3D Interaction Geometric Pre-training for Molecular Relational Learning
This addresses the need for efficient 3D interaction modeling in molecular sciences, such as drug discovery, though it is incremental by building on existing 2D methods.
The paper tackles the problem of molecular relational learning by introducing a 3D geometric pre-training strategy that overcomes the cost of traditional quantum mechanical methods, resulting in up to a 24.93% performance improvement across 40 tasks.
Molecular Relational Learning (MRL) is a rapidly growing field that focuses on understanding the interaction dynamics between molecules, which is crucial for applications ranging from catalyst engineering to drug discovery. Despite recent progress, earlier MRL approaches are limited to using only the 2D topological structure of molecules, as obtaining the 3D interaction geometry remains prohibitively expensive. This paper introduces a novel 3D geometric pre-training strategy for MRL (3DMRL) that incorporates a 3D virtual interaction environment, overcoming the limitations of costly traditional quantum mechanical calculation methods. With the constructed 3D virtual interaction environment, 3DMRL trains 2D MRL model to learn the global and local 3D geometric information of molecular interaction. Extensive experiments on various tasks using real-world datasets, including out-of-distribution and extrapolation scenarios, demonstrate the effectiveness of 3DMRL, showing up to a 24.93% improvement in performance across 40 tasks. Our code is publicly available at https://github.com/Namkyeong/3DMRL.