def run( o_options ):
"""The Main function/pipeline for duplication filter.
"""
# Parse options...
options = opt_validate( o_options )
# end of parsing commandline options
info = options.info
warn = options.warn
debug = options.debug
error = options.error
outputfile = open(options.oprefix+"_refinepeak.bed", "w")
#if options.outputfile != "stdout":
# assert not os.path.exists(options.outputfile), "%s already exists, please check!" % options.outputfile
# outfhd = open(options.outputfile,"w")
#else:
# outfhd = sys.stdout
peakio = file(options.bedfile)
peaks = PeakIO()
for l in peakio:
fs = l.rstrip().split()
peaks.add( fs[0], int(fs[1]), int(fs[2]), name=fs[3] )
peaks.sort()
#for l in peakio:
#l = peakio.readline()
#fs = l.rstrip().split()
#print fs
#1 Read tag files
info("read tag files...")
fwtrack = load_tag_files_options (options)
#info("tag size = %d" % options.tsize)
#fwtrack.fw = options.tsize
retval = fwtrack.compute_region_tags_from_peaks( peaks, find_summit, window_size = options.windowsize, cutoff = options.cutoff )
outputfile.write( "\n".join( map(lambda x: "%s\t%d\t%d\t%s\t%.2f" % x , retval) ) )
info("Done!")
info("Check output file: %s" % options.oprefix+"_refinepeak.bed")
def run( o_options ):
"""The Main function/pipeline for duplication filter.
"""
# Parse options...
options = opt_validate( o_options )
# end of parsing commandline options
info = options.info
warn = options.warn
debug = options.debug
error = options.error
outputfile = open(options.oprefix+"_refinepeak.bed", "w")
peakio = file(options.bedfile)
peaks = PeakIO()
for l in peakio:
fs = l.rstrip().split()
peaks.add( fs[0], int(fs[1]), int(fs[2]), name=fs[3] )
peaks.sort()
#1 Read tag files
info("read tag files...")
fwtrack = load_tag_files_options (options)
retval = fwtrack.compute_region_tags_from_peaks( peaks, find_summit, window_size = options.windowsize, cutoff = options.cutoff )
outputfile.write( "\n".join( map(lambda x: "%s\t%d\t%d\t%s\t%.2f" % x , retval) ) )
info("Done!")
info("Check output file: %s" % options.oprefix+"_refinepeak.bed")
def setUp( self ):
self.range = [ 0, 2000 ]
self.binding_sites = [ 300, 500, 700 ]
self.binding_strength = [ 60, 45, 55 ] # approximate binding affility
self.binding_width = [ 150, 150, 150 ]# binding width, left and right sides are cutting sites
self.cutting_variation = 50 # variation at the correct cutting sites
self.tag_size = 50
self.test_tags_file = "random_test.bed"
self.genome_size = 10000
self.plus_tags = [ ]
self.minus_tags = [ ]
for i in range( len(self.binding_sites) ):
j = 0
while j <= self.binding_strength[ i ]:
x = int( normalvariate( self.binding_sites[ i ] - self.binding_width[ i ]/2,
self.cutting_variation ) )
if x > self.range[ 0 ] and x + self.tag_size < self.range[ 1 ]:
self.plus_tags.append( x )
j += 1
j = 0
while j <= self.binding_strength[ i ]:
x = int( normalvariate( self.binding_sites[ i ] + self.binding_width[ i ]/2,
self.cutting_variation ) )
if x - self.tag_size > self.range[ 0 ] and x < self.range[ 1 ]:
self.minus_tags.append( x )
j += 1
self.plus_tags = sorted(self.plus_tags)
self.minus_tags = sorted(self.minus_tags)
#print self.plus_tags
#print self.minus_tags
self.result_peak = PeakIO()
# write reads in bed files
fhd = open( self.test_tags_file, "w" )
for x in self.plus_tags:
fhd.write( "chr1\t%d\t%d\t.\t0\t+\n" % ( x, x + self.tag_size ) )
for x in self.minus_tags:
fhd.write( "chr1\t%d\t%d\t.\t0\t-\n" % ( x - self.tag_size, x ) )
def run( args ):
"""The Differential function/pipeline for MACS.
