AI algorithm targets new coronavirus outbreaks
Researchers are using AI to predict which mammals are hosts of new coronavirus diseases, according to a study published in Nature Communications. The study comes as researchers are focused on identifying and predicting new outbreaks before they become widespread.
Coronaviruses “undergo frequent host-shifting events between non-human animal species, or non-human animals and humans,” wrote lead author Maya Wardeh, of the University of Liverpool in the U.K., et al.
Covid-19 is one such coronavirus that jumped from animals to humans, proposed to have originated in bats. The shifting between species or form animals to humans is what causes new diseases, and scientists are trying to better understand the associations between coronaviruses and mammals.
Using a machine learning method that has been used to predict drug-target and IncRNA-disease associations, called DeepWalk, researchers aimed to answer three questions: which species may have unidentified coronaviruses; what are the most probable hosts for coronaviruses; and which coronaviruses are most likely to co-infect hosts and act as sources for future novel viruses. Specifically, Wardeh et al looked at the associations between 411 known coronaviruses and 876 mammal species.
The study highlighted a few important recombination hosts of coronaviruses in its findings. The Asian palm civet was predicted as a potential host of 32 different coronaviruses. The horseshoe bat was predicted to be a host to 68 different coronaviruses, and the pangolin is a suspected intermediate host for an additional 14 different coronaviruses. The results also implicated the common hedgehog, the European rabbit and the domestic cat as predicted hosts for a large number of coronaviruses and the CARS-CoV-2 coronavirus.
The study underscores how technology could become critical in preventing new viruses from becoming deadly outbreaks and pandemics. However, the findings also reveal just how underestimated this area of study really is, as the potential for new coronaviruses and how they change as they shift across species or from humans and non-humans is huge.
“With the greater understanding of the extent of mammalian host reservoirs and the potential recombination hosts we identify here, a targeted surveillance [program] is now possible which would allow for this generation to be observed as it is happening and before a major outbreak,” Mardeh et al wrote. “Such information could help inform prevention and mitigation strategies and provide a vital early warning system for future novel coronaviruses.
Amy joined TriMed Media as a Senior Writer for HealthExec after covering home care for three years. When not writing about all things healthcare, she fulfills her lifelong dream of becoming a pirate by sailing in regattas and enjoying rum. Fun fact: she sailed 333 miles across Lake Michigan in the Chicago Yacht Club "Race to Mackinac."