def main():
snps = IntervalFile("bedtools/tests/data/snps.hg18.chr21.bed")
rmsk = IntervalFile("bedtools/tests/data/rmsk.hg18.chr21.bed")
# find snps that overlap with repeat annotations
for a in snps:
for hit in rmsk.search(a.chrom, a.start, a.end):
print a.chrom, a.start, a.end, a.name,
print hit.chrom, hit.start, hit.end, hit.name
def main():
bam = Samfile("bedtools/tests/data/NA18152.bam", "rb")
rmsk = IntervalFile("bedtools/tests/data/rmsk.hg18.chr21.bed")
for al in bam:
chrom = bam.getrname(al.rname)
start = al.pos
end = al.aend
name = al.qname
for hit in rmsk.search(chrom, start, end):
print chrom, start, end, name,
print hit.chrom, hit.start, hit.end, hit.name
def main():
bam = Samfile("bedtools/tests/data/NA18152.bam", "rb")
rmsk = IntervalFile("bedtools/tests/data/rmsk.hg18.chr21.bed")
# Example 1:
# Method: IntervalFile.all_hits()
# Report _all_ of the rmsk features that overlap with the BAM alignment
for al in bam:
strand = "+"
if al.is_reverse: strand = "-"
i = Interval(bam.getrname(al.rname), al.pos, al.aend, strand)
for hit in rmsk.all_hits(i, same_strand=True, ovlp_pct=0.75):
print "\t".join(str(x) for x in [i, hit])
def main():
bam = Samfile("bedtools/tests/data/NA18152.bam", "rb")
rmsk = IntervalFile("bedtools/tests/data/rmsk.hg18.chr21.bed")
# Example 1:
# Method: IntervalFile.all_hits()
# Report _all_ of the rmsk features that overlap with the BAM alignment
for al in bam:
strand = "+"
if al.is_reverse: strand = "-"
i = Interval(bam.getrname(al.rname), al.pos, al.aend, strand)
for hit in rmsk.all_hits(i, same_strand=True, ovlp_pct=0.75):
print "\t".join(str(x) for x in [i,hit])
def main():
"""
Examples of printing each interval in an interval file.
- Works with BED, GTF and VCF files.
- Can be uncompressed or GZIP compressed.
"""
# 0.1 Each interval in a BED file
for exon in IntervalFile("bedtools/tests/data/exons.hg18.chr21.bed"):
print exon
# 0.2 Each gene in a GTF file
for gene in IntervalFile("bedtools/tests/data/genes.hg18.chr21.gtf"):
print gene
# 0.3 Each gene in a _compressed_ GTF file
for gene in IntervalFile("bedtools/tests/data/genes.hg18.chr21.gtf.gz"):
print gene
def main(args): """ Examples of printing each interval in an interval file. - Works with BED, GTF and VCF files. - Can be uncompressed or GZIP compressed. """ ########################################################## # ex1. Report the coordinates of overlap b/w exons and rmsk # # Equivalent to: intersectBed -a exons -b rmsk # Uses: IntervalFile.all_hits() ########################################################## genes = IntervalFile(args.genefile) peaks = IntervalFile(args.peakfile) for gene in genes: for peak_hit in peaks.all_hits(gene): print "\t".join(str(f) for f in [gene.chrom, peak_hit.o_start, peak_hit.o_end])
class IntervalFileTest(unittest.TestCase):
file = "data/rmsk.hg18.chr21.bed"
def setUp(self):
self.file = os.path.join(PATH, self.file)
self.bed = IntervalFile(self.file)
def testOverlaps(self):
hits = self.bed.search("chr21", 9719768, 9739768)
print len(hits)
self.assertEqual(len(hits), 8)
for hit in hits:
self.assert_(hit.start <= 9739768 and hit.end >= 9719768)
