DecompOpt: Controllable and Decomposed Diffusion Models for Structure-based Molecular Optimization

arXiv:2403.13829v1 Announce Type: cross
Abstract: Recently, 3D generative models have shown promising performances in structure-based drug design by learning to generate ligands given target binding sites. However, only modeling the target-ligand distribution can hardly fulfill one of the main goals in drug discovery -- designing novel ligands with desired properties, e.g., high binding affinity, easily synthesizable, etc. This challenge becomes particularly pronounced when the target-ligand pairs used for training do not align with these desired properties. Moreover, most existing methods …

abstract arxiv cs.lg design designing diffusion diffusion models discovery distribution drug design drug discovery generate generative generative models however modeling novel optimization performances q-bio.bm type