Prediction of circRNA–Disease Associations via Graph Isomorphism Transformer and Dual-Stream Neural Predictor

Biomolecules, Journal Year: 2025, Volume and Issue: 15(2), P. 234 - 234

Published: Feb. 6, 2025

Circular RNAs (circRNAs) have attracted increasing attention for their roles in human diseases, making the prediction of circRNA-disease associations (CDAs) a critical research area advancing disease diagnosis and treatment. However, traditional experimental methods exploring CDAs are time-consuming resource-intensive, while existing computational models often struggle with sparsity CDA data fail to uncover potential effectively. To address these challenges, we propose novel method named Graph Isomorphism Transformer Dual-Stream Neural Predictor (GIT-DSP), which leverages knowledge graph technology predict more Specifically, model incorporates multiple between circRNAs, other non-coding (e.g., lncRNAs, miRNAs) construct multi-source heterogeneous graph, thereby expanding scope exploration. Subsequently, is proposed fully exploit both local global association information within enabling deeper insights into CDAs. Furthermore, introduced accurately complex by integrating dual-stream predictive features. Experimental results demonstrate that GIT-DSP outperforms state-of-the-art models, offering valuable precision medicine disease-related research.

Language: Английский

Redefining Biomedicine: Artificial Intelligence at the Forefront of Discovery

Biomolecules, Journal Year: 2024, Volume and Issue: 14(12), P. 1597 - 1597

Published: Dec. 14, 2024

The rapid evolution of artificial intelligence (AI) is redefining biomedicine, placing itself at the forefront groundbreaking discoveries in molecular biology, genomics, drug discovery, diagnostics, and beyond [...]

Language: Английский