MvKFN-MDA: Multi-view Kernel Fusion Network for miRNA-disease association prediction

Highlights：

• A novel multiple kernel fusion framework Multi-view Kernel Fusion Network (MvKFN) is first proposed to effectively fuse different views similarity kernels constructed from different data sources. Using MvKFNs, both different base similarity kernels for miRNA and different base similarity kernels for diseases are nonlinearly fused into two integrated similarity kernels, one for miRNA, another for disease. Then, miRNA and disease feature representations are extracted from the miRNA and disease integrated similarity kernels respectively. These features are then fed into a neural matrix completion framework which finally outputs the association prediction scores.

• We compare the proposed method with other state-of-the-art methods. The AUC results show that our method was significantly superior to existing methods. Furthermore, 49, 48, and 47 of the top 50 predicted miRNAs for three high-risk human diseases, namely, colon cancer, lymphoma, and kidney cancer, are verified respectively using experimental literature. Finally, 100% prediction accuracy is achieved when breast cancer is used as a case study to evaluate the ability of MvKFN-MDA for predicting a new disease without any known related miRNAs.

摘要

•Predicting the association between microRNA (miRNA) and disease plays an important role in identifying human disease-related miRNAs. As the identification of miRNA-disease associations via biological experiments is time-consuming and expensive, computational methods are currently used as effective complements to determine the potential associations between disease and miRNA.•A novel multiple kernel fusion framework Multi-view Kernel Fusion Network (MvKFN) is first proposed to effectively fuse different views similarity kernels constructed from different data sources. Using MvKFNs, both different base similarity kernels for miRNA and different base similarity kernels for diseases are nonlinearly fused into two integrated similarity kernels, one for miRNA, another for disease. Then, miRNA and disease feature representations are extracted from the miRNA and disease integrated similarity kernels respectively. These features are then fed into a neural matrix completion framework which finally outputs the association prediction scores.•We compare the proposed method with other state-of-the-art methods. The AUC results show that our method was significantly superior to existing methods. Furthermore, 49, 48, and 47 of the top 50 predicted miRNAs for three high-risk human diseases, namely, colon cancer, lymphoma, and kidney cancer, are verified respectively using experimental literature. Finally, 100% prediction accuracy is achieved when breast cancer is used as a case study to evaluate the ability of MvKFN-MDA for predicting a new disease without any known related miRNAs.