def _merge_circular_aligment(target_1, start_pos_1, cigar_str_1, target_2,
start_pos_2, cigar_str_2, is_reversed, qname):
if is_reversed:
# reverse back both
cigar_str_1 = ''.join(reversed(cigar_str_1))
target_1 = butil.reverse_complement(target_1)
cigar_str_2 = ''.join(reversed(cigar_str_2))
target_2 = butil.reverse_complement(target_2)
if start_pos_1 == 0:
start = start_pos_2
cigar = butil.rtrim_cigar(cigar_str_2) + butil.ltrim_cigar(cigar_str_1)
target = target_2 + target_1
elif start_pos_2 == 0:
start = start_pos_1
cigar = butil.rtrim_cigar(cigar_str_1) + butil.ltrim_cigar(cigar_str_2)
target = target_1 + target_2
else:
# not circular, duplicate
logging.error("Duplicate read with name %s", qname)
return None
if is_reversed:
cigar = ''.join(reversed(cigar))
target = butil.reverse_complement(target)
return [target, start, cigar]
def extend_cigars_in_sam(sam_in, ref_path, fastx_path, sam_out=None):
tmp_dir = None
tmp_sam_out = sam_out
inplace = sam_out is None
if inplace:
# inplace change using tmp file
tmp_dir = tempfile.mkdtemp()
tmp_sam_out = os.path.join(tmp_dir, 'tmp.sam')
ref = butil.read_fasta(ref_path)
reads = {}
with pysam.FastxFile(fastx_path, 'r') as fh:
for r in fh:
reads[r.name] = r
with pysam.AlignmentFile(sam_in, "r") as in_sam, \
pysam.AlignmentFile(tmp_sam_out, "w", template=in_sam) as out_sam:
for x in tqdm(in_sam.fetch(), unit='reads'):
if x.query_name not in reads:
logging.warning("read %s in sam not found in .fastx",
x.query_name)
continue
if x.is_unmapped:
logging.warning("read %s is unmapped, copy to out sam as is",
x.query_name)
out_sam.write(x)
continue
read_seq = reads[x.query_name].sequence
ref_seq = ref[x.reference_start:x.reference_end]
cigar_pairs = x.cigartuples
if x.is_reverse:
read_seq = butil.reverse_complement(read_seq)
x.cigarstring = extend_cigar(read_seq, ref_seq, cigar_pairs)
out_sam.write(x)
if inplace:
# clear tmp files
shutil.move(tmp_sam_out, sam_in)
shutil.rmtree(tmp_dir)
def get_target_sequences(sam_path):
result_dict = {}
cnt = defaultdict(int)
with pysam.AlignmentFile(sam_path, "r") as samfile:
for x in tqdm(samfile.fetch(), desc='Building ref'):
name = x.query_name
cnt['total'] += 1
if x.is_unmapped:
cnt['unmapped'] += 1
#logging.warning("%s unmapped" % name)
continue
try:
# hack to bypass segfault
full_cigar = butil.decompress_cigar_pairs(x.cigartuples)
r_len = butil.get_read_len_from_cigar(full_cigar)
ref_len = butil.get_ref_len_from_cigar(full_cigar)
if r_len != x.query_length or ref_len != x.reference_length:
logging.error(
"%s cigar operations do not match alignment info in md",
name)
cnt['invalid_md_cigar'] += 1
continue
target = x.get_reference_sequence()
except (ValueError, AssertionError) as e:
cnt['missign_ref'] += 1
logging.error(
"%s Mapped but reference len equals 0, md tag: %s", name,
x.has_tag('MD'))
continue
ref_name = x.reference_name
length = x.reference_length
start_pos = x.reference_start
cigar_pairs = x.cigartuples
if x.is_reverse:
target = butil.reverse_complement(target)
cigar_pairs = list(reversed(cigar_pairs))
cigar_str = butil.decompress_cigar_pairs(cigar_pairs, mode='ints')
if name in result_dict:
prev_target, _, prev_start_pos, _, prev_cigar_str = result_dict[
name]
merged = _merge_circular_aligment(prev_target, prev_start_pos,
prev_cigar_str, target,
start_pos, cigar_str,
x.is_reverse, x.query_name)
if not merged:
continue
target, start_pos, cigar_str = merged
length = len(target)
result_dict[name] = [
target, ref_name, start_pos, length, cigar_str
]
logging.warning("Results: %s", str(cnt.items()))
return result_dict