A research team from Oregon State University’s College of Engineering has employed Artificial Intelligence to help protect bees from pesticides.
Cory Simon, Assistant Professor of Chemical Engineering, and Xiaoli Fern, Associate Professor of Computer Science, led the project together. The study involved developing a machine learning model that was capable of predicting whether any proposed new herbicide, fungicide, or insecticide would be toxic to honeybees based on the compound’s molecular structure.
The findings from this study are featured on the cover of the Journal, Chemical Physics, in a special issue titled: Chemical Design by Artificial Intelligence. The scientists have emphasised that these results are significant, as they demonstrate how the majority of fruits, nuts, vegetables, and seed crops rely on bee pollination to flourish.
The National Science Foundation supported this research.
The global economic impact of bees
Without bees to transfer the pollen needed for reproduction, almost 100 commercial crops in the United States would vanish. The global economic impact bees have is annually estimated to exceed $100bn.
“Pesticides are widely utilised in agriculture, which increases crop yield and provides food security, but pesticides can harm off-target species like bees,” explained Simon. “And since insects, weeds, etc. eventually evolve resistance, new pesticides must continually be developed, ones that do not harm bees.”
Protecting bees from pesticides
Graduate students Ping Yang and Adrian Henle utilised honeybee toxicity data from pesticide exposure experiments, which involved approximately 400 different pesticide molecules, to create an algorithm capable of predicting the potential toxicity of a new pesticide molecule to honeybees.
“The model represents pesticide molecules by the set of random walks on their molecular graphs,” added Yang.
A random walk is considered a mathematical concept, which describes any meandering path, such as on the complicated chemical structure of a pesticide, where each step along the path is decided by chance.
“Imagine that you are out for an aimless stroll along a pesticide’s chemical structure, making your way from atom to atom via the bonds that hold the compound together. You travel in random directions but keep track of your route, and the sequence of atoms and bonds that you visit. Then you go out on a different molecule, comparing the series of twists and turns to what you have done before.
“The algorithm declares two molecules similar if they share many walks with the same sequence of atoms and bonds,” concluded Yang. “Our model serves as a surrogate for a bee toxicity experiment and can be utilised to quickly screen proposed pesticide molecules for their toxicity.”
