News

AI generates proteins with exceptional binding strength

Ian C. Haydon
By Ian C. Haydon
Feb. 3, 2024

A new study in Nature reports an AI-driven advance in biotechnology with implications for drug development, disease detection, and environmental monitoring. Scientists at the Institute for Protein Design at the University of Washington School of Medicine used software to create protein molecules that bind with exceptionally high affinity and specificity to a variety of challenging biomarkers, including human hormones. Notably, the scientists achieved the highest interaction strength ever reported between a computer-generated biomolecule and its target.

Susana Vasquez-Torres in a UW Medicine Institute for Protein Design laboratory, where she is working to develop new proteins with high-binding affinity and specificity to a variety of challenging biomarkers.
Ian Haydon, UW Medicine Institute for Protein Design
Susana Vasquez-Torres in a UW Medicine Institute for Protein Design laboratory, where she is working to develop new proteins with high-binding affinity and specificity to a variety of challenging biomarkers.

Senior author David Baker, professor of biochemistry at UW Medicine, Howard Hughes Medical Institute investigator, and recipient of the 2023 Frontiers of Knowledge Award in Biology and Biomedicine, emphasized the potential impact: "The ability to generate novel proteins with such high binding affinity and specificity opens up a world of possibilities, from new disease treatments to advanced diagnostics."

A new protein designed using deep-learning methods. In this case, RFdiffusion generates a binding protein.
Ian Haydon/UW Medicine Institute for Protein Design
A new protein designed using deep-learning methods. In this case, RFdiffusion generates a binding protein.

The team, led by Baker Lab members Susana Vazquez-Torres, Preetham Venkatesh, and Phil Leung, set out to create proteins that could bind to glucagon, neuropeptide Y, parathyroid hormone, and other helical peptide targets. Such molecules, crucial in biological systems, are especially difficult for drugs and diagnostic tools to recognize because they often lack stable molecular structures. Antibodies can be used to detect some of these medically relevant targets but are often costly to produce and have limited shelf lives.

"There are many diseases that are difficult to treat today simply because it is so challenging to detect certain molecules in the body. As tools for diagnosis, designed proteins may offer a more cost-effective alternative to antibodies," explained Venkatesh.

The study introduces a novel protein design approach that uses advanced deep-learning methods. The researchers present a new way of using RFdiffusion, a generative model for creating new protein shapes, in conjunction with the sequence-design tool ProteinMPNN. Developed in the Baker Lab, these programs allow scientists to create functional proteins more efficiently than ever before. By combining these tools in new ways, the team generated binding proteins by using limited target information, such as a peptide's amino acid sequence alone. The broad implications of this  "build to fit" approach suggest a new era in biotechnology in which AI-generated proteins can be used to detect complex molecules relevant to human health and the environment.

An AI-designed protein in detail from the UW Medicine Institute for Protein Design.
Ian Haydon/UW Medicine Institute for Protein Design
An AI-designed protein in detail from the UW Medicine Institute for Protein Design.

"We're witnessing an exciting era in protein design, where advanced artificial intelligence tools, like the ones featured in our study, are accelerating the improvement of protein activity. This breakthrough is set to redefine the landscape of biotechnology," noted Vazquez-Torres.

In collaboration with the Joseph Rogers Lab at the University of Copenhagen and the  Andrew Hoofnagle Lab at UW Medicine, the team conducted laboratory tests to validate their biodesign methods. Mass spectrometry was used to detect designed proteins that bind to low-concentration peptides in human serum, thereby demonstrating the potential for sensitive and accurate disease diagnostics. Additionally, the proteins were found to retain their target binding abilities despite harsh conditions including high heat, a crucial attribute for real-world application. Further showcasing the method's potential, the researchers integrated a high-affinity parathyroid hormone binder into a biosensor system and achieved a 21-fold increase in bioluminescence signal in samples that contained the target hormone. This integration into a diagnostic device highlights the immediate practical applications of AI-generated proteins.

The study, which illustrates the confluence of biotechnology and artificial intelligence and sets a new precedent in both fields, appears in Nature with the title “De novo design of high-affinity binders of bioactive helical peptides.”

(This article was produced by the University of Washington School of Medicine/UW Medicine.)

Enjoy reading ASBMB Today?

Become a member to receive the print edition monthly and the digital edition weekly.

Learn more
Ian C. Haydon
Ian C. Haydon

Ian C. Haydon is a science communicator and head of communications at the Institute for Protein Design, University of Washington School of Medicine. He holds a master's degree in biochemistry and was a 2018 Mass Media Fellow with the American Association for the Advancement of Science. He specializes in making biotechnology make sense.

Get the latest from ASBMB Today

Enter your email address, and we’ll send you a weekly email with recent articles, interviews and more.

Latest in Science

Science highlights or most popular articles

AI harnesses tumor genetics to predict treatment response
News

AI harnesses tumor genetics to predict treatment response

Feb. 18, 2024

Many paths lead to cancer resistance; artificial intelligence can decode them all simultaneously.

Progression of ALS linked to a membrane and an enzyme
News

Progression of ALS linked to a membrane and an enzyme

Feb. 17, 2024

Diminished activities of the enzyme TBK1 in mitochondrial-associated membrane reduces motor neurons’ tolerance to stressors, a causative factor in the disease.

From the journals: JLR
Journal News

From the journals: JLR

Feb. 16, 2024

Breaking down atherosclerotic plaque. Location matters in liver disease. A lipidomic profile drives liver disease. Read about recent papers on these topics.

Sibling study reveals mechanism for genetic disease
Journal News

Sibling study reveals mechanism for genetic disease

Feb. 13, 2024

Using proteomics experiments, researchers found that old proteins pile up in the mitochondria of people with a form of adult-onset muscular dystrophy.

Why don’t fruit bats get diabetes?
News

Why don’t fruit bats get diabetes?

Feb. 11, 2024

New understanding of how these animals have adapted to a high-sugar diet could lead to treatments for people.

The remaining frontiers in fighting hepatitis C
Interview

The remaining frontiers in fighting hepatitis C

Feb. 10, 2024

Charles Rice, whose work was key to finding treatments for this life-threatening virus, discusses the scientific journey and challenges that persist.