Generative artificial intelligence (AI) models trained on natural protein sequences have been used to design functional enzymes. However, their ability to predict individual reaction steps in enzyme catalysis remains unclear, limiting the potential use of sequence information for enzyme engineering. In this study, we demonstrated that sequence information can predict the rate of the SN2 step of a haloalkane dehalogenase using a generative maximum-entropy (MaxEnt) model. We then designed lower-order protein variants of haloalkane dehalogenase using the model. Kinetic measurements confirmed the successful design of protein variants that enhance catalytic activity, above that of the wild type, in the overall reaction and in particular in the SN2 step. On the simulation side, we provided molecular insights into these designs for the SN2 step using the empirical valence bond (EVB) and metadynamics simulations. The EVB calculations showed activation barriers consistent with experimental reaction rates, while examining the effect of amino acid replacements on the electrostatic effect on the activation barrier and the consequence of water penetration, as well as the extent of ground state destabilization/stabilization. Metadynamics simulations emphasize the importance of the substrate positioning in enzyme catalysis. Overall, our AI-guided approach successfully enabled the design of a variant with a faster rate for the SN2 step than the wild-type enzyme, despite haloalkane dehalogenase being extensively optimized through natural evolution.

Department of Chemistry University of Southern California Los Angeles California 90089 United States

Department of Medicinal Chemistry University of Florida Gainesville Florida 32610 United States

International Clinical Research Center St Anne's University Hospital Brno Pekarska 53 Brno 656 91 Czech Republic

Loschmidt Laboratories Department of Experimental Biology and RECETOX Faculty of Science Masaryk University Kamenice 5 Brno 625 00 Czech Republic

Zobrazit více v PubMed

Yang KK; Wu Z; Arnold FH Machine-Learning-Guided Directed Evolution for Protein Engineering. Nat. Methods 2019, 16 (8), 687–694. PubMed

Lin Z; Akin H; Rao R; Hie B; Zhu Z; Lu W; Smetanin N; Verkuil R; Kabeli O; Shmueli Y; dos Santos Costa A; Fazel-Zarandi M; Sercu T; Candido S; Rives A Evolutionary-Scale Prediction of Atomic-Level Protein Structure with a Language Model. Science 2023, 379 (6637), 1123–1130. PubMed

Hopf TA; Ingraham JB; Poelwijk FJ; Schärfe CPI; Springer M; Sander C; Marks DS Mutation Effects Predicted from Sequence Co-Variation. Nat. Biotechnol 2017, 35, 128–135. PubMed PMC

Bond-Taylor S; Leach A; Long Y; Willcocks CG Deep Generative Modelling: A Comparative Review of VAEs, GANs, Normalizing Flows, Energy-Based and Autoregressive Models. IEEE Trans. Pattern Anal. Mach. Intell 2022, 44 (11), 7327–7347. PubMed

Xie WJ; Asadi M; Warshel A Enhancing Computational Enzyme Design by a Maximum Entropy Strategy. Proc. Natl. Acad. Sci. U.S.A 2022, 119 (7), No. e2122355119. PubMed PMC

Giessel A; Dousis A; Ravichandran K; Smith K; Sur S; McFadyen I; Zheng W; Licht S Therapeutic Enzyme Engineering Using a Generative Neural Network. Sci. Rep 2022, 12 (1), No. 1536. PubMed PMC

Repecka D; Jauniskis V; Karpus L; Rembeza E; Rokaitis I; Zrimec J; Poviloniene S; Laurynenas A; Viknander S; Abuajwa W; Savolainen O; Meskys R; Engqvist MKM; Zelezniak A Expanding Functional Protein Sequence Spaces Using Generative Adversarial Networks. Nat. Mach. Intell 2021, 3, 324–333.

Hawkins-Hooker A; Depardieu F; Baur S; Couairon G; Chen A; Bikard D Generating Functional Protein Variants with Variational Autoencoders. PLOS Comput. Biol 2021, 17 (2), No. e1008736. PubMed PMC

Russ WP; Figliuzzi M; Stocker C; Barrat-Charlaix P; Socolich M; Kast P; Hilvert D; Monasson R; Cocco S; Weigt M; Ranganathan R An Evolution-Based Model for Designing Chorismate Mutase Enzymes. Science 2020, 369 (6502), 440–445. PubMed

Xie WJ; Warshel A Harnessing Generative AI to Decode Enzyme Catalysis and Evolution for Enhanced Engineering. Natl. Sci. Rev 2023, 10, No. nwad331. PubMed PMC

Prokop Z; Monincová M; Chaloupková R; Klvaňa M; Nagata Y; Janssen DB; Damborský J Catalytic Mechanism of the Haloalkane Dehalogenase LinB from Sphingomonas paucimobilis UT26*. J. Biol. Chem 2003, 278 (46), 45094–45100. PubMed

Franken SM; Rozeboom HJ; Kalk KH; Dijkstra BW Crystal Structure of Haloalkane Dehalogenase: An Enzyme to Detoxify Halogenated Alkanes. EMBO J. 1991, 10 (6), 1297–1302. PubMed PMC

Verschueren KHG; Seljee F; Kalk KH; et al. Crystallographic Analysis of the Catalytic Mechanism of Haloalkane Dehalogenase. Nature 1993, 363, 693–698. PubMed

Schanstra JP; Ridder IS; Heimeriks GJ; Rink R; Poelarends GJ; Kalk KH; Dijkstra BW; Janssen DB Kinetic Characterization and X-Ray Structure of a Mutant of Haloalkane Dehalogenase with Higher Catalytic Activity and Modified Substrate Range. Biochemistry 1996, 35 (40), 13186–13195. PubMed

