Immunotherapy company BioNTech and AI-company InstaDeep have developed a new computational method that analyses worldwide sequencing data to predict high-risk variants of SARS-CoV-2. The Early Warning System (EWS) uses AI calculated immune escape and fitness metrics.
Detecting High-Risk Variants
By combining structural modeling of the viral Spike protein and AI algorithm, the method quickly detects potential high-risk variants entered into SARS-CoV-2 sequence data repositories. It can do this within one day, and the companies were able to validate the predictions by using generated and publicly available data.
The system identified more than 90% of the World Health Organization (WHO)-designated variants on average two months in advance. For the variants Alpha, Beta, Gamma, Theta, Eta, and Omicron, the EWS detected them in the same week its sequence was first uploaded.
The new study demonstrates that the EWS can evaluate new variants in a matter of minutes, and it is fully scalable as new variant data is released.
BioNTech and InstaDeep
Ugur Sahin, M.D., is Chief Executive Officer and Co-Founder of BioNTech.
“With the advanced computational methods we have been developing over the past months we can analyse sequence information of the Spike protein and rank new variants according to their predicted immune escape and ACE2 binding score,” said Sahin. “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.”
Karim Beguir is Co-Founder and CEO of InstaDeep.
“More than 10,000 novel variant sequences are currently discovered every week and human experts simply cannot cope with complex data at this scale. We’ve addressed this challenge by deploying the powerful AI capabilities of InstaDeep’s DeepChain platform combined with BioNTech’s SARS-CoV-2 know-how and technology. 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,” Beguir said.
During a 11-month period, the EWS was able to distinguish the WHO-designated variants from the undesignated ones.
The newly developed system comes as BioNTech and InstaDeep continue to work together to combine AI and immunology, which the companies have been doing since November 2020. The two companies established a joint AI innovation Lab in London, UK, and Mainz, Germany. The lab is aimed at advancing novel drug discovery and design, protein engineering, manufacturing, and supply chain optimization.
- The Black Box Problem in LLMs: Challenges and Emerging Solutions
- Alex Ratner, CEO & Co-Founder of Snorkel AI – Interview Series
- Circleboom Review: The Best AI-Powered Social Media Tool?
- Stable Video Diffusion: Latent Video Diffusion Models to Large Datasets
- Donny White, CEO & Co-Founder of Satisfi Labs – Interview Series