TDC.Solubility_AqSolDB Leaderboard
Dataset Summary
| Dataset | Unit | Size | Task | Metric | Dataset Split |
|---|---|---|---|---|---|
| TDC.Solubility_AqSolDB | log mol/L | 9,982 | Regression | MAE | Scaffold |
Leaderboard
| Rank | Model | Contact | Link | #Params | MAE |
|---|---|---|---|---|---|
| 1 | XGBoost | Hao Tian | GitHub, Paper | 29 | 0.727 ± 0.004 |
| 2 | AttentiveFP | Kexin Huang | GitHub, Paper | 300,806 | 0.776 ± 0.008 |
| 3 | RDKit2D + MLP (DeepPurpose) | Kexin Huang | GitHub, Paper | 633,409 | 0.827 ± 0.047 |
| 4 | GCN | Kexin Huang | GitHub, Paper | 191,810 | 0.907 ± 0.020 |
| 5 | NeuralFP | Kexin Huang | GitHub, Paper | 480,193 | 0.947 ± 0.016 |
| 6 | CNN (DeepPurpose) | Kexin Huang | GitHub, Paper | 226,625 | 1.023 ± 0.023 |
| 7 | AttrMasking | Kexin Huang | GitHub, Paper | 2,067,053 | 1.026 ± 0.020 |
| 8 | ContextPred | Kexin Huang | GitHub, Paper | 2,067,053 | 1.040 ± 0.045 |
| 9 | Morgan + MLP (DeepPurpose) | Kexin Huang | GitHub, Paper | 1,477,185 | 1.203 ± 0.019 |
: The lower the better.