AI-Driven
Drug Discovery &
Precision Medicine

We combine artificial intelligence, computational chemistry, and biomedical science to advance drug discovery. Our work spans molecular property prediction, activity-cliff-aware learning, and lead optimization, with tools such as MolMap and Leadmaster. We develop AI agents that connect molecular design, synthesis planning, and experimental feedback, alongside biomedical foundation models that bring together molecular and clinical data to support target identification and therapeutic hypothesis generation.

For precision oncology, we integrate genomics, transcriptomics, and proteomics to understand tumor heterogeneity and identify therapeutic targets, using approaches such as AggMap. Our research draws on multimodal fusion, contrastive learning, and retrieval-augmented generation to connect biological insights with clinical questions. Our COMPASS model predicts immunotherapy response across cancer types, with multi-center validation supporting its clinical translation.