Enzyme-Mediated Exponential Glucose Release: A Model-Based Strategy for Continuous Defined Fed-Batch in Small-Scale Cultivations.

Miniaturized cultivation systems offer the potential to enhance experimental throughput in bioprocess development. However, they usually lack the miniaturized pumps necessary for fed-batch mode, which is commonly employed in industrial bioprocesses. An alternative are enzyme-mediated glucose release systems from starch-derived polymers, facilitating continuous glucose supply. Nevertheless, while the glucose release, and thus the feed rate, is controlled by the enzyme concentration, it also strongly depends on the type of starch derivative, and the culture conditions as well as pH and temperature. So far it was not possible to implement controlled feeding strategies (e.g., exponential feeding). In this context, we propose a model-based approach to achieve precise control over enzyme-mediated glucose release in cultivations. To this aim, an existing mathematical model was integrated into a computational framework to calculate setpoints for enzyme additions. We demonstrate the ability of the tool to maintain different pre-defined exponential growth rates during Escherichia coli cultivations in parallel mini-bioreactors integrated into a robotic facility. Although in this case study, the intermittent additions of enzyme and dextrin were performed by a liquid handler, the approach is adaptable to manual applications. Thus, we present a straightforward and robust approach for implementing defined continuous fed-batch processes in small-scale systems, where continuous feeding was only possible with low accuracy or high technical efforts until now.

Data-Driven Protein Engineering for Improving Catalytic Activity and Selectivity.

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.

Structure- and Data-Driven Protein Engineering of Transaminases for Improving Activity and Stereoselectivity.

Amine transaminases (ATAs) are powerful biocatalysts for the stereoselective synthesis of chiral amines. Machine learning provides a promising approach for protein engineering, but activity prediction models for ATAs remain elusive due to the difficulty of obtaining high-quality training data. Thus, we first created variants of the ATA from Ruegeria sp. (3FCR) with improved catalytic activity (up to 2000-fold) as well as reversed stereoselectivity by a structure-dependent rational design and collected a high-quality dataset in this process. Subsequently, we designed a modified one-hot code to describe steric and electronic effects of substrates and residues within ATAs. Finally, we built a gradient boosting regression tree predictor for catalytic activity and stereoselectivity, and applied this for the data-driven design of optimized variants which then showed improved activity (up to 3-fold compared to the best variants previously identified). We also demonstrated that the model can predict the catalytic activity for ATA variants of another origin by retraining with a small set of additional data.