Using amino acid sequence to predict the range of substrates accepted by an enzyme is challenging. Although sequence- and structure-based annotation approaches are often accurate for predicting broad categories of substrates for a given enzyme, they generally cannot predict which specific molecules will be accepted as substrates, particularly within a class of closely related molecules. Combining targeted experimental activity data with structural modeling, ligand docking, and physicochemical properties of proteins and ligands in a machine learning model provides complementary information that can lead to accurate predictions of substrate scope for a series of related enzymes. Here we describe a random forest machine learning model that can predict the substrate scope of bacterial nitrilases, which catalyze the hydrolysis of nitrile compounds to the corresponding carboxylic acids and ammonia. The resulting model has an area under the receiver-operating characteristic (ROC) curve of 0.89 and an average accuracy of 84% for a set of 12 bacterial nitrilases and 20 nitriles. This approach is expected to be useful for predicting substrate scope of other enzymes when a modest amount of training data is available.

Combining structure-based modeling and machine learning to predict enzyme substrate scope: Application to bacterial nitrilases

Macromolecular Chemistry: The Second Century

[Author Benefits](https://scimeetings.acs.org/?utm_source=pubs_content_marketing&utm_medium=website&utm_campaign=0320_MCF_NPI_Launch_Spring_Homepage&ref=pubs_content_marketing)

[How to use SciMeetings](https://storage.googleapis.com/dl.morressier.com/acs/SciMeetings-ACSSpring2020-HowToGuide_M3020-Final.pdf)

[Frequently Asked Questions](https://storage.googleapis.com/dl.morressier.com/acs/SciMtng_ACSNMSp2020_FAQ_M3120_Final.pdf)

ACS Spring 2020 National Meeting & Expo

The official archive and repository for all ACS Meetings & Expositions abstracts and select posters or presentations.