EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

MAGIN-GO: Protein function prediction based on dual graph neural networks and gene ontology structure

Runxin Li, Wentao Xie iD, Zhenhong Shang, Xiaowu Li, Guofeng Shu, Lianyin Jia, Wei Peng

PLOS One · 2026

DOI: 10.1371/journal.pone.0342072 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, 2026. Verfasst von Runxin Li und 6 weiteren Autor:innen. Beteiligte Einrichtung: Yunnan Key Laboratory of Computer Technologies Application, Kunming University of Science and Technology, Kunming, China. Hauptthemen laut MEDLINE: Gene Ontology, Proteins, Computational Biology. Die Arbeit nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Applied Basic Research Foundation of Yunnan Province, the Research Foundation of the Education Bureau of Yunnan Province, the Open Fund of Yunnan Key Laboratory of Computer Technology Application.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Proteins are fundamental to the execution of biological activities, and the accurate prediction of their functions is of paramount importance for protein research. Recent advancements in deep learning, particularly those based on Graph Neural Networks (GNNs), have demonstrated promising results by integrating protein graph features with sequence information. However, traditional GNN methods exhibit limitations in their feature representation capabilities, failing to capture long-range dependencies within sequences and lacking incorporation of inter-annotation relationships. To address these challenges, we propose a method, MAGIN-GO, which combines Graph Isomorphism Network (GIN) and Graph Convolutional Network (GCN) with Graph Convolutional Self-Attention Network (GMSA) to extract multi-source protein information and integrates Gene Ontology (GO) annotation embeddings. Our method effectively combines protein sequence features with protein-protein interaction (PPI) graph node features, extracts topological and contextual information through GIN and GMSA, and integrates pre-trained GO term embeddings into a multi-label classification framework. Comprehensive experiments on the UniProtKB/Swiss-Prot dataset demonstrate that MAGIN-GO outperforms existing methods, achieving AUPR values of 0.569, 0.434, and 0.754 for Molecular Function (MF), Biological Process (BP), and Cellular Component (CC) domains, respectively, with corresponding Fmax scores of 0.568, 0.458, and 0.752, Smin scores of 11.297, 37.709, and 8.079, and AUC scores of 0.896, 0.897, and 0.940. The experimental results showed that the performance of MAGIN-GO was good and superior to the existing methods.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Gene OntologyProteinsComputational BiologyGraph Neural NetworksProtein Interaction MapsDatabases, Protein

Substanzen

Proteins

Autor:innen und Institutionen

  • Yunnan Key Laboratory of Computer Technologies Application, Kunming University of Science and Technology, Kunming, China.
  • Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, China.

ORCID-Profile: Wentao Xie

Förderung

  • Applied Basic Research Foundation of Yunnan Province
  • the Research Foundation of the Education Bureau of Yunnan Province
  • the Open Fund of Yunnan Key Laboratory of Computer Technology Application
  • the National Natural Science Foundation of China

Zitieren

APA

Li, R., Xie, W., Shang, Z., Li, X., Shu, G., Jia, L., & Peng, W. (2026). MAGIN-GO: Protein function prediction based on dual graph neural networks and gene ontology structure. PLOS One. https://doi.org/10.1371/journal.pone.0342072

Vancouver

Li R, Xie W, Shang Z, Li X, Shu G, Jia L, et al. MAGIN-GO: Protein function prediction based on dual graph neural networks and gene ontology structure. PLOS One. 2026. doi:10.1371/journal.pone.0342072

BibTeX
@article{Li2026,
  author = {Li, Runxin and Xie, Wentao and Shang, Zhenhong and Li, Xiaowu and Shu, Guofeng and Jia, Lianyin and Peng, Wei},
  title = {MAGIN-GO: Protein function prediction based on dual graph neural networks and gene ontology structure},
  journal = {PLOS One},
  year = {2026},
  doi = {10.1371/journal.pone.0342072}
}
Kostenlos starten →