Posted in | News | Medical Robotics

Novel AI Modeling Helps Create More Complete Models of Human Proteins

Thanks to a new study based on AI algorithms, researchers have now developed more comprehensive models of the protein structures in human bodies. The study opens the door for quicker designing of vaccines and therapeutics.

Novel AI Modeling Helps Create More Complete Models of Human Proteins.
A model of sugars involved in the research. Image Credit: Dr. Jon Agirre.

Headed by the University of York, the study, utilizing artificial intelligence (AI), allowed the researchers to gain a deeper insight into the sugar that surrounds a majority of the proteins in human bodies.

Nearly 70% of human proteins are scaffolded with or surrounded by sugar, playing a crucial role in how they appear and behave. Furthermore, certain viruses — such as those that cause Ebola, AIDS, COVID-19 and Flu are also shielded by sugars or glycans. The addition of these sugars is called modification.

Sugar Components

Researchers investigated the proteins by developing software that adds missing sugar components to models developed using AlphaFold — an artificial intelligence program created by Google’s DeepMind for predicting protein structures.

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. Jon Agirre, Study Senior Author, Department of Chemistry, University of York

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,” added Dr. Agirre.

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.

Dr. Jon Agirre, Study Senior Author, Department of Chemistry, University of York

Protein Structures

The recent launch of AlphaFold and the accompanying protein structure database has allowed researchers to accurately predict the structure of all known human proteins.

It is always great to watch an international collaboration grow to bear fruit, but this is just the beginning for us. 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.

Dr. Jon Agirre, Study Senior Author, Department of Chemistry, University of York

The study was performed in collaboration with Dr. Elisa Fadda and Carl A. Fogarty from Maynooth University. Haroldas Bagdonas, a PhD student at the York Structural Biology Laboratory — a part of the Department of Chemistry — also contributed to the study, working together with Dr. Agirre.

Journal Reference:

Bagdonas, H., et al. (2021) The case for post-predictional modifications in the AlphaFold Protein Structure Database. Nature Structural & Molecular Biology. doi.org/10.1038/s41594-021-00680-9.

Source: https://www.york.ac.uk/

Tell Us What You Think

Do you have a review, update or anything you would like to add to this news story?

Leave your feedback
Submit