Abstract
In recent years, more and more evidence has shown that microRNAs (miRNAs) play an important role in the regulation of post-transcriptional gene expression, and are closely related to human diseases. Many studies have also revealed that miRNAs can be served as promising biomarkers for the potential diagnosis and treatment of human diseases. The interactions between miRNA and human disease have rarely been demonstrated, and the underlying mechanism of miRNA is not clear. Therefore, computational approaches has attracted the attention of researchers, which can not only save time and money, but also improve the efficiency and accuracy of biological experiments. In this work, we proposed a Heterogeneous Graph Attention Networks (GAT) based method for miRNA-disease associations prediction, named HGATMDA. We constructed a heterogeneous graph for miRNAs and diseases, introduced weighted DeepWalk and GAT methods to extract features of miRNAs and diseases from the graph. Moreover, a fully-connected neural networks is used to predict correlation scores between miRNA-disease pairs. Experimental results under five-fold cross validation (five-fold CV) showed that HGATMDA achieved better prediction performance than other state-of-the-art methods. In addition, we performed three case studies on breast neoplasms, lung neoplasms and kidney neoplasms. The results showed that for the three diseases mentioned above, 50 out of top 50 candidates were confirmed by the validation datasets. Therefore, HGATMDA is suitable as an effective tool to identity potential diseases-related miRNAs.
Highlights
MicoRNAs are a class of endogenous non-coding RNAs with a length of about 21–25 nucleotides, which play an important role in the regulation of post-transcriptional gene expression in organisms (Ambros, 2001, 2004; Bartel, 2004, 2018)
The results showed that HGATMDA achieved the best area under receiver operating characteristic curve (ROC) curve (AUC) of 94.54 ± 0.34%, the area under P-R curve (AUPR) of 94.05 ± 0.18%, Accuracy of 87.02%, Precision of 94.07%, Recall of 90.04%, F1-score of 87.39%
Computational methods of predicting the disease-related miRNAs can accelerate the identification process, and help us understand the potential mechanism of the interactions between miRNAs and diseases
Summary
MicoRNAs (miRNAs) are a class of endogenous non-coding RNAs with a length of about 21–25 nucleotides, which play an important role in the regulation of post-transcriptional gene expression in organisms (Ambros, 2001, 2004; Bartel, 2004, 2018). Many computational methods have been proposed for predicting the miRNA-disease associations, which can be roughly divided into two categories: one is based on similarity networks, the other is based on machine learning. You et al (2017) have constructed a heterogeneous network, proposed a novel path based method named PBMDA for inferring the disease-related miRNAs. Since various network based approaches have been proposed (Chen et al, 2016, 2018c; Pan et al, 2019; Yu et al, 2019). You et al (2017) have constructed a heterogeneous network, proposed a novel path based method named PBMDA for inferring the disease-related miRNAs This method only uses subgraph information for prediction, which can be improved by considering the global information in the heterogeneous graph. Many methods based on random walk were proposed to improve the prediction performance
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
