文献类型：期刊文献

英文题名：A Motif-Based Deep Learning Tool for the Identification of Unusual NADH-Dependent Imine Reductases

作者：Shen, Xin-Yuan[1]; Wu, Yu-Xuan[2]; Ma, Zhi-Feng[1]; Yi, Xiao[2]; Shi, Min[1]; Zhu, Zhen-Yu[1]; Jin, Tian[1]; Hu, Xiao-Yu[1]; Huang, Zi-Yi[1]; Gao, Yun-Fei[1]; Chen, Qi[1]; Yu, Hui-Qun[2]; Xu, Jian-He[1]; Fan, Gui-Sheng[2]; Zheng, Gao-Wei[1]

机构：[1] State Key Laboratory of Bioreactor Engineering, Shanghai Collaborative Innovation Center for Biomanufacturing, East China University of Science and Technology, 130 Meilong Road, Shanghai, 200237, China; [2] School of Information Science and Engineering, East China University of Science and Technology, 130 Meilong Road, Shanghai, 200237, China

年份：2025

外文期刊名：SSRN

收录：EI(收录号：20250194054)

语种：英文

外文关键词：Amination - Enzyme immobilization - Enzyme inhibition - Enzyme kinetics - Hydrolases - Lipases

摘要：Enzymes are typically discovered through sequence alignment algorithms in genetic databases. However, conventional retrieval methods are often constrained in identifying novel biocatalysts, particularly in the absence of a specific target sequence. Here, we report the discovery of 95 putative NADH-dependent native IREDs that have not yet been reported using a deep-learning approach leveraging a conserved cofactor-binding motif. The Protein Motif to Search (PM2S) method integrated rule-based approaches, dynamic programming, machine learning, protein language models, and dense vector sparsification, enabling a more comprehensive retrieval based solely on motifs, rather than sequences. Activity and biotransformation analyses confirmed that most of the tested enzymes preferred NADH as cofactor when acting on imines and carbonyl compounds. Structural analysis of enzyme-cofactor complexes provided insights into the molecular mechanism and binding conformation underpinning the preference for NADH. This study introduced a motif-based bioinformatics strategy for enzyme discovery, expanded the repertoire of IREDs for amine synthesis, and broadened their application range in biosynthesis and chemical synthesis. ? 2025, The Authors. All rights reserved.