Lorem ipsum dolor sit amet, consectetur adipiscing elit.
This web server provides a method to predict potential interaction between microRNA and disease for further biological experiments. First, we collect latest data and recalculate two similarity network: miRNA similarity network and disease similarity network, using disease information and miRNA information, respectively. Secondly, a heterogeneous network is constructed by connecting the disease similarity subnetwork and the microRNA similarity subnetwork using the experimentally verified microRNA–disease associations. We extend the framework of KATZ to predict microRNA–disease associations in the heterogeneous network.
Here are three kinds of databases: information about disease-miRNA associations, information about miRNA similarity measure, information about disease similarity measure. All Databases are availiable.
# | Data Name | Data Description | Linkage |
---|---|---|---|
1 | HMDD V2.0 | human microRNA-disease database | http://www.cuilab.cn/hmdd |
2 | miR2Disease | human microRNA-disease database | http://www.mir2disease.org/ |
3 | miRTarBase | experimentally validated microRNA-target gene interactions | http://mirtarbase.mbc.nctu.edu.tw/ |
4 | miRBase | microRNA biological information | http://www.mirbase.org/ |
5 | MeSH | Medical Subject Headings | http://www.ncbi.nlm.nih.gov/mesh |
6 | DisGeNET | a database of gene-disease associations | http://www.disgenet.org/ |
Here are part of results using methods we proposed. More details can be found in our paper.
Average area under the curve (AUC) by threefold-cross-validation for all diseases.Katz-SW and Katz-ML present better performance with AUC values of 0.8184 and 0.8681, respectively, for all diseases
Average recall rates across all diseases at different cutoffs by threefold cross –validations.Katz-SW and Katz-ML obtain approximately 68% and 84% recall rates in the top 100 candidates.