Molecular hypergraph neural networks
The Journal of Chemical Physics · 14.04.2024 · 160 (14)
DOI: 10.1063/5.0193557 ↗Kurz gefasst
Fachartikel in der Zeitschrift The Journal of Chemical Physics, online erschienen am 10.04.2024. Verfasst von Junwu Chen und 1 weiteren Autor:innen. Beteiligte Einrichtung: Laboratory of Artificial Chemical Intelligence (LIAC), Institute of Chemical Sciences and Engineering, Ecole Polytechnique Fédérale de Lausanne (EPFL…. Die Arbeit wurde bisher 37-mal zitiert (Crossref) und nennt 59 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NCCR Catalysis.
Abstract (Originalsprache)
Graph neural networks (GNNs) have demonstrated promising performance across various chemistry-related tasks. However, conventional graphs only model the pairwise connectivity in molecules, failing to adequately represent higher order connections, such as multi-center bonds and conjugated structures. To tackle this challenge, we introduce molecular hypergraphs and propose Molecular Hypergraph Neural Networks (MHNNs) to predict the optoelectronic properties of organic semiconductors, where hyperedges represent conjugated structures. A general algorithm is designed for irregular high-order connections, which can efficiently operate on molecular hypergraphs with hyperedges of various orders. The results show that MHNN outperforms all baseline models on most tasks of organic photovoltaic, OCELOT chromophore v1, and PCQM4Mv2 datasets. Notably, MHNN achieves this without any 3D geometric information, surpassing the baseline model that utilizes atom positions. Moreover, MHNN achieves better performance than pretrained GNNs under limited training data, underscoring its excellent data efficiency. This work provides a new strategy for more general molecular representations and property prediction tasks related to high-order connections.
Autor:innen und Institutionen
- Laboratory of Artificial Chemical Intelligence (LIAC), Institute of Chemical Sciences and Engineering, Ecole Polytechnique Fédérale de Lausanne (EPFL), Lausanne, Switzerland.
- National Centre of Competence in Research (NCCR) Catalysis, Ecole Polytechnique Fédérale de Lausanne (EPFL), Lausanne, Switzerland.
ORCID-Profile: Junwu Chen, Philippe Schwaller
Förderung
- NCCR Catalysis
Zitieren
APA
Chen, J., & Schwaller, P. (2024). Molecular hypergraph neural networks. The Journal of Chemical Physics, 160(14). https://doi.org/10.1063/5.0193557
Vancouver
Chen J, Schwaller P. Molecular hypergraph neural networks. The Journal of Chemical Physics. 2024;160(14). doi:10.1063/5.0193557
BibTeX
@article{Chen2024,
author = {Chen, Junwu and Schwaller, Philippe},
title = {Molecular hypergraph neural networks},
journal = {The Journal of Chemical Physics},
year = {2024},
volume = {160},
number = {14},
doi = {10.1063/5.0193557}
}
EUVIMED