DNILMF-LDA: Prediction of lncRNA-Disease Associations by Dual-Network Integrated Logistic Matrix Factorization and Bayesian Optimization.

Yan Li,Junyi Li,Naizheng Bian

doi:10.3390/genes10080608

Abstract

Identifying associations between lncRNAs and diseases can help understand disease-related lncRNAs and facilitate disease diagnosis and treatment. The dual-network integrated logistic matrix factorization (DNILMF) model has been used for drug–target interaction prediction, and good results have been achieved. We firstly applied DNILMF to lncRNA–disease association prediction (DNILMF-LDA). We combined different similarity kernel matrices of lncRNAs and diseases by using nonlinear fusion to extract the most important information in fused matrices. Then, lncRNA–disease association networks and similarity networks were built simultaneously. Finally, the Gaussian process mutual information (GP-MI) algorithm of Bayesian optimization was adopted to optimize the model parameters. The 10-fold cross-validation result showed that the area under receiving operating characteristic (ROC) curve (AUC) value of DNILMF-LDA was 0.9202, and the area under precision-recall (PR) curve (AUPR) was 0.5610. Compared with LRLSLDA, SIMCLDA, BiwalkLDA, and TPGLDA, the AUC value of our method increased by 38.81%, 13.07%, 8.35%, and 6.75%, respectively. The AUPR value of our method increased by 52.66%, 40.05%, 37.01%, and 44.25%. These results indicate that DNILMF-LDA is an effective method for predicting the associations between lncRNAs and diseases.

Highlights

Long non-coding RNAs are a class of non-coding RNAs that are more than 200 nucleotides in length and do not encode proteins [1]. lncRNAs were originally thought to be genomic transcriptional noise without biological function [2]
We further evaluated the role of the dual-network integrated logistic matrix factorization (DNILMF)-LDA model in predicting lncRNA–disease associations by studying three common and typical cancers: breast cancer, lung cancer, and colon cancer
The results showed that compared with the LRLSLDA, BiwalkLDA, SIMCLDA, and TPGLDA models, the AUC value of DNILMF-LDA was higher and the prediction performance of DNILMF-LDA better

Summary

Introduction

Long non-coding RNAs (lncRNAs) are a class of non-coding RNAs (ncRNAs) that are more than 200 nucleotides (nt) in length and do not encode proteins [1]. lncRNAs were originally thought to be genomic transcriptional noise without biological function [2]. LncRNAs were originally thought to be genomic transcriptional noise without biological function [2]. More and more evidence indicated that lncRNAs play an important role in many key biological processes, such as translation and post-translational regulation, cell differentiation, proliferation and apoptosis, and epigenetic regulation [3]. Predicting the potential associations between lncRNAs and diseases helps to explore the complex pathogenesis and etiology of disease at the molecular level and effectively improves the quality of disease diagnosis, treatment, and prevention. Several lncRNAs function–disease relationship databases have been established. The known lncRNA–disease relationship is still rare, and the use of biological experiments to explore lncRNA–disease associations is both time-consuming and expensive.

Objectives

Methods

Results

Discussion

Conclusion