支持向量机方法在T细胞表位预测中的应用
|
摘要
在T细胞介导的特异性免疫应答中,T细胞表面抗原受体(T-cell receptor,TCR)仅能识别抗原肽与主要组织相容性复合体(major histocompatibility complex,MHC)分子结合形成的复合物。此复合物的形成是依赖于抗原的加工提呈途径。内源性抗原(病毒、肿瘤抗原等)需要经过蛋白酶体(proteaome)的降解、与抗原提呈相关的转运蛋白(transporter associated with antigen processing,TAP)的转运、MHCⅠ类分子的结合后才能被细胞毒性T细胞(cytotoxic T lymphocyte,CTL)识别,相应的抗原肽称为CTL表位;外源性抗原(细菌产生的毒素)也需要经过溶酶体酶的降解和MHCⅡ类分子的结合后才能被辅助性T细胞(helper T cell,Th)识别,相应的抗原肽称为Th表位。一般来讲,抗原的加工提呈途径决定了T细胞对表位的选择性。为了进一步弄清抗原的加工提呈机制,提高T细胞表位预测的准确性和合理性,本文应用支持向量机方法对抗原加工提呈途径中三个重要的选择性阶段进行了理论预测研究。
1.在内源性抗原的加工提呈途径中,真核细胞中的泛素-蛋白酶体系统对抗原蛋白发挥着重要的酶切降解功能。为了进一步理解蛋白酶体的酶切机制,本文对蛋白酶体的裂解位点特异性进行了研究。文中采用支持向量分类器(support vector classifier,SVC)方法建立了蛋白酶体的裂解位点预测模型,预测准确度达到83.1%。在相同检验集下,本模型的性能表现要优于其他预测模型。通过分析预测模型中不同位置上氨基酸对裂解位点形成的权重系数,本文获取了蛋白酶体裂解位点及其两侧区域氨基酸的裂解特异性。这些裂解特异性反映了蛋白酶体与抗原蛋白相互作用信息,同时表明蛋白酶体对抗原蛋白的酶切处理不是随机的,而是有一定模式和选择性的。研究结果为进一步揭示蛋白酶体裂解抗原蛋白的机理提供了重要的信息。
2.在内源性抗原的加工提呈途径中,MHCⅠ类分子发挥着启动和调节免疫应答的重要作用。抗原肽只有结合MHCⅠ类分子后,才能被细胞毒性T细胞(CTL)识别,然而,对于一个给定的MHCⅠ类分子,只有一组特定的抗原肽才能与之结合。因此,准确判断哪些抗原肽能与指定MHCⅠ类分子结合,不仅有助于理解免疫机制,而且有助于开发高效的抗肿瘤疫苗。为了进一步了解MHCⅠ类分子与抗原肽结合的特异性,本文利用支持向量回归机(support vector regression,SVR)方法以及四种氨基酸编码方式建立了四个抗原肽与MHCⅠ类分子结合亲和力的预测模型。四个模型的性能比较显示,基于氨基酸物理化学性质建立的模型具有更好的预测能力。此外,本文通过分析抗原肽中不同位置氨基酸对结合MHCⅠ类分子形成的权重系数,获取了抗原肽与MHCⅠ类分子的结合特异性。
3.在外源性抗原的加工提呈途径中,抗原肽与MHCⅡ类分子的结合是激活辅助性T细胞特异性免疫应答的先决条件。对于给定的一种MHCⅡ类分子,准确预测与之结合的抗原肽,不仅有助于人们进一步理解免疫的基本原理,还对表位疫苗的开发、自身免疫性疾病(如类风湿关节炎、胰岛素依赖性糖尿病等)的治疗等有着重要的意义。本文应用迭代自洽(iterative self-consistent,ISC)策略与支持向量回归机(SVR)的组合方法和四种氨基酸编码方式,对17种MHCⅡ分子(包括14种人类的HLA DR分子和3种鼠类的H2 IA分子)的配体数据进行了回归分析,分别建立了预测模型。与其他预测模型的比较结果显示,本文模型具有更优的性能表现。此外,本文以HLA DRB1*0101为例,通过分析抗原肽中不同位置氨基酸对结合MHCⅡ类分子形成的权重系数,获取了抗原肽与MHCⅡ类分子的结合特异性。研究结果为进一步揭示Th细胞表位的产生机制提供了重要的信息。
In T-cell mediated specific immune response, the T-cell receptor (TCR) only recognizes the peptide binding to major histocompatibility complex (MHC) molecular. The formation of the peptide-MHC complex depends on the antigen processing and presentation pathway. Endogenous antigens (e.g. viruses, tumor antigens) need to be degradated by proteaome, transported by transporter associated with antigen processing (TAP) and bound by MHC classⅠmolecule before recognized by cytotoxic T lymphocytes (CTL), correspondingly, peptides generated from this pathway are called CTL eptitopes; Exogenous antigens (e.g. toxins produced by bacterias) also need to be degradated by lysosomal enzyme and bound by MHC classⅡmolecule before recognized by helper T cell (Th), and peptides generated from this pathway are called Th eptitope. Gernelly speaking, the antigen processing and presentation pathway determines the selection of T cell to eptitope. In order to further study the biological mechanism of the processing and presentation of antigen, and improve accuracy and rationality of T cells epitope prediction, support vector machine (SVM) was used to theoretically study following three important selective stages in the antigen processing and presentation pathway.
1. The ubiquitin-proteasome system of the eukaryote plays an importance role in the endogenous antigen processing and presentation pathway. In order to further study the specificity of the proteasome cleavage sites, the support vector classifier (SVC) was used to build the predictive model of proteasomal cleavage sites and the predictive accuracy of the model is 83.1%. Compared to other models with the same test set, the performance of this model is more satisfying, The specificities of the cleavage sites and their adjacent positions come from analysis based on the weight coefficient of the amino acids to cleavage sites in the predictive model, showing the information about interaction of the proteasome with an antigen protein, which demonstrates that the proteasome cleaves the target protein selectively, but not randomly. This study is helpful to further reveal intrinsic mechanism how proteasome cleave antigen protein.
2. In the endogenous antigen processing and presentation pathway, MHC classⅠmolecules play a critical role in initiating and regulating immune responses. Peptide must be bound to an MHC classⅠmolecule before recognized by the cytotoxic T lymphocytes (CTL), but only certain peptides can bind to any given MHC class I molecule. Determining which peptides bind to a specific MHC classⅠmolecule is not only helpful to understand the mechanism of immunity, but also to develop effective anti-tumor epitope vaccines. In order to further study the specificity of MHC classⅠmolecule binding antigen peptide, the support vector regression (SVR) and four amino acid encoding schemes were used to build four models of predicting binding affinities between peptides and MHC classⅠmolecules. Comparison among performances of the four models indicated that the model based on physicochemical properties of amino acids is more satisfying. Furthermore, the specificities of MHC classⅠmolecule binding antigen peptide were obtained through analysis based on the contribution of the amino acids to peptide-MHC classⅠmolecule binding affinities in the predictive model.
3. In the exogenous antigen processing and presentation pathway, peptide binding MHC classⅡmolecule is an important prerequisite for activating helper-T-cell mediated immune response. Accurate prediction of peptide that bind a specific MHC classⅡmolecule is not only helpful for understanding the immune mechanism but also is useful for developing of epitope vaccine and immunotherapy of autoimmune disease, e.g. rheumatoid arthritis (RA) and Insulin-dependent diabetes mellitus (IDDM). In this paper, a method combine an iterative self-consistent (ISC) strategy with support vector regression (SVR) and four schemes of amino acid encoding was used to build models to predict binding affinities between peptides and MHC classⅡmolecules. The predictive performance of the method is validated on data sets of 17 MHC classⅡalleles covering 14 human HLA DR alleles and 3 mouse H2 IA alleles. Compared to other models with the same data set, the predictive performance of our model is more satisfying. Furthermore, the specificities of MHC classⅡmolecule binding peptide were obtained through analysis based on the contribution of the amino acids to peptide-MHC classⅡmolecule binding affinities in the predictive model. This study is helpful to further reveal mechanism of generation of Th epitope.
