Artificial intelligence-enabled enzyme engineering

XU Shuping; WANG Jinxiu; MENG Shuaiqi; DENG Qiufeng; ZHANG Hejian; WANG Xiufeng; GUO Zhao; CUI Haiyang

doi:10.11949/0438-1157.20251130

您当前的位置：

首页 >

文章列表页 >

Artificial intelligence-enabled enzyme engineering

Reviews and monographs | 更新时间：2026-08-13

- Artificial intelligence-enabled enzyme engineering
- CIESC Journal Vol. 77, Issue 6, Pages: 3224-3238(2026)
- 作者机构：
  
  1.南京师范大学生命科学学院微生物改造技术全国重点实验室，江苏南京 210023
  2.南京师范大学大规模复杂系统数值模拟教育部重点实验室，江苏南京 210023
  3.南京理工大学环境与生物工程学院，江苏南京 210094
- 作者简介：
- 基金信息：
- DOI：10.11949/0438-1157.20251130
  CLC： Q 814
- Received：11 October 2025，
  
  Revised：2026-01-28，
  
  Online First：29 July 2026，
  
  Published：25 June 2026
- 稿件说明：
移动端阅览
徐舒萍, 汪金秀, 孟帅奇, 邓秋凤, 张鹤渐, 王秀风, 郭照, 崔海洋. 人工智能赋能酶工程[J]. 化工学报, 2026, 77(6): 3224-3238

XU Shuping, WANG Jinxiu, MENG Shuaiqi, DENG Qiufeng, ZHANG Hejian, WANG Xiufeng, GUO Zhao, CUI Haiyang. Artificial intelligence-enabled enzyme engineering[J]. CIESC Journal, 2026, 77(6): 3224-3238
徐舒萍, 汪金秀, 孟帅奇, 邓秋凤, 张鹤渐, 王秀风, 郭照, 崔海洋. 人工智能赋能酶工程[J]. 化工学报, 2026, 77(6): 3224-3238 DOI： 10.11949/0438-1157.20251130.

XU Shuping, WANG Jinxiu, MENG Shuaiqi, DENG Qiufeng, ZHANG Hejian, WANG Xiufeng, GUO Zhao, CUI Haiyang. Artificial intelligence-enabled enzyme engineering[J]. CIESC Journal, 2026, 77(6): 3224-3238 DOI： 10.11949/0438-1157.20251130.

摘要

酶工程是生物催化、合成生物学等研究的重要基础。天然酶具备较好的催化性能，但用于实际生产的天然酶普遍存在稳定性不好、亲和力差、催化活性低的问题，需要对天然酶进行改造。传统酶改造方法主要有理性设计和非理性设计，能够得到一定的效果的突变体，但试验周期长，试错成本高。随着计算机技术的发展，人工智能开始被用于酶设计。机器学习算法较为流行，可通过随机森林、支持向量机等算法挖掘序列-功能数据中的规律从而指导理性设计，缩小突变体目标范围等。深度学习则具有端到端建模能力，可以从酶序列和结构中直接提取特征，用于结构、功能和动态行为的预测。另外，将人工智能方法和分子动力学模拟、量子化学计算方法结合起来可以对突变效应从物理上进行分析，为筛选提供参考。酶设计研究从过去的经验尝试逐渐向数据驱动、模型驱动的理性设计演化，在合成生物学、生物医药、绿色生物制造等领域也越来越受到重视。

