def load_Forward_Transformer(mincount=100, worker_no=0):
'''
Load the forward prediction neural network
'''
if worker_no == 0:
MyLogger.print_and_log('Loading forward prediction model...',
model_loader_loc)
transformer = ForwardTransformer()
transformer.load(worker_no=worker_no)
if worker_no == 0:
MyLogger.print_and_log('Forward transformer loaded.', model_loader_loc)
return transformer
def configure_worker(options={}, **kwargs):
if 'queues' not in options:
# print('Queues not in options')
return
if CORRESPONDING_QUEUE not in options['queues'].split(','):
# print('Queues not in options as key')
return
print('### STARTING UP A FORWARD ENUMERATION WORKER ###')
global templates
global forwardTransformer
# # Database
# from database import db_client
# db = db_client[settings.SYNTH_TRANSFORMS['database']]
# SYNTH_DB = db[settings.SYNTH_TRANSFORMS['collection']]
# # Load templates
# mincount_synth = settings.SYNTH_TRANSFORMS['mincount']
forwardTransformer = ForwardTransformer(celery=True)
forwardTransformer.load()
print('### FORWARD ENUMERATION WORKER STARTED UP ###')
for product in stiched_result.products:
all_results.append(product.as_dict())
candidate_edits.append((product.get_smiles(), product.get_edits()))
self.stop_expansion()
return (all_results, candidate_edits)
def softmax(x):
"""Compute softmax values for each sets of scores in x."""
e_x = np.exp(x - np.max(x))
return e_x / e_x.sum()
if __name__ == '__main__':
MyLogger.initialize_logFile()
celery = False
if not celery:
forw_trans = ForwardTransformer(mincount=25, celery=False)
forw_trans.load()
scorer = TemplateNeuralNetScorer(forward_transformer=forw_trans)
else:
scorer = TemplateNeuralNetScorer(celery=celery)
scorer.load(gc.PREDICTOR['trained_model_path'])
res = scorer.evaluate('CN1C2CCC1CC(O)C2.O=C(O)C(CO)c1ccccc1', [
[80.0, '', '', '', -1, 50.0]], batch_size=100, nproc=8)
for re in res[0]:
print((re['outcome'].smiles + " {}".format(re['prob'])))
print('done')