def predict_multiple_molecules(model_name, molecule_file, charge_file,
out_file, format):
"""
Make predictions of bond energies of multiple molecules.
Args:
model_name (str): The pretrained model to use for making predictions. A model
should be of the format format `dataset/date`, e.g. `mesd/20200808`,
`pubchem/20200531`. It is possible to provide only the `dataset` part,
and in this case, the latest model will be used.
molecule_file (str): path to molecule file
charge_file (str): path to charge file, if `None` charges are set to zero
out_file (str): path to file to write output
format (str): format of molecules, e.g. `sdf`, `graph`, `pdb`, `smiles`,
and `inchi`.
"""
model_path = get_model_path(model_name)
model_info = get_model_info(model_path)
allowed_charge = model_info["allowed_charge"]
unit_converter = model_info["unit_conversion"]
predictor = PredictionMultiReactant(molecule_file,
charge_file,
format,
allowed_charge,
ring_bond=False)
molecules, labels, extra_features = predictor.prepare_data()
predictions = get_prediction(model_path, unit_converter, molecules, labels,
extra_features)
return predictor.write_results(predictions, out_file)
def predict_by_reactions(model_name, molecule_file, reaction_file, charge_file,
out_file, format):
"""
Make predictions for many bonds where each bond is specified as an reaction.
Args:
model_name (str): The pretrained model to use for making predictions. A model
should be of the format format `dataset/date`, e.g. `mesd/20200808`,
`pubchem/20200531`. It is possible to provide only the `dataset` part,
and in this case, the latest model will be used.
molecule_file (str): path to file storing all molecules
reaction_file (str): path to file specifying reactions
charge_file (str): path to charge file, if `None` charges are set to zero
out_file (str): path to file to write output
format (str): format of molecules, e.g. `sdf`, `graph`, `pdb`, `smiles`,
and `inchi`.
"""
model_path = get_model_path(model_name)
model_info = get_model_info(model_path)
unit_converter = model_info["unit_conversion"]
predictor = PredictionByReaction(molecule_file,
reaction_file,
charge_file,
format=format)
molecules, labels, extra_features = predictor.prepare_data()
predictions = get_prediction(model_path, unit_converter, molecules, labels,
extra_features)
return predictor.write_results(predictions, out_file)
def predict_by_struct_label_extra_feats_files(model_name,
molecule_file,
label_file,
extra_feats_file,
out_file="bde.yaml"):
model_path = get_model_path(model_name)
model_info = get_model_info(model_path)
unit_converter = model_info["unit_conversion"]
predictor = PredictionStructLabelFeatFiles(molecule_file, label_file,
extra_feats_file)
molecules, labels, extra_features = predictor.prepare_data()
predictions = get_prediction(model_path, unit_converter, molecules, labels,
extra_features)
return predictor.write_results(predictions, out_file)
def predict_single_molecule(
model_name,
molecule,
charge=0,
ring_bond=False,
write_result=False,
figure_name="prediction.png",
format=None,
):
"""
Make predictions for a single molecule.
Breaking a bond may result in products with different combination of products
charge, we report the smallest charge w.r.t. the product charge assignation.
Args:
model_name (str): The pre-trained model to use for making predictions. A model
should be of the format format `dataset/date`, e.g. `mesd/20200808`,
`pubchem/20200521`. It is possible to provide only the `dataset` part,
and in this case, the latest model will be used.
molecule (str): SMILES or InChI string or a path to a file storing these string.
charge (int): charge of the molecule.
ring_bond (bool): whether to make predictions for ring bond.
write_result (bool): whether to write the returned sdf to stdout.
figure_name (str): the name of the figure to be created showing the bond energy.
format (str): format of the molecule, if not provided, will guess based on the
file extension.
Returns:
str: sdf string representing the molecules and energies.
"""
model_path = get_model_path(model_name)
model_info = get_model_info(model_path)
allowed_charge = model_info["allowed_charge"]
unit_converter = model_info["unit_conversion"]
assert (charge in allowed_charge
), f"expect charge to be one of {allowed_charge}, but got {charge}"
p = to_path(molecule)
if p.is_file():
if format is None:
suffix = p.suffix.lower()
if suffix == ".sdf":
format = "sdf"
elif suffix == ".pdb":
format = "pdb"
else:
raise RuntimeError(
f"Expect file format `.sdf` or `.pdb`, but got {suffix}")
with open(p, "r") as f:
molecule = f.read().strip()
else:
if format is None:
if molecule.lower().startswith("inchi="):
format = "inchi"
else:
format = "smiles"
predictor = PredictionOneReactant(molecule, charge, format, allowed_charge,
ring_bond)
molecules, labels, extra_features = predictor.prepare_data()
predictions = get_prediction(model_path, unit_converter, molecules, labels,
extra_features)
return predictor.write_results(predictions, figure_name, write_result)