SPLHRNMTF: robust orthogonal non-negative matrix tri-factorization with self-paced learning and dual hypergraph regularization for predicting miRNA-disease associations

• Published in: BMC genomics Vol. 25; no. 1; pp. 885 - 20
• Main Authors: Ouyang, Dong, Miao, Rui, Zeng, Juan, Li, Xing, Ai, Ning, Wang, Panke, Hou, Jie, Zheng, Jinqiu
• Format: Journal Article
• Language: English
• Published: England BioMed Central Ltd 20.09.2024; BMC
• Subjects: Algorithms; Analysis; Case studies; China; Computational Biology - methods; Diseases; Functions, Orthogonal; Genetic aspects; Genetic Predisposition to Disease; Health aspects; Humans; Hypergraph regularization; L_{2,1}$$ L 2 , 1 norm; Lung Neoplasms - genetics; Machine Learning; Mathematical models; Matrices; Medical research; Medicine, Experimental; MicroRNA; MicroRNAs - genetics; MiRNA-disease associations; Non-negative matrix tri-factorization; Self-paced learning; China; MiRNA-disease associations; Self-paced learning; Hypergraph regularization; Non-negative matrix tri-factorization; norm
• ISSN: 1471-2164; 1471-2164
• DOI: 10.1186/s12864-024-10729-w

MicroRNAs (miRNAs) have been demonstrated to be closely related to human diseases. Studying the potential associations between miRNAs and diseases contributes to our understanding of disease pathogenic mechanisms. As traditional biological experiments are costly and time-consuming, computational models can be considered as effective complementary tools. In this study, we propose a novel model of robust orthogonal non-negative matrix tri-factorization (NMTF) with self-paced learning and dual hypergraph regularization, named SPLHRNMTF, to predict miRNA-disease associations. More specifically, SPLHRNMTF first uses a non-linear fusion method to obtain miRNA and disease comprehensive similarity. Subsequently, the improved miRNA-disease association matrix is reformulated based on weighted k-nearest neighbor profiles to correct false-negative associations. In addition, we utilize norm to replace Frobenius norm to calculate residual error, alleviating the impact of noise and outliers on prediction performance. Then, we integrate self-paced learning into NMTF to alleviate the model from falling into bad local optimal solutions by gradually including samples from easy to complex. Finally, hypergraph regularization is introduced to capture high-order complex relations from hypergraphs related to miRNAs and diseases. In 5-fold cross-validation five times experiments, SPLHRNMTF obtains higher average AUC values than other baseline models. Moreover, the case studies on breast neoplasms and lung neoplasms further demonstrate the accuracy of SPLHRNMTF. Meanwhile, the potential associations discovered are of biological significance.