HGIMDA: Heterogeneous graph inference for miRNA-disease association prediction

Abstract

Recently, microRNAs (miRNAs) have drawn more and more attentions because accumulating experimental studies have indicated miRNA could play critical roles in multiple biological processes as well as the development and progression of human complex diseases. Using the huge number of known heterogeneous biological datasets to predict potential associations between miRNAs and diseases is an important topic in the field of biology, medicine, and bioinformatics. In this study, considering the limitations in the previous computational methods, we developed the computational model of Heterogeneous Graph Inference for MiRNA-Disease Association prediction (HGIMDA) to uncover potential miRNA-disease associations by integrating miRNA functional similarity, disease semantic similarity, Gaussian interaction profile kernel similarity, and experimentally verified miRNA-disease associations into a heterogeneous graph. HGIMDA obtained AUCs of 0.8781 and 0.8077 based on global and local leave-one-out cross validation, respectively. Furthermore, HGIMDA was applied to three important human cancers for performance evaluation. As a result, 90% (Colon Neoplasms), 88% (Esophageal Neoplasms) and 88% (Kidney Neoplasms) of top 50 predicted miRNAs are confirmed by recent experiment reports. Furthermore, HGIMDA could be effectively applied to new diseases and new miRNAs without any known associations, which overcome the important limitations of many previous computational models.

GLNMDA: a novel method for miRNA-disease association prediction based on global linear neighborhoods

“…HGIMDA[17], EGBMMDA[33], PBMDA[21], MKRMD[29]), all of which have also achieved excellent performances in predicting potential miRNA-disease associations. As mentioned above, HGIMDA was an efficient prediction framework based on heterogeneous graph inference.…”

“…Nevertheless, HDMP cannot be applied to diseases without any known related miRNAs since it is based on local similarity measures. To solve this issue, Chen et al developed a novel computational approach called HGIMDA which integrates miRNA functional similarity, disease semantic similarity, kernel similarity of Gaussian interaction profile, and experimentally validated miRNA-disease associations to predict potential miRNA-disease associations[17]. They further constructed a heterogeneous graph to iteratively update the association scores between unconfirmed miRNAs and diseases.…”

SNMDA: A novel method for predicting microRNA‐disease associations based on sparse neighbourhood

“…To demonstrate the effectiveness of our method, we applied global LOOCV, local LOOCV and 5‐fold cross‐validation to evaluate the performance of our method, respectively. The corresponding AUCs are 0.936, 0.882 and 0.934, which in all cases outperform the four state‐of‐the‐art methods (HGIMDA,23 PBMDA,26 EGBMMDA 34 and MKRMDA33). Moreover, three types of case studies on five common neoplasms further validated the effectiveness of our method.…”

“…Specifically, WBSMDA calculated a within‐score and a between score, and combined them together to obtain a final score for miRNA‐disease associations prediction. Using the same data, they further proposed another method named HGIMDA 23. They first constructed a heterogeneous graph, and then implemented an iterative process on the graph to discover the relationships between miRNAs and diseases.…”

NDAMDA: Network distance analysis for MiRNA‐disease association prediction

“…But the room for improvement was how to choose the best parameters. Similar to the process of random work, Chen et al25 presented another iterative model named HGIMDA to find the optimal solutions based on global network similarity information. A heterogeneous graph was constructed from various disease similarity measures, diverse miRNA similarity measures and the known miRNA‐disease associations.…”