def add_sequences_from_sample(session, sample, sequences, props):
logger.info('Adding {} corrected sequences to sample {}'.format(
len(sequences), sample.id))
for sequence in periodic_commit(session, sequences):
alignment = sequence['alignment']
try:
try:
props.validate(alignment)
except AlignmentException:
continue
if sequence['r_type'] == 'NoResult':
add_sequences(session, [alignment],
sample,
error_action='raise')
session.query(NoResult).filter(
NoResult.pk == sequence['pk']).delete(
synchronize_session=False)
elif sequence['r_type'] == 'Sequence':
fields = {
'partial': alignment.partial,
'probable_indel_or_misalign': alignment.has_possible_indel,
'v_gene': format_ties(alignment.v_gene),
'j_gene': format_ties(alignment.j_gene),
'num_gaps': alignment.num_gaps,
'seq_start': alignment.seq_start,
'v_match': alignment.v_match,
'v_length': alignment.v_length,
'j_match': alignment.j_match,
'j_length': alignment.j_length,
'removed_prefix':
alignment.sequence.removed_prefix_sequence,
'removed_prefix_qual':
alignment.sequence.removed_prefix_quality,
'v_mutation_fraction': alignment.v_mutation_fraction,
'pre_cdr3_length': alignment.pre_cdr3_length,
'pre_cdr3_match': alignment.pre_cdr3_match,
'post_cdr3_length': alignment.post_cdr3_length,
'post_cdr3_match': alignment.post_cdr3_match,
'in_frame': alignment.in_frame,
'functional': alignment.functional,
'stop': alignment.stop,
'cdr3_nt': alignment.cdr3,
'cdr3_num_nts': len(alignment.cdr3),
'cdr3_aa': lookups.aas_from_nts(alignment.cdr3),
'sequence': str(alignment.sequence.sequence),
'quality': alignment.sequence.quality,
'locally_aligned': alignment.locally_aligned,
'_insertions': serialize_gaps(alignment.insertions),
'_deletions': serialize_gaps(alignment.deletions),
'germline': alignment.germline
}
# This line doesnt actually add anything to the DB, it's just
# to validate the fields
Sequence(**fields)
session.query(Sequence).filter(
Sequence.ai == sequence['pk']).update(
fields, synchronize_session=False)
except ValueError:
continue
def add_results(uniques, sample, session):
metrics = {'muts': [], 'lens': []}
for unique in itertools.chain(*uniques):
try:
add_sequences(session, [unique], sample)
metrics['lens'].append(unique.v_length)
metrics['muts'].append(unique.v_mutation_fraction)
except AlignmentException as e:
add_noresults_for_vdj(session, unique.sequence, sample, str(e))
if metrics['lens']:
sample.v_ties_len = sum(metrics['lens']) / len(metrics['lens'])
sample.v_ties_mutations = sum(metrics['muts']) / len(metrics['muts'])
session.commit()
def read_file(session, fmt, handle, sample, v_germlines, j_germlines, props):
reader = csv.DictReader(handle, delimiter='\t')
uniques = {}
for i, line in enumerate(reader):
if fmt == 'adaptive':
try:
line = extract_adaptive_sequence(i, line, v_germlines,
j_germlines)
except (AlignmentException, KeyError) as e:
seq = VDJSequence('seq_{}'.format(i), '')
add_noresults_for_vdj(session, seq, sample, str(e))
continue
seq = VDJSequence(line['SEQUENCE_ID'],
line['SEQUENCE_IMGT'].replace('.', '-'))
if 'DUPCOUNT' in line:
seq.copy_number = int(line['DUPCOUNT'])
try:
alignment = create_alignment(seq, line, v_germlines, j_germlines)
for other in uniques.setdefault(
len(alignment.sequence.sequence), []):
if dnautils.equal(other.sequence.sequence,
alignment.sequence.sequence):
other.sequence.copy_number += (
alignment.sequence.copy_number)
break
else:
uniques[len(alignment.sequence.sequence)].append(alignment)
except AlignmentException as e:
add_noresults_for_vdj(session, seq, sample, str(e))
uniques = [s for k in sorted(uniques.keys()) for s in uniques[k]]
lens = []
muts = []
for unique in uniques:
try:
props.validate(unique)
add_sequences(session, [unique], sample)
lens.append(unique.v_length)
muts.append(unique.v_mutation_fraction)
except AlignmentException as e:
add_noresults_for_vdj(session, seq, sample, str(e))
if len(lens) > 0:
sample.v_ties_len = sum(lens) / len(lens)
sample.v_ties_mutations = sum(muts) / len(muts)
session.commit()
def read_file(session, fmt, handle, sample, v_germlines, j_germlines, props):
reader = csv.DictReader(handle, delimiter='\t')
uniques = {}
for i, line in enumerate(reader):
if fmt == 'adaptive':
try:
line = extract_adaptive_sequence(i, line, v_germlines,
j_germlines)
except (AlignmentException, KeyError) as e:
seq = VDJSequence('seq_{}'.format(i), '')
