EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

SGCLDGA: unveiling drug–gene associations through simple graph contrastive learning

Yanhao Fan, Che Zhang, Xiaowen Hu, Zhijian Huang, Jiameng Xue, Lei Deng

Briefings in Bioinformatics · 2024

DOI: 10.1093/bib/bbae231 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Briefings in Bioinformatics, 2024. Verfasst von Yanhao Fan und 5 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science and Engineering, Central South University, 410075, Changsha, China. Hauptthemen laut MEDLINE: Neural Networks, Computer. Die Arbeit wurde bisher 17-mal zitiert (Crossref) und nennt 48 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Drug repurposing offers a viable strategy for discovering new drugs and therapeutic targets through the analysis of drug–gene interactions. However, traditional experimental methods are plagued by their costliness and inefficiency. Despite graph convolutional network (GCN)-based models’ state-of-the-art performance in prediction, their reliance on supervised learning makes them vulnerable to data sparsity, a common challenge in drug discovery, further complicating model development. In this study, we propose SGCLDGA, a novel computational model leveraging graph neural networks and contrastive learning to predict unknown drug–gene associations. SGCLDGA employs GCNs to extract vector representations of drugs and genes from the original bipartite graph. Subsequently, singular value decomposition (SVD) is employed to enhance the graph and generate multiple views. The model performs contrastive learning across these views, optimizing vector representations through a contrastive loss function to better distinguish positive and negative samples. The final step involves utilizing inner product calculations to determine association scores between drugs and genes. Experimental results on the DGIdb4.0 dataset demonstrate SGCLDGA’s superior performance compared with six state-of-the-art methods. Ablation studies and case analyses validate the significance of contrastive learning and SVD, highlighting SGCLDGA’s potential in discovering new drug–gene associations. The code and dataset for SGCLDGA are freely available at https://github.com/one-melon/SGCLDGA.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Neural Networks, ComputerHumansDrug RepositioningComputational BiologyAlgorithmsSoftwareDrug DiscoveryMachine Learning

Stichwörter der Autor:innen

contrastive learningdrug–gene associationgraph neural networksingular value decomposition

Autor:innen und Institutionen

  • School of Computer Science and Engineering, Central South University, 410075, Changsha, China.
  • School of software, Xinjiang University, 830046, Urumqi, China.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Fan, Y., Zhang, C., Hu, X., Huang, Z., Xue, J., & Deng, L. (2024). SGCLDGA: unveiling drug–gene associations through simple graph contrastive learning. Briefings in Bioinformatics. https://doi.org/10.1093/bib/bbae231

Vancouver

Fan Y, Zhang C, Hu X, Huang Z, Xue J, Deng L. SGCLDGA: unveiling drug–gene associations through simple graph contrastive learning. Briefings in Bioinformatics. 2024. doi:10.1093/bib/bbae231

BibTeX
@article{Fan2024,
  author = {Fan, Yanhao and Zhang, Che and Hu, Xiaowen and Huang, Zhijian and Xue, Jiameng and Deng, Lei},
  title = {SGCLDGA: unveiling drug–gene associations through simple graph contrastive learning},
  journal = {Briefings in Bioinformatics},
  year = {2024},
  doi = {10.1093/bib/bbae231}
}
Kostenlos starten →