Enzymes in the thiolase superfamily catalyze carbon-carbon bond formation for the biosynthesis of polyhydroxyalkanoate storage molecules, membrane lipids and bioactive secondary metabolites. Natural and engineered thiolases have applications in synthetic biology for the production of high-value compounds, including personal care products and therapeutics. A fundamental understanding of thiolase substrate specificity is lacking, particularly within the OleA protein family. The ability to predict substrates from sequence would advance (meta)genome mining efforts to identify active thiolases for the production of desired metabolites. To gain a deeper understanding of substrate scope within the OleA family, we measured the activity of 73 diverse bacterial thiolases with a library of 15 p-nitrophenyl ester substrates to build a training set of 1095 unique enzyme-substrate pairs. We then used machine learning to predict thiolase substrate specificity from physicochemical and structural features. The area under the receiver operating characteristic curve was 0.89 for random forest classification of enzyme activity, and our regression model had a test set root mean square error of 0.22 (R2 = 0.75) to quantitatively predict enzyme activity levels. Substrate aromaticity, oxygen content and molecular connectivity were the strongest predictors of enzyme-substrate pairing. Key amino acid residues A173, I284, V287, T292 and I316 in the Xanthomonas campestris OleA crystal structure lining the substrate binding pockets were important for thiolase substrate specificity and are attractive targets for future protein engineering studies. The predictive framework described here is generalizable and demonstrates how machine learning can be used to quantitatively understand and predict enzyme substrate specificity.
Bibliographical noteFunding Information:
Raw data and scripts to reproduce analyses, figures and tables are available at https://github.com/serina-robinson/thiolase-ma chine-learning/. An interactive web application with a searchable database and predictive models trained on the complete dataset are also available at z.umn.edu/thiolases (shortened URL) and srobinson.shinyapps.io/thiolases (permanent URL). The DNA constructs, provided in Supplementary Material S1, will be provided upon request. The DNA constructs were provided by the United States Department of Energy Joint Genome Institute, a DOE Office of Science User Facility, under Contract No. DE-AC02-05CH11231. DNA requests will be honored with the completion of a Materials Transfer Agreement as required by our contracts with the U.S. Department of Energy.
We thank the U.S. Department of Energy Joint Genome Institute for synthetic DNA. The work conducted by the U.S. Department of Energy (DOE) Joint Genome Institute, a DOE
Office of Science User Facility, is supported under [DE-AC02-05CH11231]; The National Science Foundation Graduate Research Fellowship [00039202 to S.L.R.]; National Institutes of Health Biotechnology training grant [5T32GM008347-27 to M.D.S.]. We also acknowledge support from the MnDRIVE initiative for Industry and the Environment.
© The Author(s) 2020.
Copyright 2021 Elsevier B.V., All rights reserved.
- Enzyme activity screen
- Machine learning
- P-nitrophenyl esters
- Substrate specificity