Abstract
In recent years, microRNAs (miRNAs) have been confirmed to be involved in many important biological processes and associated with various kinds of human complex diseases. Therefore, predicting potential associations between miRNAs and diseases with the huge number of verified heterogeneous biological datasets will provide a new perspective for disease therapy. In this article, we developed a novel computational model of Triple Layer Heterogeneous Network based inference for MiRNA-Disease Association prediction (TLHNMDA) by using the experimentally verified miRNA-disease associations, miRNA-long noncoding RNA (lncRNA) interactions, miRNA function similarity information, disease semantic similarity information and Gaussian interaction profile kernel similarity for lncRNAs into an triple layer heterogeneous network to predict new miRNA-disease associations. As a result, the AUCs of TLHNMDA are 0.8795 and 0.8795 ± 0.0010 based on leave-one-out cross validation (LOOCV) and 5-fold cross validation, respectively. Furthermore, TLHNMDA was implemented on three complex human diseases to evaluate predictive ability. As a result, 84% (kidney neoplasms), 78% (lymphoma) and 76% (prostate neoplasms) of top 50 predicted miRNAs for the three complex diseases can be verified by biological experiments. In addition, based on the HMDD v1.0 database, 98% of top 50 potential esophageal neoplasms-associated miRNAs were confirmed by experimental reports. It is expected that TLHNMDA could be a useful model to predict potential miRNA-disease associations with high prediction accuracy and stability.
Highlights
According to the central law of molecular biology, genetic information was found to be stored in protein-coding genes (Crick et al, 1961)
In this paper, considering many experimentally verified miRNA-long noncoding RNA (lncRNA) interactions have been confirmed by recent biological experiments (Li et al, 2014a), we introduced the model of Triple Layer Heterogeneous Network based inference for MiRNA-Disease Association prediction (TLHNMDA) to identify the potential biological links between miRNAs and diseases by integrating multi-level data regarding miRNAs, diseases, lncRNAs and their association information into a triple layer heterogeneous network
In the framework of leave-one-out cross validation (LOOCV) evaluation, each known association of miRNA-disease pair in the database was considered as test samples in turn, the other known miRNA-disease associations were considered as training samples, the miRNAdisease pairs with no known verified associations were regarded as candidate samples
Summary
According to the central law of molecular biology, genetic information was found to be stored in protein-coding genes (Crick et al, 1961). Recent studies have revealed that up to 70% of the human genome is transcribed into RNA, whereas protein-coding genes only make up less than 2% of total genome (Djebali et al, 2012). MicroRNAs (miRNAs) are endogenous non-coding RNAs (∼22 nt) that bind to the 3′-untranslated regions (3′-UTRs). MiRNA-Disease Association Prediction of their target RNAs (mRNAs) and control the expression of gene (Ganju et al, 2017). Experiments further shown that miRNAs may be a new target for the molecular targeted therapy of various cancers (Guzzi et al, 2015; Chen et al, 2017b). Database HMDD and miR2Disease (Jiang et al, 2009; Li et al, 2014c) have been constructed to collect the associations between human miRNAs and diseases based on previous biological experiments
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call