def main():
usage = "%prog [options]" + "\n"
parser = OptionParser(usage, version="%prog " + __version__)
parser.add_option(
"-i",
"--input-file",
action="store",
type="string",
dest="input_file",
help=
"BED6+ file specifying the C position. This BED file should have at least 6 columns (Chrom, ChromStart, ChromeEnd, Name, Beta_value, Strand). BED6+ file can be a regular text file or compressed file (*.gz, *.bz2) or accessible url."
)
parser.add_option(
"-r",
"--refgene",
action="store",
type="string",
dest="gene_file",
help=
"Reference gene model in standard BED12 format (https://genome.ucsc.edu/FAQ/FAQformat.html#format1). \"Strand\" column must exist in order to decide 5' and 3' UTRs, up- and down-stream intergenic regions."
)
parser.add_option(
"-d",
"--downstream",
action="store",
type="int",
dest="downstream_size",
default=2000,
help=
"Size of down-stream genomic region added to gene. default=%default (bp)"
)
parser.add_option(
"-u",
"--upstream",
action="store",
type="int",
dest="upstream_size",
default=2000,
help=
"Size of up-stream genomic region added to gene. default=%default (bp)"
)
parser.add_option("-o",
"--output",
action="store",
type='string',
dest="out_file",
help="Prefix of the output file.")
(options, args) = parser.parse_args()
print()
if not (options.input_file):
print(__doc__)
parser.print_help()
sys.exit(101)
if not (options.gene_file):
print(__doc__)
parser.print_help()
sys.exit(102)
if not (options.out_file):
print(__doc__)
parser.print_help()
sys.exit(103)
FOUT = open(options.out_file + '.txt', 'w')
ROUT = open(options.out_file + '.r', 'w')
print("\t".join(["Group", "Relative_position(5'->3')", "Average_beta"]),
file=FOUT)
#step1: read CpG file
printlog("Reading CpG file: \"%s\"" % (options.input_file))
cpg_ranges = read_CpG_bed(options.input_file)
#step2: read gene file
printlog("Reading reference gene model: \"%s\"" % (options.gene_file))
ref_gene = BED.ParseBED(options.gene_file)
group_sizes = [] #number of datapoints in each group
printlog("Process upstream regions ...")
up_2k = ref_gene.getIntergenic(direction='up', size=options.upstream_size)
s = coverage_over_range(up_2k, cpg_ranges)
group_sizes.append(len(s))
for i in sorted(s):
print('\t'.join(['Upstream_intergenic', str(i), str(s[i])]), file=FOUT)
print('Upstream_intergenic_y=c(%s)' %
','.join([str(s[i]) for i in sorted(s)]),
file=ROUT)
printlog("Process 5' UTR exons ...")
utr5_exons = ref_gene.getUTRs(utr=5)
s = coverage_over_range(utr5_exons, cpg_ranges)
group_sizes.append(len(s))
for i in sorted(s):
print('\t'.join(['Five_prime_UTR', str(i), str(s[i])]), file=FOUT)
print('Five_prime_UTR_y=c(%s)' % ','.join([str(s[i]) for i in sorted(s)]),
file=ROUT)
printlog("Process Coding exons ...")
cds_exons = ref_gene.getCDSExons()
s = coverage_over_range(cds_exons, cpg_ranges)
group_sizes.append(len(s))
for i in sorted(s):
print('\t'.join(['Coding_exon', str(i), str(s[i])]), file=FOUT)
print('Coding_exon_y=c(%s)' % ','.join([str(s[i]) for i in sorted(s)]),
file=ROUT)
printlog("Process first introns ...")
introns = ref_gene.getIntrons(itype='first')
s = coverage_over_range(introns, cpg_ranges)
group_sizes.append(len(s))
for i in sorted(s):
print('\t'.join(['First_intron', str(i), str(s[i])]), file=FOUT)
print('First_intron_y=c(%s)' % ','.join([str(s[i]) for i in sorted(s)]),
file=ROUT)
printlog("Process internal introns ...")