1.在内源性抗原的加工提呈途径中,真核细胞中的泛素-蛋白酶体系统对抗原蛋白发挥着重要的酶切降解功能。为了进一步理解蛋白酶体的酶切机制,本文对蛋白酶体的裂解位点特异性进行了研究。文中采用支持向量分类器(support vector classifier,SVC)方法建立了蛋白酶体的裂解位点预测模型,预测准确度达到83.1%。在相同检验集下,本模型的性能表现要优于其他预测模型。通过分析预测模型中不同位置上氨基酸对裂解位点形成的权重系数,本文获取了蛋白酶体裂解位点及其两侧区域氨基酸的裂解特异性。这些裂解特异性反映了蛋白酶体与抗原蛋白相互作用信息,同时表明蛋白酶体对抗原蛋白的酶切处理不是随机的,而是有一定模式和选择性的。研究结果为进一步揭示蛋白酶体裂解抗原蛋白的机理提供了重要的信息。
2.在内源性抗原的加工提呈途径中,MHCⅠ类分子发挥着启动和调节免疫应答的重要作用。抗原肽只有结合MHCⅠ类分子后,才能被细胞毒性T细胞(CTL)识别,然而,对于一个给定的MHCⅠ类分子,只有一组特定的抗原肽才能与之结合。因此,准确判断哪些抗原肽能与指定MHCⅠ类分子结合,不仅有助于理解免疫机制,而且有助于开发高效的抗肿瘤疫苗。为了进一步了解MHCⅠ类分子与抗原肽结合的特异性,本文利用支持向量回归机(support vector regression,SVR)方法以及四种氨基酸编码方式建立了四个抗原肽与MHCⅠ类分子结合亲和力的预测模型。四个模型的性能比较显示,基于氨基酸物理化学性质建立的模型具有更好的预测能力。此外,本文通过分析抗原肽中不同位置氨基酸对结合MHCⅠ类分子形成的权重系数,获取了抗原肽与MHCⅠ类分子的结合特异性。
3.在外源性抗原的加工提呈途径中,抗原肽与MHCⅡ类分子的结合是激活辅助性T细胞特异性免疫应答的先决条件。对于给定的一种MHCⅡ类分子,准确预测与之结合的抗原肽,不仅有助于人们进一步理解免疫的基本原理,还对表位疫苗的开发、自身免疫性疾病(如类风湿关节炎、胰岛素依赖性糖尿病等)的治疗等有着重要的意义。本文应用迭代自洽(iterative self-consistent,ISC)策略与支持向量回归机(SVR)的组合方法和四种氨基酸编码方式,对17种MHCⅡ分子(包括14种人类的HLA DR分子和3种鼠类的H2 IA分子)的配体数据进行了回归分析,分别建立了预测模型。与其他预测模型的比较结果显示,本文模型具有更优的性能表现。此外,本文以HLA DRB1*0101为例,通过分析抗原肽中不同位置氨基酸对结合MHCⅡ类分子形成的权重系数,获取了抗原肽与MHCⅡ类分子的结合特异性。研究结果为进一步揭示Th细胞表位的产生机制提供了重要的信息。
In T-cell mediated specific immune response, the T-cell receptor (TCR) only recognizes the peptide binding to major histocompatibility complex (MHC) molecular. The formation of the peptide-MHC complex depends on the antigen processing and presentation pathway. Endogenous antigens (e.g. viruses, tumor antigens) need to be degradated by proteaome, transported by transporter associated with antigen processing (TAP) and bound by MHC classⅠmolecule before recognized by cytotoxic T lymphocytes (CTL), correspondingly, peptides generated from this pathway are called CTL eptitopes; Exogenous antigens (e.g. toxins produced by bacterias) also need to be degradated by lysosomal enzyme and bound by MHC classⅡmolecule before recognized by helper T cell (Th), and peptides generated from this pathway are called Th eptitope. Gernelly speaking, the antigen processing and presentation pathway determines the selection of T cell to eptitope. In order to further study the biological mechanism of the processing and presentation of antigen, and improve accuracy and rationality of T cells epitope prediction, support vector machine (SVM) was used to theoretically study following three important selective stages in the antigen processing and presentation pathway.
1. The ubiquitin-proteasome system of the eukaryote plays an importance role in the endogenous antigen processing and presentation pathway. In order to further study the specificity of the proteasome cleavage sites, the support vector classifier (SVC) was used to build the predictive model of proteasomal cleavage sites and the predictive accuracy of the model is 83.1%. Compared to other models with the same test set, the performance of this model is more satisfying, The specificities of the cleavage sites and their adjacent positions come from analysis based on the weight coefficient of the amino acids to cleavage sites in the predictive model, showing the information about interaction of the proteasome with an antigen protein, which demonstrates that the proteasome cleaves the target protein selectively, but not randomly. This study is helpful to further reveal intrinsic mechanism how proteasome cleave antigen protein.
2. In the endogenous antigen processing and presentation pathway, MHC classⅠmolecules play a critical role in initiating and regulating immune responses. Peptide must be bound to an MHC classⅠmolecule before recognized by the cytotoxic T lymphocytes (CTL), but only certain peptides can bind to any given MHC class I molecule. Determining which peptides bind to a specific MHC classⅠmolecule is not only helpful to understand the mechanism of immunity, but also to develop effective anti-tumor epitope vaccines. In order to further study the specificity of MHC classⅠmolecule binding antigen peptide, the support vector regression (SVR) and four amino acid encoding schemes were used to build four models of predicting binding affinities between peptides and MHC classⅠmolecules. Comparison among performances of the four models indicated that the model based on physicochemical properties of amino acids is more satisfying. Furthermore, the specificities of MHC classⅠmolecule binding antigen peptide were obtained through analysis based on the contribution of the amino acids to peptide-MHC classⅠmolecule binding affinities in the predictive model.
3. In the exogenous antigen processing and presentation pathway, peptide binding MHC classⅡmolecule is an important prerequisite for activating helper-T-cell mediated immune response. Accurate prediction of peptide that bind a specific MHC classⅡmolecule is not only helpful for understanding the immune mechanism but also is useful for developing of epitope vaccine and immunotherapy of autoimmune disease, e.g. rheumatoid arthritis (RA) and Insulin-dependent diabetes mellitus (IDDM). In this paper, a method combine an iterative self-consistent (ISC) strategy with support vector regression (SVR) and four schemes of amino acid encoding was used to build models to predict binding affinities between peptides and MHC classⅡmolecules. The predictive performance of the method is validated on data sets of 17 MHC classⅡalleles covering 14 human HLA DR alleles and 3 mouse H2 IA alleles. Compared to other models with the same data set, the predictive performance of our model is more satisfying. Furthermore, the specificities of MHC classⅡmolecule binding peptide were obtained through analysis based on the contribution of the amino acids to peptide-MHC classⅡmolecule binding affinities in the predictive model. This study is helpful to further reveal mechanism of generation of Th epitope.
引文
[1]Fabbri M,Smart C,Pardi R.T lymphocytes[J].International Journal of Biochemistry & Cell Biology,2003.35(7):1004-1008.
[2]周光炎.免疫学原理[M].上海:上海科学技术文献出版社,2003.
[3]Kropshofer H,Vogt A B,Hammerling G J.Structural features of the invariant chain fragment CLIP controlling rapid release from HLA-DR molecules and inhibition of peptide binding[J].Proceedings of the National Academy of Sciences of the United States of America,1995.92(18):8313-8317.
[4]Berzofsky J A,Ahlers J D,Belyakov I M.Strategies for designing and optimizing new generation vaccines[J].Nature Reviews Immunology,2001.1(3):209-219.
[5]De Groot A S.Immunomics:discovering new targets for vaccines and therapeutics[J].Drug Discovery Today,2006.11(5-6):203-209.
[6]Alexander C,Kay A B,Larche M.Peptide-based vaccines in the treatment of specific allergy[J].Current Drug Targets - Inflammation and Allergy,2002.1(4):353-361.
[7]Durrant L G,Ramage J M.Development of cancer vaccines to activate cytotoxic T lymphocytes[J].Expert Opinion on Biological Therapy,2005.5(4):555-563.
[8]朱锡华,吴玉章.对表位生物学研究的认识和体会[J].上海免疫学杂志,1998(01).
[9]吴玉章.免疫识别、分子设计与抗原工程[J].第三军医大学学报,2000(10).
[10]曹雪涛.免疫学研究的发展趋势及我国免疫学研究的现状与展望[J].中国免疫学杂志,2009(01).
[11]Schirle M,Weinschenk T,Stevanovic S.Combining computer algorithms with experimental approaches permits the rapid and accurate identification of T cell epitopes from defined antigens[J].Journal of Immunological Methods,2001.257(1-2):1-16.
