Incorporating support vector machine for identifying protein tyrosine sulfation sites

(1)

Accession number:20094312393389

Title: Incorporating support vector machine for identifying protein tyrosine sulfation sites

Authors: Chang, Wen-Chi (1); Lee, Tzong-Yi (2); Shien, Dray-Ming (3);

Hsu, Justin Bo-Kai (2); Horng, Jorng-Tzong (3); Hsu, Po-Chiang (2);

Wang, Ting-Yuan (2); Huang, Hsien-Da (1); Pan, Rong-Long (4) Author affiliation:(1) Department of Biological Science and

Technology, National Chiao Tung University, Hsin-Chu, Taiwan; (2) Institute of Bioinformatics and Systems Biology, National Chiao Tung University, Hsin-Chu, Taiwan; (3) Department of Computer Science and Information Engineering, National Central University, Chung-Li 320, Taiwan; (4) Institute of Bioinformatics and Structural Biology, College of Life Sciences, National Tsing Hua University, Hsin-Chu, Taiwan; (5) Department of Electronic Engineering, Chin Min Institute of Technology, Miao-Li, Taiwan; (6) Department of Bioinformatics, Asia University, Taichung, Taiwan

Corresponding author:Huang, H.-D.

(bryan@mail.nctu.edu.tw)

Source title: Journal of Computational Chemistry Abbreviated source title:J. Comput. Chem.

Volume:30 Issue:15

Issue date:November 30, 2009 Publication year:2009

Pages:2526-2537 Language:English ISSN:01928651 E-ISSN:1096987X CODEN:JCCHDD

Document type:Journal article (JA)

Publisher:John Wiley and Sons Inc., P.O.Box 18667, Newark, NJ 07191-8667, United States

Abstract:Tyrosine sulfation is a post-translational modification of many secreted and membrane-bound proteins. It governs protein- protein interactions that are involved in leukocyte adhesion,

hemostasis, and chemokine signaling. However, the intrinsic feature of sulfated protein remains elusive and remains to be delineated.

(2)

This investigation presents SulfoSite, which is a computational method based on a support vector machine (SVM) for predicting protein sulfotyrosine sites. The approach was developed to consider structural information such as concerning the sec- ondary structure and solvent accessibility of amino acids that surround the

sulfotyrosine sites. One hundred sixtytwo experimentally verified tyrosine sulfation sites were identified using UniProtKB/SwissProt release 53.0. The results of a five-fold cross-validation evaluation suggest that the accessibility of the solvent around the sulfotyrosine sites contributes substantially to predictive accuracy. The SVM classifier can achieve an accuracy of 94.2% in five- fold cross validation when sequence positional weighted matrix (PWM) is coupled with values of the accessible sur- face area (ASA). The proposed method significantly outperforms previous methods for accurately predicting the location of tyrosine sulfation sites.©

2009 Wiley Periodicals, Inc.

Number of references:40 Main heading:Amino acids

Controlled terms: Amines - Image retrieval - Multilayer neural networks - Organic acids - Support vector machines

Uncontrolled terms: Chemokines - Cross validation - Face area - Intrinsic features - Leukocyte adhesion - matrix - Membrane-bound proteins - Post-translational modifications - Prediction - Predictive accuracy - Protein-protein interactions - Solvent accessibility - Structural information - Sulfation - SVM classifiers

Classification code:804.1 Organic Compounds - 741 Light, Optics and Optical Devices - 723.4 Artificial Intelligence - 723.2 Data Processing and Image Processing - 723 Computer Software, Data Handling and Applications - 461.1 Biomedical Engineering - 461 Bioengineering and Biology

DOI:10.1002/jcc.21258 Database:Compendex