"""
# Parse options...
options = diff_opt_validate( args )
#0 output arguments
# info("\n"+options.argtxt)
ofile_prefix = options.name
# check if tag files exist
with open(options.t1bdg) as f: pass
with open(options.c1bdg) as f: pass
with open(options.t2bdg) as f: pass
with open(options.c2bdg) as f: pass
if not options.peaks1 == '':
info("Read peaks for condition 1...")
p1io = PeakIO()
with open(options.peaks1, 'rU') as f:
p1io.read_from_xls(f)
if not options.peaks2 == '':
info("Read peaks for condition 2...")
p2io = PeakIO()
with open(options.peaks2, 'rU') as f:
p2io.read_from_xls(f)
#1 Read tag files
info("Read and build treatment 1 bedGraph...")
t1bio = cBedGraphIO.bedGraphIO(options.t1bdg)
t1btrack = t1bio.build_bdgtrack()
info("Read and build control 1 bedGraph...")
c1bio = cBedGraphIO.bedGraphIO(options.c1bdg)
c1btrack = c1bio.build_bdgtrack()
if len(options.depth) >=2:
depth1 = options.depth[0]
depth2 = options.depth[1]
else:
depth1 = options.depth[0]
depth2 = depth1
info("Read and build treatment 2 bedGraph...")
t2bio = cBedGraphIO.bedGraphIO(options.t2bdg)
t2btrack = t2bio.build_bdgtrack()
info("Read and build control 2 bedGraph...")
c2bio = cBedGraphIO.bedGraphIO(options.c2bdg)
c2btrack = c2bio.build_bdgtrack()
#3 Call Peaks
diffscore = DiffScoreTrackI( t1btrack,
c1btrack,
t2btrack,
c2btrack,
depth1, depth2 )
diffscore.finalize()
if options.call_peaks:
diffscore.set_track_score_method(options.track_score_method)
info("Calling peaks")
if options.track_score_method == 'p':
diffscore.call_peaks(cutoff = options.peaks_log_pvalue,
min_length = options.pminlen)
elif options.track_score_method == 'q':
diffscore.call_peaks(cutoff = options.peaks_log_qvalue,
min_length = options.pminlen)
else:
raise NotImplementedError
else:
info("Using existing peaks")
diffscore.store_peaks(p1io, p2io)
info("Rebuilding chromosomes")
diffscore.rebuild_chromosomes()
diffscore.annotate_peaks()
info("Calling differentially occupied peaks")
if options.score_method == 'p':
diffscore.call_diff_peaks(cutoff = options.log_pvalue,
min_length = options.dminlen,
score_method = options.score_method)
if options.score_method == 'q':
diffscore.call_diff_peaks(cutoff = options.log_qvalue,
min_length = options.dminlen,
score_method = options.score_method)
# diffscore.print_some_peaks()
# diffscore.print_diff_peaks()
info("Write output xls and BED files...")
ofhd_xls = open( os.path.join( options.outdir, options.peakxls), "w" )
ofhd_xls.write("# This file is generated by MACS version, using the diffpeak module %s\n" % (MACS_VERSION))
ofhd_xls.write( options.argtxt+"\n" )
ofhd_bed = open( os.path.join( options.outdir, options.peakbed), "w" )
# pass write method so we can print too, and include name
diffscore.write_peaks(xls=ofhd_xls, bed=ofhd_bed,
name = options.name, name_prefix="%s_peak_",
description="Peaks for %s (Made with MACS v2, " + strftime("%x") + ")",
trackline=options.trackline)
ofhd_xls.close()
ofhd_bed.close()
if diffscore.has_peakio():
info("Write annotated peak xls files...")
ofhd_xls1 = open( os.path.join( options.outdir, options.peak1xls), "w" )
ofhd_xls1.write("# This file is generated by MACS version, using the diffpeak module %s\n" % (MACS_VERSION))
ofhd_xls1.write(options.argtxt+"\n")
ofhd_xls2 = open( os.path.join( options.outdir, options.peak2xls), "w" )
ofhd_xls2.write("# This file is generated by MACS version, using the diffpeak module %s\n" % (MACS_VERSION))
ofhd_xls2.write(options.argtxt+"\n")
diffscore.write_peaks_by_summit(ofhd_xls1, ofhd_xls2,
name = options.name, name_prefix="%s_peak_")
ofhd_xls1.close()
ofhd_xls2.close()
if options.store_bdg:
info("#4 Write output bedgraph files...")
ofhd_logLR = open( os.path.join( options.outdir, options.bdglogLR), "w" )
ofhd_pvalue = open( os.path.join( options.outdir, options.bdgpvalue), "w" )
ofhd_logFC = open( os.path.join( options.outdir, options.bdglogFC), "w" )
diffscore.write_bedgraphs(logLR=ofhd_logLR, pvalue=ofhd_pvalue,
logFC=ofhd_logFC, name = options.name,
description=" for %s (Made with MACS v2, " + strftime("%x") + ")",
trackline=options.trackline)
ofhd_logLR.close()
ofhd_pvalue.close()
ofhd_logFC.close()
def run( args ):
"""The Differential function/pipeline for MACS.
