Learning Harmonic Molecular Representations on Riemannian Manifold
This work addresses molecular representation learning for AI-assisted drug discovery, offering a novel approach with demonstrated improvements in specific tasks.
The authors tackled the problem of encoding 3D molecular structures by proposing a Harmonic Molecular Representation (HMR) framework that uses Laplace-Beltrami eigenfunctions on a Riemannian manifold, which outperformed state-of-the-art models in ligand-binding protein pocket classification and rigid protein docking.
Molecular representation learning plays a crucial role in AI-assisted drug discovery research. Encoding 3D molecular structures through Euclidean neural networks has become the prevailing method in the geometric deep learning community. However, the equivariance constraints and message passing in Euclidean space may limit the network expressive power. In this work, we propose a Harmonic Molecular Representation learning (HMR) framework, which represents a molecule using the Laplace-Beltrami eigenfunctions of its molecular surface. HMR offers a multi-resolution representation of molecular geometric and chemical features on 2D Riemannian manifold. We also introduce a harmonic message passing method to realize efficient spectral message passing over the surface manifold for better molecular encoding. Our proposed method shows comparable predictive power to current models in small molecule property prediction, and outperforms the state-of-the-art deep learning models for ligand-binding protein pocket classification and the rigid protein docking challenge, demonstrating its versatility in molecular representation learning.