Congren Dai, Yue Yang, Krinos Li, Huichi Zhou, Shijie Liang, Zhang Bo, Enyang Liu, Ge Jin, Hongran An, Haosen Zhang, Peiyuan Jing, KinHei Lee, Zhenxuan Zhang, Xiaobing Li, Maosong Sun. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Predicting binding affinity between biomolecules is a critical task in drug discovery, where deep learning methods have achieved significant progress. However, many existing approaches employ modality-specific network architectures, limiting their direct applicability across diverse biomolecular interaction types. In this work, we propose F3Affinity, a novel structure-based graph transformer that is agnostic to biomolecular interaction type in its architectural design. Leveraging a frame averaging technique, our model flexibly learns SE(3)-invariant representations of input structures. We further demonstrate that F3Affinity can be independently applied to various binding affinity prediction benchmarks without requiring any pre-trained embeddings, including protein-ligand, protein-protein, and protein-nucleic acid interactions, and achieving competitive performance. These results validate its broad applicability and effectiveness across multiple biomolecular interaction types.