Cited by Carbon-based molecular properties efficiently predicted by deep learning-based quantum chemical simulation with large language models

Molecular hypergraph neural networks DOI

Junwu Chen, Philippe Schwaller

The Journal of Chemical Physics, Journal Year: 2024, Volume and Issue: 160(14)

Published: April 10, 2024

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 propose Molecular Hypergraph Neural Networks (MHNNs) predict optoelectronic properties of organic semiconductors, where hyperedges A general algorithm is designed for irregular high-order which can efficiently operate on with orders. The results show that MHNN outperforms all baseline models most tasks photovoltaic, OCELOT chromophore v1, PCQM4Mv2 datasets. Notably, achieves without any 3D geometric information, surpassing utilizes atom positions. Moreover, better than pretrained GNNs under limited training data, underscoring its excellent data efficiency. This work provides a new strategy more representations property prediction related connections.

Language: Английский

Citations

GTC: GNN-Transformer co-contrastive learning for self-supervised heterogeneous graph representation DOI

Yundong Sun, Dongjie Zhu, Yansong Wang

et al.

Neural Networks, Journal Year: 2024, Volume and Issue: 181, P. 106645 - 106645

Published: Aug. 16, 2024

Language: Английский

Citations

Perspectives on Advancing Multimodal Learning in Environmental Science and Engineering Studies DOI

Wenjia Liu, Jingwen Chen, Haobo Wang

et al.

Environmental Science & Technology, Journal Year: 2024, Volume and Issue: unknown

Published: Sept. 3, 2024

The environment faces increasing anthropogenic impacts, resulting in a rapid increase environmental issues that undermine the natural capital essential for human wellbeing. These are complex and often influenced by various factors represented data with different modalities. While machine learning (ML) provides data-driven tools addressing issues, current ML models science engineering (ES&E) neglect utilization of multimodal data. With advancement deep learning, (MML) holds promise comprehensive descriptions harnessing from diverse This has potential to significantly elevate accuracy robustness prediction ES&E studies, providing enhanced solutions modeling tasks. perspective summarizes MML methodologies proposes applications including quality assessment, chemical hazards, optimization pollution control techniques. Additionally, we discuss challenges associated implementing propose future research directions this domain.

Language: Английский

Citations

Collaborative weighting in federated graph neural networks for disease classification with the human-in-the-loop DOI

Christian Hausleitner,

Heimo Mueller,

Andreas Holzinger

et al.

Scientific Reports, Journal Year: 2024, Volume and Issue: 14(1)

Published: Sept. 19, 2024

Language: Английский

Citations

Carbon-based molecular properties efficiently predicted by deep learning-based quantum chemical simulation with large language models DOI

Haoyu Wang, Bin Chen, Hangling Sun

et al.

Computers in Biology and Medicine, Journal Year: 2024, Volume and Issue: 176, P. 108531 - 108531

Published: May 1, 2024

Language: Английский

Citations