(a) Construction of the multi-level composite network. This network is constructed by six sub-networks. White circle indicates lncRNA; white square indicates gene; white triangle indicates phenotype. The thickness of the edge indicates the weight score. (b) The flow chart by which LncPriCNet optimizes the candidate lncRNAs. First, the candidate lncRNAs of interest and seed nodes are mapped to the multi-level composite network. Then, a global extended RWR method is used to score the candidate lncRNAs according to their proximity to seed nodes. Finally, the candidate lncRNAs are ranked according to the scores. Purple circles represent the candidate lncRNAs of interest; red triangle indicates disease phenotype (phenotype seed) of interest from the OMIM data base; red squares represent known disease genes (gene seeds) from the OMIM database; and red circles indicate known disease lncRNAs (lncRNA seeds) from the lncRNADisease database.