Random walks on mutual microRNA-target gene interaction network improve the prediction of disease-associated microRNAs

Abstract

Background: MicroRNAs (miRNAs) have been shown to play an important role in pathological initiation, progression and maintenance. Because identification in the laboratory of disease-related miRNAs is not straightforward, numerous network-based methods have been developed to predict novel miRNAs in silico. Homogeneous networks (in which every node is a miRNA) based on the targets shared between miRNAs have been widely used to predict their role in disease phenotypes. Although such homogeneous networks can predict potential disease-associated miRNAs, they do not consider the roles of the target genes of the miRNAs. Here, we introduce a novel method based on a heterogeneous network that not only considers miRNAs but also the corresponding target genes in the network model.

Results: Instead of constructing homogeneous miRNA networks, we built heterogeneous miRNA networks consisting of both miRNAs and their target genes, using databases of known miRNA-target gene interactions. In addition, as recent studies demonstrated reciprocal regulatory relations between miRNAs and their target genes, we considered these heterogeneous miRNA networks to be undirected, assuming mutual miRNA-target interactions. Next, we introduced a novel method (RWRMTN) operating on these mutual heterogeneous miRNA networks to rank candidate disease-related miRNAs using a random walk with restart (RWR) based algorithm. Using both known disease-associated miRNAs and their target genes as seed nodes, the method can identify additional miRNAs involved in the disease phenotype. Experiments indicated that RWRMTN outperformed two existing state-of-the-art methods: RWRMDA, a network-based method that also uses a RWR on homogeneous (rather than heterogeneous) miRNA networks, and RLSMDA, a machine learning-based method. Interestingly, we could relate this performance gain to the emergence of "disease modules" in the heterogeneous miRNA networks used as input for the algorithm. Moreover, we could demonstrate that RWRMTN is stable, performing well when using both experimentally validated and predicted miRNA-target gene interaction data for network construction. Finally, using RWRMTN, we identified 76 novel miRNAs associated with 23 disease phenotypes which were present in a recent database of known disease-miRNA associations.

Conclusions: Summarizing, using random walks on mutual miRNA-target networks improves the prediction of novel disease-associated miRNAs because of the existence of "disease modules" in these networks.

Keywords: Disease-associated microRNAs; Network analysis; Random walk with restart; microRNA targets.

Fig. 1

Illustration of the RWRMTN and RWRMDA methods. a Heterogeneous miRNA networks/MiRNA-target networks were constructed using miRNA-target gene interactions. b Homogeneous miRNA networks/MiRNA functional similarity networks were constructed using target genes shared among miRNAs. c Two miRNAs known to be associated with a disease under study are mapped as source/seed nodes in a homogeneous miRNA network. In addition to these two known disease-associated miRNAs, their target genes are also used as source/seed nodes in a heterogeneous miRNA network. d Ranking methods score all nodes in the heterogeneous or homogeneous miRNA network

Fig. 2

Performance of RWRMTN as a function of the algorithm parameters, using mutual heterogeneous miRNA networks. Performance is an average of AUC values over a set of disease phenotypes collected from the miR2Disease database [45]. The restart probability γ was varied in the range [0.1, 0.9]. The weight parameter α) was set to values in {0.1, 0.3, 0.5, 0.7, 0.9}. Results are reported for (a) HetermiRWalkNet-mutual and (b) HeterTargetScanNet-mutual

Fig. 3

Performance comparison between RWRMTN and RWRMDA. The performance of each method on each heterogeneous/homogeneous miRNA network is calculated as the average AUC values over a set of disease phenotypes collected from the miR2Disease database [45]. The restart probability was varied from 0.1 to 0.9. The weight parameter was set to 0.1. a Comparison between RWRMTN (using HetermiRWalkNet-mutual) and RWRMDA (using HomomiRWalkNet). b Comparison between RWRMTN (using HeterTargetScanNet-mutual) and RWRMDA (using HomoTargetScanNet)

Fig. 4

Heterogeneous miRNA networks contain known disease genes and known disease miRNAs, regulating known disease genes. a Percent of known disease genes in HetermiRWalkNet-mutual. b Percent of known disease genes in HeterTargetScanNet-mutual. c Percent of known disease miRNAs regulating disease genes in HetermiRWalkNet-mutual. d Percent of known disease miRNAs regulating disease genes in HeterTargetScanNet-mutual. Known disease genes and known disease miRNAs were collected from the OMIM [47] and miR2Disease [45] databases, respectively

Fig. 5

Comparison between RWRMTN and RLSMDA. The set of disease phenotypes and their associated miRNAs were collected from the miR2Disease database [45]. a MiRNA networks were constructed using the miRWalk database. b MiRNA networks were constructed using TargetScan database. Weight parameter α and restart probability γ were set to the optimal settings (α = 0.9 and γ = 0.7) for RWRMTN. For RLSMDA, we used the parameter settings (η _M = η _D = 1 and w = 0.9) reported in the study [33]