MSU researchers use AI to stay ahead of COVID-19 and other diseases

MSU researchers use AI to stay ahead of COVID-19 and other diseases

Newswise – EAST LANSING, Michigan – The National Institutes of Health has awarded researchers at Michigan State University $2.7 million to continue developing artificial intelligence algorithms that predict key features of viruses as they evolve.

The team is led by Guowei Weissan expert in AI who has almost published 30 papers on COVID-19, and Yong-hui Zheng, whose extensive background in virology helps verify and improve AI predictions. The team also includes Jiahui Chen, a visiting assistant professor at MSU who was instrumental in developing the AI ​​models.

The Wei lab has already shown that those models can make accurate predictions about new variants of the new coronavirus, and with this grant the researchers are working to strengthen their algorithms.

“What we’re doing is making our predictions more accurate and up-to-date,” said Wei, an MSU Foundation Professor in the College of Natural Sciences Department of Mathematics and Department of Biochemistry and Molecular Biology† “And now our work is not just for COVID, but for many other viral infections as well.”

The work could one day help drug developers create universal vaccines and therapies that are more effective and “evolution-proof” against a range of viral diseases, including flu, HIV and COVID-19.

“HIV, Ebola, flu, the coronavirus – they are all different viruses, but they have common characteristics,” said Zheng, a professor in the College of Osteopathic Medicine with the Department of Microbiology and Molecular Genetics† “If we learn how to attack one, that can tell us how to attack the others.”

“The goal is to be much better prepared for any future disease or pandemic,” Wei said.

How AI, data and experiments can inform public health

More immediately, the Wei team believes its AI could help inform public health officials if they need to update their recommended protective measures — such as providing masks and social distancing guidelines — against emerging coronavirus variants.

While vaccines and treatments are now available that did not exist when the US first declared a public health emergency in response to the novel coronavirus, the virus is still evolving. In fact, our immune responses naturally influence the trajectory of that evolution.

Thinking in terms of “survival of the fittest,” a virus that can evade vaccines or natural immunity, will be more appropriate than its predecessor, Wei said. That means it is better equipped to survive, multiply and infect others. The message isn’t that people shouldn’t protect themselves, Wei said, but that a virus still infects that about 100,000 Americans daily will not get tired, bored or just give up.

“Viruses have no personality. They just survive,” Wei said. “We want to make sure we’re prepared.”

This new grant, funded by the National Institute of Allergy and Infectious Diseases, is an investment to improve our preparedness through advanced technology. But it also uses the expertise and experience of Wei and Zheng.

Zheng has been leading NIH-funded grants for two decades, although this will be his first with an explicit focus on the coronavirus.

“I’m very proud that this is the first,” he said. “But we don’t want it to be the last. This new grant will expand the capacity of my lab to meet more needs across the campus and we want to use that to drive more collaboration.”

Zheng brings a unique virology skills to MSU. He was first recruited in 2005 as an HIV researcher, and over time his lab has grown to study the molecular biology of influenza and Ebola. When the coronavirus pandemic hit, he knew his team could provide valuable experimental infrastructure to better study the new virus.

For example, his team developed less dangerous versions of the virus along with lab-grown cells to infect these “pseudoviruses” while preserving the biochemistry of real, clinical infections. The researchers also created highly sensitive assays, or tests, that would reveal which viruses were infecting which cells. All of this provided researchers with safer, faster and easier ways to study a complex virus while generating valuable biological data.

Likewise, in early 2020, Wei’s team began deploying its unique skills in the fight against the coronavirus.

“Before the pandemic, we had success in global competitions and were recognized as one of the top labs in combining AI and mathematics for drug discovery,” said Wei, who also has an appointment in the Department of Electrical and Computer Engineering in the Technical University

Wei’s research focused on using AI to design new drugs in collaboration with Pfizer and Bristol-Myers Squibb. Within days of the Wuhan shutdown in China in January 2020, Wei’s team began sharing its AI resources to help find drugs to fight the coronavirus and reveal new potential drug targets† But the researchers also recognized that their algorithms could do more.

With a global community working to fight the coronavirus, there has regularly been a wealth of new genomic data describing the virus. Wei and his team saw an opportunity to combine that data with their AI framework to gain insight how the virus mutated as time went on.

For example, they were among the first to see how “survival of the fittest” played out in the virus and guided its evolution, Wei said. His team then used that knowledge to look ahead and identify two potentially vital sites on the virus’s spike protein, the protein the virus uses to attach to and infect cells. Mutations in those two spike protein sites would later prove to play critical roles in the most common variants of the virus, Wei said.

“We took what we did with deep learning and math, and combined that with the viral genomic data to understand the evolution of the virus, look at its trajectory and ask what’s going to happen,” Wei said. “That gives us a way to predict what might happen in the future.

Predicting successful virus behavior

Wei and Zheng have been working together for about a year, starting before the scholarship was awarded. Their teamwork has informed precise algorithms with real-world data and produced real experimental results to compare with AI predictions.

“We need that interdisciplinary collaboration to make this work,” Zheng said. “Everything the computer models predicted, we had to confirm with experiments in a living system.”

Even though Wei’s team validated his AI with lab experiments, the researchers still knew they had to prove that their algorithms could work with a brand new variant with very little data. Then, in the fall of 2021, the first ommicron variant appeared.

“At the end of November, people didn’t know what was going to happen,” Wei said.

Researchers and public health officials responded immediately, but the process of experimenting and collecting data takes weeks. Meanwhile, Wei’s team has put its AI to the test.

Their projections showed that this first iteration of omicron would be more infectious, better able to evade vaccine protection, and less responsive to antibody treatments than previous variants.

“Within days we had our predictions,” Wei said. “A month and a half later everything we predicted proven to be true by experimental labs around the world. With AI, we can give people a month or two to prepare.”

Then, in early 2022, a new sub-variant of omicron called BA.2 started to spread. A similar scenario played out. Wei’s team predicted it would be more contagious and even more elusive, making it the next dominant variant.

“We made our predictions on February 11 and on March 26 the World Health Organization announced it was the dominant form of the virus,” Wei said.

Now that scientists and officials have a better understanding of omicron, the newer versions are not getting the same level of attention as their predecessors. But new variants and sub-variants are still being added. With support from the National Institutes of Health, the MSU team is working to ensure we stay prepared for what’s to come, whether that’s a new strain, something more familiar like the flu, or something completely different.

Photos:

MSU Foundation Professor Guowei Wei

Professor Yong-Hui Zheng

At the far left of this image is a computer-generated visualization of the spike protein of the novel coronavirus. The magenta dots represent regions where the omicron variants are mutated. The bar charts on the right show how those mutations affect biochemistry

Reprinted with permission from Chen, J., Wei, G. J. Phys. Chem. please. 2022

Michigan State University has been promoting the common good with an unusual will for more than 165 years. MSU, one of the world’s leading research universities, is pushing the boundaries of discovery to create a better, safer and healthier world for all while providing life-changing opportunities to a diverse and inclusive academic community through more than 200 programs of study in 17- college degrees.

For MSU news on the web, visit: MSUtoday† Follow MSU News on Twitter at twitter.com/MSUnews

Leave a Comment

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