WBNPMD

WBNPMD (Weighted Bipartite Network Projection for miRNA-Disease Association Prediction) is a computational framework to predict potential associations between microRNAs (miRNAs) and diseases. Traditional experimental methods for detecting these associations are expensive and time-consuming, so computational techniques like WBNPMD are essential for identifying undiscovered interactions.

The method works by constructing transfer weights using known miRNA and disease similarities and configuring the initial information. It then applies a two-step bipartite network algorithm to infer potential miRNA-disease associations.

To evaluate the performance of WBNPMD, the authors applied it to known miRNA-disease association data and conducted leave-one-out cross-validation (LOOCV) and fivefold cross-validation. The results showed that WBNPMD achieved high AUC values (0.9321 and [Formula: see text]) and outperformed four other state-of-the-art methods.

The authors also conducted case studies on prostate, colorectal, and lung neoplasms. Based on various databases (dbDeMC, miR2Disease, and HMDD V3.0), most of the top 50 predicted miRNAs were confirmed to be associated with the corresponding diseases.