EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

MSF-HierGNN: a multi-source substructure-fusion hierarchical GNN method and web server to predict molecular property for drug design

Ming Xiao iD, Yi Xiao, Yingping Wu, Yujie You, Xiaolei Liu, Hoang Van Thanh, Le Zhang iD

Briefings in Bioinformatics · 2026

DOI: 10.1093/bib/bbag491 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Briefings in Bioinformatics, 2026. Verfasst von Ming Xiao und 6 weiteren Autor:innen. Beteiligte Einrichtung: College of Computer Science, Sichuan University, No. 24 South Section 1, Yihuan Road, Wuhou District, Chengdu 610065, China. Hauptthemen laut MEDLINE: Drug Design, Software. Die Arbeit nennt 73 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Sichuan Science and Technology Program Key Project, National Natural Science Foundation of China, Noncommunicable Chronic Diseases-National Science and Technology Major Project.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate prediction of the biological and physicochemical properties of molecules is of great significance in shortening the process and decreasing the failure rate of drug design. Thus, previous studies have established several benchmark datasets and developed several Graph Neural Networks (GNNs) based artificial intelligence (AI) predictive methods. However, since these methods encounter challenges such as incomplete representation of molecular hierarchical structures, insufficient exploration of local topological features, and under-extraction of correlations among atomic features, our study proposes a graph neural network that combines hierarchical pooling with localized substructure modeling named MSF-HierGNN (Multi-Source Substructure-Fusion Hierarchical Graph Neural Network) to solve these problems. Firstly, MSF-HierGNN constructs a more comprehensive and multiscale graph-level representation by preserving chemically salient structures and fusing multiple sources of substructure. Secondly, the model can more comprehensively represent molecular substructure features by integrating multiple fragmentation algorithms and incorporating five molecular fingerprints. Additionally, the model further captures correlations among atomic features by increasing the message-passing mechanism. Finally, we validate the model's effectiveness using public benchmark datasets and develop an interactive and user-friendly web server application based on MSF-HierGNN. Experiments based on benchmark datasets demonstrate that our model not only can effectively extract molecular substructure features and capture correlations among atomic features, but also can more accurately predict molecular properties, thereby offering a novel AI method and application to support drug discovery and design.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Drug DesignSoftwareGraph Neural NetworksAlgorithmsInternetArtificial Intelligence

Stichwörter der Autor:innen

drug discovery and target predictiongraph neural networkmolecular property predictionmulti-source information fusionsubstructure representation

Autor:innen und Institutionen

  • College of Computer Science, Sichuan University, No. 24 South Section 1, Yihuan Road, Wuhou District, Chengdu 610065, China.
  • School of Computer Science and Engineering, Sichuan University of Science and Engineering, No. 1 Baita Road, Sanjiang New Area, Yibin 644000, China.
  • Department of Geriatrics and National Clinical Research Center for Geriatrics, West China Hospital, Sichuan University, No. 37 Guoxue Alley, Wuhou District, Chengdu, Sichuan 610041, China.
  • College of Mechanical Engineering, Vietnam Maritime University, No. 484 Lach Tray Street, Le Chan District, Hai Phong 180000, Vietnam.

ORCID-Profile: Ming Xiao, Le Zhang

Förderung

  • Sichuan Science and Technology Program Key Project
  • National Natural Science Foundation of China
  • Noncommunicable Chronic Diseases-National Science and Technology Major Project

Zitieren

APA

Xiao, M., Xiao, Y., Wu, Y., You, Y., Liu, X., Van Thanh, H., & Zhang, L. (2026). MSF-HierGNN: a multi-source substructure-fusion hierarchical GNN method and web server to predict molecular property for drug design. Briefings in Bioinformatics. https://doi.org/10.1093/bib/bbag491

Vancouver

Xiao M, Xiao Y, Wu Y, You Y, Liu X, Van Thanh H, et al. MSF-HierGNN: a multi-source substructure-fusion hierarchical GNN method and web server to predict molecular property for drug design. Briefings in Bioinformatics. 2026. doi:10.1093/bib/bbag491

BibTeX
@article{Xiao2026,
  author = {Xiao, Ming and Xiao, Yi and Wu, Yingping and You, Yujie and Liu, Xiaolei and Van Thanh, Hoang and Zhang, Le},
  title = {MSF-HierGNN: a multi-source substructure-fusion hierarchical GNN method and web server to predict molecular property for drug design},
  journal = {Briefings in Bioinformatics},
  year = {2026},
  doi = {10.1093/bib/bbag491}
}
Kostenlos starten →