文献类型：期刊文献

英文题名：Retrieval-Augmented Multimodal Learning for Enzyme–Substrate Interaction Prediction Under Low-Homology Shift

作者：Liu, Chen[1]; Zhou, Bingxin[2]; Wang, Xinyuan[3]; Li, Ming[4]; Fan, Guisheng[1]; Hong, Liang[2]

机构：[1] School of Information Science and Engineering, East China University of Science and Technology, Shanghai, 200237, China; [2] Institute of Natural Sciences, Zhangjiang Institute for Advanced Study, Shanghai Jiao Tong University, Shanghai, 200240, China; [3] School of Life Sciences and Biotechnology, Shanghai Jiao Tong University, Shanghai, 200240, China; [4] Zhejiang Key Laboratory of Intelligent Education Technology and Application, Zhejiang Normal University, Jinhua, China

年份：2026

外文期刊名：arXiv

收录：EI(收录号：20260326867)

语种：英文

外文关键词：Biochemistry - Enzymes - Machine learning - Substrates

摘要：Enzyme–substrate interaction (ESI) prediction is a fundamental computational task for biocatalyst discovery and reaction screening in large biochemical spaces. In practical settings, ESI prediction is challenged by sparse positive supervision and low-homology distribution shift, where test enzymes share limited sequence identity with those observed during training. To address these challenges, we propose RAMMESI, a retrieval-augmented multimodal framework for robust ESI prediction. RAMMESI learns explicit pairwise enzyme–substrate representations through directional cross-modal interaction modeling and adaptive fusion. To enhance robustness, RAMMESI retrieves neighboring enzymes at inference time, recombines them with the query substrate, and aggregates the resulting pairwise predictions as contextual evidence. To improve learning under sparse positive supervision, we further adopt an imbalance-aware weighted-BCE objective. Experiments on two ESI benchmarks under sequence-identity-aware splits demonstrate that RAMMESI achieves consistently strong performance, with particular advantages in more challenging low-identity regimes. In addition, the retrieval module improves multiple ESI backbones in a plug-and-play manner, suggesting that retrieval provides a general mechanism for improving robustness under homology shift. The source code is publicly available at the following link https://github.com/code4luck/RAMMESI.git Copyright ? 2026, The Authors. All rights reserved.