def find_similar_mols_from_file(test_path: str,
train_path: str,
distance_measure: str,
checkpoint_path: str = None,
num_neighbors: int = -1,
batch_size: int = 50) -> List[OrderedDict]:
"""
For each test molecule, finds the N most similar training molecules according to some distance measure.
Loads molecules and model from file.
:param test_path: Path to a CSV file containing test SMILES.
:param train_path: Path to a CSV file containing train SMILES.
:param checkpoint_path: Path to a .pt model checkpoint file (only needed for distance_measure == 'embedding').
:param distance_measure: The distance measure to use to determine nearest neighbors.
:param num_neighbors: The number of nearest training molecules to find for each test molecule.
:param batch_size: Batch size.
:return: A list of OrderedDicts containing the test smiles, the num_neighbors nearest training smiles,
and other relevant distance info.
"""
print('Loading data')
test_smiles, train_smiles = get_smiles(
test_path, flatten=True), get_smiles(train_path, flatten=True)
if checkpoint_path is not None:
print('Loading model')
model = load_checkpoint(checkpoint_path)
else:
model = None
return find_similar_mols(test_smiles=test_smiles,
train_smiles=train_smiles,
distance_measure=distance_measure,
model=model,
num_neighbors=num_neighbors,
batch_size=batch_size)
def run_split_data(args: Args):
# Load raw data
with open(args.data_path) as f:
reader = csv.reader(f)
header = next(reader)
lines = list(reader)
# Load SMILES
smiles = get_smiles(path=args.data_path, smiles_columns=args.smiles_column)
# Make sure lines and smiles line up
assert len(lines) == len(smiles)
assert all(s in line for smile, line in zip(smiles, lines) for s in smile)
# Create data
data = []
for smile, line in tqdm(zip(smiles, lines), total=len(smiles)):
datapoint = MoleculeDatapoint(smiles=smile)
datapoint.line = line
data.append(datapoint)
data = MoleculeDataset(data)
train, val, test = split_data(data=data,
split_type=args.split_type,
sizes=args.split_sizes,
seed=args.seed)
makedirs(args.save_dir)
for name, dataset in [('train', train), ('val', val), ('test', test)]:
with open(os.path.join(args.save_dir, f'{name}.csv'), 'w') as f:
writer = csv.writer(f)
writer.writerow(header)
for datapoint in dataset:
writer.writerow(datapoint.line)
def test_flatten(self):
"""Testing with flattened output"""
smiles = get_smiles(
path=self.smiles_path,
flatten=True,
)
self.assertEqual(smiles, ['C', 'CC', 'CC', 'CN', 'O', 'CO'])
def overlap(args: Args):
smiles_1 = get_smiles(path=args.data_path_1,
smiles_columns=args.smiles_column_1,
flatten=True)
smiles_2 = get_smiles(path=args.data_path_2,
smiles_columns=args.smiles_column_2,
flatten=True)
smiles_1, smiles_2 = set(smiles_1), set(smiles_2)
size_1, size_2 = len(smiles_1), len(smiles_2)
intersection = smiles_1.intersection(smiles_2)
size_intersect = len(intersection)
print(f'Size of dataset 1: {size_1}')
print(f'Size of dataset 2: {size_2}')
print(f'Size of intersection: {size_intersect}')
print(
f'Size of intersection as frac of dataset 1: {size_intersect / size_1}'
)
print(
f'Size of intersection as frac of dataset 2: {size_intersect / size_2}'
)
if args.save_intersection_path is not None:
with open(args.data_path_1,
'r') as rf, open(args.save_intersection_path, 'w') as wf:
reader, writer = csv.reader(rf), csv.writer(wf)
header = next(reader)
writer.writerow(header)
for line in reader:
if line[0] in intersection:
writer.writerow(line)
if args.save_difference_path is not None:
with open(args.data_path_1, 'r') as rf, open(args.save_difference_path,
'w') as wf:
reader, writer = csv.reader(rf), csv.writer(wf)
header = next(reader)
writer.writerow(header)
for line in reader():
if line[0] not in intersection:
writer.writerow(line)
def interpret(args: InterpretArgs) -> None:
"""
Runs interpretation of a Chemprop model using the Monte Carlo Tree Search algorithm.
:param args: A :class:`~chemprop.args.InterpretArgs` object containing arguments for interpretation.
"""
if args.number_of_molecules != 1:
raise ValueError(
"Interpreting is currently only available for single-molecule models."
