BioNTech teams up with AI start-up to develop coronavirus early warning system

BioNTech, the German biotech group that co-developed one of the leading Covid-19 vaccines, has worked with InstaDeep, a north African startup, to create an early warning system that predicts the highest-risk coronavirus variants from their genetic code.

Using artificial intelligence (AI), the software tool developed by the two companies was able to identify more than 90 per cent of variants of concern, including the Omicron strain, on average two months before they were designated as high-risk by the World Health Organization (WHO), a study found.

The results from the study, which is yet to be peer reviewed, show that the tool can evaluate the risks of new variants from their spike proteins within minutes, and monitor them as they evolve “nearly in real time”. The two companies have agreed to make the tool freely available.

Ugur Sahin, chief executive of BioNTech, said: “Early flagging of potential high-risk variants could be an effective tool to alert researchers, vaccine developers, health authorities and policymakers, providing more time to respond to new variants of concern.”

The system identified Omicron as high risk on the same day its genomic sequence was first uploaded to the global Gisaid database late last year – three days before it was classified as a variant of concern by the WHO. It was one of more than 70,000 variants discovered between early October and late November, the study said. It was also able to flag the Alpha variant, which spread quickly in southern England last winter, 65 days before its official designation by the WHO.

Human experts cannot cope with complex data at scale

Using global sequence repositories such as Gisaid, the BioNTech/InstaDeep program scans hundreds of thousands of registered virus variants and analyses each variant’s ability to spread and its ability to evade existing immunity to the coronavirus. These two metrics are then combined to create a risk score. A higher score indicates increased risk of the variant affecting global health. Omicron scored extremely highly on both these metrics.

“More than 10,000 novel variant sequences are discovered every week and human experts simply cannot cope with complex data at this scale,” said Karim Beguir, co-founder and chief executive of InstaDeep. “For the first time, high-risk variants could be detected on the spot, potentially saving months of precious time.”

Emma Hodcroft, an evolutionary geneticist at the University of Bern, cautioned that “these predictions are only as good as the information we have to feed into them”. She added: “A lot of scientists also flagged Omicron on the day it was made available, but we’re still really limited by when we are able to sample such variants,” she said.

The ability to identify in advance which variants are high risk will help scientists adapt vaccines.