News Tech and Science

Researchers use Artificial Intelligence to predict when COVID-like virus could infect humans

AI detect Covid virus
Source: Pixabay

An international research team of scientists has demonstrated the ability of Artificial Intelligence (AI) to predict which viruses, such as the Covid virus, could infect humans, which animals could host them, and where they could emerge.

The team, led by scientists from Georgetown University, completed an 18-month project to identify specific bat species likely to carry betacoronaviruses – a large group of viruses that includes SARS-CoV (the virus that caused the 2002-2004 SARS outbreak) and SARS-CoV-2 (the virus that causes Covid-19). In the journal Lancet Microbe, they published an ensemble of predictive models of likely reservoir hosts.

“If you want to find these viruses, you have to start by profiling their hosts – their ecology, their evolution, even the shape of their wings,” explains Colin Carlson, Assistant Research Professor in the Department of Microbiology and Immunology at the varsity.

“Artificial Intelligence lets us take data on bats and turn it into concrete predictions: where should we be looking for the next SARS?” Carlson said

The new study suggests that the search for closely related viruses may be difficult, with betacoronaviruses predicted to be present in over 400 bat species around the world.

Although the origin of SARS-CoV-2 is unknown, the spread of other viruses from bats is becoming a growing concern due to factors such as agricultural expansion and climate change.

The research team trained eight different statistical models that predicted which types of animals could host betacoronaviruses in the first quarter of 2020. The team then tracked the discovery of 40 new bat hosts of betacoronaviruses for more than a year to validate initial predictions and dynamically update their models.

The researchers discovered that models based on data on bat ecology and evolution performed exceptionally well when it came to predicting new hosts. In contrast, cutting-edge network science models that used high-level mathematics but less biological data performed about as well or worse than expected at random.

“One of the most important things our study gives us is a data-driven shortlist of which bat species should be studied further,” said Daniel Becker, Assistant Professor of biology at the University of Oklahoma.

“After identifying these likely hosts, the next step is then to invest in monitoring to understand where and when betacoronaviruses are likely to spill over,” he added.

According to Carlson, the team is now collaborating with other scientists from around the world to test bat samples for coronaviruses based on their predictions.

“If we spend less money, resources, and time looking for these viruses, we can put all of those resources into the things that actually save lives down the road. We can invest in building universal vaccines to target those viruses, or monitoring for spillover in people that live near bats,” said Carlson. “It’s a win-win for science and public health.”


About the author

Brendan Taylor

Brendan Taylor was a TV news producer for 5 and a half years. He is an experienced writer. Brendan covers Breaking News at Insider Paper.

Daily Newsletter