Soosung Kang

FragDockRL uses reinforcement learning to design ligands by assembling building blocks and tethered docking, outperforming random search on three protein targets.

EnsDTI improves drug-target interaction prediction by combining multiple models and providing confidence scores, achieving a 2.7% accuracy improvement over baselines.

EnsDTI-kinase is a web-server that combines eight computational models to predict kinase-inhibitor interactions, offering improved accuracy and mutagenesis analysis.