Inferring LncRNA-disease associations based on graph autoencoder matrix completion

Ximin Wu; Wei Lan; Qingfeng Chen; Yi Dong; Jin Liu; Wei Peng

doi:10.1016/j.compbiolchem.2020.107282

Inferring LncRNA-disease associations based on graph autoencoder matrix completion

Comput Biol Chem. 2020 May 20:87:107282. doi: 10.1016/j.compbiolchem.2020.107282. Online ahead of print.

Authors

Ximin Wu¹, Wei Lan², Qingfeng Chen³, Yi Dong⁴, Jin Liu⁵, Wei Peng⁶

Affiliations

¹ School of Computer, Electronic and Information, Guangxi University, Nanning, China. Electronic address: ximinwu@qq.com.
² School of Computer, Electronic and Information, Guangxi University, Nanning, China; Hunan Provincial Key Lab on Bioinformatics, School of Computer Science and Engineering, Central South University, Changsha, China. Electronic address: lanwei@gxu.edu.cn.
³ School of Computer, Electronic and Information, Guangxi University, Nanning, China. Electronic address: qingfeng@gxu.edu.cn.
⁴ School of Computer, Electronic and Information, Guangxi University, Nanning, China. Electronic address: dongyi@st.gxu.edu.cn.
⁵ Hunan Provincial Key Lab on Bioinformatics, School of Computer Science and Engineering, Central South University, Changsha, China. Electronic address: liujin06@csu.edu.cn.
⁶ The Network Center, Kunming University of Science and Technology, Kunming, China. Electronic address: weipeng1980@gmail.com.

PMID: 32502934
DOI: 10.1016/j.compbiolchem.2020.107282

Abstract

Accumulating studies have indicated that long non-coding RNAs (lncRNAs) play crucial roles in large amount of biological processes. Predicting lncRNA-disease associations can help biologist to understand the molecular mechanism of human disease and benefit for disease diagnosis, treatment and prevention. In this paper, we introduce a computational framework based on graph autoencoder matrix completion (GAMCLDA) to identify lncRNA-disease associations. In our method, the graph convolutional network is utilized to encode local graph structure and features of nodes for learning latent factor vectors of lncRNA and disease. Further, the inner product of lncRNA factor vector and disease factor vector is used as decoder to reconstruct the lncRNA-disease association matrix. In addition, the cost-sensitive neural network is utilized to deal with the imbalance between positive and negative samples. The experimental results show GAMLDA outperforms other state-of-the-art methods in prediction performance which is evaluated by AUC value, AUPR value, PPV and F1-score. Moreover, the case study shows our method is the effectively tool for potential lncRNA-disease prediction.

Keywords: Graph convolutional network; Inner product; LncRNA-disease association; Matrix completion.