EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Information-theoretic multi-scale geometric pre-training for enhanced molecular property prediction

Xiaoyu Hu, Xiuyuan Zhao, Jiyuan Wang iD, Yongbin Yang iD

PLOS One · 2025

DOI: 10.1371/journal.pone.0332640 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, 2025. Verfasst von Xiaoyu Hu und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Chemical Engineering and Materials Science, Stevens Institute of Technology, Hoboken, New Jersey, United States of America. Hauptthemen laut MEDLINE: Information Theory. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 52 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Maximizing information transfer across different structural scales is critical for effective molecular representation learning. Current molecular graph neural networks fail to fully capture the multi-scale nature of molecular geometry, leading to suboptimal information propagation between local and global structural features. We propose Multi-Scale Geometric Pre-training (MSG-Pre), an information-theoretic framework that hierarchically integrates molecular information across atomic, functional group, and conformer levels through entropy-guided mechanisms. Our approach employs a scale-adaptive attention mechanism that dynamically weights geometric features based on their information content, coupled with a hierarchical contrastive learning scheme that maximizes mutual information between complementary structural views. This is further reinforced by a geometric regularization strategy that minimizes information loss of essential conformational properties. Rigorous empirical validation on 14 molecular benchmark datasets demonstrates state-of-the-art performance with improvements up to 5.2% over previous methods. Notably, MSG-Pre significantly enhances information extraction for nanomedicine applications including nanoparticle-protein interactions and surface functionalization efficacy. Theoretical analysis reveals that MSG-Pre effectively maximizes cross-scale mutual information while minimizing intra-scale redundancy, maintaining an optimal information-entropy balance in molecular representations. Our work establishes an information-theoretic foundation for geometric pre-training that improves molecular understanding and enhances prediction capabilities for both drug discovery and nanomaterial design applications.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Information TheoryNeural Networks, ComputerAlgorithmsEntropy

Autor:innen und Institutionen

  • Department of Chemical Engineering and Materials Science, Stevens Institute of Technology, Hoboken, New Jersey, United States of America.
  • Stevens Institute of Technology, Hoboken, New Jersey, United States of America.
  • Duke University, Durham, North Carolina, United States of America.
  • University of Southern California, Los Angeles, California, United States of America.

ORCID-Profile: Jiyuan Wang, Yongbin Yang

Zitieren

APA

Hu, X., Zhao, X., Wang, J., & Yang, Y. (2025). Information-theoretic multi-scale geometric pre-training for enhanced molecular property prediction. PLOS One. https://doi.org/10.1371/journal.pone.0332640

Vancouver

Hu X, Zhao X, Wang J, Yang Y. Information-theoretic multi-scale geometric pre-training for enhanced molecular property prediction. PLOS One. 2025. doi:10.1371/journal.pone.0332640

BibTeX
@article{Hu2025,
  author = {Hu, Xiaoyu and Zhao, Xiuyuan and Wang, Jiyuan and Yang, Yongbin},
  title = {Information-theoretic multi-scale geometric pre-training for enhanced molecular property prediction},
  journal = {PLOS One},
  year = {2025},
  doi = {10.1371/journal.pone.0332640}
}
Kostenlos starten →