Water buffalo, Sunda pangolins and mink are among the Based on their biology and where they live, 540 mammals are predicted to likely spread the coronavirus
November 17, 2021
An AI tool has predicted 540 mammal species most likely to spread Covid-19 using information about where they live and aspects of their biology.
According to the model, minks, Sunda pangolins and bats are among the top 10 percent of species most likely to spread Covid-19, consistent with results of lab experiments.
The SARS-CoV-2 coronavirus, which causes Covid-19, invades human and animal cells by activating the ACE2 protein on host cells with its spike protein. This step is necessary to infect an animal and be transferred to other hosts.
Different species have different versions of the protein, so understanding how well their ACE2 protein binds to the coronavirus spike protein can help scientists predict which animals are most likely to spread Covid-19. But the amino acid sequences that make up the ACE2 protein are available for only about 300 species.
Barbara Han of the Cary Institute of Ecosystem Studies in New York and her colleagues built a machine learning tool to predict whether the ACE2 protein of 5,400 mammal species can bind strongly enough to the spike protein of the original coronavirus variant to spread the virus , even without knowing their ACE2 amino acid sequences.
Species predicted to harbor the virus include white-tailed deer, which were recently found to have very high infection rates in North America.
Striped skunk and 76 rodent species, including rats and deer mice, were also thought to spread the coronavirus, along with some farmed species such as water buffalo.
To create the model, the team first estimated how strongly the spike protein binds to the ACE2 protein of 142 mammalian species whose ACE2 sequences are known, and whether these species are likely to spread the coronavirus based on this binding strength.
They then trained the AI to learn patterns between transferability and a set of about 60 ecological and biological traits collected from previous studies. The traits include where the animals live, how much their habitats overlap with human populations, their life spans, how varied their diet is, and their body weight.
Based on biological and ecological characteristics of the other species, the model was able to estimate the likelihood that different species could spread the coronavirus.
These results need to be followed up with systematic surveillance and lab studies to test and validate the predictions, Han says.
“This is an incredibly useful approach for prioritizing animal species for surveillance,” said Arinjay Banerjee of the University of Saskatchewan in Canada. Surveillance will help detect viral infections and the possible emergence of animal-adapted coronavirus variants, Banerjee says.
Reference magazine: Proceedings of the Royal Society B, DOI: 10.1098/rspb.2021.1651
More on these topics: