MicroRNA-disease association detection software tools | Non-coding RNA data analysis
In the recent few years, an increasing number of studies have shown that microRNAs (miRNAs) play critical roles in many fundamental and important biological processes. As one of pathogenetic factors, the molecular mechanisms underlying human complex diseases still have not been completely understood from the perspective of miRNA. Predicting potential miRNA-disease associations makes important contributions to understanding the pathogenesis of diseases, developing new drugs, and formulating individualized diagnosis and treatment for diverse human complex diseases.
Allows users to predict the microRNA-disease associations thanks to a combinatorial prioritization algorithm. M2DMiners contains six inference methods which aim to infer the novel associations between microRNAs and diseases by modifying the existing maximizing information flow method. It also can be used to detect novel microRNAs for diseases without the known related microRNAs.
Allows users to predict potential miRNA disease associations. SPM integrates the verified miRNA-associated diseases with the disease and miRNA similarity networks. It allows selection of part of links from the bilayer network to form a perturbation set and uses the perturbation set to agitate the remaining links by first-order approximation. Then, it assists in computing the perturbed adjacency matrix.
Predicts novel miRNAs for diseases which do not have any known related miRNAs. RLSMDA is able to reconstruct the missing associations for all the diseases simultaneously. It integrates disease-disease semantic similarity information, miRNA-miRNA functional similarity information, and known human miRNA-disease associations on a large scale. This tool can obtain negative disease-miRNA associations samples in practical problems.
Constructs a heterogeneous graph consisting of three interlinked sub-graphs and further adopted depth-first search algorithm to infer potential miRNA-disease associations. PBMDA is a prediction model that could serve as a powerful computational tool to accelerate the identification of disease-miRNA associations. Integrating different types of heterogeneous biological datasets allows that PBMDA could be applied to the new diseases with no known associated miRNAs and the new miRNAs with no known associated diseases.
Infers potential miRNA–disease associations. RWRMDA implements random walk on the miRNA functional similarity network to prioritize candidate miRNAs for disease of interest. It is composed of three steps: (1) decide the initial probability of each miRNA, (2) implement random walk on the MFSN, and (3) obtain stable probability of random walk and rank candidate miRNAs. This tool shows a high performance of prediction.
An approach in which miRNAs are linked to diseases via proteins, thereby directly providing biological hypotheses. Specifically, we infer miRNA–disease associations by network analysis of known or predicted miRNA–protein associations and text-mined protein–disease associations. To account for the variable reliability of both types of associations, we provide a scoring scheme that allows for ranking of the inferences by confidence.
Predicts potential microRNA (miRNA) candidates for the diseases with known related miRNAs. MIDP can assist users in relieving the negative effect of noisy data. To perform, it exploits the characteristics of the nodes and the various ranges of topologies. Moreover, this tool also contains features to determine candidates specially for the diseases without any known related miRNAs.