Predicting human olfactory perception from chemical features of odor molecules

• DOI: 10.1126/science.aal2014
• Publication Date: 2017-02-21T01:10:13Z
• Authors: Andreas Keller; Richard C. Gerkin; Yuanfang Guan; Amit Dhurandhar; Gabor Turu; Bence Szalai; Joel D. Mainland; Yusuke Ihara; Chung Wen Yu; Russ Wolfinger; Celine Vens; leander schietgat; Kurt De Grave; Raquel Norel; ; Gustavo Stolovitzky; Guillermo A. Cecchi; Leslie B. Vosshall; pablo meyer
• Keywords: Adult; Male; 0301 basic medicine; 570; neurológia; General Science & Technology; QD Chemistry / kémia; Neurosciences; Datasets as Topic; Biological; Olfactory Perception; Models, Biological; RC0321 Neuroscience. Biological psychiatry. Neuropsychiatry / idegkórtan; DREAM Olfaction Prediction Consortium; Smell; 03 medical and health sciences; Models; pszichiátria; Odorants; Humans

How will this molecule smell? We still do not understand what a given substance smell like. Keller et al. launched an international crowd-sourced competition in which many teams tried to solve how the of be perceived by humans. The were access database responses from subjects who had sniffed large number molecules and been asked rate each across range different qualities. also comprehensive list physical chemical features smelled. produced algorithms predict correspondence between quality molecule. best models that emerged challenge could accurately new would smell. Science , issue p. 820