terminator.models.layers.graph_features.PositionalEncodings

class terminator.models.layers.graph_features.PositionalEncodings(num_embeddings)

Bases: Module

Module to generate differential positional encodings for protein graph edges

__init__(num_embeddings)

Initializes internal Module state, shared by both nn.Module and ScriptModule.

Methods

__init__(num_embeddings)	Initializes internal Module state, shared by both nn.Module and ScriptModule.
forward(E_idx)	Generate directional differential positional encodings for edges

Attributes

T_destination	alias of TypeVar('T_destination', bound=Mapping[str, Tensor])
dump_patches	This allows better BC support for load_state_dict().

forward(E_idx)

Generate directional differential positional encodings for edges

Parameters:

E_idx (torch.LongTensor) – Protein kNN edge indices Shape: n_batches x seq_len x k

Returns:

E – Directional Diffential positional encodings for edges Shape: n_batches x seq_len x k x num_embeddings

Return type:

torch.Tensor