Accessibility navigation

A principal odor map unifies diverse tasks in olfactory perception

Lee, B. K. ORCID:, Mayhew, E. J. ORCID:, Sanchez-Lengeling, B. ORCID:, Wei, J. N. ORCID:, Qian, W. W. ORCID:, Little, K. A. ORCID:, Andres, M. ORCID:, Nguyen, B. B., Moloy, T. ORCID:, Yasonik, J. ORCID:, Parker, J. K. ORCID:, Gerkin, R. C. ORCID:, Mainland, J. D. ORCID: and Wiltschko, A. B. ORCID: (2023) A principal odor map unifies diverse tasks in olfactory perception. Science, 381 (6661). pp. 999-1006. ISSN 1095-9203

Text - Accepted Version
· Please see our End User Agreement before downloading.


It is advisable to refer to the publisher's version if you intend to cite from this work. See Guidance on citing.

To link to this item DOI: 10.1126/science.ade4401


Mapping molecular structure to odor perception is a key challenge in olfaction. We used graph neural networks to generate a principal odor map (POM) that preserves perceptual relationships and enables odor quality prediction for previously uncharacterized odorants. The model was as reliable as a human in describing odor quality: On a prospective validation set of 400 out-of-sample odorants, the model-generated odor profile more closely matched the trained panel mean than did the median panelist. By 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.

Item Type:Article
Divisions:Life Sciences > School of Chemistry, Food and Pharmacy > Department of Food and Nutritional Sciences
ID Code:113304
Uncontrolled Keywords:Cheminformatics, Humans, Olfactory Perception, Smell, Neural Networks, Computer, Odorants
Publisher:American Association for the Advancement of Science


Downloads per month over past year

University Staff: Request a correction | Centaur Editors: Update this record

Page navigation