"""
# Parse options...
options = diff_opt_validate( args )
#0 output arguments
# info("\n"+options.argtxt)
ofile_prefix = options.name
# check if tag files exist
with open(options.t1bdg) as f: pass
with open(options.c1bdg) as f: pass
with open(options.t2bdg) as f: pass
with open(options.c2bdg) as f: pass
if not options.peaks1 == '':
info("Read peaks for condition 1...")
p1io = PeakIO()
with open(options.peaks1, 'rU') as f:
p1io.read_from_xls(f)
if not options.peaks2 == '':
info("Read peaks for condition 2...")
p2io = PeakIO()
with open(options.peaks2, 'rU') as f:
p2io.read_from_xls(f)
#1 Read tag files
info("Read and build treatment 1 bedGraph...")
t1bio = cBedGraphIO.bedGraphIO(options.t1bdg)
t1btrack = t1bio.build_bdgtrack()
info("Read and build control 1 bedGraph...")
c1bio = cBedGraphIO.bedGraphIO(options.c1bdg)
c1btrack = c1bio.build_bdgtrack()
if len(options.depth) >=2:
depth1 = options.depth[0]
depth2 = options.depth[1]
else:
depth1 = options.depth[0]
depth2 = depth1
info("Read and build treatment 2 bedGraph...")
t2bio = cBedGraphIO.bedGraphIO(options.t2bdg)
t2btrack = t2bio.build_bdgtrack()
info("Read and build control 2 bedGraph...")
c2bio = cBedGraphIO.bedGraphIO(options.c2bdg)
c2btrack = c2bio.build_bdgtrack()
#3 Call Peaks
diffscore = DiffScoreTrackI( t1btrack,
c1btrack,
t2btrack,
c2btrack,
depth1, depth2 )
diffscore.finalize()
if options.call_peaks:
diffscore.set_track_score_method(options.track_score_method)
info("Calling peaks")
if options.track_score_method == 'p':
diffscore.call_peaks(cutoff = options.peaks_log_pvalue,
min_length = options.pminlen)
elif options.track_score_method == 'q':
diffscore.call_peaks(cutoff = options.peaks_log_qvalue,
min_length = options.pminlen)
else:
raise NotImplementedError
else:
info("Using existing peaks")
diffscore.store_peaks(p1io, p2io)
info("Rebuilding chromosomes")
diffscore.rebuild_chromosomes()
diffscore.annotate_peaks()
info("Calling differentially occupied peaks")
if options.score_method == 'p':
diffscore.call_diff_peaks(cutoff = options.log_pvalue,
min_length = options.dminlen,
score_method = options.score_method)
if options.score_method == 'q':
diffscore.call_diff_peaks(cutoff = options.log_qvalue,
min_length = options.dminlen,
score_method = options.score_method)
# diffscore.print_some_peaks()
# diffscore.print_diff_peaks()
info("Write output xls and BED files...")
ofhd_xls = open( os.path.join( options.outdir, options.peakxls), "w" )
ofhd_xls.write("# This file is generated by MACS version, using the diffpeak module %s\n" % (MACS_VERSION))
ofhd_xls.write( options.argtxt+"\n" )
ofhd_bed = open( os.path.join( options.outdir, options.peakbed), "w" )
# pass write method so we can print too, and include name
diffscore.write_peaks(xls=ofhd_xls, bed=ofhd_bed,
name = options.name, name_prefix="%s_peak_",
description="Peaks for %s (Made with MACS v2, " + strftime("%x") + ")",
trackline=options.trackline)
ofhd_xls.close()
ofhd_bed.close()
if diffscore.has_peakio():
info("Write annotated peak xls files...")
ofhd_xls1 = open( os.path.join( options.outdir, options.peak1xls), "w" )
ofhd_xls1.write("# This file is generated by MACS version, using the diffpeak module %s\n" % (MACS_VERSION))
ofhd_xls1.write(options.argtxt+"\n")
ofhd_xls2 = open( os.path.join( options.outdir, options.peak2xls), "w" )
ofhd_xls2.write("# This file is generated by MACS version, using the diffpeak module %s\n" % (MACS_VERSION))
ofhd_xls2.write(options.argtxt+"\n")
diffscore.write_peaks_by_summit(ofhd_xls1, ofhd_xls2,
name = options.name, name_prefix="%s_peak_")
ofhd_xls1.close()
ofhd_xls2.close()
if options.store_bdg:
info("#4 Write output bedgraph files...")
ofhd_logLR = open( os.path.join( options.outdir, options.bdglogLR), "w" )
ofhd_pvalue = open( os.path.join( options.outdir, options.bdgpvalue), "w" )
ofhd_logFC = open( os.path.join( options.outdir, options.bdglogFC), "w" )
diffscore.write_bedgraphs(logLR=ofhd_logLR, pvalue=ofhd_pvalue,
logFC=ofhd_logFC, name = options.name,
description=" for %s (Made with MACS v2, " + strftime("%x") + ")",
trackline=options.trackline)
ofhd_logLR.close()
ofhd_pvalue.close()
ofhd_logFC.close()