Abstract

Enzyme engineering serves as a crucial foundation for research in biocatalysis

synthetic biology

and related fields. While natural enzymes possess excellent catalytic properties

those used in actual production often suffer from poor stability

low affinity

and low catalytic activity

necessitating their modification. Traditional enzyme modification methods primarily include rational design and non-rational design

which can yield mutants with certain benefits but with lengthy testing cycles and high trial-and-error costs. With the advancement of computer technology

artificial intelligence has begun to be applied to enzyme design. Machine learning algorithms are widely used. Methods such as random forests and support vector machines can uncover patterns in sequence-function data to guide rational design and narrow down the scope of potential mutants. On the other hand

deep learning offers end-to-end modeling capabilities

enabling the direct extraction of features from enzyme sequences and structures for predicting structure

function

and dynamic behavior. Furthermore

combining AI methods with molecular dynamics simulations and quantum chemistry calculations allows for a physical analysis of mutation effects

providing valuable insights for screening. Enzyme design research is evolving from past empirical trial-and-error approaches toward data-driven and model-driven rational design

and is gaining increasing attention in fields such as synthetic biology

biomedicine

and green biomanufacturing.

关键词

Keywords

references

Bornscheuer U T , Huisman G W , Kazlauskas R J , et al . Engineering the third wave of biocatalysis [J ] . Nature , 2012 , 485 ( 7397 ): 185 - 194 .

Yi D , Bayer T , Badenhorst C P S , et al . Recent trends in biocatalysis [J ] . Chemical Society Reviews , 2021 , 50 ( 14 ): 8003 - 8049 .

Sheldon R A , Brady D . The limits to biocatalysis: pushing the envelope [J ] . Chemical Communications , 2018 , 54 ( 48 ): 6088 - 6104 .

Packer M S , Liu D R . Methods for the directed evolution of proteins [J ] . Nature Reviews Genetics , 2015 , 16 ( 7 ): 379 - 394 .

Zhou Y , Zhu L Y , Zou P . A brief introduction to Nobel prize in chemistry 2018: harnessing the power of evolution [J ] . University Chemistry , 2019 , 34 ( 1 ): 1 - 6 .

Vaissier Welborn V , Head-Gordon T . Computational design of synthetic enzymes [J ] . Chemical Reviews , 2019 , 119 ( 11 ): 6613 - 6630 .

徐沛 , 汪卫华 , 宁洪伟 , 等 . 人工智能辅助的酶分子改造应用进展 [J ] . 生物工程学报 , 2024 , 40 ( 6 ): 1728 - 1741 .

Xu P , Wang W H , Ning H W , et al . Progress in the application of artificial intelligence-assisted molecular modification of enzymes [J ] . Chinese Journal of Biotechnology , 2024 , 40 ( 6 ): 1728 - 1741 .

Yang J , Li F Z , Arnold F H . Opportunities and challenges for machine learning-assisted enzyme engineering [J ] . ACS Central Science , 2024 , 10 ( 2 ): 226 - 241 .

Kouba P , Kohout P , Haddadi F , et al . Machine learning-guided protein engineering [J ] . ACS Catalysis , 2023 , 13 ( 21 ): 13863 - 13895 .

Wang X Y , Li A N , Li X J , et al . Empowering protein engineering through recombination of beneficial substitutions [J ] . Chemistry – A European Journal , 2024 , 30 ( 16 ): e202303889 .

Chen L , Zhang Z H , Li Z H , et al . Learning protein fitness landscapes with deep mutational scanning data from multiple sources [J ] . Cell Systems , 2023 , 14 ( 8 ): 706 - 721 .

Romero P A , Arnold F H . Exploring protein fitness landscapes by directed evolution [J ] . Nature Reviews Molecular Cell Biology , 2009 , 10 ( 12 ): 866 - 876 .

Wu Z , Jennifer Kan S B , Lewis R D , et al . Machine learning-assisted directed protein evolution with combinatorial libraries [J ] . Proceedings of the National Academy of Sciences of the United States of America , 2019 , 116 ( 18 ): 8852 - 8858 .

Fox R J , Huisman G W . Enzyme optimization: moving from blind evolution to statistical exploration of sequence–function space [J ] . Trends in Biotechnology , 2008 , 26 ( 3 ): 132 - 138 .

King R D , Sternberg M J E . Machine learning approach for the prediction of protein secondary structure [J ] . Journal of Molecular Biology , 1990 , 216 ( 2 ): 441 - 457 .

