Protein Engineering by Efficient Sequence Space Exploration Through Combination of Directed Evolution and Computational Design Methodologies

Pramanik, Subrata; Contreras, Francisca; Davari, Mehdi D.; Schwaneberg, Ulrich

doi:10.1002/9783527815128.ch7

Cited by 8 publications

(6 citation statements)

References 83 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These methods combine directed-evolution campaigns with computational analysis to achieve a more efficient library generation. Examples of how combined approaches aid in semirational, rather than entirely random, variant design are a statistical analysis of substitution accessibility at each amino acid position or models which partially infer a molecular understanding of the sequence–structure–function relationship . Common combined methods include for example KnowVolution, which has successfully been used to engineer enzyme variants with improved thermostability, ionic liquid tolerance, or product selectivities .…”

Section: Enzyme Engineering Strategiesmentioning

confidence: 99%

See 1 more Smart Citation

Learning Epistasis and Residue Coevolution Patterns: Current Trends and Future Perspectives for Advancing Enzyme Engineering

2022

Self Cite

View full text Add to dashboard Cite

Engineering proteins and enzymes with the desired functionality has broad applications in molecular biology, biotechnology, biomedical sciences, health, and medicine. The vastness of protein sequence space and all the possible proteins it represents can pose a considerable barrier for enzyme engineering campaigns through directed evolution and rational design. The nonlinear effects of coevolution between amino acids in protein sequences complicate this further. Data-driven models increasingly provide scientists with the computational tools to navigate through the largely undiscovered forest of protein variants and catch a glimpse of the rules and effects underlying the topology of sequence space. In this review, we outline a complete theoretical journey through the processes of protein engineering methods such as directed evolution and rational design and reflect on these strategies and data-driven hybrid strategies in the context of sequence space. We discuss crucial phenomena of residue coevolution, such as epistasis, and review the history of models created over the past decade, aiming to infer rules of protein evolution from data and use this knowledge to improve the prediction of the structure− function relationship of proteins. Data-driven models based on deep learning algorithms are among the most promising methods that can account for the nonlinear phenomena of sequence space to some degree. We also critically discuss the available models to predict evolutionary coupling and epistatic effects (classical and deep learning) in terms of their capabilities and limitations. Finally, we present our perspective on possible future directions for developing data-driven approaches and provide key orientation points and necessities for the future of the fast-evolving field of enzyme engineering.

show abstract

Section: Enzyme Engineering Strategiesmentioning

confidence: 99%

“…60 A discussion of these combined approaches is not the aim of this review. A detailed comparison can be found in a recent book chapter by Pramanik et al 58 2.5. Data-Driven Approaches.…”

Section: Combined Approachesmentioning

confidence: 99%

Learning Epistasis and Residue Coevolution Patterns: Current Trends and Future Perspectives for Advancing Enzyme Engineering

2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…The advancement of protein engineering, driven by directed evolution (DE) and (semi)rational design (RD), has significantly enhanced protein properties (Wang et al, 2021; Wittmund et al, 2022; Pramanik et al, 2021). These improvements have had far-reaching implications across diverse sectors, including biocatalysis, pharmaceuticals and medicine, livestock, and agriculture (Arnold, 2018).…”

Section: Introductionmentioning

confidence: 99%

Interpretable and explainable predictive machine learning models for data-driven protein engineering

Medina-Ortiz,

Khalifeh,

Anvari-Kazemabad

et al. 2024

Preprint

Self Cite

View full text Add to dashboard Cite

Protein engineering using directed evolution and (semi)rational design has emerged as a powerful strategy for optimizing and enhancing enzymes or proteins with desired properties. Integrating artificial intelligence methods has further enhanced and accelerated protein engineering through predictive models developed in data-driven strategies. However, the lack of explainability and interpretability in these models poses challenges. Explainable Artificial Intelligence addresses the interpretability and explainability of machine learning models, providing transparency and insights into predictive processes. Nonetheless, there is a growing need to incorporate explainable techniques in predicting protein properties in machine learning-assisted protein engineering. This work explores incorporating explainable artificial intelligence in predicting protein properties, emphasizing its role in trustworthiness and interpretability. It assesses different machine learning approaches, introduces diverse explainable methodologies, and proposes strategies for seamless integration, improving trust-worthiness. Practical cases demonstrate the explainable model’s effectiveness in identifying DNA binding proteins and optimizing Green Fluorescent Protein brightness. The study highlights the utility of explainable artificial intelligence in advancing computationally assisted protein design, fostering confidence in model reliability.

