EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

BridgeNet: a high-efficiency framework integrating sequence and structure for protein and enzyme function prediction

Yilin Ye, Hongliang Duan, Yuguang Mu iD, Lei Wu, Jingjing Guo iD

Briefings in Bioinformatics · 2025

DOI: 10.1093/bib/bbaf607 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Briefings in Bioinformatics, 2025. Verfasst von Yilin Ye und 4 weiteren Autor:innen. Beteiligte Einrichtung: Faculty of Applied Sciences, Macao Polytechnic University, R. de Luís Gonzaga Gomes, Macao, 999078, China. Hauptthemen laut MEDLINE: Proteins, Enzymes, Computational Biology, Deep Learning. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 78 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: Macao Polytechnic University, Science and Technology Development Fund of Macau.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Understanding the relationship between protein sequences and structures is essential for accurate protein property prediction. We propose BridgeNet, a pre-trained deep learning framework that integrates sequence and structural information through a novel latent environment matrix, enabling seamless alignment of these two modalities. The model’s modular architecture—comprising sequence encoding, structural encoding, and a bridge module—effectively captures complementary features without requiring explicit structural inputs during inference. Extensive evaluations on tasks such as enzyme classification, Gene Ontology annotation, coenzyme specificity prediction, and peptide toxicity prediction demonstrate its superior performance over state-of-the-art models. BridgeNet provides a scalable and robust solution, advancing protein representation learning and enabling applications in computational biology and structural bioinformatics.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

ProteinsEnzymesComputational BiologyDeep LearningSequence Analysis, ProteinSoftwareProtein ConformationAmino Acid SequenceDatabases, ProteinAlgorithms

Stichwörter der Autor:innen

deep learning in bioinformaticsprotein property predictionprotein representation learningsequence-structure integration

Substanzen

ProteinsEnzymes

Autor:innen und Institutionen

  • Faculty of Applied Sciences, Macao Polytechnic University, R. de Luís Gonzaga Gomes, Macao, 999078, China.
  • School of Biological Sciences, Nanyang Technological University, 50 Nanyang Avenue, 639798, Singapore.
  • College of Mechanical and Electronic Engineering, China University of Petroleum (East China), 66 Changjiang West Road, Huangdao District, Qingdao, 266580, China.

ORCID-Profile: Yuguang Mu, Jingjing Guo

Förderung

  • Macao Polytechnic University
  • Science and Technology Development Fund of Macau

Zitieren

APA

Ye, Y., Duan, H., Mu, Y., Wu, L., & Guo, J. (2025). BridgeNet: a high-efficiency framework integrating sequence and structure for protein and enzyme function prediction. Briefings in Bioinformatics. https://doi.org/10.1093/bib/bbaf607

Vancouver

Ye Y, Duan H, Mu Y, Wu L, Guo J. BridgeNet: a high-efficiency framework integrating sequence and structure for protein and enzyme function prediction. Briefings in Bioinformatics. 2025. doi:10.1093/bib/bbaf607

BibTeX
@article{Ye2025,
  author = {Ye, Yilin and Duan, Hongliang and Mu, Yuguang and Wu, Lei and Guo, Jingjing},
  title = {BridgeNet: a high-efficiency framework integrating sequence and structure for protein and enzyme function prediction},
  journal = {Briefings in Bioinformatics},
  year = {2025},
  doi = {10.1093/bib/bbaf607}
}
Kostenlos starten →