Muggleton S , King R D , Stenberg M J E . Protein secondary structure prediction using logic-based machine learning [J ] . Protein Engineering, Design and Selection , 1992 , 5 ( 7 ): 647 - 657 .

Aita T , Hamamatsu N , Nomiya Y , et al . Surveying a local fitness landscape of a protein with epistatic sites for the study of directed evolution [J ] . Biopolymers , 2002 , 64 ( 2 ): 95 - 105 .

Pires D E V , Ascher D B , Blundell T L . mCSM: predicting the effects of mutations in proteins using graph-based signatures [J ] . Bioinformatics , 2014 , 30 ( 3 ): 335 - 342 .

Folkman L , Stantic B , Sattar A , et al . EASE-MM: sequence-based prediction of mutation-induced stability changes with feature-based multiple models [J ] . Journal of Molecular Biology , 2016 , 428 ( 6 ): 1394 - 1405 .

Greenhalgh J C , Fahlberg S A , Pfleger B F , et al . Machine learning-guided acyl-ACP reductase engineering for improved in vivo fatty alcohol production [J ] . Nature Communications , 2021 , 12 : 5825 .

Matsushita T , Kishimoto S , Hara K , et al . Functional enhancement of flavin-containing monooxygenase through machine learning methodology [J ] . ACS Catalysis , 2024 , 14 ( 9 ): 6945 - 6951 .

Fox R J , Davis S C , Mundorff E C , et al . Improving catalytic function by ProSAR-driven enzyme evolution [J ] . Nature Biotechnology , 2007 , 25 ( 3 ): 338 - 344 .

Liao J , Warmuth M K , Govindarajan S , et al . Engineering proteinase K using machine learning and synthetic genes [J ] . BMC Biotechnology , 2007 , 7 ( 1 ): 16 .

LeCun Y , Bengio Y , Hinton G . Deep learning [J ] . Nature , 2015 , 521 ( 7553 ): 436 - 444 .

Lin Z M , Akin H , Rao R , et al . Evolutionary-scale prediction of atomic-level protein structure with a language model [J ] . Science , 2023 , 379 ( 6637 ): 1123 - 1130 .

Elnaggar A , Heinzinger M , Dallago C , et al . ProtTrans: toward understanding the language of life through self-supervised learning [J ] . IEEE Transactions on Pattern Analysis and Machine Intelligence , 2022 , 44 ( 10 ): 7112 - 7127 .

Luo Y N , Jiang G D , Yu T H , et al . ECNet is an evolutionary context-integrated deep learning framework for protein engineering [J ] . Nature Communications , 2021 , 12 : 5743 .

Kulmanov M , Hoehndorf R . DeepGOPlus: improved protein function prediction from sequence [J ] . Bioinformatics , 2020 , 36 ( 2 ): 422 - 429 .

Høie M H , Kiehl E N , Petersen B , et al . NetSurfP-3.0: accurate and fast prediction of protein structural features by protein language models and deep learning [J ] . Nucleic Acids Research , 2022 , 50 ( W1 ): W510 - W515 .

Bileschi M L , Belanger D , Bryant D H , et al . Using deep learning to annotate the protein universe [J ] . Nature Biotechnology , 2022 , 40 ( 6 ): 932 - 937 .

Zhou J , Troyanskaya O G . Predicting effects of noncoding variants with deep learning–based sequence model [J ] . Nature Methods , 2015 , 12 ( 10 ): 931 - 934 .

Jumper J , Evans R , Pritzel A , et al . Highly accurate protein structure prediction with AlphaFold [J ] . Nature , 2021 , 596 ( 7873 ): 583 - 589 .

Gligorijević V , Renfrew P D , Kosciolek T , et al . Structure-based protein function prediction using graph convolutional networks [J ] . Nature Communications , 2021 , 12 : 3168 .

