Abstract
microRNAs (miRNAs) mutation and maladjustment are related to the occurrence and development of human diseases. Studies on disease-associated miRNA have contributed to disease diagnosis and treatment. To address the problems, such as low prediction accuracy and failure to predict the relationship between new miRNAs and diseases and so on, we design a Laplacian score of graphs to calculate the global similarity of networks and propose a Global Similarity method based on a Two-tier Random Walk for the prediction of miRNA–disease association (GSTRW) to reveal the correlation between miRNAs and diseases. This method is a global approach that can simultaneously predict the correlation between all diseases and miRNAs in the absence of negative samples. Experimental results reveal that this method is better than existing approaches in terms of overall prediction accuracy and ability to predict orphan diseases and novel miRNAs. A case study on GSTRW for breast cancer and conlon cancer is also conducted, and the majority of miRNA–disease association can be verified by our experiment. This study indicates that this method is feasible and effective.
Highlights
Given that an increasing number of disease-associated miRNA databases have been established[22,23,24,25,26], computational methods can be effectively applied to predict the potential correlation between miRNA and diseases[27,28,29,30,31,32,33] Bioinformatics prediction methods of miRNA–disease association can be generally divided into two categories: one is based on machine learning, and the other one is based on biological networks
The prediction method of miRNA–disease association is discussed on the basis of these two categories
Xu et al.[37] established a disease-associated miRNA prediction method that integrates the expression spectrum of miRNA and mRNA associated with a disease exhibiting phenotypic similarity
Summary
In 2009, Jiang et al.[19] developed a hypergeometric distribution calculation model to predict miRNA– disease association They used the relationship between target genes to regulate miRNA and establish an miRNA similarity network. The functional similarity of miRNA, the phenotypic similarity of disease, the semantic similarity of disease and the unknown association between miRNAs and diseases are used to establish a similar network and to predict the potential miRNA–disease association by using the k neighbours and miRNA functional similarity With this method, only the information of the miRNA’s neighbour is considered in its ranking system, and a local similarity measure instead of a global measure is used. Chen et al.[43] further calculated the global network similarity by determining the Laplacian score of graphs and proposed an miRNA–disease association prediction method based on random walk, namely, NetGS. No negative samples are needed in this method, and it can be applied to predict isolated diseases and new miRNAs
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
