AI may aid scientists in identifying the next virus to spread from animals to people.


AI may aid scientists in identifying the next virus to spread from animals to people.

Scientists are continually monitoring the threat of zoonotic illnesses, but the work is made more difficult by the fact that there are millions of viruses spreading throughout animal populations.

Scientists are enlisting the help of sophisticated algorithms and machine learning to boost the chances of identifying the next virus to move from animals to humans — before it may cause a worldwide pandemic.

Researchers believe that artificial intelligence can be used to predict the possibility that an animal-infecting virus could infect people in a new proof-of-concept study published Tuesday in the journal PLOS Biology.

Researchers began by compiling a database of 861 zoonotic virus species from 36 families in order to create the new machine-learning model. The scientists then train their model with artificial intelligence to discover genomic patterns connected to the risk of human infection.

Scientists utilized the new model to assess the risks posed by a new group of virus species that were not included in the initial dataset.

The researchers wrote in the paper, “Our model reduced a second set of 645 animal-associated viruses that were excluded from training to 272 high and 41 very high-risk candidate zoonoses and showed significantly elevated predicted zoonotic risk in viruses from nonhuman primates, but not other mammalian or avian host groups.”

The modeling experiment revealed that genomic patterns are more indicative of the risk of human infection than the taxonomic relationships between virus species.

Without any prior information of other SARS-related coronaviruses, the model effectively recognized the virus that causes COVID-19, SARS-CoV-2, as a “somewhat high-risk coronavirus.”

While millions of viruses are found in animal populations, research show that only a small number of them are capable of infecting humans.

Scientists can use machine learning to rule out non-threatening viruses and focus on the ones that are the most dangerous.

Once artificial intelligence models have discovered potential hazards, scientists can employ various inquiry approaches to better anticipate the threat and devise mitigation strategies.

In a press release, study co-author Simon Babayan remarked, “These discoveries add a critical element to the already amazing amount of information that we can extract from the genomic sequence of viruses using AI approaches.”

“A genome sequence is often the first and only information we have on newly discovered viruses, and the more information we can extract from it, the sooner we can identify the virus’s origins and zoonotic danger… Article Summary from Nokia News


Comments are closed.