DeepDDI¶
- class DeepDDI(*, drug_channels, hidden_channels=2048, hidden_layers_num=9, out_channels=1)[source]¶
Bases:
chemicalx.models.base.Model
An implementation of the DeepDDI model from [ryu2018].
See also
This model was suggested in https://github.com/AstraZeneca/chemicalx/issues/2
- ryu2018
Ryu, J. Y., et al. (2018). Deep learning improves prediction of drug–drug and drug–food interactions. Proceedings of the National Academy of Sciences, 115(18), E4304–E4311.
Methods Summary
forward
(drug_features_left, drug_features_right)Run a forward pass of the DeepDDI model.
unpack
(batch)Return the context features, left drug features and right drug features.
Methods Documentation
- forward(drug_features_left, drug_features_right)[source]¶
Run a forward pass of the DeepDDI model.
- Parameters
drug_features_left (
FloatTensor
) – A matrix of head drug features.drug_features_right (
FloatTensor
) – A matrix of tail drug features.
- Return type
FloatTensor
- Returns
A column vector of predicted interaction scores.