Long noncoding RNAs are the group of noncoding RNA with
the lengths more than 200 nucleotides. Recently, lncRNAs have
attracted increasing attentions from biological researchers [17]. A
number of evidences have demonstrated that lncRNA is essential in
many biological processes such as RNA modification chromosome
dosage compensation, genomic imprinting, epigenetic regulation,
nuclear and cytoplasmic trafficking, cell proliferation, cell differen-
tiation, cell growth, cell metabolism, cell apoptosis, etc.
[18–20]. Furthermore, accumulating studies have proved that the
mutations and dysregulations of lncRNAs have close association
with many complex human diseases, such as breast cancer, cervix
cancer, lung cancer, esophagus cancer, ovarian cancer, parotid can-
cer, tongue cancer, renal disease, rhabdomyosarcoma, cardiomyop-
athy, leukemia, dyskeratosis congenital, pancreaticobiliary
maljunction, squamous carcinoma, Klinefelter’s syndrome, autoim-
mune thyroid disease, ductal carcinoma, etc. [21, 22]. For example,
MALAT1 (also known as NEAT2) was found to be highly
expressed in lung cancer, and it was used as early prognostic marker
for poor patient survival rates [23]. Figure1 shows the abnormity
of lncRNA-disease network. The triangle and rectangle denote
lncRNA and disease, respectively. It can be observed that the muta-
tion and dysregulation of lncRNA can cause disease.
Despite the results of lncRNA-disease association, the determi-
nation of the most likely lncRNA with disease is still a big challenge
for molecular biologists and medical geneticists [24, 25]. Due to
limitations of experimental approaches such as time and labor, it is
appealing to develop efficient computational methods to tackle this
obstacle. Recently, several computational approaches have been
proposed to predict the interactions between lncRNAs and diseases
[26]. This chapter aims at offering the state of arts of algorithms
and tools used to prioritize candidate lncRNAs related to disease,
by which to assist readers in catching up with recent and important
developments in this filed. The paper is organized as follows: In
Subheading2, some available data resources are presented. Recent
computational approaches for lncRNA-disease association identifi-
cation are provided in Subheading3. Subheading4 highlights the
key issues and the future works.2 Biological Data Resources
Recently, with the rapid increase of biological data, some specific
databases have been built to store and manage the data. In this
section, we describe the public databases of disease and lncRNA.
The overviews of disease and lncRNA databases are showed in
Tables1 and 2, respectively.206 Wei Lan et al.