olorenchemengine.beta package#

Submodules#

olorenchemengine.beta.gnn module#

class olorenchemengine.beta.gnn.SuperGATModel_beta(hidden_channels: int = 8, heads: int = 8, pooling_function: str = 'mean', negative_slope: float = 0.2, dropout: float = 0.0, add_self_loops: bool = True, bias: bool = True, attention_type: str = 'MX', neg_sample_ratio: float = 0.5, edge_sample_ratio: float = 1.0, is_undirected: bool = True, lr: float = 0.0001, optim: str = 'adam')#

Bases: BaseLightningModule

SuperGAT is a network

Parameters:

  • dropout (float, optional) – The dropout rate to use for the model. Default is 0.1.

  • lr (float, optional) – The learning rate to use for training. Default is 1e-4.

  • optim (str, optional) – The optimizer to use for training. Default is “adam”.

create(dimensions)#
forward(batch)#
test_step(batch, batch_idx)#
training_step(batch, batch_idx)#
validation_step(batch, batch_idx)#

olorenchemengine.beta.representations module#

class olorenchemengine.beta.representations.SimLookup_beta(rep: BaseCompoundVecRepresentation, *args, metric: str = 'cosine', k: int = 3, return_reps: bool = False, log: bool = True, **kwargs)#

Bases: BaseCompoundVecRepresentation

convert(Xs, ys=None, fit=False, **kwargs)#

Computes a vector representation from each structure in Xs.

Module contents#