German COVID-19 vaccine maker BioNTech has developed a method to quickly determine whether a new virus variant is a cause for concern, collaborating with UK artificial intelligence start-up InstaDeep.
In a joint statement, BioNTech and its partner said the new computational method, called the Early Warning System (EWS) can analyse genetic sequencing data of new coronavirus mutations found in infected people and assesses the risk they pose within days and sometimes within just minutes.
The company conducted an 11-month study that showcased the capabilities of EWS and found it could evaluate new variants within minutes, with the system identifying over 90 percent of the World health Organisation’s listed variants, including variants of concern, interest and variants under monitoring, on average two months in advance.
The alpha, beta, gamma, theta, eta and omicron variants were all detected by EWS in the same week its sequences were first uploaded. The omicron variant was even ranked as a high-risk variant the same day its sequence became available, according to BioNTech.
“Early flagging of potential high-risk variants could be an effective tool to alert researchers, vaccine developers, health authorities and policy makers, thereby providing more time to respond to new variants of concern,” said Ugur Sahin, CEO and co-founder of BioNTech.
The EWS algorithm assigns variants an immune escape score and a fitness prior score, which represents the variant’s transmissibility potential. Combining these two metrics produces a Pareto score which BioNTech says is the best assessment of the risk posed by a given virus variant.
The higher the score the higher the risk a variant has of impacting global health.
BioNTech noted that the EWS approach is solely dependent on existing data and is not dependent on a “wait-and-watch” approach.
“More than 10,000 novel variant sequences are currently discovered every week and human experts simply cannot cope with complex data at this scale, “ added Karim Beguir, Co-Founder and CEO of InstaDeep.
“For the first time, high-risk variants could be detected on the spot, potentially saving months of precious time. We are happy to make our research work publicly available and, most importantly, look forward to its continued real-world impact,” said Beguir.