Navigating the Fragrance Space Using Graph Generative Models and Predicting Odors

Abstract

We explore a suite of generative modeling techniques to efficiently navigate and explore the complex landscapes of odor and the broader chemical space. Unlike traditional approaches, we not only generate molecules but also predict the odor likeliness with a ROC AUC score of 0.97 and assign probable odor labels. We correlate odor likeliness with physicochemical features of molecules using machine learning techniques and leverage SHAP (SHapley Additive exPlanations) to demonstrate the interpretability of the function. The whole process involves four key stages: molecule generation, stringent sanitization checks for molecular validity, fragrance likeliness screening, and odor prediction of the generated molecules. By making our code and trained models publicly accessible, we aim to facilitate the broader adoption of our research across applications in fragrance discovery and olfactory research.