In short
- Researchers identified a key molecular interaction that viruses depend on to enter cells and disrupted it in laboratory experiments.
- The work used AI and molecular simulations to narrow down thousands of interactions to one critical target.
- Scientists say the approach could help guide future research into antivirals and diseases, although it is still in its early stages.
Most antiviral drugs target viruses after they have already entered human cells. Researchers at Washington State University said they have found a way to intervene earlier, by identifying a single molecular interaction that viruses depend on to enter cells.
The research was published in the journal in November Nanoscalefocused on viral entry, one of the least understood and most difficult stages of infection to disrupt, using artificial intelligence and molecular simulations to identify a critical interaction within a fusion protein that, when modified in laboratory experiments, prevented the virus from entering new cells.
“Viruses attack cells through thousands of interactions,” said Professor Jin Liu, professor of mechanical engineering and materials science at Washington State University. Declutter. “Our research aims to identify the most important ones, and once we identify that interaction, we can devise a way to prevent the virus from entering cells and stop the spread of disease.”
The study grew out of work that began more than two years ago, shortly after the COVID-19 pandemic, and was led by Professor of Veterinary Microbiology and Pathology Anthony Nicola, with funding from the National Institutes of Health.
In the study, researchers examined herpes viruses as a test case.
These viruses depend on a surface fusion protein, glycoprotein B (gB), which is essential for driving membrane fusion during entry.
Scientists have long known that gB plays a central role in infections, but its large size, complex architecture, and coordination with other viral entry proteins have made it difficult to determine which of its many internal interactions are functionally critical.
Liu said the value of artificial intelligence in the project is not that it uncovers something unknowable to human researchers, but that it makes the search much more efficient.
Instead of relying on trial and error, the team used simulations and machine learning to analyze thousands of possible molecular interactions simultaneously and rank which were most important.
“In biological experiments, you usually start with a hypothesis. You think this region might be important, but in that region there are hundreds of interactions,” Liu said. “You test one, maybe it’s not important, and then another one. That takes a lot of time and a lot of money. With simulations the costs can be neglected, and our method is able to identify the really important interactions that can then be tested in experiments.”
AI is increasingly being used in medical research to identify disease patterns that are difficult to detect with traditional methods.
Recent studies have used machine learning to predict Alzheimer’s disease years before symptoms appear, to spot subtle signs of the disease on MRI scans, and to predict long-term risks for hundreds of conditions using large medical record data sets.
The US government has also begun investing in the approach, including a $50 million National Institutes of Health initiative to apply AI to childhood cancer research.
Beyond virology, Liu said the same computational framework could be applied to diseases caused by altered protein interactions, including neurodegenerative disorders such as Alzheimer’s disease.
“The most important thing is to know which interaction to focus on,” says Liu. “Once we can achieve that goal, people can look at ways to weaken it, strengthen it, or block it. That’s really the significance of this work.”
Generally intelligent Newsletter
A weekly AI journey narrated by Gen, a generative AI model.
