Enhanced stereodivergent evolution of carboxylesterase for efficient kinetic resolution of near-symmetric esters through machine learning

Abstract

Carboxylesterases serve as potent biocatalysts in the enantioselective synthesis of chiral carboxylic acids and esters. However, naturally occurring carboxylesterases exhibit limited enantioselectivity, particularly towards ethyl 3-cyclohexene-1-carboxylate (CHCE), due to its nearly symmetric structure. While machine learning has proven effective in expediting directed evolution, the lack of models for prediction of enantioselectivity for carboxylesterases has hindered progress, primarily due to challenges obtaining high-quality training datasets. In this study, we devised a high-throughput method by coupling alcohol dehydrogenase to determine the apparent enantioselectivity of the carboxylesterase AcEst1 from Acinetobacter sp. JNU9335, thereby generating a high-quality dataset. Leveraging seven features derived from biochemical considerations, we quantitively described the steric, hydrophobic, hydrophilic, electrostatic, hydrogen bonding, and π-π interaction effects of residues within AcEst1. A robust gradient boosting regression tree model was trained to facilitate stereodivergent evolution, resulting in the enhanced enantioselectivity of AcEst1 towards CHCE. Through this approach, we successfully obtained two stereocomplementary variants, DR3 and DS6, demonstrating significantly increased and reversed enantioselectivity. Notably, DR3 and DS6 exhibited utility in the enantioselective hydrolysis of various symmetric esters. Comprehensive kinetic parameter analysis, molecular dynamics simulations, and QM/MM calculations provided insights into the kinetic and thermodynamic aspects underlying the manipulated enantioselectivity of DR3 and DS6.

Protein Representations: Encoding Biological Information for Machine Learning in Biocatalysis

“…Another example is the recent pre-print by Xu et al, where the authors employ physicochemical properties such as volume, hydrophobicity, and π-π interactions to model and improve enantioselectivity of carboxylesterase AcEst1 from Acinetobacter sp. JNU9335 (Xu et al, 2024). Instead of manually choosing between the many similar indices, the inherent patterns of the physicochemical properties can be extracted through their principle components, such as the Vectors of Hydrophobic, Steric, and Electronic properties (VSHE) (Mei et al, 2005), zscales (Hellberg et al, 1987;Jonsson et al, 1989;Sandberg et al, 1998;Wold et al, 2011), the DL-based amino acid parameter representations by Meiler et al (Meiler et al, 2001), or the five factors described by Atchley et al (Atchley et al, 2005).…”

Application of Directed Evolution and Machine Learning to Enhance the Diastereoselectivity of Ketoreductase for Dihydrotetrabenazine Synthesis

“…A variety of techniques, including error-prone PCR (epPCR), , saturation mutagenesis, and others, can be used to explore the vast sequence space and discover new biocatalysts. , Traditional directed evolution has been extensively used to improve the regioselectivity, diastereoselectivity, − and enzyme activity. , (2) Recently, machine learning has emerged as a powerful tool to support directed evolution, enabling the exploration of larger sequence spaces (Figure c). Numerous studies have demonstrated the capacity of machine learning to predict sequence-activity (selectivity) relationships. − While there has been considerable research in machine learning for protein engineering, − the approach is seldom used to achieve stereodivergent synthesis and only a limited number of studies have compared directed evolution and machine-directed evolution. , …”