2011, Vol.16 No.3, 260-264
Article ID 1007-1202(2011)03-0260-05
DOI 10.1007/s11859-011-0747-6
Prediction of Protein Structural
Classes Using the Theory of Increment of Diversity and Support Vector Machine
□ WANG Fangping1, WANG Zhijian1, LI Hong2 ,
YANG Keli2
1. School of Physics and Information Science, Tianshui Normal University, Tianshui 741001,Gansu, China;
2. College of Sciences and Technology, Inner Mongolia University, Hohhot 010021, Inner Mongolia, China
© Wuhan University and Springer-Verlag Berlin Heidelberg 2011
0 Introduction
As early as in 1976, according to the protein second structure from the x-ray diffraction known as 31 globular protein crystals, Levitt and Chothia[1] proposed the con-cept of protein structural classes. That is the protein sec-ond structural types, which are classified into four main structural classes: all-α, all-β, α/β (the α/β class repre-sents those proteins with both α-helices and β-strands that are largely interspersed in forming mainly parallel β-sheets), and α+β (the α+β class represents those also with both α-helices and β-strands but largely segregated in forming mainly antiparallel β-sheets)[2]. The predic-tion on the protein structure is an important research domain in bioinformatics. In 1970s, researchers sug-gested that the amino acid sequences of protein deter-mined its space structure[3]. In 1980s, Nishikawa et al[4] proved that correlations do exist between the structural class of a protein and its amino acid composition (AAC). With rapid development computer science, based on AAC, many approaches have been developed to predict protein structural classes, such as, the vector composi-tion method[5], distance functions approach[6], neural network[7], fuzzy clustering[8], and support vector ma-chine (SVM)-based methods[9-12]. However, the above methods have a common limitation that some informa-tion associated with the sequence order would miss in representing a protein sample with its AAC. Hence, Chou et al[13]


introduced the pseudo amino acid compo-
Abstract: Based on the concept of the pseudo amino acid com-position (PseAAC), protein structural classes are predicted by using an approach of increment of diversity combined with sup-port vector machine (ID-SVM), in which the dipeptide amino acid composition of proteins is used as the source of diversity. Jack-knife test shows that total prediction accuracy is 96.6% and higher than that given by other approaches. Besides, the specificity (Sp) and the Matthew’s correlation coefficient (MCC) are also calcu-lated for each protein structural class, the Sp is more than 88%, the MCC is higher than 92%, and the higher MCC and Sp imply that it is credible to use ID-SVM model predicting protein structural class. The results indicate that: ① the choice of the source of diversity is reasonable, ② the predictive performance of ID- SVM is excellent, and ③ the amino acid sequences of proteins contain information of protein structural classes.
Key words: dipeptide amino acid composition; increment of diversity; support vector machines; protein structure classes CLC number: Q 61
Received date: 2010-05-10
Foundation item: Supported by the National Natural Science Foundation of China (30660044)
Biography: WANG Fangping, female, Ph.D., research direction: bioinformat-ics and codon usage. E-mail: wfangping@yahoo.cn
To whom correspondence should be addressed. E-mail: lihong499 @ hotmail. com
Prediction of Protein Se... 暂无评价 9页 免费...proteins using the Internet resources are described...structural diversity of proteins begins with ...
Prediction of protein protein interaction types using the decisionPrediction of protein protein interaction types using the decision隐藏>> Mathematical and ...
Prediction of Protein Topologies Using GIOHMMs and GRNNs Department of Information and Computer Science University of California, Irvine Irvine, CA 92697-3425...
Prediction of the secondary structural content might be considered the ?rst step in analyzing a new protein sequence and predicting its tertiary architecture ...
Structural Prediction of Membrane Protein: Application to Known Structures_专业资料。Joma fDogu iest(nulonhaUnvriyEg.E)V12d.o.7,No.(00)221 2 89 ...
feature selection using markov blanket induction for the prediction of protein...351 molecular structural properties that predict binding to thrombin (and thus...
Using the discovered associative feature we predict implicit protein interactions...theory based feature dimension reduction filter with fea- Prediction of ...
12页 1财富值 Prediction of Protein St... 暂无评价 5页 5财富值...更多>>We show that the rst-order theory of structural subtyping of non-...
12页 1财富值 Prediction of Protein St... 暂无评价 5页 5财富值... On the Theory of Structural Subtyping Viktor Kuncak and Martin Rinard ...
Sharan et al Box 2 Function prediction using the MRF method The Markov ...Data of a high diversity and dimensionality have been integrated using ...
热门文档