Frontiers in Molecular Biosciences: Researchers use AI to identify 191 new destructive viruses

Researchers from the University of Waterloo (Canada) have successfully classified, using artificial intelligence, 191 previously unidentified astroviruses. Their research was published in the scientific journal Frontiers in Molecular Biosciences.

Astroviruses are some of the most damaging and widespread viruses in the world. In humans, these viruses cause severe diarrhea, which kills more than 440,000 children under the age of five annually.

In the poultry industry, astroviruses like avian flu have an 80 percent infection rate and a 50 percent mortality rate among livestock. 

The new three-part classification method includes supervised machine learning, unsupervised machine learning, and manual labeling of each astrovirus’s host.

In 2023, there were 322 unidentified astroviruses with distinct genomes. This year, that number has risen to 479.

“At any given point, between two and nine percent of humans carry one of these viruses. That number can be as high as 30 per cent in some countries,” said Fatemeh Alipour, PhD candidate in computer science at Waterloo and the lead computer science author of the aforesaid research study. “Understanding and classifying these viruses effectively is essential for developing vaccines.”

Follow NEWS.am Medicine on Facebook and Twitter