provides the lncRNA expression pattern, experimental techniques,
a brief functional description, the original reference, and additional
annotation information. Further, it allows users to search, browse,
and download the data or submit new data to the database.
MNDR (http://www.rna-society.org/mndr)[38] is an online
knowledgebase of mammal ncRNA-disease relationships in mam-
mals that aims to provide a platform to globally view the ncRNA-
mediated disease network. In the present version, it contains 807 -
lncRNA-associated, 229 miRNA-associated, 13 piRNA-associated,
and 100 snoRNA-associated.3 Predicting lncRNA-Disease Associations Based on Computational Methods
In the following, we review computational approaches for identifi-
cation of lncRNA-disease interaction. The core assumption of
lncRNA-disease interaction prediction is that functional similar
lncRNAs with similar function are likely to relate with phenotypic
similar diseases.3.1 Information
Propagation-Based
Methods
It has been demonstrated that phenotypically similar diseases often
share a set of functional similar lncRNAs [39–43]. According to
this observation, several information propagation-based methods
have been proposed to predict disease-related lncRNA.
Several studies have been developed to predict disease-related
lncRNA based on lncRNA similarity network. This is made by
integrating different biological data resources. Then, the informa-
tion propagation method is employed to predict novel disease-
related lncRNAs.
Sun et al. [44] presented a network-based method, RWRlncD,
to infer potential human lncRNA-disease associations based on
lncRNA functional similarity network. They constructed lncRNA
similarity network by integrating lncRNA-disease association and
Disease Ontology information. The random walk with restart
method was employed to prioritize disease-related lncRNA on the
function similarity network. The RWRlncD was robust to different
parameter selections. Similar work has been developed by Cheng
et al. [45]; they developed an integrative framework, IntNetLnc-
Sim, for lncRNA-disease interaction inference. They constructed
lncRNA function similarity network by integrating lncRNA-
regulatory network, mRNA-mRNA interaction network, and
miRNA-mRNA interaction network. ITM Probe was applied for
assigning a weight to each mRNA and miRNA for lncRNA and the
cosine similarity was implemented for calculating disease similarity.
The random walk with restart was used to predict disease-related
lncRNAs. The performance of IntNetLncSim is superior to
RWRlncD methods. Considering the limitations of traditional ran-
dom walk with restart (RWR), Chen et al. [46] developed a model,210 Wei Lan et al.