High-throughput screening, next generation sequencing and machine learning: advanced methods in enzyme engineering

Vanella, Rosario; Kovačević, Gordana; Doffini, Vanni; Santaella, Jaime Fernández de; Nash, Michael A.

doi:10.1039/d1cc04635g

Cited by 40 publications

(38 citation statements)

References 116 publications

(125 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Modern technologies such as high-throughput screening (HTS), next generation sequencing, and deep mutational scanning (DMS) allow to sequence and screen protein variants in an automated fashion, consequently generating huge protein sequence databases [11]. However, establishing such HTS systems is very elaborate such that they are not implemented in most protein engineering campaigns [12].…”

Section: Introductionmentioning

confidence: 99%

“…In recent years, machine learning (ML) and statistical approaches have expanded the toolbox of protein engineers by extracting knowledge from data for constructing a model of the protein sequence-fitness landscape that can subsequently be explored in silico [11, 14]. Such a model not only enables in silico screening, which has orders of magnitude higher throughput compared to experimental methods [15] while minimizing costs, but can also support exploration and recombination.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A hybrid model combining evolutionary probability and machine learning leverages data-driven protein engineering

Illig

Siedhoff

Schwaneberg

et al. 2022

Preprint

View full text Add to dashboard Cite

Protein engineering through directed evolution and (semi)rational approaches has been applied successfully to optimize protein properties for broad applications in molecular biology, biotechnology, and biomedicine. The potential of protein engineering is not yet fully realized due to the limited screening throughput hampering the efficient exploration of the vast protein sequence space. Data-driven strategies have emerged as a powerful tool to leverage protein engineering by providing a model of the sequence-fitness landscape that can exhaustively be explored in silico and capitalize on the high diversity potential offered by nature. However, as both the quality and quantity of the inputted data determine the success of such approaches, the applicability of data-driven strategies is often limited due to sparse data. Here, we present a hybrid model that combines direct coupling analysis and machine learning techniques to enable data-driven protein engineering when only a few labeled sequences are available. Our method achieves high performance in predicting a proteins fitness based on its sequence regardless of the number of sequences-fitness pairs in the training dataset. Besides reducing the computational effort compared to state-of-the-art methods, it outperforms them for sparse data situations, i.e., 50-250 labeled sequences available for training. In essence, the developed method is auspicious for data-driven protein engineering, especially for protein engineers who have only access to a limited amount of data for sequence-fitness landscape modeling.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A hybrid model combining evolutionary probability and machine learning leverages data-driven protein engineering

Illig

Siedhoff

Schwaneberg

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…First, it can mitigate several issues, such as product inhibition and product toxicity. 4 Second, it can avoid the requirement of chemically modified substrate analogs or bulky fluorescent groups, allowing enzyme variants to be screened on natural substrates. Third, it can offer opportunities to increase screening throughput by providing an output that can be evaluated at a higher speed and throughput than conventional chemical analyses, such as mass spectrometry and liquid chromatography.…”

Section: Introductionmentioning

confidence: 99%

“…A critical issue for the establishment of machine learning assisted directed evolution is the quantity of training data. 4 Some methods, such as kernel-based methods, require dozens or hundreds of data points while other methods, such as deep neural networks, typically require thousands or even more data points. Thus, it is essential to develop a high-throughput enzyme evaluation system.…”

Section: Introductionmentioning

confidence: 99%

“…Third, it can offer opportunities to increase screening throughput by providing an output that can be evaluated at a higher speed and throughput than conventional chemical analyses, such as mass spectrometry and liquid chromatography. 4 Thus, if it accurately reflects the activity of the target enzyme, the range of enzymes for which machine learning-assisted directed evolution is applicable would be extended. XylS is a transcriptional activator of Pseudomonas putida that recognizes several aromatic compounds as ligands.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Engineering the substrate specificity of toluene degrading enzyme XylM using biosensor XylS and machine learning

Ogawa

Saitô

Yamaguchi

et al. 2022

Preprint

View full text Add to dashboard Cite

Enzyme engineering using machine learning has been developed in recent years. However, to obtain a large amount of data on enzyme activities for training data, it is necessary to develop a high-throughput and accurate method for evaluating en-zyme activities. Here, we examined whether a biosensor-based enzyme engineering method can be applied to machine learn-ing. As a model experiment, we aimed to modify the substrate specificity of XylM, a rate-determining enzyme in a multistep oxidation reaction catalyzed by XylMABC in Pseudomonas putida. XylMABC naturally converts toluene and xylene to benzoic acid and toluic acid, respectively. We aimed to engineer XylM to improve its conversion efficiency to a non-native substrate, 2,6-xylenol. Wild-type XylMABC slightly converted 2,6-xylenol to 3-methylsalicylic acid, which is the ligand of the transcrip-tional regulator XylS in P. putida. By locating a fluorescent protein gene under the control of the Pm promoter to which XylS binds, a XylS-producing Escherichia coli strain showed higher fluorescence intensity in a 3-methylsalicylic acid concentra-tion-dependent manner. We evaluated the 3-methylsalicylic acid productivity of XylM variants using the fluorescence inten-sity of the sensor strain as an indicator. The obtained data provided the training data for machine learning for the directed evolution of XylM. Two cycles of machine learning-assisted directed evolution resulted in the acquisition of XylM-D140E-V144K-F243L-N244S with 15 times higher productivity than wild-type XylM. These results demonstrate that an indirect enzyme activity evaluation method using biosensors is sufficiently quantitative and high-throughput to be used as training data for machine learning. The findings expand the versatility of machine learning in enzyme engineering.

show abstract

Screening and Selection Techniques

2023

Enzyme Engineering

View full text Add to dashboard Cite

High-throughput screening, next generation sequencing and machine learning: advanced methods in enzyme engineering

Abstract: Enzyme engineering is an important biotechnological process capable of generating tailored biocatalysts for applications in industrial chemical conversion and biopharma. Typical enhancements sought in enzyme engineering and in vitro evolution...

Cited by 40 publications

References 116 publications

A hybrid model combining evolutionary probability and machine learning leverages data-driven protein engineering

A hybrid model combining evolutionary probability and machine learning leverages data-driven protein engineering

Engineering the substrate specificity of toluene degrading enzyme XylM using biosensor XylS and machine learning

Screening and Selection Techniques

Contact Info

Product

Resources

About