF)
#MAPPING TO THE STITCHED GFF
# bin for bam mapping
nBin =1
#IMPORTANT
#CHANGE cmd1 and cmd2 TO PARALLELIZE OUTPUT FOR BATCH SUBMISSION
#e.g. if using LSF cmd1 = "bsub python bamToGFF.py -f 1 -e 200 -r -m %s -b %s -i %s -o %s" % (nBin,bamFile,stitchedGFFFile,mappedOut1)
for bamFile in bamFileList:
bamFileName = bamFile.split('/')[-1]
#MAPPING TO THE STITCHED GFF
mappedOut1 ='%s%s_%s_MAPPED.gff' % (mappedFolder,stitchedGFFName,bamFileName)
#WILL TRY TO RUN AS A BACKGROUND PROCESS. BATCH SUBMIT THIS LINE TO IMPROVE SPEED
cmd1 = "python /usr/local/'bin'/ROSE_bamToGFF.py -f 1 -e 200 -r -m %s -b %s -i %s -o %s &" % (nBin,bamFile,stitchedGFFFile,mappedOut1)
print(cmd1)
os.system(cmd1)
#MAPPING TO THE ORIGINAL GFF
mappedOut2 ='%s%s_%s_MAPPED.gff' % (mappedFolder,inputName,bamFileName)
#WILL TRY TO RUN AS A BACKGROUND PROCESS. BATCH SUBMIT THIS LINE TO IMPROVE SPEED
cmd2 = "python /usr/local/'bin'/ROSE_bamToGFF.py -f 1 -e 200 -r -m %s -b %s -i %s -o %s &" % (nBin,bamFile,inputGFFFile,mappedOut2)
print(cmd2)
os.system(cmd2)
print('PAUSING TO MAP')
time.sleep(10)
#CHECK FOR MAPPING OUTPUT
outputDone = False
ticker = 0
print('WAITING FOR MAPPING TO COMPLETE. ELAPSED TIME (MIN):')
while not outputDone:
'''
check every 5 minutes for completed output
'''
outputDone = True
if ticker%6 == 0:
print(ticker*5)
ticker +=1
#CHANGE THIS PARAMETER TO ALLOW MORE TIME TO MAP
if ticker == 144:
print('ERROR: OPERATION TIME OUT. MAPPING OUTPUT NOT DETECTED')
exit()
break
for bamFile in bamFileList:
#GET THE MAPPED OUTPUT NAMES HERE FROM MAPPING OF EACH BAMFILE
bamFileName = bamFile.split('/')[-1]
mappedOut1 ='%s%s_%s_MAPPED.gff' % (mappedFolder,stitchedGFFName,bamFileName)
try:
mapFile = open(mappedOut1,'r')
mapFile.close()
except IOError:
outputDone = False
mappedOut2 ='%s%s_%s_MAPPED.gff' % (mappedFolder,inputName,bamFileName)
try:
mapFile = open(mappedOut2,'r')
mapFile.close()
except IOError:
outputDone = False
if outputDone == True:
break
time.sleep(300)
print('MAPPING TOOK %s MINUTES' % (ticker*5))
print('BAM MAPPING COMPLETED NOW MAPPING DATA TO REGIONS')
#CALCULATE DENSITY BY REGION
mapCollection(stitchedCollection,referenceCollection,bamFileList,mappedFolder,outputFile1,refName = stitchedGFFName)
time.sleep(10)
print('CALLING AND PLOTTING SUPER-ENHANCERS')
if options.control:
rankbyName = options.rankby.split('/')[-1]
controlName = options.control.split('/')[-1]
cmd = 'R --no-save %s %s %s %s < /usr/local/bin/ROSE_callSuper.R' % (outFolder,outputFile1,inputName,controlName)
else:
rankbyName = options.rankby.split('/')[-1]
controlName = 'NONE'
cmd = 'R --no-save %s %s %s %s < /usr/local/bin/ROSE_callSuper.R' % (outFolder,outputFile1,inputName,controlName)
print(cmd)
os.system(cmd)
def main():
'''
main run call
'''
debug = False
from optparse import OptionParser
usage = "usage: %prog [options] -g [GENOME] -i [INPUT_ENHANCER_FILE]"
parser = OptionParser(usage=usage)
#required flags
parser.add_option(
"-i",
"--i",
dest="input",
nargs=1,
default=None,
help="Enter a ROSE ranked enhancer or super-enhancer file")
