AI-created flu vaccine starts testing in US

The drug wouldn't replace the old vaccine but would work with it, according to a report.

Shelby Brown Editor II
Shelby Brown (she/her/hers) is an editor for CNET's services team. She covers tips and tricks for apps, operating systems and devices, as well as mobile gaming and Apple Arcade news. Shelby also oversees Tech Tips coverage. Before joining CNET, she covered app news for Download.com and served as a freelancer for Louisville.com.
  • She received the Renau Writing Scholarship in 2016 from the University of Louisville's communication department.
Shelby Brown
2 min read
Flu vaccination

The flu vaccine is getting a boost from AI.

Picture Alliance / Getty Images

The flu vaccine isn't perfect, but Australian scientists are trying to make it work better. Researchers at Flinders University in South Australia have developed a way to use artificial intelligence to create a "turbocharged" flu vaccine.

A vaccine created with the computer program -- Smart Algorithms for Medical Discovery, or Sam for short -- started clinical trials in the US about a week ago, Flinders University Professor Nikolai Petrovsky said in an email to CNET.

Petrovsky told the Australian Broadcasting Corporation that Sam can be trained and can then learn to create new drugs. The researchers have used Sam to experiment with existing drugs known to work and those that failed. A drug developed by Sam would work in tandem with the existing flu vaccination to make it more effective. In his email, Petrovsky said the AI approach could also help design a flu vaccine that works independently but that the AI needs existing data to train on. 

"We essentially showed all of that to ... 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," Petrovsky said, according to the ABC report.

Petrovsky said in the email that his team still grapples with the way the flu virus is constantly mutating. 

"I believe that only a properly trained AI will have the ability to explore these patterns and choices [in the mutations] so that it can then actually predict where the virus is likely to go next," Petrovsky said, "so we can then use this to get it to design a vaccine that predicts against future flu viruses rather than past ones, which would then solve the problem of strain mismatch."   

Originally published July 3.
Update, July 12: Adds comments from Professor Nikolai Petrovsky.

Watch this: This pill expands to over 100x its own size
The information contained in this article is for educational and informational purposes only and is not intended as health or medical advice. Always consult a physician or other qualified health provider regarding any questions you may have about a medical condition or health objectives.