def make_chimera(cluster_pair, cluster_shelve, transcript_dict,
genome_tx_trees, annotation_source):
# lookup 5' and 3' clusters
cluster5p = cluster_shelve[str(cluster_pair.id5p)]
cluster3p = cluster_shelve[str(cluster_pair.id3p)]
# get 5' and 3' transcripts
transcripts5p = lookup_transcripts(cluster5p, transcript_dict,
genome_tx_trees)
transcripts3p = lookup_transcripts(cluster3p, transcript_dict,
genome_tx_trees)
# lookup chimera type and distance
chimera_type, distance = get_chimera_type(cluster5p, cluster3p,
transcripts5p, transcripts3p,
transcript_dict, genome_tx_trees)
# format transcript information
tx_names_5p, gene_names_5p, biotypes_5p = get_transcript_info(
transcripts5p, annotation_source)
tx_names_3p, gene_names_3p, biotypes_3p = get_transcript_info(
transcripts3p, annotation_source)
# make chimera object
c = Chimera()
c.rname5p = cluster5p.rname
c.start5p = cluster5p.start
c.end5p = cluster5p.end
c.rname3p = cluster3p.rname
c.start3p = cluster3p.start
c.end3p = cluster3p.end
c.chimera_id = "CHIMERA%d" % (cluster_pair.pair_id)
frags = set(cluster_pair.qnames)
frags.update(cluster_pair.spanning_qnames)
c.num_frags = len(frags)
c.strand5p = cluster5p.strand
c.strand3p = cluster3p.strand
c.chimera_type = chimera_type
c.distance = distance
c.num_discordant_frags = len(cluster_pair.qnames)
c.num_spanning_frags = len(cluster_pair.spanning_qnames)
c.num_discordant_frags_5p = len(cluster5p.qnames)
c.num_discordant_frags_3p = len(cluster3p.qnames)
c.num_concordant_frags_5p = cluster5p.concordant_frags
c.num_concordant_frags_3p = cluster3p.concordant_frags
c.biotypes_5p = sorted(biotypes_5p)
c.biotypes_3p = sorted(biotypes_3p)
c.genes_5p = sorted(gene_names_5p)
c.genes_3p = sorted(gene_names_3p)
c.transcripts_5p = sorted(tx_names_5p)
c.transcripts_3p = sorted(tx_names_3p)
return c
def make_chimera(cluster_pair,
cluster_shelve,
transcript_dict,
genome_tx_trees,
annotation_source):
# lookup 5' and 3' clusters
cluster5p = cluster_shelve[str(cluster_pair.id5p)]
cluster3p = cluster_shelve[str(cluster_pair.id3p)]
# get 5' and 3' transcripts
transcripts5p = lookup_transcripts(cluster5p, transcript_dict, genome_tx_trees)
transcripts3p = lookup_transcripts(cluster3p, transcript_dict, genome_tx_trees)
# lookup chimera type and distance
chimera_type, distance = get_chimera_type(cluster5p, cluster3p,
transcripts5p, transcripts3p,
transcript_dict, genome_tx_trees)
# format transcript information
tx_names_5p, gene_names_5p, biotypes_5p = get_transcript_info(transcripts5p, annotation_source)
tx_names_3p, gene_names_3p, biotypes_3p = get_transcript_info(transcripts3p, annotation_source)
# make chimera object
c = Chimera()
c.rname5p = cluster5p.rname
c.start5p = cluster5p.start
c.end5p = cluster5p.end
c.rname3p = cluster3p.rname
c.start3p = cluster3p.start
c.end3p = cluster3p.end
c.chimera_id = "CHIMERA%d" % (cluster_pair.pair_id)
frags = set(cluster_pair.qnames)
frags.update(cluster_pair.spanning_qnames)
c.num_frags = len(frags)
c.strand5p = cluster5p.strand
c.strand3p = cluster3p.strand
c.chimera_type = chimera_type
c.distance = distance
c.num_discordant_frags = len(cluster_pair.qnames)
c.num_spanning_frags = len(cluster_pair.spanning_qnames)
c.num_discordant_frags_5p = len(cluster5p.qnames)
c.num_discordant_frags_3p = len(cluster3p.qnames)
c.num_concordant_frags_5p = cluster5p.concordant_frags
c.num_concordant_frags_3p = cluster3p.concordant_frags
c.biotypes_5p = sorted(biotypes_5p)
c.biotypes_3p = sorted(biotypes_3p)
c.genes_5p = sorted(gene_names_5p)
c.genes_3p = sorted(gene_names_3p)
c.transcripts_5p = sorted(tx_names_5p)
