Probing the functions of long non-coding RNAs by exploiting the topology of global association and interaction network. (June 2018)

• Record Type: Journal Article
• Authors: Deng, Lei; Wu, Hongjie; Liu, Chuyao; Zhan, Weihua; Zhang, Jingpu
• Is Part Of: Computational biology and chemistry. Volume 74(2018)
• Page Start: 360
• Page End: 367
• Publication Date: 2018-06
• Subjects: 00−01 -- 99−00; lncRNA function -- Network topology -- Random walks with restart -- Singular value decomposition; Chemistry -- Data processing -- Periodicals; Biology -- Data processing -- Periodicals; Biochemistry -- Data processing; Biology -- Data processing; Molecular biology -- Data processing; Periodicals; Electronic journals; 542.85
• DOI: 10.1016/j.compbiolchem.2018.03.017
• Languages: English
• ISSNs: 1476-9271

Abstract

Abstract: Long non-coding RNAs (lncRNAs) are involved in many biological processes, such as immune response, development, differentiation and gene imprinting and are associated with diseases and cancers. But the functions of the vast majority of lncRNAs are still unknown. Predicting the biological functions of lncRNAs is one of the key challenges in the post-genomic era. In our work, We first build a global network including a lncRNA similarity network, a lncRNA–protein association network and a protein–protein interaction network according to the expressions and interactions, then extract the topological feature vectors of the global network. Using these features, we present an SVM-based machine learning approach, PLNRGO, to annotate human lncRNAs. In PLNRGO, we construct a training data set according to the proteins with GO annotations and train a binary classifier for each GO term. We assess the performance of PLNRGO on our manually annotated lncRNA benchmark and a protein-coding gene benchmark with known functional annotations. As a result, the performance of our method is significantly better than that of other state-of-the-art methods in terms of maximum F-measure and coverage.