introns = ref_gene.getIntrons(itype='internal')
s = coverage_over_range(introns, cpg_ranges)
group_sizes.append(len(s))
for i in sorted(s):
print('\t'.join(['Internal_intron', str(i), str(s[i])]), file=FOUT)
print('Internal_intron_y=c(%s)' % ','.join([str(s[i]) for i in sorted(s)]),
file=ROUT)
printlog("Process last introns ...")
introns = ref_gene.getIntrons(itype='last')
s = coverage_over_range(introns, cpg_ranges)
group_sizes.append(len(s))
for i in sorted(s):
print('\t'.join(['Last_intron', str(i), str(s[i])]), file=FOUT)
print('Last_intron_y=c(%s)' % ','.join([str(s[i]) for i in sorted(s)]),
file=ROUT)
printlog("Process 3' UTR exons ...")
utr3_exons = ref_gene.getUTRs(utr=3)
s = coverage_over_range(utr3_exons, cpg_ranges)
group_sizes.append(len(s))
for i in sorted(s):
print('\t'.join(['Three_prime_UTR', str(i), str(s[i])]), file=FOUT)
print('Three_prime_UTR_y=c(%s)' % ','.join([str(s[i]) for i in sorted(s)]),
file=ROUT)
printlog("Process downstream regions ...")
down_2k = ref_gene.getIntergenic(direction='down',
size=options.downstream_size)
s = coverage_over_range(down_2k, cpg_ranges)
group_sizes.append(len(s))
for i in sorted(s):
print('\t'.join(['Downstream_intergenic',
str(i), str(s[i])]),
file=FOUT)
print('Downstream_intergenic_y=c(%s)' %
','.join([str(s[i]) for i in sorted(s)]),
file=ROUT)
print('\n')
print('pdf(file=\"%s\", width=10, height=5)' % (options.out_file + '.pdf'),
file=ROUT)
print(
'plot(1:%d, c(Upstream_intergenic_y, Five_prime_UTR_y, Coding_exon_y, First_intron_y, Internal_intron_y, Last_intron_y, Three_prime_UTR_y, Downstream_intergenic_y),ylim=c(0,1), xaxt="n",xlab="", ylab="Average methylation", type="l", col="red")'
% sum(group_sizes),
file=ROUT)
print(
'abline(v = c(100,201,302,403,504,605,706),col="blue", lty="dashed")',
file=ROUT)
print('abline(v = c(%d,%d,%d,%d,%d,%d,%d),col="blue", lty="dashed")' %
(sum(group_sizes[0:1]), sum(group_sizes[0:2]), sum(group_sizes[0:3]),
sum(group_sizes[0:4]), sum(group_sizes[0:5]), sum(
group_sizes[0:6]), sum(group_sizes[0:7])),
file=ROUT)
print('abline(h = 0.5,col="grey", lty="dashed")', file=ROUT)
print(
'text(x=c(%d,%d,%d,%d,%d,%d,%d, %d)+50, y=0.9, cex=0.7, labels=c("Upstream\\n(5\'->3\')", "5\'UTR exon\\n(5\'->3\')","Coding exon\\n(5\'->3\')","First intron\\n(5\'->3\')","Internal intron\\n(5\'->3\')","Last intron\\n(5\'->3\')", "3\'UTR exon\\n(5\'->3\')","Downstream\n(5\'->3\')"))'
% (0, sum(group_sizes[0:1]), sum(group_sizes[0:2]),
sum(group_sizes[0:3]), sum(group_sizes[0:4]), sum(group_sizes[0:5]),
sum(group_sizes[0:6]), sum(group_sizes[0:7])),
file=ROUT)
print('dev.off()', file=ROUT)
FOUT.close()
ROUT.close()
try:
subprocess.call("Rscript " + options.out_file + '.r', shell=True)
except:
print("Cannot generate pdf file from " + options.out_file + '.r',
file=sys.stderr)
pass
def main():
usage="%prog [options]" + "\n"
parser = OptionParser(usage,version="%prog " + __version__)
parser.add_option("-i","--input_file",action="store",type="string",dest="input_file",help="BED file specifying the C position. This BED file should have at least three columns (Chrom, ChromStart, ChromeEnd). Note: the first base in a chromosome is numbered 0. This file can be a regular text file or compressed file (.gz, .bz2).")
