New AI Tool Envisions the Future of Viral Variants, Revolutionizing Vaccine Development
The COVID-19 pandemic caught the world off guard with its relentless wave of new SARS-CoV-2 variants, presenting challenges for vaccine development and containment efforts. However, scientists have now developed a groundbreaking artificial intelligence (AI) tool that can predict future viral variants before they emerge. The tool, called EVEscape, has been developed by researchers from Harvard Medical School and the University of Oxford.
EVEscape combines a model of evolutionary sequences with detailed biological and structural information about the virus. This unique combination enables the tool to make accurate predictions about the variants most likely to occur as the virus evolves. In a recent study published in Nature, the researchers demonstrated that if EVEscape had been deployed at the start of the COVID-19 pandemic, it would have accurately predicted the most frequent mutations and identified the most concerning variants for SARS-CoV-2. Remarkably, EVEscape also showed promise in predicting variants for other viruses, including HIV and influenza.
The researchers are now utilizing EVEscape to anticipate future variants of concern for SARS-CoV-2. Every two weeks, they release a ranking of new variants, providing valuable insights for vaccine development and therapeutic strategies. The potential implications of this tool are enormous, as it could greatly enhance scientists’ ability to design more effective vaccines and therapies. The team also plans to expand their work to include a wider range of viruses.
Senior author Debora Marks, associate professor of systems biology at Harvard Medical School, stated, 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.
The foundation of EVEscape originated from EVE (evolutionary model of variant effect), which was initially developed to analyze gene mutations causing human diseases. EVE utilizes a generative model to predict the functionality of proteins based on evolutionary data across different species. This approach has proven effective in discerning disease-causing mutations from benign ones, providing crucial insights into various conditions.
The researchers behind EVEscape recognized an opportunity to adapt EVE for the purpose of predicting viral variants amidst the ongoing COVID-19 pandemic. By integrating biological and structural details about the virus, including information about regions targeted by the immune system, they created a flexible framework that can be easily applied to any virus.
For their study, the researchers used EVEscape to predict the mutations that would occur in SARS-CoV-2 at the beginning of the pandemic. The tool accurately predicted these mutations with similar accuracy to experimental approaches that test the virus’s ability to bind to antibodies. Moreover, EVEscape outperformed the experimental approaches in identifying the most prevalent mutations. Crucially, EVEscape provided faster and more efficient predictions by eliminating the need to wait for relevant antibodies to emerge in the population.
EVEscape also successfully flagged antibody-based therapies that would lose their efficacy as the virus evolved and developed mutations to evade these treatments. Additionally, the tool was capable of sifting through the vast number of new SARS-CoV-2 variants produced weekly, highlighting those that were likely to pose problems.
The researchers have taken their work a step further by demonstrating the applicability of EVEscape to other common viruses, such as HIV and influenza. This adaptability showcases the potential of EVEscape in anticipating the evolution of various viral strains.
In real-time, the researchers are utilizing EVEscape to predict future variants of SARS-CoV-2, incorporating all available information to inform their predictions. To facilitate global awareness and collaboration, the team publishes a biweekly ranking of new variants on their website and shares this information with organizations like the World Health Organization. Furthermore, the complete code for EVEscape is freely available online.
The researchers are also testing EVEscape on understudied viruses, such as Lassa and Nipah, which have the potential for pandemic outbreaks but lack sufficient data for comprehensive analysis.
One of the critical applications of EVEscape lies in evaluating the effectiveness of existing and future vaccines and therapies against viral variants. This ability could help scientists design treatments that can withstand the escape mechanisms acquired by evolving viruses.
Nicole Thadani, a former research fellow in the Marks lab, expressed the significance of this approach, stating, We want to figure out how we can actually design vaccines and therapies that are future-proof.
The development of EVEscape represents a crucial breakthrough in predicting viral variants, offering invaluable insights for vaccine development and public health decision-making. By leveraging AI and evolutionary data, scientists are now equipped with a powerful tool to stay one step ahead of rapidly evolving viruses, potentially saving lives and mitigating the impact of future pandemics.