[12]Brusic V,Bajic V B,Petrovsky N.Computational methods for prediction of T-cell epitopes - a framework for modelling,testing,and applications[J].Methods,2004.34(4):436-443.
[13]Viatte S,Alves P M,Romero P.Reverse immunology approach for the identification of CD8 T-cell-defined antigens:Advantages and hurdles[J].Immunology and Cell Biology,2006.84:318-330.
[14]Tsurui R,Takahashi T.Prediction of T-cell epitope[J].Journal of Pharmacological Sciences,2007.105(4):299-316.
[15]黄艳新,鲍永利,李玉新.抗原表位预测的免疫信息学方法研究进展[J].中国免疫学杂志,2008(09).
[16]Rammensee H G,Bachmann J,Emmerich N P N,et al.SYFPEITHI:database for MHC ligands and peptide motifs[J].Immunogenetics,1999.50(3-4):213-219.
[17]Reche P A,Glutting J P,Reinherz E L.Prediction of MHC class I binding peptides using profile motifs[J].Human Immunology,2002.63(9):701-709.
[18]Reche P A,Glutting J P,Zhang H,et al.Enhancement to the RANKPEP resource for the prediction of peptide binding to MHC molecules using profiles[J].Immunogenetics,2004.56(6):405-419.
[19]Parker K C,Bednarek M A,Coligan J E.Scheme for ranking potential HLA-A2 binding peptides based on independent binding of individual peptide side-chains[J].Journal of Immunology,1994.152(1):163-175.
[20]Bian H J,Hammer J.Discovery of promiscuous HLA-Ⅱ-restricted T cell epitopes with TEPITOPE[J].Methods,2004.34(4):468-475.
[21]Bian H J, Reidhaar-Olson J F, Hammer J. The use of bioinformatics for identifying class II-restricted T-cell epitopes [J]. Methods, 2003. 29(3): 299-309.
[22] Guan P, Doytchinova I A, Zygouri C, et al. MHCPred: bringing a quantitative dimension to the online prediction of MHC binding[J]. Appl Bioinformatics, 2003. 2(1): 63-6.
[23]Guan P P, Doytchinova I A, Zygouri C, et al. MHCPred: a server for quantitative prediction of peptide-MHC binding[J]. Nucleic Acids Research, 2003. 31(13): 3621-3624.
[24] Singh H, Raghava G P S. ProPred: prediction of HLA-DR binding sites [J]. Bioinformatics, 2001. 17(12): 1236-1237.
[25] Zhang G L, Khan A M, Srinivasan K N, et al. MULTIPRED: a computational system for prediction of promiscuous HLA binding peptides [J]. Nucleic Acids Research, 2005. 33: W172-W179.
[26] Wang L, Pan D L, Hu X H, et al. BiodMHC: an online server for the prediction of MHC class II-peptide binding affinity[J]. Journal of Genetics and Genomics, 2009. 36(5): 289-296.
[27] Bui H H, Sidney J, Peters B, et al. Automated generation and evaluation of specif ic MHC binding predict ive tools: ARB matrix applications [J]. Immunogenetics, 2005. 57(5): 304-314.
[28] Nielsen M, Lundegaard C, Lund O. Prediction of MHC class II binding affinity using SMM-align, a novel stabilization matrix alignment method[J]. Bmc Bioinformatics, 2007. 8.
[29] Kuttler C, Nussbaum A IC, Dick T P, et al. An algorithm for the prediction of proteasomal cleavages [J]. Journal of Molecular Biology, 2000. 298(3): 417-429.
[30] Nussbaum A K, Kuttler C, Hadeler K P, et al. PAProC: a prediction algorithm for proteasomal cleavages available on the WWW[J]. Immunogenetics, 2001. 53(2): 87-94.
[31] Kesmir C, Nussbaum A K, Schild H, et al. Prediction of proteasome cleavage motifs by neural networks[J]. Protein Engineering, 2002. 15(4): 287-296.
[32]Brusic V, Rudy G, Honeyman M, et al. Predict ion of MHC class II-binding peptides using an evolutionary algorithm and artificial neural network [J]. Bioinformatics, 1998. 14(2): 121-130.
[33] Nielsen M, Lundegaard C, Worning P, et al. Improved prediction of MHC class I and class II epitopes using a novel Gibbs sampling approach [J]. Bioinformatics, 2004. 20(9): 1388-1397.
[34]Lata S, Bhasin M, Raghava G P S. Application of machine learning techniques in predicting MHC binders[J]. Methods in Molecular Biology, 2007: 201-215.
[35]Donnes P, Elofsson A. Predict ion of MHC class I binding peptides, using SVMHC[J]. Bmc Bioinformatics, 2002. 3.
[36] Wan J, Liu W, Xu Q Q, et al. SVRMHC prediction server for MHC-binding peptides [J]. Bmc Bioinformatics, 2006. 7.
[37] Doytchinova I A, Flower D R. Quantitative approaches to computational vaccinology[J]. Immunology and Cell Biology, 2002. 80(3): 270-279.
[38] Flower D R, McSparron H, Blythe M J, et al. Computational vaccinology: quantitative approaches[J]. Novartis Found Symp, 2003. 254: 102-20; discussion 120-5, 216-22, 250-2.
[39] Holzhutter H G, Frommel C, Kloetzel P M. A theoretical approach towards the identification of cleavage-determining amino acid motifs of the 20 S proteasome[J]. Journal of Molecular Biology, 1999. 286(4): 1251-1265.
[40]Holzhutter H G,Kloetzel P M.A kinetic model of vertebrate 20S protcasome accounting for the generation of major proteolytic fragments from oligomeric peptide substrates[J].Biophysical Journal,2000.79(3):1196-1205.
[41]McCammon J A,Gelin B R,Karplus M.Dynamics of folded proteins[J].Nature,1977.267(5612):585-590.
[42]Cardenas C,Villaveces J L,Bohorquez H,et al.Quantum chemical analysis explains hemagglutinin peptide-MHC class Ⅱ molecule HLA-DR beta I*0101 interactions[J].Biochemical and Biophysical Research Communications,2004.323(4):1265-1277.
[43]Agudelo W A,Galindo J F,Ortiz M,et al.Variations in the electrostatic landscape of class Ⅱ human leukocyte antigen molecule induced by modifications in the myelin basic protein peptide:a theoretical approach[J].PLoS ONE,2009.4(1):e4164.
[44]Toseland C P,Clayton D J,McSparron H,et al.AntiJen:a quantitative immunology database integrating functional,thermodynamic,kinetic,biophysical,and cellular data[J].Immunome Res,2005.1(1):4.
[45]Brusic V,Rudy G,Harrison L C.MHCPEP,a database of MHC-binding peptides:update 1997[J].Nucleic Acids Research,1998.26(1):368-371.
[46]Bhasin M,Singh H,Raghava G P S.MHCBN:a comprehensive database of MHC binding and non-binding peptides[J].Bioinformatics,2003.19(5):665-666.
[47]Robinson J,Waller M J,Fail S C,et al.The IMGT/HLA database[J].Nucleic Acids Research,2009.37:D1013-D1017.
[48]Vapnik V N.Statistical Learning Theory[M].New York:Wiley Interscience,1998.
[49]Vapnik V N著,张学工译.统计学习理论的本质[M]:清华大学出版社,2000.
[50]Vapnik V N.An overview of statistical learning theory[J].Ieee Transactions on Neural Networks,1999.10(5):988-999.
[51]Vapnik V N著,许建华,张学工译.统计学习理论[M]:电子工业出版社,2004.
[52]Cherkassky V.The nature of statistical learning theory[J].IEEE Trans Neural Netw,1997.8(6):1564.
[53]Cherkassky V,Mulier F.Vapnik-Chervoncnkis(VC) learning theory and its applications[J].Ieee Transactions on Neural Networks,1999.10(5):985-987.
[54]邓乃扬,田英杰.数据挖掘中的新方法--支持向量机[M]:科学出版社,2004.
[55]Burges C J C.A tutorial on Support Vector Machines for pattern recognition[J].Data Mining and Knowledge Discovery,1998.2(2):121-167.
[56]Keerthi S S,Shcvade S K,Bhattacharyya C,et al.Improvements to Platt's SMO algorithm for SVM classifier design[J].Neural Computation,2001.13(3):637-649.
