Fuzzy k-nearest neighbor classifier to predict protein solvent accessibility

Jyh-Yeong Chang, Jia-Jie Shyu, Yi-Xiang Shi

Research output: Contribution to conferencePaper

1 Scopus citations

Abstract

The prediction of protein solvent accessibility is an intermediate step for predicting the tertiary structure of proteins. Knowledge of solvent accessibility has proved useful for identifying protein function, sequence motifs, and domains. Using a position-specific scoring matrix (PSSM) generated from PSI-BLAST in this paper, we develop the modified fuzzy k-nearest neighbor method to predict the protein relative solvent accessibility. By modifying the membership functions of the fuzzy k-nearest neighbor method by Sim et al. [1], has recently been applied to protein solvent accessibility prediction with excellent results. Our modified fuzzy k-nearest neighbor method is applied on the three-state, E, I, and B, and two-state, E, and B, relative solvent accessibility predictions, and its prediction accuracy compares favorly with those by the fuzzy k-NN and other approaches.
Original languageEnglish
Pages837-845
Number of pages9
StatePublished - 2008
Event14th International Conference on Neural Information Processing (ICONIP 2007) - Kitakyushu, Japan
Duration: 13 Nov 200716 Nov 2007

Conference

Conference14th International Conference on Neural Information Processing (ICONIP 2007)
CountryJapan
CityKitakyushu
Period13/11/0716/11/07

Keywords

  • SECONDARY STRUCTURE PREDICTION
  • ACCURACY
  • PROFILES

Fingerprint Dive into the research topics of 'Fuzzy k-nearest neighbor classifier to predict protein solvent accessibility'. Together they form a unique fingerprint.

  • Cite this

    Chang, J-Y., Shyu, J-J., & Shi, Y-X. (2008). Fuzzy k-nearest neighbor classifier to predict protein solvent accessibility. 837-845. Paper presented at 14th International Conference on Neural Information Processing (ICONIP 2007), Kitakyushu, Japan.