Opportunities and Challenges for Machine Learning-Assisted Enzyme Engineering

ACS Central Science, Год журнала: 2024, Номер 10(2), С. 226 - 241

Опубликована: Фев. 5, 2024

Enzymes can be engineered at the level of their amino acid sequences to optimize key properties such as expression, stability, substrate range, and catalytic efficiency-or even unlock new activities not found in nature. Because search space possible proteins is vast, enzyme engineering usually involves discovering an starting point that has some desired activity followed by directed evolution improve its "fitness" for a application. Recently, machine learning (ML) emerged powerful tool complement this empirical process. ML models contribute (1) discovery functional annotation known protein or generating novel with functions (2) navigating fitness landscapes optimization mappings between associated values. In Outlook, we explain how complements discuss future potential improved outcomes.

Язык: Английский

---

Atomic Engineering of Single‐Atom Nanozymes for Biomedical Applications

Advanced Materials, Год журнала: 2024, Номер 36(21)

Опубликована: Фев. 7, 2024

Single-atom nanozymes (SAzymes) showcase not only uniformly dispersed active sites but also meticulously engineered coordination structures. These intricate architectures bestow upon them an exceptional catalytic prowess, thereby captivating numerous minds and heralding a new era of possibilities in the biomedical landscape. Tuning microstructure SAzymes on atomic scale is key factor designing targeted with desirable functions. This review first discusses summarizes three strategies for their impact reactivity biocatalysis. The effects choices carrier, different synthesis methods, modulation first/second shell, type number metal centers enzyme-like activity are unraveled. Next, attempt made to summarize biological applications tumor therapy, biosensing, antimicrobial, anti-inflammatory, other from mechanisms. Finally, how designed regulated further realization diverse reviewed prospected. It envisaged that comprehensive presented within this exegesis will furnish novel perspectives profound revelations regarding SAzymes.

Язык: Английский

---

Automated in vivo enzyme engineering accelerates biocatalyst optimization

Nature Communications, Год журнала: 2024, Номер 15(1)

Опубликована: Апрель 24, 2024

Achieving cost-competitive bio-based processes requires development of stable and selective biocatalysts. Their realization through in vitro enzyme characterization engineering is mostly low throughput labor-intensive. Therefore, strategies for increasing while diminishing manual labor are gaining momentum, such as vivo screening evolution campaigns. Computational tools like machine learning further support efforts by widening the explorable design space. Here, we propose an integrated solution to challenges whereby ML-guided, automated workflows (including library generation, implementation hypermutation systems, adapted laboratory evolution, growth-coupled selection) could be realized accelerate pipelines towards superior

Язык: Английский

---

Navigating the landscape of enzyme design: from molecular simulations to machine learning

Chemical Society Reviews, Год журнала: 2024, Номер 53(16), С. 8202 - 8239

Опубликована: Янв. 1, 2024

Global environmental issues and sustainable development call for new technologies fine chemical synthesis waste valorization. Biocatalysis has attracted great attention as the alternative to traditional organic synthesis. However, it is challenging navigate vast sequence space identify those proteins with admirable biocatalytic functions. The recent of deep-learning based structure prediction methods such AlphaFold2 reinforced by different computational simulations or multiscale calculations largely expanded 3D databases enabled structure-based design. While approaches shed light on site-specific enzyme engineering, they are not suitable large-scale screening potential biocatalysts. Effective utilization big data using machine learning techniques opens up a era accelerated predictions. Here, we review applications machine-learning guided We also provide our view challenges perspectives effectively employing design integrating molecular learning, importance database construction algorithm in attaining predictive ML models explore fitness landscape

Язык: Английский

---

Biocatalysis for the Synthesis of Active Pharmaceutical Ingredients in Deep Eutectic Solvents: State-of-the-Art and Prospects

Catalysts, Год журнала: 2024, Номер 14(1), С. 84 - 84

Опубликована: Янв. 19, 2024

Biocatalysis holds immense potential for pharmaceutical development as it enables synthetic routes to various chiral building blocks with unparalleled selectivity. Therein, solvent and water use account a large contribution the environmental impact of reactions. In spirit Green Chemistry, transition from traditional highly diluted aqueous systems intensified non-aqueous media overcome limitations (e.g., shortages, recalcitrant wastewater treatments, low substrate loadings) has been observed. Benefiting spectacular advances in enzyme stabilization techniques, plethora biotransformations non-conventional have established. Deep eutectic solvents (DESs) emerge sort (potentially) greener medium increasing biocatalysis. This review discusses state-of-the-art DESs focus on biocatalytic pathways synthesis active ingredients (APIs). Representative examples different classes are discussed, together critical vision discussing prospects using

Язык: Английский

---

From Ground-State to Excited-State Activation Modes: Flavin-Dependent “Ene”-Reductases Catalyzed Non-natural Radical Reactions

