Researchers say Artificial intelligence (AI) is able to spot the next animal to a human virus which is likely to infect humans.
In a Tuesday study published in the journal PLoS Biology, the Glasgow-based team said to have devised a genomic model that could “retrospectively or prospectively predict the probability that viruses will be able to infect humans.”
“Our findings show that the zoonotic potential of viruses can be inferred to a surprisingly large extent from their genome sequence. By highlighting viruses with the greatest potential to become zoonotic, genome-based ranking allows further ecological and virological characterization to be targeted more effectively,”THE RESEARCHERS AT THE UNIVERSITY OF GLASGOW REPORTED
The group of researchers has developed a Machine Learning model to single out zoonotic viruses using signatures of host range encoded in the viral genome.
The researchers said the model is a potential tool to detect the animal viruses potentially infecting humans and the viruses spotted by the model will be tested in the laboratory before commencing of further study.
The model will potentially help the researchers to prioritize the order in which they study the zoonotic viruses in the order of their likeliness to affect humans which thus could prevent future pandemics or at least minimize the consequences due to prior precautions.
Upon further conversion of predicted probabilities of zoonotic potential into four categories, 92% of human-infecting viruses were predicted to have medium, high, or very high zoonotic potential, and a total of 18 viruses not currently considered to infect humans by their criteria were projected to have very high zoonotic potential – at least three of which had serological evidence of human infection, suggesting they could be valid zoonoses, said Fox News in a report.
“Across the full dataset, 77.2% of viruses predicted to have very high zoonotic potential were known to infect humans,”the researcher said
The scientist tested different learning-based models to find the most accurate model which was used to rank 758 virus species and 38 viral families.
“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’ origins and the zoonotic risk it may pose,”Co-author Simon Babayan said in a journal news release.
The researchers also believe that with more viruses being characterized the model will become more efficient in identifying rare viruses that must be closely monitored for vaccine development.