)
global C_PUCT, MIN_ATOMS
chemprop_model = ChempropModel(args)
def scoring_function(smiles: List[str]) -> List[float]:
return chemprop_model(smiles)[:, args.property_id - 1]
C_PUCT = args.c_puct
MIN_ATOMS = args.min_atoms
all_smiles = get_smiles(path=args.data_path,
smiles_columns=args.smiles_columns)
header = get_header(path=args.data_path)
property_name = header[
args.property_id] if len(header) > args.property_id else 'score'
print(f'smiles,{property_name},rationale,rationale_score')
for smiles in all_smiles:
score = scoring_function([smiles])[0]
if score > args.prop_delta:
rationales = mcts(smiles=smiles[0],
scoring_function=scoring_function,
n_rollout=args.rollout,
max_atoms=args.max_atoms,
prop_delta=args.prop_delta)
else:
rationales = []
if len(rationales) == 0:
print(f'{smiles},{score:.3f},,')
else:
min_size = min(len(x.atoms) for x in rationales)
min_rationales = [
x for x in rationales if len(x.atoms) == min_size
]
rats = sorted(min_rationales, key=lambda x: x.P, reverse=True)
print(f'{smiles},{score:.3f},{rats[0].smiles},{rats[0].P:.3f}')
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 compare_datasets_tsne(args: Args):
if len(args.smiles_paths) > len(args.colors) or len(
args.smiles_paths) > len(args.sizes):
raise ValueError(
'Must have at least as many colors and sizes as datasets')
# Random seed for random subsampling
np.random.seed(0)
# Load the smiles datasets
print('Loading data')
smiles, slices, labels = [], [], []
for smiles_path in args.smiles_paths:
# Get label
label = os.path.basename(smiles_path).replace('.csv', '')
# Get SMILES
new_smiles = get_smiles(path=smiles_path,
smiles_columns=args.smiles_column,
flatten=True)
print(f'{label}: {len(new_smiles):,}')
# Subsample if dataset is too large
if len(new_smiles) > args.max_per_dataset:
print(f'Subsampling to {args.max_per_dataset:,} molecules')
new_smiles = np.random.choice(new_smiles,
size=args.max_per_dataset,
replace=False).tolist()
slices.append(slice(len(smiles), len(smiles) + len(new_smiles)))
labels.append(label)
smiles += new_smiles
# Compute Morgan fingerprints
print('Computing Morgan fingerprints')
morgan_generator = get_features_generator('morgan')
morgans = [
morgan_generator(smile) for smile in tqdm(smiles, total=len(smiles))
]
print('Running t-SNE')
start = time.time()
tsne = TSNE(n_components=2, init='pca', random_state=0, metric='jaccard')
X = tsne.fit_transform(morgans)
print(f'time = {time.time() - start:.2f} seconds')
if args.cluster:
import hdbscan # pip install hdbscan
print('Running HDBSCAN')
start = time.time()
clusterer = hdbscan.HDBSCAN(min_cluster_size=5, gen_min_span_tree=True)
colors = clusterer.fit_predict(X)
print(f'time = {time.time() - start:.2f} seconds')
print('Plotting t-SNE')
x_min, x_max = np.min(X, axis=0), np.max(X, axis=0)
X = (X - x_min) / (x_max - x_min)
makedirs(args.save_path, isfile=True)
plt.clf()
fontsize = 50 * args.scale
fig = plt.figure(figsize=(64 * args.scale, 48 * args.scale))
plt.title('t-SNE using Morgan fingerprint with Jaccard similarity',
fontsize=2 * fontsize)
ax = fig.gca()
handles = []
legend_kwargs = dict(loc='upper right', fontsize=fontsize)
if args.cluster:
plt.scatter(X[:, 0],
X[:, 1],
s=150 * np.mean(args.sizes),
c=colors,
cmap='nipy_spectral')
else:
for slc, color, label, size in zip(slices, args.colors, labels,
args.sizes):
if args.plot_molecules:
# Plots molecules
handles.append(mpatches.Patch(color=color, label=label))
for smile, (x, y) in zip(smiles[slc], X[slc]):
img = Draw.MolsToGridImage([Chem.MolFromSmiles(smile)],
molsPerRow=1,
subImgSize=(200, 200))
imagebox = offsetbox.AnnotationBbox(
offsetbox.OffsetImage(img), (x, y),
bboxprops=dict(color=color))
ax.add_artist(imagebox)
else:
# Plots points
plt.scatter(X[slc, 0],
X[slc, 1],
s=150 * size,
color=color,
label=label)
if args.plot_molecules:
legend_kwargs['handles'] = handles
plt.legend(**legend_kwargs)
plt.xticks([]), plt.yticks([])
print('Saving t-SNE')
plt.savefig(args.save_path)
def test_noheader_2mol(self):
"""Testing with no header and 2 molecules."""
