AI pinpointed a hidden viral weak spot, revealing a promising path to next-generation monkeypox and smallpox protection. Credit: Shutterstock
Scientists leveraged AlphaFold 3 to pinpoint a previously overlooked monkeypox protein that antibodies latch onto. By injecting this AI-identified antigen into mice, researchers triggered strong neutralizing responses.
The finding could pave the way for safer, simpler vaccines and antibody therapies. It may even bolster defenses against smallpox biothreats.
AI Helps Researchers Identify a New Path to Mpox Protection
With support from artificial intelligence, an international research team has taken an important step toward developing a more efficient way to defend against the monkeypox virus (MPXV). This virus can cause severe …
AI pinpointed a hidden viral weak spot, revealing a promising path to next-generation monkeypox and smallpox protection. Credit: Shutterstock
Scientists leveraged AlphaFold 3 to pinpoint a previously overlooked monkeypox protein that antibodies latch onto. By injecting this AI-identified antigen into mice, researchers triggered strong neutralizing responses.
The finding could pave the way for safer, simpler vaccines and antibody therapies. It may even bolster defenses against smallpox biothreats.
AI Helps Researchers Identify a New Path to Mpox Protection
With support from artificial intelligence, an international research team has taken an important step toward developing a more efficient way to defend against the monkeypox virus (MPXV). This virus can cause severe pain and can be life-threatening, especially for children, pregnant women, and people with weakened immune systems. In findings published today (December 10) in Science Translational Medicine, the scientists reported that mice produced strong, neutralizing antibodies after being injected with a viral surface protein selected through AI analysis. The result points to the potential for a new mpox vaccine or antibody-based treatment.
In 2022, mpox circulated globally and infected more than 150,000 people, leading to nearly 500 deaths. Symptoms ranged from flu-like illness to painful rashes and lesions. During the outbreak, health officials relied on smallpox vaccines to protect those at the highest risk. However, manufacturing those vaccines is challenging and costly because they rely on a full, weakened virus.
“Unlike a whole-virus vaccine that’s big and complicated to produce, our innovation is just a single protein that’s easy to make,” said Jason McLellan, a professor of molecular biosciences at The University of Texas at Austin and co-lead author of the study.
Structure of a surface protein on the monkeypox virus (MPXV OPG153, highlighted in pink) in complex with two neutralizing antibodies: 08E11 (highlighted in blue) and 12I12 (highlighted in yellow). Credit: University of Texas at Austin
Finding the Antibodies That Neutralize Monkeypox
Two of the study’s lead authors, Rino Rappuoli and Emanuele Andreano of the Fondazione Biotecnopolo di Siena in Italy, identified 12 antibodies that effectively shut down MPXV. They analyzed blood samples from people who had either recovered from the virus or received a vaccine, which revealed the antibodies but not the specific viral targets they attached to.
MPXV carries many different proteins on its surface, and at least one is essential for allowing the virus to spread. Some of the newly identified antibodies were known to block that critical protein, but researchers did not know which one. To move forward with vaccine or drug development, they needed to determine the exact match between an antibody and the viral protein it recognizes, also known as an antigen.
AI Pinpoints a Promising Viral Target
The Texas research group used the AlphaFold 3 model to predict which of the roughly 35 surface proteins on MPXV the antibodies were most likely to bind. According to the model, several antibodies were predicted with high confidence to target a protein called OPG153. Laboratory testing later confirmed that prediction. This discovery indicated that OPG153 could serve as a strong candidate for designing new antibody treatments or vaccine components aimed at stimulating an immune response to mpox.
“It would have taken years to find this target without AI,” said McLellan, the Robert A. Welch Chair in Chemistry and one of the leaders of Texas Biologics, a research group at UT Austin working to develop new drugs and other medical advances. “It was really exciting because no one had ever considered it before for vaccine or antibody development. It had never been shown to be a target of neutralizing antibodies.”
Because MPXV is closely related to the virus responsible for smallpox, this insight may also guide the development of better vaccines or therapies for smallpox, which remains a concern due to its high fatality rate and potential misuse as a bioterrorism weapon.
Advancing Toward Next-Generation Vaccines and Therapies
The researchers are now refining versions of the antigen and antibodies that could offer strong protection while being easier and cheaper to produce than existing options, which rely on weakened forms of related poxviruses. Their goal is to eventually test these vaccine antigens and antibody treatments in people to guard against mpox and smallpox. McLellan describes the strategy used in this work as “reverse vaccinology.”
“We started with people who survived infection with monkeypox virus, isolated antibodies that they naturally produced and worked backward to find what part of the virus acted as the antigen for those antibodies. Then we engineered the antigen to elicit similar antibodies in mice,” McLellan said.
Reference: “Antigen-agnostic identification of poxvirus broadly neutralizing antibodies targeting OPG153” 10 December 2025, Science Translational Medicine. DOI: 10.1126/scitranslmed.aeb3840
UT Austin has filed a patent application on the use of OPG153 (and its derivatives) as a vaccine antigen. The Fondazione Biotecnopolo di Siena filed a patent application on antibodies that target OPG153.
The other UT Austin co-authors are Emily Rundlet, Ling Zhou and Connor Mullins.
This work was funded in part by the Welch Foundation.
Never miss a breakthrough: Join the SciTechDaily newsletter. Follow us on Google and Google News.