An innovative machine learning approach has been shown to rapidly predict multiple protein configurations. A new paper presents the method that predicts the relative populations of protein conformations using AlphaFold 2 (an AI-powered method that enables the accurate prediction of protein structures).

This work will advance the understanding of protein dynamics and functions. The authors noted that the technique is accurate, fast, cost-effective, and has the potential to revolutionize drug discovery by uncovering more targets for new treatments.

This work is published in Nature Communications in the article, “High-throughput prediction of protein conformational distributions with subsampled AlphaFold2.”

The work of Gabriel Monteiro da Silva, a PhD candidate in molecular biology, cell biology, and biochemistry at Brown University, tries to improve computational methods to model protein dynamics. For this study, he experimented with AlphaFold 2.

“During most cellular processes, proteins will change shape dynamically,” Monteiro da Silva said. “In order to match protein targets to drugs to treat cancer and other diseases, we need a more accurate understanding of these physiological changes. We need to go beyond 3D shapes to understanding 4D shapes, with the fourth dimension being time. That’s what we did with this approach.”

While Monteiro da Silva said that the accuracy of AlphaFold 2 has revolutionized protein structure prediction, the method has limitations: It allows scientists to model proteins only in a static state at a specific point in time. The authors further that sentiment when they write that although AlphaFold 2 has shown exceptional accuracy and speed, “it is designed to predict proteins’ ground state conformations and is limited in its ability to predict conformational landscapes.” In this study, they demonstrated how AlphaFold 2 “can directly predict the relative populations of different protein conformations by subsampling multiple sequence alignments.”

The researchers were able to manipulate the evolutionary signals from the protein to use AlphaFold 2 to rapidly predict multiple protein conformations, as well as how often those structures are populated.

“If you understand the multiple snapshots that make up the dynamics of what’s going on with the protein, then you can find multiple different ways of targeting the proteins with drugs and treating diseases,” said Brenda Rubenstein, PhD, associate professor of chemistry and physics at Brown University.

The researchers tested their method against nuclear magnetic resonance experiments on two proteins “with drastically different amounts of available sequence data”—Abl1 kinase and the granulocyte-macrophage colony-stimulating factor. They predicted changes in their relative state populations with more than 80% accuracy.

The researchers noted that existing computational methods are cost- and time-intensive. “They’re expensive in terms of materials, in terms of infrastructure; they take a lot of time, and you can’t really do these computations in a high throughput kind of way—I’m sure I was one of the top users of GPUs in Brown’s computer cluster,” Monteiro da Silva said. “On a larger scale, this is a problem because there’s a lot to explore in the protein world: how protein dynamics and structure are involved in poorly understood diseases, in drug resistance, and in emerging pathogens.”

As for next steps, the research team is refining their machine learning approach, making it more accurate as well as generalizable, and more useful for a range of applications.

Previous articleDNA Damage, Inflammation Required For Forming Long-Term Memories
Next articleREGENXBIO and AbbVie Advance Wet AMD Gene Therapy to Phase III