def testStrands(self):
hits = self.bed.search("chr21", 9719768, 9739768, "+")
for hit in hits:
self.assert_(hit.strand == '+')
hits = self.bed.search("chr21", 9719768, 9739768, "-")
for hit in hits:
self.assert_(hit.strand == '-')
def main():
"""
"""
##########################################################
# ex1. Report the coordinates of overlap b/w exons and rmsk
#
# Equivalent to: intersectBed -a exons -b rmsk
# Uses: IntervalFile.all_hits()
##########################################################
exons = IntervalFile("bedtools/tests/data/exons.hg18.chr21.bed")
rmsk = IntervalFile("bedtools/tests/data/rmsk.hg18.chr21.bed")
# allow 1kb of "slop" on each side of the exon
# when looking for hits
window = 1000
for exon in exons:
# add the slop and search
exon_slop = Interval(exon.chrom, exon.start-window, exon.end + window, exon.strand)
for rmsk_hit in rmsk.all_hits(exon_slop):
print "\t".join(str(f) for f in [exon, rmsk_hit])
def main():
"""
"""
##########################################################
# ex1. Report the coordinates of overlap b/w exons and rmsk
#
# Equivalent to: intersectBed -a exons -b rmsk
# Uses: IntervalFile.all_hits()
##########################################################
exons = IntervalFile("bedtools/tests/data/exons.hg18.chr21.bed")
rmsk = IntervalFile("bedtools/tests/data/rmsk.hg18.chr21.bed")
# allow 1kb of "slop" on each side of the exon
# when looking for hits
window = 1000
for exon in exons:
# add the slop and search
exon_slop = Interval(exon.chrom, exon.start - window,
exon.end + window, exon.strand)
for rmsk_hit in rmsk.all_hits(exon_slop):
print "\t".join(str(f) for f in [exon, rmsk_hit])
class IntervalFileTest(unittest.TestCase):
file = "data/rmsk.hg18.chr21.bed"
def setUp(self):
self.file = os.path.join(PATH, self.file)
self.bed = IntervalFile(self.file)
def testOverlaps(self):
i = Interval("chr21", 9719768, 9739768)
hits = self.bed.all_hits(i)
print len(hits)
self.assertEqual(len(hits), 8)
for hit in hits:
self.assert_(hit.start <= 9739768 and hit.end >= 9719768)
def testStrands(self):
i = Interval("chr21", 9719768, 9739768, "+")
hits = self.bed.all_hits(i, same_strand=True)
for hit in hits:
self.assert_(hit.strand == '+')
i = Interval("chr21", 9719768, 9739768, "-")
hits = self.bed.all_hits(i, same_strand=True)
for hit in hits:
self.assert_(hit.strand == '-')
def Main():
args=ParseArg()
#store bam files and count information:
bams={}
total_reads=np.zeros(len(args.bams))
for i in range(len(args.bams)):
temp_name=args.name[i]
print >> sys.stderr, "\nReading bam file:"+temp_name+"..."
bams[temp_name]=pysam.Samfile(args.bams[i],'rb')
if args.normalize:
for b in bams[temp_name]:
if not b.is_unmapped:
total_reads[i]+=1
if total_reads[i]%10000==0:
print >> sys.stderr, " reading %d reads..\r"%(total_reads[i]),
output=open(args.output+"_count.txt",'w')
#read interval regions:
intervals=IntervalFile(args.interval)
header='\t'.join (str(f) for f in ['chr','start','end','name','score']) + '\t' + '\t'.join(str(f) for f in args.name )
output.write(header+'\n')
print >> sys.stderr,"\n\n Start counting reads for intervals..."
