Research Article

Prediction of the bonding states of cysteines Using the support vector machines based on multiple feature vectors and cysteine state sequences

  1. Yu-Ching Chen1,
  2. Yeong-Shin Lin2,
  3. Chih-Jen Lin3,
  4. Jenn-Kang Hwang1,2,*

Article first published online: 16 APR 2004

DOI: 10.1002/prot.20079

Issue

Proteins: Structure, Function, and Bioinformatics

Proteins: Structure, Function, and Bioinformatics

Volume 55, Issue 4, pages 1036–1042, 1 June 2004

Additional Information

How to Cite

Chen, Y.-C., Lin, Y.-S., Lin, C.-J. and Hwang, J.-K. (2004), Prediction of the bonding states of cysteines Using the support vector machines based on multiple feature vectors and cysteine state sequences. Proteins, 55: 1036–1042. doi: 10.1002/prot.20079

Author Information

  1. 1

    Institute of Bioinformatics, National Chiao Tung University, HsinChu, Taiwan, ROC

  2. 2

    Department of Biological Science and Technology, National Chiao Tung University, HsinChu, Taiwan, ROC

  3. 3

    Department of Computer Science, National Taiwan University, Taipei, Taiwan, ROC

*Department of Biological Science and Technology, National Chiao Tung University, Hsinchu 30050, Taiwan, ROC

Publication History

  1. Issue published online: 6 MAY 2004
  2. Article first published online: 16 APR 2004
  3. Manuscript Accepted: 4 DEC 2003
  4. Manuscript Received: 22 SEP 2003

Funded by

  • National Science Council in Taiwan, Republic of China

SEARCH

SEARCH BY CITATION

ARTICLE TOOLS

View Full Article (HTML) Get PDF (306K)

Keywords:

  • support vector machines;
  • disulfide bonds;
  • cysteine state sequences;
  • multiple feature vectors

Abstract

The support vector machine (SVM) method is used to predict the bonding states of cysteines. Besides using local descriptors such as the local sequences, we include global information, such as amino acid compositions and the patterns of the states of cysteines (bonded or nonbonded), or cysteine state sequences, of the proteins. We found that SVM based on local sequences or global amino acid compositions yielded similar prediction accuracies for the data set comprising 4136 cysteine-containing segments extracted from 969 nonhomologous proteins. However, the SVM method based on multiple feature vectors (combining local sequences and global amino acid compositions) significantly improves the prediction accuracy, from 80% to 86%. If coupled with cysteine state sequences, SVM based on multiple feature vectors yields 90% in overall prediction accuracy and a 0.77 Matthews correlation coefficient, around 10% and 22% higher than the corresponding values obtained by SVM based on local sequence information. Proteins 2004;55:000–000. © 2004 Wiley-Liss, Inc.

View Full Article (HTML) Get PDF (306K)