add_noresults_for_vdj(session, seq, sample, str(e))
continue
seq = VDJSequence(line['SEQUENCE_ID'],
line['SEQUENCE_IMGT'].replace('.', '-'))
if 'DUPCOUNT' in line:
seq.copy_number = int(line['DUPCOUNT'])
try:
alignment = create_alignment(seq, line, v_germlines, j_germlines)
for other in uniques.setdefault(len(alignment.sequence.sequence),
[]):
if dnautils.equal(other.sequence.sequence,
alignment.sequence.sequence):
other.sequence.copy_number += (
alignment.sequence.copy_number)
break
else:
uniques[len(alignment.sequence.sequence)].append(alignment)
except AlignmentException as e:
add_noresults_for_vdj(session, seq, sample, str(e))
uniques = [s for k in sorted(uniques.keys()) for s in uniques[k]]
lens = []
muts = []
for unique in uniques:
try:
props.validate(unique)
add_sequences(session, [unique], sample)
lens.append(unique.v_length)
muts.append(unique.v_mutation_fraction)
except AlignmentException as e:
add_noresults_for_vdj(session, seq, sample, str(e))
if len(lens) > 0:
sample.v_ties_len = sum(lens) / float(len(lens))
sample.v_ties_mutations = sum(muts) / float(len(muts))
session.commit()
def aggregate_collapse(aggregate_queue, db_config, sample_id, props):
seqs_to_add = []
session = config.init_db(db_config, create=False)
sample = session.query(Sample).filter(Sample.id == sample_id).one()
for i, alignment in enumerate(aggregate_queue):
for seq in alignment:
seqs_to_add.append(seq)
if len(seqs_to_add) >= 1000:
add_sequences(session, seqs_to_add, sample,
strip_alleles=not props.genotyping)
seqs_to_add = []
session.commit()
if seqs_to_add:
add_sequences(session, seqs_to_add, sample,
strip_alleles=not props.genotyping)
logger.info('Finished aggregating sequences')
session.commit()
session.close()
def aggregate_collapse(aggregate_queue, db_config, sample_id, props):
seqs_to_add = []
session = config.init_db(db_config, create=False)
sample = session.query(Sample).filter(Sample.id == sample_id).one()
for i, alignment in enumerate(aggregate_queue):
for seq in alignment:
seqs_to_add.append(seq)
if len(seqs_to_add) >= 1000:
add_sequences(session, seqs_to_add, sample,
strip_alleles=not props.genotyping)
seqs_to_add = []
session.commit()
if seqs_to_add:
add_sequences(session, seqs_to_add, sample,
strip_alleles=not props.genotyping)
logger.info('Finished aggregating sequences')
session.commit()
session.close()
def add_sequences_from_sample(session, sample, sequences, props):
logger.info('Adding {} corrected sequences to sample {}'.format(
len(sequences), sample.id))
for sequence in periodic_commit(session, sequences):
alignment = sequence['alignment']
try:
try:
props.validate(alignment)
except AlignmentException:
continue
if sequence['r_type'] == 'NoResult':
add_sequences(session, [alignment], sample,
error_action='raise')
session.query(NoResult).filter(
NoResult.pk == sequence['pk']
).delete(synchronize_session=False)
elif sequence['r_type'] == 'Sequence':
fields = {
'partial': alignment.partial,
'probable_indel_or_misalign':
alignment.has_possible_indel,
'v_gene': format_ties(alignment.v_gene),
'j_gene': format_ties(alignment.j_gene),
'num_gaps': alignment.num_gaps,
'seq_start': alignment.seq_start,
'v_match': alignment.v_match,
'v_length': alignment.v_length,
'j_match': alignment.j_match,
'j_length': alignment.j_length,
'removed_prefix':
alignment.sequence.removed_prefix_sequence,
'removed_prefix_qual':
alignment.sequence.removed_prefix_quality,
'v_mutation_fraction': alignment.v_mutation_fraction,
'pre_cdr3_length': alignment.pre_cdr3_length,
'pre_cdr3_match': alignment.pre_cdr3_match,
'post_cdr3_length': alignment.post_cdr3_length,
'post_cdr3_match': alignment.post_cdr3_match,
'in_frame': alignment.in_frame,
'functional': alignment.functional,
'stop': alignment.stop,
'cdr3_nt': alignment.cdr3,
'cdr3_num_nts': len(alignment.cdr3),
'cdr3_aa': lookups.aas_from_nts(alignment.cdr3),
'sequence': str(alignment.sequence.sequence),
'quality': alignment.sequence.quality,
'locally_aligned': alignment.locally_aligned,
'_insertions': serialize_gaps(alignment.insertions),
'_deletions': serialize_gaps(alignment.deletions),
'germline': alignment.germline
}
# This line doesnt actually add anything to the DB, it's just
# to validate the fields
Sequence(**fields)
session.query(Sequence).filter(
Sequence.ai == sequence['pk']
).update(fields, synchronize_session=False)
except ValueError:
continue
