def kmer_homology(self, k=10, span=100):
seq1 = ''.join([
a.capitalize() for a in hg.interval(
self.v1.chrom, max(1, self.v1.pos - span),
min(self.v1.pos + span, hg.chrLen[hg.chrNum(self.v1.chrom)]),
self.v1.strand).sequence()
])
seq2 = ''.join([
a.capitalize() for a in hg.interval(
self.v2.chrom, max(1, self.v2.pos - span),
min(self.v2.pos +
span, hg.chrLen[hg.chrNum(self.v2.chrom)]), -1 *
self.v2.strand).sequence()
])
kset1 = Set([seq1[i:i + 10] for i in range(len(seq1) - k + 1)])
kset2 = Set([seq2[i:i + 10] for i in range(len(seq2) - k + 1)])
return len(kset1.intersection(kset2))
def kmer_homology(self, k=10, span=100):
"""Number of shared k-mers within "span" distance on either side of vertex positions"""
seq1 = ''.join([
a.capitalize() for a in hg.interval(
self.v1.chrom, max(1, self.v1.pos - span),
min(self.v1.pos + span, hg.chrLen[hg.chrNum(self.v1.chrom)]),
self.v1.strand).sequence()
])
seq2 = ''.join([
a.capitalize() for a in hg.interval(
self.v2.chrom, max(1, self.v2.pos - span),
min(self.v2.pos +
span, hg.chrLen[hg.chrNum(self.v2.chrom)]), -1 *
self.v2.strand).sequence()
])
kset1 = Set([seq1[i:i + 10] for i in range(len(seq1) - k + 1)])
kset2 = Set([seq2[i:i + 10] for i in range(len(seq2) - k + 1)])
return len(kset1.intersection(kset2))
old_stdout = sys.stdout
sys.stdout = mystdout = StringIO()
amplist = bamFileb2b.interval_hops(rdList, explore=False)
alist = hg.interval_list(
[hg.interval(e[0].v1.chrom, e[0].v1.pos, e[0].v1.pos) for e in de] +
[hg.interval(e[0].v2.chrom, e[0].v2.pos, e[0].v2.pos)
for e in de] + rdList)
alist.sort()
rdList = hg.interval_list([
i[0] for i in alist.merge_clusters(extend=5000000) if len(
hg.interval_list([i[0]]).intersection(amplist) +
hg.interval_list([i[0]]).intersection(rdList)) > 0
])
rdList = hg.interval_list([
hg.interval(i.chrom, max(0, i.start - 10000),
min(i.end + 10000, hg.chrLen[hg.chrNum(i.chrom)]))
for i in rdList
])
iout = open(outName + '.integration_search.out', 'w')
iout.write(mystdout.getvalue())
iout.close()
sys.stdout = old_stdout
all_ilist = copy.copy(rdList)
irdhops = []
irddict = {}
irdSets = Set([Set([ird]) for ird in rdList])
irdgroupdict = {ird: Set([ird]) for ird in rdList}
if args.extendmode == 'EXPLORE' or args.extendmode == 'VIRAL':
for ird in rdList:
logging.info("#TIME " + '%.3f\t' % (clock() - TSTART) +
