Kavli Affiliate: Leslie B. Vosshall
| Authors: Vahid Satarifard, Laura Sisson, Yikun Han, Pedro Ilidio, Matej Hladis, Maxence Lalis, Xuebo Song, Wenjie Yin, Aharon Ravia, CiCi Xingyu Zheng, Gaia Andreoletti, Jake Albrecht, Robert Pellegrino, Zehua Wang, Stephen Yang, Robbe D’hondt, Achilleas Ghinis, Jasper de Boer, Felipe Kenji Nakano, Alireza Gharahighehi, DREAM Olfactory Mixtures Prediction Consortium, Benjamin Sanchez-Lengeling, Andreas Keller, Leslie B. Vosshall, Sebastien Fiorucci, Ambuj Tewari, Jeremie Topin, Celine Vens, Marten Bjorkman, Danica Kragic, Noam Sobel, Nicholas A. Christakis, Joel D. Mainland and Pablo Meyer
| Summary:
A central goal in sensory science is to establish quantitative mappings between physical stimuli and perceptual responses. While such mappings are well characterized in vision and audition, they remain poorly defined in olfaction, limiting progress toward understanding the representations of smell. Predicting perceptual similarity between odor mixtures offers a promising route to formalize these relationships. To advance this effort, the DREAM (Dialogue for Reverse Engineering Assessment and Methods) Olfactory Mixtures Prediction Challenge assembled a curated, cross-study dataset describing the similarity of 507 mixture pairs and an unpublished test set of 46 mixture pairs. Teams competed to predict the perceptual similarity of mixture pairs, and then collaborated post-challenge to create an ensemble combining top-performing models that notably improves predictions over the existing state-of-the-art models. Moreover, ensemble model maintains high predictive accuracy in novel validation set. Our model provides a reproducible framework for neuroscientists, chemists, and engineers to compare odor mixtures and provides a foundation for future efforts towards better understanding the olfactory properties of mixtures.