parser.add_option("-g",
"--genome",
dest="genome",
nargs=1,
default=None,
help="Enter the genome build (MM9,MM8,HG18,HG19,HG38)")
#optional flags
parser.add_option("-l",
"--list",
dest="geneList",
nargs=1,
default=None,
help="Enter a gene list to filter through")
parser.add_option(
"-o",
"--out",
dest="out",
nargs=1,
default=None,
help="Enter an output folder. Default will be same folder as input file"
)
parser.add_option(
"-r",
"--refseq",
dest="refseq",
action='store_true',
default=False,
help="If flagged will write output by refseq ID and not common name")
#RETRIEVING FLAGS
(options, args) = parser.parse_args()
if not options.input or not options.genome:
parser.print_help()
exit()
#GETTING THE INPUT
enhancerFile = options.input
#making the out folder if it doesn't exist
if options.out:
outFolder = ROSE_utils.formatFolder(options.out, True)
else:
outFolder = '/'.join(enhancerFile.split('/')[0:-1]) + '/'
#GETTING THE GENOME
genome = options.genome
print(('USING %s AS THE GENOME' % genome))
#GETTING THE CORRECT ANNOT FILE
cwd = os.getcwd()
genomeDict = {
'HG18': '%s/annotation/hg18_refseq.ucsc' % (cwd),
'MM9': '%s/annotation/mm9_refseq.ucsc' % (cwd),
'HG19': '%s/annotation/hg19_refseq.ucsc' % (cwd),
'HG38': '%s/annotation/hg38_refseq.ucsc' % (cwd),
'MM8': '%s/annotation/mm8_refseq.ucsc' % (cwd),
'MM10': '%s/annotation/mm10_refseq.ucsc' % (cwd),
}
annotFile = genomeDict[genome.upper()]
#GETTING THE TRANSCRIBED LIST
if options.geneList:
transcribedFile = options.geneList
else:
transcribedFile = ''
enhancerToGeneTable, geneToEnhancerTable = mapEnhancerToGene(
annotFile,
enhancerFile,
uniqueGenes=True,
byRefseq=options.refseq,
transcribedFile=transcribedFile)
#Writing enhancer output
enhancerFileName = enhancerFile.split('/')[-1].split('.')[0]
#writing the enhancer table
out1 = '%s%s_ENHANCER_TO_GENE.txt' % (outFolder, enhancerFileName)
ROSE_utils.unParseTable(enhancerToGeneTable, out1, '\t')
#writing the gene table
out2 = '%s%s_GENE_TO_ENHANCER.txt' % (outFolder, enhancerFileName)
ROSE_utils.unParseTable(geneToEnhancerTable, out2, '\t')
def main():
'''
main run call
'''
debug = False
from optparse import OptionParser
usage = "usage: %prog [options] -g [GENOME] -i [INPUT_REGION_GFF] -r [RANKBY_BAM_FILE] -o [OUTPUT_FOLDER] [OPTIONAL_FLAGS]"
parser = OptionParser(usage = usage)
#required flags
parser.add_option("-i","--i", dest="input",nargs = 1, default=None,
help = "Enter a .gff or .bed file of binding sites used to make enhancers")
parser.add_option("-r","--rankby", dest="rankby",nargs = 1, default=None,
help = "bamfile to rank enhancer by")
parser.add_option("-o","--out", dest="out",nargs = 1, default=None,
help = "Enter an output folder")
parser.add_option("-g","--genome", dest="genome",nargs = 1, default=None,
help = "Enter the genome build (MM9,MM8,HG18,HG19)")
#optional flags
parser.add_option("-b","--bams", dest="bams",nargs = 1, default=None,
help = "Enter a comma separated list of additional bam files to map to")
parser.add_option("-c","--control", dest="control",nargs = 1, default=None,
