Open access
Aug 2026
A unified framework for molecular property prediction based on hierarchical multi-granularity molecular representation learning
An atom–bond bipartite graph modeling approach that treats atoms and bonds as explicit learnable node types and jointly models atom–atom, atom–bond, and bond–bond local interactions within a unified propagation framework is introduced.
Xing Zhao, Xianlai Chen, Yunbo Wang et al.
· Bioinformatics · 0 citations