smiles = get_smiles(path=self.no_header_path,
number_of_molecules=2,
header=False)
self.assertEqual(smiles, [['C', 'CC'], ['CC', 'CN'], ['O', 'CO']])
def test_noheader_1mol(self):
"""Testing with no header"""
smiles = get_smiles(path=self.no_header_path, header=False)
self.assertEqual(smiles, [['C'], ['CC'], ['O']])
def test_specified_columns_changed_order(self):
"""Testing with no optional arguments."""
smiles = get_smiles(path=self.smiles_path,
smiles_columns=['column1', 'column0'])
self.assertEqual(smiles, [['CC', 'C'], ['CN', 'CC'], ['CO', 'O']])
def test_specified_column_inputs(self):
"""Testing with a specified smiles column argument."""
smiles = get_smiles(path=self.smiles_path, smiles_columns=['column1'])
self.assertEqual(smiles, [['CC'], ['CN'], ['CO']])
def test_default_inputs(self):
"""Testing with no optional arguments."""
smiles = get_smiles(path=self.smiles_path)
self.assertEqual(smiles, [['C', 'CC'], ['CC', 'CN'], ['O', 'CO']])
print(
f'Average dice similarity = {np.mean(similarities):.4f} +/- {np.std(similarities):.4f}'
)
print(f'Minimum dice similarity = {np.min(similarities):.4f}')
print(f'Maximum dice similarity = {np.max(similarities):.4f}')
print()
print('Percentiles for dice similarity')
print(' | '.join([
f'{i}% = {np.percentile(similarities, i):.4f}'
for i in range(0, 101, 10)
]))
if __name__ == '__main__':
args = Args().parse_args()
smiles_1 = get_smiles(path=args.data_path_1,
smiles_columns=args.smiles_column_1,
flatten=True)
smiles_2 = get_smiles(path=args.data_path_2,
smiles_columns=args.smiles_column_2,
flatten=True)
if args.similarity_measure == 'scaffold':
scaffold_similarity(smiles_1, smiles_2)
elif args.similarity_measure == 'morgan':
morgan_similarity(smiles_1, smiles_2, args.radius, args.sample_rate)
else:
raise ValueError(
f'Similarity measure "{args.similarity_measure}" not supported.')
def generate_and_save_features(args: Args):
"""
Computes and saves features for a dataset of molecules as a 2D array in a .npz file.
:param args: Arguments.
"""
# Create directory for save_path
makedirs(args.save_path, isfile=True)
# Get data and features function
smiles = get_smiles(path=args.data_path, smiles_column=args.smiles_column)
features_generator = get_features_generator(args.features_generator)
temp_save_dir = args.save_path + '_temp'
# Load partially complete data
if args.restart:
if os.path.exists(args.save_path):
os.remove(args.save_path)
if os.path.exists(temp_save_dir):
shutil.rmtree(temp_save_dir)
else:
if os.path.exists(args.save_path):
raise ValueError(
f'"{args.save_path}" already exists and args.restart is False.'
)
if os.path.exists(temp_save_dir):
features, temp_num = load_temp(temp_save_dir)
if not os.path.exists(temp_save_dir):
makedirs(temp_save_dir)
features, temp_num = [], 0
# Build features map function
smiles = smiles[len(
features
):] # restrict to data for which features have not been computed yet
if args.sequential:
features_map = map(features_generator, smiles)
else:
features_map = Pool().imap(features_generator, smiles)
# Get features
temp_features = []
for i, feats in tqdm(enumerate(features_map), total=len(smiles)):
temp_features.append(feats)
# Save temporary features every save_frequency
if (i > 0 and
(i + 1) % args.save_frequency == 0) or i == len(smiles) - 1:
save_features(os.path.join(temp_save_dir, f'{temp_num}.npz'),
temp_features)
features.extend(temp_features)
temp_features = []
temp_num += 1
try:
# Save all features
save_features(args.save_path, features)
# Remove temporary features
shutil.rmtree(temp_save_dir)
except OverflowError:
print(
'Features array is too large to save as a single file. Instead keeping features as a directory of files.'
)