Schanstra JP; Ridder A; Kingma J; Janssen DB Influence of Mutations of Val226 on the Catalytic Rate of Haloalkane Dehalogenase. Protein Eng., Des. Sel 1997, 10 (1), 53–61. PubMed

Krooshof GH; Ridder IS; Tepper AWJW; Vos GJ; Rozeboom HJ; Kalk KH; Dijkstra BW; Janssen DB Kinetic Analysis and X-Ray Structure of Haloalkane Dehalogenase with a Modified Halide-Binding Site. Biochemistry 1998, 37 (43), 15013–15023. PubMed

Boháč M; Nagata Y; Prokop Z; Prokop M; Monincová M; Tsuda M; Koča J; Damborský J Halide-Stabilizing Residues of Haloalkane Dehalogenases Studied by Quantum Mechanic Calculations and Site-Directed Mutagenesis. Biochemistry 2002, 41 (48), 14272–14280. PubMed

Xie WJ; Liu D; Wang X; Zhang A; Wei Q; Nandi A; Dong S; Warshel A Enhancing Luciferase Activity and Stability through Generative Modeling of Natural Enzyme Sequences. Proc. Natl. Acad. Sci. U.S.A 2023, 120 (48), No. e2312848120. PubMed PMC

Schindler JF; Naranjo PA; Honaberger DA; Chang C-H; Brainard JR; Vanderberg LA; Unkefer CJ Haloalkane Dehalogenases: Steady-State Kinetics and Halide Inhibition. Biochemistry 1999, 38 (18), 5772–5778. PubMed

Kamerlin SCL; Warshel A The Empirical Valence Bond Model: Theory and Applications. WIREs Comput. Mol. Sci 2011, 1 (1), 30–45.

Warshel A; Weiss RM An Empirical Valence Bond Approach for Comparing Reactions in Solutions and in Enzymes. J. Am. Chem. Soc 1980, 102 (20), 6218–6226.

Schopf P; Warshel A Validating Computer Simulations of Enantioselective Catalysis; Reproducing the Large Steric and Entropic Contributions in Candida Antarctica Lipase B. Proteins: Struct., Funct., Bioinf 2014, 82 (7), 1387–1399. PubMed PMC

Singh N; Warshel A Absolute Binding Free Energy Calculations: On the Accuracy of Computational Scoring of Protein−Ligand Interactions. Proteins: Struct., Funct., Bioinf 2010, 78 (7), 1705–1723. PubMed PMC

Wilkins RS; Lund BA; Isaksen GV; Åqvist J; Brandsdal BO. Accurate Computation of Thermodynamic Activation Parameters in the Chorismate Mutase Reaction from Empirical Valence Bond Simulations. J. Chem. Theory Comput 2024, 20 (1), 451–458. PubMed PMC

Nandi A; Zhang A; Arad E; Jelinek R; Warshel A Assessing the Catalytic Role of Native Glucagon Amyloid Fibrils. ACS Catal. 2024, 14 (7), 4656–4664. PubMed PMC

Warshel A; Sussman F; Hwang J-K Evaluation of Catalytic Free Energies in Genetically Modified Proteins. J. Mol. Biol 1988, 201 (1), 139–159. PubMed

Jindal G; Ramachandran B; Bora RP; Warshel A Exploring the Development of Ground-State Destabilization and Transition-State Stabilization in Two Directed Evolution Paths of Kemp Eliminases. ACS Catal. 2017, 7 (5), 3301–3305. PubMed PMC

Jindal G; Slanska K; Kolev V; Damborsky J; Prokop Z; Warshel A Exploring the Challenges of Computational Enzyme Design by Rebuilding the Active Site of a Dehalogenase. Proc. Natl. Acad. Sci. U.S.A 2019, 116 (2), 389–394. PubMed PMC

Mondal D; Kolev V; Warshel A Combinatorial Approach for Exploring Conformational Space and Activation Barriers in Computer-Aided Enzyme Design. ACS Catal. 2020, 10, 6002–6012. PubMed PMC

Olsson MHM; Warshel A Solute Solvent Dynamics and Energetics in Enzyme Catalysis: The S PubMed

Warshel A; Sharma PK; Kato M; Xiang Y; Liu H; Olsson MHM Electrostatic Basis for Enzyme Catalysis. Chem. Rev 2006, 106 (8), 3210–3235. PubMed

Damborský J; Koča J Analysis of the Reaction Mechanism and Substrate Specificity of Haloalkane Dehalogenases by Sequential and Structural Comparisons. Protein Eng. Des. Sel 1999, 12 (11), 989–998. PubMed

Barducci A; Bussi G; Parrinello M Well-Tempered Metadynamics: A Smoothly Converging and Tunable Free-Energy Method. Phys. Rev. Lett 2008, 100 (2), No. 020603. PubMed

Shurki A; Štrajbl M; Villà J; Warshel A How Much Do Enzymes Really Gain by Restraining Their Reacting Fragments? J. Am. Chem. Soc 2002, 124 (15), 4097–4107. PubMed

Wijma HJ; Marrink SJ; Janssen DB Computationally Efficient and Accurate Enantioselectivity Modeling by Clusters of Molecular Dynamics Simulations. J. Chem. Inf. Model 2014, 54 (7), 2079–2092. PubMed

Janssen DB; Stucki G Perspectives of Genetically Engineered Microbes for Groundwater Bioremediation. Environ. Sci.: Process Impacts 2020, 22 (3), 487–499. PubMed

Engineering Dehalogenase Enzymes Using Variational Autoencoder-Generated Latent Spaces and Microfluidics