Format

Send to

Choose Destination
Science. 2017 Feb 24;355(6327):820-826. doi: 10.1126/science.aal2014. Epub 2017 Feb 20.

Predicting human olfactory perception from chemical features of odor molecules.

Author information

1
Laboratory of Neurogenetics and Behavior, The Rockefeller University, New York, NY 10065, USA.
2
School of Life Sciences, Arizona State University, Tempe, AZ 85281, USA.
3
Department of Computational Medicine and Bioinformatics, University of Michigan, Ann Arbor, MI 48109, USA.
4
Thomas J. Watson Computational Biology Center, IBM, Yorktown Heights, NY 10598, USA.
5
Department of Physiology, Faculty of Medicine, Semmelweis University, 1085 Budapest, Hungary.
6
Laboratory of Molecular Physiology, Hungarian Academy of Science, Semmelweis University (MTA-SE), 1085 Budapest, Hungary.
7
Monell Chemical Senses Center, Philadelphia, PA 19104, USA.
8
Department of Neuroscience, University of Pennsylvania, Philadelphia, PA 19104, USA.
9
Institution for Innovation, Ajinomoto Co., Inc., Kawasaki, Kanagawa 210-8681, Japan.
10
SAS Institute, Inc., Cary, NC 27513, USA.
11
Department of Public Health and Primary Care, KU Leuven, Kulak, 8500 Kortrijk, Belgium.
12
Department of Computer Science, KU Leuven, 3001 Leuven, Belgium.
13
Flanders Make, 3920 Lommel, Belgium.
14
Department of Genetics and Genomic Sciences, Icahn School of Medicine at Mount Sinai, New York, NY 10029, USA.
15
Howard Hughes Medical Institute, New York, NY 10065, USA.
16
Thomas J. Watson Computational Biology Center, IBM, Yorktown Heights, NY 10598, USA. pmeyerr@us.ibm.com.

Abstract

It 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.

PMID:
28219971
PMCID:
PMC5455768
DOI:
10.1126/science.aal2014
[Indexed for MEDLINE]
Free PMC Article

Supplemental Content

Full text links

Icon for HighWire Icon for PubMed Central
Loading ...
Support Center