Papers › Uni-Mol: A Universal 3D Molecular Representation Learning Framework

Uni-Mol: A Universal 3D Molecular Representation Learning Framework

8 Sep 2022ChemRxiv 2022 9archive 2025-07-28

Gengmo Zhou, Zhifeng Gao, Qiankun Ding, Hang Zheng, Hongteng Xu, Zhewei Wei, Linfeng Zhang, Guolin Ke

Molecular representation learning (MRL) has gained tremendous attention due to its critical role in learning from limited supervised data for applications like drug design. In most MRL methods, molecules are treated as 1D sequential tokens or 2D topology graphs, limiting their ability to incorporate 3D information for downstream tasks and, in particular, making it almost impossible for 3D geometry prediction or generation. Herein, we propose Uni-Mol, a universal MRL framework that significantly enlarges the representation ability and application scope of MRL schemes. Uni-Mol is composed of two models with the same SE(3)-equivariant transformer architecture: a molecular pretraining model trained by 209M molecular conformations; a pocket pretraining model trained by 3M candidate protein pocket data. The two models are used independently for separate tasks, and are combined when used in protein-ligand binding tasks. By properly incorporating 3D information, Uni-Mol outperforms SOTA in 14/15 molecular property prediction tasks. Moreover, Uni-Mol achieves superior performance in 3D spatial tasks, including protein-ligand binding pose prediction, molecular conformation generation, etc. Finally, we show that Uni-Mol can be successfully applied to the tasks with few-shot data like pocket druggability prediction. The model and data will be made publicly available at https://github.com/dptech-corp/Uni-Mol.

Paper PDF Code

Code

dptech-corp/Uni-Mol mentioned in paperpytorchMIT report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

3D Geometry Prediction 3D geometry Drug Design Molecular Property Prediction Pose Prediction Prediction Property Prediction Representation Learning molecular representation

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Molecular Property Prediction	BACE	Uni-Mol	ROC-AUC	85.7	#3 of 20	Archive leaderboard	report
Molecular Property Prediction	BBBP	Uni-Mol	ROC-AUC	72.9	#15 of 29	Archive leaderboard	report
Molecular Property Prediction	ESOL	Uni-Mol	RMSE	0.788	#13 of 20	Archive leaderboard	report
Molecular Property Prediction	FreeSolv	Uni-Mol	RMSE	1.620	#13 of 22	Archive leaderboard	report
Molecular Property Prediction	HIV	Uni-Mol	ROC-AUC	80.8	#2 of 4	Archive leaderboard	report
Molecular Property Prediction	Lipophilicity	Uni-Mol	RMSE	0.603	#1 of 13	Archive leaderboard	report
Molecular Property Prediction	MUV	Uni-Mol	ROC-AUC	82.1	#2 of 5	Archive leaderboard	report
Molecular Property Prediction	PCBA	Uni-Mol	ROC-AUC	88.5	#2 of 2	Archive leaderboard	report
Molecular Property Prediction	QM7	Uni-Mol	MAE	41.8	#1 of 8	Archive leaderboard	report
Molecular Property Prediction	QM8	Uni-Mol	MAE	0.0156	#1 of 8	Archive leaderboard	report
Molecular Property Prediction	QM9	Uni-Mol	MAE	0.00467	#1 of 8	Archive leaderboard	report
Molecular Property Prediction	SIDER	Uni-Mol	ROC-AUC	65.9	#7 of 19	Archive leaderboard	report
Molecular Property Prediction	Tox21	Uni-Mol	ROC-AUC	79.6	#5 of 20	Archive leaderboard	report
Molecular Property Prediction	ToxCast	Uni-Mol	ROC-AUC	69.6	#3 of 8	Archive leaderboard	report
Molecular Property Prediction	clintox	Uni-Mol	Molecules (M)	19	#5 of 20	Archive leaderboard	report
Molecular Property Prediction	clintox	Uni-Mol	ROC-AUC	91.9	#5 of 20	Archive leaderboard	report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections