Mixed Continuous and Categorical Flow Matching for 3D De Novo Molecule Generation

arXiv:2404.19739v1 Announce Type: cross
Abstract: Deep generative models that produce novel molecular structures have the potential to facilitate chemical discovery. Diffusion models currently achieve state of the art performance for 3D molecule generation. In this work, we explore the use of flow matching, a recently proposed generative modeling framework that generalizes diffusion models, for the task of de novo molecule generation. Flow matching provides flexibility in model design; however, the framework is predicated on the assumption of continuously-valued data. 3D …

arxiv categorical continuous cs.lg flow mixed q-bio.bm type