Abstract
LncRNAs play pivotal roles in many important biological processes, but research on the functions of lncRNAs in human disease is still in its infancy. Therefore, it is urgent to prioritize lncRNAs that are potentially associated with diseases. In this work, we developed a novel algorithm, LncPriCNet, that uses a multi-level composite network to prioritize candidate lncRNAs associated with diseases. By integrating genes, lncRNAs, phenotypes and their associations, LncPriCNet achieves an overall performance superior to that of previous methods, with high AUC values of up to 0.93. Notably, LncPriCNet still performs well when information on known disease lncRNAs is lacking. When applied to breast cancer, LncPriCNet identified known breast cancer-related lncRNAs, revealed novel lncRNA candidates and inferred their functions via pathway analysis. We further constructed the human disease-lncRNA landscape, revealed the modularity of the disease-lncRNA network and identified several lncRNA hotspots. In summary, LncPriCNet is a useful tool for prioritizing disease-related lncRNAs and may facilitate understanding of the molecular mechanisms of human disease at the lncRNA level.
Highlights
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 the total genome
We present a novel computational method, LncPriCNet, to prioritize and predict disease candidate Long non-coding RNAs (lncRNAs) by integrating multi-level information regarding genes, lncRNAs, phenotypes and their associations
A breast cancer case study showed that LncPriCNet was able to capture well-documented lncRNAs as well as identify and infer the functional roles of novel lncRNAs
Summary
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 the total genome. On the basis of the assumption that similar diseases tend to be associated with similar functional lncRNAs, several network-based methods have been developed to prioritize disease-related lncRNAs16–19. On the basis of these previous results, we believe that associations between lncRNAs and genes, and disease-gene information are valuable information, and should be integrated in the study of lncRNA function This integration is a feature unique to LncPriCNet. It is reasonable to integrate multi-level data regarding genes, phenotypes, lncRNAs and their association information to prioritize disease-related lncRNA candidates. Assuming that functionally related lncRNAs and genes play roles in phenotypically similar diseases, we proposed a computational method called LncPriCNet (disease candidate LncRNAs Prioritization based on a Composite Network) to prioritize disease-related lncRNAs. First, we constructed a composite network integrating multi-level information including phenotypes, lncRNAs, genes and their associations. Considering the global functional interactions of the multi-level composite network, LncPriCNet prioritizes the candidate lncRNAs on the basis of their similarity to known disease information. A disease-lncRNA landscape was constructed and analyzed to provide a global view of disease lncRNAs
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
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