show abstract

“…In addition to the experimental techniques [e.g., circular dichroism (CD), dynamic light scattering (DLS), and nuclear magnetic resonance (NMR)], , the relationship between proteins and their stability in solvents can be accomplished by molecular dynamics (MD) simulations with significant accuracy. − Moreover, using directed evolution methods and computational investigations, , the enzymes’ characteristics can be adjusted to be active perfectly with a predetermined IL environment. ,, …”

Section: Introductionmentioning

confidence: 99%

“…In addition to the experimental techniques [e.g., circular dichroism (CD), dynamic light scattering (DLS), and nuclear magnetic resonance (NMR)], 20,22 the relationship between proteins and their stability in solvents can be accomplished by molecular dynamics (MD) simulations with significant accuracy. 23−25 Moreover, using directed evolution methods and computational investigations, 26,27 the enzymes' characteristics can be adjusted to be active perfectly with a predetermined IL environment. 4,28,29 The use of ILs for lipase-catalyzed reactions is a popular method of organic synthesis 30 because lipases may catalyze a variety of processes, including hydrolysis, transesterification, alcoholysis, and esterification, by taking a wide range of substrates.…”

Section: Introductionmentioning

confidence: 99%

Enzyme Hydration: How to Retain Resistance in Ionic Liquids

Cui

Zhang

Yildiz

et al. 2022

ACS Sustainable Chem. Eng.

Self Cite

View full text Add to dashboard Cite

Application of ionic liquids (ILs) as media in biocatalysis has enormous potential for synthesizing valuable compounds and bulk products in pharmaceuticals and bioenergy due to their unique solvent properties such as volatility, flammability, and solubility. However, ILs as reaction media are often limited by poor enzymatic activity and stability in ILs. We printed a comprehensive IL−enzyme interaction map by studying 45 molecular observables of 30 lipase A from Bacillus subtilis (BSLA) variants in four ILs and a substitutional landscape with 1504 BSLA variants. The results demonstrated that the enzyme hydration shell is the deciding and independent factor determining the enzyme's IL resistance. A universal positive correlation (up to R 2 = 0.96 in 1-butyl-3-methylimidazolium trifluoromethanesulfonate ([BMIM][TfO]) and R 2 = 0.85 in 1-butyl-3methylimidazolium chloride ([BMIM]Cl)) was verified, and an experimentally derived ranking of amino acid substitutions is summarized in a list to provide benefits for better protein engineering practice. Hydration-guided engineering yielded a supremely tolerant BSLA variant I12R/D34K/A132K with 8.1-fold, 8.6-fold, 6.6-fold, and 4.6-fold improved tolerance toward [BMIM]Cl, [BMIM]Br, [BMIM]I, and [BMIM][TfO], respectively, when compared to the wild-type BSLA. The obtained knowledge provides a lesson learned on forecasting enzyme stability in ILs and simplifies a rational design of the IL-tolerant enzymes.

show abstract

Protein Engineering by Efficient Sequence Space Exploration Through Combination of Directed Evolution and Computational Design Methodologies

Cited by 8 publications

References 83 publications

Learning Epistasis and Residue Coevolution Patterns: Current Trends and Future Perspectives for Advancing Enzyme Engineering

Learning Epistasis and Residue Coevolution Patterns: Current Trends and Future Perspectives for Advancing Enzyme Engineering

Interpretable and explainable predictive machine learning models for data-driven protein engineering

Enzyme Hydration: How to Retain Resistance in Ionic Liquids

Contact Info

Product

Resources

About