Scientists create first AI-designed viruses to target drug-resistant superbugs

Scientists are using a new type of generative artificial intelligence to design specialized viruses that target and destroy harmful bacteria. The breakthrough could pave the way for a new generation of treatments capable of combating drug-resistant “superbugs.”

Using the AI model Evo 2, which can generate novel DNA sequences, scientists from Stanford University developed a series of viruses known as bacteriophages — microorganisms capable of destroying bacteria.

In laboratory tests, a mixture of 16 highly effective viruses designed with the help of Evo 2 rapidly destroyed E. coli bacteria that had already developed resistance to naturally occurring phages, Euronews reports.

E. coli is a group of bacteria that can cause intestinal infections and is becoming increasingly resistant to available antibiotics.

Antibiotic resistance is growing worldwide, largely due to the inappropriate and excessive use of these drugs. This drives bacteria to develop survival mechanisms that can render existing medicines ineffective.

“If bacteria develop resistance to one phage, the treatment is over,” said Brian Hie, a chemical engineer at Stanford University and co-author of the study.

“But if a mixture contains several genetically distinct phages, it will be much more difficult for bacteria to develop resistance to the entire cocktail.”

The researchers say the technology could eventually be used against other dangerous bacteria, including those that cause tuberculosis and common healthcare-associated infections such as MRSA (methicillin-resistant Staphylococcus aureus).

The researchers have made the Evo 2 AI model openly and freely available, raising concerns about its potential misuse.

The authors acknowledge that releasing the tool publicly has sparked discussions about safety. One major concern is that malicious actors could use modified versions of the technology to create dangerous biological agents.

“As the authors themselves point out, this raises serious regulatory and safety questions,” said Simon Clark, an associate professor of cellular microbiology at the University of Reading in the UK, who was not involved in the study.

“Although research of this kind is normally strictly controlled, it is somewhat reassuring that these scientists have taken additional precautions and incorporated important safeguards. But there is no guarantee that every other scientist who decides to pursue similar work will be equally cautious,” he added.

According to Clark, natural pathogens currently pose a much greater threat than AI-designed ones because they are easier to access and produce than entirely new agents created from scratch.

The authors say one advantage of AI-designed biology over natural evolution is that safety mechanisms can be incorporated directly into the design process.

Follow NEWS.am Medicine on Facebook and Twitter