EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

ASCE-PPIS: A Protein-Protein Interaction Sites Predictor Based on Equivariant Graph Neural Network with Fusion of Structure-Aware Pooling and Graph Collapse

Guanghao Shen, Ziqi Zhang, Zhaohong Deng iD, Xiaoyong Pan iD, Hong-Bin Shen iD, Dong-Jun Yu iD, Shudong Hu, Yuxi Ge

Bioinformatics · 2025

DOI: 10.1093/bioinformatics/btaf423 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bioinformatics, 2025. Verfasst von Guanghao Shen und 7 weiteren Autor:innen. Beteiligte Einrichtung: School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, Jiangsu 214012, China. Hauptthemen laut MEDLINE: Neural Networks, Computer, Protein Interaction Mapping, Computational Biology, Proteins. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National key R&D program, NSFC, Leading Talents in Medical and Health Professions.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Motivation Identifying protein-protein interaction sites constitutes a crucial step in understanding disease mechanisms and drug development. As experimental methods for PPIS identification are expensive and time-consuming, numerous computational screening approaches have been developed, among which graph neural network based methods have achieved remarkable progress in recent years. However, existing methods lack the utilization of interactions between amino acid molecules and fail to address the dense characteristics of protein graphs. Results We propose ASCE-PPIS, an equivariant graph neural network-based method for protein-protein interaction prediction. This novel approach integrates graph pooling and graph collapse to address the aforementioned challenges. Our model learns molecular features and interactions through an equivariant neural network, and constructs subgraphs to acquire multi-scale features based on a structure-adaptive sampling strategy, and fuses the information of the original and subgraphs through graph collapse. Finally, we fusing protein large language model features through the ensemble strategy based on bagging and meta-modeling to improve the generalization performance on different proteins. Experimental results demonstrate that ASCE-PPIS achieves over 10% performance improvement compared to existing methods on the Test60 dataset, highlighting its potential in PPI site prediction tasks. Availability and implementation The datasets and the source codes along with the pre-trained models of ASCE-PPIS are available at https://github.com/nunhehheh/ASCE-PPIS. Supplementary information Supplementary data are available at Bioinformatics online.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Neural Networks, ComputerProtein Interaction MappingComputational BiologyProteinsAlgorithmsDatabases, ProteinBinding SitesGraph Neural Networks

Substanzen

Proteins

Autor:innen und Institutionen

  • School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, Jiangsu 214012, China.
  • Engineering Research Center of Intelligent Technology for Healthcare, Ministry of Education, Jiangnan University, Wuxi, Jiangsu 214012, China.
  • School of Automation and Intelligent Sensing, Shanghai Jiao Tong University, Shanghai 200240, China.
  • School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing 210014, China China.
  • Affiliated Hospital of Jiangnan University, Wuxi 214000, China.

ORCID-Profile: Zhaohong Deng, Xiaoyong Pan, Hong-Bin Shen, Dong-Jun Yu

Förderung

  • National key R&D program
  • NSFC
  • Leading Talents in Medical and Health Professions
  • Mading academician
  • Basic Research Funds for Central Universities

Zitieren

APA

Shen, G., Zhang, Z., Deng, Z., Pan, X., Shen, H. B., Yu, D. J., Hu, S., & Ge, Y. (2025). ASCE-PPIS: A Protein-Protein Interaction Sites Predictor Based on Equivariant Graph Neural Network with Fusion of Structure-Aware Pooling and Graph Collapse. Bioinformatics. https://doi.org/10.1093/bioinformatics/btaf423

Vancouver

Shen G, Zhang Z, Deng Z, Pan X, Shen HB, Yu DJ, et al. ASCE-PPIS: A Protein-Protein Interaction Sites Predictor Based on Equivariant Graph Neural Network with Fusion of Structure-Aware Pooling and Graph Collapse. Bioinformatics. 2025. doi:10.1093/bioinformatics/btaf423

BibTeX
@article{Shen2025,
  author = {Shen, Guanghao and Zhang, Ziqi and Deng, Zhaohong and Pan, Xiaoyong and Shen, Hong-Bin and Yu, Dong-Jun and Hu, Shudong and Ge, Yuxi},
  title = {ASCE-PPIS: A Protein-Protein Interaction Sites Predictor Based on Equivariant Graph Neural Network with Fusion of Structure-Aware Pooling and Graph Collapse},
  journal = {Bioinformatics},
  year = {2025},
  doi = {10.1093/bioinformatics/btaf423}
}
Kostenlos starten →