Related Experiment Video
Updated: May 4, 2026
Drug Repurposing Hypothesis Generation Using the "RE:fine Drugs" System
Published on: December 11, 2016
Integrating AI-enhanced kinase enrichment analysis (KEA) with geometric deep learning and federated learning for
Saleem Iqbal1, Jing Chen2, Debnath Pal3
1Department of Critical Care Medicine, Joint Laboratory of Artificial Intelligence for Critical Care Medicine and Institutes for Systems Genetics, Frontiers Science Center for Disease-Related Molecular Network, West China Hospital, Sichuan University, Xinchuan Road, 2222 Chengdu, Sichuan, China; Department of Neurology and Institutes for Systems Genetics, Frontiers Science Center for Disease-Related Molecular Network, West China Hospital, Sichuan University, Xinchuan Road, 2222 Chengdu, Sichuan, China; Department of Computational and Data Sciences, Indian Institute of Science, Bangalore 560012, India.
Abstract:
Artificial intelligence (AI) is reshaping drug repurposing by integrating systems biology with molecular design. Here, we present a unified framework combining AI-enhanced Kinase Enrichment Analysis (KEA), geometric deep learning, and federated learning to enable scalable and privacy-preserving therapeutic discovery. KEA prioritizes disease-relevant kinases from multi-omics data, while geometric deep learning captures structure-activity relationships (SARs) at atomic resolution. Federated learning facilitates secure, multi-institutional model training across heterogeneous datasets. This integrative pipeline enhances identification of repurposable kinase inhibitors and supports emerging modalities, such as proteolysis-targeting chimeras (PROTACs). A case study in Alzheimer's disease (AD) highlights improved target prioritization and predictive performance. By bridging kinase signaling networks with AI-driven modeling, this framework provides a robust strategy for accelerating precision drug discovery and repurposing.