[57]Smola A J,Scholkopf B.A tutorial on support vector regression[J].Statistics and Computing,2004.14(3):199-222.
[58]Ancona N.classification properties of support vector machines for regression[J].Technical Report,1999(R.I.-IESI/CNR-Nr.02/99).
[59]Bi J B,Bennett K P.Duality,geometry,and support vector regression[J].Advances in Neural Information Processing Systems 14,Vols 1 and 2,2002.14:593-600.
[60]King R W,Deshaies R J,Peters J M,et al.How proteolysis drives the cell cycle[J].Science,1996.274(5293):1652-1659.
[61]Adams J.The proteasome:structure,function,and role in the cell[J].Cancer Treatment Reviews,2003.29:3-9.
[62]Vijaykumar S,Bugg C E,Cook W J.STRUCTORE OF UBIQUITIN REFINED AT 1.8 A RESOLUTION[J].Journal of Molecular Biology,1987.194(3):531-544.
[63] Ubiquitin. Molecule of the Month 2004. Available from: http://www. rcsb. org/pdb/static. do?p=education.discussion/molecule_of_the_month/pdb6 0_1.html.
[64] Ubiquitination. Molecule of the Month 2004. Available from: http: //www. rcsb. org/pdb/static. do?p=education_discussion/molecule_of_the_month/pdb6 0-2. html.
[65] Haas A L, Warms J V B, Hershko A, et al. Ubiquitin-activating enzyme - mechanism and role in protein-ubquitin conjugation[J]. Journal of Biological Chemistry, 1982. 257(5): 2543-2548.
[66]Risseeuw E P, Daskalchuk T E, Banks T W, et al. Protein interaction analysis of SCF ubiquitin E3 ligase subunits from Arabidopsis [J]. Plant Journal, 2003. 34(6): 753-767.
[67] Thrower J S, Hoffman L, Rechsteiner M, et al. Recognition of the polyubiquitin proteolytic signal[J]. Embo Journal, 2000. 19(1): 94-102.
[68] Passmore L A, Barford D. Getting into position: the catalytic mechanisms of protein ubiquitylation[J]. Biochemical Journal, 2004. 379: 513-525.
[69] Coux O, Tanaka K, Goldberg A L. Structure and functions of the 20S and 26S proteasomes [J]. Annual Review of Biochemistry, 1996. 65: 801-847.
[70] Tanaka K. The proteasome: Overview of structure and functions[J]. Proceedings of the Japan Academy Series B-Physical and Biological Sciences, 2009. 85(1): 12-36.
[71]Kisselev A F, Akopian T N, Woo K M, et al. The sizes of peptides generated from protein by mammalian 26 and 20 S proteasomes - Implications for understanding the degradative mechanism and antigen presentation[J]. Journal of Biological Chemistry, 1999. 274(6): 3363-3371.
[72] Hershko A, Ciechanover A. The ubiqui tin system[J]. Annual Review of Biochemistry, 1998. 67: 425-479.
[73] Goldberg A, Smith D M, Benaroudj N. Proteasomes and their associated ATPases: A destructive combination[J]. Journal of Stuctural Biology, 2006. 156(1): 72-83.
[74] Knowlton J R, Johnston S C, Whitby F G, et al. Structure of the proteasome activator REG alpha (PA28 alpha) [J]. Nature, 1997. 390(6660): 639-643.
[75]Whitby F G, Masters E I, Kramer L, et al. Structural basis for the activation of 20S proteasomes by 11S regulators [J]. Nature, 2000. 408(6808): 115-120.
[76] Toes R E M, Nussbaum A K, Degermann S, et al. Discrete cleavage motifs of constitutive and immunoproteasomes revealed by quantitative analysis of cleavage products[J]. Journal of Experimental Medicine, 2001. 194(1): 1-12.
[77] Heinemeyer W, Ramos P C, Dohmen R J. Ubiquitin-proteasome system - The ultimate nanoscale mincer: assembly, structure and active sites of the 20S proteasome core[J]. Cellular and Molecular Life Sciences, 2004. 61(13): 1562-1578.
[78] DeLano W. The PyMOL molecular graphics system. 2002. Available from: http: //www. pymol. org.
[79]Goldberg A L, Cascio P, Saric T, et al. The importance of the proteasome and subsequent proteolytic steps in the generation of antigenic peptides [J]. Molecular Immunology, 2002. 39(3-4): 147-164.
[80] Blythe M J, Doytchinova I A, Flower D R. JenPep: a database of quantitative functional peptide data for immunology[J]. Bioinformatics, 2002. 18(3): 434-439.
[81] Saxova P, Buus S, Brunak S, et al. Predicting proteasomal cleavage sites: a comparison of available methods[J]. International Immunology, 2003. 15(7): 781-787.
[82]Altuvia Y,Margalit H.Sequence signals for generation of antigenic peptides by the proteasome:Implications for proteasomal cleavage mechanism[J].Journal of Molecular Biology,2000.295(4):879-890.
[83]Bhasin M,Raghava G P S.Prediction of CTL epitopes using QM,SVM and ANN techniques[J].Vaccine,2004.22(23-24):3195-3204.
[84]Song Z,Liu T,Jiao C B,et al.Specificity of the proteasome cleavage to the antigen protein[J].Science in China Series B-Chemistry,2009.52(1):39-47.
[85]Wenzel T,Eckerskorn C,Lottspeich F,et al.existence of a molecular ruler in proteasomes suggested by analysis of degradation products[J].Febs Letters,1994.349(2):205-209.
[86]Dick L R,Moomaw C R,Demartino G N,et al.degradation of oxidized insulin b-chain by the multiproteinase complex macropain(proteasome)[J].Biochemistry,1991.30(10):2725-2734.
[87]Altuvia Y,Margalit H.A structure-based approach for prediction of MHC-binding peptides[J].Methods,2004.34(4):454-459.
[88]Falk K,Rotzsehke O,Stevanovic S,et al.allele-specific motifs revealed by sequencing of self-peptides eluted from MHC molecules[J].Nature,1991.351(6324):290-296.
[89]Nussbaum A K,Dick T P,Keilholz W,et al.Cleavage motifs of the yeast 20S proteasome beta subunits deduced from digests of enolase 1[J].Proceedings of the National Academy of Sciences of the United States of America,1998.95(21):12504-12509.
[90]Song Z,Liu T,Liu W,et al.QSAR model study of interaction between peptides and MHC molecules[J].Acta Physico-Chimica Sinica,2007.23(2):198-205.
[91]Liu T,Song Z,Liu W,et al.Prediction of CTL epitopes based on modified artificial neural network[J].Dalian Ligong Daxue Xuebao/Journal of Dalian University of Technology,2007.47(4):473-478.
[92]宋哲,刘涛,王雪莹等.PLS方法应用于T细胞表位定量构效关系的研究[J].免疫学杂志,2007(02).
[93]Pamer E,Cresswell P.Mechanisms of MHC class Ⅰ - Restricted antigen processing[J].Annual Review of Immunology,1998.16:323-358.
[94]Cresswell P,Ackerman A L,Giodini A,et al.Mechanisms of MHC class I-restricted antigen processing and cross-presentation[J].Immunological Reviews,2005.207:145-157.
[95]Janeway C A著,钱旻,马瑞主译.免疫生物学[M]:科学出版社,2008.
[96]Saper M A,Bjorkman P J,Wiley D C.Refined structure of the human histocompatibility antigen HLA-A2 at 2.6A resolution[J].Journal of Molecular Biology,1991.219(2):277-319.
[97]Major Histocompatibility Complex.Medical College of Yangzhou University.Available from:http://jpkc.yzu.edu.cn/course/yxmyx/chapter5/text_5.htm.
[98]Sayle R A,Milnerwhite E J.RASMOL- biomolecular graphics for all[J].Trends in Biochemical Sciences,1995.20(9):374-376.
[99]Doytchinova I A,Flower D R.Towards the in silico identification of class Ⅱrestricted T-cell epitopes:a partial least squares iterative self-consistent algorithm for affinity prediction[J].Bioinformatics,2003.19(17):2263-2270.
[100]Zhao B,Mathura V S,Rajaseger G,et al.A novel MHCp binding prediction model[J].Human Immunology,2003.64(12):1123-1143.
