Pharmaceutical company BioNTech and startup InstaDeep have developed an AI early warning system (EWS) that analyzes SARS-CoV-2 genome sequencing data and predicts high-risk options.
We, together with @instadeepai, have developed an Early Warning System as a new computational method detecting high risk #SARS-CoV-2 variants. In trial period, the system identified> 90% of @WHO designated variants 2mths before their official designation. https://t.co/XJgH4LjHLE pic.twitter.com/vAQN2y9lVQ
– BioNTech SE (@BioNTech_Group) January 11, 2022
The new method combines the structural modeling of the viral spike protein and artificial intelligence algorithms. This allows the system to quickly flag potential dangerous variants of the coronavirus based on metrics that assess their fitness and ability to evade the immune response.
During trials, EWS identified over 90% of variants two months before it was identified WHO… The organization’s designated strains “alpha”, “beta”, “gamma”, “theta” and “this” were discovered by the system the same week that scientists uploaded information about them to the database. The omicron version was noted by EWS as high risk the same day its sequence became available.
The study results highlight that EWS can evaluate new variants in minutes and track their pedigrees in near real time. It is also able to scale as new data on coronavirus mutations emerge.
InstaDeep co-founder and CEO Karim Begir said that more than 10,000 new variation sequences are discovered every week, and human experts cannot handle complex data on this scale.
“This was the first time high risk options could be found on site, potentially saving months of valuable time,” he said.
Early detection of potentially dangerous strains of coronavirus could be an effective tool to alert researchers, vaccine developers and health authorities, giving them more time to respond, says BioNTech CEO and Founder Ugur Sakhin.
Recall that in December 2021, a Canadian scientist announced the development of an algorithm that discovered more than 1000 potential treatments for COVID-19.
In March, British scientists created an AI tool to diagnose coronavirus by the sound of a cough.