With the help of artificial intelligence, an international research team has made the first major progress ever toward a new and more effective way to combat monkeypox virus (MPXV). MPXV causes a painful and sometimes fatal illness that is particularly dangerous to children, pregnant women, and immunocompromised people. Published in the journal Science Translational Medicine, the team found that when mice were injected with an AI-recommended viral surface protein, the animals produced antibodies that neutralized MPXV, suggesting this breakthrough could be used in new mpox vaccines or antibody therapies.
In 2022, mpox began spreading around the world, causing flu-like symptoms and painful rashes and lesions in more than 150,000 people, and killing about 500 people. Vaccines developed to fight smallpox were repurposed to help the most vulnerable patients during smallpox epidemics, but because they are made from weakened whole viruses, they are complex and expensive.
“Unlike whole-virus vaccines, which are large-scale and complex to manufacture, our innovation is a single protein that is easy to make,” said Jason McClellan, a professor of molecular biosciences at the University of Texas at Austin and co-lead author of the study.
The study's other first authors, Lino Rapuoli and Emanuele Andreano of Italy's Fondazione Biotechnopolo Siena, helped identify 12 antibodies that effectively neutralize MPXV. Researchers used blood from patients who had previously been infected with the virus or been vaccinated to identify the antibodies, but they did not know which part of the virus they targeted.
That's because MPXV has dozens of different proteins on its surface. Scientists knew that at least one of these surface proteins was important for the spread of infection and could be blocked by some of the newly identified antibodies. But which one? They needed to find matches between surface proteins and antibodies, known as antigens, that would be suitable for new drugs and tools to help prevent infections.
Introducing the Texas team and the AI. McClellan and his lab at the University of Texas at Austin used the AlphaFold 3 model to predict which of about 35 different proteins on the surface of the virus antibodies would bind strongly to. The model reliably predicted that some antibodies bind to a viral surface protein called OPG153, and follow-up studies verified the results. This suggested that the protein would be a good target for developing new antibody therapies to treat mpox, or for use in vaccines to pacify a person's immune system and encourage it to fight the virus.
“Without AI, it would have taken us years to find this target,” said McClellan, the Robert A. Welch Chair in Chemistry and one of the leaders of Texas Biologics, a research group at Texas Biologics that works to develop new drugs and other medical advances. “It was really exciting because no one had looked at this before in vaccine or antibody development. It had never been shown to be a target for neutralizing antibodies.”
Because MPXV is closely related to the virus that causes smallpox, this discovery could lead to better vaccines and treatments for smallpox. Smallpox poses a high risk as a bioterrorism weapon because it is highly contagious and has a high mortality rate.
The research team is currently working to develop versions of vaccine antigens and antibodies that are more effective at fighting the disease, but also cheaper and easier to produce than existing versions that use weakened versions of closely related poxviruses. Ultimately, researchers hope to test vaccine antigens and antibody treatments to protect people from mpox and smallpox. McClellan calls the approach used in this study “reverse vaccinology.”
“We started with people who survived monkeypox virus infection, isolated the antibodies they naturally produce, and worked backwards to find which parts of the virus served as antigens for those antibodies. We then engineered the antigens to elicit similar antibodies in mice,” McClellan said.
UT Austin has filed a patent application for the use of OPG153 (and its derivatives) as a vaccine antigen. Fondazione Biotecnopolo di Siena has filed a patent for an antibody targeting OPG153.
Other co-authors from UT Austin are Emily Landrett, Lin Chow, and Connor Mullins.
Funding for this research was provided in part by the Welch Foundation.
/Open to the public. This material from the original organization/author may be of a contemporary nature and has been edited for clarity, style, and length. Mirage.News does not take any institutional position or position, and all views, positions, and conclusions expressed herein are those of the authors alone. Read the full text here.
