Three-layer heterogeneous network based on the integration of CircRNA information for MiRNA-disease association...

Area of Science:

• Bioinformatics
• Computational Biology
• Genomics

Background:

• Abnormal microRNA (miRNA) expression is linked to complex diseases.
• Biological experiments face limitations in identifying disease-miRNA associations.
• Computational approaches are needed to enhance prediction accuracy.

Purpose of the Study:

• To develop a novel computational model, TLHNICMDA, for predicting disease-miRNA associations.
• To integrate circRNA information into a heterogeneous network for improved prediction.
• To overcome the limitations of experimental methods in identifying disease-miRNA links.

Main Methods:

• Constructed a three-layer heterogeneous network incorporating disease-miRNA associations, miRNA-circRNA interactions, and similarity data.
• Employed an update algorithm on the global network to identify potential disease-miRNA associations.
• Validated the model using global and local leave-one-out cross-validation (LOOCV) and 5-fold cross-validation.

Main Results:

• Achieved high Area Under the Curve (AUC) values of 0.8795 (global LOOCV) and 0.7774 (local LOOCV).
• Demonstrated a mean AUC of 0.8777 ± 0.0010 in 5-fold cross-validations.
• Case studies confirmed the model's utility in predicting disease-miRNA interactions.

Conclusions:

• TLHNICMDA effectively predicts disease-miRNA associations by integrating diverse biological data.
• The model offers a valuable computational tool for understanding disease mechanisms.
• This approach enhances the identification of potential therapeutic targets through miRNA-disease links.