DA-HGL: a domain-augmented heterogeneous graph learning framework for protein function prediction
Briefings in Bioinformatics · 2025
DOI: 10.1093/bib/bbaf511 ↗Kurz gefasst
Fachartikel in der Zeitschrift Briefings in Bioinformatics, 2025. Verfasst von Sai Hu und 2 weiteren Autor:innen. Beteiligte Einrichtung: School of Mathematics, Changsha University, No. 98 Hongshan Road, Changsha, Hunan 410022, China. Hauptthemen laut MEDLINE: Computational Biology, Proteins, Software, Machine Learning. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Hunan Provincial Key Laboratory of Industrial Internet Technology and Security, National Scientific Research Foundation of Hunan Province, Natural Science Foundation of Hunan Province.
Abstract (Originalsprache)
Accurate protein function prediction is critical for deciphering disease mechanisms and advancing precision medicine, yet remains challenging for proteins with sparse annotations. Traditional methods struggle with annotation sparsity and fail to integrate multimodal data holistically. We propose DA-HGL, a heterogeneous graph learning framework that integrates protein sequences, domain architectures, and Gene Ontology (GO) hierarchies through a multilayered graph and non-negative matrix factorization with dual biological constraints. DA-HGL uniquely models domain-function coherence, GO semantic consistency, and topological congruence. Evaluated on yeast and human proteomes, DA-HGL achieves Fmax gains of 9.0% (yeast CC) and 17.2% (human BP) over state-of-the-art methods. By dynamically learning domain-context associations and resolving annotation sparsity, DA-HGL excels in cold-start scenarios and disease-specific predictions (e.g. Parkinson’s “ubiquitin-dependent catabolism”). This framework offers a robust tool for accelerating functional genomics and precision medicine. Code/data: https://github.com/husaiccsu/DA-HGL.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- School of Mathematics, Changsha University, No. 98 Hongshan Road, Changsha, Hunan 410022, China.
- School of Computer Science and Engineering, Changsha University, No. 98 Hongshan Road, Changsha, Hunan 410022, China.
- Hunan Provincial Key Laboratory of Industrial Internet Technology and Security, Changsha University, No. 98 Hongshan Road, Changsha, Hunan 410022, China.
ORCID-Profile: Bihai Zhao
Förderung
- Hunan Provincial Key Laboratory of Industrial Internet Technology and Security
- National Scientific Research Foundation of Hunan Province
- Natural Science Foundation of Hunan Province
- National Natural Science Foundation of China
Zitieren
APA
Hu, S., Zhang, W., & Zhao, B. (2025). DA-HGL: a domain-augmented heterogeneous graph learning framework for protein function prediction. Briefings in Bioinformatics. https://doi.org/10.1093/bib/bbaf511
Vancouver
Hu S, Zhang W, Zhao B. DA-HGL: a domain-augmented heterogeneous graph learning framework for protein function prediction. Briefings in Bioinformatics. 2025. doi:10.1093/bib/bbaf511
BibTeX
@article{Hu2025,
author = {Hu, Sai and Zhang, Wei and Zhao, Bihai},
title = {DA-HGL: a domain-augmented heterogeneous graph learning framework for protein function prediction},
journal = {Briefings in Bioinformatics},
year = {2025},
doi = {10.1093/bib/bbaf511}
}
EUVIMED