Computer-generated flu vaccine enters clinical trials in the US

Computer-generated flu vaccine enters clinical trials in the US

• Download PDF Copy

By Lois Zoppi, BAJul 4 2019Reviewed by Kate Anderton, B.Sc. (Editor)

A seasonal flu vaccine has been developed at Flinders University in South Australia and is set to be tested in clinical trials in the US. The vaccine has been created with artificial intelligence and scientists claim that it is more effective than the traditional seasonal flu vaccine.

Tero Vesalainen | Shutterstock

Professor of medicine at Flinders University Nikolai Petrovsky and lead researcher on the vaccine said that to his knowledge, a flu vaccine developed with artificial intelligence had not advanced to clinical trials in humans, making this an exciting progression in vaccine development.

Petrovsky spoke on the clear need for an effective flu vaccine:

Despite currently available vaccines, flu remains a very major global health problem. So far in 2019 there have been over 96 thousand confirmed cases across Australia. The number in WA nearly doubled to 10 thousand, as did the number of deaths, there have been 57 deaths recorded in NSW, 44 in SA, and nearly 40 in Queensland.”

Nikolai Petrovsky, Lead Researcher

Halting the advancement of new drugs is the fact that the process to develop vaccines is labor-intensive and extremely costly, as Petrovsky explained.

“Normally, big companies […] will screen millions of compounds with thousands of people working week in week out on this for about five years. It costs hundreds of millions of dollars to come up with one lead.”

Speeding up the development process

Using artificial intelligence proved to substantially shorten the process, with Petrovsky’s research team only taking two years to develop the new vaccine.

Artificial intelligence uses artificial neural networks similar to the human brain and is able to recognize patterns and adapt to change. An extremely powerful resource, artificial intelligence can process significantly more information than the human brain and Petrovsky believes that artificial intelligence technology will be regularly used in drug development in as little as 20 years.

To develop this new vaccine, researchers created a computer program called Sam that they taught to recognize vaccines that were effective against flu and to identify those that were not.

Another computer program was created that Petrovsky described as a “mad chemist”, which was able to generate trillions of imaginary compounds. After this, a shortlist was compiled of the 10 most effective compound targets.

From this information, Sam was able to suggest a possible effective vaccine.

Petrovsky elaborated on the process:

Rather than screening millions of compounds, we only worked with a handful. It took just a few weeks to synthesize them and then we tested them on human blood. The compounds then went through animal testing and are now in humans.”

The human tests will use around 240 volunteers whose immune responses to the vaccine will be tested and analyzed. “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.

This comes just after the World Health Organization warned that the world is “not prepared enough” for a flu pandemic and developing new and more effective vaccines is urgently necessary.

The vaccine could be available within 3 years

The current flu vaccine does not give people complete protection against the illness, with the 2017 to 2018 flu season being served by a vaccine that only had a 10% efficacy among over 65s and an average of 15% efficacy across all age groups, as stated by Public Health England.

“AI has been progressively used in clinical decision-making – which drugs should I use for which patient. But drug design has been considered such a difficult thing to do it was thought to be beyond the capability of current AI. But we’ve shown that we can do it,” Petrovsky said.

If the vaccine progresses through the final stages of clinical trials, Petrovsky believes it could be available within the next three years.

“Given the need and the pull to provide a better flu vaccine this is not something that’s going to sit on the shelf for the next 10 years.”

The research, funded by the National Institute of Allergy and Infectious Diseases, part of the US National Institutes of Health, “represents the start of a new era where artificial intelligence is going to play an increasingly dominant role in drug discovery and design.”

Source:

U.S. clinical trials for more effective flu vaccine. Flinders University Press Release.