AI finds previously unknown associations of viruses with mammals

New study from the University of Liverpool will help scientists mitigate the spread of zoonotic and livestock diseases caused by existing viruses. To do this, an AI-based model predicted which animals could carry certain viruses.

Researchers have used AI-powered machine learning to predict over 20,000 unknown associations between viruses and susceptible mammalian species. The results of the study, published in the journal Nature Communications, can be used to develop disease surveillance programs.

Scientists already knew that thousands of viruses infect mammals, with the latest estimates that less than 1% of the viral diversity of mammals has been discovered to date. Some of these viruses, such as human immunodeficiency viruses and feline immunodeficiency viruses, have a very narrow host range, while others, such as rabies and West Nile viruses, have a very wide host range.

“Habitat is an important indicator of whether a virus is zoonotic and therefore a danger to humans. More recently, it was found that SARS-CoV-2 has a relatively wide range of hosts – this has contributed to its spread among humans. However, our knowledge of the habitat of most viruses remains limited, ”the researchers note.

To close this gap, the researchers developed a new machine learning system to predict unknown associations between viruses and susceptible mammalian species.

Their results indicate that there are five times more associations between known zoonotic viruses and wild and semi-domestic mammals than previously thought. In particular, bats and rodents, which have been linked to recent outbreaks of new viruses such as coronaviruses and hantaviruses, have been associated with an increased risk of contracting zoonotic viruses.

The model also predicts a five-fold increase in associations between wild and semi-domesticated mammals and viruses of economically important domestic species.

“As viruses continue to move around the globe, our model provides an opportunity to assess potential hosts that they have yet to meet. Such foresight can help in identifying and mitigating the risks of animal diseases that can spread to the human population, ”the researchers added.

If you have found a spelling error, please, notify us by selecting that text and pressing Ctrl+Enter.

Leave a Comment

This site uses Akismet to reduce spam. Learn how your comment data is processed.

Alexandr Ivanov earned his Licentiate Engineer in Systems and Computer Engineering from the Free International University of Moldova. Since 2013, Alexandr has been working as a freelance web programmer.
Function: Web Developer and Editor
Alexandr Ivanov

Spelling error report

The following text will be sent to our editors: