pIC50 prediction (train)
0.44RMSEUnified RNN-CNN
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Unified RNN-CNNArchitecture=Unified RNN-CNN, Ensemble Strategy=parameter+NN ensemble, Representation=novel representations learned from seq2seq2018.06 | 0.44 | 0.95 | |
| Unified RNN-CNNArchitecture=Unified RNN-CNN, Ensemble Strategy=parameter ensemble, Representation=novel representations learned from seq2seq2018.06 | 0.45 | 0.95 | |
| Unified RNN-CNNArchitecture=Unified RNN-CNN, Ensemble Strategy=single, Representation=novel representations learned from seq2seq2018.06 | 0.47 | 0.94 | |
| Random ForestArchitecture=RF, Ensemble Strategy=single, Representation=novel representations learned from seq2seq2018.06 | 0.63 | 0.91 | |
| Separate RNN-CNNArchitecture=Separate RNN-CNN, Ensemble Strategy=parameter+NN ensemble, Representation=novel representations learned from seq2seq2018.06 | 0.67 | 0.9 | |
| Separate RNN-CNNArchitecture=Separate RNN-CNN, Ensemble Strategy=parameter ensemble, Representation=novel representations learned from seq2seq2018.06 | 0.68 | 0.88 |