2DCSi 使用二維叢集分析法(2D cluster analysis)來分析不同二級結構的化學位移，即螺旋體、β褶疊以及不規則形，同時並利用計分矩陣(scoring matrix)，使2DCSi的準確率達到90%以上。根據觀察的結果，大部份的預測錯誤均出現在端點部份，然而令人遺憾的是2DCSi並無法分辨端點及內部的差別，因此我們相信準確率仍可大幅提昇。本論文將朝著研究化學位移的分類並以提昇2DCSi的預測準確度而努力。
為達此目的，首先要找出所有我們認為有可能會影響化學位移的因素，例如pre-proline與其他胺基酸的差別、連續結構的端點分類、氫鍵的能量以及褶板結構平行與逆平行等數種因素。除此之外，我們亦處理由DSSP與STRIDE指派結果不一致的部分。

2DCSi employs the 2D cluster analysis for the chemical shifts of various secondary structures, namely, helix, beta sheets, and coils. By simultaneously taking advantage of the scoring matrix, the 2DCSi was reported to achieve an accuracy of above 90%. However, we believe that the accuracy still can be much improved mainly because of the following observation: A high portion of prediction errors occur at terminals. Unfortunately, the 2DCSi fails in distinguishing terminals from inside ones. Therefore, this study initiates the effort aiming at improving the 2DCSi prediction accuracy by investigating the distinguishable classes of chemical shifts.
To achieve this goal, first we try to find out all the factors that are believed to have affected the chemical shifts, such as distinction of pre-proline from others, the terminal classification of continuous structure, the energy of hydrogen bond, the parallel or anti-parallel of extended structure, and etc. In addition, inconsistency of assignment results by DSSP and STRIDE are addressed.

[1] Chou, P. Y. and Fasman G. D., “Prediction of protein
conformation,”Biochemistry, 1974; 13, 222–245.
[2] Frishman, D. and Argos, P., “Knowledge-based protein
secondary structure assignment,” Proteins, 1995; 23,
566-579.
[3] Jones, D. T., “Protein secondary structure prediction
based on position-specific scoring matrices,” J. Mol.
Biol., 1993; 292,195-202.
[4] Kabsch, W. and Sander, C. A. “Dictionary of protein
secondary structure: pattern recognition of hydrogen-
bonded and geometrical features,” Biopolymers, 1983;
22, 2577-2637.
[5] Rost, B. and Sander, C., “Prediction of secondary
structure at better than 70% accuracy,” J. Mol.
Biol., 1993; 232,584-599.
[6] Sharma, D. and Rajarathnam, K. “13C NMR chemical
shifts can predict disulfide bond formation,” J
Biomol NMR, 2000; 18, 165-171.
[7] Wishart, D. S., Sykes, B. D. and Richards, F. M.,
“Relationship between nuclear magnetic resonance
chemical shift and protein secondary structure,” J
Biomol NMR, 1991; 222, 311-333.
[8] Wishart, D. S., Sykes, B. D. and Richards, F. M.,
“The chemical shift index: A fast and simple method
for the assignment of protein secondary structure
through NMR spectroscopy,” Biochemistry, 1992; 31,
1647–1651.
[9] Wang, Y. and Jardetzky, O. “Probability-based protein
secondary structure identification using combined NMR
chemical-shift data,” Protein Sci., 2002; 11, 852-861.
[10] Willard, L., Ranjan, A., Zhang, H., Monzavi, H.,
Boyko, R. F., Sykes, B. D., and Wishart, D. S.,
“VADAR: a web server for quantitative evaluation of
protein structure quality,” Nucleic Acids Res., 2003;
31, 3316-3319.
[11] Wang, C. C., Chen, J. H., Yin, S. H. and Chuang, W.
J. “Predicting the Redox State and Secondary
Structure of Cysteine Residues in Proteins Using NMR
Chemical Shifts,” Proteins, 2006; 63, 219-226.
[12] Zhang, H., Neal, S., and Wishart, D. S. “RefDB: a
database of uniformly referenced protein chemical
shifts,” J Biomol NMR, 2003; 25,173-195.
[13] 賴文忠(2006)，“利用核磁共振化學位移之二維分析預測蛋白
質二級結構與胱胺酸氧化還原狀態之網路伺服器”，成功大學
製造工程所碩士論文