Please use this identifier to cite or link to this item: http://hdl.handle.net/11455/19339
標題: 利用蛋白質兩面角辨識α螺旋結構及β摺板結構
Recognition of Protein α-helices and β-sheets with Dihedral Angles
作者: 蔡杰松
TSAI, Jie-Sung
關鍵字: protein
蛋白質
secondary structure prediction
dihedral angles
二級結構
結構預測
兩面角
出版社: 資訊科學系所
引用: [1]A. A. Salamov and V. V. Solovyev. Protein secondary structure prediction using local alignments. J. Mol. Biol., vol. 268, no.1, pp. 31-36, 1997. [2]A. G. Murzin, S. E. Brenner, T. Hubbard, and C. Chothia. SCOP: a structural classification of proteins database for the investigation of sequences and structures. J. Mol. Biol. 247, 536-540, 1995. [3]A. Kloczkowski, K.L. Ting, R. L. Jernigan, and J. Garnier. Combining the GOR V algorithm with evolutionary information for protein secondary structure prediction from amino acid sequence. Proteins, vol. 49, no. 2, pp. 154-166, 2002. [4]B. Bergeron. Bioinformatics Computing. M.D. Harvard Medical School and Massachusetts Institute of Technology, 2002. [5]B. Rost and C. Sander. Prediction of protein secondary structure at better than 70% accuracy. J. Mol. Biol. 232, 584-599, 1993. [6]B. Rost, C. Sander, and R. Schneider. Redefining the goals of protein secondary structure prediction. J. Mol. Biol., vol. 235 no. 1,pp.13-26,1994. [7]C. B. Anfinsen, E. Haber, M. Sela, and F. H. White. The kinetics of formation of native ribonuclease during oxidation of the reduced polypeptide chain. Proc. Nat. Acad. Sci., U.S.A. 47, 1309-1314, 1961. [8]C. Brand and J. Tooze. Introduction to Protein Structure. Garland, 1991. [9]D. T. Jones. Protein secondary structure prediction based on position-specific scoring matrices. J. Mol. Biol., vol. 292, no. 2, pp. 195-202, 1999. [10]EValuatoin of Automatic protein structure prediction, http://cubic.bioc.columbia.edu/eva/doc/ftp.html [11]G. Gibas and P. Jambeck. Developing Bioinformatics Computer Skills. O'REILLY, 2001. [12]G. Pollastri, D. Przybylski, B. Rost, P. Baldi, and G. Pollastri. Improving the prediction of protein secondary structure in three and eight classes using recurrent neural networks and profiles. Proteins, vol. 47, no. 2, pp. 228-35, 2002. [13]H. Kim and H. Park. Protein Secondary Structure Prediction Based on an Improved Support Vector Machines Approach. Dept. of Computer Science and Engineering Univ. of Minnesota, Minneapolis, MN 55455, U.S.A, 2003. [14]H. M. Berman, J. Westbrook, Z. Feng, G. Gilliland, T. N. Bhat, H. Weissig, I. N. Shindyalov, and P. E. Bourne. The Protein Data Bank. Nucleic AcidsRes, 28, 235-242, 2000. [15]H. N. Lin, J. M. Chang, K. P. Wu, T.Y. Sung, and W. L. Hsu. HYPROSP II - A knowledge-based hybrid method for protein secondary structure prediction based on local prediction confidence. BIOINFORMATICS,Vol.21, no.15,pages 3227-3233, Taiwan, 2005. [16]J. A. Cuff and G. J. Barton. Application of multiple sequence alignment rofiles to improve protein secondary structure prediction. Proteins 40,502-511, 2000. [17]J. A. Cuff, M. E. Clamp, A. S. Siddiqui, M. Finlay, and G. J. Barton. JPred: a consensus secondary structure prediction server. Bioinformatics, vol. 14, no. 10, pp. 892-893, 1998. [18]J. Martin. Protein secondary structure assignment revisited: a detailed analysis of different assignment methods. BMC Structure Biology 2005.5:17, 2005. [19]L. Pauling and R. B. Corey. Configurations of polypeptide chains with favored orientations around single bonds: Two new pleated sheet. Proc. Natl. Acad. Sci. USA 37, 729-740, 1951. [20]L. Pauling, R. B. Corey, and H. R. Branson. The structure of proteins: Two hydrogen-bonded helical configurations of the polypeptide chain. Proc. Natl. Acad. Sci. USA 37, 205-234, 1951. [21]L. Stryer. STRYER'S: Biochemistry, Fourth