Dauparas J , Anishchenko I , Bennett N , et al . Robust deep learning-based protein sequence design using ProteinMPNN [J ] . Science , 2022 , 378 ( 6615 ): 49 - 56 .

Lu H Y , Diaz D J , Czarnecki N J , et al . Machine learning-aided engineering of hydrolases for PET depolymerization [J ] . Nature , 2022 , 604 ( 7907 ): 662 - 667 .

Zhou B X , Zheng L R , Wu B H , et al . Protein engineering with lightweight graph denoising neural networks [J ] . Journal of Chemical Information and Modeling , 2024 , 64 ( 9 ): 3650 - 3661 .

Tian Y , Zhang D C , Xing H D , et al . Computational glycosyltransferases masked deoxynivalenol toxicity and halted FHB spread in wheat grains [J ] . Journal of Advanced Research , 2026 , 83 : 129 - 139 .

Jiang L , Sun S Z , Qi B Q , et al . Chem3DLLM: 3D multimodal large language models for chemistry [EB/OL ] . arXiv : 2508 . 10696 v 1 , 2025 . https://arxiv.org/html/2508.10696v1 https://arxiv.org/html/2508.10696v1 .

崔颖璐 , 吴边 . 符合工程化需求的生物元件设计 [J ] . 中国科学院院刊 , 2018 , 33 ( 11 ): 1150 - 1157 .

Cui Y L , Wu B . Biological components design for engineering requirements [J ] . Bulletin of the Chinese Academy of Sciences , 2018 , 33 ( 11 ): 1150 - 1157 .

Meng S Q , Li Z Y , Zhang P , et al . Deep learning guided enzyme engineering of Thermobifida fusca cutinase for increased PET depolymerization [J ] . Chinese Journal of Catalysis , 2023 , 50 : 229 - 238 .

Cao H L , Wang J X , He L P , et al . DeepDDG: predicting the stability change of protein point mutations using neural networks [J ] . Journal of Chemical Information and Modeling , 2019 , 59 ( 4 ): 1508 - 1514 .

Dieckhaus H , Brocidiacono M , Randolph N Z , et al . Transfer learning to leverage larger datasets for improved prediction of protein stability changes [J ] . Proceedings of the National Academy of Sciences of the United States of America , 2024 , 121 ( 6 ): e2314853121 .

Zakary S , Oyewusi H , Huyop F . Dehalogenases for pollutant degradation in brief: a mini review [J ] . Journal of Tropical Life Science , 2021 , 11 ( 1 ): 17 - 24 .

Ryu J Y , Kim H U , Lee S Y . Deep learning enables high-quality and high-throughput prediction of enzyme commission numbers [J ] . Proceedings of the National Academy of Sciences of the United States of America , 2019 , 116 ( 28 ): 13996 - 14001 .

Yu T H , Cui H Y , Li J C , et al . Enzyme function prediction using contrastive learning [J ] . Science , 2023 , 379 ( 6639 ): 1358 - 1363 .

Repecka D , Jauniskis V , Karpus L , et al . Expanding functional protein sequence spaces using generative adversarial networks [J ] . Nature Machine Intelligence , 2021 , 3 ( 4 ): 324 - 333 .

Çarklı Yavuz B , Yurtay N , Ozkan O . Prediction of protein secondary structure with clonal selection algorithm and multilayer perceptron [J ] . IEEE Access , 2018 , 6 : 45256 - 45261 .

Ferruz N , Schmidt S , Höcker B . ProtGPT2 is a deep unsupervised language model for protein design [J ] . Nature Communications , 2022 , 13 : 4348 .

Biswas S , Khimulya G , Alley E C , et al . Low-N protein engineering with data-efficient deep learning [J ] . Nature Methods , 2021 , 18 ( 4 ): 389 - 396 .

Shroff R , Cole A W , Diaz D J , et al . Discovery of novel gain-of-function mutations guided by structure-based deep learning [J ] . ACS Synthetic Biology , 2020 , 9 ( 11 ): 2927 - 2935 .

