def get_highest_coverage_isoforms(input_file, gene_file):
# place overlapping chimeras into clusters
logging.debug("Building isoform cluster lookup table")
tx_cluster_map = build_tx_cluster_map(open(gene_file))
# build a lookup table to get genome coordinates from transcript
# coordinates
tx_genome_map = build_gene_to_genome_map(open(gene_file))
cluster_chimera_dict = collections.defaultdict(lambda: [])
for c in Chimera.parse(open(input_file)):
key = (c.name,
c.get_num_unique_spanning_positions(),
c.get_weighted_cov(),
c.get_num_frags())
# get cluster of overlapping genes
cluster5p = tx_cluster_map[c.partner5p.tx_name]
cluster3p = tx_cluster_map[c.partner3p.tx_name]
# get genomic positions of breakpoints
coord5p = gene_to_genome_pos(c.partner5p.tx_name, c.partner5p.end-1, tx_genome_map)
coord3p = gene_to_genome_pos(c.partner3p.tx_name, c.partner3p.start, tx_genome_map)
# add to dictionary
cluster_chimera_dict[(cluster5p,cluster3p,coord5p,coord3p)].append(key)
# choose highest coverage chimeras within each pair of clusters
logging.debug("Finding highest coverage isoforms")
kept_chimeras = set()
for stats_list in cluster_chimera_dict.itervalues():
stats_dict = collections.defaultdict(lambda: set())
for stats_info in stats_list:
# index chimera names
stats_dict[stats_info[1:]].add(stats_info[0])
# find highest scoring key
sorted_keys = sorted(stats_dict.keys(), reverse=True)
kept_chimeras.update(stats_dict[sorted_keys[0]])
return kept_chimeras
def get_highest_coverage_isoforms(input_file, gene_file):
# place overlapping chimeras into clusters
logging.debug("Building isoform cluster lookup table")
tx_cluster_map = build_tx_cluster_map(open(gene_file))
# build a lookup table to get genome coordinates from transcript
# coordinates
tx_genome_map = build_gene_to_genome_map(open(gene_file))
cluster_chimera_dict = collections.defaultdict(lambda: [])
for c in Chimera.parse(open(input_file)):
key = (c.name, c.get_num_unique_spanning_positions(),
c.get_weighted_cov(), c.get_num_frags())
# get cluster of overlapping genes
cluster5p = tx_cluster_map[c.partner5p.tx_name]
cluster3p = tx_cluster_map[c.partner3p.tx_name]
# get genomic positions of breakpoints
coord5p = gene_to_genome_pos(c.partner5p.tx_name, c.partner5p.end - 1,
tx_genome_map)
coord3p = gene_to_genome_pos(c.partner3p.tx_name, c.partner3p.start,
tx_genome_map)
# add to dictionary
cluster_chimera_dict[(cluster5p, cluster3p, coord5p,
coord3p)].append(key)
# choose highest coverage chimeras within each pair of clusters
logging.debug("Finding highest coverage isoforms")
kept_chimeras = set()
for stats_list in cluster_chimera_dict.itervalues():
stats_dict = collections.defaultdict(lambda: set())
for stats_info in stats_list:
# index chimera names
stats_dict[stats_info[1:]].add(stats_info[0])
# find highest scoring key
sorted_keys = sorted(stats_dict.keys(), reverse=True)
kept_chimeras.update(stats_dict[sorted_keys[0]])
return kept_chimeras
def annotate_multihits(bamfh, reads, tid_genome_map):
hits = set()
any_unmapped = False
for r in reads:
if r.is_unmapped:
any_unmapped = True
continue
if r.rname not in tid_genome_map:
tid = r.rname
pos = r.pos
else:
# use the position that is most 5' relative to genome
left_tid, left_strand, left_pos = gene_to_genome_pos(r.rname, r.pos, tid_genome_map)
right_tid, right_strand, right_pos = gene_to_genome_pos(r.rname, r.aend-1, tid_genome_map)
tid = left_tid
pos = imin2(left_pos, right_pos)
hits.add((tid, pos))
#print r.qname, bamfh.getrname(r.rname), r.pos, bamfh.getrname(tid), pos
for i,r in enumerate(reads):
# annotate reads with 'HI', and 'IH' tags
r.tags = r.tags + [("HI",i), ("IH",len(reads)), ("NH", len(hits))]
return any_unmapped
