Oregon State University (OSU) researchers trained a machine learning model to forecast whether new herbicides, fungicides, or insecticides would harm honey bees.
The researchers used honey bee toxicity data from pesticide exposure experiments involving roughly 400 pesticide molecules to teach an algorithm to predict a new pesticide molecule's toxicity.
OSU's Ping Yang said the model equates pesticide molecules with a series of random walks (mathematical equivalents of meandering paths) on their molecular graphs.
Yang explained, "The algorithm declares two molecules similar if they share many walks with the same sequence of atoms and bonds. Our model serves as a surrogate for a bee toxicity experiment and can be used to quickly screen proposed pesticide molecules for their toxicity."
From Oregon State University News
View Full Article
Abstracts Copyright © 2022 SmithBucklin, Washington, DC, USA
No entries found