EUVIMEDEUVIMED entdecken
Crossref

CLHGNNMDA: Hypergraph Neural Network Model Enhanced by Contrastive Learning for miRNA–Disease Association Prediction

Rong Zhu iD, Yong Wang, Ling-Yun Dai

Journal of Computational Biology · 2025

DOI: 10.1089/cmb.2024.0720 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Computational Biology, 2025. Verfasst von Rong Zhu und 2 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science, Qufu Normal University, Rizhao, China. Hauptthemen laut MEDLINE: MicroRNAs, Neural Networks, Computer, Algorithms, Computational Biology. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 68 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Numerous biological experiments have demonstrated that microRNA (miRNA) is involved in gene regulation within cells, and mutations and abnormal expression of miRNA can cause a myriad of intricate diseases. Forecasting the association between miRNA and diseases can enhance disease prevention and treatment and accelerate drug research, which holds considerable importance for the development of clinical medicine and drug research. This investigation introduces a contrastive learning-augmented hypergraph neural network model, termed CLHGNNMDA, aimed at predicting associations between miRNAs and diseases. Initially, CLHGNNMDA constructs multiple hypergraphs by leveraging diverse similarity metrics related to miRNAs and diseases. Subsequently, hypergraph convolution is applied to each hypergraph to extract feature representations for nodes and hyperedges. Following this, autoencoders are employed to reconstruct information regarding the feature representations of nodes and hyperedges and to integrate various features of miRNAs and diseases extracted from each hypergraph. Finally, a joint contrastive loss function is utilized to refine the model and optimize its parameters. The CLHGNNMDA framework employs multi-hypergraph contrastive learning for the construction of a contrastive loss function. This approach takes into account inter-view interactions and upholds the principle of consistency, thereby augmenting the model’s representational efficacy. The results obtained from fivefold cross-validation substantiate that the CLHGNNMDA algorithm achieves a mean area under the receiver operating characteristic curve of 0.9635 and a mean area under the precision-recall curve of 0.9656. These metrics are notably superior to those attained by contemporary state-of-the-art methodologies.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

MicroRNAsNeural Networks, ComputerAlgorithmsComputational BiologyHumansGenetic Predisposition to DiseaseMachine Learning

Stichwörter der Autor:innen

contrastive learningfive-fold cross-validationhypergraph neural networkmiRNA–disease association prediction

Substanzen

MicroRNAs

Autor:innen und Institutionen

  • School of Computer Science, Qufu Normal University, Rizhao, China.
  • Laboratory Experimental Teaching and Equipment Management Center, Qufu Normal University, Rizhao, China.

ORCID-Profile: Rong Zhu

Zitieren

APA

Zhu, R., Wang, Y., & Dai, L. Y. (2025). CLHGNNMDA: Hypergraph Neural Network Model Enhanced by Contrastive Learning for miRNA–Disease Association Prediction. Journal of Computational Biology. https://doi.org/10.1089/cmb.2024.0720

Vancouver

Zhu R, Wang Y, Dai LY. CLHGNNMDA: Hypergraph Neural Network Model Enhanced by Contrastive Learning for miRNA–Disease Association Prediction. Journal of Computational Biology. 2025. doi:10.1089/cmb.2024.0720

BibTeX
@article{Zhu2025,
  author = {Zhu, Rong and Wang, Yong and Dai, Ling-Yun},
  title = {CLHGNNMDA: Hypergraph Neural Network Model Enhanced by Contrastive Learning for miRNA–Disease Association Prediction},
  journal = {Journal of Computational Biology},
  year = {2025},
  doi = {10.1089/cmb.2024.0720}
}
Kostenlos starten →