Edition. New York, 1995. [22]M. J. Wood and J. D. Hirst. Protein Secondary Structure Prediction with Dihedral Angles. PROTEINS: Structure, Function, and Bioinformatics 59:476-481, 2005. [23]P. Y. Chou and G. D. Fasman. Conformational parameters for amino acids in helical, beta-sheet, and random coil regions calculated from proteins. Biochemistry 13, 211-222, 1974. [24]PDBselect - selection of a representative set of PDB chains, http://bioinfo.tg.fh-giessen.de/pdbselect/ [25]PIR International Protein Sequence Database, URL: http://pir.georgetown.edu/ [26]S. F. Altschul, T. L. Madden, A. A. Schaffer, J. Zhang, Z. Zhang, W. Miller and D. J. Lipman. Gapped BLAST and PSI-BLAST: a new generation of protein database search programs. Nucleic Acids Res., vol. 25, no. 17, pp. 3389-3402,1997. [27]T.E Creighton. Proteins: Structures and Molecular Properties, 2E. W. H. Rreeman, 1992. [28]V. Daggett and M. Levitt. Protein unfolding pathways explored through molecular dynamics simulations. J. Mol. Biol. 232, 600- 619, 1993. [29]V. I. Lim. Algorithm for prediction of α-helical and β-structural regions in globular proteins. J. Mol. Biol. 88, 873-894, 1974. [30]W. Kabsch and C. Sander. Dictionary of protein secondary structure: Pattern recognition of hydrogen-bonded and geometrical features. Bioplymers 22, 2577-2637, 1983.
摘要: 近年來蛋白質結構領域的研究學者將蛋白質二級結構預測視為分類的問題,研究重心主要放在改良輸入資訊和分類預測模型上,現今預測方法在輸入資訊上大多採用PSI-Blast資料庫所產生的特定位置計分矩陣(PSSM, Position Specific Scoring Matrix)來做為連結胺基酸序列和蛋白質二級結構之間關係的輸入資訊;而在預測模型的建立上,早期主要利用統計和化學知識的方法來預測,目前則利用機器學習方法中的類神經網路(Neural Network)和近年來最熱門的支援向量機(Support Vector Machine)來訓練預測模型;然而使用黑盒子式的預測模型機制只能產生優良的預測結果,並無法提供額外資訊來幫助分析胺基酸序列形成二級結構的主要法則為何,這是目前研究方法中相當可惜的一點。 本研究以蛋白質結構為出發點提出新的輸入資訊方式,首先對已知結構的蛋白質擷取兩面角的資訊,再利用兩面角的資訊把胺基酸序列和二級結構的關係結合在一起,最後利用產生的計分矩陣與未知蛋白質序列做比對和預測的工作。本研究除了可以辨識α-螺旋及β-摺板結構以外,辨識過程中會產生對每個胺基酸位置的信心水準分數,並且可以得到支持該位置二級結構之計分矩陣的詳細資訊。由於產生該計分矩陣的胺基酸序列片段集合具有相似的結構演化性質,因此本預測機制所產生的額外資訊在蛋白質結構演化上是具有生物意義的,並非只像以往的研究只單純具有統計上的意義,而這也是本研究方法最大的貢獻。
The prediction of the protein secondary structure helps biologists to evaluate the similarities between proteins with unknown 3D structures and those proteins with known 3D structures. In this study, we propose a new method based on dihedral angle vectors to recognize the regions of α-helices and β-sheets. First, we assume that the information of secondary structure of a protein could be conserved in the dihedral angle vectors of consecutive secondary structure sequences. And then, we apply the clustering method on the sets of dihedral angel vectors to gather groups of vectors which have characteristics of similar 3D structures. In the end, we use the obtained results from the clustering method to construct the scoring matrix of peptide segments connecting with the relationships between the primary and secondary structure sequences of the non-redundant dataset of PDB. Our method provides not only the predictor of α-helices and β-sheets but also the given level of confidence on each position of a testing protein. Moreover, the predictor reveals information about the secondary structure supported by a particular scoring matrix; that is, the predictor provides information about the rules of primary sequences to form the secondary structure. In contrast, predictors that use neural network or support vector machine to construct the prediction models only provide prediction of 3-state protein secondary structure.
URI: http://hdl.handle.net/11455/19339
其他識別: U0005-1407200602113700
文章連結: http://www.airitilibrary.com/Publication/alDetailedMesh1?DocID=U0005-1407200602113700
Appears in Collections:資訊科學與工程學系所

文件中的檔案:

取得全文請前往華藝線上圖書館

Show full item record
 
TAIR Related Article
 
Citations:


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.