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)
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():
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])
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): """ 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])
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])
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
])