olorenchemengine.external.MolCLR package#

Submodules#

olorenchemengine.external.MolCLR.main module#

class olorenchemengine.external.MolCLR.main.MolCLR(model_type='ginet', epochs=100, batch_size=32, init_lr=0.0005, init_base_lr=None, base_coef=1, weight_decay=1e-06, **kwargs)#

Bases: BaseModel

model_config = {'drop_ratio': 0.3, 'emb_dim': 300, 'feat_dim': 512, 'num_layer': 5, 'pool': 'mean'}#
preprocess(X, y, **kwargs)#
Parameters:

X (list of smiles) –

Returns:

Processed list converted into whatever input for the model

class olorenchemengine.external.MolCLR.main.MolCLRVecRep(model_type='ginet', epochs=100, batch_size=32, init_lr=0.0005, init_base_lr=0.0001, weight_decay=1e-06, log=True, **kwargs)#

Bases: BaseVecRepresentation

convert(X, **kwargs)#

BaseVecRepresentation’s convert returns a list of numpy arrays.

Parameters:

  • Xs (Union[list, pd.DataFrame, dict, str]) – input data

  • ys (Union[list, pd.Series, np.ndarray], optional) – included for compatibility, unused argument. Defaults to None.

Returns:

list of molecular vector representations

Return type:

List[np.ndarray]

model_config = {'drop_ratio': 0.3, 'emb_dim': 300, 'feat_dim': 512, 'num_layer': 5, 'pool': 'mean'}#
class olorenchemengine.external.MolCLR.main.MolCLR_AF(log=True)#

Bases: AtomFeaturizer

convert(atom: _MockObject.Chem.Atom)#
property length#
class olorenchemengine.external.MolCLR.main.MolCLR_BF(log=True)#

Bases: BondFeaturizer

convert(bond: _MockObject.Chem.Bond)#
property length#
class olorenchemengine.external.MolCLR.main.MolCLR_PYG#

Bases: TorchGeometricGraph

olorenchemengine.external.MolCLR.model module#

Module contents#