Machine learning identifies the next deadly virus

thank you. Listen to this article using the player above. ✖

Researchers at the University of Waterloo have successfully classified 191 previously unidentified astroviruses using a new machine learning-enabled classification process.

Astrovirus is one of the most harmful and widespread viruses in the world. These viruses cause severe diarrhea that kills more than 440,000 children under the age of 5 each year. In the poultry industry, astroviruses like avian influenza have an 80% infection rate and a 50% mortality rate in livestock, leading to economic devastation, supply chain disruptions, and food shortages.

Because astroviruses can mutate rapidly and spread easily to more than 160 host species, researchers and public health officials are in a constant race to classify and understand new astroviruses as they emerge. Exposed. In 2023, there were 322 unidentified astroviruses with different genomes. This year, that number has increased to 479.

“At any given time, between 2 and 9 percent of humans carry one of these viruses, and in some countries that number can be as high as 30 percent,” said Dr. candidate and computer science lead author of the research study, Fatemeh Alipour said. “Effectively understanding and classifying these viruses is essential to developing vaccines.”

The astrovirus research team included computer science researchers from the University of Waterloo and biology researchers from the University of Western Ontario.

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

“The main idea behind this classification method is to leverage machine learning to classify species by learning from their 'genomic features,'” said David R. Cheriton, a professor in the School of Computer Science. said one Lila Kali. “This classification method is interesting both in terms of speed and general applicability.”

“This method helps us understand how viruses are transmitted between different animals. It can also be used to classify viruses into other virus families, such as HIV and dengue.”

reference: Alipour F, Holmes C, Lu YY, Hill KA, Kari L. Leveraging machine learning for taxonomic classification of emerging astroviruses. front mole biosi. 2024;10:1305506. doi: 10.3389/fmolb.2023.1305506

This article has been reprinted from the following material: Note: Materials may be edited for length and content. Please contact the citation source for details.You can access our press release publishing policy here.