PREDICTING MICRORNA-DISEASE ASSOCIATIONS USING HETEROGENEOUS GRAPH REPRESENTATION LEARNING

DOI: 10.18173/2354-1059.2023-0026

Tóm tắt

MicroRNAs (miRNAs) are small non-coding RNAs that play a crucial role in regulating gene expression post-transcriptionally. These molecules have been implicated in various diseases, including cancer, viral infections, cardiovascular disorders, and neurodegenerative conditions. This study introduces a novel approach for predicting miRNA-disease associations by leveraging heterogeneous graph representation learning. By integrating both structural and semantic information from the heterogeneous graph, our method offers an enhanced prediction process for discerning the relationship between miRNAs and diseases. Our experimental findings demonstrate the effectiveness of our prediction method, yielding promising results with an average AUC value of 0.907.