computational approaches for lncRNA-disease interaction predic-
tion. Although these methods have achieved a great success in the
past few years, there are some further researches that are needed to
improve these methods.- It cannot be ignored that current available data contain large
amounts of false-positive and false-negative noises. It has been
showed that integrating other types of biological data can
improve performance of disease-related lncRNA prioritization.
However, it is still difficult to combine multiple data resources
appropriate for lncRNA-disease association prediction. There-
fore, methods for effectively integrating various data resources
are needed to develop to improve network quality for lncRNA-
disease interaction identification. - Different methods make use of different biological data to
predict lncRNA-disease association. The criteria of data selec-
tion and data integration may be different. These differences
give rise to biases among different approaches. Therefore, it is
still challenging to design suitable strategy for assessing the
performance of different methods. - Few computational tools have been developed to lncRNA-
disease prediction. Although these tools have achieved great
successes, some improvements are still necessary. For example,
some tools only provide the ranking of lncRNA in the final
report. It would be better to provide more supplemental infor-
mation such as P values of ranking and other features of
lncRNAs to enhance confidence of the results.
Acknowledgments
This work is supported in part by the National Natural Science
Foundation of China under Grant No. 61702122, 61751314 and
61363025; a key project of Natural Science Foundation of Guangxi
2017GXNSFDA198033 and a key research and development plan
of Guangxi AB17195055; the Director Open Fund of Qinzhou
City Key Laboratory of Advanced Technology of Internet of
Things IOT2017A04.References
- Altshuler DL, Durbin RM, Abecasis GR, Bent-
ley DR, Chakravarti A, Clark AG, Collins FS,
Vega FMDL, Donnelly P, Egholm M (2010)
Consortium, T.G.P.: a map of human genome
variation from population-scale sequencing.
Nature 467(7319):1061–1073 - Chen Q, Luo H, Zhang C, Chen P (2015)
Bioinformatics in protein kinases regulatory
network and drug discovery. Math Biosci
262:147–156- Green ED, Guyer MS (2011) Charting a
course for genomic medicine from base pairs
to bedside. Nature 470(7333):204 - Yan C, Wang J, Lan W, Wu F, Pan Y (2017)
SDTRLS: Predicting Drug-Target Interactions
for Complex Diseases Based on Chemical
218 Wei Lan et al.