[101]Kessler J H,Beekman N J,Bres-Vloemans S A,et al.Efficient identification of novel HLA-A*0201-presented cytotoxic T lymphocyte epitopes in the widely expressed tumor antigen PRAME by proteasome-mediated digestion analysis[J]. Journal of Experimental Medicine, 2001. 193(1): 73-88.
[102]Sneath P H A. Relations between chemical structure and biological activity in peptides[J]. Journal of Theoretical Biology, 1966. 12(2): 157-4.
[103] Hellberg S, Sjostrom M, Skagerberg B, et al. peptide quantitative structure-activity relationships, a multivariate approach[J]. Journal of Medicinal Chemistry, 1987. 30(7): 1126-1135.
[104]Sandberg M, Eriksson L, Jonsson J, et al. New chemical descriptors relevant for the design of biologically active peptides. A multivariate characterization of 87 amino acids[J]. Journal of Medicinal Chemistry, 1998. 41(14): 2481-2491.
[105] Liu W, Meng X S, Xu Q Q, et al. Quantitative prediction of mouse class I MHC peptide binding affinity using support vector machine regression (SVR) models [J]. Bmc Bioinformatics, 2006. 7.
[106]Collantes E R, Dunn W J. Amino-acid side-chain descriptors for quantitative structure-activity relationship studies of peptide analogs[J]. Journal of Medicinal Chemistry, 1995. 38(14): 2705-2713.
[107]Zaliani A, Gancia E. MS-WHIM scores for amino acids: A new 3D-description for peptide QSAR and QSPR studies [J]. Journal of Chemical Information and Computer Sciences, 1999. 39(3): 525-533.
[108]Cocchi M, Johansson E. Amino acids characterization by GRID and multivariate data analysis[J]. Quantitative Structure-Activity Relationships, 1993. 12: 1-8.
[109]Liu S S, Yin C S, Cai S X, et al. A novel MHDV descriptor for dipeptide QSAR studies[J]. Journal of the Chinese Chemical Society, 2001. 48(2): 253-260.
[110]Zhou P, Zhou Y, Wu S R, et al. A new descriptor of amino acids based on the three-dimensional vector of atomic interaction field [J]. Chinese Science Bulletin, 2006. 51(5): 524-529.
[111]Kirksey T J, Pogue-Caley R R, Frelinger J A, et al. The structural basis for the increased immunogenicity of two HIV-reverse transcriptase peptide variant/class I major histocompatibility complexes [J]. Journal of Biological Chemistry, 1999. 274(52): 37259-37264.
[112] Chicz R M, Urban R G, Gorga J C, et al. Specificity and promiscuity among naturally processed peptides bound to HLA-DR alleles[J]. Journal of Experimental Medicine, 1993. 178(1): 27-47.
[113] Stern L J, Brown J H, Jardetzky T S, et al. Crystal-structure of the human class-II MHC protein HLA-DR1 complexed with an influenza-virus peptide [J]. Nature, 1994. 368(6468): 215-221.
[114] Jardetzky T S, Brown J H, Gorga J C, et al. Crystallographic analysis of endogenous peptides associated with HLA-DR1 suggests a common, polyproline II-like conformation for bound peptides[J]. Proceedings of the National Academy of Sciences of the United States of America, 1996. 93(2): 734-738.
[115] Zavala-Ruiz Z, Strug I, Anderson M W, et al. A polymorphic pocket at the P10 position contributes to peptide binding specificity in class II MHC proteins[J]. Chemistry 4 Biology, 2004. 11(10): 1395-1402.
[116] Rammensee H G, Friede T, Stevanovic S. MHC ligands and peptide motifs - first listing[J]. Immunogenetics, 1995. 41(4): 178-228.
[117] Madden D R. The 3-dimensional structure of peptde-MHC complexes [J]. Annual Review of Immunology, 1995. 13: 587-622.
[118] Kawashima S, Pokarowski P, Pokarowska M, et al. AAindex: amino acid index database, progress report 2008[J]. Nucleic Acids Research, 2008. 36: D202-D205.
[119] Wang R F, Wang X, Rosenberg S A. Identification of a novel major histocompatibility complex class II-restricted tumor antigen resulting from a chromosomal rearrangement recognized by CD4(+) T cells [J]. Journal of Experimental Medicine, 1999. 189(10): 1659-1667.
[120] Bhasin M, Raghava G P S. Pcleavage: an SVM based method for prediction of constitutive proteasome and immunoproteasome cleavage sites in antigenic sequences[J]. Nucleic Acids Research, 2005. 33: W202-W207.
[121]Zavala-Ruiz Z, Sundberg E J, Stone J D, et al. Exploration of the P6/P7 region of the peptide-binding site of the human class II major histocompatability complex protein HLA-DR1 [J]. Journal of Biological Chemistry, 2003. 278(45): 44904-44912.
[122] Jonassen I, Eidhammer I, Conklin D, et al. Structure motif discovery and mining the PDB[J]. Bioinformatics, 2002. 18(2): 362-367.
[123] Swets J A. Measuring the accuracy of diagnostic systems [J]. Science, 1988. 240(4857): 1285-1293.
[124] Hammer J, Takacs B, Sinigaglia F. Identification of a motif for HLA-DR1 binding peptides usingM13 display libraries [J]. Journal of Experimental Medicine, 1992. 176(4): 1007-1013.
[125]Sundberg E J, Sawicki M W, Southwood S, et al. Minor structural changes in a mutated human melanoma antigen correspond to dramatically enhanced stimulation of a CD4 (+) tumor-infiltrating lymphocyte line[J]. Journal of Molecular Biology, 2002. 319(2): 449-461.
[126] Rosloniec E F, Ivey R A, Whittington K B, et al. Crystallographic structure of a rheumatoid arthritis MHC susceptibility allele, HLA-DR1 (DRBI*0101), complexed with the immunodominant determinant of human type II collagen[J]. Journal of Immunology, 2006. 177(6): 3884-3892.
[127] Busch R, Hill C M, Hayball J D, et al. Effect of natural polymorphism at residue-86 of the HLA-DR beta-chain on peptide binding [J]. Journal of Immunology, 1991. 147(4): 1292-1298.
[128] Newtonnash D K, Eckels D D. Differential effect of polymorphism at HLA-DR1 beta-chain position-85 and position-86 on binding and recognition of DR1-restricted antigenic peptides[J]. Journal of Immunology, 1993. 150(5): 1813-1821.
[129]Hill C M, Liu A, Marshall K W, et al. Exploration of requirements for peptide binding to HLA DRBl*0101 and DRBl*0401 [J]. Journal of Immunology, 1994. 152(6): 2890-2898.
[130] Jardetzky T S, Gorga J C, Busch R, et al. Peptide binding to HLA-DR1 - a peptide with most residues substituted to alanine retains MHC binding[J]. Embo Journal, 1990. 9(6): 1797-1803.
[131] Murthy V L, Stern L J. The class II MHC protein HLA-DR1 in complex with an endogenous peptide: implications for the structural basis of the specificity of peptide binding[J]. Structure, 1997. 5(10): 1385-1396.
[132] Vargas L E, Parra C A, Salazar L M, et al. MHC allele-specific binding of a malaria peptide makes it become promiscuous on fitting a glycine residue into pocket 6[J]. Biochemical and Biophysical Research Communications, 2003. 307(1): 148-156.
[133] Fremont D H, Hendrickson W A, Marrack P, et al. Structures of an MHC class II molecule with covalently bound single peptides [J]. Science, 1996. 272(5264): 1001-1004.
[134]Wilson N, Fremont D, Marrack P, et al. Mutations changing the kinetics of class II MHC peptide exchange[J]. Immunity, 2001. 14(5): 513-522.
[2]周光炎.免疫学原理[M].上海:上海科学技术文献出版社,2003.
[3]Kropshofer H,Vogt A B,Hammerling G J.Structural features of the invariant chain fragment CLIP controlling rapid release from HLA-DR molecules and inhibition of peptide binding[J].Proceedings of the National Academy of Sciences of the United States of America,1995.92(18):8313-8317.
[4]Berzofsky J A,Ahlers J D,Belyakov I M.Strategies for designing and optimizing new generation vaccines[J].Nature Reviews Immunology,2001.1(3):209-219.
[5]De Groot A S.Immunomics:discovering new targets for vaccines and therapeutics[J].Drug Discovery Today,2006.11(5-6):203-209.
