Wednesday, February 8, 2023

Researchers use artificial intelligence to guide search for next SARS-like virus

Researchers Use Artificial Intelligence To Guide Search For Next Sars-Like Virus

Rhinolophus ruxi, which lives in parts of South Asia, was identified by the study authors as a likely but not known betacoronavirus host. credit: Brock and Sherry Fenton

An international research team led by scientists at Georgetown University has demonstrated the power of artificial intelligence to predict which viruses can infect humans – such as SARS-CoV-2, the virus that The cause was the COVID-19 pandemic – which animals host them, and where they could have emerged.

Their ensemble of predictive models of potential reservoir hosts, published 10 Jan lancet microbe (“Adaptation of predictive models to prioritize viral discovery in zoonotic reservoirs”), was validated in an 18-month project to identify specific bat species likely to carry betacoronavirus, the group that includes viruses such as SARS. Huh.

“If you want to find these viruses, you have to look at their hosts—their ecology, their evolution, even the shape of their wings,” explains the study’s senior author, Colin Carlson, PhD, an assistant research professor. Have to start by profiling.” in the Department of Microbiology and Immunology and member of the Georgetown Center for Global Health Science and Security at Georgetown University Medical Center. “Artificial intelligence lets us take data on bats and turn it into concrete predictions: where should we look for SARS next?”

Despite global investments in disease surveillance, it remains difficult to identify and monitor wildlife reservoirs of viruses that may someday infect humans. Statistical models are increasingly being used to prioritize which wildlife species to sample in an area, but predictions arising from any one model can be highly uncertain. Scientists rarely track their success or failure after making their predictions, which makes it difficult to learn and better model the future. Together, these limitations mean that there is a high uncertainty in which models may be best suited for the task.

This new study suggests that the discovery of a closely related virus may be non-trivial, with more than 400 bat species worldwide predicted to host betacoronaviruses, a large group of viruses that have a link to SARS-CoV. Responsible viruses are involved. 2002-2004 SARS outbreak) and SARS-CoV-2 (the virus that causes COVID-19). Although the origin of SARS-CoV-2 remains uncertain, the spread of other viruses from bats is a growing problem due to factors such as agricultural expansion and climate change.

Greg Albery, a postdoctoral fellow in Georgetown’s Department of Biology, says COVID-19 provided impetus to accelerate his research. “It’s a really rare opportunity,” Albery explains. “Outside of a pandemic, we won’t learn that much about these viruses in this short time frame. A decade of research has collapsed in about a year after publication, and that means we can really show that These tools work.”

In the first quarter of 2020, the research team trained eight different statistical models to predict which types of animals might host betacoronavirus. Over more than a year, the team tracked the discovery of 40 new bat hosts of the betacoronavirus to validate initial predictions and dynamically update their models. The researchers found that models using data on bat ecology and evolution performed very well at predicting new hosts. In contrast, state-of-the-art models of network science that used high-level mathematics – but less biological data – performed better or worse than expected at random.

“One of the most important things we get from our study is a data-driven shortlist that needs to be studied further,” says Danielle Baker, MD, assistant professor of biology at the University of Oklahoma. “Having identified these potential hosts, the next step is to invest in surveillance to understand where and when betacoronavirus may spread.”

Carlson says the team is now working with other scientists around the world to test bat samples for the coronavirus based on their predictions.

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

Scientists discover SARS-CoV-2 related coronaviruses in Cambodian bats since 2010

more information:
“Optimization of predictive models for prioritizing viral discovery in zoonotic reservoirs” lancet microbe, DOI: 10.1016/s2666-5247(21)00245-7

Provided by Georgetown University Medical Center

Citation: Researchers use artificial intelligence to guide the search for the next SARS-like virus (2022, Jan 10), published Jan 11, 2022 at Recovered from -like-virus. .html

This document is subject to copyright. No part may be reproduced without written permission, except for any fair use for the purpose of personal study or research. The content is provided for information purposes only.

Nation World News Desk
Nation World News Desk
Nation World News is the fastest emerging news website covering all the latest news, world’s top stories, science news entertainment sports cricket’s latest discoveries, new technology gadgets, politics news, and more.
Latest news
Related news