Interpretable multi-instance heterogeneous graph network learning modelling CircRNA-drug sensitivity association prediction
MiGNN2CDS achieves better prediction accuracy than many state-of-the-art models do. Case studies show that MiGNN2CDS can effectively predict unknown associations, and the model interpretability of MiGNN2CDS is verified by high-confidence meta-path analysis. The code and data are available at https://github.com/nmt315320/MiGNN2CDS.git .
Authors
- Quan Zou (ORCID: https://orcid.org/0000-0001-6406-1142)
- Ximei Luo
- Mengting Niu (ORCID: https://orcid.org/0000-0001-9175-4649)
- Yaojia Chen (ORCID: https://orcid.org/0000-0003-0204-2725)
- Chunyu Wang (ORCID: https://orcid.org/0000-0002-2965-9920)
Institutions
- University of Electronic Science and Technology of China (CN)
- Shenzhen Polytechnic University (CN)
- Harbin Institute of Technology (CN)
- Wenzhou Medical University (CN)
- Australian Regenerative Medicine Institute (AU)
- First Affiliated Hospital of Wenzhou Medical University (CN)
- Macao Polytechnic University (MO)
- Monash University (AU)
Publication Details
- Journal
- BMC Biology
- Published
- 2025-05-14
- DOI
- https://doi.org/10.1186/s12915-025-02223-w
- Citations
- 6
- Primary Topic
- Circular RNAs in diseases
- Type
- article
- Field-Weighted Citation Impact
- 4.84
Funders
- National Natural Science Foundation of China