High-order graph convolutional networks for circular Ribonucleic Acid and disease association prediction incorporating multiple biological relationships

Abstract

Background

The search for circular Ribonucleic Acid (circRNA) associated with complex diseases holds considerable importance for disease diagnosis, treatment and research, helping to improve the early recognition and therapeutic efficacy of diseases, deepen the understanding of disease mechanisms, and provide guidance for new drug development.

Methods

This study presents an innovative high-order graph convolutional neural network, which leverages Gaussian kernels to compute the second-order proximity between nodes, thereby capturing long-range dependencies more effectively. Based on the topological structure of nodes in the graph, the model derives high-order embeddings, which not only enhance the preservation of the global network structure but also overcome the limitations of traditional methods that focus solely on local neighborhoods. Furthermore, by integrating this model with heterogeneous networks composed of multiple biological relationships, we successfully implement accurate predictions of circRNA-disease associations.

Results

This study achieved an area under the curve (AUC) of 0.9491 and an accuracy of 0.9920 on the constructed benchmark dataset, significantly outperforming existing methods in predictive performance, while most of the candidate circRNAs screened in the case studies of breast neoplasms and glioma have been confirmed in the literature.

Conclusions

This method provides a new perspective for integrating heterogeneous biological data in the study of complex disease-related circRNAs, and will advance further research and practical applications in this field.