def register_user_db_tasks(handler, config, databases):
'''Run conditional recipricol best hits LAST (CRBL) against the
user-supplied databases.
'''
if not 'user_databases' in config:
return
shmlast_tasks = set()
input_fn = handler.files['transcriptome']
for db_path in config['user_databases']:
db_path = path.abspath(db_path)
db_basename = path.basename(db_path)
results_fn = '{0}.x.{1}.crbl.csv'.format(input_fn, db_basename)
gff3_fn = '{0}.x.{1}.crbl.gff3'.format(input_fn, db_basename)
crbl = CRBL(input_fn,
db_path,
results_fn,
n_threads=config['n_threads'],
cutoff=config['evalue'])
for task in crbl.tasks():
if tuple(sorted(task.targets)) in shmlast_tasks:
continue
shmlast_tasks.add(tuple(sorted(task.targets)))
task.name = 'user-database:{0}-shmlast-{1}'.format(
db_basename, task.name)
handler.register_task(task.name, add_profile_actions(task))
handler.register_task(
'gff3:{0}'.format(results_fn),
get_shmlast_gff3_task(results_fn, gff3_fn, db_basename),
files={'{0}-crbl-gff3'.format(db_basename): gff3_fn})
handler.files['{0}-crbl'.format(db_basename)] = results_fn
def register_lastal_tasks(handler,
config,
databases,
include_uniref=False,
include_nr=False):
'''Register tasks for `lastal` searches. By default, this will just
align the transcriptome against OrthoDB; if requested, it will align against
uniref90 as well, which takes considerably longer.
Args:
handler (handler.TaskHandler): The task handler to register on.
config (dict): Config dictionary, which contains the command
line arguments and the entries from the config file.
databases (dict): The dictionary of files from a database
TaskHandler.
include_uniref (bool): If True, add tasks for searching uniref90.
'''
input_fn = handler.files['transcriptome']
lastal_cfg = config['last']['lastal']
dbs = OrderedDict()
dbs['OrthoDB'] = databases['OrthoDB']
dbs['sprot'] = databases['sprot']
if include_uniref is True:
dbs['uniref90'] = databases['uniref90']
if include_nr is True:
dbs['nr'] = databases['nr']
for name, db in dbs.items():
output_fn = '{0}.x.{1}.maf'.format(input_fn, name)
handler.register_task('lastal:{0}'.format(name),
add_profile_actions(LastalTask().task(
input_fn,
db,
output_fn,
translate=True,
cutoff=config['evalue'],
n_threads=config['n_threads'],
frameshift=lastal_cfg['frameshift'],
pbs=config['sshloginfile'],
params=lastal_cfg['params'])),
files={name: output_fn})
best_fn = '{0}.x.{1}.best.csv'.format(input_fn, name)
gff3_fn = '{0}.x.{1}.best.gff3'.format(input_fn, name)
handler.register_task('lastal:best-hits:{0}'.format(name),
get_maf_best_hits_task(output_fn, best_fn),
files={'{0}-best-hits'.format(name): best_fn})
handler.register_task('gff3:{0}'.format(name),
get_maf_gff3_task(best_fn, gff3_fn, name),
files={'{0}-gff3'.format(name): gff3_fn})