Skip to yearly menu bar Skip to main content


In-Person Poster presentation / poster accept

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

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

MH1-2-3-4 #110

Keywords: [ Large-Scale 3D Molecular Pretraining ] [ representation learning ] [ Molecular Property ] [ Protein-Ligand Complex ] [ Machine Learning for Sciences ]


Abstract:

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/generation. In this paper, we propose a universal 3D MRL framework, called Uni-Mol, that significantly enlarges the representation ability and application scope of MRL schemes. Uni-Mol contains two pretrained models with the same SE(3) Transformer architecture: a molecular model pretrained by 209M molecular conformations; a pocket model pretrained by 3M candidate protein pocket data. Besides, Uni-Mol contains several finetuning strategies to apply the pretrained models to various downstream 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. The code, model, and data are made publicly available at https://github.com/dptech-corp/Uni-Mol.

Chat is not available.