Data Science Investment Counter —Funding raised by UK data science companies in 2018.
£ 5.640 Million

AI invents world’s most effective flu vaccine, researchers say

Scientists at Flinders University in Australia claim to have created the first artificial intelligence-designed flu vaccine, the ABC reported on Tuesday.

The vaccine, who has gone on trial in the US, has been described by the researchers as “turbo-charged”, which means that it contains an extra component able to stimulate the human immune system to make more antibodies against the flu virus than a normal vaccine.

Professor Nikolai Petrovsky told the ABC the drug was invented by a computer running a program called Sam. The researchers had the program experiment with existing working medicines but also with those that had failed.

“We essentially showed all of that to the AI program called Sam and then Sam came up with its own suggestion of what might be an effective adjuvant, which we then took and tested, and sure enough, it worked”, he explained.

Each year regular flu vaccine provide is inoculated to protect from four strains of the virus. The strains are decided on a yearly basis by the World Health Organisation, according to the most widespread in the previous northern or southern hemisphere flu seasons.

This year, for example, the Australian vaccine for people aged over 65 contained a component which boosted their immune system, just as the new drug by Flinders University.

The news of the new “AI-vaccine” comes amid an unusually harsh flu season in Australia, with 116,000 cases recorded and more than 220 lives claimed this year.

“We had a very low flu season last year, then a high what we call ‘inter-seasonal flu’ during summer, which has then morphed into an early flu season, which is really the earliest we’ve ever seen,” Australian chief medical officer Professor Brendan Murphy told the ABC.

“What we don’t know is whether this season will fade out early and not be a very big season, or whether it’ll continue at its current level with another strain becoming predominant. It’s very hard to predict.”

Professor Murphy added he was unaware of the Flinders University findings, but he welcomed the developments.

“The complexity of drug and receptor interactions is so huge that’s it’s very definitely enhanced by IT systems and AI systems,” he explained.

“So I think in general principles, it’s a very promising area to look at.”

Image via Pixabay and Needpix.


Co-working space and blog dedicated to all things data science.

Subscribe to our newsletter