[6]Alexander C,Kay A B,Larche M.Peptide-based vaccines in the treatment of specific allergy[J].Current Drug Targets - Inflammation and Allergy,2002.1(4):353-361.
[7]Durrant L G,Ramage J M.Development of cancer vaccines to activate cytotoxic T lymphocytes[J].Expert Opinion on Biological Therapy,2005.5(4):555-563.
[8]朱锡华,吴玉章.对表位生物学研究的认识和体会[J].上海免疫学杂志,1998(01).
[9]吴玉章.免疫识别、分子设计与抗原工程[J].第三军医大学学报,2000(10).
[10]曹雪涛.免疫学研究的发展趋势及我国免疫学研究的现状与展望[J].中国免疫学杂志,2009(01).
[11]Schirle M,Weinschenk T,Stevanovic S.Combining computer algorithms with experimental approaches permits the rapid and accurate identification of T cell epitopes from defined antigens[J].Journal of Immunological Methods,2001.257(1-2):1-16.
[12]Brusic V,Bajic V B,Petrovsky N.Computational methods for prediction of T-cell epitopes - a framework for modelling,testing,and applications[J].Methods,2004.34(4):436-443.
[13]Viatte S,Alves P M,Romero P.Reverse immunology approach for the identification of CD8 T-cell-defined antigens:Advantages and hurdles[J].Immunology and Cell Biology,2006.84:318-330.
[14]Tsurui R,Takahashi T.Prediction of T-cell epitope[J].Journal of Pharmacological Sciences,2007.105(4):299-316.
[15]黄艳新,鲍永利,李玉新.抗原表位预测的免疫信息学方法研究进展[J].中国免疫学杂志,2008(09).
[16]Rammensee H G,Bachmann J,Emmerich N P N,et al.SYFPEITHI:database for MHC ligands and peptide motifs[J].Immunogenetics,1999.50(3-4):213-219.
[17]Reche P A,Glutting J P,Reinherz E L.Prediction of MHC class I binding peptides using profile motifs[J].Human Immunology,2002.63(9):701-709.
[18]Reche P A,Glutting J P,Zhang H,et al.Enhancement to the RANKPEP resource for the prediction of peptide binding to MHC molecules using profiles[J].Immunogenetics,2004.56(6):405-419.
[19]Parker K C,Bednarek M A,Coligan J E.Scheme for ranking potential HLA-A2 binding peptides based on independent binding of individual peptide side-chains[J].Journal of Immunology,1994.152(1):163-175.
[20]Bian H J,Hammer J.Discovery of promiscuous HLA-Ⅱ-restricted T cell epitopes with TEPITOPE[J].Methods,2004.34(4):468-475.
[21]Bian H J, Reidhaar-Olson J F, Hammer J. The use of bioinformatics for identifying class II-restricted T-cell epitopes [J]. Methods, 2003. 29(3): 299-309.
[22] Guan P, Doytchinova I A, Zygouri C, et al. MHCPred: bringing a quantitative dimension to the online prediction of MHC binding[J]. Appl Bioinformatics, 2003. 2(1): 63-6.
[23]Guan P P, Doytchinova I A, Zygouri C, et al. MHCPred: a server for quantitative prediction of peptide-MHC binding[J]. Nucleic Acids Research, 2003. 31(13): 3621-3624.
[24] Singh H, Raghava G P S. ProPred: prediction of HLA-DR binding sites [J]. Bioinformatics, 2001. 17(12): 1236-1237.
[25] Zhang G L, Khan A M, Srinivasan K N, et al. MULTIPRED: a computational system for prediction of promiscuous HLA binding peptides [J]. Nucleic Acids Research, 2005. 33: W172-W179.
[26] Wang L, Pan D L, Hu X H, et al. BiodMHC: an online server for the prediction of MHC class II-peptide binding affinity[J]. Journal of Genetics and Genomics, 2009. 36(5): 289-296.
[27] Bui H H, Sidney J, Peters B, et al. Automated generation and evaluation of specif ic MHC binding predict ive tools: ARB matrix applications [J]. Immunogenetics, 2005. 57(5): 304-314.
[28] Nielsen M, Lundegaard C, Lund O. Prediction of MHC class II binding affinity using SMM-align, a novel stabilization matrix alignment method[J]. Bmc Bioinformatics, 2007. 8.
[29] Kuttler C, Nussbaum A IC, Dick T P, et al. An algorithm for the prediction of proteasomal cleavages [J]. Journal of Molecular Biology, 2000. 298(3): 417-429.
[30] Nussbaum A K, Kuttler C, Hadeler K P, et al. PAProC: a prediction algorithm for proteasomal cleavages available on the WWW[J]. Immunogenetics, 2001. 53(2): 87-94.
[31] Kesmir C, Nussbaum A K, Schild H, et al. Prediction of proteasome cleavage motifs by neural networks[J]. Protein Engineering, 2002. 15(4): 287-296.
[32]Brusic V, Rudy G, Honeyman M, et al. Predict ion of MHC class II-binding peptides using an evolutionary algorithm and artificial neural network [J]. Bioinformatics, 1998. 14(2): 121-130.
[33] Nielsen M, Lundegaard C, Worning P, et al. Improved prediction of MHC class I and class II epitopes using a novel Gibbs sampling approach [J]. Bioinformatics, 2004. 20(9): 1388-1397.
[34]Lata S, Bhasin M, Raghava G P S. Application of machine learning techniques in predicting MHC binders[J]. Methods in Molecular Biology, 2007: 201-215.
[35]Donnes P, Elofsson A. Predict ion of MHC class I binding peptides, using SVMHC[J]. Bmc Bioinformatics, 2002. 3.
[36] Wan J, Liu W, Xu Q Q, et al. SVRMHC prediction server for MHC-binding peptides [J]. Bmc Bioinformatics, 2006. 7.
[37] Doytchinova I A, Flower D R. Quantitative approaches to computational vaccinology[J]. Immunology and Cell Biology, 2002. 80(3): 270-279.
[38] Flower D R, McSparron H, Blythe M J, et al. Computational vaccinology: quantitative approaches[J]. Novartis Found Symp, 2003. 254: 102-20; discussion 120-5, 216-22, 250-2.
[39] Holzhutter H G, Frommel C, Kloetzel P M. A theoretical approach towards the identification of cleavage-determining amino acid motifs of the 20 S proteasome[J]. Journal of Molecular Biology, 1999. 286(4): 1251-1265.
[40]Holzhutter H G,Kloetzel P M.A kinetic model of vertebrate 20S protcasome accounting for the generation of major proteolytic fragments from oligomeric peptide substrates[J].Biophysical Journal,2000.79(3):1196-1205.
[41]McCammon J A,Gelin B R,Karplus M.Dynamics of folded proteins[J].Nature,1977.267(5612):585-590.
[42]Cardenas C,Villaveces J L,Bohorquez H,et al.Quantum chemical analysis explains hemagglutinin peptide-MHC class Ⅱ molecule HLA-DR beta I*0101 interactions[J].Biochemical and Biophysical Research Communications,2004.323(4):1265-1277.
[43]Agudelo W A,Galindo J F,Ortiz M,et al.Variations in the electrostatic landscape of class Ⅱ human leukocyte antigen molecule induced by modifications in the myelin basic protein peptide:a theoretical approach[J].PLoS ONE,2009.4(1):e4164.
[44]Toseland C P,Clayton D J,McSparron H,et al.AntiJen:a quantitative immunology database integrating functional,thermodynamic,kinetic,biophysical,and cellular data[J].Immunome Res,2005.1(1):4.
[45]Brusic V,Rudy G,Harrison L C.MHCPEP,a database of MHC-binding peptides:update 1997[J].Nucleic Acids Research,1998.26(1):368-371.
[46]Bhasin M,Singh H,Raghava G P S.MHCBN:a comprehensive database of MHC binding and non-binding peptides[J].Bioinformatics,2003.19(5):665-666.
[47]Robinson J,Waller M J,Fail S C,et al.The IMGT/HLA database[J].Nucleic Acids Research,2009.37:D1013-D1017.
[48]Vapnik V N.Statistical Learning Theory[M].New York:Wiley Interscience,1998.
[49]Vapnik V N著,张学工译.统计学习理论的本质[M]:清华大学出版社,2000.
[50]Vapnik V N.An overview of statistical learning theory[J].Ieee Transactions on Neural Networks,1999.10(5):988-999.
[51]Vapnik V N著,许建华,张学工译.统计学习理论[M]:电子工业出版社,2004.