parser.add_option("-r","--refgene",action="store",type="string",dest="gene_file",help="Reference gene model in standard BED-12 format (https://genome.ucsc.edu/FAQ/FAQformat.html#format1). ")
parser.add_option("-d","--downstream",action="store",type="int",dest="downstream_size",default=2000,help="Size of down-stream intergenic region w.r.t. TES (transcription end site). default=%default (bp)")
parser.add_option("-u","--upstream",action="store",type="int",dest="upstream_size",default=2000,help="Size of up-stream intergenic region w.r.t. TSS (transcription start site). default=%default (bp)")
parser.add_option("-o","--output",action="store",type='string', dest="out_file",help="The prefix of the output file.")
(options,args)=parser.parse_args()
print ()
if not (options.input_file):
print (__doc__)
parser.print_help()
sys.exit(101)
if not (options.gene_file):
print (__doc__)
parser.print_help()
sys.exit(102)
if not (options.out_file):
print (__doc__)
parser.print_help()
sys.exit(103)
FOUT = open(options.out_file + '.tsv','w')
ROUT = open(options.out_file + '.r','w')
#step1: read CpG file
printlog("Reading CpG file: \"%s\"" % (options.input_file))
cpg_ranges = read_CpG_bed(options.input_file)
#step2: read gene file
printlog("Reading reference gene model: \"%s\"" % (options.gene_file))
ref_gene = BED.ParseBED(options.gene_file)
result = [("Priority_order", "Name", "Number_of_regions", "Size_of_regions(bp)", "CpG_raw_count", "CpG_count_per_KB")]
#priority order: #1
printlog("Extract Coding exons ...")
cds_exons = ref_gene.getCDSExons(stranded=False)
printlog("Merge Coding exons ...")
cds_exons = BED.unionBed3(cds_exons)
printlog("Count CpGs in Coding exons ...")
(size,count) = count_over_range(cds_exons, cpg_ranges)
result.append(['0','Coding exons', len(cds_exons), size, count, count*1000.0/size]) #Class, number_of_region, size_of_region, CpG_raw_count, CpG_count_perKb
#priority order: #2
printlog("Extract UTR exons ...")
utr_exons = ref_gene.getUTRs(utr=35, uniquify=True, stranded = False)
printlog("Merge UTR exons ...")
utr_exons = BED.unionBed3(utr_exons)
printlog("Subtract regions with higher priority from UTR exons ...")
utr_exons = BED.subtractBed3(utr_exons, cds_exons) #nucleotides of utr_exons that overlaps with coding exons will be removed
printlog("Count CpGs in UTR exons ...")
(size,count) = count_over_range(utr_exons, cpg_ranges)
result.append(['1','UTR exons', len(utr_exons), size, count, count*1000.0/size])
#priority order: #3
printlog("Extract introns ...")
introns = ref_gene.getIntrons(itype='all', uniquify=True, stranded=False)
printlog("Merge introns ...")
introns = BED.unionBed3(introns)
printlog("Subtract regions with higher priority from introns ...")
introns = BED.subtractBed3(introns, cds_exons)
introns = BED.subtractBed3(introns, utr_exons)
printlog("Count CpGs in introns ...")
(size,count) = count_over_range(introns, cpg_ranges)
result.append(['2','Introns', len(introns), size, count, count*1000.0/size])
#priority order: #4
printlog("Extract upstream intergenic regions ...")
upstream = ref_gene.getIntergenic(direction='up', size=options.upstream_size, uniquify=True, stranded = False)
printlog("Merge upstream intergenic regions ...")
upstream = BED.unionBed3(upstream)
printlog("Subtract regions with higher priority from upstream intergenic regions...")
upstream = BED.subtractBed3(upstream, cds_exons)
upstream = BED.subtractBed3(upstream, utr_exons)
upstream = BED.subtractBed3(upstream, introns)
printlog("Count CpGs in upstream regions ...")
