MatchMaker¶
- class MatchMaker(*, context_channels, drug_channels, input_hidden_channels=32, middle_hidden_channels=32, final_hidden_channels=32, out_channels=1, dropout_rate=0.5)[source]¶
Bases:
chemicalx.models.base.ModelAn implementation of the MatchMaker model from [kuru2021].
See also
This model was suggested in https://github.com/AstraZeneca/chemicalx/issues/23
- kuru2021
Kuru, H. I., et al. (2021). MatchMaker: A Deep Learning Framework for Drug Synergy Prediction. IEEE/ACM Transactions on Computational Biology and Bioinformatics, 1–1.
Methods Summary
forward(context_features, …)Run a forward pass of the MatchMaker model.
unpack(batch)Return the context features, left drug features, and right drug features.
Methods Documentation
- forward(context_features, drug_features_left, drug_features_right)[source]¶
Run a forward pass of the MatchMaker model.
- Parameters
context_features (
FloatTensor) – A matrix of biological context features.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 synergy scores.