EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Multi-View Heterogeneous Dual-Stream Graph Autoencoder for Predicting circRNA–Disease Associations

Yu-Hao Zhou, Chang-Qing Yu, Si-Qi Yao, Lei Wang, Zhu-Hong You iD

Biology · 04.11.2026 · 15 (21) · 2001

DOI: 10.3390/biology15212001 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Biology, online erschienen am 04.11.2026. Verfasst von Yu-Hao Zhou und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Electronic Information, Xijing University, Xi'an 710123, China. Die Arbeit nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Guangxi Science and Technology Program, Natural Science Foundation of Guangxi.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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.

Schlagwörter

Stichwörter der Autor:innen

CDA predictioncontrastive learning constraintsdual-stream graph autoencoderheterogeneous relation enhancementmulti-view graph attention network

Autor:innen und Institutionen

  • School of Electronic Information, Xijing University, Xi'an 710123, China.
  • Guangxi Key Lab of Human-Machine Interaction and Intelligent Decision, Guangxi Academy of Sciences, Nanning 530007, China.
  • School of Computer Science and Technology, China University of Mining and Technology, Xuzhou 221116, China.
  • School of Computer Science, Northwestern Polytechnical University, Xi'an 710129, China.

ORCID-Profile: Zhu-Hong You

Förderung

  • National Natural Science Foundation of China
  • Guangxi Science and Technology Program
  • Natural Science Foundation of Guangxi
  • Natural Science Foundation of Shandong
  • National Science Foundation for Distinguished Young Scholars of China

Zitieren

APA

Zhou, Y. H., Yu, C. Q., Yao, S. Q., Wang, L., & You, Z. H. (2026). A Multi-View Heterogeneous Dual-Stream Graph Autoencoder for Predicting circRNA–Disease Associations. Biology, 15(21), 2001. https://doi.org/10.3390/biology15212001

Vancouver

Zhou YH, Yu CQ, Yao SQ, Wang L, You ZH. A Multi-View Heterogeneous Dual-Stream Graph Autoencoder for Predicting circRNA–Disease Associations. Biology. 2026;15(21):2001. doi:10.3390/biology15212001

BibTeX
@article{Zhou2026,
  author = {Zhou, Yu-Hao and Yu, Chang-Qing and Yao, Si-Qi and Wang, Lei and You, Zhu-Hong},
  title = {A Multi-View Heterogeneous Dual-Stream Graph Autoencoder for Predicting circRNA–Disease Associations},
  journal = {Biology},
  year = {2026},
  volume = {15},
  number = {21},
  pages = {2001},
  doi = {10.3390/biology15212001}
}
Kostenlos starten →