Application of artificial intelligence in enzyme engineering

doi:10.16178/j.issn.0528-9017.20250132

Abstract

Abstract:

As an efficient and specific biocatalyst, enzymes are widely used in industry, medicine and environmental protection. However, the limitations of natural enzymes in terms of stability, catalytic activity, and selectivity limit their industrial applications. Enzyme engineering mainly adopts a variety of strategies such as rational design, directed evolution, semi-rational design, and artificial intelligence-aided design. Among them, directed evolution simulated the process of natural selection and screened out enzyme mutants with better performance. The rational design is based on the known structure and active site of the enzyme and is precisely modified. Although traditional enzyme engineering methods have achieved some success, they face challenges such as large sequence space, high experimental cost and scarce data. In recent years, the introduction of artificial intelligence technology has brought revolutionary breakthroughs to enzyme engineering. AI technology has shown significant advantages in protein structure prediction, function optimization, and mutant screening, which greatly expands the ability to explore enzyme sequence space and improves the efficiency of enzyme molecular modification. However, the application of AI technology in enzyme engineering still faces challenges such as data scarcity, model generalization, and experimental verification efficiency. In the future, with the improvement of computing power and the advancement of experimental technology, AI technology is expected to achieve higher precision and wider application in enzyme design, providing strong support for green industry and sustainable development.

Key words: enzyme engineering, artificial intelligence, machine learning, deep learning

CLC Number:

Q814
TP18

WU Jianxiong, BAO Yufeng. Application of artificial intelligence in enzyme engineering[J]. Journal of Zhejiang Agricultural Sciences, 2025, 66(6): 1542-1550.

Figures/Tables 3

References 22

[1]	KOHN W D, HODGES R S. De novo design of α-helical coiled coils and bundles: models for the development of protein-design principles[J]. Trends in Biotechnology, 1998, 16(9): 379-389.
[2]	SIMONS K T, BONNEAU R, RUCZINSKI I, et al. Ab initio protein structure prediction of CASP Ⅲ targets using ROSETTA[J]. Proteins: Structure, Function, and Genetics, 1999, 37(S3): 171-176.
[3]	YANG Y, NIROULA A, SHEN B R, et al. PON-Sol: prediction of effects of amino acid substitutions on protein solubility[J]. Bioinformatics, 2016, 32(13): 2032-2034.
[4]	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.
[5]	HUANG L T, GROMIHA M M, HO S Y. iPTREE-STAB: interpretable decision tree based method for predicting protein stability changes upon mutations[J]. Bioinformatics, 2007, 23(10): 1292-1293.
[6]	KOSKINEN P, TÖRÖNEN P, NOKSO-KOIVISTO J, et al. PANNZER: high-throughput functional annotation of uncharacterized proteins in an error-prone environment[J]. Bioinformatics, 2015, 31(10): 1544-1552.
[7]	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.
[8]	LU H, DIAZ DJ, CZARNECKI NJ, et al. Machine learning aided engineering of hydrolases for PET depolymerization[J]. Nature, 2022, 604(7907): 662-667.
[9]	ROMERO P A, KRAUSE A, ARNOLD F H. Navigating the protein fitness landscape with Gaussian processes[J]. Proceedings of the National Academy of Sciences of the United States of America, 2013, 110(3): E193-E201.
[10]	CADET F, FONTAINE N, LI G Y, et al. A machine learning approach for reliable prediction of amino acid interactions and its application in the directed evolution of enantioselective enzymes[J]. Scientific Reports, 2018, 8: 16757.
[11]	LANDWEHR G M, BOGART J W, MAGALHAES C, et al. Accelerated enzyme engineering by machine-learning guided cell-free expression[J]. Nature Communications, 2025, 16: 865.
[12]	WANG X R, YIN X D, JIANG D J, et al. Multi-modal deep learning enables efficient and accurate annotation of enzymatic active sites[J]. Nature Communications, 2024, 15: 7348.
[13]	YEH A H, NORN C, KIPNIS Y, et al. De novo design of luciferases using deep learning[J]. Nature, 2023, 614(7949): 774-780.
[14]	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.
[15]	NORN C, WICKY B I M, JUERGENS D, et al. Protein sequence design by conformational landscape optimization[J]. Proceedings of the National Academy of Sciences of the United States of America, 2021, 118(11): e2017228118.
[16]	YANG J Y, ANISHCHENKO I, PARK H, et al. Improved protein structure prediction using predicted interresidue orientations[J]. Proceedings of the National Academy of Sciences of the United States of America, 2020, 117(3): 1496-1503.
[17]	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.
[18]	BAEK M, DIMAIO F, ANISHCHENKO I, et al. Accurate prediction of protein structures and interactions using a three-track neural network[J]. Science, 2021, 373,871-876.
[19]	WATSON J L, JUERGENS D, BENNETT N R, et al. De novo design of protein structure and function with RF diffusion[J]. Nature, 2023, 620(7976): 1089-1100.
[20]	WANG W K, FENG C J, HAN R M, et al. trRosettaRNA: automated prediction of RNA 3D structure with transformer network[J]. Nature Communications, 2023, 14: 7266.
[21]	SHEN T, HU Z H, SUN S Q, et al. Accurate RNA 3D structure prediction using a language model-based deep learning approach[J]. Nature Methods, 2024, 21(12): 2287-2298.
[22]	KAGAYA Y, ZHANG Z C, IBTEHAZ N, et al. NuFold: end-to-end approach for RNA tertiary structure prediction with flexible nucleobase center representation[J]. Nature Communications, 2025, 16: 881.