EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

MGMA-PPIS: Predicting the protein–protein interaction site with multiview graph embedding and multiscale attention fusion

Yong Han iD, Shao-Wu Zhang iD, Qing-Qing Zhang iD, Ming-Hui Shi iD

GigaScience · 2025

DOI: 10.1093/gigascience/giaf114 ↗

Kurz gefasst

Fachartikel in der Zeitschrift GigaScience, 2025. Verfasst von Yong Han und 3 weiteren Autor:innen. Beteiligte Einrichtung: MOE Key Laboratory of Information Fusion Technology, School of Automation, Northwestern Polytechnical University, Xi'an 710072, China. Hauptthemen laut MEDLINE: Computational Biology, Protein Interaction Mapping, Neural Networks, Computer, Proteins. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Protein–protein interactions (PPIs) play a crucial role in numerous biological processes. Accurate identification of protein–protein interaction sites is critical for a comprehensive understanding of protein functions and pathological mechanisms. However, conventional experimental approaches for detecting PPIs are often time-consuming and labor-intensive, thereby motivating the development of efficient computational methods to identify PPI sites.

Results

In this work, we propose a novel graph neural network–based method (called MGMA-PPIS) to predict PPI sites by adopting multiview graph embedding and multiscale attention fusion. MGMA-PPIS integrates global node features extracted by an equivariant graph neural network and multiscale local node features extracted by an edge graph attention network across different neighborhood scales, thereby constructing a multiview graph feature representation. Then, a multiscale attention network is employed to perform deep feature fusion across multiple scales for achieving high-precision prediction of PPI sites.

Conclusions

Experimental results on benchmark datasets show that our MGMA-PPIS outperforms other state-of-the-art methods, and it can effectively predict PPI sites.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Computational BiologyProtein Interaction MappingNeural Networks, ComputerProteinsAlgorithmsDatabases, ProteinProtein Interaction MapsHumans

Stichwörter der Autor:innen

graph neural networkmultiscale attention networkprotein–protein interaction sites

Substanzen

Proteins

Autor:innen und Institutionen

  • MOE Key Laboratory of Information Fusion Technology, School of Automation, Northwestern Polytechnical University, Xi'an 710072, China.
  • Department of Police Administration, Henan Judicial Police Vocational College, Zhengzhou 450046, China.

ORCID-Profile: Yong Han, Shao-Wu Zhang, Qing-Qing Zhang, Ming-Hui Shi

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Han, Y., Zhang, S. W., Zhang, Q. Q., & Shi, M. H. (2025). MGMA-PPIS: Predicting the protein–protein interaction site with multiview graph embedding and multiscale attention fusion. GigaScience. https://doi.org/10.1093/gigascience/giaf114

Vancouver

Han Y, Zhang SW, Zhang QQ, Shi MH. MGMA-PPIS: Predicting the protein–protein interaction site with multiview graph embedding and multiscale attention fusion. GigaScience. 2025. doi:10.1093/gigascience/giaf114

BibTeX
@article{Han2025,
  author = {Han, Yong and Zhang, Shao-Wu and Zhang, Qing-Qing and Shi, Ming-Hui},
  title = {MGMA-PPIS: Predicting the protein–protein interaction site with multiview graph embedding and multiscale attention fusion},
  journal = {GigaScience},
  year = {2025},
  doi = {10.1093/gigascience/giaf114}
}
Kostenlos starten →