More than 10,000 novel variant sequences of Covid are being discovered every week. AI is helping decipher them.

New Tech Entering The Battle With Covid Virus

If it were possible to catch a new variant of the Covid-19 virus, the world would be on board immediately. We have news from that says that early warning ability may just have been invented, with the help of AI.

BioNTech, the German biotech company that pioneered the messenger RNA technology behind the Pfizer COVID-19 vaccine, has teamed up with London-based A.I. company InstaDeep to create what the two firms say is an effective “early warning system” for spotting potentially dangerous new coronavirus variants.

In tests, the two companies said that their early warning system was able to pick up 12 of the 13 coronavirus variants that the World Health Organization has so far designated as potentially dangerous, doing so on average two months before the WHO reached that conclusion. For the Omicron variant, the system identified it as potentially dangerous on the same day its genetic sequence was first made available, according to a paper BioNTech and InstaDeep published on the non-peer-reviewed academic repository on Wednesday.

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

And while the virus continues to proliferate, it appears the new variants will be less fatal, also causing fewer hospitalizations of shorter duration. The science and medical fields are still struggling to keep up with vaccine formulas and even the number of doses needed to give protection from the virus. But progress is finally being made. And it takes AI to fully catalog this much data.

“…human experts simply cannot cope with complex data at this scale,’ Karim Beguir, the cofounder and chief executive of InstaDeep, said in a statement.”

Missed Delta, Caught Omicron

With this two-pronged approach, BioNTech and Instadeep used different models and older molecular simulation methods to study the disease.

Based on this modeling, the system awards the variant two scores: one for how easily that spike protein latches on to a receptor, called ACE 2, that it uses to invade human cells. The other score ranks how easily antibodies, such as those generated in people inoculated with BioNTech’s vaccine, can bind with that spike protein, preventing the virus from infecting cells. Both scores were validated using lab experiments.

The article by Jeremy Kahn goes into some detail about the science of predicting a changing variant. And he explains how this new system actually missed the Delta variant.

But for Omicron it was a quick catch for the system which holds great promise we can discover and develop medicine for whatever the virus throws at us next.

For Omicron, the researchers said, the system flagged the variant immediately, finding it had the highest “immune escape” score of any of the 70,000 variants that had been analyzed during the study period.

“With the advanced computational methods we have been developing over the past months, we can analyze sequence information of the spike protein and rank new variants according to their predicted immune escape and ACE2 binding score,” Sahin said.

Things are defiantly improving, but there is still such a long way to go. We will probably never get back to what the normal was prior to the virus, but we can create a new normal with the help of AI and the scientists who are using it for all our benefits.