TDC.LD50_Zhu Leaderboard

Dataset Summary

Dataset Unit Size Task Metric Dataset Split
TDC.LD50_Zhu log(1/(mol/kg)) 7,385 Regression MAE Scaffold

Leaderboard

Rank Model Contact Link #Params MAE
1 BaseBoosting KyQVZ6b2 David Huang GitHub, Paper N/A 0.552 ± 0.009
2 MACCS keys + autoML Alexander Scarlat GitHub, Paper N/A 0.588 ± 0.005
3 Chemprop Kyle Swanson GitHub, Paper N/A 0.606 ± 0.024
4 MapLight Jim Notwell GitHub, Paper N/A 0.621 ± 0.003
5 QuGIN Shuai Shi GitHub, Paper 1,797,506 0.622 ± 0.015
6 Chemprop-RDKit Kyle Swanson GitHub, Paper N/A 0.625 ± 0.022
7 MapLight + GNN Jim Notwell GitHub, Paper N/A 0.633 ± 0.003
8 Basic ML Nilavo Boral GitHub, Paper N/A 0.636 ± 0.001
9 Euclia ML model Euclia GitHub, Paper 50 0.646 ± 0.011
10 GCN Kexin Huang GitHub, Paper 191,810 0.649 ± 0.026
11 Morgan + MLP (DeepPurpose) Kexin Huang GitHub, Paper 1,477,185 0.649 ± 0.019
12 NeuralFP Kexin Huang GitHub, Paper 480,193 0.667 ± 0.020
13 ContextPred Kexin Huang GitHub, Paper 2,067,053 0.669 ± 0.030
14 CNN (DeepPurpose) Kexin Huang GitHub, Paper 226,625 0.675 ± 0.011
15 RDKit2D + MLP (DeepPurpose) Kexin Huang GitHub, Paper 633,409 0.678 ± 0.003
16 AttentiveFP Kexin Huang GitHub, Paper 300,806 0.678 ± 0.012
17 AttrMasking Kexin Huang GitHub, Paper 2,067,053 0.685 ± 0.025

: The higher the better.