TSMDA: Target and symptom-based computational model for miRNA-disease-association prediction

Area of Science:

• Bioinformatics
• Computational Biology
• Genomics

Background:

• High-throughput sequencing highlights microRNAs (miRNAs) in diseases like cancer.
• Understanding miRNA-disease links is crucial for pathogenesis insights, diagnosis, and treatment.
• Current methods for identifying miRNA-disease associations are expensive and time-consuming.

Purpose of the Study:

• To develop a novel computational method for predicting miRNA-disease associations.
• To improve the efficiency and accuracy of identifying potential miRNA-disease links.
• To provide a user-friendly tool for researchers in the field.

Main Methods:

• Introduction of TSMDA, a machine learning model.
• Leveraging target and symptom information for prediction.
• Incorporating negative sample selection to enhance model training.

Main Results:

• TSMDA achieved high predictive performance with an AUC of 0.989 (5-fold CV) and 0.982 (blind test).
• The method successfully identified potential miRNA-disease associations in breast, prostate, and lung cancers.
• Demonstrated superior performance compared to existing computational methods.

Conclusions:

• TSMDA is a powerful and accurate tool for prioritizing miRNA-disease associations.
• The method facilitates the discovery of novel associations for experimental validation.
• A freely accessible web interface is available for community use.