Prediction of miRNA-mRNA-Disease Association Using Network Consistency Projection

Extensive studies have demonstrated the role of microRNAs (miRNAs) in disease diagnosis, treatment, and prognosis, making it crucial to uncover their associations with various diseases. Traditional biological experimental methods for this exploration can be both costly and inefficient. In contrast, computer-based algorithms offer a promising <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">a</sup>lternati<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">ve</sup> for swiftly predicting miRNA-disease associations. While several approaches have been developed, they typically concentrate on the direct links between miRNAs and diseases. Therefore, there is a need for a new method that incorporates broader information to enhance predictive accuracy. In this research, we introduce a novel approach, termed PMMDA-NCP, designed for predicting miRNA-disease associations. This method employs the network consistency projection algorithm and leverages interactions among mRNAs, miRNAs, and diseases to enhance prediction accuracy. To evaluate the efficacy of our method, we conducted a 5-fold cross-validation, revealing that PMMDA-NCP achieved an average area under the receiver operating characteristic curve (AUC) exceeding 0.92, indicating robust performance.