UCL Discovery Stage
UCL home » Library Services » Electronic resources » UCL Discovery Stage

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

Vignac, C; Osman, N; Toni, L; Frossard, P; (2023) MiDi: Mixed Graph and 3D Denoising Diffusion for Molecule Generation. In: Joint European Conference on Machine Learning and Knowledge Discovery in Databases ECML PKDD 2023: Machine Learning and Knowledge Discovery in Databases: Research Track. (pp. pp. 560-576). Springer: Cham, Switzerland. Green open access

[thumbnail of MiDi___ECML___camera_ready.pdf]
Preview
Text
MiDi___ECML___camera_ready.pdf - Accepted Version

Download (946kB) | Preview

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 for the previous EDM model that uses interatomic distances for bond prediction, and using EDM followed by an algorithm that directly optimizes bond orders for validity. Our code is available at github.com/cvignac/MiDi.

Type: Proceedings paper
Title: MiDi: Mixed Graph and 3D Denoising Diffusion for Molecule Generation
Event: European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases 2023
Location: Turin, Italy
Dates: 18 Sep 2023 - 22 Sep 2023
ISBN-13: 9783031434143
Open access status: An open access version is available from UCL Discovery
DOI: 10.1007/978-3-031-43415-0_33
Publisher version: https://doi.org/10.1007/978-3-031-43415-0_33
Language: English
Additional information: This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions.
Keywords: Diffusion Model, Drug Discovery, Graph Generation
UCL classification: UCL
UCL > Provost and Vice Provost Offices > UCL BEAMS
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Electronic and Electrical Eng
URI: https://discovery-pp.ucl.ac.uk/id/eprint/10181491
Downloads since deposit
30Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item