def nominate_chimeras(index_dir, isize_dist_file, input_file, output_file,
trim_bp, max_read_length, homology_mismatches):
# read insert size distribution
isize_dist = InsertSizeDistribution.from_file(open(isize_dist_file))
# build a lookup table to get genomic intervals from transcripts
logging.debug("Reading gene information")
gene_file = os.path.join(index_dir, config.GENE_FEATURE_FILE)
tx_name_gene_map = build_tx_name_gene_map(gene_file, rname_prefix=None)
#genome_tx_trees = build_genome_tx_trees(gene_file)
# open the reference sequence fasta file
ref_fasta_file = os.path.join(index_dir, config.ALIGN_INDEX + ".fa")
ref_fa = pysam.Fastafile(ref_fasta_file)
# keep track of mapping from breakpoint sequence to breakpoint id
# this requires storing all breakpoint sequences in memory which is
# potentially expensive. TODO: investigate whether this should be
# moved to a separate sort-update-sort procedure
breakpoint_seq_name_map = {}
breakpoint_num = 1
# group discordant read pairs by gene
logging.debug("Parsing discordant reads")
chimera_num = 1
outfh = open(output_file, "w")
for tx_name_5p, tx_name_3p, frags in parse_discordant_bedpe_by_transcript_pair(open(input_file)):
# get gene information
tx5p = tx_name_gene_map[tx_name_5p]
tx3p = tx_name_gene_map[tx_name_3p]
# bin fragments into putative breakpoints
breakpoint_dict = collections.defaultdict(lambda: [])
for dr5p,dr3p in frags:
# given the insert size find the highest probability
# exon junction breakpoint between the two transcripts
isize_prob, breakpoints = \
choose_best_breakpoints(dr5p, dr3p, tx5p, tx3p,
trim_bp, isize_dist)
for breakpoint in breakpoints:
breakpoint_dict[breakpoint].append((dr5p, dr3p))
# iterate through breakpoints and build chimera candidates
for breakpoint,frags in breakpoint_dict.iteritems():
exon_num_5p, tx_end_5p, exon_num_3p, tx_start_3p = breakpoint
breakpoint_seq_5p, breakpoint_seq_3p, homology_left, homology_right = \
extract_breakpoint_sequence(config.GENE_REF_PREFIX + tx5p.tx_name, tx_end_5p,
config.GENE_REF_PREFIX + tx3p.tx_name, tx_start_3p,
ref_fa, max_read_length,
homology_mismatches)
tx3p_length = sum((end - start) for start,end in tx3p.exons)
# get unique breakpoint id based on sequence
breakpoint_seq = breakpoint_seq_5p + breakpoint_seq_3p
if breakpoint_seq in breakpoint_seq_name_map:
breakpoint_name = breakpoint_seq_name_map[breakpoint_seq]
else:
breakpoint_name = "B%07d" % (breakpoint_num)
breakpoint_seq_name_map[breakpoint_seq] = breakpoint_name
breakpoint_num += 1
# write gene, breakpoint, and raw reads to a file and follow the
# BEDPE format
gene_name_5p = '_'.join(tx5p.gene_name.split())
gene_name_3p = '_'.join(tx3p.gene_name.split())
fields = [tx5p.tx_name, 0, tx_end_5p, # chrom1, start1, end1
tx3p.tx_name, tx_start_3p, tx3p_length, # chrom2, start2, end2
"C%07d" % (chimera_num), # name
1.0, # pvalue
tx5p.strand, tx3p.strand, # strand1, strand2
gene_name_5p, gene_name_3p, # gene names
# exon interval information
'%d-%d' % (0, exon_num_5p),
'%d-%d' % (exon_num_3p, len(tx3p.exons)),
# breakpoint information
breakpoint_name,
breakpoint_seq_5p, breakpoint_seq_3p,
homology_left, homology_right,
# fragments
frags_to_encomp_string(frags),
# spanning reads
None]
print >>outfh, '\t'.join(map(str, fields))
chimera_num += 1
outfh.close()
ref_fa.close()
return config.JOB_SUCCESS
def write_output(input_file, bam_file, output_file, index_dir):
gene_file = os.path.join(index_dir, config.GENE_FEATURE_FILE)
# build a lookup table to get genome coordinates from transcript
# coordinates
transcript_genome_map = build_transcript_genome_map(open(gene_file))
tx_name_gene_map = build_tx_name_gene_map(gene_file)
genome_tx_trees = build_genome_tx_trees(gene_file)
# 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, gene_file):
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_name_gene_map[c.tx_name_5p],
tx_name_gene_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
