The most complex protein node with seven crossings (left) predicted by AlphaFold and a simplified representation (right). Credit: Maarten Brems
The question of how a protein’s chemical composition – its amino acid sequence – determines its 3D structure has been one of the greatest challenges in biophysics for more than half a century. This knowledge about the so-called “folding” of proteins is in great demand, because it makes an important contribution to the understanding of various diseases and their treatment, among other things. For these reasons, the DeepMind research team at Google has developed AlphaFold, an artificial intelligence that predicts 3D structures.
A team of researchers from Johannes Gutenberg University Mainz (JGU) and the University of California, Los Angeles has now taken a closer look at these structures and examined them for knots. We mainly know knots from shoelaces and cables, but they also occur on a nanoscale in our cells. Knotted proteins can not only be used to assess the quality of structure predictions, but also raise important questions about folding mechanisms and the evolution of proteins.
The most complex knots as a test for AlphaFold
“We numerically examined all — that’s about 100,000 — AlphaFold’s predictions for new protein nodes,” said Maarten A. Brems, a Ph.D. student in the group of Dr. Peter Virnau at the University of Mainz. The aim was to identify rare, high-quality structures containing complex and previously unknown protein nodes to provide a basis for experimental verification of AlphaFold’s predictions. The study not only discovered the most complex knotted protein to date, but also the first composite knots in proteins. The latter can be thought of as two separate knots on the same string.
“These new discoveries also provide insight into the evolutionary mechanisms behind such rare proteins,” added Robert Runkel, a theoretical physicist also involved in the project. The results of this study were recently published in protein science.
dr. Peter Virnau is pleased with the results: “We have already established a collaboration with our colleague Dr. Todd Yeates from UCLA to experimentally confirm these structures. This line of research will shape the biophysical community’s view of artificial intelligence – and we have lucky to have an expert like Todd Yeates involved.”
Physicists use mathematical algorithms to investigate experimental 3D structures of chromosomes
Maarten A. Brems et al, AlphaFold predicts the most complex protein knot and composite protein knots, protein science (2022). DOI: 10.1002/pro.4380
John Jumper et al, Highly accurate protein structure prediction with AlphaFold, Nature (2021). DOI: 10.1038/s41586-021-03819-2
Provided by Johannes Gutenberg University Mainz
Quote: Physicists use AI to find most complex protein nodes yet (2022, July 14) retrieved July 15, 2022 from https://phys.org/news/2022-07-physicists-ai-complex-protein.html
This document is copyrighted. Other than fair dealing for personal study or research, nothing may be reproduced without written permission. The content is provided for informational purposes only.