Using Network Distance Analysis to Predict lncRNA-miRNA Interactions.

Area of Science:

• Genomics
• Bioinformatics
• Computational Biology

Background:

• Long non-coding RNA-microRNA (lncRNA-miRNA) interactions are crucial in human disease regulation.
• Experimental identification of these interactions is challenging and costly.
• Existing computational methods for predicting lncRNA-miRNA associations have limitations.

Purpose of the Study:

• To develop and validate a novel computational model, Network Distance Analysis Model for lncRNA-miRNA Association prediction (NDALMA), for large-scale prediction of lncRNA-miRNA interactions.
• To improve the accuracy and efficiency of identifying regulatory relationships between lncRNAs and miRNAs.

Main Methods:

• Constructed similarity networks for lncRNAs and miRNAs.
• Integrated Gaussian interaction profile (GIP) kernel similarity.
• Applied network distance analysis to integrated networks.
• Calculated confidence scores and converted them for final prediction.

Main Results:

• NDALMA achieved high performance in fivefold cross-validation with an Area Under the Curve (AUC) of 0.8810 and an Area Under the Precision-Recall Curve (AUPR) of 0.8315.
• The model demonstrated superior prediction performance compared to other network algorithms.
• Case studies confirmed the reliability of NDALMA in predicting biologically relevant lncRNA-miRNA associations.

Conclusions:

• NDALMA is a reliable and effective computational tool for predicting lncRNA-miRNA associations.
• The model offers a flexible and scalable approach for identifying potential biomarkers and therapeutic targets in human diseases.
• The developed datasets and source code are publicly available for further research.