pIC50 prediction on pIC50 Generalization - Tyrosine Kinase
1.23RMSEUnified RNN-CNN
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Unified RNN-CNNArchitecture=Unified RNN-CNN, Ensemble Strategy=parameter+NN ensemble, Representation=novel representations learned from seq2seq2018.06 | 1.23 | 0.42 | |
| Unified RNN-CNNArchitecture=Unified RNN-CNN, Ensemble Strategy=single, Representation=novel representations learned from seq2seq2018.06 | 1.24 | 0.39 | |
| Unified RNN-CNNArchitecture=Unified RNN-CNN, Ensemble Strategy=parameter ensemble, Representation=novel representations learned from seq2seq2018.06 | 1.25 | 0.38 | |
| Random ForestArchitecture=RF, Ensemble Strategy=single, Representation=novel representations learned from seq2seq2018.06 | 1.58 | 0.11 | |
| Separate RNN-CNNArchitecture=Separate RNN-CNN, Ensemble Strategy=parameter+NN ensemble, Representation=novel representations learned from seq2seq2018.06 | 1.62 | 0.1 | |
| Separate RNN-CNNArchitecture=Separate RNN-CNN, Ensemble Strategy=parameter ensemble, Representation=novel representations learned from seq2seq2018.06 | 1.66 | 0.09 |