As the world continues to struggle with the COVID-19 pandemic, it’s not surprising that some researchers have turned their attention to developing techniques that will help predict what other animal-based viruses might be able to make the jump to humans.
To that end, a team at the University of Glasgow recently published a study that explored the capacity of AI to predict the likelihood of an animal-infecting virus to infect humans.
The good news is that only a small minority the estimated 1.67 million animal viruses are able to infect humans. On the other hand, the team noted in their report, “(e)xisting models of human infection risk rely on viral phenotypic information that is unknown for newly discovered viruses (e.g., the diversity of species a virus can infect) or that vary insufficiently to discriminate risk at the virus species or strain level (e.g., replication in the cytoplasm), limiting their predictive value before the virus in question has been characterized.”
In a release accompanying the report, the team explained that “to develop machine learning models using viral genome sequences, the researchers first compiled a dataset of 861 virus species from 36 families. They then built machine learning models, which assigned a probability of human infection based on patterns in virus genomes. The authors then applied the best-performing model to analyze patterns in the predicted zoonotic potential of additional virus genomes sampled from a range of species.”
The researchers found that viral genomes may have generalizable features that are 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 with potential to infect humans.
“Our findings show that the zoonotic potential of viruses can be inferred to a surprisingly large extent from their genome sequence,” the team wrote. “By highlighting viruses with the greatest potential to become zoonotic, genome-based ranking allows further ecological and virological characterisation to be targeted more effectively.”
The researchers added that viruses flagged by the models will require confirmatory laboratory testing before pursuing major additional research investments. Further, while these models predict whether viruses might be able to infect humans, the ability to infect is just one part of broader zoonotic risk, which is also influenced by the virus’ virulence in humans, ability to transmit between humans, and the ecological conditions at the time of human exposure.
Photo by cofotoisme/Getty Images