期刊文献+
任意字段
题名或关键词
题名
关键词
文摘
作者
第一作者
机构
刊名
分类号
参考文献
作者简介
基金资助
栏目信息

基于PRIN描述子的肽毛细管区带电泳迁移率支持向量回归预测模型

Modeling prediction of electrophoretic mobilities of peptides in capillary zone electrophoresis by support vectors regression based on amino acid descriptors(PRIN)
在线阅读 下载PDF
导出
摘要 基于氨基酸描述子PRIN,利用加和法构建了102个混杂肽(从2肽到14肽)毛细管区带电泳迁移率的支持向量回归(SVR)预测模型(ε=0.012、σ=5和C=5),并与多元线性回归作了比较研究,结果表明SVR要好于多元线性回归方法,SVR方法对训练集和预测集的预测残差平方和(PRESS)分别是0.0097和0.0135及预测复相关系数分别为0.9774和0.9419,其预测结果与实验值一致,且提出了一个简单的方法并指出迁移率与描述肽的分子结构信息的PRIN参数存在着非线性关系。 Based on amino acid descriptors （PRIN） and additive method, modeling prediction of electrophoretic mobilities of 102 promiscuous peptides （from 2 peptides to 14 peptides） in capillary zone electrophoresis by support vectors regression （SVR）. The prediction result of the SVM model （ε=0.012、σ=5 and C =5） is much better than that obtained by multiple linear regression （MLR） method. The PRESS error of the training set and the test set is 0. 0097,0. 0135 and the prediction correlation coefficient is 0. 9774 and 0. 9419, respectively. The prediction results are in agreement with the experimental values. This paper provided a simple and effective method for predicting the electrophoretic behavior of peptide and some insight into what structural features are related to the electrophoretic mobility of peptides. Moreover, it also offered an idea about nonlinear relation between electrophoretic mobility of peptides and their structural descriptors （PRIN）.
作者 印家健 邹平 崔扬健
机构地区 四川农业大学生命理学院
出处 《黑龙江大学自然科学学报》 CAS 北大核心 2007年第4期516-521,共6页 Journal of Natural Science of Heilongjiang University
基金 四川农业大学生命科学与理学院科技创新基金资助
关键词 肽 定量结构一迁移率关系 支持向量机 PRIN参数 预测 peptide quantitative structure - mobility relationships support vector machine PRIN parameter prediction
分类号 O629 [理学—有机化学] R914 [医药卫生—药物化学]
  • 相关文献

参考文献16

  • 1Janini G M,Metral C J,Issaq H J.Peptide mapping by capillary zone electrophoresis:How close is theoretical simulation to experimental determination[J].J Chromatogr A,2001,924:291-306.
  • 2Cross R F,Gamham N F.Aqueous capillary eleotrophoresis of peptides part2:an investigation of quantitative determinants of hydration and solvation relationships[J].Chromatographia,2001,54:639-646.
  • 3Sanz-Nebot V,Benavente F,Toro I,et al.Evaluation of chromatographic versus electrophoretic behavionr of a series of therapeutical peptide hormones[J].J Chromatogr,2003,985:411-423.
  • 4Simo C,Cifuentes A.Capillary electrophoresis-mass spectrometry of peptides from enzymatic protein hydrolysis:Simulation and optimization[J].Electrophoresis,2003,24:834-842.
  • 5Liu H X,Yao X j,Xue C X,et al.study of quantitative structure-mobility relationship of the peptides based on the structural descriptors and support vector machines[J].Analytica Chimica Acta,2005,542:249-259.
  • 6Mehdi J-H,Yang S.Mestafa H et al Prediction of electmphoretic mobilities of peptides in capillary zone electrophoresis by quantitative structure-mobility relationships using the offord model and artificial neural networks[J].Eleetrophoresis,2005,26:1874-1885.
  • 7Spyridon V,Boojala V B R.Prediction of distant residue contacts with the use of evolutionary information[J].PROTEINS:Structure,Function and Bioinformatics,2005,58:935-949.
  • 8Alex J S,Bernhrd S.Atutorial on support vector regression[J].Statistics and Computing,2004,(14):199-222.
  • 9Vladimir N V.统计学习理论[M].许建华,张学工,译.北京:电子工业出版社,2004.
  • 10李梦龙,刘军红,黎金明,陆敏春,王克龙.基于支持向量机的炭黑工艺建模[J].应用基础与工程科学学报,2005,13(1):51-57. 被引量：6

二级参考文献18

  • 1Janik M. Production of industrial carbon black from tar raw materials in Czechoslovakia [ J ]. Fuel and Energy Abstract,2001,42( 1 ) :24.
  • 2俞沲勤.化学计量学导论[M].湖南:湖南教育出版社,1991.345-346.
  • 3VapnieVN.统计学习理论[M].北京:电子工业出版社,2004.365-373.
  • 4Haykin S. Neural networks: a comprehensive foundation[ M]. New Jersey: Prentice-Hall, 1999:318-347.
  • 5Thissen U, Van Brakel R, De Weijer A P, et al. Using support vector machines for time series prediction [J].Chemometrics and Intelligent Laboratory Systems, 2003, 69( 1 ):35-49.
  • 6Tay F E H, Cao L J. Modified support vector machines in financial time series forecasting[ J]. Neurocomputing,2002, 48(1-4) :847-861.
  • 7Thissen U, Pepers M, Ustun B, et al. Comparing support vector machines to PLS for spectral regression applications[ J ]. Chemometrics and Intelligent Laboratory Systems,2004, 73 (2) : 169-179.
  • 8Svozil D, Kvasnieka V, Pospiehal J. Introduction to multi-layer feed-forward neural networks [ J ]. Chemometrics and Intelligent Laboratory Systems, 1997, 39 ( 1 ) :43-62.
  • 9Kim B, Park S. An optimal neural network plasma model: a case study[J]. Chemometrics and Intelligent Laboratory Systems, 2001,56( 1 ) : 39-50.
  • 10Alaradi A A, Rohani, S. Identification and control of a riser-type FCC unit using neural networks [ J ]. Computers and Chemical Engineering 2002, 26(3) : 401-421.

共引文献53

黑龙江大学自然科学学报
2007年 第4期

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部