(size,count) = count_over_range(upstream, cpg_ranges)
result.append(['3','Upstream of TSS', len(upstream), size, count, count*1000.0/size])
#priority order: #5
printlog("Extract downstream intergenic regions ...")
downstream = ref_gene.getIntergenic(direction='down', size=options.downstream_size, uniquify=True, stranded = False)
printlog("Merge downstream intergenic regions ...")
downstream = BED.unionBed3(downstream)
printlog("Subtract regions with higher priority from downstream intergenic regions...")
downstream = BED.subtractBed3(downstream, cds_exons)
downstream = BED.subtractBed3(downstream, utr_exons)
downstream = BED.subtractBed3(downstream, introns)
downstream = BED.subtractBed3(downstream, upstream)
printlog("Count CpGs in downstream regions ...")
(size,count) = count_over_range(downstream, cpg_ranges)
result.append(['4','Downstream of TES', len(downstream), size, count, count*1000.0/size])
print('\n')
names=[] #[0,1,2,3,4]
labels = [] #[bed names]
density=[]
for tmp in result:
print ('\t'.join([str(i) for i in tmp]), file=FOUT)
names.append(tmp[0])
labels.append(tmp[1])
density.append(tmp[5])
FOUT.close()
print("name = c(%s)" % ','.join(['"' + i + '"' for i in names[1:]]), file=ROUT)
print("values = c(%s)" % ','.join([str(i) for i in density[1:]]), file=ROUT)
print ('pdf("%s", width=8, height=6)' % (options.out_file + '.pdf'), file=ROUT)
print ('layout(matrix(c(1,1,2,1,1,2), nrow=2, byrow=TRUE))', file=ROUT)
print ('barplot(values,names.arg=name,col=c(%s),ylab="CpG per Kb")' % ','.join(colors(5)), file=ROUT)
print ("plot(c(0, 1), c(0, 1), ann = F, bty = 'n', type = 'n', xaxt = 'n', yaxt = 'n')", file=ROUT)
for name,label in zip(names[1:], labels[1:]):
x_pos = 0.0
y_pos = 1-(int(name)*20.0 +5)/100
print ("text(x=%f, y=%f, labels=c(\"%s = %s\"),adj=c(0,0))" % (x_pos, y_pos,name,label), file=ROUT)
print ('dev.off()', file=ROUT)
ROUT.close()
printlog("Running R script ...")
try:
subprocess.call("Rscript " + options.out_file + '.r', shell=True)
except:
print ("Cannot generate pdf file from " + options.out_file + '.r', file=sys.stderr)
pass
def main():
usage = "%prog [options]" + "\n"
parser = OptionParser(usage, version="%prog " + __version__)
parser.add_option(
"-i",
"--cpg",
action="store",
type="string",
dest="cpg_file",
help=
"BED file specifying the C position. This BED file should have at least three columns (Chrom, ChromStart, ChromeEnd). Note: the first base in a chromosome is numbered 0. This file can be a regular text file or compressed file (.gz, .bz2)."
)
parser.add_option("-b",
"--bed",
action="store",
type="string",
dest="bed_files",
help="List of BED files specifying the genomic regions.")
parser.add_option("-o",
"--output",
action="store",
type='string',
dest="out_file",
help="The prefix of the output file.")
