Responses of olfactory receptors (ORs) can be predicted by applying machine learning methods on a multivariate encoding of an odorant's chemical structure. Physicochemical descriptors that encode features of the molecular graph are a popular choice for such an encoding. Here, we explore the EVA descriptor set, which encodes features derived from the vibrational spectrum of a molecule. We assessed the performance of Support Vector Regression (SVR) and Random Forest Regression (RFR) to predict the gradual response of Drosophila ORs. We compared a 27-dimensional variant of the EVA descriptor against a set of 1467 descriptors provided by the eDragon software package, and against a 32-dimensional subset thereof that has been proposed as the basis for an odor metric consisting of 32 descriptors (HADDAD). The best prediction performance was reproducibly achieved using SVR on the highest-dimensional feature set. The low-dimensional EVA and HADDAD feature sets predicted odor-OR interactions with similar accuracy. Adding charge and polarizability information to the EVA descriptor did not improve the results but rather decreased predictive power. Post-hoc in vivo measurements confirmed these results. Our findings indicate that EVA provides a meaningful low-dimensional representation of odor space, although EVA hardly outperformed "classical" descriptor sets.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.