def find_nearest_transcripts(chrom, start, end, strand, locus_trees):
# first check for overlap
nearest_features = []
hits = locus_trees[chrom].find(start, end)
for hit in hits:
for t in hit.value:
if cmp_strand(t.strand, strand):
c = Category.ENCOMPASSING_SAME_STRAND
else:
c = Category.ENCOMPASSING_OPP_STRAND
nearest_features.append((t, c, 0))
# look left and right
left_hits = locus_trees[chrom].before(start,
num_intervals=1,
max_dist=MAX_LOCUS_DIST)
right_hits = locus_trees[chrom].after(end,
num_intervals=1,
max_dist=MAX_LOCUS_DIST)
# look for nearest hit
for hits in (left_hits, right_hits):
nearest_locus_hit = None
nearest_dist = MAX_LOCUS_DIST
for hit in hits:
dist = min(abs(start - hit.end), abs(hit.start - end))
if dist < nearest_dist:
nearest_dist = dist
nearest_locus_hit = hit
if nearest_locus_hit is not None:
for t in nearest_locus_hit.value:
dist = min(abs(start - t.end), abs(t.start - end))
nearest_features.append((t, Category.INTERGENIC, dist))
return nearest_features
def find_nearest_transcripts(chrom, start, end, strand, locus_trees):
# first check for overlap
nearest_features = []
hits = locus_trees[chrom].find(start, end)
for hit in hits:
for t in hit.value:
if cmp_strand(t.strand, strand):
c = Category.ENCOMPASSING_SAME_STRAND
else:
c = Category.ENCOMPASSING_OPP_STRAND
nearest_features.append((t, c, 0))
# look left and right
left_hits = locus_trees[chrom].before(start, num_intervals=1, max_dist=MAX_LOCUS_DIST)
right_hits = locus_trees[chrom].after(end, num_intervals=1, max_dist=MAX_LOCUS_DIST)
# look for nearest hit
for hits in (left_hits, right_hits):
nearest_locus_hit = None
nearest_dist = MAX_LOCUS_DIST
for hit in hits:
dist = min(abs(start - hit.end), abs(hit.start - end))
if dist < nearest_dist:
nearest_dist = dist
nearest_locus_hit = hit
if nearest_locus_hit is not None:
for t in nearest_locus_hit.value:
dist = min(abs(start - t.end), abs(t.start - end))
nearest_features.append((t, Category.INTERGENIC, dist))
return nearest_features
def compare_locus(transcripts):
# store reference introns
# (strand,start,end) -> ids (set)
ref_intron_dict = collections.defaultdict(lambda: [])
ref_node_dict = collections.defaultdict(lambda: [])
ref_splicing_patterns = collections.defaultdict(lambda: [])
ref_dict = {}
# find the intron domains of the transcripts
boundaries = find_exon_boundaries(transcripts)
test_transcripts = []
for t in transcripts:
# separate ref and nonref transcripts
is_ref = bool(int(t.attrs[GTFAttr.REF]))
if is_ref:
# add to dict
ref_id = t.attrs[GTFAttr.TRANSCRIPT_ID]
ref_dict[ref_id] = t
# split exons that cross boundaries and get the
# nodes in the transcript path
for n in split_exons(t, boundaries):
ref_node_dict[n].append(t)
# add to introns
splicing_pattern = []
for start, end in t.iterintrons():
intron = (t.strand, start, end)
ref_intron_dict[intron].append(t)
splicing_pattern.append(intron)
# add to splicing patterns
if len(splicing_pattern) > 0:
ref_splicing_patterns[tuple(splicing_pattern)].append(t)
else:
test_transcripts.append(t)
# index introns for fast intersection
intron_tree = IntervalTree()
for intron, refs in ref_intron_dict.iteritems():
strand, start, end = intron
intron_tree.insert_interval(
Interval(start, end, strand=strand, value=refs))
# categorize transcripts
for t in test_transcripts:
# get transcript nodes and introns
nodes = list(split_exons(t, boundaries))
introns = []
for start, end in t.iterintrons():
introns.append((t.strand, start, end))
splicing_pattern = tuple(introns)
# keep list of all matching ref transcripts
matches = collections.defaultdict(lambda: Match())