(options, args) = parser.parse_args()
print()
if not (options.cpg_file):
print(__doc__)
parser.print_help()
sys.exit(101)
if not (options.bed_files):
print(__doc__)
parser.print_help()
sys.exit(101)
if not (options.out_file):
print(__doc__)
parser.print_help()
sys.exit(102)
FOUT = open(options.out_file + '.txt', 'w')
ROUT = open(options.out_file + '.r', 'w')
#step1: read CpG file
printlog("Reading CpG file: \"%s\"" % (options.cpg_file))
cpg_ranges = read_CpG_bed(options.cpg_file)
#step2: check BED file
printlog("Checking BED files: \"%s\"" % (options.bed_files))
input_bed_files = options.bed_files.replace(' ', '').split(',')
for i in input_bed_files:
if os.path.exists(i):
print("\t%s" % i, file=sys.stderr)
else:
print("\"%s\" does not exist!" % i, file=sys.stderr)
sys.exit(103)
#step3: read, merge, and subtract BED file
dat = {}
result = [("Priority_order", "Name", "Number_of_regions",
"Size_of_regions(bp)", "CpG_raw_count", "CpG_count_per_KB")]
#step3.1: read the first BED file
i = 0
printlog("Reading BED file: \"%s\"" % (input_bed_files[i]))
file_name = os.path.basename(input_bed_files[i])
tmp = read_bed_as_list(input_bed_files[i])
printlog("Merging overlap entries in BED file: \"%s\"" %
(input_bed_files[i]))
dat[i] = BED.unionBed3(tmp)
printlog("Counting CpGs ...")
(size, count) = count_over_range(dat[i], cpg_ranges)
result.append(
[str(i), file_name,
len(dat[i]), size, count, count * 1000.0 / size]
) #Class, number_of_region, size_of_region, CpG_raw_count, CpG_count_perKb
#step3.2: read the remaining BED files
for i in range(1, len(input_bed_files)):
printlog("Reading BED file: \"%s\"" % (input_bed_files[i]))
file_name = os.path.basename(input_bed_files[i])
tmp = read_bed_as_list(input_bed_files[i])
printlog("Merging overlap entries in BED file: \"%s\"" %
(input_bed_files[i]))
dat[i] = BED.unionBed3(tmp)
for j in range(0, i):
printlog("Subtract \"%s\" from \"%s\"" %
(input_bed_files[j], input_bed_files[i]))
dat[i] = BED.subtractBed3(dat[i], dat[j])
(size, count) = count_over_range(dat[i], cpg_ranges)
result.append([
str(i), file_name,
len(dat[i]), size, count, count * 1000.0 / size
])
print('\n')
names = [] #[0,1,2,3,4,...]
labels = [] #[bed names]
density = []
for tmp in result:
print('\t'.join([str(i) for i in tmp]), file=FOUT)
names.append(tmp[0])
labels.append(tmp[1])
density.append(tmp[5])
FOUT.close()
print("name = c(%s)" % ','.join(['"' + i + '"' for i in names[1:]]),
file=ROUT)
print("values = c(%s)" % ','.join([str(i) for i in density[1:]]),
file=ROUT)
print('pdf("%s", width=8, height=6)' % (options.out_file + '.pdf'),
file=ROUT)
print('layout(matrix(c(1,1,2,1,1,2), nrow=2, byrow=TRUE))', file=ROUT)
print('barplot(values,names.arg=name,col=c(%s),ylab="CpG per Kb")' %
','.join(colors(len(input_bed_files))),
file=ROUT)
print(
"plot(c(0, 1), c(0, 1), ann = F, bty = 'n', type = 'n', xaxt = 'n', yaxt = 'n')",
file=ROUT)
for name, label in zip(names[1:], labels[1:]):
x_pos = 0.0
y_pos = 1 - (int(name) * 20.0 + 5) / 200
print("text(x=%f, y=%f, labels=c(\"%s = %s\"),adj=c(0,0))" %
(x_pos, y_pos, name, label),
file=ROUT)
print('dev.off()', file=ROUT)
ROUT.close()
printlog("Running R script ...")
try:
subprocess.call("Rscript " + options.out_file + '.r', shell=True)
except:
print("Cannot generate pdf file from " + options.out_file + '.r',
file=sys.stderr)
pass