help = "bamfile to rank enhancer by")
parser.add_option("-s","--stitch", dest="stitch",nargs = 1, default=12500,
help = "Enter a max linking distance for stitching")
parser.add_option("-t","--tss", dest="tss",nargs = 1, default=0,
help = "Enter a distance from TSS to exclude. 0 = no TSS exclusion")
#RETRIEVING FLAGS
(options,args) = parser.parse_args()
if not options.input or not options.rankby or not options.out or not options.genome:
print('hi there')
parser.print_help()
exit()
#making the out folder if it doesn't exist
outFolder = ROSE_utils.formatFolder(options.out,True)
#figuring out folder schema
gffFolder = ROSE_utils.formatFolder(outFolder+'gff/',True)
mappedFolder = ROSE_utils.formatFolder(outFolder+ 'mappedGFF/',True)
#GETTING INPUT FILE
if options.input.split('.')[-1] == 'bed':
#CONVERTING A BED TO GFF
inputGFFName = options.input.split('/')[-1][0:-4]
inputGFFFile = '%s%s.gff' % (gffFolder,inputGFFName)
ROSE_utils.bedToGFF(options.input,inputGFFFile)
elif options.input.split('.')[-1] =='gff':
#COPY THE INPUT GFF TO THE GFF FOLDER
inputGFFFile = options.input
os.system('cp %s %s' % (inputGFFFile,gffFolder))
else:
print('WARNING: INPUT FILE DOES NOT END IN .gff or .bed. ASSUMING .gff FILE FORMAT')
#COPY THE INPUT GFF TO THE GFF FOLDER
inputGFFFile = options.input
os.system('cp %s %s' % (inputGFFFile,gffFolder))
def main():
'''
main run call
'''
debug = False
from optparse import OptionParser
usage = "usage: %prog [options] -g [GENOME] -i [INPUT_ENHANCER_FILE]"
parser = OptionParser(usage=usage)
#required flags
parser.add_option(
"-i",
"--i",
dest="input",
nargs=1,
default=None,
help="Enter a ROSE ranked enhancer or super-enhancer file")
parser.add_option("-g",
"--genome",
dest="genome",
nargs=1,
default=None,
help="Enter the genome build (MM9,MM8,HG18,HG19)")
#optional flags
parser.add_option("-l",
"--list",
dest="geneList",
nargs=1,
default=None,
help="Enter a gene list to filter through")
parser.add_option(
"-o",
"--out",
dest="out",
nargs=1,
default=None,
help="Enter an output folder. Default will be same folder as input file"
)
parser.add_option(
"-w",
"--window",
dest="window",
nargs=1,
default=50000,
help="Enter a search distance for genes. Default is 50,000bp")
parser.add_option(
"-f",
"--format",
dest="formatTable",
action="store_true",
default=False,
help="If flagged, maintains original formatting of input table")
#RETRIEVING FLAGS
(options, args) = parser.parse_args()
if not options.input or not options.genome:
parser.print_help()
exit()
#GETTING THE INPUT
enhancerFile = options.input
window = int(options.window)
#making the out folder if it doesn't exist
if options.out:
outFolder = ROSE_utils.formatFolder(options.out, True)
else:
outFolder = join(enhancerFile.split('/')[0:-1], '/') + '/'
#GETTING THE GENOME
genome = options.genome
print('USING %s AS THE GENOME' % genome)
#CHECK FORMATTING FLAG
if options.formatTable:
noFormatTable = True
else:
noFormatTable = False
#GETTING THE CORRECT ANNOT FILE
cwd = os.getcwd()
genomeDict = {
