BioStructNet: Structure-Based Network with Transfer Learning for Predicting Biocatalyst Functions DOI Creative Commons
Xiangwen Wang, Jiahui Zhou,

Jessica Mueller

et al.

Journal of Chemical Theory and Computation, Journal Year: 2024, Volume and Issue: unknown

Published: Dec. 20, 2024

Enzyme–substrate interactions are essential to both biological processes and industrial applications. Advanced machine learning techniques have significantly accelerated biocatalysis research, revolutionizing the prediction of biocatalytic activities facilitating discovery novel biocatalysts. However, limited availability data for specific enzyme functions, such as conversion efficiency stereoselectivity, presents challenges accuracy. In this study, we developed BioStructNet, a structure-based deep network that integrates protein ligand structural capture complexity enzyme–substrate interactions. Benchmarking studies with different algorithms showed enhanced predictive accuracy BioStructNet. To further optimize small set, implemented transfer in framework, training source model on large set fine-tuning it small, function-specific using CalB case study. The performance was validated by comparing attention heat maps generated BioStructNet interaction module revealed from molecular dynamics simulations complexes. would accelerate functional enzymes use, particularly cases where sets small.

Language: Английский

Polymer gels for aqueous metal batteries DOI
Tianfu Zhang, Keliang Wang,

Hengwei Wang

et al.

Progress in Materials Science, Journal Year: 2025, Volume and Issue: unknown, P. 101426 - 101426

Published: Jan. 1, 2025

Citations

3
Robust enzyme discovery and engineering with deep learning using CataPro DOI Creative Commons
Zechen Wang, Dongqi Xie, Di Wu

et al.

Nature Communications, Journal Year: 2025, Volume and Issue: 16(1)

Published: March 20, 2025

Abstract Accurate prediction of enzyme kinetic parameters is crucial for exploration and modification. Existing models face the problem either low accuracy or poor generalization ability due to overfitting. In this work, we first developed unbiased datasets evaluate actual performance these methods proposed a deep learning model, CataPro, based on pre-trained molecular fingerprints predict turnover number ( k c t ), Michaelis constant K m catalytic efficiency / ). Compared with previous baseline models, CataPro demonstrates clearly enhanced datasets. representational mining project, by combining traditional methods, identified an (SsCSO) 19.53 times increased activity compared initial (CSO2) then successfully engineered it improve its 3.34 times. This reveals high potential as effective tool future discovery

Language: Английский

Citations

2
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

7
Enzymatic functionalization of bacterial nanocellulose: current approaches and future prospects DOI Creative Commons
Monika Kaczmarek, Aneta Białkowska

Journal of Nanobiotechnology, Journal Year: 2025, Volume and Issue: 23(1)

Published: Feb. 4, 2025

Faced with the challenges of modern industry and medicine associated dynamic development civilization, there is a constantly growing demand for production novel functional materials that are clearly oriented towards fulfilling specific applications. Herein, we provide an overview current status recent findings related to enzymatic functionalization bacterial nanocellulose. Commonly, biocellulose modification involves utilization simple cost-effective chemical and/or physical approaches. However, these methods may have adverse effect on both biological properties biomaterial natural environment. An alternative procedures highly nanocellulose, which perfectly fits into assumptions green technologies, making process eco-friendly not limiting any outlooks further usage obtained biocomposites. The employment enzymes targeted alteration this material's based either direct method, such as controlled hydrolysis nanofication [i.e., synthesis different morphological forms cellulose (e.g., rod-shaped nanocrystals)] using cellulases, attachment reactive groups polymer structure via oxidation utilizing laccase/TEMPO catalytic system or lytic polysaccharide monooxygenases) esterification catalyzed by lipases; indirect procedure involving application nanocellulose matrix enzyme immobilization laccase, glucose oxidase, horseradish peroxidase, lysozyme, bromelain, lipase, papain), thus creating system. Overall, sustainable promising strategy create biocomposites tailored wide range industrial medical

Language: Английский

Citations

1
High-Temperature Catalytic Platform Powered by Thermophilic Microorganisms and Thermozymes DOI
Jiawei Li, Lichao Sun, Yi‐Xin Huo

et al.

Synthetic biology and engineering, Journal Year: 2025, Volume and Issue: 3(1), P. 10001 - 10001

Published: Jan. 1, 2025

Language: Английский

Citations

1
Methods for Theoretical Treatment of Local Fields in Proteins and Enzymes DOI
Mark E. Eberhart, Anastassia N. Alexandrova, Pujan Ajmera

et al.

