PT  - JOURNAL ARTICLE
AU  - Lee, Brian K.
AU  - Mayhew, Emily J.
AU  - Sanchez-Lengeling, Benjamin
AU  - Wei, Jennifer N.
AU  - Qian, Wesley W.
AU  - Little, Kelsie
AU  - Andres, Matthew
AU  - Nguyen, Britney B.
AU  - Moloy, Theresa
AU  - Parker, Jane K.
AU  - Gerkin, Richard C.
AU  - Mainland, Joel D.
AU  - Wiltschko, Alexander B.
TI  - A Principal Odor Map Unifies Diverse Tasks in Human Olfactory Perception
AID  - 10.1101/2022.09.01.504602
DP  - 2022 Jan 01
TA  - bioRxiv
PG  - 2022.09.01.504602
4099  - http://biorxiv.org/content/early/2022/09/06/2022.09.01.504602.short
4100  - http://biorxiv.org/content/early/2022/09/06/2022.09.01.504602.full
AB  - 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.Competing Interest StatementThe authors have declared no competing interest.