Data‐Driven Protein Engineering for Improving Catalytic Activity and Selectivity

Abstract

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

Protein Representations: Encoding Biological Information for Machine Learning in Biocatalysis

“…This could, in turn, assist in addressing tasks such as predicting substrate specificity or elucidating the structure-function of enzymes (Berselli et al, 2021). Within the realm of ML, features extracted from substrate-docking have yet to be fully leveraged (Ao et al, 2024) and are possibly challenged by difficulties in translating protein-substrate complexes into a numerical and general representation. However, some studies have successfully included information harvested from protein-substrate complexes for ML models employing different strategies which will be introduced in this section (Figure 6).…”

The Development and Opportunities of Predictive Biotechnology

“…It is important to note that the list is not exhaustive and serves to showcase the diversity in the field of predictive biotechnology. Herein, the authors' focus mostly on biotransformations, enzymes, and protein engineering campaigns underscores the remarkable advances in this field, as evidenced by recent reviews [1,7–15] …”

“…As a result, protein engineers must run numerous iterative rounds of mutagenesis and screening. Hence, the large protein mutation space continues to be challenging [8] …”

“…It also offers an opportunity to save time and resources by designing enzymatic processes and bringing them to life with minimal experimental validations. A concept article by Ao and colleagues (2024) provides an insightful overview of the potential of data‐driven protein engineering [8] …”

Functional Enhancement of Flavin-Containing Monooxygenase through Machine Learning Methodology

“…However, directed evolution of enzymes often fails to obtain desirable variants because of the difficulty in exploring the huge sequence space . To obtain active variants from a very limited number of variants accessible at a laboratory scale, machine learning (ML)-guided protein engineering is becoming an attractive methodology. − Among the enzymes involved in the biosynthesis of secondary metabolites, flavin-containing monooxygenases (FMOs) in particular play an important role in the biosynthesis of NPs by catalyzing a wide range of oxidative reactions . Furthermore, some FMOs have relaxed substrate specificities and convert substrate analogues into products that differ from the original product by catalyzing the complex rearrangement, contributing to the structural diversification of NPs. − As such, FMOs constitute an enzyme family with flexible activities, and their functional modification is expected to contribute to the generation of catalysts that can facilitate the expansion of the chemical space of secondary metabolites.…”