Chemical Reviews, Journal Year: 2025, Volume and Issue: unknown

Published: Feb. 24, 2025

Electric fields generated by protein scaffolds are crucial in enzymatic catalysis. This review surveys theoretical approaches for detecting, analyzing, and comparing electric fields, electrostatic potentials, their effects on the charge density within enzyme active sites. Pioneering methods like empirical valence bond approach rely evaluating ionic covalent resonance forms influenced field. Strategies employing polarizable force also facilitate field detection. The vibrational Stark effect connects computational simulations to experimental spectroscopy, enabling direct comparisons. We highlight how dynamics induce fluctuations local influencing activity. Recent techniques assess throughout site volume rather than only at specific bonds, machine learning helps relate these global reactivity. Quantum theory of atoms molecules captures entire electron landscape, providing a chemically intuitive perspective field-driven Overall, methodologies show protein-generated highly dynamic heterogeneous, understanding both aspects is critical elucidating mechanisms. holistic view empowers rational engineering tuning promising new avenues drug design, biocatalysis, industrial applications. Future directions include incorporating as explicit design targets enhance catalytic performance biochemical functionalities.

Language: Английский

Citations

1
Artificial intelligence in plastic recycling and conversion: A review DOI
Yi Fang,

Yuming Wen,

Leilei Dai

et al.

Resources Conservation and Recycling, Journal Year: 2024, Volume and Issue: 215, P. 108090 - 108090

Published: Dec. 18, 2024

Language: Английский

Citations

3
Highly Selective Electrocatalytic 1,4‐NADH Regeneration Based on Host–Guest Recognition Mediated by Cucurbit[8]uril on NiO DOI Open Access

Hongxia Ning,

Yizhou Wu, Chang Liu

et al.

Angewandte Chemie International Edition, Journal Year: 2025, Volume and Issue: unknown

Published: March 6, 2025

Abstract Efficient regeneration of nicotinamide adenine dinucleotide (NADH) cofactors, particularly 1,4‐NADH, is crucial for advancing oxidoreductase catalysis. Electrocatalysis provides a promising route 1,4‐NADH regeneration, but an expensive catalyst, typically rhodium organometallic complex, frequently required to guarantee the high selectivity significantly limiting its large‐scale application. Herein, inspired by catalytic pocket and enzyme–substrate interaction in nature, direct electrochemical was designed modification surface nickel oxide (NiO) with cucurbit[8]uril (CB[8]) (denoted as CB[8]–NiO). The host–guest between CB[8] NAD + proved, which similar principle substrate–enzyme‐specific recognition. acted , providing suitable cavity volume accommodate positively charged part . entered approached surface‐adsorbed hydrogen atoms on NiO reaction‐ready configuration achieve regioselective regeneration. Remarkably higher 97.8% CB[8]–NiO obtained at −0.47 V versus reversible electrode (RHE) than that bare (77.4%).

Language: Английский

Citations

0
Generative artificial intelligence for enzyme design: Recent advances in models and applications DOI Creative Commons

S. P. Wen,

Wen Zheng, Uwe T. Bornscheuer

et al.

Current Opinion in Green and Sustainable Chemistry, Journal Year: 2025, Volume and Issue: 52, P. 101010 - 101010

Published: March 2, 2025

Citations

0
Highly Selective Electrocatalytic 1,4‐NADH Regeneration Based on Host–Guest Recognition Mediated by Cucurbit[8]uril on NiO DOI Open Access

Hongxia Ning,

Yizhou Wu, Chang Liu

et al.

Angewandte Chemie, Journal Year: 2025, Volume and Issue: unknown

Published: March 6, 2025

Abstract Efficient regeneration of nicotinamide adenine dinucleotide (NADH) cofactors, particularly 1,4‐NADH, is crucial for advancing oxidoreductase catalysis. Electrocatalysis provides a promising route 1,4‐NADH regeneration, but an expensive catalyst, typically rhodium organometallic complex, frequently required to guarantee the high selectivity significantly limiting its large‐scale application. Herein, inspired by catalytic pocket and enzyme–substrate interaction in nature, direct electrochemical was designed modification surface nickel oxide (NiO) with cucurbit[8]uril (CB[8]) (denoted as CB[8]–NiO). The host–guest between CB[8] NAD + proved, which similar principle substrate–enzyme‐specific recognition. acted , providing suitable cavity volume accommodate positively charged part . entered approached surface‐adsorbed hydrogen atoms on NiO reaction‐ready configuration achieve regioselective regeneration. Remarkably higher 97.8% CB[8]–NiO obtained at −0.47 V versus reversible electrode (RHE) than that bare (77.4%).

Language: Английский

Citations

0