Predict MiRNA-Disease Associations Using a Variant of Deep Forest Model and Improving Feature Vectors by Graph Convolutional Network

Abstract

MicroRNAs (miRNAs) play a significant role in biological processes, serving as potential biomarkers and therapeutic targets for disease diagnosis and treatment. However, traditional experimental methods for identifying miRNA-disease associations (MDAs) are costly and time-consuming. These challenges prompt a critical need for computational approaches. This study proposes GCNDFMDA, a method that employs a variant of the deep forest model for MDAs prediction. Unlike simple multi-source integration, GCNDFMDA first captures the interactive features of miRNAs and diseases by extracting diverse information sources for comprehensive representation. Next, it utilizes graph convolutional networks, followed by neural projection, to derive latent representations from similarity networks, thereby reducing dimensionality and obtaining an optimal feature space. It then calculates integrated similarities for miRNAs and diseases and constructs feature vectors. Finally, it employs a variant of the deep forest model to obtain the final prediction. Experimental results on three datasets (HMDD v2.0, HMDD v3.2, and an independent dataset), along with de novo validation, highlight the superior performance of GCNDFMDA compared to seven compared methods. In addition, case studies confirm its reliability, with all the top 50 predicted miRNAs related to these diseases verified in real applications. The source code of GCNDFMDA is available at https://github.com/npxquynhdhsp/GCNDFMDA/.