def get_contigs_info(contigs_file):
contigs_info = {}
contigs_fasta = fp.read_fasta_dict(contigs_file)
for ctg_id, ctg_seq in contigs_fasta.iteritems():
contig_type = ctg_id.split("_")[0]
contigs_info[ctg_id] = ContigInfo(ctg_id, len(ctg_seq), contig_type)
return contigs_info
def get_bubbles(alignment_path, contigs_info, contigs_path,
err_mode, num_proc, min_alignment):
"""
The main function: takes an alignment and returns bubbles
"""
aln_reader = SynchronizedSamReader(alignment_path,
fp.read_fasta_dict(contigs_path),
min_alignment)
manager = multiprocessing.Manager()
results_queue = manager.Queue()
error_queue = manager.Queue()
#making sure the main process catches SIGINT
orig_sigint = signal.signal(signal.SIGINT, signal.SIG_IGN)
threads = []
for _ in xrange(num_proc):
threads.append(multiprocessing.Process(target=_thread_worker,
args=(aln_reader, contigs_info,
err_mode, results_queue,
error_queue)))
signal.signal(signal.SIGINT, orig_sigint)
for t in threads:
t.start()
try:
for t in threads:
t.join()
except KeyboardInterrupt:
for t in threads:
t.terminate()
if not error_queue.empty():
raise error_queue.get()
bubbles = []
total_long_bubbles = 0
total_long_branches = 0
total_empty = 0
total_aln_errors = []
while not results_queue.empty():
(ctg_bubbles, num_long_bubbles,
num_empty, num_long_branch, aln_errors) = results_queue.get()
total_long_bubbles += num_long_bubbles
total_long_branches += num_long_branch
total_empty += num_empty
total_aln_errors.extend(aln_errors)
bubbles.extend(ctg_bubbles)
mean_aln_error = float(sum(total_aln_errors)) / (len(total_aln_errors) + 1)
logger.debug("Alignment error rate: {0}".format(mean_aln_error))
logger.debug("Generated {0} bubbles".format(len(bubbles)))
logger.debug("Split {0} long bubbles".format(total_long_bubbles))
logger.debug("Skipped {0} empty bubbles".format(total_empty))
logger.debug("Skipped {0} bubbles with long branches".format(total_long_branches))
return bubbles
def run(self):
logger.info("Polishing genome ({0}/{1})".format(
self.stage_id, self.args.num_iters))
contigs_fasta = fp.read_fasta_dict(self.in_reference)
reference_file = os.path.join(
self.work_dir, "blasr_ref_{0}.fasta".format(self.stage_id))
aln.make_blasr_reference(contigs_fasta, reference_file)
aln.make_alignment(reference_file, self.args.reads, self.args.threads,
self.out_alignment)
os.remove(reference_file)
Job.run_description["stage_name"] = self.name
Job.run_description["stage_id"] = self.stage_id
def patch_genome(alignment, reference_file, out_patched):
aln_by_ctg = defaultdict(list)
for aln in alignment:
aln_by_ctg[aln.trg_id].append(aln)
ref_fasta = fp.read_fasta_dict(reference_file)
fixed_fasta = {}
for ctg_id, ctg_aln in aln_by_ctg.iteritems():
patches = _get_patching_alignmemnts(ctg_aln)
fixed_sequence = _apply_patches(patches, ref_fasta[ctg_id])
fixed_fasta[ctg_id] = fixed_sequence
fp.write_fasta_dict(fixed_fasta, out_patched)
def get_consensus(alignment_path, contigs_path, contigs_info, min_aln_length,
platform, num_proc):
"""
Main function
"""
aln_reader = SynchronizedSamReader(alignment_path,
fp.read_fasta_dict(contigs_path),
min_aln_length)
manager = multiprocessing.Manager()
results_queue = manager.Queue()
error_queue = manager.Queue()
#making sure the main process catches SIGINT
orig_sigint = signal.signal(signal.SIGINT, signal.SIG_IGN)
threads = []
for _ in xrange(num_proc):
threads.append(
multiprocessing.Process(target=_thread_worker,
args=(aln_reader, contigs_info, platform,
results_queue, error_queue)))
signal.signal(signal.SIGINT, orig_sigint)
for t in threads:
t.start()
try:
for t in threads:
t.join()
except KeyboardInterrupt:
for t in threads:
t.terminate()
if not error_queue.empty():
raise error_queue.get()
out_fasta = {}
total_aln_errors = []
while not results_queue.empty():
ctg_id, ctg_seq, aln_errors = results_queue.get()
total_aln_errors.extend(aln_errors)
if len(ctg_seq) > 0:
out_fasta[ctg_id] = ctg_seq
mean_aln_error = float(sum(total_aln_errors)) / (len(total_aln_errors) + 1)
logger.debug("Alignment error rate: {0}".format(mean_aln_error))
return out_fasta
def concatenate_contigs(contigs_file):
"""
Concatenates contig parts output by assembly module
"""
genome_framents = fp.read_fasta_dict(contigs_file)
contig_types = {}
by_contig = defaultdict(list)
for h, s in genome_framents.iteritems():
tokens = h.split("_")
cont_type = tokens[0]
contig_id = tokens[0] + "_" + tokens[1]
part_id = int(tokens[3])
contig_types[contig_id] = cont_type
by_contig[contig_id].append((part_id, s))
contigs_fasta = {}
for contig_id, contig_seqs in by_contig.iteritems():
seqs_sorted = sorted(contig_seqs, key=lambda p: p[0])
contig_concat = "".join(map(lambda p: p[1], seqs_sorted))
contig_len = len(contig_concat)
contigs_fasta[contig_id] = contig_concat
return contigs_fasta