def read_input(path):
vdjs = []
parser = SeqIO.parse(path, 'fasta' if path.endswith('.fasta') else 'fastq')
# Collapse identical sequences
logger.info('Parsing input')
for record in parser:
try:
vdjs.append(
VDJSequence(
seq_id=record.description,
sequence=str(record.seq),
quality=funcs.ord_to_quality(
record.letter_annotations.get('phred_quality'))))
except ValueError:
continue
logger.info('There are {} sequences'.format(len(vdjs)))
return vdjs
def read_input(path):
vdjs = []
parser = SeqIO.parse(path, 'fasta' if path.endswith('.fasta') else 'fastq')
# Collapse identical sequences
logger.info('Parsing input')
for record in parser:
try:
vdjs.append(VDJSequence(
seq_id=record.description,
sequence=str(record.seq),
quality=funcs.ord_to_quality(
record.letter_annotations.get('phred_quality')
)
))
except ValueError:
continue
logger.info('There are {} sequences'.format(len(vdjs)))
return vdjs
def do_task(self, args):
meta = args['meta']
self.info('Starting sample {}'.format(meta['sample_name']))
study, sample = self._setup_sample(meta)
vdjs = {}
parser = SeqIO.parse(
args['path'],
'fasta' if args['path'].endswith('.fasta') else 'fastq')
# Collapse identical sequences
self.info('\tCollapsing identical sequences')
for record in parser:
try:
seq = str(record.seq)
if seq not in vdjs:
vdjs[seq] = VDJSequence(
ids=[],
sequence=seq,
quality=funcs.ord_to_quality(
record.letter_annotations.get('phred_quality')))
vdjs[seq].ids.append(record.description)
except ValueError:
continue
alignments = {}
aligner = AnchorAligner(self._v_germlines, self._j_germlines)
self.info('\tAligning {} unique sequences'.format(len(vdjs)))
# Attempt to align all unique sequences
for sequence in funcs.periodic_commit(self._session,
sorted(vdjs.keys())):
vdj = vdjs[sequence]
del vdjs[sequence]
try:
# The alignment was successful. If the aligned sequence
# already exists, append the seq_ids. Otherwise add it as a
# new unique sequence.
alignment = aligner.get_alignment(vdj)
seq_key = alignment.sequence.sequence
if seq_key in alignments:
alignments[seq_key].sequence.ids.extend(
alignment.sequence.ids)
else:
alignments[seq_key] = alignment
except AlignmentException as e:
add_as_noresult(self._session, vdj, sample, str(e))
except Exception:
self.error(
'\tUnexpected error processing sequence {}\n\t{}'.format(
vdj.ids[0], traceback.format_exc()))
if len(alignments) > 0:
avg_len = (sum([v.v_length for v in alignments.values()]) /
float(len(alignments)))
avg_mut = (
sum([v.v_mutation_fraction
for v in alignments.values()]) / float(len(alignments)))
sample.v_ties_mutations = avg_mut
sample.v_ties_len = avg_len
self.info('\tRe-aligning {} sequences to V-ties, Mutations={}, '
'Length={}'.format(len(alignments), round(avg_mut, 2),
round(avg_len, 2)))
add_uniques(self._session, sample, alignments.values(),
self._props, aligner, avg_len, avg_mut)
self._session.commit()
self.info('Completed sample {}'.format(sample.name))
def do_task(self, args):
meta = args['meta']
self.info('Starting sample {}'.format(meta.get('sample_name')))
study, sample = self._setup_sample(meta)
vdjs = {}
parser = SeqIO.parse(
os.path.join(args['path'], args['fn']),
'fasta' if args['fn'].endswith('.fasta') else 'fastq')
# Collapse identical sequences
self.info('\tCollapsing identical sequences')
for record in parser:
seq = str(record.seq)
if seq not in vdjs:
vdjs[seq] = VDJSequence(
ids=[],
seq=seq,
v_germlines=self._v_germlines,
j_germlines=self._j_germlines,
quality=funcs.ord_to_quality(
record.letter_annotations.get('phred_quality')))
vdjs[seq].ids.append(record.description)
self.info('\tAligning {} unique sequences'.format(len(vdjs)))
# Attempt to align all unique sequences
for sequence in funcs.periodic_commit(self._session,
sorted(vdjs.keys())):
vdj = vdjs[sequence]
del vdjs[sequence]
try:
# The alignment was successful. If the aligned sequence
# already exists, append the seq_ids. Otherwise add it as a
# new unique sequence.
vdj.analyze()
if vdj.sequence in vdjs:
vdjs[vdj.sequence].ids += vdj.ids
else:
vdjs[vdj.sequence] = vdj
except AlignmentException as e:
add_as_noresult(self._session, vdj, sample, str(e))
except:
self.error(
'\tUnexpected error processing sequence {}\n\t{}'.format(
vdj.ids[0], traceback.format_exc()))
if len(vdjs) > 0:
avg_len = sum(map(lambda vdj: vdj.v_length,
vdjs.values())) / float(len(vdjs))
avg_mut = sum(map(lambda vdj: vdj.mutation_fraction,
vdjs.values())) / float(len(vdjs))
sample.v_ties_mutations = avg_mut
sample.v_ties_len = avg_len
self.info('\tRe-aligning {} sequences to V-ties, Mutations={}, '
'Length={}'.format(len(vdjs), round(avg_mut, 2),
round(avg_len, 2)))
add_uniques(self._session, sample, vdjs.values(), avg_len, avg_mut,
self._min_similarity, self._max_vties, self._trim_to,
self._max_padding)
self._session.commit()
self.info('Completed sample {}'.format(sample.name))