Accounts of Chemical Research, Год журнала: 2024, Номер 57(9), С. 1446 - 1457

Опубликована: Апрель 11, 2024

ConspectusEnzymes are desired catalysts for chemical synthesis, because they can be engineered to provide unparalleled levels of efficiency and selectivity. Yet, despite the astonishing array reactions catalyzed by natural enzymes, many reactivity patterns found in small molecule have no counterpart living world. With a detailed understanding mechanisms utilized catalysts, we identify existing enzymes with potential catalyze that currently unknown nature. Over past eight years, our group has demonstrated flavin-dependent "ene"-reductases (EREDs) various radical-mediated selectivity, solving long-standing challenges asymmetric synthesis.This Account presents development EREDs as general radical reactions. While developed multiple generating radicals within protein active sites, this account will focus on examples where flavin mononucleotide hydroquinone (FMNhq) serves an electron transfer initiator. initial mechanistic hypotheses were rooted electron-transfer-based initiation commonly used synthetic organic chemists, ultimately uncovered emergent unique site. We begin covering intramolecular discussing how activates substrate reduction altering redox-potential alkyl halides templating charge complex between flavin-cofactor. Protein engineering been modify fundamental photophysics these reactions, highlighting opportunity tune systems further using directed evolution. This section highlights range coupling partners termination available reactions.The next intermolecular role enzyme-templated ternary complexes among cofactor, halide, partner gating ensure it only occurs when both substrates bound highlight applications activation mode, including olefin hydroalkylation, carbohydroxylation, arene functionalization, nitronate alkylation. also discusses favor steps elusive solution reductive nitroalkanes. aware several recent EREDs-catalyzed photoenzymatic transformations from other groups. discuss results papers context nuances substrates.These biocatalytic often complement state-of-the-art small-molecule-catalyzed making valuable addition chemist's toolbox. Moreover, underlying principles studied potentially operative cofactor-dependent proteins, opening door different types enzyme-catalyzed anticipate serve guide inspire broad interest repurposing access new transformations.

Язык: Английский

---

Machine learning-guided co-optimization of fitness and diversity facilitates combinatorial library design in enzyme engineering

Nature Communications, Год журнала: 2024, Номер 15(1)

Опубликована: Июль 29, 2024

Abstract The effective design of combinatorial libraries to balance fitness and diversity facilitates the engineering useful enzyme functions, particularly those that are poorly characterized or unknown in biology. We introduce MODIFY, a machine learning (ML) algorithm learns from natural protein sequences infer evolutionarily plausible mutations predict fitness. MODIFY co-optimizes predicted sequence starting libraries, prioritizing high-fitness variants while ensuring broad coverage. In silico evaluation shows outperforms state-of-the-art unsupervised methods zero-shot prediction enables ML-guided directed evolution with enhanced efficiency. Using we engineer generalist biocatalysts derived thermostable cytochrome c achieve enantioselective C-B C-Si bond formation via new-to-nature carbene transfer mechanism, leading six away previously developed enzymes exhibiting superior comparable activities. These results demonstrate MODIFY’s potential solving challenging problems beyond reach classic evolution.

Язык: Английский

---

The shortest path method (SPM) webserver for computational enzyme design

Protein Engineering Design and Selection, Год журнала: 2024, Номер 37

Опубликована: Янв. 1, 2024

Abstract SPMweb is the online webserver of Shortest Path Map (SPM) tool for identifying key conformationally-relevant positions a given enzyme structure and dynamics. The server built on top DynaComm.py code enables calculation visualization SPM pathways. easy-to-use as it only requires three input files: three-dimensional protein interest, two matrices (distance correlation) previously computed from Molecular Dynamics simulation. We provide in this publication information how to generate files construction even non-expert users discuss most relevant parameters that can be modified. extremely fast (it takes less than one minute per job), thus allowing rapid identification distal connected active site pocket enzyme. applications expand computational design, especially if combined with other tools identify preferred substitution at identified position, but also rationalizing allosteric regulation, cryptic drug discovery. simple user interface setup make accessible whole scientific community. freely available academia http://spmosuna.com/.

Язык: Английский

---

Choose Your Own Adventure: A Comprehensive Database of Reactions Catalyzed by Cytochrome P450 BM3 Variants

ACS Catalysis, Год журнала: 2024, Номер 14(8), С. 5560 - 5592

Опубликована: Март 29, 2024

Cytochrome P450 BM3 monooxygenase is the topic of extensive research as many researchers have evolved this enzyme to generate a variety products. However, abundance information on increasingly diversified variants that catalyze broad array chemistry not in format enables easy extraction and interpretation. We present database categorizes by their catalyzed reactions includes details about substrates provide reaction context. This >1500 downloadable machine-readable instructions maximize ease gathering information. The allows rapid identification commonly reported substitutions, aiding who are unfamiliar with identifying starting points for engineering. For those actively engaged engineering BM3, database, along review, provides powerful user-friendly platform understand, predict, identify attributes variants, encouraging further enzyme.

Язык: Английский

---

Practical Machine Learning-Assisted Design Protocol for Protein Engineering: Transaminase Engineering for the Conversion of Bulky Substrates

ACS Catalysis, Год журнала: 2024, Номер 14(9), С. 6462 - 6469

Опубликована: Апрель 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).

Язык: Английский

---