“POM: A Principal Odor Map Unifies Diverse Tasks in Human Olfactory Perception”, Brian K. Lee, Emily J. Mayhew, Benjamin Sanchez-Lengeling, Jennifer N. Wei, Wesley W. Qian, Kelsie Little, Matthew Andres, Britney B. Nguyen, Theresa Moloy, Jane K. Parker, Richard C. Gerkin, Joel D. Mainland, Alexander B. Wiltschko2022-12-13 (Transformer, human olfaction)⁠:

[media] Mapping molecular structure to odor perception is a key challenge in olfaction.

Here, we use graph neural networks (GNN) to generate a Principal Odor Map (POM) that preserves perceptual relationships and enables odor quality prediction for novel odorants.

The model is as reliable as a human in describing odor quality: on a prospective validation set of 400 novel odorants, the model-generated odor profile more closely matched the trained panel mean (n = 15) than did the median panelist. Applying simple, interpretable, theoretically-rooted transformations, the POM outperformed chemoinformatic models on several other odor prediction tasks, indicating that the POM successfully encoded a generalized map of structure-odor relationships.

This approach broadly enables odor prediction and paves the way toward digitizing odors.

One-Sentence Summary: An odor map achieves human-level odor description performance and generalizes to diverse odor-prediction tasks.