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.
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.
20 November 2023 in Angewandte Chemie International Edition
Enzyme‐catalyzed late‐stage functionalization (LSF), such as methylation of drug molecules and lead structures, enables direct access to more potent active pharmaceutical ingredients (API). S‐adenosyl‐l‐methionine‐dependent methyltransferases (MTs) can play a key role in the development of new APIs, as they catalyze the chemo‐ and regioselective methylation of O‐, N‐, S‐ and C‐atoms, being superior to traditional chemical routes. To identify suitable MTs, we developed a continuous fluorescence‐based, high‐throughput assay for SAM‐dependent methyltransferases, which facilitates screening using E. coli cell lysates. This assay involves two enzymatic steps for the conversion of S‐adenosyl‐l‐homocysteine into H2S to result in a selective fluorescence readout via reduction of an azidocoumarin sulfide probe. Investigation of two O‐MTs and an N‐MT confirmed that this assay is suitable for the determination of methyltransferase activity in E. coli cell lysates.
The methylation of small molecules is of immense value to various chemical industries. Since chemical alkylation requires rather unselective and harsh reaction conditions, sustainable biocatalytic approaches are highly desired. Methyltransferases, particularly N ‐methyltransferases (NMTs), facilitate the selective introduction of methyl (and other alkyl) groups under mild conditions in aqueous solution and are a promising alternative to chemical synthesis. In this work, we expanded the toolbox of NMTs through the bioinformatic‐assisted mining of databases and the high‐throughput characterization of novel NMTs by a fluorescence‐based assay. The latter can assess enzyme activity in cell lysates, independent of the investigated substrate, and was used to guide the engineering of newly identified NMTs. Mutants, exhibiting up to 8‐fold improved selective methylation of (non‐)natural N ‐heterocyclic drug precursors, were identified and promise great potential for synthetic applications.
Amintransaminasen (ATAs) sind leistungsstarke Biokatalysatoren für die stereoselektive Synthese chiraler Amine. Machine learning ist ein vielversprechender Ansatz für das Protein‐Engineering, aber Modelle zur Aktivitätsvorhersage für ATAs sind aufgrund der Schwierigkeit, qualitativ hochwertige Trainingsdaten zu erhalten, schwer zu finden. Aus diesem Grund haben wir zunächst Varianten der ATA aus Ruegeria sp. (3FCR) mit verbesserter katalytischer Aktivität (bis zu 2000‐fach) sowie umgekehrter Stereoselektivität durch strukturabhängiges rationales Design entwickelt und dabei einen hochwertigen Datensatz gesammelt. Anschließend entwarfen wir einen modifizierten One‐Hot‐Code, um sterische und elektronische Effekte von Substraten und Aminosäureresten innerhalb von ATAs zu beschreiben. Schließlich erstellten wir einen Gradient Boosting Regression Tree Prädiktor zur Vorhersage der katalytischen Aktivität und Stereoselektivität und wendeten diesen für das datengesteuerte Design optimierter Varianten an, die dann eine verbesserte Aktivität zeigten (bis zum Dreifachen im Vergleich zu den besten zuvor identifizierten Varianten). Wir haben zudem gezeigt, dass das Modell die katalytische Aktivität für ATA‐Varianten eines anderen Enzyms vorhersagen kann, indem es mit einem kleinen Satz zusätzlicher Daten neu trainiert wurde.