ncPred: ncRNA-Disease Association Prediction through Tripartite Network-Based Inference

Abstract

Motivation: Over the past few years, experimental evidence has highlighted the role of microRNAs to human diseases. miRNAs are critical for the regulation of cellular processes, and, therefore, their aberration can be among the triggering causes of pathological phenomena. They are just one member of the large class of non-coding RNAs, which include transcribed ultra-conserved regions (T-UCRs), small nucleolar RNAs (snoRNAs), PIWI-interacting RNAs (piRNAs), large intergenic non-coding RNAs (lincRNAs) and, the heterogeneous group of long non-coding RNAs (lncRNAs). Their associations with diseases are few in number, and their reliability is questionable. In literature, there is only one recent method proposed by Yang et al. (2014) to predict lncRNA-disease associations. This technique, however, lacks in prediction quality. All these elements entail the need to investigate new bioinformatics tools for the prediction of high quality ncRNA-disease associations. Here, we propose a method called ncPred for the inference of novel ncRNA-disease association based on recommendation technique. We represent our knowledge through a tripartite network, whose nodes are ncRNAs, targets, or diseases. Interactions in such a network associate each ncRNA with a disease through its targets. Our algorithm, starting from such a network, computes weights between each ncRNA-disease pair using a multi-level resource transfer technique that at each step takes into account the resource transferred in the previous one.

Results: The results of our experimental analysis show that our approach is able to predict more biologically significant associations with respect to those obtained by Yang et al. (2014), yielding an improvement in terms of the average area under the ROC curve (AUC). These results prove the ability of our approach to predict biologically significant associations, which could lead to a better understanding of the molecular processes involved in complex diseases.

Availability: All the ncPred predictions together with the datasets used for the analysis are available at the following url: http://alpha.dmi.unict.it/ncPred/

Keywords: lncRNAs functional characterization; ncRNAs-diseases association predictions; network-based inference; resource transfer algorithm; tripartite networks.

Figure 1

Operating principle of ncPred in a tripartite network. Here, we represent ncRNAs in blue, targets in orange, and diseases in red. Without loss of generality, and in order to simplify the reading of the image, we decided to put λ₁ and λ₂ to 1, so as to obtain a uniform distribution of resources in the network. In the first step, a resource is assigned to each target and disease node (1). Thereafter, two separate transfer process are launched to compute the resource in target nodes (2a, 2b) and disease nodes (3a, 3b). Finally, resources are combined to obtain the total quantity in each disease node (4). In (4), the literals are used only for example purposes due to lack of space. They are to be replaced with the values computed in steps (2b) and (3b).

Figure 2

Degree distribution of the two networks used as datasets: (A) Chen et al. (2013), (B) Helwak et al. (2013). The two plots are in log-log scale. As can be seen the degree distribution for the two networks can be approximated to an exponential one. We can therefore assume that the two networks are scale-free.

Figure 3

Comparison between ncPred and Yang et al. (2014) by means of receiver operating characteristic (ROC) curves, computed for the recommendation lists built on our two datasets. Such curves measure the quality of the algorithms in terms of false positives rate against true positives rate. (A,B) are independent since computed on two separate datasets. The significance of the difference highlighted between ncPred and Yang et al. (2014) was measured by applying the Friedman rank sum test as assessed in Table 4.