文献类型：期刊文献

英文题名：Protein Engineering with Lightweight Graph Denoising Neural Networks

作者：Zhou, Bingxin[1,2];Zheng, Lirong[1];Wu, Banghao[1,3];Tan, Yang[1,4,5];Lv, Outongyi[1];Yi, Kai[6];Fan, Guisheng[4];Hong, Liang[1,2,5,7]

机构：[1]Shanghai Jiao Tong Univ, Inst Nat Sci, Shanghai 200240, Peoples R China;[2]Shanghai Natl Ctr Appl Math SJTU Ctr, Shanghai 200240, Peoples R China;[3]Shanghai Jiao Tong Univ, Sch Life Sci & Biotechnol, Shanghai 200240, Peoples R China;[4]East China Univ Sci & Technol, Sch Informat Sci & Engn, Shanghai 200237, Peoples R China;[5]Shanghai Artificial Intelligence Lab, Shanghai 200232, Peoples R China;[6]Univ New South Wales, Sch Math & Stat, Sydney 2052, Australia;[7]Shanghai Jiao Tong Univ, Zhangjiang Inst Adv Study, Shanghai 201203, Peoples R China

年份：2024

卷号：64

期号：9

起止页码：3650

外文期刊名：JOURNAL OF CHEMICAL INFORMATION AND MODELING

收录：;EI(收录号：20241715956393);WOS:【SCI-EXPANDED(收录号:WOS:001227969400001)】；

基金：The authors acknowledge the Center for High-Performance Computing at Shanghai Jiao Tong University for computing resources. This work was supported by the National Natural Science Foundation of China (31630002, 62302291), the Innovation Program of Shanghai Municipal Education Commission (2019-01-07-00-02-E00076), the Computational Biology Program of Shanghai Science and Technology Commission (23JS1400600), the Student Innovation Center at Shanghai Jiao Tong University, and Shanghai Artificial Intelligence Laboratory.

语种：英文

外文关键词：Amino acids - Deep learning - Genetic engineering - Graph neural networks - Physicochemical properties

摘要：Protein engineering faces challenges in finding optimal mutants from a massive pool of candidate mutants. In this study, we introduce a deep-learning-based data-efficient fitness prediction tool to steer protein engineering. Our methodology establishes a lightweight graph neural network scheme for protein structures, which efficiently analyzes the microenvironment of amino acids in wild-type proteins and reconstructs the distribution of the amino acid sequences that are more likely to pass natural selection. This distribution serves as a general guidance for scoring proteins toward arbitrary properties on any order of mutations. Our proposed solution undergoes extensive wet-lab experimental validation spanning diverse physicochemical properties of various proteins, including fluorescence intensity, antigen-antibody affinity, thermostability, and DNA cleavage activity. More than 40% of ProtLGN-designed single-site mutants outperform their wild-type counterparts across all studied proteins and targeted properties. More importantly, our model can bypass the negative epistatic effect to combine single mutation sites and form deep mutants with up to seven mutation sites in a single round, whose physicochemical properties are significantly improved. This observation provides compelling evidence of the structure-based model's potential to guide deep mutations in protein engineering. Overall, our approach emerges as a versatile tool for protein engineering, benefiting both the computational and bioengineering communities.