[ad_1]
Artificial intelligence (AI) could be essential in helping scientists identify the next animal virus capable of infecting humans, the researchers say.
In a study published Tuesday in the journal PLoS Biology, the Glasgow-based team said they had designed a genomic model that could “retrospectively or prospectively predict the likelihood that viruses will be able to infect humans.”
The group has developed machine learning models to identify candidate zoonotic viruses using host range signatures encoded in viral genomes.
GOOGLE KNOWS WHAT YOU ENTER, WATCH AND SAY, UNLESS YOU TAKE THESE STEPS
With a dataset of 861 viral species with known zoonotic status, the researchers collected a single genomic sequence representative of hundreds of RNA and DNA virus species, spanning 36 viral families.
They categorized each virus as either capable of infecting humans or not, merging three previously published datasets that reported data at the viral species level and did not take into account the potential for range variation. hosts within virus species.
Researchers have trained models to classify viruses accordingly.
Binary predictions correctly identified nearly 72% of viruses that primarily or exclusively infect humans and nearly 70% of zoonotic viruses as infecting humans, although performance varies among viral families.
After further conversion of the predicted probabilities of zoonotic potential into four categories, 92% of viruses infecting humans would have medium, high or very high zoonotic potential and a total of 18 viruses currently not considered to infect humans according to their criteria are expected to have. very high zoonotic potential – of which at least three had serological evidence of human infection, suggesting that they could be valid zoonoses.
“Out of the dataset, 77.2% of viruses predicted to have very high zoonotic potential were known to infect humans,” the researchers wrote.
Next, the scientists tested several learning-based models to find the best performing model, which was used to classify 758 virus species – and 38 viral families – not present in the training data.
Among a second set of 645 animal-associated viruses excluded from training data, models predicted an increased risk of zoonotic transmission of genetically similar viruses associated with non-human primates.
YOUR APPS LOOK EVERYWHERE YOU GO UNLESS YOU CHANGE THIS SETTING
“Taken together, our results are consistent with the expectation that the relatively close phylogenetic proximity of non-human primates may facilitate virus sharing with humans and suggest that this may in part reflect common selective pressures on the composition of the viral genome. in humans and non-human primates. However, the large differences between other groups of animals appear to have less influence on zoonotic potential than the characteristics of the virus, ”the authors said.
In total, 70.8% of viruses collected from humans were correctly identified with a high or very high zoonotic potential.
A second case study predicted the zoonotic potential of all currently recognized coronavirus species and the human and animal genomes of all coronaviruses linked to severe acute respiratory syndrome.
“Our results show that the zoonotic potential of viruses can be inferred to a large extent from the sequence of their genome,” the researchers reported. “By highlighting the viruses with the greatest potential to become zoonotic, genome-based classification makes it possible to more effectively target further ecological and virological characterization. “
By identifying high-risk viruses and conducting further investigation, they said the predictions could contribute to the growing imbalance between the rapid pace of virus discovery and the research needed to comprehensively assess risk.
Almost 2 million animal viruses can infect humans.
“It is important to note that, given the limitations of diagnosis and the likelihood that not all viruses capable of human infection have had the opportunity to emerge and be detected, viruses not reported as infecting humans can represent undetected, undocumented, or truly non-zoonotic species. Identifying potential or undocumented zoonoses within our was a priori objective of our analysis, ”said the group.
CLICK HERE TO GET THE FOX NEWS APP
“A genomic sequence is usually the first, and often the only, piece of information we have about newly discovered viruses, and the more information we can extract from it, the sooner we can identify the origins of the virus and the zoonotic risk it faces. can pose “, co. – Author Simon Babayan of the University of Glasgow’s Biodiversity Institute said in a press release.
“As more viruses are characterized, the more effective our machine learning models will become in identifying rare viruses that need to be closely monitored and prioritized for the development of preventive vaccines,” he said. added.
[ad_2]
Source link