A Universal Framework for Accurate and Efficient Geometric Deep Learning of Molecular Systems
This work addresses the challenge of applying deep learning to diverse molecular systems efficiently, which is crucial for real-world applications in molecular sciences.
The authors tackled the problem of inefficient and non-universal geometric deep learning for molecular systems by introducing PAMNet, a physics-informed framework that outperforms state-of-the-art methods in accuracy and efficiency across small molecules, RNA structures, and protein-ligand binding tasks.
Molecular sciences address a wide range of problems involving molecules of different types and sizes and their complexes. Recently, geometric deep learning, especially Graph Neural Networks, has shown promising performance in molecular science applications. However, most existing works often impose targeted inductive biases to a specific molecular system, and are inefficient when applied to macromolecules or large-scale tasks, thereby limiting their applications to many real-world problems. To address these challenges, we present PAMNet, a universal framework for accurately and efficiently learning the representations of three-dimensional (3D) molecules of varying sizes and types in any molecular system. Inspired by molecular mechanics, PAMNet induces a physics-informed bias to explicitly model local and non-local interactions and their combined effects. As a result, PAMNet can reduce expensive operations, making it time and memory efficient. In extensive benchmark studies, PAMNet outperforms state-of-the-art baselines regarding both accuracy and efficiency in three diverse learning tasks: small molecule properties, RNA 3D structures, and protein-ligand binding affinities. Our results highlight the potential for PAMNet in a broad range of molecular science applications.