for interval in intervals:
if 'random' in interval.chrom: continue
print_line='\t'.join (str(f) for f in [interval.chrom,interval.start,interval.end,interval.name,interval.score])
for i in range(len(args.bams)):
name=args.name[i]
count=Count_num(bams[name],interval,args.len,args.fragmentL,total_reads[i])
print_line=print_line+'\t'+str(count)
output.write(print_line+'\n')
#close files
output.close()
def main():
# setup a reverse_complement translation
rev_table = string.maketrans('ACGTacgt', 'TGCAtgca')
def revcomp(seq, rev_table):
return seq.translate(rev_table)
# open your fasta file
fasta = Fastafile("bedtools/tests/data/chr21.fa")
# open your bed file
bed = IntervalFile("bedtools/tests/data/rmsk.hg18.chr21.bed")
# for each bed, grab the the DNA in that interval
for b in bed:
# grab the seq, rev. comp if necessary
seq = fasta.fetch(b.chrom, b.start, b.end)
if b.strand == "-":
seq = revcomp(seq, rev_table)
# print the interval and the seq
print b.chrom, b.start, b.end, b.strand, seq
def main():
"""
"""
##########################################################
# ex1. Report the coordinates of overlap b/w exons and rmsk
#
# Equivalent to: intersectBed -a exons -b rmsk
# Uses: IntervalFile.all_hits()
##########################################################
exons = IntervalFile("bedtools/tests/data/exons.hg18.chr21.bed")
rmsk = IntervalFile("bedtools/tests/data/rmsk.hg18.chr21.bed")
for exon in exons:
for rmsk_hit in rmsk.all_hits(exon):
print "\t".join(
str(f) for f in [exon.chrom, rmsk_hit.o_start, rmsk_hit.o_end])
##########################################################
# ex2. Report the original features for overlapping
# exons and rmsk
#
# Equivalent to: intersectBed -a exons -b rmsk -wa -wb
# Uses: IntervalFile.all_hits()
##########################################################
exons = IntervalFile("bedtools/tests/data/exons.hg18.chr21.bed")
rmsk = IntervalFile("bedtools/tests/data/rmsk.hg18.chr21.bed")
for exon in exons:
for rmsk_hit in rmsk.all_hits(exon):
print "\t".join(
str(f) for f in [
exon.chrom, exon.start, exon.end, exon.name, exon.score,
exon.strand, rmsk_hit.chrom, rmsk_hit.start, rmsk_hit.end,
rmsk_hit.name, rmsk_hit.score, rmsk_hit.strand
])
##########################################################
# ex3. Report the count of rmsk overlapping each exon
#
# Equivalent to: intersectBed -a exons -b rmsk -c
# Uses: IntervalFile.count_hits()
##########################################################
exons = IntervalFile("bedtools/tests/data/exons.hg18.chr21.bed")
rmsk = IntervalFile("bedtools/tests/data/rmsk.hg18.chr21.bed")
for exon in exons:
# get the number of hits in rmsk
num_hits = rmsk.count_hits(exon)
print "\t".join(
str(f) for f in [
exon.chrom, exon.start, exon.end, exon.name, exon.score,
exon.strand, num_hits
])
##########################################################
# ex4. Report exons that overlap at least one rmsk
#
# Equivalent to: intersectBed -a exons -b rmsk -u
# Uses: IntervalFile.any_hits()
##########################################################
exons = IntervalFile("bedtools/tests/data/exons.hg18.chr21.bed")
rmsk = IntervalFile("bedtools/tests/data/rmsk.hg18.chr21.bed")
for exon in exons:
# does this exon overlap any rmsk?
if rmsk.any_hits(exon):
print "\t".join(
str(f) for f in [
exon.chrom, exon.start, exon.end, exon.name, exon.score,
exon.strand
])
##########################################################
# ex5. Report exons that DO NOT overlap at least one rmsk
#
# Equivalent to: intersectBed -a exons -b rmsk -v
# Uses: IntervalFile.any_hits()
##########################################################
exons = IntervalFile("bedtools/tests/data/exons.hg18.chr21.bed")
rmsk = IntervalFile("bedtools/tests/data/rmsk.hg18.chr21.bed")
for exon in exons:
# does this exon overlap any rmsk?
if not rmsk.any_hits(exon):
print "\t".join(
str(f) for f in [
exon.chrom, exon.start, exon.end, exon.name, exon.score,
exon.strand
])
##########################################################
# ex6. Report overlap b/w exons and rmsk on the same strand
#
# Equivalent to: intersectBed -a exons -b rmsk -s
# Uses: IntervalFile.all_hits(same_strand=True)
##########################################################
exons = IntervalFile("bedtools/tests/data/exons.hg18.chr21.bed")
rmsk = IntervalFile("bedtools/tests/data/rmsk.hg18.chr21.bed")
for exon in exons:
# use "same_strand" to enforce, well, same strand.
for rmsk_hit in rmsk.all_hits(exon, same_strand=True):
print "\t".join(
str(f) for f in [
exon.chrom, exon.start, exon.end, exon.strand, rmsk_hit.
