def predict_properties(pred_smiles: List[Optional[str]], checkpoint_dir: str, computed_prop: str) -> List[float]:
# Check that exactly one of checkpoint_dir and computed_prop is provided
assert (checkpoint_dir is None) != (computed_prop is None)
pred_smiles = [smiles for smiles in pred_smiles if smiles is not None]
# Create and modify predict args
parser = ArgumentParser()
add_predict_args(parser)
args = parser.parse_args([])
if checkpoint_dir is not None:
args.test_path = 'None'
args.checkpoint_dir = checkpoint_dir
update_checkpoint_args(args)
args.quiet = True
print('Make predictions')
with NamedTemporaryFile() as temp_file:
args.preds_path = temp_file.name
property_predictions = make_predictions(args, smiles=pred_smiles)
property_predictions = [property_prediction[0] for property_prediction in property_predictions]
else:
if computed_prop == 'penalized_logp':
scorer = penalized_logp
elif computed_prop == 'logp':
scorer = logp
elif computed_prop == 'qed':
scorer = qed
elif computed_prop == 'sascore':
scorer = sascore
elif computed_prop == 'drd2':
scorer = drd2
else:
raise ValueError(f'Computed property "{computed_prop}" not supported')
property_predictions = [scorer(s) for s in pred_smiles]
return property_predictions
def predict():
"""Renders the predict page and makes predictions if the method is POST."""
if request.method == 'GET':
return render_predict()
# Get arguments
ckpt_id = request.form['checkpointName']
if request.form['textSmiles'] != '':
smiles = request.form['textSmiles'].split()
elif request.form['drawSmiles'] != '':
smiles = [request.form['drawSmiles']]
else:
# Upload data file with SMILES
data = request.files['data']
data_name = secure_filename(data.filename)
data_path = os.path.join(app.config['TEMP_FOLDER'], data_name)
data.save(data_path)
# Check if header is smiles
possible_smiles = get_header(data_path)[0]
smiles = [possible_smiles
] if Chem.MolFromSmiles(possible_smiles) is not None else []
# Get remaining smiles
smiles.extend(get_smiles(data_path))
models = db.get_models(ckpt_id)
model_paths = [
os.path.join(app.config['CHECKPOINT_FOLDER'], f'{model["id"]}.pt')
for model in models
]
task_names = load_task_names(model_paths[0])
num_tasks = len(task_names)
gpu = request.form.get('gpu')
train_args = load_args(model_paths[0])
# Build arguments
arguments = [
'--test_path', 'None', '--preds_path',
os.path.join(app.config['TEMP_FOLDER'],
app.config['PREDICTIONS_FILENAME']), '--checkpoint_paths',
*model_paths
]
if gpu is not None:
if gpu == 'None':
arguments.append('--no_cuda')
else:
arguments += ['--gpu', gpu]
# Handle additional features
if train_args.features_path is not None:
# TODO: make it possible to specify the features generator if trained using features_path
arguments += [
'--features_generator', 'rdkit_2d_normalized',
'--no_features_scaling'
]
elif train_args.features_generator is not None:
arguments += ['--features_generator', *train_args.features_generator]
if not train_args.features_scaling:
arguments.append('--no_features_scaling')
# Parse arguments
args = PredictArgs().parse_args(arguments)
# Run predictions
preds = make_predictions(args=args, smiles=smiles)
if all(p is None for p in preds):
return render_predict(errors=['All SMILES are invalid'])
# Replace invalid smiles with message
invalid_smiles_warning = 'Invalid SMILES String'
preds = [
pred if pred is not None else [invalid_smiles_warning] * num_tasks
for pred in preds
]
return render_predict(
predicted=True,
smiles=smiles,
num_smiles=min(10, len(smiles)),
show_more=max(0,
len(smiles) - 10),
task_names=task_names,
num_tasks=len(task_names),
preds=preds,
warnings=["List contains invalid SMILES strings"]
if None in preds else None,
errors=["No SMILES strings given"] if len(preds) == 0 else None)
def predict():
if request.method == 'GET':
return render_template('predict.html',
checkpoints=get_checkpoints(),
cuda=app.config['CUDA'],
gpus=app.config['GPUS'])
# Get arguments
checkpoint_name = request.form['checkpointName']
if 'data' in request.files:
# Upload data file with SMILES
show_file_upload = True
data = request.files['data']
data_name = secure_filename(data.filename)
data_path = os.path.join(app.config['TEMP_FOLDER'], data_name)
data.save(data_path)
smiles = []
with open(data_path, 'r') as f:
header = f.readline()
try: # if there's no header, add the smiles in the first line
possible_smiles = header.strip().split(',')[0]
mol = Chem.MolFromSmiles(possible_smiles)
smiles.append(possible_smiles)
except:
pass
for line in f:
smiles.append(line.strip().split(',')[0])
else:
show_file_upload = False
smiles = request.form['smiles']
smiles = smiles.split()
checkpoint_path = os.path.join(app.config['CHECKPOINT_FOLDER'],
checkpoint_name)
task_names = load_task_names(checkpoint_path)
gpu = request.form.get('gpu', None)
# Create and modify args
parser = ArgumentParser()
add_predict_args(parser)
args = parser.parse_args()
preds_path = os.path.join(app.config['TEMP_FOLDER'],
app.config['PREDICTIONS_FILENAME'])
args.preds_path = preds_path
args.checkpoint_paths = [checkpoint_path]
if gpu is not None:
if gpu == 'None':
args.no_cuda = True
else:
args.gpu = int(gpu)
invalid_smiles_warning = "Invalid SMILES String"
if len(smiles) > 0:
# Run prediction
preds = make_predictions(args,
smiles=smiles,
invalid_smiles_warning=invalid_smiles_warning)
else:
preds = []
return render_template(
'predict.html',
checkpoints=get_checkpoints(),
cuda=app.config['CUDA'],
gpus=app.config['GPUS'],
predicted=True,
smiles=smiles,
num_smiles=min(10, len(smiles)),
show_more=max(0,
len(smiles) - 10),
task_names=task_names,
num_tasks=len(task_names),
preds=preds,
show_file_upload=show_file_upload,
warning="List contains invalid SMILES strings"
if invalid_smiles_warning in preds else None,
error="No SMILES strings given" if len(preds) == 0 else None)
def predict():
"""Renders the predict page and makes predictions if the method is POST."""
