Scientists Want To Use Artificial Intelligence To ‘Predict The Next Coronavirus’

A team of scientists are working to use artificial intelligence (AI) to work out when another novel coronavirus could emerge. The researchers are using a combination of fundamental biology as well as machine learning to get a better grasp over where these viruses come from. 

The computer algorithm being used has already predicted a multitude of potential hosts that new virus strains have been detected in during past studies, and could potentially be detected in during future outbreaks. The findings themselves have been published in the journal of Nature Communications. 

Dr. Marcus Blagrove is a virologist from the University of Liverpool in the UK who was involved in the study. He explained that the goal of the study was to hopefully get a grasp on where the next coronavirus could come from. 

Embed from Getty Images

“One way coronaviruses are generated is through recombination between two existing coronaviruses. Basically two viruses infect the same cell and recombine into a ‘daughter’ virus, or an entirely new strain of the virus we’ve been fighting.”

Researchers were able to place existing biological evidence into an AI algorithm, which then taught the computer how to spot certain viruses and host species that are the most likely to be the source of the recombination based on environmental stats. 

The team first “asked” their AI algorithm to look at certain biological patterns so that they could predict which mammals may be the most susceptible to known coronavirus strains. This would mean that those specific species are most vulnerable to being the host for recombinations as well. The initial research showed links between 411 coronavirus strains and 876 potential mammal species hosts. 

Embed from Getty Images

Lead researcher Dr. Maya Wardeh was able to use existing biological knowledge to teach the algorithm to search for specific patterns that equated to a correlation between the species and virus strains. 

“We were able to predict which species had the chance for many coronaviruses to infect them, either because they are very closely related to a species known to carry a coronavirus or because they share the same geographical space.”

The Asian palm civet and greater horseshoe bat, for example, were predicted to be host to 32 and 68 different coronaviruses, respectively. And in species including the common hedgehog, the European rabbit and the dromedary camel, the algorithm predicted that Sars-CoV-2 might recombine with other, existing coronaviruses,” she continued.

The scientists behind the study claim that their findings could help target the surveillance for new diseases, and potentially prevent another pandemic from occurring before it even starts.  Dr Wardeh explained, however, that these findings are “not a reason to demonize these species. Spill-over of viruses into human populations tends to be linked to human activities like wildlife trade and farming. But it’s virtually impossible to survey all animals all the time, so our approach enables prioritization. It says these are the species to watch. If we can find them before they get into humans, then we could work on developing drugs and vaccines and on stopping them getting into humans in the first place.”

0 replies

Leave a Reply

Want to join the discussion?
Feel free to contribute!

Leave a Reply

Your email address will not be published. Required fields are marked *