back Back

New AI tool predicts viral outbreaks, using generative model

Oct. 12, 2023.
2 min. read Interactions

AI tool predicts viral mutation and new variants

About the Writer

Amara Angelica

174.42073 MPXR

Amara Angelica is Editor, Mindplex

Immune escape occurs when the immune system of a host (especially of a human being) is unable to respond to an infectious agent—the host’s immune system is no longer able to recognize and eliminate a pathogen, such as a virus; EVEscape quantifies the viral escape potential of mutations at scale (credit: Harvard Medical School and the University of Oxford)

A radical new AI tool called EVEscape predicts viral mutations and new variants, using evolutionary biological information.

In tests, it successfully predicted the most concerning new SARS-CoV-2 (severe acute respiratory syndrome coronavirus 2) variants that occurred during the COVID-19 pandemic, according to its developers at Harvard Medical School and the University of Oxford. EVEscape can also help inform the development of vaccines and therapies for SARS-CoV-2 and other rapidly mutating viruses.

Model predicts changes about likely variants every two weeks

EVEscape has a generative model of evolutionary sequences that predicts changes that can occur to a virus, along with detailed biological and structural information about the virus. Together, they allow EVEscape to make predictions about the variants most likely to occur as the virus evolves.

In a study published Oct. 11 in Nature, the researchers show that if it had been deployed at the start of the COVID-19 pandemic, EVEscape would have predicted the most frequent mutations and identified the most concerning variants for SARS-CoV-2. The tool also made accurate predictions about other viruses, including HIV and influenza.

“We want to know if we can anticipate the variation in viruses and forecast new variants—because if we can, that’s going to be extremely important for designing vaccines and therapies,” said senior author Debora Marks, associate professor of systems biology in the Blavatnik Institute at Harvard Medical School.

From EVE to EVEscape

The researchers first developed EVE, short for evolutionary model of variant effect, in a different context: gene mutations that cause human diseases. In a previous study, EVE allowed researchers to discern disease-causing from benign mutations in genes linked to various conditions, including cancers and heart rhythm disorders.

Designing mutation-proof vaccines and therapies 

The team is now applying EVEscape to SARS-CoV-2 in real time, using all of the information available to make predictions about how it might evolve next. 

The researchers publish a biweekly ranking of new SARS-CoV-2 variants on their website and share this information with entities such as the World Health Organization. The complete code for EVEscape is also freely available online.

They are also testing EVEscape on understudied viruses such as Lassa and Nipah, two pathogens of pandemic potential for which relatively little information

Funding for the research was provided by the National Institutes of Health (GM141007-01A1), the Coalition for Epidemic Preparedness Innovations, the Chan Zuckerberg Initiative, GSK, the UK Engineering and Physical Sciences Research Council, and the Alan Turing Institute.

Citation: Thadani, N. N., Gurev, S., Notin, P., Youssef, N., Rollins, N. J., Ritter, D., Sander, C., Gal, Y., & Marks, D. S. (11-Oct-2023). Learning from prepandemic data to forecast viral escape. Nature, 1-8. (open-access)

Let us know your thoughts! Sign up for a Mindplex account now, join our Telegram, or follow us on Twitter

Comment on this content


0 thoughts on “New AI tool predicts viral outbreaks, using generative model




💯 💘 😍 🎉 👏
🟨 😴 😡 🤮 💩

Here is where you pick your favorite article of the month. An article that collected the highest number of picks is dubbed "People's Choice". Our editors have their pick, and so do you. Read some of our other articles before you decide and click this button; you can only select one article every month.

People's Choice