Predicting lncRNA-miRNA Interaction via Graph Convolution Auto-Encoder

Abstract

The interaction of miRNA and lncRNA is known to be important for gene regulations. However, the number of known lncRNA-miRNA interactions is still very limited and there are limited computational tools available for predicting new ones. Considering that lncRNAs and miRNAs share internal patterns in the partnership between each other, the underlying lncRNA-miRNA interactions could be predicted by utilizing the known ones, which could be considered as a semi-supervised learning problem. It is shown that the attributes of lncRNA and miRNA have a close relationship with the interaction between each other. Effective use of side information could be helpful for improving the performance especially when the training samples are limited. In view of this, we proposed an end-to-end prediction model called GCLMI (Graph Convolution for novel lncRNA-miRNA Interactions) by combining the techniques of graph convolution and auto-encoder. Without any preprocessing process on the feature information, our method can incorporate raw data of node attributes with the topology of the interaction network. Based on a real dataset collected from a public database, the results of experiments conducted on k-fold cross validations illustrate the robustness and effectiveness of the prediction performance of the proposed prediction model. We prove the graph convolution layer as designed in the proposed model able to effectively integrate the input data by filtering the graph with node features. The proposed model is anticipated to yield highly potential lncRNA-miRNA interactions in the scenario that different types of numerical features describing lncRNA or miRNA are provided by users, serving as a useful computational tool.

Functional Interaction among lncRNA HOTAIR and MicroRNAs in Cancer and Other Human Diseases

“…This model analyzes the patterns in large-scale expression profiles of known lncRNA–miRNA interactions and it is based on the assumption that lncRNAs that are very similar to each other tend to have similar interaction or non-interaction patterns with miRNAs and vice versa [ 182 ]; (ii) the Graph Convolution for novel LncRNA-MiRNA Interactions (GCLMI), based on graph convolutional networks (GCNs), a powerful type of neural network designed to work directly on graphs and leverage their structural information. GCLMI is a network-based algorithm that considers known lncRNA–miRNA interactions along with lncRNA and miRNA expression levels, and aims to calculate the possibility that an lncRNA–miRNA pair is interactive in biological processes [ 183 ]; (iii) the Linear Neighbour Representation to predict LncRNA-MiRNA Interactions (LNRLMI) is based on the implementation of an lncRNA–miRNA network realized combining the known interaction network and similarities based on expression profiles of lncRNAs and miRNAs. To predict the new links of the known lncRNA–miRNA interaction network, a linear optimization, a semi-supervised model, has been added to this model [ 184 ].…”

Deep Learning in LncRNAome: Contribution, Challenges, and Perspectives

“…Huang et al proposed the first large-scale lncRNA–miRNA predictive model using a network diffusion method on sequence information, expression profiles, and biological function ([ 93 , 94 ]). Similarly, Huang et al proposed GCN-based model, graph convolution for novel lncRNA–miRNA interactions (GCLMI), to predict lncRNA–miRNA interactions [ 63 ]. Based on the proposed model, which combines graph convolution and an auto-encoder, Huang et al found that the area under the curve (AUC) for the predictor was around 0.85, indicating that DL-based methods are important contributors in this research field.…”

“…proposed GCN-based model, graph convolution for novel lncRNA-miRNA interactions (GCLMI), to predict lncRNA-miRNA interactions [63]. Based on the proposed model, which combines graph convolution and an auto-encoder, Huang et al found that the area under the curve (AUC) for the predictor was around 0.85, indicating that DL-based methods are important contributors in this research field.…”

The various regulatory functions of long noncoding RNAs in apoptosis, cell cycle, and cellular senescence

“…miRNAs and lncRNAs interact with each other, organizing an extensive regulatory network that can modulate the expression of genes in transcriptional, posttranscriptional, and posttranslational levels. These two ncRNA families can affect almost all cell cycle aspects, cell division, differentiation, and apoptosis 30 …”