ScienceDaily: Researchers create computer models to predict whether pesticides will harm bees.


Share post:

Researchers at the Oregon State University College of Engineering used artificial intelligence to protect honeybees against pesticides.

Cory Simon, assistant professor in chemical engineering, and Xiaoli Flor, associate professor in computer science led the project. It involved training a machine-learning model to predict whether any new herbicide, fungicide, or insecticide would cause harm to honeybees based upon the compound’s molecular structures.

The cover of the magazine features the findings. The Journal of Chemical PhysicsSpecial issue: Chemical Design by Artificial Intelligence. This special issue is important because many fruit and vegetable, as well as seed crops, depend on bee pollination.

Nearly 100 American commercial crops would disappear if there were no bees to transmit the pollen necessary for reproduction. The global economic impact of bees is estimated at more than $100 billion annually.

Simon explained that although pesticides are widely used in agriculture which increase crop yields and provide food security, they can cause harm to off-target species, such as bees. “And insects, weeds, and others. New pesticides that aren’t harmful to bees must be constantly developed.

Adrian Henle, a graduate student, and Ping Yang, a graduate student, used honey bee toxicology data from pesticide-exposure experiments that involved nearly 400 pesticide molecules to create an algorithm to predict if the new pesticide molecule will be toxic to honeybees.

Yang stated that the model represented pesticide molecules through a set of random walks on their molecular charts.

Random walks are mathematical concepts that describe any path.

Yang says that it’s possible to imagine yourself going aimlessly along the chemical structure of a pesticide, going from one atom to the next using the bonds that hold the compound. While you travel in random directions, keep track of the route and the number of bonds and atoms that you have visited. You then go on another molecule and compare the twists, turns with what you have done before.

Yang explained that Yang used the algorithm to declare two molecules identical if they share many walks and have the same sequences of atoms or bonds. Our model can be used as a surrogate in a bee toxicology experiment, and it can be used to screen pesticide molecules for their toxicity.

This research was supported by the National Science Foundation.

Story Source:

MaterialsProvided by Oregon State University. Original by Steve Lundeberg Notice: Content can be edited to improve style and length.


Please enter your comment!
Please enter your name here


Related articles

The Benefits of a Creative Subscription with Envato Elements

If you’re looking to find and use royalty-free images and other creative resources, it can be tough to...

Get an Additional ₹100 Cashback When You Pay with Domino’s Digital Wallet Partners

How does ₹100 cashback sound? Find out more about the additional cashback you can get when you pay...

Get Unlimited Access to DataCamp’s Library of Online Courses

DataCamp subscriptions enable access to over 300 courses, as well as projects, assessments, and additional content. Whether you're...

Why You Should Buy from DaMENSCH: The Best in Quality, Service, and Value

Buying products online can be dangerous; you never know if you’re getting an authentic product, or one that’s...