[52]Cherkassky V.The nature of statistical learning theory[J].IEEE Trans Neural Netw,1997.8(6):1564.
[53]Cherkassky V,Mulier F.Vapnik-Chervoncnkis(VC) learning theory and its applications[J].Ieee Transactions on Neural Networks,1999.10(5):985-987.
[54]邓乃扬,田英杰.数据挖掘中的新方法--支持向量机[M]:科学出版社,2004.
[55]Burges C J C.A tutorial on Support Vector Machines for pattern recognition[J].Data Mining and Knowledge Discovery,1998.2(2):121-167.
[56]Keerthi S S,Shcvade S K,Bhattacharyya C,et al.Improvements to Platt's SMO algorithm for SVM classifier design[J].Neural Computation,2001.13(3):637-649.
[57]Smola A J,Scholkopf B.A tutorial on support vector regression[J].Statistics and Computing,2004.14(3):199-222.
[58]Ancona N.classification properties of support vector machines for regression[J].Technical Report,1999(R.I.-IESI/CNR-Nr.02/99).
[59]Bi J B,Bennett K P.Duality,geometry,and support vector regression[J].Advances in Neural Information Processing Systems 14,Vols 1 and 2,2002.14:593-600.
[60]King R W,Deshaies R J,Peters J M,et al.How proteolysis drives the cell cycle[J].Science,1996.274(5293):1652-1659.
[61]Adams J.The proteasome:structure,function,and role in the cell[J].Cancer Treatment Reviews,2003.29:3-9.
[62]Vijaykumar S,Bugg C E,Cook W J.STRUCTORE OF UBIQUITIN REFINED AT 1.8 A RESOLUTION[J].Journal of Molecular Biology,1987.194(3):531-544.
[63] Ubiquitin. Molecule of the Month 2004. Available from: http://www. rcsb. org/pdb/static. do?p=education.discussion/molecule_of_the_month/pdb6 0_1.html.
[64] Ubiquitination. Molecule of the Month 2004. Available from: http: //www. rcsb. org/pdb/static. do?p=education_discussion/molecule_of_the_month/pdb6 0-2. html.
[65] Haas A L, Warms J V B, Hershko A, et al. Ubiquitin-activating enzyme - mechanism and role in protein-ubquitin conjugation[J]. Journal of Biological Chemistry, 1982. 257(5): 2543-2548.
[66]Risseeuw E P, Daskalchuk T E, Banks T W, et al. Protein interaction analysis of SCF ubiquitin E3 ligase subunits from Arabidopsis [J]. Plant Journal, 2003. 34(6): 753-767.
[67] Thrower J S, Hoffman L, Rechsteiner M, et al. Recognition of the polyubiquitin proteolytic signal[J]. Embo Journal, 2000. 19(1): 94-102.
[68] Passmore L A, Barford D. Getting into position: the catalytic mechanisms of protein ubiquitylation[J]. Biochemical Journal, 2004. 379: 513-525.
[69] Coux O, Tanaka K, Goldberg A L. Structure and functions of the 20S and 26S proteasomes [J]. Annual Review of Biochemistry, 1996. 65: 801-847.
[70] Tanaka K. The proteasome: Overview of structure and functions[J]. Proceedings of the Japan Academy Series B-Physical and Biological Sciences, 2009. 85(1): 12-36.
[71]Kisselev A F, Akopian T N, Woo K M, et al. The sizes of peptides generated from protein by mammalian 26 and 20 S proteasomes - Implications for understanding the degradative mechanism and antigen presentation[J]. Journal of Biological Chemistry, 1999. 274(6): 3363-3371.
[72] Hershko A, Ciechanover A. The ubiqui tin system[J]. Annual Review of Biochemistry, 1998. 67: 425-479.
[73] Goldberg A, Smith D M, Benaroudj N. Proteasomes and their associated ATPases: A destructive combination[J]. Journal of Stuctural Biology, 2006. 156(1): 72-83.
[74] Knowlton J R, Johnston S C, Whitby F G, et al. Structure of the proteasome activator REG alpha (PA28 alpha) [J]. Nature, 1997. 390(6660): 639-643.
[75]Whitby F G, Masters E I, Kramer L, et al. Structural basis for the activation of 20S proteasomes by 11S regulators [J]. Nature, 2000. 408(6808): 115-120.
[76] Toes R E M, Nussbaum A K, Degermann S, et al. Discrete cleavage motifs of constitutive and immunoproteasomes revealed by quantitative analysis of cleavage products[J]. Journal of Experimental Medicine, 2001. 194(1): 1-12.
[77] Heinemeyer W, Ramos P C, Dohmen R J. Ubiquitin-proteasome system - The ultimate nanoscale mincer: assembly, structure and active sites of the 20S proteasome core[J]. Cellular and Molecular Life Sciences, 2004. 61(13): 1562-1578.
[78] DeLano W. The PyMOL molecular graphics system. 2002. Available from: http: //www. pymol. org.
[79]Goldberg A L, Cascio P, Saric T, et al. The importance of the proteasome and subsequent proteolytic steps in the generation of antigenic peptides [J]. Molecular Immunology, 2002. 39(3-4): 147-164.
[80] Blythe M J, Doytchinova I A, Flower D R. JenPep: a database of quantitative functional peptide data for immunology[J]. Bioinformatics, 2002. 18(3): 434-439.
[81] Saxova P, Buus S, Brunak S, et al. Predicting proteasomal cleavage sites: a comparison of available methods[J]. International Immunology, 2003. 15(7): 781-787.
[82]Altuvia Y,Margalit H.Sequence signals for generation of antigenic peptides by the proteasome:Implications for proteasomal cleavage mechanism[J].Journal of Molecular Biology,2000.295(4):879-890.
[83]Bhasin M,Raghava G P S.Prediction of CTL epitopes using QM,SVM and ANN techniques[J].Vaccine,2004.22(23-24):3195-3204.
[84]Song Z,Liu T,Jiao C B,et al.Specificity of the proteasome cleavage to the antigen protein[J].Science in China Series B-Chemistry,2009.52(1):39-47.
[85]Wenzel T,Eckerskorn C,Lottspeich F,et al.existence of a molecular ruler in proteasomes suggested by analysis of degradation products[J].Febs Letters,1994.349(2):205-209.
[86]Dick L R,Moomaw C R,Demartino G N,et al.degradation of oxidized insulin b-chain by the multiproteinase complex macropain(proteasome)[J].Biochemistry,1991.30(10):2725-2734.
[87]Altuvia Y,Margalit H.A structure-based approach for prediction of MHC-binding peptides[J].Methods,2004.34(4):454-459.
[88]Falk K,Rotzsehke O,Stevanovic S,et al.allele-specific motifs revealed by sequencing of self-peptides eluted from MHC molecules[J].Nature,1991.351(6324):290-296.
[89]Nussbaum A K,Dick T P,Keilholz W,et al.Cleavage motifs of the yeast 20S proteasome beta subunits deduced from digests of enolase 1[J].Proceedings of the National Academy of Sciences of the United States of America,1998.95(21):12504-12509.
[90]Song Z,Liu T,Liu W,et al.QSAR model study of interaction between peptides and MHC molecules[J].Acta Physico-Chimica Sinica,2007.23(2):198-205.
[91]Liu T,Song Z,Liu W,et al.Prediction of CTL epitopes based on modified artificial neural network[J].Dalian Ligong Daxue Xuebao/Journal of Dalian University of Technology,2007.47(4):473-478.
[92]宋哲,刘涛,王雪莹等.PLS方法应用于T细胞表位定量构效关系的研究[J].免疫学杂志,2007(02).
[93]Pamer E,Cresswell P.Mechanisms of MHC class Ⅰ - Restricted antigen processing[J].Annual Review of Immunology,1998.16:323-358.
[94]Cresswell P,Ackerman A L,Giodini A,et al.Mechanisms of MHC class I-restricted antigen processing and cross-presentation[J].Immunological Reviews,2005.207:145-157.
[95]Janeway C A著,钱旻,马瑞主译.免疫生物学[M]:科学出版社,2008.
[96]Saper M A,Bjorkman P J,Wiley D C.Refined structure of the human histocompatibility antigen HLA-A2 at 2.6A resolution[J].Journal of Molecular Biology,1991.219(2):277-319.
