Connect with us

Healthcare

New Research Shows How AI Modeling Can Provide insight Into Protein Structures

Published

 on

New research into artificial intelligence (AI) algorithms coming out of the University of York is enabling scientists to develop more complete models of the protein structures in the human body. This can have a big impact on the design of therapeutics and vaccines. 

The research was published in the journal Nature Structural and Molecular Biology.

Up to 70 percent of human proteins are either surrounded and scaffolded with sugar, and this has an impact on how they look and act. Viruses that are behind things like COVID-19 and Ebola are shielded behind sugars as well, and the addition of them is called modification.

AlphaFold AI Program

The researchers first developed software that adds missing sugar components to models created with an AI program called AlphaFold, and this enabled them to study proteins deeper. AlphaFold was created by Google’s DeepMind, and it performs predictions of protein structures. 

Dr. Jon Agiree from the Department of Chemistry is senior author of the research, which was conducted alongside Dr. Elisa Fadda and Carl A. Fogarty from Maynooth University. It also involved Haroldas Bagdonas, who is a PhD student at the York Structural Biology Laboratory. 

“The proteins of the human body are tiny machines that in their billions, make up our flesh and bones, transport our oxygen, allow us to function, and defend us from pathogens. And just like a hammer relies on a metal head to strike pointy objects including nails, proteins have specialised shapes and compositions to get their jobs done,” Dr. Agiree said.

“The AlphaFold method for protein structure prediction has the potential to revolutionise workflows in biology, allowing scientists to understand a protein and the impact of mutations faster than ever.”

“However, the algorithm does not account for essential modifications that affect protein structure and function, which gives us only part of the picture. Our research has shown that this can be addressed in a relatively straightforward manner, leading to a more complete structural prediction.”

Making Accurate Structure Predictions

Through the new AlphaFold program and the corresponding database of protein structures, the team of scientists can make accurate structure predictions for all known human proteins, which is a major step forward in the field. 

“It is always great to watch an international collaboration grow to bear fruit, but this is just the beginning for us,” Dr. Agiree continued. “Our software was used in the glycan structural work that underpinned the mRNA vaccines against SARS-CoV-2, but now there is so much more we can do thanks to the AlphaFold technological leap. It is still early stages, but the objective is to move on from reacting to changes in a glycan shield to anticipating them.”

Alex McFarland is a Brazil-based writer who covers the latest developments in artificial intelligence & blockchain. He has worked with top AI companies and publications across the globe.