Contrastive self-supervised graph convolutional network for detecting the relationship among lncRNAs, miRNAs, and diseases

Inferring potential relationships among long non-coding RNAs (lncRNAs), microRNAs (miRNAs), and diseases play a crucial role in investigation of disease aetiology and pathogenesis. Due to the high cost of laboratory experiments, there is a practical requirement to develop appropriate computational methods that promise to accelerate the experimental screening process for potential lncRNA-disease associations (LDAs), miRNA-disease associations (MDAs), and lncRNA-miRNA interactions (LMIs). However, most existing methods are applied to predict LDAs, MDAs, and LMIs in specific domains, neglecting the important benefits of integrating multiple sources data and limiting the ability of transferring models to other tasks. Furthermore, with the high sparsity of LDA, MDA, and LMI data, it is difficult for many computational models to exploit enough knowledge to learn the comprehensive patterns of node embedding. In this study, inspired by the recent success of graph contrastive learning, we develop a Contrastive Self-supervised Graph convolutional network to identify potential LDAs, MDAs, and LMIs (called CSGLMD). CSGLMD combines supervised learning and self-supervised learning to fully capture node features. Specifically, CSGLMD primarily leverages the rich association and similarity relationships among lncRNA, miRNA, and disease to construct a lncRNA-miRNA-disease heterogeneous graph (LMDHG) that contains three types of biological entities. It can effectively embed multi-source biological data and assist the model extension to other prediction tasks. In addition, we consider applying a label instantiation mechanism to make the LMDHG better adapt graph neural network structures and control the strength of similarity relationships between the same biological entities. Secondly, CSGLMD implements graph convolutional network (GCN) as encoder to extract node embedding features from the LMDHG, and utilizes a multi-relational modelling decoder to predict LDAs, MDAs, or LMIs. Finally, we designed a contrastive self-supervised learning task that guides the learning of node embeddings without relying on labels, and acts as a regularize in a multi-task learning paradigm to enhance the generalization ability of the model. Extensive results on two datasets (from the old and new versions of the database, respectively) show that CSGLMD significantly outperforms 12 state-of-the-art methods (5 LDA prediction and 7 MDA prediction) in predicting disease-associated lncRNAs and miRNAs. Case studies on old and new datasets can further demonstrate the capability of CSGLMD to discover disease-related new candidate lncRNAs and miRNAs. The source data and code for the proposed model are publicly available on https://github.com/sheng-n/CSGLMD.

I. Introduction

LncRNAs and miRNAs are two class of ncRNAs, lncRNAs are longer than 200 nucleotides in length, while miRNAs are 21-25 nucleotides in length. In recent years, they have received widespread attention and are considered to be involved in developmental processes and various diseases [1]. However, traditional laboratory experiments have accurate experimental results, they are usually time-consuming and labour-intensive. Therefore, developing suitable computational methods to explore the relationship among lncRNA, miRNA, and disease by using reliable biological experimental results can facilitate biologists to screen candidate lncRNAs and miRNAs as tumour biomarkers.