AI Powers New Insights into H5N1 Viral Evolution

The H5N1 avian influenza virus has infected birds and animals worldwide. As of June 2025, 70 people had been infected, and one person had died in the United States.

A recent study found that the virus is developing more advanced methods to avoid the immune system. Researchers at the University of North Carolina at Charlotte (UNCC) used artificial intelligence to analyze hundreds of viral proteins. They discovered that the proteins’ connections to protective antibodies have weakened over time.

Newer versions of the virus are now better at evading the human immune system.

The virus has certainly mutated away from what we saw a decade ago. They do not even look the same.

Colby T. Ford, Ph.D, Study Lead and Computational Biologist, University of North Carolina at Charlotte

According to him, these changes increase the virus's potential to cause a pandemic. Vaccines developed a decade ago may not work well against the virus's current strains.

This has the potential to be bad,” Ford added.

Ford presented the findings at ASM Microbe 2025, the annual conference of the American Society for Microbiology in Los Angeles. He was joined by Shirish Yasa, B.S., who worked on the project as an undergraduate and is now studying at Eastern Virginia Medical School.

The researchers began by collecting data on more than 1,800 H5N1 proteins. They used AlphaFold 3, an artificial intelligence protein-folding algorithm, to predict the shapes of the viral proteins. Then, they applied physics-based modeling to measure how well 11 antibodies—collected from both humans and mice—attached to the proteins.

According to Ford, stronger bonds provide better protection. However, the analysis showed that the binding has been deteriorating over time.

Ford stated, “Antibody performance is waning as we get to the newer isolates that we are seeing.”

The team also used large H5N1 datasets to better understand how different viral clades relate to specific transmission patterns.

We can see that there are distinct clades with very different paths in terms of transmission between hosts,” Ford said.

Recently, the researchers linked the H5N1-related death of a person in Louisiana to a clade capable of spreading directly from birds to humans, without another animal in between.

These results suggest that the virus is finding ways to avoid the immune system, Ford said. They also show how AI and computer modeling could help scientists track the virus’s evolution and possibly develop more effective antibodies. In a preprint, the researchers describe a method for designing targeted treatments using molecular data from new and emerging strains.

Can we start to generate novel therapeutics based off those strains? The answer is yes, and we can do it fairly quickly with the AI pipeline we have built,” Ford concluded.

Tell Us What You Think

Do you have a review, update or anything you would like to add to this news story?

Leave your feedback
Your comment type
Submit

While we only use edited and approved content for Azthena answers, it may on occasions provide incorrect responses. Please confirm any data provided with the related suppliers or authors. We do not provide medical advice, if you search for medical information you must always consult a medical professional before acting on any information provided.

Your questions, but not your email details will be shared with OpenAI and retained for 30 days in accordance with their privacy principles.

Please do not ask questions that use sensitive or confidential information.

Read the full Terms & Conditions.