DiffMol: 3D Structured Molecule Generation with Discrete Denoising Diffusion Probabilistic Models
Abstract
3D structures of molecules are often required to investigate atomistic phenomena accurately in industries such as drug design. We propose DiffMol, a novel method that utilizes diffusion models to generate the 3D position of atoms and utilizes the discrete denoising diffusion process to generate the atom type. Compared to existing methods, our algorithm offers greater flexibility for post-processing and refining the generated molecules and demonstrates faster performance. We provide theoretical proof of the equivariance of the diffusion process for molecule position generation. Our model achieved better than state-of-the-art performance in molecule/atom stability and molecule validity on benchmarks generating 3D molecules.
Cite
Text
Zhang et al. "DiffMol: 3D Structured Molecule Generation with Discrete Denoising Diffusion Probabilistic Models." ICML 2023 Workshops: SPIGM, 2023.Markdown
[Zhang et al. "DiffMol: 3D Structured Molecule Generation with Discrete Denoising Diffusion Probabilistic Models." ICML 2023 Workshops: SPIGM, 2023.](https://mlanthology.org/icmlw/2023/zhang2023icmlw-diffmol/)BibTeX
@inproceedings{zhang2023icmlw-diffmol,
title = {{DiffMol: 3D Structured Molecule Generation with Discrete Denoising Diffusion Probabilistic Models}},
author = {Zhang, Weitong and Wang, Xiaoyun and Smith, Justin and Eaton, Joe and Rees, Brad and Gu, Quanquan},
booktitle = {ICML 2023 Workshops: SPIGM},
year = {2023},
url = {https://mlanthology.org/icmlw/2023/zhang2023icmlw-diffmol/}
}