Table 2.
The information of 8 public datasets.
| Dataset type | Dataset name | Description | Numbers | Reference |
|---|---|---|---|---|
| Regression | delaney | ESOL Water solubility | 1128 | (Delaney, 2004) |
| Lipop | Lipop Lipophilicity | 4200 | (Shen et al., 2021) | |
| FreeSolv | FreeSolv Solvation free energy | 642 | (Shen et al., 2021) | |
| PDBbind | PDBbind-refined | 3040 | (Shen et al., 2021) | |
| Classification | N6512 | Ames mutagenicity data set | 6506 | (Hansen et al., 2009) |
| BBBP | BBBP Blood-brain barrier penetration | 2039 | (Shen et al., 2021) | |
| ClinTox2 | ClinTox Clinical trial toxicity | 1478 | (Shen et al., 2021) | |
| BACE | BACE-1 benchmark set | 1513 | (Shen et al., 2021) |