'HG18': '%s/annotation/hg18_refseq.ucsc' % (cwd),
'MM9': '%s/annotation/mm9_refseq.ucsc' % (cwd),
'HG19': '%s/annotation/hg19_refseq.ucsc' % (cwd),
'MM8': '%s/annotation/mm8_refseq.ucsc' % (cwd),
'MM10': '%s/annotation/mm10_refseq.ucsc' % (cwd),
}
annotFile = genomeDict[upper(genome)]
#GETTING THE TRANSCRIBED LIST
if options.geneList:
transcribedFile = options.geneList
else:
transcribedFile = ''
enhancerToGeneTable, geneToEnhancerTable = mapEnhancerToGene(
annotFile, enhancerFile, transcribedFile, True, window, noFormatTable)
#Writing enhancer output
enhancerFileName = enhancerFile.split('/')[-1].split('.')[0]
if window != 50000:
#writing the enhancer table
out1 = '%s%s_ENHANCER_TO_GENE_%sKB.txt' % (outFolder, enhancerFileName,
window / 1000)
ROSE_utils.unParseTable(enhancerToGeneTable, out1, '\t')
#writing the gene table
out2 = '%s%s_GENE_TO_ENHANCER_%sKB.txt' % (outFolder, enhancerFileName,
window / 1000)
ROSE_utils.unParseTable(geneToEnhancerTable, out2, '\t')
else:
#writing the enhancer table
out1 = '%s%s_ENHANCER_TO_GENE.txt' % (outFolder, enhancerFileName)
ROSE_utils.unParseTable(enhancerToGeneTable, out1, '\t')
#writing the gene table
out2 = '%s%s_GENE_TO_ENHANCER.txt' % (outFolder, enhancerFileName)
ROSE_utils.unParseTable(geneToEnhancerTable, out2, '\t')
def main():
'''
main run call
'''
debug = False
from optparse import OptionParser
usage = "usage: %prog [options] -g [GENOME] -i [INPUT_REGION_GFF] -r [RANKBY_BAM_FILE] -o [OUTPUT_FOLDER] [OPTIONAL_FLAGS]"
parser = OptionParser(usage=usage)
#required flags
parser.add_option(
"-i",
"--i",
dest="input",
nargs=1,
default=None,
help="Enter a .gff or .bed file of binding sites used to make enhancers"
)
parser.add_option("-r",
"--rankby",
dest="rankby",
nargs=1,
default=None,
help="bamfile to rank enhancer by")
parser.add_option("-o",
"--out",
dest="out",
nargs=1,
default=None,
help="Enter an output folder")
parser.add_option(
"-g",
"--genome",
dest="genome",
nargs=1,
default=None,
help="Enter the genome build (MM9,MM8,HG18,HG19,MM10,HG38)")
#optional flags
parser.add_option(
"-b",
"--bams",
dest="bams",
nargs=1,
default=None,
help="Enter a comma separated list of additional bam files to map to")
parser.add_option("-c",
"--control",
dest="control",
nargs=1,
default=None,
help="bamfile to rank enhancer by")
parser.add_option("-s",
"--stitch",
dest="stitch",
nargs=1,
default=12500,
help="Enter a max linking distance for stitching")
parser.add_option(
"-t",
"--tss",
dest="tss",
nargs=1,
default=0,
help="Enter a distance from TSS to exclude. 0 = no TSS exclusion")
#RETRIEVING FLAGS
(options, args) = parser.parse_args()
if not options.input or not options.rankby or not options.out or not options.genome:
print('hi there')
parser.print_help()
exit()
#making the out folder if it doesn't exist
outFolder = ROSE_utils.formatFolder(options.out, True)
#figuring out folder schema
gffFolder = ROSE_utils.formatFolder(outFolder + 'gff/', True)
mappedFolder = ROSE_utils.formatFolder(outFolder + 'mappedGFF/', True)
#GETTING INPUT FILE
