The Chemical Space of Terpenes: Insights from Data Science and AI

Abstract

Terpenes are a widespread class of natural products with significant chemical and biological diversity, and many of these molecules have already made their way into medicines. In this work, we employ a data science-based approach to identify, compile, and characterize the diversity of terpenes currently known in a systematic way, in a total of 59,833 molecules. We also employed several methods for the purpose of classifying terpene subclasses using their physicochemical descriptors. Light gradient boosting machine, k-nearest neighbours, random forests, Gaussian naïve Bayes and Multilayer perceptron were tested, with the best-performing algorithms yielding accuracy, F1 score, precision and other metrics all over 0.9, thus showing the capabilities of these approaches for the classification of terpene subclasses. These results can be important for the field of phytochemistry and pharmacognosy, as they allow the prediction of the subclass of novel terpene molecules, even when biosynthetic studies are not available.