Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2025 Jul;64(27):e202507031.
doi: 10.1002/anie.202507031. Epub 2025 Jun 1.

AI.zymes: A Modular Platform for Evolutionary Enzyme Design

Lucas P Merlicek  1 , Jannik Neumann  1 , Abbie Lear  2 , Vivian Degiorgi  1 , Moor M de Waal  1 , Tudor-Stefan Cotet  1 , Adrian J Mulholland  2 , H Adrian Bunzel  1   2
Affiliations

AI.zymes: A Modular Platform for Evolutionary Enzyme Design

Lucas P Merlicek et al. Angew Chem Int Ed Engl. 2025 Jul.

Abstract

The ability to create new-to-nature enzymes would substantially advance bioengineering, medicine, and the chemical industry. Despite recent breakthroughs in protein design and structure prediction, designing novel biocatalysts remains challenging. Here, we present AI.zymes, a modular platform integrating cutting-edge protein engineering algorithms within an evolutionary framework (https://github.com/bunzela/AIzymes). By combining bioengineering tools such as Rosetta, ESMFold, ProteinMPNN, and FieldTools in iterative rounds of design and selection, AI.zymes can optimize a broad range of catalytically relevant properties. In addition to enhancing transition state affinity and protein stability, AI.zymes can also improve properties that are not targeted by the employed design algorithms. For instance, AI.zymes can enhance electrostatic catalysis by iteratively selecting variants with stronger catalytic electric fields. Benchmarking AI.zymes on the promiscuous Kemp eliminase activity of ketosteroid isomerase led to a 7.7-fold activity increase after experimentally testing just 7 variants. Due to its modularity, AI.zymes can readily incorporate emerging design algorithms, paving the way for a unifying framework for enzyme design.

Keywords: Biocatalysis; Computational design; Directed evolution; Electric fields; Enzyme design.

PubMed Disclaimer

References

    1. R. Buller, S. Lutz, R. J. Kazlauskas, R. Snajdrova, J. C. Moore, U. T. Bornscheuer, Science 2023, 382, eadh8615.
    1. E. L. Bell, W. Finnigan, S. P. France, A. P. Green, M. A. Hayes, L. J. Hepworth, S. L. Lovelock, H. Niikura, S. Osuna, E. Romero, K. S. Ryan, N. J. Turner, S. L. Flitsch, Nat. Rev. Methods Primers 2021, 1, 46.
    1. H. A. Bunzel, J. L. R. Anderson, A. J. Mulholland, Curr. Opin. Struct. Biol. 2021, 67, 212–218.
    1. F. H. Arnold, Angew. Chem. Int. Ed. 2018, 57, 4143–4148.
    1. M. S. Packer, D. R. Liu, Nat. Rev. Genet. 2015, 16, 379–394.

LinkOut - more resources