This week for the TDAI Data Science Spotlight, we are highlighting core faculty member, Xia Ning, and her pioneering research in AI-powered drug discovery. 

Dr. Ning, a professor of biomedical informatics and computer science and engineering at The Ohio State University as well as co-director of TDAI's Computational Health & Life Sciences community of practice, recently introduced DiffSMol with the help of her research team. DiffSMol is a generative AI model that is capable of generating realistic 3D structures of small molecules with strong potential as drug candidates. 

This generative AI model works by learning the shapes of known ligands, which are molecules that bind to protein targets, and uses them to generate new molecules with improved binding characteristics.

"By using well-known shapes as a condition, we can train our model to generate novel molecules with similar shapes that don't exist in previous chemical databases, " said Ning.

The model achieved a significant success rate of 61.4%, which showed a substantial leap over prior methods which averaged around 12%. DiffSMol also generates new molecules in just one second, dramatically accelerating the early stages of drug development. 

This study highlighted case studies targeting proteins involved specifically in cancer and Alzheimer's. 

"It's very encouraging for us to find molecules with even better properties than known ligands.... It indicates that our developed models have great potential in identifying good drug candidates," said Ning.

The research, supported by the National Science Foundation and other federal agencies, also emphasizes the importance of translational and open science. The DiffSMol research team made DiffSMol's code publicly available to encourage further innovation. Looking ahead, Dr. Ning and her team aim to extend the model's capabilities to handle more complex data and a broader range of molecular interactions. 

TDAI is proud to support the groundbreaking work of its core faculty and can't wait to see where Dr. Xia Ning and her research go next. To find more about this study, please follow to https://www.nature.com/articles/s42256-025-01030-w