def run_fix_sequences(session, args):
v_germlines = VGermlines(args.v_germlines)
j_germlines = JGermlines(args.j_germlines, args.upstream_of_cdr3)
indexes = set()
props = IdentificationProps(**args.__dict__)
for sample in session.query(Sample):
sequences = process_sample(session, sample, indexes, args.temp,
v_germlines, j_germlines, args.nproc)
add_sequences_from_sample(session, sample, sequences, props)
remove_duplicates(session, sample)
logger.info('Updating copy numbers')
session.connection(mapper=Sequence).execute(
text('''
UPDATE
sequences
SET
copy_number = 1 + (
SELECT
COUNT(*)
FROM
duplicate_sequences
WHERE
duplicate_seq_ai = ai
)
'''))
def run_import(session, args):
v_germlines = VGermlines(args.v_germlines)
j_germlines = JGermlines(args.j_germlines, args.upstream_of_cdr3,
args.anchor_len)
meta_fn = args.metadata if args.metadata else os.path.join(
args.sample_dir, 'metadata.tsv')
if not os.path.isfile(meta_fn):
logger.error('Metadata file not found.')
return
with open(meta_fn, 'rU') as fh:
try:
metadata = parse_metadata(session, fh, args.warn_existing,
args.warn_missing, args.sample_dir)
except MetadataException as ex:
logger.error(ex.message)
return
props = IdentificationProps(**args.__dict__)
for sample_name in sorted(metadata.keys()):
sample = create_sample(session, metadata[sample_name])
if sample:
path = os.path.join(args.sample_dir,
metadata[sample_name]['file_name'])
with open(path) as fh:
read_file(session, args.format, fh, sample, v_germlines,
j_germlines, props)
def run_import(session, args, remaps=None):
v_germlines = VGermlines(args.v_germlines)
j_germlines = JGermlines(args.j_germlines, args.upstream_of_cdr3,
args.anchor_len, args.min_anchor_len)
study, new = funcs.get_or_create(session, Study, name=args.study_name)
if new:
logger.info('Created new study "{}"'.format(study.name))
session.commit()
sample, new = funcs.get_or_create(session,
Sample,
name=args.sample_name,
study=study)
if new:
sample.date = args.date
logger.info('Created new sample "{}"'.format(sample.name))
for key in ('subset', 'tissue', 'disease', 'lab', 'experimenter',
'ig_class', 'v_primer', 'j_primer'):
setattr(sample, key, vars(args).get(key, None))
subject, new = funcs.get_or_create(session,
Subject,
study=study,
identifier=args.subject)
sample.subject = subject
session.commit()
else:
logger.error('Sample "{}" already exists'.format(args.sample_name))
return
with open(args.input_file) as fh:
read_file(session, fh, sample, v_germlines, j_germlines, args, remaps)
def run_fix_sequences(session, args):
v_germlines = VGermlines(args.v_germlines)
j_germlines = JGermlines(args.j_germlines, args.upstream_of_cdr3)
indexes = set()
props = IdentificationProps(**args.__dict__)
samples = session.query(Sample)
if args.sample_ids:
samples = samples.filter(Sample.id.in_(args.sample_ids))
for sample in samples:
sequences = process_sample(session, sample, indexes, args.temp,
v_germlines, j_germlines, args.nproc)
add_sequences_from_sample(session, sample, sequences, props)
remove_duplicates(session, sample)
def run_identify(session, args):
mod_log.make_mod('identification',
session=session,
commit=True,
info=vars(args))
session.close()
# Load the germlines from files
v_germlines = VGermlines(args.v_germlines)
j_germlines = JGermlines(args.j_germlines, args.upstream_of_cdr3,
args.anchor_len, args.min_anchor_len)
tasks = concurrent.TaskQueue()
# If metadata is not specified, assume it is "metadata." in the
# directory
meta_fn = args.metadata if args.metadata else os.path.join(
args.sample_dir, 'metadata.tsv')
# Verify the metadata file exists
if not os.path.isfile(meta_fn):
logger.error('Metadata file not found.')
return
with open(meta_fn, 'rU') as fh:
try:
metadata = parse_metadata(session, fh, args.warn_existing,
args.sample_dir)
except MetadataException as ex:
logger.error(ex.message)
return
# Create the tasks for each file
for sample_name in sorted(metadata.keys()):
tasks.add_task({
'path':
os.path.join(args.sample_dir, metadata[sample_name]['file_name']),
'meta':
metadata[sample_name]
})
props = IdentificationProps(**args.__dict__)
lock = mp.Lock()
for i in range(0, min(args.nproc, tasks.num_tasks())):
worker_session = config.init_db(args.db_config)
tasks.add_worker(
IdentificationWorker(worker_session, v_germlines, j_germlines,
props, lock))
tasks.start()
def run_identify(session, args):
mod_log.make_mod('identification', session=session, commit=True,
info=vars(args))
# Load the germlines from files
v_germlines = VGermlines(args.v_germlines,
ties=args.ties and not args.genotyping)
j_germlines = JGermlines(args.j_germlines, args.upstream_of_cdr3,
args.anchor_len, args.min_anchor_len,
ties=args.ties and not args.genotyping)
# If metadata is not specified, assume it is "metadata." in the
# directory
meta_fn = args.metadata if args.metadata else os.path.join(
args.sample_dir, 'metadata.tsv')
# Verify the metadata file exists
if not os.path.isfile(meta_fn):
logger.error('Metadata file not found.')
sys.exit(-1)
with open(meta_fn, 'rU') as fh:
try:
metadata = parse_metadata(session, fh, args.warn_existing,
args.warn_missing, args.sample_dir)
except MetadataException as ex:
logger.error(ex)
sys.exit(-1)
session.close()
# Create the tasks for each file
props = IdentificationProps(**args.__dict__)
for sample_name in sorted(metadata.keys()):
process_sample(
args.db_config, v_germlines, j_germlines,
os.path.join(
args.sample_dir,
metadata[sample_name]['file_name']
),
metadata[sample_name],
props,
args.nproc
)