KAIST and Nobel Laureate Achieve Success in Designing "Artificial Proteins" Using AI

KAIST announced on April 9, 2026, that Professor Lee Gyuri from the Department of Biological Sciences at KAIST and Professor David Baker from the University of Washington in the United States have successfully designed "artificial proteins" that selectively recognize specific compounds using artificial intelligence (AI).

Professor Lee is a member of the AI-CRED Innovative Drug Discovery InnoCORE research team. Professor David Baker, who was awarded the 2024 Nobel Prize in Chemistry, collaborated with Professor Lee in the joint research and participated in the process of designing artificial proteins using AI.

The joint research focused on designing proteins from scratch that can recognize specific compounds through AI and implementing them as functional biosensors.

Previously, the main approach was to search for natural proteins or modify certain functions. In contrast, the joint research team’s study is significant in that they "custom-built" proteins with desired functions through AI-based design and completed experimental validation.

In particular, the joint research team succeeded in designing a protein that selectively recognizes cortisol, a stress hormone, and then implementing a biosensor designed by AI based on this protein.

This demonstrates not only the design of the protein, but also its expansion into measurable sensor technology. It is also regarded as a case that solves the long-standing challenge in the field of protein design—recognizing small molecules.

The joint research team anticipates that the results of this study will be applicable in a wide range of fields, including disease diagnosis, drug development, and environmental monitoring.

Additionally, the team expects that precise detection of biomarkers in blood will enable early disease diagnosis and that the design of proteins that selectively recognize specific molecules can contribute to the development of targeted therapeutics.

Furthermore, the team expects this technology to enable the development of sensors that detect environmental pollutants and allow real-time monitoring of air and water quality, advancing the implementation of customized biosensor technologies.

Professor Lee stated, "This study has experimentally proven that it is possible to design proteins that precisely recognize specific compounds using AI," adding, "The joint research team plans to expand our research to develop protein design technologies applicable to various fields, such as disease diagnosis, drug development, and environmental monitoring."

Meanwhile, this study was conducted with Professor Lee Gyuri from KAIST as the first author and Professor David Baker as the corresponding author. The research results were published in the international journal 'Nature Communications' on March 28, 2026.

This content was produced with the assistance of AI translation services.