AI Models Forecast Viral Mutations, Enhancing Pandemic Preparedness

AI  is playing a significant role in helping scientists predict how viruses evolve, potentially improving pandemic preparedness and aiding in the development of vaccines and antiviral treatments.

While predicting viral evolution is still in its infancy, researchers are using AI to forecast how RNA viruses, like SARS-CoV-2 and influenza, will mutate, as detailed in a new report by Nature.

RNA viruses constantly accumulate mutations, some of which may enable them to escape immune detection and spread more easily. Nature notes that by forecasting these mutations, scientists could design more effective vaccines and treatments ahead of time, addressing future threats before they become widespread.

Currently, AI tools are able to predict which single mutations are likely to be successful and which viral variants might dominate in the short term. However, Nature says that predicting long-term changes or complex combinations of mutations remains a challenge.

AI’s role in this field has been bolstered by advanced protein-structure prediction models like AlphaFold, ESM-2, and ESMFold, which analyze how mutations affect viral proteins. Nature says that these tools are revolutionizing the ability to simulate viral evolution and help scientists understand how viruses like SARS-CoV-2 adapt over time.

The availability of massive amounts of genetic data is crucial for AI models to predict viral evolution. With nearly 17 million sequenced SARS-CoV-2 genomes, AI models have a wealth of data to train on, allowing researchers to simulate potential future variants, says Nature.

For example, the CoVFit model, developed by Jumpei Ito’s team at the University of Tokyo, has been instrumental in predicting which SARS-CoV-2 variants are likely to spread and dominate in the population, as reported by Nature.

In addition to tracking known viruses, AI is also helping scientists uncover new ones. A study published in October revealed that researchers used AI to identify 70,500 new RNA viruses, many of which thrive in extreme environments such as salt lakes and hydrothermal vents.

This study applies metagenomics, allowing scientists to analyze genetic material from diverse ecosystems without growing individual viruses in the lab.

Despite progress, Nature says that challenges remain when trying to accurately predict sudden viral leaps, such as the emergence of the Omicron variant, which introduced more than 50 mutations in a single leap.

For these AI models to become even more accurate, they need more than five years of data on viral evolution, says Nature. Combining surveillance sequencing with experimental data will improve predictions and help researchers stay ahead of evolving viral threats.