GIMDA: Graphlet interaction-based MiRNA-disease association prediction

Abstract

MicroRNAs (miRNAs) have been confirmed to be closely related to various human complex diseases by many experimental studies. It is necessary and valuable to develop powerful and effective computational models to predict potential associations between miRNAs and diseases. In this work, we presented a prediction model of Graphlet Interaction for MiRNA-Disease Association prediction (GIMDA) by integrating the disease semantic similarity, miRNA functional similarity, Gaussian interaction profile kernel similarity and the experimentally confirmed miRNA-disease associations. The related score of a miRNA to a disease was calculated by measuring the graphlet interactions between two miRNAs or two diseases. The novelty of GIMDA lies in that we used graphlet interaction to analyse the complex relationships between two nodes in a graph. The AUCs of GIMDA in global and local leave-one-out cross-validation (LOOCV) turned out to be 0.9006 and 0.8455, respectively. The average result of five-fold cross-validation reached to 0.8927 ± 0.0012. In case study for colon neoplasms, kidney neoplasms and prostate neoplasms based on the database of HMDD V2.0, 45, 45, 41 of the top 50 potential miRNAs predicted by GIMDA were validated by dbDEMC and miR2Disease. Additionally, in the case study of new diseases without any known associated miRNAs and the case study of predicting potential miRNA-disease associations using HMDD V1.0, there were also high percentages of top 50 miRNAs verified by the experimental literatures.

Keywords: disease; graphlet interaction; miRNA; miRNA-disease association.

Figure 1

Graphlet types labelled by G ₀ to G ₈ and automorphism orbits labelled by 0 to 14 (A); Graphlet interaction isomers labelled by I ₁ to I ₂₈ (B). As shown in (A), different colours denote different types of orbits in the same graphlet. In (B), graphlet interaction is from the blue node to the green one in each isomer.

Figure 2

Flow chart of GIMDA model to predict the potential miRNA‐disease associations.

Figure 3

Performance of GIMDA was compared with HGIMDA, RLSMDA, HDMP, WBSMDA and MCMDA in terms of ROC curve and AUC of global leave‐one‐out cross‐validation (LOOCV) (left) and local LOOCV (right). As is shown, GIMDA achieves AUCs of 0.9006 and 0.8455 in the global and local LOOCV, significantly superior to previous models.