MCCMF: Collaborative matrix factorization based on matrix completion for predicting miRNA-disease associations

Abstract

Background: MicroRNAs (MiRNAs) are non-coding RNAs with regulatory functions. Many studies have shown that miRNAs are closely associated with human diseases. Among the methods to explore the relationship between the miRNA and the disease, traditional methods are time-consuming and the accuracy needs to be improved. In view of the shortcoming of previous models, a collaborative matrix factorization based on matrix completion (MCCMF) is proposed to predict the unknown miRNA-disease associations.Results: The complete matrix of the miRNA and the disease is obtained by matrix completion. Moreover, Gaussian Interaction Profile (GIP) kernel is added to the miRNA functional similarity matrix and the disease semantic similarity matrix to form the GIP kernel similarity matrix. Then the Weight K Nearest Known Neighbors (WKNKN) method is used to pretreat the association matrix, so the model is close to the reality. Finally, collaborative matrix factorization (CMF) method is applied to obtain the prediction results. Therefore, the MCCMF obtains a satisfactory result in the five-fold cross-validation, with an AUC of 0.9569(0.0005). Conclusions: The AUC value of MCCMF is higher than other advanced methods in the 5-fold cross validation experiment. In order to comprehensively evaluate the performance of MCCMF, f-measure and other evaluation indexes are also added. The final experimental results demonstrate that MCCMF outperforms other methods in prediction miRNA-disease associations. In the end, the effectiveness and practicability of MCCMF are further verified by researching three specific diseases.

Neural Collective Matrix Factorization for integrated analysis of heterogeneous biomedical data

“…Numerous methods have been designed to integrate additional information into MF-based techniques such as those based on Inductive Matrix Completion (Li et al, 2020(Li et al, , 2021, Graph-regularized Matrix Factorization (Zhang et al, 2020), and Collaborative Matrix Factorization (Wu et al, 2020). The typical setting in these methods comprises a central matrix containing known and unknown values of the association of interest (e.g., gene-disease or drug-target) and various ways of incorporating auxiliary data (as features or networks) of the entities of interest (genes and diseases, or drugs and targets) within the modeling framework used.…”

MEAHNE: MiRNA-disease association prediction based on semantic information in heterogeneous networks

“…This method builds the miRNA disease relationship into a matrix and decomposes the matrix. Wu et al [15] completes and optimizes the miRNA-disease adjacency matrix. They use the miRNA functional similarity matrix and the disease semantic similarity matrix and the KNN method to complete the miRNA-disease adjacency matrix.…”