chrom, rmsk_hit.start, rmsk_hit.end, rmsk_hit.strand
])
##########################################################
# ex7. Report overlap b/w exons and rmsk where the rmsk
# feature covers at least 50% of the exon.
#
# Equivalent to: intersectBed -a exons -b rmsk -f 0.50
# Uses: IntervalFile.all_hits()
##########################################################
exons = IntervalFile("bedtools/tests/data/exons.hg18.chr21.bed")
rmsk = IntervalFile("bedtools/tests/data/rmsk.hg18.chr21.bed")
for exon in exons:
# use "ovlp_pct" to enforce the faction of overlap w.r.t to exon
for rmsk_hit in rmsk.all_hits(exon, ovlp_pct=0.50):
print "\t".join(
str(f) for f in [
exon.chrom, exon.start, exon.end, exon.strand, rmsk_hit.
chrom, rmsk_hit.start, rmsk_hit.end, rmsk_hit.strand
])
##########################################################
# ex8. Report overlap b/w exons and rmsk where the rmsk
# feature covers at least 50% of the exon.
#
# Equivalent to: intersectBed -a exons -b rmsk -s -f 0.50
# Uses: IntervalFile.all_hits()
##########################################################
exons = IntervalFile("bedtools/tests/data/exons.hg18.chr21.bed")
rmsk = IntervalFile("bedtools/tests/data/rmsk.hg18.chr21.bed")
for exon in exons:
# use "same_strand" to enforce, well, same strand.
for rmsk_hit in rmsk.all_hits(exon, same_strand=True, ovlp_pct=0.50):
print "\t".join(
str(f) for f in [
exon.chrom, exon.start, exon.end, exon.strand, rmsk_hit.
chrom, rmsk_hit.start, rmsk_hit.end, rmsk_hit.strand
])
["help", "interval", "folder", "ovlp_pct", "suffix"])
folder = "./"
percent = 0.5
for o, a in opts:
if o in ("-h", "--help"):
show_help()
exit(0)
elif o in ("-i", "--interval"):
interval_file = a
elif o in ("-f", "--folder"):
folder = a
elif o in ("-p", "--ovlp_pct"):
percent = float(a)
elif o in ("-s", "--suffix"):
suffix = a
bedlist = []
name = 'chr\tstart\tend'
for i in restlist:
i = i.strip()
bedlist.append(IntervalFile(folder + i + suffix))
name = name + '\t' + i.split("_")[-1]
print name
intervals = IntervalFile(interval_file)
for i in intervals:
line = i.chrom + '\t' + str(i.start) + '\t' + str(i.end)
for j in bedlist:
num = j.count_hits(i, ovlp_pct=percent)
line = line + '\t' + str(num)
print line
from bedtools import Interval, IntervalFile
# Input
inFileName = sys.argv[1]
inFileName2 = sys.argv[2]
outFileName = sys.argv[3]
min_value = 1000000
inFile = open(inFileName2, "r")
for line in inFile:
line = line.strip("\n")
ll = line.split("\t")
min_value = min(min_value, float(ll[3]) - 0.01)
inFile.close()
footprints = IntervalFile(inFileName2)
inFile = open(inFileName, "r")
outFile = open(outFileName, "w")
for line in inFile:
line = line.strip("\n")
ll = line.split("\t")
chr = ll[0]
pos1 = int(ll[1])
pos2 = int(ll[2])
query = Interval(chr, pos1, pos2)
score = min_value
for h in footprints.search(query):
score = max(score, float(h.name))
##########################################################################
# Add footprint column to features file
##########################################################################
newFeaturesFileName = outLoc + "newFeaturesFile.bed"
toRemove.append(newFeaturesFileName)
min_value = 1000000
inFile = open(bitInsideFootFileName, "r")
for line in inFile:
line = line.strip("\n")
ll = line.split("\t")
min_value = min(min_value, float(ll[3]) - 0.01)
inFile.close()
footprints = IntervalFile(bitInsideFootFileName)
inFile = open(featuresFileName, "r")
outFile = open(newFeaturesFileName, "w")
for line in inFile:
line = line.strip("\n")
ll = line.split("\t")
chr = ll[0]
pos1 = int(ll[1])
pos2 = int(ll[2])
query = Interval(chr, pos1, pos2)
score = min_value
for h in footprints.search(query):
score = max(score, float(h.name))
def setUp(self):
self.file = os.path.join(PATH, self.file)
self.bed = IntervalFile(self.file)
def setUp(self):
self.file = os.path.join(PATH, self.file)
self.bed = IntervalFile(self.file)