CSI 2.0: a significantly improved version of the Chemical Shift Index
- 765 Downloads
Protein chemical shifts have long been used by NMR spectroscopists to assist with secondary structure assignment and to provide useful distance and torsion angle constraint data for structure determination. One of the most widely used methods for secondary structure identification is called the Chemical Shift Index (CSI). The CSI method uses a simple digital chemical shift filter to locate secondary structures along the protein chain using backbone 13C and 1H chemical shifts. While the CSI method is simple to use and easy to implement, it is only about 75–80 % accurate. Here we describe a significantly improved version of the CSI (2.0) that uses machine-learning techniques to combine all six backbone chemical shifts (13Cα, 13Cβ, 13C, 15N, 1HN, 1Hα) with sequence-derived features to perform far more accurate secondary structure identification. Our tests indicate that CSI 2.0 achieved an average identification accuracy (Q3) of 90.56 % for a training set of 181 proteins in a repeated tenfold cross-validation and 89.35 % for a test set of 59 proteins. This represents a significant improvement over other state-of-the-art chemical shift-based methods. In particular, the level of performance of CSI 2.0 is equal to that of standard methods, such as DSSP and STRIDE, used to identify secondary structures via 3D coordinate data. This suggests that CSI 2.0 could be used both in providing accurate NMR constraint data in the early stages of protein structure determination as well as in defining secondary structure locations in the final protein model(s). A CSI 2.0 web server (http://csi.wishartlab.com) is available for submitting the input queries for secondary structure identification.
KeywordsNuclear magnetic resonance Chemical shifts Secondary structure multi-class support-vector machine Markov model
The authors would like to thank Yongjie Liang for his help in preparing the CSI 2.0 web server. Financial support from the Natural Sciences and Engineering Research Council (NSERC), the Alberta Prion Research Institute (APRI) and PrioNet is gratefully acknowledged.
- Andrec M, Snyder DA, Zhou Z, Young J, Montelione GT, Levy RM (2007) A large data set comparison of protein structures determined by crystallography and NMR: statistical test for structural differences and the effect of crystal packing. Proteins Struct Funct Bioinform 69(3):449–465CrossRefGoogle Scholar
- Development Core Team R (2009) R: a language and environment for statistical computing. R Foundation for Statistical Computing, ViennaGoogle Scholar
- Karatzoglou A, Smola A, Hornik K, Zeileis A (2004) kernlab-an S4 package for kernel methods in R. J Stat Softw 11:1–20Google Scholar
- Kuhn M (2008) Building predictive models in R using the caret package. J Stat Softw 28(5):1–26Google Scholar
- Levitt M (1978) Conformational preferences for globular proteins. J Am Chem Soc 17(20):4277–4284Google Scholar
- Ulrich EL, Akutsu H, Doreleijers JF, Harano Y, Ioannidis YE, Lin J et al (2008) BioMagResBank. Nucleic Acids Res 36(Suppl 1):D402–D408Google Scholar
- Wishart DS, Nip AM (1998) Protein chemical shift analysis: a practical guide. Biochm Cell Biol 76(2–3):153–163Google Scholar
- Wuthrich K (1986) NMR of proteins and nucleic acids. Wiley, New YorkGoogle Scholar
- Wuthrich K (1990) Protein structure determination in solution by NMR spectroscopy. J Bio Chem 265(36):22059–22062Google Scholar