if request.method == 'GET':
return render_predict()
# Get arguments
ckpt_id = request.form['checkpointName']
if request.form['textSmiles'] != '':
smiles = request.form['textSmiles'].split()
elif request.form['drawSmiles'] != '':
smiles = [request.form['drawSmiles']]
else:
print(" GOT HERE")
# Upload data file with SMILES
data = request.files['data']
data_name = secure_filename(data.filename)
data_path = os.path.join(app.config['TEMP_FOLDER'], data_name)
data.save(data_path)
# Check if header is smiles
possible_smiles = get_header(data_path)[0]
smiles = [possible_smiles] if Chem.MolFromSmiles(possible_smiles) is not None else []
# Get remaining smiles
smiles.extend(get_smiles(data_path))
models = db.get_models(ckpt_id)
model_paths = [os.path.join(app.config['CHECKPOINT_FOLDER'], f'{model["id"]}.pt') for model in models]
task_names = load_task_names(model_paths[0])
num_tasks = len(task_names)
gpu = request.form.get('gpu')
# Create and modify args
args = load_args(model_paths[0])
if args.features_path != None:
args.features_generator = ["rdkit_2d_normalized"]
args.features_path = None
preds_path = os.path.join(app.config['TEMP_FOLDER'], app.config['PREDICTIONS_FILENAME'])
args.test_path = 'None' # TODO: Remove this hack to avoid assert crashing in modify_predict_args
args.preds_path = preds_path
args.checkpoint_paths = model_paths
if gpu is not None:
if gpu == 'None':
args.no_cuda = True
else:
args.gpu = int(gpu)
modify_predict_args(args)
# Run predictions
preds = make_predictions(args, smiles=smiles)
if all(p is None for p in preds):
return render_predict(errors=['All SMILES are invalid'])
# Replace invalid smiles with message
invalid_smiles_warning = "Invalid SMILES String"
preds = [pred if pred is not None else [invalid_smiles_warning] * num_tasks for pred in preds]
return render_predict(predicted=True,
smiles=smiles,
num_smiles=min(10, len(smiles)),
show_more=max(0, len(smiles)-10),
task_names=task_names,
num_tasks=len(task_names),
preds=preds,
warnings=["List contains invalid SMILES strings"] if None in preds else None,
errors=["No SMILES strings given"] if len(preds) == 0 else None)
def predict():
if request.method == 'GET':
return render_predict()
# Get arguments
checkpoint_name = request.form['checkpointName']
if 'data' in request.files:
# Upload data file with SMILES
data = request.files['data']
data_name = secure_filename(data.filename)
data_path = os.path.join(app.config['TEMP_FOLDER'], data_name)
data.save(data_path)
# Check if header is smiles
possible_smiles = get_header(data_path)[0]
smiles = [possible_smiles
] if Chem.MolFromSmiles(possible_smiles) is not None else []
# Get remaining smiles
smiles.extend(get_smiles(data_path))
elif request.form['textSmiles'] != '':
smiles = request.form['textSmiles'].split()
else:
smiles = [request.form['drawSmiles']]
checkpoint_path = os.path.join(app.config['CHECKPOINT_FOLDER'],
checkpoint_name)
task_names = load_task_names(checkpoint_path)
num_tasks = len(task_names)
gpu = request.form.get('gpu')
# Create and modify args
parser = ArgumentParser()
add_predict_args(parser)
args = parser.parse_args()
preds_path = os.path.join(app.config['TEMP_FOLDER'],
app.config['PREDICTIONS_FILENAME'])
args.test_path = 'None' # TODO: Remove this hack to avoid assert crashing in modify_predict_args
args.preds_path = preds_path
args.checkpoint_path = checkpoint_path
args.write_smiles = True
if gpu is not None:
if gpu == 'None':
args.no_cuda = True
else:
args.gpu = int(gpu)
modify_predict_args(args)
# Run predictions
preds = make_predictions(args, smiles=smiles)
if all(p is None for p in preds):
return render_predict(errors=['All SMILES are invalid'])
# Replace invalid smiles with message
invalid_smiles_warning = "Invalid SMILES String"
preds = [
pred if pred is not None else [invalid_smiles_warning] * num_tasks
for pred in preds
]
return render_predict(
predicted=True,
smiles=smiles,
num_smiles=min(10, len(smiles)),
show_more=max(0,
len(smiles) - 10),
task_names=task_names,
num_tasks=len(task_names),
preds=preds,
warnings=["List contains invalid SMILES strings"]
if None in preds else None,
errors=["No SMILES strings given"] if len(preds) == 0 else None)