AI RESEARCH
Don't Retrain, Just Reuse: Recovering Dual-Target Molecules from Single-Target Diffusion Models
arXiv CS.AI
•
ArXi:2605.25681v1 Announce Type: cross Designing a single molecule that modulates two targets is a promising strategy for polypharmacology, but it remains substantially harder than standard single-target generation because one candidate must satisfy two binding requirements while preserving drug-likeness and synthesizability. Existing dual-target generative methods typically