A miRNA-Disease Association Prediction Method Integrating Graph Matrix Factorization With L$_{21}$ Similarity Constraint and Network Projection Fusion

Discovering miRNAs associated with diseases can contribute to understanding the pathogenesis and treatment strategies of diseases. In the commonly used graph regularized non-negative matrix factorization methods for miRNA-disease association prediction, there exist issues such as interference from low-dimensional matrix noise and loss of network topology information from partial original data. To solve these issues, we propose a method called L$_{21}$ S-NPFM, which combines L$_{21}$ similarity constrain graph matrix factorization and network projection fusion for miRNA-disease association prediction. First, we introduce a similarity constraint term based on the L$_{21}$-norm (L$_{21}$ SGMF) into matrix factorization, effectively suppressing noise in the low-dimensional matrix. Second, we design a network projection fusion method (NPFM) to integrate the consistency projection matrices of miRNA/disease networks and initial score matrices, compensating for the lost network topology information. Experimental results from LOOCV and 5-fold CV findings show that L$_{21}$ S-NPFM works better than six other mainstream methods. Additionally, case studies show its accuracies of up to 100% for 10 miRNAs associated with diabetic nephropathy (DN) and 80% for 10 miRNAs associated with thoracic aortic aneurysm (TAA), respectively.