Multi-hop graph structural modeling for cancer-related circRNA-miRNA interaction prediction

A substantial body of research indicates that circRNA can act as a sponge to absorb miRNA, thereby regulating the development of cancers. Existing circRNA-miRNA interactions (CMIs) prediction models mainly focus on single features and local structures of molecules, making it difficult to fully describe the overall properties of molecules and overlooking the multi-hierarchical associations between them. To address these challenges, we propose a computational model named GraCMI based on multi-hop graph structural modeling, which predicts CMIs by integrating structural and attribute information of molecules. GraCMI learns the representation of molecules in multi-level neighborhoods through constructing heterogeneous networks and performing high- and low-order matrix factorization. GraCMI captures both the intrinsic properties and global structures of molecules, extracting and fusing multi-source features, improving prediction accuracy. In the case studies, 7 out of the top 10 CMI pairs predicted using GraCMI on a real cancer-related dataset were confirmed. Additionally, GraCMI demonstrates a competitive advantage on two other classic datasets. Overall, the experimental results show that GraCMI can effectively predict CMIs, which is expected to provide new insights into future miRNA-mediated circRNA regulation of cancer development.