Müller A T , Hiss J A , Schneider G . Recurrent neural network model for constructive peptide design [J ] . Journal of Chemical Information and Modeling , 2018 , 58 ( 2 ): 472 - 479 .

Wu M Q , Yang Y X , Wang H , et al . A deep learning method to more accurately recall known lysine acetylation sites [J ] . BMC Bioinformatics , 2019 , 20 ( 1 ): 49 .

Xie Y B , Luo X T , Li Y P , et al . DeepNitro: prediction of protein nitration and nitrosylation sites by deep learning [J ] . Genomics , Proteomics & Bioinformatics, 2018 , 16 ( 4 ): 294 - 306 .

Semwal R , Aier I , Tyagi P , et al . DeEPn: a deep neural network based tool for enzyme functional annotation [J ] . Journal of Biomolecular Structure and Dynamics , 2021 , 39 ( 8 ): 2733 - 2743 .

Kao H W , Lu W L , Ho M R , et al . Robust design of effective allosteric activators for Rsp5 E3 ligase using the machine learning tool ProteinMPNN [J ] . ACS Synthetic Biology , 2023 , 12 ( 8 ): 2310 - 2319 .

Li F R , Yuan L , Lu H Z , et al . Deep learning-based kcat prediction enables improved enzyme-constrained model reconstruction [J ] . Nature Catalysis , 2022 , 5 ( 8 ): 662 - 672 .

Boorla V S , Maranas C D . CatPred: a comprehensive framework for deep learning in vitro enzyme kinetic parameters [J ] . Nature Communications , 2025 , 16 : 2072 .

Wang C , Zou Q . Prediction of protein solubility based on sequence physicochemical patterns and distributed representation information with DeepSoluE [J ] . BMC Biology , 2023 , 21 ( 1 ): 12 .

Chen J W , Zheng S J , Zhao H Y , et al . Structure-aware protein solubility prediction from sequence through graph convolutional network and predicted contact map [J ] . Journal of Cheminformatics , 2021 , 13 ( 1 ): 7 .

Anishchenko I , Pellock S J , Chidyausiku T M , et al . De novo protein design by deep network hallucination [J ] . Nature , 2021 , 600 ( 7889 ): 547 - 552 .

Zhang C H , Xu Z Y , Lin K , et al . CycleDesigner: leveraging CycRFdiffusion and HighFold to design cyclic peptide binders for specific targets [J ] . Journal of Chemical Information and Modeling , 2025 , 65 ( 12 ): 6155 - 6165 .

Butcher J , Krishna R , Mitra R , et al . De novo design of all-atom biomolecular interactions with RFdiffusion3 [PP/OL ] . bioRxiv ( 2025-11-19 )[ 2026-01-04 ] . http://doi.org/10.1101/2025.09.18. 676967 http://doi.org/10.1101/2025.09.18.676967 .

Vázquez Torres S , Leung P J Y , Venkatesh P , et al . De novo design of high-affinity binders of bioactive helical peptides [J ] . Nature , 2024 , 626 ( 7998 ): 435 - 442 .

Watson J L , Juergens D , Bennett N R , et al . De novo design of protein structure and function with RFdiffusion [J ] . Nature , 2023 , 620 ( 7976 ): 1089 - 1100 .

Singh N , Lane S , Yu T H , et al . A generalized platform for artificial intelligence-powered autonomous enzyme engineering [J ] . Nature Communications , 2025 , 16 : 5648 .

Lai H , Wang L Y , Qian R Y , et al . Interformer: an interaction-aware model for protein-ligand docking and affinity prediction [J ] . Nature Communications , 2024 , 15 : 10223 .

Luttens A , Cabeza de Vaca I , Sparring L , et al . Rapid traversal of vast chemical space using machine learning-guided docking screens [J ] . Nature Computational Science , 2025 , 5 ( 4 ): 301 - 312 .

