AI Framework Developed to Identify and Track COVID-19 Variants
The Universities of Manchester and Oxford have made a groundbreaking discovery in the fight against COVID-19. A new AI framework developed by scientists at these institutions can identify and track new and concerning variants of the virus, such as alpha, delta, and omicron, at an early stage. This framework, presented in the journal PNAS, combines dimension reduction techniques and a new explainable clustering algorithm called CLASSIX.
The high mutation rate and rapid evolution of COVID-19 make it challenging to identify problematic strains in the vast amount of genomic data available. However, the new AI framework can process 5.7 million sequences in just one to two days on a standard laptop, making it more accessible to researchers. This automation of tasks allows for quicker identification of concerning pathogen strains and frees up human experts for other vital developments.
The AI framework breaks down genetic sequences of the virus into smaller “words” and groups similar sequences together based on their patterns using machine learning techniques. The clustering algorithm CLASSIX is less computationally demanding than traditional methods and provides textual and visual explanations of the computed clusters.
This new approach serves as a proof of concept for the potential use of machine learning methods in early detection of emerging variants without relying solely on phylogenetic analysis. While phylogenetics remains important for understanding viral ancestry, machine learning methods can handle a much larger number of sequences at a lower computational cost.
The research team believes that this AI framework could revolutionize the way we track and respond to viral outbreaks in the future. By identifying concerning variants early on, researchers can be more proactive in developing tailored vaccines and potentially eliminate these variants before they become established. This innovative technology represents a significant step forward in the ongoing battle against COVID-19 and other infectious diseases.
