Scientists at Washington State University used artificial intelligence and molecular simulations to identify a crucial amino acid interaction in a herpes virus fusion protein that is required for cell invasion. When they engineered a mutation at this site, the virus could no longer fuse with or enter cells, according to a study published in Nanoscale.
Researchers from Washington State University's School of Mechanical and Materials Engineering and Department of Veterinary Microbiology and Pathology collaborated on a study targeting a fusion protein that herpes viruses use to enter cells. This protein undergoes complex shape changes to drive infection, and limited understanding of its dynamics has made vaccine and drug development difficult.
To investigate the problem, professors Jin Liu and Prashanta Dutta turned to artificial intelligence and detailed molecular simulations to analyze thousands of potential interactions among amino acids in the fusion protein, Washington State University reports. They built an algorithm to examine these interactions and then applied machine learning to identify those most likely to be essential for viral entry.
"Viruses are very smart. The whole process of invading cells is very complex, and there are a lot of interactions. Not all of the interactions are equally important—most of them may just be background noise, but there are some critical interactions," Liu said in the university's account of the work.
After simulations highlighted one key amino acid interaction, the team moved to laboratory experiments led by Anthony Nicola in the Department of Veterinary Microbiology and Pathology. By introducing a targeted mutation at this amino acid, they found that the virus could no longer successfully fuse with cells, effectively blocking the herpes virus from entering cells altogether, according to the ScienceDaily summary of the study.
Liu said the computational screening substantially accelerated the research. Experimentally testing interactions one by one would have taken far longer, he noted. "It was just a single interaction from thousands of interactions. If we don't do the simulation and instead did this work by trial and error, it could have taken years to find. The combination of theoretical computational work with the experiments is so efficient and can accelerate the discovery of these important biological interactions," he said.
Although the team confirmed the importance of this specific interaction for viral fusion and entry, they cautioned that many questions remain about how the mutation alters the three-dimensional structure and large-scale motions of the full fusion protein. The researchers plan to continue using simulations and machine learning to explore how small molecular changes propagate across the protein and to narrow down other potentially vulnerable sites.
"There is a gap between what the experimentalists see and what we can see in the simulation," Liu said. "The next step is how this small interaction affects the structural change at larger scales. That is also very challenging for us."
The work, carried out by Liu, Dutta, Nicola and PhD students Ryan Odstrcil, Albina Makio, and McKenna Hull, was funded by the National Institutes of Health and is detailed in the journal Nanoscale under the title Modulation of specific interactions within a viral fusion protein predicted from machine learning blocks membrane fusion.
According to Washington State University, this AI-guided approach could inform future antiviral strategies by helping scientists pinpoint and disrupt specific molecular "switches" in viral proteins that are essential for infection.
