Opinion: AI Beats Animal Testing at Finding Toxic Chemicals

Machine learning could be the key to reducing the use of animals in experiments.

Written byThomas Hartung
| 3 min read
AI mice in labs

Register for free to listen to this article
Listen with Speechify
0:00
3:00
Share

ABOVE: MODIFIED FROM ©ISTOCK.COM, jxfzsy

There are more than 100,000 chemicals in consumer products. For the vast majority, there is very little information about their toxicity. Traditionally, researchers will test chemicals of interest in animals. As an extreme example, a pesticide undergoes about 30 animal tests, costing about $20 million and consuming more than 10,000 mice, rats, rabbits, and dogs over five years. About 20 kilograms of the chemical are needed for this testing; obtaining such a volume can be quite a challenge for a substance not yet on the market. Other substances receive less scrutiny, but even products with lower regulatory standards, such as industrial chemicals, can require $5 million worth of animal testing before entering the marketplace.

Our group, the Center for Alternatives to Animal Testing (CAAT) at Johns Hopkins University, sought a better way. As so many biologists are doing these days, we turned to intelligent computer ...

Interested in reading more?

Become a Member of

The Scientist Logo
Receive full access to digital editions of The Scientist, as well as TS Digest, feature stories, more than 35 years of archives, and much more!
Already a member? Login Here
Illustration of a developing fetus surrounded by a clear fluid with a subtle yellow tinge, representing amniotic fluid.
January 2026, Issue 1

What Is the Amniotic Fluid Composed of?

The liquid world of fetal development provides a rich source of nutrition and protection tailored to meet the needs of the growing fetus.

View this Issue
Redefining Immunology Through Advanced Technologies

Redefining Immunology Through Advanced Technologies

Ensuring Regulatory Compliance in AAV Manufacturing with Analytical Ultracentrifugation

Ensuring Regulatory Compliance in AAV Manufacturing with Analytical Ultracentrifugation

Beckman Coulter Logo
Skip the Wait for Protein Stability Data with Aunty

Skip the Wait for Protein Stability Data with Aunty

Unchained Labs
Graphic of three DNA helices in various colors

An Automated DNA-to-Data Framework for Production-Scale Sequencing

illumina

Products

nuclera logo

Nuclera eProtein Discovery System installed at leading Universities in Taiwan

Brandtech Logo

BRANDTECH Scientific Introduces the Transferpette® pro Micropipette: A New Twist on Comfort and Control

Biotium Logo

Biotium Launches GlycoLiner™ Cell Surface Glycoprotein Labeling Kits for Rapid and Selective Cell Surface Imaging

Colorful abstract spiral dot pattern on a black background

Thermo Scientific X and S Series General Purpose Centrifuges

Thermo Fisher Logo