c.transcripts_3p = sorted(tx_names_3p)
return c
def write_output(input_file, bam_file, output_file, index_dir):
# read transcripts
logging.debug("Reading transcripts")
transcript_file = os.path.join(index_dir, config.TRANSCRIPT_FEATURE_FILE)
transcripts = list(TranscriptFeature.parse(open(transcript_file)))
# build a lookup table to get genome coordinates from transcript
# coordinates
transcript_genome_map = build_transcript_genome_map(transcripts)
tx_id_map = build_transcript_map(transcripts)
genome_tx_trees = build_genome_transcript_trees(transcripts)
# open BAM file for checking wild-type isoform
bamfh = pysam.Samfile(bam_file, "rb")
# group chimera isoforms together
lines = []
chimera_clusters = 0
for key,chimeras in get_chimera_groups(input_file, tx_id_map):
txs5p = set()
txs3p = set()
genes5p = set()
genes3p = set()
names = set()
for c in chimeras:
txs5p.add("%s:%d-%d" % (c.tx_name_5p, c.tx_start_5p, c.tx_end_5p-1))
txs3p.add("%s:%d-%d" % (c.tx_name_3p, c.tx_start_3p, c.tx_end_3p-1))
genes5p.add(c.gene_name_5p)
genes3p.add(c.gene_name_3p)
names.add(c.name)
c = get_best_coverage_chimera(chimeras)
# get chimera type and distance between genes
chimera_type, distance = get_chimera_type(tx_id_map[c.tx_name_5p],
tx_id_map[c.tx_name_3p],
genome_tx_trees)
# get genomic positions of chimera
chrom5p,strand5p,start5p = transcript_to_genome_pos(c.tx_name_5p, c.tx_start_5p, transcript_genome_map)
chrom5p,strand5p,end5p = transcript_to_genome_pos(c.tx_name_5p, c.tx_end_5p-1, transcript_genome_map)
if strand5p == 1:
start5p,end5p = end5p,start5p
chrom3p,strand3p,start3p = transcript_to_genome_pos(c.tx_name_3p, c.tx_start_3p, transcript_genome_map)
chrom3p,strand3p,end3p = transcript_to_genome_pos(c.tx_name_3p, c.tx_end_3p-1, transcript_genome_map)
if strand3p == 1:
start3p,end3p = end3p,start3p
# get breakpoint spanning sequences
spanning_seqs = set()
spanning_fasta_lines = []
for dr in c.get_spanning_reads():
if dr.seq in spanning_seqs:
continue
spanning_seqs.add(dr.seq)
spanning_fasta_lines.extend([">%s/%d;pos=%d;strand=%s" %
(dr.qname, dr.readnum+1, dr.pos,
"-" if dr.is_reverse else "+"),
dr.seq])
# get isoform fraction
num_wt_frags_5p, num_wt_frags_3p = get_wildtype_frags(c, bamfh)
num_chimeric_frags = c.get_num_frags()
frac5p = float(num_chimeric_frags) / (num_chimeric_frags + num_wt_frags_5p)
frac3p = float(num_chimeric_frags) / (num_chimeric_frags + num_wt_frags_3p)
# setup fields of BEDPE file
fields = [chrom5p, start5p, end5p,
chrom3p, start3p, end3p,
"CLUSTER%d" % (chimera_clusters),
c.get_num_frags(),
"+" if (strand5p == 0) else "-",
"+" if (strand3p == 0) else "-",
','.join(txs5p),
','.join(txs3p),
','.join(genes5p),
','.join(genes3p),
chimera_type, distance,
c.get_num_frags(),
c.get_num_spanning_frags(),
c.get_num_unique_positions(),
frac5p, frac3p,
','.join(spanning_fasta_lines),
','.join(names)]
lines.append(fields)
chimera_clusters += 1
bamfh.close()
logging.debug("Clustered chimeras: %d" % (chimera_clusters))
# sort
lines = sorted(lines, key=operator.itemgetter(18, 17, 16), reverse=True)
f = open(output_file, "w")
print >>f, '\t'.join(['#chrom5p', 'start5p', 'end5p',
'chrom3p', 'start3p', 'end3p',
'chimera_cluster_id', 'score',
'strand5p', 'strand3p',
'transcript_ids_5p', 'transcript_ids_3p',
'genes5p', 'genes3p',
'type', 'distance',
'total_frags',
'spanning_frags',
'unique_alignment_positions',
'isoform_fraction_5p',
'isoform_fraction_3p',
'breakpoint_spanning_reads',
'chimera_ids'])
for fields in lines:
print >>f, '\t'.join(map(str, fields))
f.close()
return config.JOB_SUCCESS
