Researchers trained a computer model to predict which smells honey bees avoid, then screened over 50 million compounds and found more than 130 candidates. The top seven repelled free-flying bees in field tests, which could help keep bees off pesticide-treated crops.
1
A machine-learning model predicting bee aversion from chemical structure screened more than 50 million compounds and flagged over 130 repellent candidates.
2
Laboratory tests with honey bees showed high predictive success, and data from honey bees and Drosophila fruit flies was used to refine the model.
3
The top seven candidates strongly repelled freely foraging honey bees in a field assay.
mail
Weekly plant science — one email, Saturdays.
Check your inbox to confirm — link expires in 24 hours.
Something went wrong — please try again.
Too many signup attempts from your network. Try again in an hour, or email hello@plant.news.