Researchers at the Icahn School of Medicine at Mount Sinai have identified a previously hidden site for drugs in a cancer-related protein that could open the door to the development of a new generation of more precise cancer drugs. The finding also reveals significant limitations in current AI tools for drug discovery.
The study, published in the June 2 online issue of Journal of the American Chemical Society [10.1021/jacs.6c05178]focused on PKMYT1, a type of protein known as a kinase that helps control how cells grow and divide. Because this process can go wrong in cancer, PKMYT1 has emerged as a promising target for new anticancer drugs.
Most experimental drugs designed to block the kinases work by targeting a region called the ATP-binding site — the part of the protein that uses the cell’s energy supply to function. However, many kinases share nearly identical ATP-binding sites, making it difficult for drugs to distinguish between their desired target and other kinases, which can lead to unwanted side effects.
Using a combination of AI-based protein prediction tools and laboratory experiments, the researchers discovered an entirely new “hidden” pocket in PKMYT1 where a molecule could bind—a location missed by today’s state-of-the-art AI systems.
Our study shows both the power and limitations of artificial intelligence in drug discovery. The AI was very accurate in predicting known protein shapes, but missed a completely unexpected binding pocket that we could only uncover experimentally. This hidden site may ultimately provide a new way to design more selective anticancer drugs.”
Avner Schlessinger, PhD, co-senior and co-corresponding author, Professor of Pharmacological Sciences, Director of the AI Micromolecule Drug Discovery Center and Associate Director, Mount Sinai Center for Therapeutic Discovery, Icahn School of Medicine at Mount Sinai
The findings suggest that proteins like PKMYT1 are much more flexible than previously appreciated, constantly shifting between different conformations rather than existing in a single stable form. The study also found that even tiny chemical changes in a molecule could dramatically change how and where it binds to the protein, the researchers say.
The research team used the AI system AlphaFold2 to predict possible structures of PKMYT1 and then performed virtual screening to identify molecules that could interact with it. X-ray crystallography, biochemical tests and cell studies followed to confirm how the molecules behaved in various experimental systems.
Additional AI tools, including AlphaFold3 and Boltz-2, along with molecular dynamics simulations were then used to test whether current computational approaches could predict the newly discovered docking function.
“One of the most surprising findings was that a very small chemical modification caused the molecule to switch from binding in this hidden pocket to binding in a much more conventional way,” says co-senior and co-corresponding author Michael Lazarus, PhD, Associate Professor of Pharmacological Sciences and Associate Director of Theraphna’s Discover Center. Medicine at Mount Sinai. “This tells us that these proteins are incredibly dynamic and sensitive to subtle molecular changes. It also reinforces why experimental validation remains essential, even in the age of artificial intelligence.”
The researchers say the work could eventually help scientists develop more selective drugs that avoid some of the toxicity and specificity challenges associated with traditional kinase inhibitors. The findings may also help improve future artificial intelligence systems by teaching them to better recognize hidden and dynamic protein states that are currently overlooked.
While additional research is needed, the findings provide an important early basis for the development of future therapies targeting this newly discovered site. The compounds identified in the study represent promising starting points for further optimization and testing in disease models.
Next, the team plans to develop more potent compounds that target the newly discovered site and investigate whether similar hidden pockets exist in other cancer-related kinases. They also hope to improve computational methods so that AI systems can better predict these hard-to-detect protein shapes in the future.
Source:
Journal Reference:
