Can AI foresee the next virus transmission from animals to human?

Most emerging infectious diseases of humans (like COVID-19) are zoonotic – caused by viruses originating from other animal species. Identifying high-risk viruses earlier can improve research and surveillance priorities. A recent study at the University of Glasgow, United Kingdom, suggests that machine learning  using viral genomes may predict the likelihood that any animal-infecting virus will infect humans, given biologically relevant exposure.

Identifying zoonotic diseases before emergence is a major challenge because only a tiny minority of the estimated 1.67 million animal viruses can infect humans.

The researchers are using viral genome sequences to develop machine learning models. They found that viral genomes may have generalisable features independent of virus taxonomic relationships and may preadapt viruses to infect humans. They were able to develop machine learning models capable of identifying candidate zoonoses using viral genomes.

These models have limitations, as computer models are only a preliminary step of identifying zoonotic viruses that can potentially infect humans. These models predict that viruses might infect humans; the ability to infect is just one part of the broader zoonotic risk, ability to transmit between humans, and the ecological conditions at the time of human exposure.