Drug Discovery & Repurposing

Summary

Discovering a therapy requires connecting evidence across molecular profiles, chemical structures, protein targets, pathways, clinical data and experimental models. We develop and evaluate computational strategies that bring these sources together to prioritize drug-target relationships and therapeutic candidates.

Our work combines network medicine, machine learning, molecular docking and experimental validation. A central goal is to understand when predictive models generalize to new proteins, compounds and diseases, rather than performing well only on well-annotated examples.

Drug repurposing is an important part of this research. By systematically evaluating existing compounds, it can shorten the path between a biological hypothesis and a candidate therapy, particularly for emerging infections, rare diseases and conditions underserved by traditional drug development.

Research directions

• Network-based prioritization of drugs and therapeutic targets
• Generalizable and interpretable protein-ligand prediction
• Integration of computational rankings with experimental evidence
• Evaluation of drug repurposing strategies across diseases

Selected publications

• Chatterjee A, Walters R, Shafi Z, et al. Improving the generalizability of protein-ligand binding predictions with AI-Bind. Nature Communications (2023). doi:10.1038/s41467-023-37572-z

• Patten JJ, Keiser PT, Gysi DM, et al. Multidose evaluation of 6,710 drug repurposing library identifies potent SARS-CoV-2 infection inhibitors in vitro and in vivo. iScience (2022). Read the article

• Gysi DM, do Valle I, Zitnik M, et al. Network medicine framework for identifying drug-repurposing opportunities for COVID-19. Proceedings of the National Academy of Sciences (2021). doi:10.1073/pnas.2025581118