AI Article Synopsis
- Researchers organized the DREAM Olfaction Prediction Challenge to improve the prediction of how molecules produce odors, using crowd-sourced data.
- Teams created machine-learning algorithms that accurately forecasted odor intensity, pleasantness, and certain semantic descriptors like "sweet" and "flower."
- Regularized linear models showed predictive accuracy similar to more complex models, approaching a theoretical limit and enabling better understanding of molecules' sensory qualities.
Article 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.
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC5455768 | PMC |
| http://dx.doi.org/10.1126/science.aal2014 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Want AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!