Two views of 3D PCA data visualization of Mamastrovirus and Avastrovirus sequence k-mer frequencies: Astrovirus sequences from dataset 2 (with known genus labels) and 191 with genus labels predicted by 3PCM. astrovirus genome. For comparison purposes, HAstV and GoAstV are highlighted in different colors with the remaining mamastroviruses (non-HAstV mamastroviruses) and the remaining avastroviruses (non-GoAstV avastroviruses), respectively. The lavender surface shows the separation between two possible subgenera of mamastrovirus. The gray area indicates the separation between two possible subgenera of Avastrovirus. credit: Frontiers of molecular life science (2024). DOI: 10.3389/fmolb.2023.1305506
× close
Two views of 3D PCA data visualization of Mamastrovirus and Avastrovirus sequence k-mer frequencies: Astrovirus sequences from dataset 2 (with known genus labels) and 191 with genus labels predicted by 3PCM. astrovirus genome. For comparison purposes, HAstV and GoAstV are highlighted in different colors with the remaining mamastroviruses (non-HAstV mamastroviruses) and the remaining avastroviruses (non-GoAstV avastroviruses), respectively. The lavender surface shows the separation between two possible subgenera of mamastrovirus. The gray area indicates the separation between two possible subgenera of Avastrovirus. credit: Frontiers of molecular life science (2024). DOI: 10.3389/fmolb.2023.1305506
Researchers at the University of Waterloo have successfully classified 191 previously unidentified astroviruses using a new classification process powered by machine learning.
A study titled “Using Machine Learning for Taxonomic Classification of Emerging Astroviruses” recently Frontiers of molecular life science.
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 50% mortality rate in livestock, causing 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% of humans carry one of these viruses, and in some countries that number can reach 30%,” said Dr. Fatemeh Alipour. candidate in Computer Science at the University of Waterloo and lead author of the research study Computer Science. “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.”
For more information:
Fatemeh Alipour et al., Utilizing Machine Learning for Taxonomic Classification of Emerging Astroviruses, Frontiers of molecular life science (2024). DOI: 10.3389/fmolb.2023.1305506
