Molecular Mechanics-Driven Graph Neural Network with Multiplex Graph for Molecular Structures
This work addresses the problem of efficient and accurate molecular property prediction for AI-aided molecular design, representing an incremental improvement by balancing expressive power and computational complexity.
The authors tackled the challenge of predicting physicochemical properties from molecular structures by proposing a molecular mechanics-driven Graph Neural Network (MXMNet) that uses a two-layer multiplex graph to capture covalent and non-covalent interactions, achieving superior results on QM9 and PDBBind datasets compared to state-of-the-art models under restricted resources.
The prediction of physicochemical properties from molecular structures is a crucial task for artificial intelligence aided molecular design. A growing number of Graph Neural Networks (GNNs) have been proposed to address this challenge. These models improve their expressive power by incorporating auxiliary information in molecules while inevitably increase their computational complexity. In this work, we aim to design a GNN which is both powerful and efficient for molecule structures. To achieve such goal, we propose a molecular mechanics-driven approach by first representing each molecule as a two-layer multiplex graph, where one layer contains only local connections that mainly capture the covalent interactions and another layer contains global connections that can simulate non-covalent interactions. Then for each layer, a corresponding message passing module is proposed to balance the trade-off of expression power and computational complexity. Based on these two modules, we build Multiplex Molecular Graph Neural Network (MXMNet). When validated by the QM9 dataset for small molecules and PDBBind dataset for large protein-ligand complexes, MXMNet achieves superior results to the existing state-of-the-art models under restricted resources.