Deep Learning-Based Self-Adaptive Evolution of Enzymes DOI Creative Commons
Shuiqin Jiang, Dong Yi

Pharmaceutical Fronts, Journal Year: 2024, Volume and Issue: 06(03), P. e252 - e264

Published: Sept. 1, 2024

Abstract Biocatalysis has been widely used to prepare drug leads and intermediates. Enzymatic synthesis advantages, mainly in terms of strict chirality regional selectivity compared with chemical methods. However, the enzymatic properties wild-type enzymes may or not meet requirements for biopharmaceutical applications. Therefore, protein engineering is required improve their catalytic activities. Thanks advances algorithmic models accumulation immense biological data, artificial intelligence can provide novel approaches functional evolution enzymes. Deep learning advantage functions that predict previously unknown sequences. learning-based computational algorithms intelligently navigate sequence space reduce screening burden during evolution. Thus, intelligent design combined laboratory a powerful potentially versatile strategy developing functions. Herein, we introduce summarize deep-learning-assisted enzyme adaptive strategies based on recent studies application deep Altogether, developments technology data characterization functions, become tool future.

Language: Английский

Microbes Saving Lives and Reducing Suffering DOI Creative Commons
Kenneth N. Timmis, Zeynep Ceren Karahan, Juan L. Ramos

et al.

Microbial Biotechnology, Journal Year: 2025, Volume and Issue: 18(1)

Published: Jan. 1, 2025

Language: Английский

Citations

3
Excellent Laccase Mimic Activity of Cu-Melamine and Its Applications in the Degradation of Congo Red DOI
Siyuan Chai, Enze Huang, Jinsheng Zeng

et al.

Applied Biochemistry and Biotechnology, Journal Year: 2025, Volume and Issue: unknown

Published: Feb. 1, 2025

Language: Английский

Citations

2
Practical Machine Learning-Assisted Design Protocol for Protein Engineering: Transaminase Engineering for the Conversion of Bulky Substrates DOI
Marian J. Menke, Yu‐Fei Ao, Uwe T. Bornscheuer

et al.

ACS Catalysis, Journal Year: 2024, Volume and Issue: 14(9), P. 6462 - 6469

Published: April 12, 2024

Protein engineering is essential for improving the catalytic performance of enzymes applications in biocatalysis, which machine learning provides an emerging approach variant design. Transaminases are powerful biocatalysts stereoselective synthesis chiral amines but one major challenge their limited substrate scope. We present a general and practical design protocol protein to combine advantages three strategies, including directed evolution, rational design, learning, demonstrate application transaminases with higher activity toward bulky substrates. A high-quality data set was obtained by selected key positions, then applied create model transaminase activity. This data-assisted optimized variants, showed improved (up 3-fold over parent) substrates, maintaining enantioselectivity starting enzyme scaffold as well enantiomeric excess >99%ee).

Language: Английский

Citations

13
A non-canonical nucleophile unlocks a new mechanistic pathway in a designed enzyme DOI Creative Commons

Amy E. Hutton,

Jake Foster,

Rebecca Crawshaw

et al.

Nature Communications, Journal Year: 2024, Volume and Issue: 15(1)

Published: March 4, 2024

Abstract Directed evolution of computationally designed enzymes has provided new insights into the emergence sophisticated catalytic sites in proteins. In this regard, we have recently shown that a histidine nucleophile and flexible arginine can work synergy to accelerate Morita-Baylis-Hillman (MBH) reaction with unrivalled efficiency. Here, show replacing non-canonical N δ -methylhistidine (MeHis23) leads substantially altered evolutionary outcome which Arg124 been abandoned. Instead, Glu26 emerged, mediates rate-limiting proton transfer step deliver an enzyme (BH MeHis 1.8) is more than order magnitude active our earlier MBHase. Interestingly, although MeHis23 His substitution BH 1.8 reduces activity by 4-fold, resulting containing variant still potent MBH biocatalyst. However, analysis trajectory reveals was crucial early stages engineering unlock mechanistic pathway. This study demonstrates how even subtle perturbations key elements lead vastly different outcomes, solutions complex chemical transformations.

Language: Английский

Citations

12
Data‐Driven Protein Engineering for Improving Catalytic Activity and Selectivity DOI Creative Commons
Yu‐Fei Ao,

Mark Dörr,

Marian J. Menke

et al.

