EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

EGPDI: identifying protein–DNA binding sites based on multi-view graph embedding fusion

Mengxin Zheng iD, Guicong Sun iD, Xueping Li, Yongxian Fan iD

Briefings in Bioinformatics · 2024

DOI: 10.1093/bib/bbae330 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Briefings in Bioinformatics, 2024. Verfasst von Mengxin Zheng und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science and Information Security, Guilin University of Electronic Technology, Guilin 541004, China. Hauptthemen laut MEDLINE: DNA, DNA-Binding Proteins, Neural Networks, Computer, Computational Biology. Die Arbeit wurde bisher 21-mal zitiert (Crossref) und nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Guangxi Natural Science Foundation, Innovation Project of GUET Graduate Education.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Mechanisms of protein-DNA interactions are involved in a wide range of biological activities and processes. Accurately identifying binding sites between proteins and DNA is crucial for analyzing genetic material, exploring protein functions, and designing novel drugs. In recent years, several computational methods have been proposed as alternatives to time-consuming and expensive traditional experiments. However, accurately predicting protein-DNA binding sites still remains a challenge. Existing computational methods often rely on handcrafted features and a single-model architecture, leaving room for improvement. We propose a novel computational method, called EGPDI, based on multi-view graph embedding fusion. This approach involves the integration of Equivariant Graph Neural Networks (EGNN) and Graph Convolutional Networks II (GCNII), independently configured to profoundly mine the global and local node embedding representations. An advanced gated multi-head attention mechanism is subsequently employed to capture the attention weights of the dual embedding representations, thereby facilitating the integration of node features. Besides, extra node features from protein language models are introduced to provide more structural information. To our knowledge, this is the first time that multi-view graph embedding fusion has been applied to the task of protein–DNA binding site prediction. The results of five-fold cross-validation and independent testing demonstrate that EGPDI outperforms state-of-the-art methods. Further comparative experiments and case studies also verify the superiority and generalization ability of EGPDI.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

DNADNA-Binding ProteinsNeural Networks, ComputerComputational BiologyBinding SitesAlgorithmsProtein Binding

Stichwörter der Autor:innen

equivariant graph neural networkgated attention mechanismmulti-view graph embedding fusionprotein language modelsprotein–DNA binding site prediction

Substanzen

DNADNA-Binding Proteins

Autor:innen und Institutionen

  • School of Computer Science and Information Security, Guilin University of Electronic Technology, Guilin 541004, China.

ORCID-Profile: Mengxin Zheng, Guicong Sun, Yongxian Fan

Förderung

  • National Natural Science Foundation of China
  • Guangxi Natural Science Foundation
  • Innovation Project of GUET Graduate Education

Zitieren

APA

Zheng, M., Sun, G., Li, X., & Fan, Y. (2024). EGPDI: identifying protein–DNA binding sites based on multi-view graph embedding fusion. Briefings in Bioinformatics. https://doi.org/10.1093/bib/bbae330

Vancouver

Zheng M, Sun G, Li X, Fan Y. EGPDI: identifying protein–DNA binding sites based on multi-view graph embedding fusion. Briefings in Bioinformatics. 2024. doi:10.1093/bib/bbae330

BibTeX
@article{Zheng2024,
  author = {Zheng, Mengxin and Sun, Guicong and Li, Xueping and Fan, Yongxian},
  title = {EGPDI: identifying protein–DNA binding sites based on multi-view graph embedding fusion},
  journal = {Briefings in Bioinformatics},
  year = {2024},
  doi = {10.1093/bib/bbae330}
}
Kostenlos starten →