期刊
SCIENCE
卷 355, 期 6327, 页码 820-+出版社
AMER ASSOC ADVANCEMENT SCIENCE
DOI: 10.1126/science.aal2014
关键词
-
资金
- NIH [R01DC013339, R01MH106674, R01EB021711, UL1RR024143]
- Russian Science Foundation [14-24-00155]
- Slovenian Research Agency [P2-0209]
- Research Fund KU Leuven
- Flemish Agency for Innovation by Science and Technology-Flanders-Strategic Basic Research Project (IWT-SBO) NEMOA
- Branco Weiss Science in Society Fellowship
- Hungarian Academy of Sciences
- Ontario Institute for Cancer Research - Government of Ontario
- Terry Fox Research Institute New Investigator Award
- Canadian Institutes of Health Research New Investigator Award
- Council of Scientific and Industrial Research-Central Scientific Instruments Organisation, Chandigarh, India
- Flemish Council of Scientific and Industrial Research (IWT) InSPECtor
- European Research Council (ERC) Proof of Concept SNIPER
- DREAM Olfaction Prediction Challenge
- Div Of Biological Infrastructure
- Direct For Biological Sciences [1300426] Funding Source: National Science Foundation
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.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据