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

Abstract

This work introduces MiDi, a novel diffusion model for jointly generating molecular graphs and their corresponding 3D atom arrangements. Unlike existing methods that rely on predefined rules to determine molecular bonds based on the 3D conformation, MiDi offers an end-to-end differentiable approach that streamlines the molecule generation process. Our experimental results demonstrate the effectiveness of this approach. On the challenging GEOM-DRUGS dataset, MiDi generates 92% of stable molecules, against $6\%$ for the previous EDM model that uses interatomic distances for bond prediction, and $40\%$ using EDM followed by an algorithm that directly optimizes bond orders for validity. Our code is available at github.com/cvignac/MiDi .

Cite

Text

Vignac et al. "MiDi: Mixed Graph and 3D Denoising Diffusion for Molecule Generation." European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2023. doi:10.1007/978-3-031-43415-0_33

Markdown

[Vignac et al. "MiDi: Mixed Graph and 3D Denoising Diffusion for Molecule Generation." European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2023.](https://mlanthology.org/ecmlpkdd/2023/vignac2023ecmlpkdd-midi/) doi:10.1007/978-3-031-43415-0_33

BibTeX

@inproceedings{vignac2023ecmlpkdd-midi,
  title     = {{MiDi: Mixed Graph and 3D Denoising Diffusion for Molecule Generation}},
  author    = {Vignac, Clément and Osman, Nagham and Toni, Laura and Frossard, Pascal},
  booktitle = {European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases},
  year      = {2023},
  pages     = {560-576},
  doi       = {10.1007/978-3-031-43415-0_33},
  url       = {https://mlanthology.org/ecmlpkdd/2023/vignac2023ecmlpkdd-midi/}
}