Scientists at the Scripps Research Translational Institute have developed a groundbreaking machine-learning system that can track the evolution of epidemic viruses and predict the emergence of new variants with unique properties. This type of artificial intelligence (AI) application focuses on monitoring the detailed evolution of viruses to provide early warnings for potential pandemics.
In a recent study published in Cell Patterns, the scientists demonstrated the effectiveness of their system by analyzing data on recorded SARS-CoV-2 variants and Covid-19 mortality rates. They were able to show that their AI-based system could have predicted the emergence of new variants of concern (VOCs) before they were officially designated by the World Health Organization (WHO).
The implications of this research are significant. The ability to predict viral variants and their associated properties in advance can play a crucial role in managing future viral pandemics effectively. There are rules of pandemic virus evolution that we have not understood but can be discovered and used in an actionable sense by private and public health organizations through this unprecedented machine-learning approach, said Professor William Balch from the Scripps Research Translational Institute.
To conduct their study, the team created machine-learning software using a technique called Gaussian process-based spatial covariance. They combined three data sets related to the Covid-19 pandemic: the genetic sequences of SARS-CoV-2 variants found globally, the frequency of these variants, and the global mortality rate for Covid-19. By analyzing these datasets, they were able to track the genetic changes occurring in SARS-CoV-2 variants around the world.
The researchers observed that certain genetic changes correlated with increased spread rates and decreased mortality rates, indicating the virus’s adaptations to various factors such as lockdowns, mask wearing, vaccines, and increasing natural immunity. These changes were identified weeks before the corresponding VOCs were officially designated by the WHO.
This tracking system for SARS-CoV-2 can serve as an early warning system, detecting gene variants associated with significant changes in viral spread and mortality rates. Its predictive capabilities allow health organizations to stay one step ahead and respond promptly to emerging variants.
The development of this AI-based tracking and early-warning system is a significant step forward in our ability to proactively address future viral outbreaks. By leveraging machine learning and analyzing large datasets in real-time, we can enhance our understanding of viral evolution and better prepare for global health challenges.
With further research and refinement, this technology could potentially be applied to other viral outbreaks, enabling us to identify patterns and trends that can lead to early intervention and containment. The combination of AI and epidemiology has the potential to revolutionize how we approach infectious diseases and improve global health outcomes.
It is necessary to continuously invest in these advancements and collaborate closely with public and private health organizations to harness the full potential of AI in virus tracking and mitigation. By leveraging the power of technology, we can prioritize global health and effectively combat future pandemics.