Gao K Y , Pei Q Z , Zhang G B , et al . FABind+: enhancing molecular docking through improved pocket prediction and pose generation [C ] // Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining . ACM , 2025 : 330 - 341 .

Luo D , Qu X Y , Lu D X , et al . Ligand-conditioned side chain packing for flexible molecular docking [J ] . Journal of Chemical Theory and Computation , 2025 , 21 ( 3 ): 1494 - 1505 .

Hollingsworth S A , Dror R O . Molecular dynamics simulation for all [J ] . Neuron , 2018 , 99 ( 6 ): 1129 - 1143 .

Lewis S , Hempel T , Jiménez-Luna J , et al . Scalable emulation of protein equilibrium ensembles with generative deep learning [J ] . Science , 2025 , 389 ( 6761 ): eadv9817 .

Osuna S , Jiménez-Osés G , Noey E L , et al . Molecular dynamics explorations of active site structure in designed and evolved enzymes [J ] . Accounts of Chemical Research , 2015 , 48 ( 4 ): 1080 - 1089 .

Platero-Rochart D , Krivobokova T , Gastegger M , et al . Prediction of enzyme catalysis by computing reaction energy barriers via steered QM/MM molecular dynamics simulations and machine learning [J ] . Journal of Chemical Information and Modeling , 2023 , 63 ( 15 ): 4623 - 4632 .

Madushanka A , Laird E , Clark C , et al . SmartCADD: AI-QM empowered drug discovery platform with explainability [J ] . Journal of Chemical Information and Modeling , 2024 , 64 ( 17 ): 6799 - 6813 .

Cheng F , Zhu L L , Schwaneberg U . Directed evolution 2.0: improving and deciphering enzyme properties [J ] . Chemical Communications , 2015 , 51 ( 48 ): 9760 - 9772 .

Cui H Y , Davari M D , Schwaneberg U . Recombination of compatible substitutions by 2GenReP and InSiReP [M ] // Enzyme Engineering . New York, NY : Springer US , 2021 : 71 - 81 .

Cui H Y , Cao H , Cai H Y , et al . Computer-assisted recombination (CompassR) teaches us how to recombine beneficial substitutions from directed evolution campaigns [J ] . Chemistry — A European Journal , 2020 , 26 ( 3 ): 643 - 649 .

Siedhoff N E , Schwaneberg U , Davari M D . Machine learning-assisted enzyme engineering [M ] // Methods in Enzymology . Amsterdam : Elsevier , 2020 : 281 - 315 .

Listov D , Goverde C A , Correia B E , et al . Opportunities and challenges in design and optimization of protein function [J ] . Nature Reviews Molecular Cell Biology , 2024 , 25 ( 8 ): 639 - 653 .

Weigmann K F G , Heijl S , Vroling B , et al . Navigating the sequence-function landscape: AI-driven discovery of unseen and synergistic mutations in an amine transaminase [J ] . ACS Catalysis , 2025 , 15 ( 17 ): 15121 - 15131 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Enlightenment of general AI to chemical engineering AGI: construction of synergy system integrating data, computing power, tools, and mechanisms

Non-natural redox cofactors empowered biomanufacturing

Understanding pyrolysis process of polyethylene by combined method of molecular-level kinetic model with machine learning

Advances in enzyme self-immobilization mediated by protein nanocages

A review of oxide/metal inverse catalysts for catalytic CO2 hydrogenation

Related Author

MENG Shuaiqi

GU Ziyi

WANG Xiangru

NIU Yingchun

WANG Yufei

ZHOU Tianhang

WANG Xueying

ZHOU Yongjin

Related Institution

State Key Laboratory of Heavy Oil, China University of Petroleum

Division of Biotechnology, Dalian Institute of Chemical Physics, CAS

School of Bioengineering, Dalian University of Technology

Department of Chemical Engineering, Tsinghua University

China Petroleum Planning and Engineering Institute (CPPEI), China National Petroleum Corporation

⁰