Nov 2026· Biology· Vol 15, pp. 2001· 0 citations· 41 references
TL;DR
A multi-view heterogeneous dual-stream graph autoencoder for CDA prediction that combines multi-view graph attention encoding, heterogeneous relation enhancement, dual-stream association reconstruction, and contrastive regularization is proposed.
Abstract
Circular RNAs (circRNAs) participate in gene regulation and disease-associated processes. Computational prediction of circRNA–disease associations (CDAs) can help prioritize candidates for biological investigation. Here, we propose a multi-view heterogeneous dual-stream graph autoencoder (MHDA) for CDA prediction. MHDA combines multi-view graph attention encoding, heterogeneous relation enhancement, dual-stream association reconstruction, and contrastive regularization. The encoder learns representations from complementary similarity views and adaptively fuses them. A heterogeneous attention module then integrates within-type and cross-type relationships. The decoder combines element-wise interactions with concatenated pair representations through gated fusion to score candidate associations. On the CircR2Disease dataset, MHDA achieves an AUC of 0.9633 and an AUPR of 0.9599 under five-fold cross-validation. Ablation analyses support the contributions of the main model components. Of the top 25 ranked candidate associations, 22 have supporting evidence in the published literature. These results suggest that MHDA is useful for prioritizing potential CDAs and provides promising candidates for subsequent experimental validation.
Accumulating evidence suggests that long noncoding RNAs (lncRNAs) interact synergistically with diverse cellular molecules to regulate a wide range of biological processes. Identifying lncRNA-disease associations (LDAs) is therefore essential for elucidating disease mechanisms and advancing biomarker discovery. Althoug...
Lin Ni, Qing-Yang Liu, Hong-Jiu Liu et al.· Computational biology and ch...· 0 citations
Circular RNAs (circRNAs) have a covalently closed structure and high stability in complex biological samples, making them promising disease biomarkers. However, the sparsity and imbalance of known circRNA–disease associations (CDAs) necessitate computational approaches for CDA prediction. Competition among multiple cir...
Yu-Hao Zhou, Xiao-Peng Ji, Zhu-Hong You et al.· Biology· 0 citations
IHCDA is proposed, an information-enhanced and heterogeneity-aware learning model for circRNA-disease association prediction that introduces auxiliary relational structures to enhance sparse similarity information by incorporating structural relational knowledge, and seamlessly integrates it into the representation lea...
Yu-Qing Ma, Mao-Zu Guo, Le Tian et al.· Scientific Reports· 0 citations
CDVGL-PDA’s strong predictive performance across balanced, imbalanced, and low-similarity datasets is demonstrated, while case studies highlight its ability to uncover potential PDAs, illustrating its promise for advancing disease mechanism research and therapeutic target discovery.
Xiang Chen, Li-Jun Quan, Ye-Xuan Mao et al.· Bioinform.· 0 citations
Abstract Motivation CircRNA–miRNA interactions (CMIs) play regulatory roles in human diseases and provide clues for therapeutic target discovery. However, most existing prediction methods rely on circRNA–miRNA pairs and overlook disease-level regulatory contexts, which limits their ability to characterize cross-pathway...
Mengmeng Wei, Lei Wang, Yu-An Huang et al.· Bioinformatics· 1 citation
Identifying Metabolite–Disease Associations (MDAs) is essential for understanding
disease mechanisms and discovering biomarkers. However, traditional experimental validation
is costly and incomplete, necessitating advanced computational approaches to infer potential associations
from biological data.
We prop...
Yu Guo, Hao-Zheng Liang, Shi-Zheng Qiu et al.· Current Bioinformatics· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.