Uncover miRNA-Disease Association by Exploiting Global Network Similarity

Abstract

Identification of miRNA-disease association is a fundamental challenge in human health clinic. However, the known miRNA-disease associations are rare and experimental verification methods are expensive and time-consuming. Therefore, there is a strong incentive to develop computational methods. In this paper, we calculate the similarity score for each miRNAs pair by integrating miRNA functional similarity and miRNA family information. We use the disease phenotype similarity data to construct the disease similarity network. Then we introduce a new miRNA-disease association prediction method (NETwork Group Similarity, NetGS) to explore the global network similarity, capturing the relationship between the disease and other diseases, the similarity between the potential disease-related miRNA and other miRNAs. Finally based on the consistency of diffusion profiles we get the miRNA-disease association scores. NetGS is tested by the leave-one-out cross validation and achieves an AUC value of 0.8450, which improves the prediction accuracy. NetGS can also be applied to solve the new miRNA-disease association and obtain reliable accuracy. Moreover, we use NetGS to predict new causing miRNAs of three cancers including breast cancer, lung cancer and Hepatocellular cancer. And the top predictions have been confirmed in the online databases. The encouraging results indicate that NetGS might play an essential role for future scientific research.

A novel information diffusion method based on network consistency for identifying disease related microRNAs

“…27 The data set is successfully applied to multiple methods. 80,[93][94][95] We use matrix SM to represent the adjacency matrix of miRNA, and SM(i, j) is the score of functional similarity score between miRNA i and miRNA j.…”

LDAI-ISPS: LncRNA–Disease Associations Inference Based on Integrated Space Projection Scores

“…However, the prediction results may be affected by the quality of the dataset as well as those lncRNAs with low expression level. Numerous researchers introduced random walk into the prediction of lncRNA-disease associations [44][45][46][47][48][49][50][51][52][53][54]. Sun et al [55] executed random walk with restart (RWR) on lncRNA functional similarity network to infer lncRNA-disease associations.…”

LSGSP: a novel miRNA–disease association prediction model using a Laplacian score of the graphs and space projection federated method

“…Shi et al 27 further integrated miRNA-gene relationships and random walks to predict miRNA-disease associations. Liao et al 28 proposed a new prediction method for disease-related miRNAs using the Laplacian score of the graphs and a random walk method. Chen et al 29 also proposed a new computational method named WBSMDA to uncover potential miRNAs related to multiple complex diseases through integrating known miRNA-disease association, semantic disease similarity, miRNA functional similarity, Gauss's nuclear spectrum of disease and miRNA to obtain nal relevance scores for uncon-rmed miRNA-disease associations.…”