Prediction of disease-linked miRNAs based on SODNMF-DM. (May 2023)

• Record Type: Journal Article
• Authors: Yang, Bingsheng; Li, Jian; Ji, Zhiwei; Ruan, Yaoping; Liu, Tongcun; Feng, Hailin
• Is Part Of: Biomedical signal processing and control. Volume 83(2023)
• Publication Date: 2023-05
• Subjects: miRNA -- Disease-miRNA relations -- Matrix factorisation -- Resemblance; Signal processing -- Periodicals; Biomedical engineering -- Periodicals; Signal Processing, Computer-Assisted -- Periodicals; Image Processing, Computer-Assisted -- Periodicals; Biomedical Engineering -- Periodicals; 610.28
• DOI: 10.1016/j.bspc.2023.104621
• Languages: English
• ISSNs: 1746-8094

Abstract

Abstract: Motivation: MicroRNAs (miRNAs) play a crucial role in the life processes of organisms and affect the occurrence of many complex human diseases. Discovering potential links between diseases and miRNAs can aid in the prevention, diagnosis, and therapy of complex human diseases. Description: Identifying diseases and miRNA associations through existing biological experiments is expensive, while scientific computing approaches can quickly and efficiently predict the potential links between diseases and miRNAs. We propose SODNMF-DM, a SODNMF based Disease-MiRNA matrix factorisation algorithm. Result: The SODNMF-DM model exhibited an AUC of 0.9051 and an AUPR of 0.4774, respectively. To directly verify the effectiveness of SODNMF-DM, we studied three common human cancers. The experimental results showed that 25 of the top 30 potential miRNAs predicted by our proposed SODNMF-DM model were confirmed by HMDDv3.0 database. Conclusion: SODNMF-DM outperformed four other approaches in AUC and AUPR. In addition, our proposed approach exhibited good performance in practical cases. The approach presented in this study is thus expected to complement the field of biological research. Highlights: We fully consider disease similarity and miRNA similarity from multiple perspectives. We use the alternating gradient descent method to ensure the stability of the solution. The SODNMF-DM model has low overall complexity, simple operation and easy replication.