AI Fast-Tracks Drug Discovery and Treatment Innovation

A new computational tool, developed with support from the U.S. National Science Foundation, promises to significantly accelerate the process of determining RNA’s 3D structure—a crucial step in advancing RNA-based drug development, identifying drug-binding sites, and expanding RNA’s role in biotechnology and medicine.

The tool, called NuFold, uses advanced machine learning to predict the structure of a wide range of RNA molecules directly from their sequences. This capability enables scientists to visualize potential RNA shapes and explore their functions in drug delivery, disease treatment, and other biomedical applications. The research behind NuFold was recently published in Nature Communications.

RNAs are essential biological molecules, carrying genetic information like DNA and performing vital cellular functions like proteins. Yet, only a small fraction of RNA structures—about 3%—have been identified and documented in resources like the NSF-supported RCSB Protein Data Bank. The traditional methods for determining RNA structure are labor-intensive, slow, and expensive, limiting our ability to fully understand RNA’s diverse roles.

By accurately predicting RNA structures from sequence data alone, NuFold could dramatically speed up the discovery of RNA functions and unlock new possibilities for designing RNA-based therapies and biotechnologies.

SOURCE: https://www.nsf.gov/news/using-machine-learning-speed-discovery-drug-delivery-disease 

CREDITS: NATIONAL SCIENCE FOUNDATION