MiDi: Mixed Graph and 3D Denoising Diffusion for Molecule Generation

Clement Vignac, Nagham Osman, Laura Toni, Pascal Frossard

Keywords: Molecule generation, diffusion models, graph generation, 3D generation

TL;DR: MiDi is a denoising diffusion model that simultaneously generates a molecular graph and a corresponding conformer.

Abstract: This work introduces MiDi, a diffusion model for jointly generating molecular graphs and corresponding 3D conformers. In contrast to existing models which derive molecular bonds from the conformation using predefined rules, MiDi streamlines the molecule generation process with an end-to-end differentiable model. Preliminary results demonstrate the benefits of this approach: on the complex GEOM-DRUGS dataset, our model generates significantly better molecular graphs than 3D-based models, and even surpasses specialized algorithms that directly optimize the bond orders for validity.

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/arxiv:2302.09048/code)