A Machine Learning-Guided Approach to Navigate the Substrate Activity Scope of Galactose Oxidase: Application in the Conversion of Pharmaceutically Relevant Bulky Secondary Alcohols
Page view(s)
27
Checked on Feb 09, 2025
A Machine Learning-Guided Approach to Navigate the Substrate Activity Scope of Galactose Oxidase: Application in the Conversion of Pharmaceutically Relevant Bulky Secondary Alcohols
A Machine Learning-Guided Approach to Navigate the Substrate Activity Scope of Galactose Oxidase: Application in the Conversion of Pharmaceutically Relevant Bulky Secondary Alcohols
Supekar, S., Tay, D. W. P., Yeo, W. L., Tam, K. W. E., Koo, Y. S., See, J. Y., Miyajima, J. M. T., Maurer-Stroh, S., Ang, E. L., Lim, Y. H., & Fan, H. (2024). A Machine Learning-Guided Approach to Navigate the Substrate Activity Scope of Galactose Oxidase: Application in the Conversion of Pharmaceutically Relevant Bulky Secondary Alcohols. ACS Catalysis, 17233–17243. https://doi.org/10.1021/acscatal.4c04660
Abstract:
Biocatalysis is increasingly being adopted in industry for producing important chemicals in a selective and efficient manner. Engineering an enzyme can often confer it with an altered chemical scope, making it accessible to nontraditional and desirable chemistry. Identifying enzymes with the desired substrate specificity and activity, however, remains time-consuming and costly. Galactose oxidase (GOase) is a copper-dependent enzyme that converts alcohols to their corresponding carbonyls, an important transformation in industrial synthesis. Here, we present a machine learning aided protocol to develop a catalytic activity prediction model (R2 ∼ 0.7–0.9) for GOase based on a focused data set of engineered GOase variants with activity toward bulky benzylic secondary alcohols. The trained GOase activity prediction models (with no additional training) also partially retained their predictive power when applied to another member of the oxidase family, an aryl-alcohol oxidase. Inspired by the fragment-based optimization methods used in drug discovery, we developed an active-site structure-aware substrate library for select GOase variants. Experimental validation of a subset of the constructed substrate library against select variants indicates that the trained models provide reasonable prediction (R2 = 0.61) of GOase activity, enabling the identification of the best GOase variant from the select variant subset for each identified substrate. This ability to identify optimal GOase variants from the selected variants for the synthesis of industrially important chemicals was demonstrated for dyclonine, an FDA-approved drug. Our machine learning-guided approach enables rapid navigation of the substrate-activity scope of GOase, thereby reducing the burden of extensive experimental screening and streamlining the deployment of biocatalysis in industrial synthesis.
License type:
Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0)
Funding Info:
This research / project is supported by the Agency for Science, Technology and Research (A*STAR), Singapore - Advanced Manufacturing and Engineering (AME) SERC Strategic Funds
Grant Reference no. : A1718g0092
This research / project is supported by the Agency for Science, Technology and Research (A*STAR), Singapore - AME Industry Alignment Fund Prepositioning (IAF-PP) PIPS
Grant Reference no. : A19B3a0009
This research / project is supported by the Agency for Science, Technology and Research (A*STAR), Singapore - AME Industry Alignment Fund Prepositioning (IAF-PP) PIPS
Grant Reference no. : M23B3a0047
This research / project is supported by the Agency for Science, Technology and Research (A*STAR), Singapore - Strategic Research Programme (SIBER)
Grant Reference no. : C211917003
This research / project is supported by the Agency for Science, Technology and Research (A*STAR), Singapore - Strategic Research Programme (SIBER)
Grant Reference no. : C211917010
This research / project is supported by the Agency for Science, Technology and Research (A*STAR), Singapore - Strategic Research Programme (SIBER2.0)
Grant Reference no. : C233017004
This research / project is supported by the Agency for Science, Technology and Research (A*STAR), Singapore - Manufacturing Trade and Connectivity (MTC) Individual Research Grant (IRG)
Grant Reference no. : M22K2c0086