LncADeep: anab initiolncRNA identification and functional annotation tool based on deep learning

• DOI: 10.1093/bioinformatics/bty428
• Publication Date: 2018-05-23T19:16:35Z
• Authors: Cheng Yang; Longshu Yang; Man Zhou; Haoling Xie; Chengjiu Zhang; May D Wang; Huaiqiu Zhu
• Keywords: Identification; KEGG

Abstract Motivation To characterize long non-coding RNAs (lncRNAs), both identifying and functionally annotating them are essential to be addressed. Moreover, a comprehensive construction for lncRNA annotation is desired facilitate the research in field. Results We present LncADeep, novel identification functional tool. For identification, LncADeep integrates intrinsic homology features into deep belief network constructs models targeting full- partial-length transcripts. annotation, predicts lncRNA’s interacting proteins based on neural networks, using sequence structure information. Furthermore, KEGG Reactome pathway enrichment analysis module detection with predicted proteins, provides enriched pathways modules as annotations lncRNAs. Test results show that outperforms state-of-the-art tools, lncRNA–protein interaction prediction, then presents interpretation. expect can contribute Availability implementation freely available academic use at http://cqb.pku.edu.cn/ZhuLab/lncadeep/ https://github.com/cyang235/LncADeep/. Supplementary information data Bioinformatics online.