Keller AYEN-JEN OYANG et al.2021-09-022021-09-02201700368075https://www.scopus.com/inward/record.uri?eid=2-s2.0-85013999403&doi=10.1126%2fscience.aal2014&partnerID=40&md5=fa5c346bb70dbc0088665759cf8165c9https://scholars.lib.ntu.edu.tw/handle/123456789/581540It is still not possible to predict whether a given molecule will have a perceived odor or what olfactory percept it will produce.We therefore organized the crowd-sourced DREAM Olfaction Prediction Challenge. Using a large olfactory psychophysical data set, teams developed machine-learning algorithms to predict sensory attributes of molecules based on their chemoinformatic features.The resulting models accurately predicted odor intensity and pleasantness and also successfully predicted 8 among 19 rated semantic descriptors ("garlic," "fish," "sweet," "fruit," "burnt," "spices," "flower," and "sour"). Regularized linear models performed nearly as well as random forest-based ones, with a predictive accuracy that closely approaches a key theoretical limit.These models help to predict the perceptual qualities of virtually any molecule with high accuracy and also reverse-engineer the smell of a molecule.algorithm; bioinformatics; data set; numerical method; odor; olfaction; olfactory cue; perception; Article; chemical structure; human; medical literature; odor; prediction; priority journal; psychophysiology; random forest; smelling; adult; biological model; information processing; male; Allium sativum; fragrance; Adult; Datasets as Topic; Humans; Male; Models, Biological; Odorants; Olfactory Perception; Smelljournal article10.1126/science.aal2014282199712-s2.0-85013999403