A Group Symmetric Stochastic Differential Equation Model for Molecule Multi-modal Pretraining
This work addresses a critical issue in AI-based drug discovery by improving molecule representation learning through multi-modal integration, offering a novel approach with broad applicability in the domain.
The paper tackles the problem of molecule multi-modal pretraining by proposing MoleculeSDE, a model that uses group symmetric stochastic differential equations to generate 3D geometries from 2D topologies and vice versa, achieving state-of-the-art performance on 26 out of 32 downstream tasks.
Molecule pretraining has quickly become the go-to schema to boost the performance of AI-based drug discovery. Naturally, molecules can be represented as 2D topological graphs or 3D geometric point clouds. Although most existing pertaining methods focus on merely the single modality, recent research has shown that maximizing the mutual information (MI) between such two modalities enhances the molecule representation ability. Meanwhile, existing molecule multi-modal pretraining approaches approximate MI based on the representation space encoded from the topology and geometry, thus resulting in the loss of critical structural information of molecules. To address this issue, we propose MoleculeSDE. MoleculeSDE leverages group symmetric (e.g., SE(3)-equivariant and reflection-antisymmetric) stochastic differential equation models to generate the 3D geometries from 2D topologies, and vice versa, directly in the input space. It not only obtains tighter MI bound but also enables prosperous downstream tasks than the previous work. By comparing with 17 pretraining baselines, we empirically verify that MoleculeSDE can learn an expressive representation with state-of-the-art performance on 26 out of 32 downstream tasks.