if options.input.split('.')[-1] == 'bed':
#CONVERTING A BED TO GFF
inputGFFName = options.input.split('/')[-1][0:-4]
inputGFFFile = '%s%s.gff' % (gffFolder, inputGFFName)
ROSE_utils.bedToGFF(options.input, inputGFFFile)
elif options.input.split('.')[-1] == 'gff':
#COPY THE INPUT GFF TO THE GFF FOLDER
inputGFFFile = options.input
os.system('cp %s %s' % (inputGFFFile, gffFolder))
else:
print(
'WARNING: INPUT FILE DOES NOT END IN .gff or .bed. ASSUMING .gff FILE FORMAT'
)
#COPY THE INPUT GFF TO THE GFF FOLDER
inputGFFFile = options.input
os.system('cp %s %s' % (inputGFFFile, gffFolder))
#GETTING THE LIST OF BAMFILES TO PROCESS
if options.control:
bamFileList = [options.rankby, options.control]
else:
bamFileList = [options.rankby]
if options.bams:
bamFileList += options.bams.split(',')
bamFileLIst = ROSE_utils.uniquify(bamFileList)
#optional args
#Stitch parameter
stitchWindow = int(options.stitch)
#tss options
tssWindow = int(options.tss)
if tssWindow != 0:
removeTSS = True
else:
removeTSS = False
#GETTING THE BOUND REGION FILE USED TO DEFINE ENHANCERS
print('USING %s AS THE INPUT GFF' % (inputGFFFile))
inputName = inputGFFFile.split('/')[-1].split('.')[0]
#GETTING THE GENOME
genome = options.genome
print('USING %s AS THE GENOME' % genome)
#GETTING THE CORRECT ANNOT FILE
cwd = os.getcwd()
genomeDict = {
'HG18': '%s/annotation/hg18_refseq.ucsc' % (cwd),
'MM9': '%s/annotation/mm9_refseq.ucsc' % (cwd),
'HG19': '%s/annotation/hg19_refseq.ucsc' % (cwd),
'MM8': '%s/annotation/mm8_refseq.ucsc' % (cwd),
'MM10': '%s/annotation/mm10_refseq.ucsc' % (cwd),
'HG38': '%s/annotation/hg38_refseq.ucsc' % (cwd),
}
annotFile = genomeDict[upper(genome)]
#MAKING THE START DICT
print('MAKING START DICT')
startDict = ROSE_utils.makeStartDict(annotFile)
#LOADING IN THE BOUND REGION REFERENCE COLLECTION
print('LOADING IN GFF REGIONS')
referenceCollection = ROSE_utils.gffToLocusCollection(inputGFFFile)
#NOW STITCH REGIONS
print('STITCHING REGIONS TOGETHER')
stitchedCollection, debugOutput = regionStitching(inputGFFFile,
stitchWindow, tssWindow,
annotFile, removeTSS)
#NOW MAKE A STITCHED COLLECTION GFF
print('MAKING GFF FROM STITCHED COLLECTION')
stitchedGFF = ROSE_utils.locusCollectionToGFF(stitchedCollection)
if not removeTSS:
stitchedGFFFile = '%s%s_%sKB_STITCHED.gff' % (gffFolder, inputName,
stitchWindow / 1000)
stitchedGFFName = '%s_%sKB_STITCHED' % (inputName, stitchWindow / 1000)
debugOutFile = '%s%s_%sKB_STITCHED.debug' % (gffFolder, inputName,
stitchWindow / 1000)
else:
stitchedGFFFile = '%s%s_%sKB_STITCHED_TSS_DISTAL.gff' % (
gffFolder, inputName, stitchWindow / 1000)
stitchedGFFName = '%s_%sKB_STITCHED_TSS_DISTAL' % (inputName,
stitchWindow / 1000)
debugOutFile = '%s%s_%sKB_STITCHED_TSS_DISTAL.debug' % (
gffFolder, inputName, stitchWindow / 1000)
#WRITING DEBUG OUTPUT TO DISK
if debug:
print('WRITING DEBUG OUTPUT TO DISK AS %s' % (debugOutFile))
ROSE_utils.unParseTable(debugOutput, debugOutFile, '\t')
#WRITE THE GFF TO DISK
print('WRITING STITCHED GFF TO DISK AS %s' % (stitchedGFFFile))
ROSE_utils.unParseTable(stitchedGFF, stitchedGFFFile, '\t')
#SETTING UP THE OVERALL OUTPUT FILE
outputFile1 = outFolder + stitchedGFFName + '_ENHANCER_REGION_MAP.txt'
print('OUTPUT WILL BE WRITTEN TO %s' % (outputFile1))
#MAPPING TO THE NON STITCHED (ORIGINAL GFF)
#MAPPING TO THE STITCHED GFF
# bin for bam mapping
nBin = 1
#IMPORTANT
#CHANGE cmd1 and cmd2 TO PARALLELIZE OUTPUT FOR BATCH SUBMISSION
#e.g. if using LSF cmd1 = "bsub python bamToGFF.py -f 1 -e 200 -r -m %s -b %s -i %s -o %s" % (nBin,bamFile,stitchedGFFFile,mappedOut1)
for bamFile in bamFileList:
bamFileName = bamFile.split('/')[-1]
#MAPPING TO THE STITCHED GFF
mappedOut1 = '%s%s_%s_MAPPED.gff' % (mappedFolder, stitchedGFFName,
bamFileName)
#WILL TRY TO RUN AS A BACKGROUND PROCESS. BATCH SUBMIT THIS LINE TO IMPROVE SPEED
cmd1 = "python ROSE_bamToGFF_turbo.py -e 200 -r -m %s -b %s -i %s -o %s &" % (
nBin, bamFile, stitchedGFFFile, mappedOut1)
print(cmd1)
os.system(cmd1)
#MAPPING TO THE ORIGINAL GFF
mappedOut2 = '%s%s_%s_MAPPED.gff' % (mappedFolder, inputName,
bamFileName)
#WILL TRY TO RUN AS A BACKGROUND PROCESS. BATCH SUBMIT THIS LINE TO IMPROVE SPEED
cmd2 = "python ROSE_bamToGFF_turbo.py 1 -e 200 -r -m %s -b %s -i %s -o %s &" % (
nBin, bamFile, inputGFFFile, mappedOut2)
print(cmd2)
os.system(cmd2)
print('PAUSING TO MAP')
time.sleep(10)
#CHECK FOR MAPPING OUTPUT
outputDone = False
ticker = 0
print('WAITING FOR MAPPING TO COMPLETE. ELAPSED TIME (MIN):')
while not outputDone:
'''
check every 1 minutes for completed output
'''
outputDone = True
if ticker % 6 == 0:
print(ticker * 5)
ticker += 1
#CHANGE THIS PARAMETER TO ALLOW MORE TIME TO MAP
if ticker == 120:
print(
'ERROR: OPERATION TIME OUT. MAPPING OUTPUT NOT DETECTED AFTER 2 HOURS'
)
exit()
break
for bamFile in bamFileList:
#GET THE MAPPED OUTPUT NAMES HERE FROM MAPPING OF EACH BAMFILE
bamFileName = bamFile.split('/')[-1]
mappedOut1 = '%s%s_%s_MAPPED.gff' % (mappedFolder, stitchedGFFName,
bamFileName)
try:
mapFile = open(mappedOut1, 'r')
mapFile.close()
except IOError:
outputDone = False
mappedOut2 = '%s%s_%s_MAPPED.gff' % (mappedFolder, inputName,
bamFileName)
try:
mapFile = open(mappedOut2, 'r')
mapFile.close()
except IOError:
outputDone = False
if outputDone == True:
break
time.sleep(60)
print('MAPPING TOOK %s MINUTES' % (ticker))
print('BAM MAPPING COMPLETED NOW MAPPING DATA TO REGIONS')
#CALCULATE DENSITY BY REGION
mapCollection(stitchedCollection,
referenceCollection,
bamFileList,
mappedFolder,
outputFile1,
refName=stitchedGFFName)
time.sleep(10)
print('CALLING AND PLOTTING SUPER-ENHANCERS')
if options.control:
rankbyName = options.rankby.split('/')[-1]
controlName = options.control.split('/')[-1]
cmd = 'R --no-save %s %s %s %s < ROSE_callSuper.R' % (
outFolder, outputFile1, inputName, controlName)
else:
rankbyName = options.rankby.split('/')[-1]
controlName = 'NONE'
cmd = 'R --no-save %s %s %s %s < ROSE_callSuper.R' % (
outFolder, outputFile1, inputName, controlName)
print(cmd)
os.system(cmd)
#calling the gene mapper
time.sleep(20)
superTableFile = "%s_SuperEnhancers.table.txt" % (inputName)
