A new virus research study led by the University of Glasgow uses machine learning (ML) and genome sequencing to establish which animal viruses could jump to humans.

Part of the research, published in PLOS Biology and funded by the Medical Research Council (MRC) and Wellcome, is an attempt to learn more about the virus genome sequencing, often the only thing scientifically known about newly found or poorly characterised animal viruses.

The new method ranks the viruses as low, medium, high, or very high risk using the same modelling.

Without any prior knowledge of the previous SARS outbreak in humans, it was able to accurately predict SARS-CoV-2, the virus that caused Covid-19, and that its closest viral relatives had a high risk of being able to infect humans.

These findings, together with more formal testing on hundreds of viruses with known zoonotic status, showed that the model makes actionable predictions on a diverse range of RNA and DNA viruses, even those that are entirely new to science.

However, the modelling method cannot determine how dangerous they may be in terms of either symptoms or epidemic/pandemic potential, nor when they might jump into human populations.

The first step towards a virus causing an outbreak is infection of humans, however, there are a number of contributing factors, such as reservoir and human contact, whether the virus can transmit between humans, and our response to such ‘spillover infections’.

Commenting on the research, lead author Nardus Mollentze, of the MRC-University of Glasgow Centre for Virus Research, said: “Calls for investment in virus discovery programmes targeting wildlife have been controversial, since it remains unclear how to go from knowing which viruses are out there to outbreak preparedness.

“Finding out what newly described viruses are capable of, and how to respond to that, requires extensive characterisation in both the lab and in their natural environment, and this characterisation currently cannot keep up with the number of viruses being found.

“When viruses are first discovered, often all we have is their genome sequence, so developing an accurate machine learning tool that is based on information contained within that should enable us to better understand which animal viruses pose the highest risk and should therefore be characterised and investigated first.”

The researchers claimed the new modelling method could help better prioritise research efforts on the animal viruses most likely to successfully infect humans, an important step towards future human outbreak preparedness and planning.

Recommended

• Glasgow Uni launches Centre for Quantum Technology
• Scottish first as AI used in life-saving procedures for heart patients
• Cybercrime figures in Scotland almost double in the last year

Mollentze added: “Such predictions are still only a first step, however. If we want investments in virus discovery to translate into pandemic preparedness, there is a need to develop both higher-throughput virus characterisation methods and further models capable of turning the information generated by these methods into updated risk predictions.”

Co-author Simon Babayan, from the Institute of Biodiversity, Animal Health and Comparative Medicine, added: “As most emerging infectious diseases in humans are caused by a small number of viruses that originated in other animal species, it remains an enormous challenge to know where to look for the next virus epidemic.

“Now we provide a rapid, low-cost approach to enable evidence-driven virus surveillance and characterisation of viruses that could specifically infect humans and may therefore better help with future epidemic and pandemic preparedness.”

Join the Conversation: Digital Transformation 2021 Summit

The use of machine learning in R&D will be a key theme at the upcoming Digital Transformation Summit on 28th October.

Now in its sixth year, the Summit has established itself as Scotland’s largest annual conference focussed on digitalisation and organisational change.

For more information on how to register a free place visit: https://www.digifutures.co.uk/