Molecular geometry pretraining with SE(3)-invariant denoising distance matching

Par Conseil national de recherches du Canada

Téléchargement	Voir la version de l’auteur : Molecular geometry pretraining with SE(3)-invariant denoising distance matching (PDF, 2.2 Mio)
Auteur	Rechercher : Liu, Shengchao; Rechercher : Guo, Hongyu¹; Rechercher : Tang, Jian
Affiliation	Conseil national de recherches du Canada. Technologies numériques
Format	Texte, Article
Conférence	Eleventh International Conference on Learning Representations (ICLR) 2023, May 1-5, 2023, Kigali, Rwanda [Hybrid]
Description physique	27 p.
Sujet	molecule; pretraining; representation; geometry; denoising score matching
Résumé	Molecular representation pretraining is critical in various applications for drug and material discovery due to the limited number of labeled molecules, and most existing work focuses on pretraining on 2D molecular graphs. However, the power of pretraining on 3D geometric structures has been less explored. This is owing to the difficulty of finding a sufficient proxy task that can empower the pretraining to effectively extract essential features from the geometric structures. Motivated by the dynamic nature of 3D molecules, where the continuous motion of a molecule in the 3D Euclidean space forms a smooth potential energy surface, we propose GeoSSL, a 3D coordinate denoising pretraining framework to model such an energy landscape. Further by leveraging an SE(3)-invariant score matching method, we propose GeoSSL-DDM in which the coordinate denoising proxy task is effectively boiled down to denoising the pairwise atomic distances in a molecule. Our comprehensive experiments confirm the effectiveness and robustness of our proposed method.
Date de publication	2023-05-05
Maison d’édition	The Conference OpenReview
Dans	ICLR 2023 - Eleventh International Conference on Learning Representations (5 mai 2023).
Données connexes	Molecular Geometry Pretraining with SE(3)-Invariant Denoising Distance Matching. https://github.com/chao1224/GeoSSL.
Autre version	Liu, Shengchao, Hongyu Guo, et Jian Tang. « Molecular Geometry Pretraining with SE(3)-Invariant Denoising Distance Matching ». arXiv, 2022. https://doi.org/10.48550/ARXIV.2206.13602.
Langue	anglais
Publications évaluées par des pairs	Oui
Exporter la notice	Exporter en format RIS
Signaler une correction	Signaler une correction (s'ouvre dans un nouvel onglet)
Identificateur de l’enregistrement	ab800d88-7e47-4470-b78d-43446b99a020
Enregistrement créé	2023-08-11
Enregistrement modifié	2023-08-14

Date de modification :: 2024-07-23