Prediction of lncRNA-Disease Associations Based on Kernel Matrix Factorization Embedding

Long non-coding RNAs play pivotal roles in many complex human diseases, so it is important to explore the associations between lncRNAs and diseases. In this paper, we propose a new method for predicting lncRNA-disease associations based on kernel matrix factorization embedding and matrix completion (KMFELDA). Based on the known associations, topological similarity is computed by the method of kernel matrix factorization embedding, which is then fused with the functional similarity of lncRNAs and the semantic similarity of diseases. Finally, the constraints including the neighborhood graph incorporation and restricting predicted scores are simultaneously considered by introducing one-bit matrix completion.The 5-fold cross-validation method was utilized to evaluate the performance of our model.