Artificial intelligence predicts unknown links between viruses and mammals

Share
An abstract representation of networks of (1) observed and (2) predicted associations between wild and semi-domesticated mammalian hosts and known virus species. Image: Dr Maya Wardeh
An abstract representation of networks of (1) observed and (2) predicted associations between wild and semi-domesticated mammalian hosts and known virus species. Image: Dr Maya Wardeh

Scientists appear to be under-estimating the reach of viruses, in terms of the number of animal species they are capable of infecting, research findings suggest.

Thousands of viruses are known to affect mammals, with recent estimates indicating that less than 1% of mammalian viral diversity has been discovered to date.

Some of these viruses have a very narrow host range, whereas others such as rabies and West Nile viruses have very wide host ranges.

Researches acknowledge that our knowledge of viral host ranges remains limited.

Building this picture by identifying unknown hosts of known viruses is an important research aim that can help identify and reduce disease risk, including spill-overs from animal reservoirs into human populations.

Researchers at the University of Liverpool used a form of artificial intelligence called machine-learning to predict more than 20,000 unknown associations between known viruses and susceptible mammalian species.

The findings, published in the journal Nature Communications, could be used to help target disease surveillance programmes.

These results showed that their approach can highlight large numbers of potentially missing associations of medically- and veterinary-important viruses and their potential hosts.

“Host range is an important predictor of whether a virus is zoonotic and therefore poses a risk to humans,” said lead researcher Dr Maya Wardeh, from the university’s Institute of Infection, Veterinary and Ecological Sciences.

“Most recently, SARS-CoV-2 has been found to have a relatively broad host range which may have facilitated its spill-over to humans. However, our knowledge of the host range of most viruses remains limited.”

To address this knowledge gap, the researchers developed a novel machine learning framework to predict unknown associations between known viruses and susceptible mammalian species by consolidating three distinct perspectives – that of each virus, each mammal, and the network connecting them, respectively.

Their results suggest that there are more than five times as many associations between known zoonotic viruses and wild and semi-domesticated mammals than previously thought.

In particular, bats and rodents, which have been associated with recent outbreaks of emerging viruses such as coronaviruses and hantaviruses, were linked with an increased risk of 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 such as livestock and pets.

Wardeh said: “As viruses continue to move across the globe, our model provides a powerful way to assess potential hosts they have yet to encounter. Having this foresight could help to identify and mitigate zoonotic and animal-disease risks, such as spill-over from animal reservoirs into human populations.”

Wardeh is currently expanding the approach to predict the ability of ticks and insects to transmit viruses to birds and mammals, which will enable the prioritisation of laboratory-based vector-competence studies worldwide to help mitigate future outbreaks of vector-borne diseases.

Maya Wardeh et al., Divide-and-conquer: machine-learning integrates mammalian and viral traits with network features to predict virus-mammal associations, Nature Communications, DOI: 10.1038/s41467-021-24085-w

 

Horsetalk.co.nz

Latest research and information from the horse world.

Leave a Reply

Your email address will not be published. Required fields are marked *