Like COVID-19, many of the new infectious viruses that emerge in humans originate from other animal species. However, as only a tiny proportion of the estimated 1.7 million viruses carried by animals are capable of infecting humans, pinning down the ones that pose the greatest threat is a gargantuan task.


Now, researchers at the University of Glasgow have figured out a method of using machine learning – a type of artificial intelligence – to comb through the viruses’ genomes and predict their likelihood of infecting humans.

The method may help scientists to develop vaccines to protect against the most likely candidates before they make the jump from animals to humans.

“These findings add a crucial piece to the already surprising amount of information that we can extract from the genetic sequence of viruses using AI techniques,” said study author Dr Simon Babayan, a lecturer at the Institute of Biodiversity Animal Health & Comparative Medicine, University of Glasgow.

Read more about viruses:

“A genomic sequence is typically the first, and often only, information we have on newly-discovered viruses, and the more information we can extract from it, the sooner we might identify the virus’s origins and the zoonotic risk it may pose.

"As more viruses are characterised, the more effective our machine learning models will become at identifying the rare viruses that ought to be closely monitored and prioritised for pre-emptive vaccine development.”

The team trained machine learning models to scour through the genomes of 861 animal viruses and assign probabilities to them based on their similarity to the genomes of viruses known to infect humans. They then used their best performing model to analyse the patterns in the genomes of additional viruses sampled from a range of different animal species.

More like this

They found that some virus genomes may have identifiable genetic features that enable them to jump from animals to humans.


The viruses identified by the models will now require further lab testing to confirm they are able to infect humans, but even so further study will be required to investigate their ability to pass between humans and the environmental conditions in which they are able to survive, the researchers say.

Reader Q&A:How do viruses jump from animals to humans?

Every animal species hosts unique viruses that have specifically adapted to infect it. Over time, some of these have jumped to humans – these are known as ‘zoonotic’ viruses.

As our populations grow, we move into wilder areas, which brings us into more frequent contact with animals we don’t normally have contact with. Viruses can jump from animals to humans in the same way that they can pass between humans, through close contact with body fluids like mucus, blood, faeces or urine.

Because every virus has evolved to target a particular species, it’s rare for a virus to be able to jump to another species. When this does happen, it’s by chance, and it usually requires a large amount of contact with the virus.

Initially, the virus is usually not well-suited to the new host and doesn’t spread easily. Over time, however, it can evolve in the new host to produce variants that are better adapted.

When viruses jump to a new host, a process called zoonosis, they often cause more severe disease. This is because viruses and their initial hosts have evolved together, and so the species has had time to build up resistance. A new host species, on the other hand, might not have evolved the ability to tackle the virus. For example, when we come into contact with bats and their viruses, we may develop rabies or Ebola virus disease, while the bats themselves are less affected.

It’s likely that bats were the original source of three recently emerged coronaviruses: SARS-CoV (2003), MERS-CoV (2012) and SARS-CoV-2, the cause of the 2019-20 coronavirus outbreak. All of these jumped from bats to humans via an intermediate animal; in the case of SARS-CoV-2, this may have been pangolins, but more research is needed.

Read more:



Jason Goodyer
Jason GoodyerCommissioning editor, BBC Science Focus

Jason is the commissioning editor for BBC Science Focus. He holds an MSc in physics and was named Section Editor of the Year by the British Society of Magazine Editors in 2019. He has been reporting on science and technology for more than a decade. During this time, he's walked the tunnels of the Large Hadron Collider, watched Stephen Hawking deliver his Reith Lecture on Black Holes and reported on everything from simulation universes to dancing cockatoos. He looks after the magazine’s and website’s news sections and makes regular appearances on the Instant Genius Podcast.