RT Journal Article
SR Electronic
T1 Reverse-engineering human olfactory perception from chemical features of odor molecules
JF bioRxiv
FD Cold Spring Harbor Laboratory
SP 082495
DO 10.1101/082495
A1 Keller, Andreas
A1 Gerkin, Richard C.
A1 Guan, Yuanfang
A1 Dhurandhar, Amit
A1 Turu, Gabor
A1 Szalai, Bence
A1 Mainland, Joel D.
A1 Ihara, Yusuke
A1 Yu, Chung Wen
A1 Wolfinger, Russ
A1 Vens, Celine
A1 Schietgat, Leander
A1 De Grave, Kurt
A1 Norel, Raquel
A1 ,
A1 Stolovitzky, Gustavo
A1 Cecchi, Guillermo
A1 Vosshall, Leslie B.
A1 Meyer, Pablo
YR 2016
UL http://biorxiv.org/content/early/2016/10/21/082495.abstract
AB Despite 25 years of progress in understanding the molecular mechanisms of olfaction, it is still not possible to predict whether a given molecule will have a perceived odor, or what olfactory percept it will produce. To address this stimulus-percept problem for olfaction, we organized the crowd-sourced DREAM Olfaction Prediction Challenge. Working from a large olfactory psychophysical dataset, teams developed machine learning algorithms to predict sensory attributes of molecules based on their chemoinformatic features. The resulting models predicted odor intensity and pleasantness with high accuracy, and also successfully predicted eight semantic descriptors (“garlic”, “fish”, “sweet”, “fruit”, “burnt”, “spices”, “flower”, “sour”). Regularized linear models performed nearly as well as random-forest-based approaches, with a predictive accuracy that closely approaches a key theoretical limit. The models presented here make it possible to predict the perceptual qualities of virtually any molecule with an impressive degree of accuracy to reverse-engineer the smell of a molecule.One Sentence Summary Results of a crowdsourcing competition show that it is possible to accurately predict and reverse-engineer the smell of a molecule.