cmd = "python ROSE_geneMapper.py -g %s -i %s%s" % (genome, outFolder,
superTableFile)
os.system(cmd)
def main():
'''
main run call
'''
debug = False
from optparse import OptionParser
usage = "usage: %prog [options] -g [GENOME] -i [INPUT_ENHANCER_FILE]"
parser = OptionParser(usage = usage)
#required flags
parser.add_option("-i","--i", dest="input",nargs = 1, default=None,
help = "Enter a ROSE ranked enhancer or super-enhancer file")
parser.add_option("-g","--genome", dest="genome",nargs = 1, default=None,
help = "Enter the genome build (MM9,MM8,HG18,HG19)")
#optional flags
parser.add_option("-l","--list", dest="geneList",nargs = 1, default=None,
help = "Enter a gene list to filter through")
parser.add_option("-o","--out", dest="out",nargs = 1, default=None,
help = "Enter an output folder. Default will be same folder as input file")
parser.add_option("-w","--window", dest="window",nargs = 1, default=50000,
help = "Enter a search distance for genes. Default is 50,000bp")
parser.add_option("-f","--format", dest="formatTable",action= "store_true", default=False,
help = "If flagged, maintains original formatting of input table")
#RETRIEVING FLAGS
(options,args) = parser.parse_args()
if not options.input or not options.genome:
parser.print_help()
exit()
#GETTING THE INPUT
enhancerFile = options.input
window = int(options.window)
#making the out folder if it doesn't exist
if options.out:
outFolder = ROSE_utils.formatFolder(options.out,True)
else:
outFolder = join(enhancerFile.split('/')[0:-1],'/') + '/'
#GETTING THE GENOME
genome = options.genome
print('USING %s AS THE GENOME' % genome)
#CHECK FORMATTING FLAG
if options.formatTable:
noFormatTable =True
else:
noFormatTable = False
#GETTING THE CORRECT ANNOT FILE
cwd = os.getcwd()
genomeDict = {
'HG18':'%s/annotation/hg18_refseq.ucsc' % (cwd),
'MM9': '%s/annotation/mm9_refseq.ucsc' % (cwd),
'HG19':'%s/annotation/hg19_refseq.ucsc' % (cwd),
'MM8': '%s/annotation/mm8_refseq.ucsc' % (cwd),
'MM10':'%s/annotation/mm10_refseq.ucsc' % (cwd),
}
annotFile = genomeDict[upper(genome)]
#GETTING THE TRANSCRIBED LIST
if options.geneList:
transcribedFile = options.geneList
else:
transcribedFile = ''
enhancerToGeneTable,geneToEnhancerTable = mapEnhancerToGene(annotFile,enhancerFile,transcribedFile,True,window,noFormatTable)
#Writing enhancer output
enhancerFileName = enhancerFile.split('/')[-1].split('.')[0]
if window != 50000:
#writing the enhancer table
out1 = '%s%s_ENHANCER_TO_GENE_%sKB.txt' % (outFolder,enhancerFileName,window/1000)
ROSE_utils.unParseTable(enhancerToGeneTable,out1,'\t')
#writing the gene table
out2 = '%s%s_GENE_TO_ENHANCER_%sKB.txt' % (outFolder,enhancerFileName,window/1000)
ROSE_utils.unParseTable(geneToEnhancerTable,out2,'\t')
else:
#writing the enhancer table
out1 = '%s%s_ENHANCER_TO_GENE.txt' % (outFolder,enhancerFileName)
ROSE_utils.unParseTable(enhancerToGeneTable,out1,'\t')
#writing the gene table
out2 = '%s%s_GENE_TO_ENHANCER.txt' % (outFolder,enhancerFileName)
ROSE_utils.unParseTable(geneToEnhancerTable,out2,'\t')