Computational Systems Biology Methods and Protocols.7z

an extremely unbalanced training dataset. The performance of

O-GlcNAcylation sites predictors needs to be improved in the

future work.

4 Conclusion and Perspectives

The development of computational tools for the accurate predic-

tion of protein O-GlcNAcylation is a worthy goal, given the impor-

tance of these modifications in molecular biology and the

incomplete state of our present knowledge. However, the findings

presented in this chapter of six prediction tools suggest that the

prediction performance of the majority of these tools is far from

satisfactory, especially regarding their sensitivity. There is, there-

fore, great opportunity to update the accuracy of prediction tools

by constructing optimized datasets, improving novel feature extrac-

tion methods, and developing ensemble classification algorithms.

In the future, we suggest that researchers focus on these three

aspects to develop powerful and efficient predictors for

O-GlcNAcylation sites identification.

Acknowledgments

This work was supported by the Fundamental Research Funds for

the Central Universities (3132016306, 3132017048).

References

1. Torres CR, Hart GW (1984) Topography and
   polypeptide distribution of terminal
   N-acetylglucosamine residues on the surfaces
   of intact lymphocytes. Evidence for O-linked
   GlcNAc. J Biol Chem 259:3308–3317


2. Comer FI, Hart GW (1999) O-GlcNAc and
   the control of gene expression. Biochim Bio-
   phys Acta 1473:161–171
   3. McClain DA, Crook ED (1996) Hexosamines
   and insulin resistance. Diabetes 45:1003–1009
   4. Liu F et al (2004) O-GlcNAcylation regulates
   phosphorylation of tau: a mechanism involved
   in Alzheimer’s disease. Proc Natl Acad Sci U S
   A 101:10804–10809
   5. Wang Z et al (2010) Enrichment and site
   mapping of O-linked N-acetylglucosamine by

Table 2
Performances comparisons among six predictors

Tool name Sn (%) Sp (%) Acc (%) MCC

YinOYang 34.33 89.36 88.85 0.0725

O-GlcNAcscan 31.34 92.45 91.89 0.0847

O-GlcNAcPRED 56.72 64.77 64.70 0.0428

PGlcS 64.62 68.40 68.37 0.0697

Lee 2015 34.33 95.15 94.60 0.1275

244 Cangzhi Jia and Yun Zuo