EPGCNDS¶
- class EPGCNDS(*, molecule_channels=66, hidden_channels=32, middle_channels=16, out_channels=1)[source]¶
Bases:
chemicalx.models.base.Model
An implementation of the EPGCN-DS model from [sun2020].
See also
This model was suggested in https://github.com/AstraZeneca/chemicalx/issues/22
- sun2020
Sun, M., et al. (2020). Structure-Based Drug-Drug Interaction Detection via Expressive Graph Convolutional Networks and Deep Sets. Proceedings of the AAAI Conference on Artificial Intelligence, 34(10), 13927–13928.
Methods Summary
forward
(molecules_left, molecules_right)Run a forward pass of the EPGCN-DS model.
unpack
(batch)Return the left molecular graph and right molecular graph.
Methods Documentation
- forward(molecules_left, molecules_right)[source]¶
Run a forward pass of the EPGCN-DS model.
- Parameters
molecules_left (
PackedGraph
) – Batched molecules for the left side drugs.molecules_right (
PackedGraph
) – Batched molecules for the right side drugs.
- Return type
FloatTensor
- Returns
A column vector of predicted synergy scores.