ChemBioChem, Journal Year: 2023, Volume and Issue: 25(3)

Published: Nov. 29, 2023

Abstract Protein engineering is essential for altering the substrate scope, catalytic activity and selectivity of enzymes applications in biocatalysis. However, traditional approaches, such as directed evolution rational design, encounter challenge dealing with experimental screening process a large protein mutation space. Machine learning methods allow approximation fitness landscapes identification patterns using limited data, thus providing new avenue to guide campaigns. In this concept article, we review machine models that have been developed assess enzyme‐substrate‐catalysis performance relationships aiming improve through data‐driven engineering. Furthermore, prospect future development field provide additional strategies tools achieving desired activities selectivities.

Language: Английский

Citations

22
Computational design of highly active de novo enzymes DOI Creative Commons
M. J. BRAUN, Adrian Tripp,

Morakot Chakatok

et al.

bioRxiv (Cold Spring Harbor Laboratory), Journal Year: 2024, Volume and Issue: unknown

Published: Aug. 3, 2024

Custom designed enzymes can further enhance the use of biocatalysts in industrial biotransformations, thereby helping to tackle biotechnological challenges 21st century. We present rotamer inverted fragment finder - diffusion (Riff-Diff) a hybrid machine learning and atomistic modeling strategy for scaffolding catalytic arrays de novo protein backbones with custom substrate pockets. used Riff-Diff scaffold tetrad capable efficiently catalyzing retro-aldol reaction. Functional designs exhibit high fold diversity, pockets similar natural enzymes. Some thus generated show activities rivaling those optimized by in-vitro evolution. The design can, principle, be applied any catalytically competent amino acid constellation. These findings are paving way address factors practical applicability catalysts processes shed light on fundamental principles enzyme catalysis.

Language: Английский

Citations

8
The Development and Opportunities of Predictive Biotechnology DOI Creative Commons
Bettina M. Nestl, Bernd A. Nebel, Verena Resch

et al.

ChemBioChem, Journal Year: 2024, Volume and Issue: 25(13)

Published: May 7, 2024

Recent advances in bioeconomy allow a holistic view of existing and new process chains enable novel production routines continuously advanced by academia industry. All this progress benefits from growing number prediction tools that have found their way into the field. For example, automated genome annotations, for building model structures proteins, structural protein methods such as AlphaFold2

Language: Английский

Citations

6
Transition Path Sampling Study of Engineered Enzymes That Catalyze the Morita–Baylis–Hillman Reaction: Why Is Enzyme Design so Difficult? DOI
Sree Ganesh Balasubramani, Kseniia Korchagina, Steven D. Schwartz

et al.

Journal of Chemical Information and Modeling, Journal Year: 2024, Volume and Issue: 64(6), P. 2101 - 2111

Published: March 7, 2024

It is hoped that artificial enzymes designed in laboratories can be efficient alternatives to chemical catalysts have been used synthesize organic molecules. However, the design of challenging and requires a detailed molecular-level analysis understand mechanism they promote order variants. In this study, we computationally investigate proficient Morita–Baylis–Hillman developed using combination computational directed evolution. The powerful transition path sampling method coupled with in-depth post-processing has successfully elucidate different pathways, states, protein dynamics, free energy barriers reactions catalyzed by such laboratory-optimized enzymes. This research provides an explanation for how modifications enzyme affect its catalytic activity ways are not predictable static algorithms.

Language: Английский

Citations

5
Revolutionizing Molecular Design for Innovative Therapeutic Applications through Artificial Intelligence DOI Creative Commons

Ahrum Son,

Jongham Park, Woojin Kim

et al.

Molecules, Journal Year: 2024, Volume and Issue: 29(19), P. 4626 - 4626

Published: Sept. 29, 2024

The field of computational protein engineering has been transformed by recent advancements in machine learning, artificial intelligence, and molecular modeling, enabling the design proteins with unprecedented precision functionality. Computational methods now play a crucial role enhancing stability, activity, specificity for diverse applications biotechnology medicine. Techniques such as deep reinforcement transfer learning have dramatically improved structure prediction, optimization binding affinities, enzyme design. These innovations streamlined process allowing rapid generation targeted libraries, reducing experimental sampling, rational tailored properties. Furthermore, integration approaches high-throughput techniques facilitated development multifunctional novel therapeutics. However, challenges remain bridging gap between predictions validation addressing ethical concerns related to AI-driven This review provides comprehensive overview current state future directions engineering, emphasizing their transformative potential creating next-generation biologics advancing synthetic biology.

Language: Английский

Citations

5
Using residue interaction networks to understand protein function and evolution and to engineer new proteins DOI Creative Commons
Dariia Yehorova, Bruno Di Geronimo, Michael Robinson

et al.

Current Opinion in Structural Biology, Journal Year: 2024, Volume and Issue: 89, P. 102922 - 102922

Published: Sept. 26, 2024

Language: Английский

Citations

4