[97]Major Histocompatibility Complex.Medical College of Yangzhou University.Available from:http://jpkc.yzu.edu.cn/course/yxmyx/chapter5/text_5.htm.
[98]Sayle R A,Milnerwhite E J.RASMOL- biomolecular graphics for all[J].Trends in Biochemical Sciences,1995.20(9):374-376.
[99]Doytchinova I A,Flower D R.Towards the in silico identification of class Ⅱrestricted T-cell epitopes:a partial least squares iterative self-consistent algorithm for affinity prediction[J].Bioinformatics,2003.19(17):2263-2270.
[100]Zhao B,Mathura V S,Rajaseger G,et al.A novel MHCp binding prediction model[J].Human Immunology,2003.64(12):1123-1143.
[101]Kessler J H,Beekman N J,Bres-Vloemans S A,et al.Efficient identification of novel HLA-A*0201-presented cytotoxic T lymphocyte epitopes in the widely expressed tumor antigen PRAME by proteasome-mediated digestion analysis[J]. Journal of Experimental Medicine, 2001. 193(1): 73-88.
[102]Sneath P H A. Relations between chemical structure and biological activity in peptides[J]. Journal of Theoretical Biology, 1966. 12(2): 157-4.
[103] Hellberg S, Sjostrom M, Skagerberg B, et al. peptide quantitative structure-activity relationships, a multivariate approach[J]. Journal of Medicinal Chemistry, 1987. 30(7): 1126-1135.
[104]Sandberg M, Eriksson L, Jonsson J, et al. New chemical descriptors relevant for the design of biologically active peptides. A multivariate characterization of 87 amino acids[J]. Journal of Medicinal Chemistry, 1998. 41(14): 2481-2491.
[105] Liu W, Meng X S, Xu Q Q, et al. Quantitative prediction of mouse class I MHC peptide binding affinity using support vector machine regression (SVR) models [J]. Bmc Bioinformatics, 2006. 7.
[106]Collantes E R, Dunn W J. Amino-acid side-chain descriptors for quantitative structure-activity relationship studies of peptide analogs[J]. Journal of Medicinal Chemistry, 1995. 38(14): 2705-2713.
[107]Zaliani A, Gancia E. MS-WHIM scores for amino acids: A new 3D-description for peptide QSAR and QSPR studies [J]. Journal of Chemical Information and Computer Sciences, 1999. 39(3): 525-533.
[108]Cocchi M, Johansson E. Amino acids characterization by GRID and multivariate data analysis[J]. Quantitative Structure-Activity Relationships, 1993. 12: 1-8.
[109]Liu S S, Yin C S, Cai S X, et al. A novel MHDV descriptor for dipeptide QSAR studies[J]. Journal of the Chinese Chemical Society, 2001. 48(2): 253-260.
[110]Zhou P, Zhou Y, Wu S R, et al. A new descriptor of amino acids based on the three-dimensional vector of atomic interaction field [J]. Chinese Science Bulletin, 2006. 51(5): 524-529.
[111]Kirksey T J, Pogue-Caley R R, Frelinger J A, et al. The structural basis for the increased immunogenicity of two HIV-reverse transcriptase peptide variant/class I major histocompatibility complexes [J]. Journal of Biological Chemistry, 1999. 274(52): 37259-37264.
[112] Chicz R M, Urban R G, Gorga J C, et al. Specificity and promiscuity among naturally processed peptides bound to HLA-DR alleles[J]. Journal of Experimental Medicine, 1993. 178(1): 27-47.
[113] Stern L J, Brown J H, Jardetzky T S, et al. Crystal-structure of the human class-II MHC protein HLA-DR1 complexed with an influenza-virus peptide [J]. Nature, 1994. 368(6468): 215-221.
[114] Jardetzky T S, Brown J H, Gorga J C, et al. Crystallographic analysis of endogenous peptides associated with HLA-DR1 suggests a common, polyproline II-like conformation for bound peptides[J]. Proceedings of the National Academy of Sciences of the United States of America, 1996. 93(2): 734-738.
[115] Zavala-Ruiz Z, Strug I, Anderson M W, et al. A polymorphic pocket at the P10 position contributes to peptide binding specificity in class II MHC proteins[J]. Chemistry 4 Biology, 2004. 11(10): 1395-1402.
[116] Rammensee H G, Friede T, Stevanovic S. MHC ligands and peptide motifs - first listing[J]. Immunogenetics, 1995. 41(4): 178-228.
[117] Madden D R. The 3-dimensional structure of peptde-MHC complexes [J]. Annual Review of Immunology, 1995. 13: 587-622.
[118] Kawashima S, Pokarowski P, Pokarowska M, et al. AAindex: amino acid index database, progress report 2008[J]. Nucleic Acids Research, 2008. 36: D202-D205.
[119] Wang R F, Wang X, Rosenberg S A. Identification of a novel major histocompatibility complex class II-restricted tumor antigen resulting from a chromosomal rearrangement recognized by CD4(+) T cells [J]. Journal of Experimental Medicine, 1999. 189(10): 1659-1667.
[120] Bhasin M, Raghava G P S. Pcleavage: an SVM based method for prediction of constitutive proteasome and immunoproteasome cleavage sites in antigenic sequences[J]. Nucleic Acids Research, 2005. 33: W202-W207.
[121]Zavala-Ruiz Z, Sundberg E J, Stone J D, et al. Exploration of the P6/P7 region of the peptide-binding site of the human class II major histocompatability complex protein HLA-DR1 [J]. Journal of Biological Chemistry, 2003. 278(45): 44904-44912.
[122] Jonassen I, Eidhammer I, Conklin D, et al. Structure motif discovery and mining the PDB[J]. Bioinformatics, 2002. 18(2): 362-367.
[123] Swets J A. Measuring the accuracy of diagnostic systems [J]. Science, 1988. 240(4857): 1285-1293.
[124] Hammer J, Takacs B, Sinigaglia F. Identification of a motif for HLA-DR1 binding peptides usingM13 display libraries [J]. Journal of Experimental Medicine, 1992. 176(4): 1007-1013.
[125]Sundberg E J, Sawicki M W, Southwood S, et al. Minor structural changes in a mutated human melanoma antigen correspond to dramatically enhanced stimulation of a CD4 (+) tumor-infiltrating lymphocyte line[J]. Journal of Molecular Biology, 2002. 319(2): 449-461.
[126] Rosloniec E F, Ivey R A, Whittington K B, et al. Crystallographic structure of a rheumatoid arthritis MHC susceptibility allele, HLA-DR1 (DRBI*0101), complexed with the immunodominant determinant of human type II collagen[J]. Journal of Immunology, 2006. 177(6): 3884-3892.
[127] Busch R, Hill C M, Hayball J D, et al. Effect of natural polymorphism at residue-86 of the HLA-DR beta-chain on peptide binding [J]. Journal of Immunology, 1991. 147(4): 1292-1298.
[128] Newtonnash D K, Eckels D D. Differential effect of polymorphism at HLA-DR1 beta-chain position-85 and position-86 on binding and recognition of DR1-restricted antigenic peptides[J]. Journal of Immunology, 1993. 150(5): 1813-1821.
[129]Hill C M, Liu A, Marshall K W, et al. Exploration of requirements for peptide binding to HLA DRBl*0101 and DRBl*0401 [J]. Journal of Immunology, 1994. 152(6): 2890-2898.
[130] Jardetzky T S, Gorga J C, Busch R, et al. Peptide binding to HLA-DR1 - a peptide with most residues substituted to alanine retains MHC binding[J]. Embo Journal, 1990. 9(6): 1797-1803.
[131] Murthy V L, Stern L J. The class II MHC protein HLA-DR1 in complex with an endogenous peptide: implications for the structural basis of the specificity of peptide binding[J]. Structure, 1997. 5(10): 1385-1396.
[132] Vargas L E, Parra C A, Salazar L M, et al. MHC allele-specific binding of a malaria peptide makes it become promiscuous on fitting a glycine residue into pocket 6[J]. Biochemical and Biophysical Research Communications, 2003. 307(1): 148-156.
[133] Fremont D H, Hendrickson W A, Marrack P, et al. Structures of an MHC class II molecule with covalently bound single peptides [J]. Science, 1996. 272(5264): 1001-1004.
[134]Wilson N, Fremont D, Marrack P, et al. Mutations changing the kinetics of class II MHC peptide exchange[J]. Immunity, 2001. 14(5): 513-522.