Leveraging explainable multi-scale features for fine-grained circRNA-miRNA interaction prediction
We utilize a manifold-based method to examine model performance in detail, revealing that MFERL exhibits robust generalization, robustness, and interpretability. Extensive experiments show that MFERL outperforms state-of-the-art models and offers a promising direction for understanding CMI intrinsic mechanisms.
Authors
- Xiangzheng Fu (ORCID: https://orcid.org/0000-0001-6840-2573)
- Dongsheng Cao (ORCID: https://orcid.org/0000-0003-3604-3785)
- Zhiyuan Yang (ORCID: https://orcid.org/0000-0003-2013-2281)
- Li Peng (ORCID: https://orcid.org/0000-0001-5358-6736)
- Wang Wang (ORCID: https://orcid.org/0000-0002-1637-677X)
- Wei Liang (ORCID: https://orcid.org/0009-0005-8905-6127)
Institutions
- Hunan University of Science and Technology (CN)
- Central South University (CN)
Publication Details
- Journal
- BMC Biology
- Published
- 2025-05-09
- DOI
- https://doi.org/10.1186/s12915-025-02227-6
- Citations
- 1
- Primary Topic
- Cancer-related molecular mechanisms research
- Type
- article
- Field-Weighted Citation Impact
- 0.94
Funders
- National Natural Science Foundation of China