EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

PF-AGCN: an adaptive graph convolutional network for protein–protein interaction-based function prediction

Shumin Yang, Yuhan Su iD, Yuchen Lin, Qin Lin, Zhong Chen

Bioinformatics · 2025

DOI: 10.1093/bioinformatics/btaf473 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bioinformatics, 2025. Verfasst von Shumin Yang und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Electronic Science and Engineering, Xiamen University, Fujian 361005, China. Hauptthemen laut MEDLINE: Protein Interaction Mapping, Neural Networks, Computer, Software, Proteins. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Fujian Provincial Natural Science Foundation of China, Ministry of Education Industry-University Cooperation and Collaborative Education Project of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Motivation Proteins carry out most biological processes via interactions with other proteins, known as protein–protein interactions (PPIs). Accurately predicting PPIs is crucial for understanding protein function, yet existing methods often fall short in capturing their complex and hierarchical nature. Results We propose PF-AGCN, an adaptive graph convolutional network that leverages two distinct graph structures: a function graph representing hierarchical Gene Ontology term relationships and a protein graph modeling direct interactions between proteins. Unlike traditional graph attention networks, PF-AGCN preserves the original biological structures while dynamically learning new relationships, ensuring the retention of essential biological information. Additionally, our framework integrates a protein language model with stacked dilated causal convolutional neural networks, enabling the synergistic fusion of global sequence semantics and local structural patterns. Extensive experiments on a comprehensive protein dataset across three evaluation facets demonstrate PF-AGCN’s superior prediction accuracy. Availability and implementation The source code is publicly available at https://github.com/smyang107/PFAGCN.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Protein Interaction MappingNeural Networks, ComputerSoftwareProteinsComputational BiologyDatabases, ProteinGene OntologyAlgorithmsProtein Interaction Maps

Substanzen

Proteins

Autor:innen und Institutionen

  • School of Electronic Science and Engineering, Xiamen University, Fujian 361005, China.
  • First Affiliated Hospital of Xiamen University, Fujian 361000, China.

ORCID-Profile: Yuhan Su

Förderung

  • National Natural Science Foundation of China
  • Fujian Provincial Natural Science Foundation of China
  • Ministry of Education Industry-University Cooperation and Collaborative Education Project of China

Zitieren

APA

Yang, S., Su, Y., Lin, Y., Lin, Q., & Chen, Z. (2025). PF-AGCN: an adaptive graph convolutional network for protein–protein interaction-based function prediction. Bioinformatics. https://doi.org/10.1093/bioinformatics/btaf473

Vancouver

Yang S, Su Y, Lin Y, Lin Q, Chen Z. PF-AGCN: an adaptive graph convolutional network for protein–protein interaction-based function prediction. Bioinformatics. 2025. doi:10.1093/bioinformatics/btaf473

BibTeX
@article{Yang2025,
  author = {Yang, Shumin and Su, Yuhan and Lin, Yuchen and Lin, Qin and Chen, Zhong},
  title = {PF-AGCN: an adaptive graph convolutional network for protein–protein interaction-based function prediction},
  journal = {Bioinformatics},
  year = {2025},
  doi = {10.1093/bioinformatics/btaf473}
}
Kostenlos starten →