def exon_matching(exon_tree,
ref_exon,
match_extend_tolerate_left,
match_extend_tolerate_right,
intervals_adjacent=True):
"""
exon_tree --- an IntervalTree made from .baseC/.altC using exon detection; probably only short read data
ref_exon --- an Interval representing an exon; probably from PacBio
match_extend_tolerate --- maximum difference between the matched start/end
find a continuous exon path (consisting of 1 or more nodes for which the intervals must be adjacent)
in exon_tree that matches to ref_exon
"""
matches = exon_tree.find(ref_exon.start, ref_exon.end)
if len(matches) == 0: # likely due to very low coverage on transcript
return None
# check that all matches are adjacent (no splicing! this just one integral exon)
if (not intervals_adjacent) or c_branch.intervals_all_adjacent(matches):
# check if the ends differ a little, if so, extend to min/max
for i in xrange(len(matches)):
d_start = abs(matches[i].start - ref_exon.start)
#print "matching {0} to {1}".format(matches[i].start, ref_exon.start)
#pdb.set_trace()
if d_start <= match_extend_tolerate_left: # now find the furthest end that satisfies the results
for j in xrange(len(matches) - 1, i - 1, -1):
if abs(matches[j].end -
ref_exon.end) <= match_extend_tolerate_right:
return matches[i:(j + 1)]
return None
else: # ack! could not find evidence for this :<
return None
def exon_matching(exon_tree, ref_exon, match_extend_tolerate_left, match_extend_tolerate_right, intervals_adjacent=True):
"""
exon_tree --- an IntervalTree made from .baseC/.altC using exon detection; probably only short read data
ref_exon --- an Interval representing an exon; probably from PacBio
match_extend_tolerate --- maximum difference between the matched start/end
find a continuous exon path (consisting of 1 or more nodes for which the intervals must be adjacent)
in exon_tree that matches to ref_exon
"""
matches = exon_tree.find(ref_exon.start, ref_exon.end)
if len(matches) == 0: # likely due to very low coverage on transcript
return None
# check that all matches are adjacent (no splicing! this just one integral exon)
if (not intervals_adjacent) or c_branch.intervals_all_adjacent(matches):
# check if the ends differ a little, if so, extend to min/max
for i in xrange(len(matches)):
d_start = abs(matches[i].start - ref_exon.start)
#print "matching {0} to {1}".format(matches[i].start, ref_exon.start)
#pdb.set_trace()
if d_start <= match_extend_tolerate_left: # now find the furthest end that satisfies the results
for j in xrange(len(matches)-1, i-1, -1):
if abs(matches[j].end - ref_exon.end) <= match_extend_tolerate_right:
return matches[i:(j+1)]
return None
else: # ack! could not find evidence for this :<
return None