Molecular property prediction holds significant importance in the fields of cheminformatics and drug discovery. Current modeling paradigms used for molecular representation mainly rely on 1D or 2D molecular formats, which are unable to distinguish between common stereoisomers, especially conformational and chiral isomers with the same bond connections but different spatial configurations. In addition, a single molecular representation paradigm inhibits the versatility and adaptability of models in various modes. To address these challenges, we propose a Multi-Graph Representation Fusion Network (MGRFN) which employs Graph Attention Network and SphereNet to extract 2D chemical features and 3D geometric information respectively, and design a bilinear fusion module to achieve efficient integration of multimodal representations. Experimental results on the QM9, MD17, and two chiral molecular datasets demonstrate the superior performance of MGRFN in predicting molecular quantum chemical properties and various conformational properties. Moreover, the visualization of molecular representations and attention weights shows that MGRFN can distinguish the physicochemical properties of different molecules and capture molecule-related substructures, which further enhances our understanding of its performance.
Shu et al. (Wed,) studied this question.