EUVIMEDEUVIMED entdecken
Crossref

MOL-Mamba: Enhancing Molecular Representation with Structural & Electronic Insights

Jingjing Hu, Dan Guo, Zhan Si, Deguang Liu, Yunfeng Diao, Jing Zhang, Jinxing Zhou, Meng Wang

Proceedings of the AAAI Conference on Artificial Intelligence · 11.04.2025 · 39 (1) · 317-325

DOI: 10.1609/aaai.v39i1.32009 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 11.04.2025. Verfasst von Jingjing Hu und 7 weiteren Autor:innen. Die Arbeit wurde bisher 7-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Molecular representation learning plays a crucial role in various downstream tasks, such as molecular property prediction and drug design. To accurately represent molecules, Graph Neural Networks (GNNs) and Graph Transformers (GTs) have shown potential in the realm of self-supervised pretraining. However, existing approaches often overlook the relationship between molecular structure and electronic information, as well as the internal semantic reasoning within molecules. This omission of fundamental chemical knowledge in graph semantics leads to incomplete molecular representations, missing the integration of structural and electronic data. To address these issues, we introduce MOL-Mamba, a framework that enhances molecular representation by combining structural and electronic insights. MOL-Mamba consists of an Atom & Fragment Mamba-Graph (MG) for hierarchical structural reasoning and a Mamba-Transformer (MT) fuser for integrating molecular structure and electronic correlation learning. Additionally, we propose a Structural Distribution Collaborative Training and E-semantic Fusion Training framework to further enhance molecular representation learning. Extensive experiments demonstrate that MOL-Mamba outperforms state-of-the-art baselines across eleven chemical-biological molecular datasets.

Zitieren

APA

Hu, J., Guo, D., Si, Z., Liu, D., Diao, Y., Zhang, J., Zhou, J., & Wang, M. (2025). MOL-Mamba: Enhancing Molecular Representation with Structural & Electronic Insights. Proceedings of the AAAI Conference on Artificial Intelligence, 39(1), 317-325. https://doi.org/10.1609/aaai.v39i1.32009

Vancouver

Hu J, Guo D, Si Z, Liu D, Diao Y, Zhang J, et al. MOL-Mamba: Enhancing Molecular Representation with Structural & Electronic Insights. Proceedings of the AAAI Conference on Artificial Intelligence. 2025;39(1):317-325. doi:10.1609/aaai.v39i1.32009

BibTeX
@article{Hu2025,
  author = {Hu, Jingjing and Guo, Dan and Si, Zhan and Liu, Deguang and Diao, Yunfeng and Zhang, Jing and Zhou, Jinxing and Wang, Meng},
  title = {MOL-Mamba: Enhancing Molecular Representation with Structural & Electronic Insights},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2025},
  volume = {39},
  number = {1},
  pages = {317--325},
  doi = {10.1609/aaai.v39i1.32009}
}
Kostenlos starten →