EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Relational similarity-based graph contrastive learning for DTI prediction

Jilong Bian iD, Hao Lu, Limin Wei, Yang Li iD, Guohua Wang iD

Briefings in Bioinformatics · 2025

DOI: 10.1093/bib/bbaf122 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Briefings in Bioinformatics, 2025. Verfasst von Jilong Bian und 4 weiteren Autor:innen. Beteiligte Einrichtung: College of Computer and Control Engineering, Northeast Forestry University, Harbin 150040, Heilongjiang, China. Hauptthemen laut MEDLINE: Drug Repositioning, Deep Learning, Proteins, Computational Biology. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, National Key R&D Program of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

As part of the drug repurposing process, it is imperative to predict the interactions between drugs and target proteins in an accurate and efficient manner. With the introduction of contrastive learning into drug-target prediction, the accuracy of drug repurposing will be further improved. However, a large part of DTI prediction methods based on deep learning either focus only on the structural features of proteins and drugs extracted using GNN or CNN, or focus only on their relational features extracted using heterogeneous graph neural networks on a DTI heterogeneous graph. Since the structural and relational features of proteins and drugs describe their attribute information from different perspectives, their combination can improve DTI prediction performance. We propose a relational similarity-based graph contrastive learning for DTI prediction (RSGCL-DTI), which combines the structural and relational features of drugs and proteins to enhance the accuracy of DTI predictions. In our proposed method, the inter-protein relational features and inter-drug relational features are extracted from the heterogeneous drug–protein interaction network through graph contrastive learning, respectively. The results demonstrate that combining the relational features obtained by graph contrastive learning with the structural ones extracted by D-MPNN and CNN enhances feature representation ability, thereby improving DTI prediction performance. Our proposed RSGCL-DTI outperforms eight SOTA baseline models on the four benchmark datasets, performs well on the imbalanced dataset, and also shows excellent generalization ability on unseen drug–protein pairs.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Drug RepositioningDeep LearningProteinsComputational BiologyNeural Networks, ComputerHumansAlgorithms

Stichwörter der Autor:innen

DTI predictiongraph contrastive learningrelational similarity networkstructural features

Substanzen

Proteins

Autor:innen und Institutionen

  • College of Computer and Control Engineering, Northeast Forestry University, Harbin 150040, Heilongjiang, China.

ORCID-Profile: Jilong Bian, Yang Li, Guohua Wang

Förderung

  • National Natural Science Foundation of China
  • National Key R&D Program of China

Zitieren

APA

Bian, J., Lu, H., Wei, L., Li, Y., & Wang, G. (2025). Relational similarity-based graph contrastive learning for DTI prediction. Briefings in Bioinformatics. https://doi.org/10.1093/bib/bbaf122

Vancouver

Bian J, Lu H, Wei L, Li Y, Wang G. Relational similarity-based graph contrastive learning for DTI prediction. Briefings in Bioinformatics. 2025. doi:10.1093/bib/bbaf122

BibTeX
@article{Bian2025,
  author = {Bian, Jilong and Lu, Hao and Wei, Limin and Li, Yang and Wang, Guohua},
  title = {Relational similarity-based graph contrastive learning for DTI prediction},
  journal = {Briefings in Bioinformatics},
  year = {2025},
  doi = {10.1093/bib/bbaf122}
}
Kostenlos starten →