This New AI Tool Can Track Virus Variants
This post is also available in: 
עברית (Hebrew)
Researchers at the University of Oxford and Harvard Medical School developed an artificial intelligence model that can predict new variants of viruses before they emerge, claiming it could have predicted mutations of the COVID-19 virus during the pandemic.
The model is named EVEscape- short for Evolutionary Model of Variant Effect. It combines a deep-learning model of how a virus evolves along with detailed biological and structural information about it. It is meant to help in the design of vaccines by studying how viruses mutate in response to the human immune system, with the University of Oxford saying this technology was “predicting the future”.
According to BBC News, during the COVID-19 pandemic, the waves were driven by different variants of the virus that had undergone multiple genetic changes, mutations that can alter the virus’s behavior and potentially make it spread faster or make it harder for our immune systems to recognize and fight off.
The research team described in an interview with the journal ‘Nature’ how the model works by predicting the likelihood that a viral mutation will enable it to escape immune responses, for example, by preventing antibodies from binding.
The model was reportedly tested with information that was available at the beginning of the COVID-19 pandemic in February 2020 and managed to successfully predict which SARS-CoV-2 mutations would occur and which would become most prevalent. The team reported that it also predicted which antibody-based therapies would lose their efficacy as the pandemic progressed and the virus developed mutations to escape these treatments.
Experts now hope the technology will help in prevention measures and the design of vaccines that target variants of concern before they become rampant.
Co-lead author for the study Pascal Notin said: “This work is of tremendous value, both for pandemic surveillance efforts, but also to inform vaccine design in a way that is robust to the emergence of certain at-risk mutations.”
