TDC.hERG Leaderboard

Dataset Summary

Dataset Unit Size Task Metric Dataset Split
TDC.hERG % 648 Binary AUROC Scaffold

Leaderboard

Rank Model Contact Link #Params AUROC
1 RDKit2D + MLP (DeepPurpose) Kexin Huang GitHub, Paper 633,409 0.841 ± 0.020
2 AttentiveFP Kexin Huang GitHub, Paper 300,806 0.825 ± 0.007
3 AttrMasking Kexin Huang GitHub, Paper 2,067,053 0.778 ± 0.046
4 ContextPred Kexin Huang GitHub, Paper 2,067,053 0.756 ± 0.023
5 CNN (DeepPurpose) Kexin Huang GitHub, Paper 226,625 0.754 ± 0.037
6 GCN Kexin Huang GitHub, Paper 191,810 0.738 ± 0.038
7 Morgan + MLP (DeepPurpose) Kexin Huang GitHub, Paper 1,477,185 0.736 ± 0.023
8 NeuralFP Kexin Huang GitHub, Paper 480,193 0.722 ± 0.034

: The higher the better.