A new approach to human microRNA target prediction using ensemble pruning and rotation forest

Area of Science:

• Bioinformatics
• Computational Biology
• Genomics

Background:

• MicroRNAs (miRNAs) are key regulators of gene expression.
• Experimental identification of miRNA targets is time-consuming and expensive.
• Machine learning offers a promising avenue for efficient miRNA target prediction.

Purpose of the Study:

• To develop and evaluate a novel ensemble machine learning approach for human miRNA target prediction.
• To enhance the accuracy and efficiency of identifying miRNA-gene interactions.
• To compare the proposed method against existing techniques.

Main Methods:

• Proposed a novel Ensemble Pruning and Rotation Forest (EP-RTF) method.
• Utilized Genetic Algorithm (GA) for selecting optimal classifier subsets and optimizing Rotation Forest (RTF) parameters.
• Combined selected classifiers using weighted majority voting.

Main Results:

• EP-RTF demonstrated superior performance in classification accuracy, sensitivity, and specificity across four human miRNA target datasets.
• Diversity-error analysis indicated that EP-RTF generates more accurate and diverse individual classifiers compared to other ensemble methods.
• The proposed method significantly outperforms previously applied techniques.

Conclusions:

• EP-RTF is a highly effective and recommended approach for improving human miRNA target prediction.
• The integration of GA with ensemble strategies enhances predictive model performance.
• This method offers a more efficient and accurate alternative to experimental approaches.