Robust and comprehensive meta-path modeling with multi-graph learning for miRNA-disease association prediction.
- 1PEI DINGYI Institute of Cryptology and Cyberspace Institute of Advanced Technology, Guangzhou University, 230 Wai Huan Xi Road, Guangzhou Higher Education Mega Center, 510006, Guangzhou, Guangdong, China.
- 2School of Cyber Science and Technology, Beihang University, 37 Xueyuan Road, Haidian District, Beijing 100191, China.
- 3The Tenth Clinical Medical College of Guangzhou University of Traditional Chinese Medicine, Zhongshan Hospital of Traditional Chinese Medicine, 3 Kangxin Road, West District, 528400, Zhongshan, Guangdong, China.
Abstract
MicroRNA (miRNA)-disease association prediction is important for biomarker discovery and therapeutic target prioritization. However, existing methods have not adequately captured heterogeneous biological semantics while maintaining robustness under incomplete or perturbed graphs. Therefore, this study aims to develop a robust graph-learning framework that more effectively captures heterogeneous biological semantics. We propose the Semantic Hierarchical Integration for miRNA-Disease Association prediction (SHiMDA) on contextual heterogeneous biomedical graphs. SHiMDA constructs independent views for direct associations and biologically meaningful meta-paths, and performs segment-wise message passing to explicitly encode the internal structure of meta-path instances rather than collapsing each path into a coarse source-target shortcut. A confidence-weighted ranking loss and over-smoothing regularization further reduce supervision bias and representation homogenization under graph perturbations. Extensive experiments on benchmark datasets show that SHiMDA achieves strong predictive performance in basic and contextual settings and consistently outperforms representative state-of-the-art baselines under adversarial edge and feature perturbations. By explicitly modeling segment-wise meta-path semantics and introducing robustness-oriented optimization, SHiMDA improves the reliability of miRNA-disease association prediction under incomplete or perturbed graphs. This work enhances the reliability of computational miRNA-disease association analysis, facilitating more effective biomarker discovery and therapeutic target prioritization in precision medicine.
Related
- Relation-Aware Heterogeneous Graph Learning for miRNA–Drug Response Association Prediction Under Cold-Start Generalization
- Bone morphogenetic protein 4 meets artificial intelligence: a comprehensive review of AI-driven advances in drug discovery, structural modeling, and clinical translation
- Deep learning-based genetic disease prediction with Monte Carlo (MC) dropout uncertainty estimation: a comparative study with classical machine learning baselines
- Extracellular Vesicles in Molecular Crosstalk and Disease Pathogenesis: A Comprehensive Review on Mechanisms and Therapeutic Prospects
- An integrative multi-omics modeling framework for chemotherapy response prediction through microRNA–target regulatory signatures
BibTeX
@article{li2026robust,
title = {{Robust and comprehensive meta-path modeling with multi-graph learning for miRNA-disease association prediction.}},
author = {Zhi Li and Liqun Yang and Wei Qin and Jiahui Liang and Qiao Zhao},
journal = {Briefings in bioinformatics},
year = {2026},
month = sep,
doi = {10.1093/bib/bbag580},
url = {https://europepmc.org/article/MED/42932846},
note = {CC BY-NC},
}
RIS
TY - JOUR
TI - Robust and comprehensive meta-path modeling with multi-graph learning for miRNA-disease association prediction.
AU - Zhi Li
AU - Liqun Yang
AU - Wei Qin
AU - Jiahui Liang
AU - Qiao Zhao
PY - 2026
DA - 2026/09/01
JO - Briefings in bioinformatics
DO - 10.1093/bib/bbag580
UR - https://europepmc.org/article/MED/42932846
AB - MicroRNA (miRNA)-disease association prediction is important for biomarker discovery and therapeutic target prioritization. However, existing methods have not adequately captured heterogeneous biological semantics while maintaining robustness under incomplete or perturbed graphs. Therefore, this study aims to develop a robust graph-learning framework that more effectively captures heterogeneous biological semantics. We propose the Semantic Hierarchical Integration for miRNA-Disease Association prediction (SHiMDA) on contextual heterogeneous biomedical graphs. SHiMDA constructs independent views for direct associations and biologically meaningful meta-paths, and performs segment-wise message passing to explicitly encode the internal structure of meta-path instances rather than collapsing each path into a coarse source-target shortcut. A confidence-weighted ranking loss and over-smoothing regularization further reduce supervision bias and representation homogenization under graph perturbations. Extensive experiments on benchmark datasets show that SHiMDA achieves strong predictive performance in basic and contextual settings and consistently outperforms representative state-of-the-art baselines under adversarial edge and feature perturbations. By explicitly modeling segment-wise meta-path semantics and introducing robustness-oriented optimization, SHiMDA improves the reliability of miRNA-disease association prediction under incomplete or perturbed graphs. This work enhances the reliability of computational miRNA-disease association analysis, facilitating more effective biomarker discovery and therapeutic target prioritization in precision medicine.
SN - 1467-5463
SN - 1477-4054
ER -