University of Washington professor David Baker has made a name for himself by borrowing computer science concepts like machine learning and artificial intelligence to solve problems in biology. A few years ago, his lab surprised scientists by constructing an AI-powered protein-folding prediction system rivaling Google’s DeepMind AlphaFold. Now Baker is pushing forward in a different area of drug discovery research.
“Look, there’s this huge class of compounds we can make that chemically are just very, very different from proteins,” Baker told STAT, with “building blocks that really don’t look anything like the L-amino acids that existing proteins [have], and have all kinds of unnatural backbones and chemistries.”
A new paper from Baker’s lab, out Thursday in Science, details a new computational method for quickly compiling a large library of macrocycle drug candidates, a class of drugs that are bigger than small molecules but smaller than biologics. These Goldilocks drugs are prized because they can be taken orally and pass through membranes, reaching important proteins inside the cell, but also have the requisite size and shape to target receptors that usually require bigger molecules like antibodies.
This article is exclusive to STAT+ subscribers
Unlock this article — plus in-depth analysis, newsletters, premium events, and networking platform access.
Already have an account? Log in
Already have an account? Log in
About the Author Reprints
To submit a correction request, please visit our Contact Us page.
STAT encourages you to share your voice. We welcome your commentary, criticism, and expertise on our subscriber-only platform, STAT+ Connect