# dict of reference transcripts -> category -> list of nodes
for n in nodes:
if n in ref_node_dict:
# look for reference transcripts that share this node
for ref in ref_node_dict[n]:
if cmp_strand(t.strand, ref.strand):
c = Category.SAME_STRAND
else:
c = Category.OPP_STRAND
ref_id = ref.attrs[GTFAttr.TRANSCRIPT_ID]
m = matches[ref_id]
m.nodes[c].append(n)
# look for reference introns that overlap this node
for hit in intron_tree.find(*n):
if cmp_strand(t.strand, hit.strand):
c = Category.INTRONIC_SAME_STRAND
else:
c = Category.INTRONIC_OPP_STRAND
for ref in hit.value:
ref_id = ref.attrs[GTFAttr.TRANSCRIPT_ID]
m = matches[ref_id]
m.nodes[c].append(n)
# dict of introns -> list of reference transcripts
for intron in introns:
if intron in ref_intron_dict:
for ref in ref_intron_dict[intron]:
ref_id = ref.attrs[GTFAttr.TRANSCRIPT_ID]
m = matches[ref_id]
m.introns.append(intron)
# check splicing pattern matches
if len(splicing_pattern) > 0:
if splicing_pattern in ref_splicing_patterns:
for ref in ref_splicing_patterns[splicing_pattern]:
ref_id = ref.attrs[GTFAttr.TRANSCRIPT_ID]
m = matches[ref_id]
m.splicing = True
# go through the matches for this transcript and determine
# the transcript category
match_stats = []
for ref_id, m in matches.iteritems():
ref = ref_dict[ref_id]
# calculate coverage
same_strand_bp = sum(
(n[1] - n[0]) for n in m.nodes[Category.SAME_STRAND])
opp_strand_bp = sum(
(n[1] - n[0]) for n in m.nodes[Category.OPP_STRAND])
# count shared introns
num_shared_introns = len(m.introns)
# decide category for this test/ref transcript pair
if m.splicing or (num_shared_introns > 0) or (same_strand_bp > 0):
c = Category.SAME_STRAND
elif (opp_strand_bp > 0):
c = Category.OPP_STRAND
else:
# count nodes of different types
num_same_strand = len(m.nodes[Category.SAME_STRAND])
num_opp_strand = len(m.nodes[Category.OPP_STRAND])
num_intronic_same_strand = len(
m.nodes[Category.INTRONIC_SAME_STRAND])
num_intronic_opp_strand = len(
m.nodes[Category.INTRONIC_OPP_STRAND])
assert num_same_strand == 0
assert num_opp_strand == 0
num_intronic = (num_intronic_same_strand +
num_intronic_opp_strand)
assert num_intronic > 0
if (num_intronic == len(nodes)):
# completely intronic
if num_intronic_same_strand > 0:
c = Category.INTRONIC_SAME_STRAND
else:
c = Category.INTRONIC_OPP_STRAND
else:
# interleaving means some nodes intronic and other intergenic
if num_intronic_same_strand > 0:
c = Category.INTERLEAVING_SAME_STRAND
else:
c = Category.INTERLEAVING_OPP_STRAND
# create a match object
ms = MatchStats.from_transcript(t, ref)
ms.shared_same_strand_bp = same_strand_bp
ms.shared_opp_strand_bp = opp_strand_bp
ms.shared_introns = num_shared_introns
ms.shared_splicing = m.splicing
ms.category = Category.to_str(c)
ms.distance = 0
match_stats.append(ms)
yield (t, match_stats)
def compare_locus(transcripts):
# store reference introns
# (strand,start,end) -> ids (set)
ref_intron_dict = collections.defaultdict(lambda: [])
ref_node_dict = collections.defaultdict(lambda: [])
ref_splicing_patterns = collections.defaultdict(lambda: [])
ref_dict = {}
# find the intron domains of the transcripts
boundaries = find_exon_boundaries(transcripts)
test_transcripts = []
for t in transcripts:
# separate ref and nonref transcripts
is_ref = bool(int(t.attrs[GTFAttr.REF]))
if is_ref:
# add to dict
ref_id = t.attrs[GTFAttr.TRANSCRIPT_ID]
ref_dict[ref_id] = t
# split exons that cross boundaries and get the
# nodes in the transcript path
for n in split_exons(t, boundaries):
ref_node_dict[n].append(t)
# add to introns
splicing_pattern = []
for start,end in t.iterintrons():
intron = (t.strand, start, end)
ref_intron_dict[intron].append(t)
splicing_pattern.append(intron)
# add to splicing patterns
if len(splicing_pattern) > 0:
ref_splicing_patterns[tuple(splicing_pattern)].append(t)
else:
test_transcripts.append(t)
# index introns for fast intersection
intron_tree = IntervalTree()
for intron, refs in ref_intron_dict.iteritems():
strand, start, end = intron
intron_tree.insert_interval(Interval(start,end,strand=strand,value=refs))
# categorize transcripts
for t in test_transcripts:
# get transcript nodes and introns
nodes = list(split_exons(t, boundaries))
introns = []
for start,end in t.iterintrons():
introns.append((t.strand,start,end))
splicing_pattern = tuple(introns)
# keep list of all matching ref transcripts
matches = collections.defaultdict(lambda: Match())
# dict of reference transcripts -> category -> list of nodes
for n in nodes:
if n in ref_node_dict:
# look for reference transcripts that share this node
for ref in ref_node_dict[n]:
if cmp_strand(t.strand, ref.strand):
c = Category.SAME_STRAND
else:
c = Category.OPP_STRAND
ref_id = ref.attrs[GTFAttr.TRANSCRIPT_ID]
m = matches[ref_id]
m.nodes[c].append(n)
# look for reference introns that overlap this node
for hit in intron_tree.find(*n):
if cmp_strand(t.strand, hit.strand):
c = Category.INTRONIC_SAME_STRAND
else:
c = Category.INTRONIC_OPP_STRAND
for ref in hit.value:
ref_id = ref.attrs[GTFAttr.TRANSCRIPT_ID]
m = matches[ref_id]
m.nodes[c].append(n)
# dict of introns -> list of reference transcripts
for intron in introns:
if intron in ref_intron_dict:
for ref in ref_intron_dict[intron]:
ref_id = ref.attrs[GTFAttr.TRANSCRIPT_ID]
m = matches[ref_id]
m.introns.append(intron)
# check splicing pattern matches
if len(splicing_pattern) > 0:
if splicing_pattern in ref_splicing_patterns:
for ref in ref_splicing_patterns[splicing_pattern]:
ref_id = ref.attrs[GTFAttr.TRANSCRIPT_ID]
m = matches[ref_id]
m.splicing = True
# go through the matches for this transcript and determine
# the transcript category
match_stats = []
for ref_id, m in matches.iteritems():
ref = ref_dict[ref_id]
# calculate coverage
same_strand_bp = sum((n[1] - n[0]) for n in m.nodes[Category.SAME_STRAND])
opp_strand_bp = sum((n[1] - n[0]) for n in m.nodes[Category.OPP_STRAND])
# count shared introns
num_shared_introns = len(m.introns)
# decide category for this test/ref transcript pair
if m.splicing or (num_shared_introns > 0) or (same_strand_bp > 0):
c = Category.SAME_STRAND
elif (opp_strand_bp > 0):
c = Category.OPP_STRAND
else:
# count nodes of different types
num_same_strand = len(m.nodes[Category.SAME_STRAND])
num_opp_strand = len(m.nodes[Category.OPP_STRAND])
num_intronic_same_strand = len(m.nodes[Category.INTRONIC_SAME_STRAND])
num_intronic_opp_strand = len(m.nodes[Category.INTRONIC_OPP_STRAND])
assert num_same_strand == 0
assert num_opp_strand == 0
num_intronic = (num_intronic_same_strand +
num_intronic_opp_strand)
assert num_intronic > 0
if (num_intronic == len(nodes)):
# completely intronic
if num_intronic_same_strand > 0:
c = Category.INTRONIC_SAME_STRAND
else:
c = Category.INTRONIC_OPP_STRAND
else:
# interleaving means some nodes intronic and other intergenic
if num_intronic_same_strand > 0:
c = Category.INTERLEAVING_SAME_STRAND
else:
c = Category.INTERLEAVING_OPP_STRAND
# create a match object
ms = MatchStats.from_transcript(t, ref)
ms.shared_same_strand_bp = same_strand_bp
ms.shared_opp_strand_bp = opp_strand_bp
ms.shared_introns = num_shared_introns
ms.shared_splicing = m.splicing
ms.category = Category.to_str(c)
ms.distance = 0
match_stats.append(ms)
yield (t, match_stats)
