Scatter-search with support vector machine for prediction of relative solvent accessibility

Main Article Content

Amir Hosein Kashefi
Alireza Meshkin
Mina Zargoosh
Javad Zahiri
Mohsen Taheri
Saman Ashtiani

Abstract

Proteins have vital roles in the living cells. The protein function is almost completely dependent on protein structure. The prediction of relative solvent accessibility gives helpful information for the prediction of tertiary structure of a protein. In recent years several relative solvent accessibility (RSA) prediction methods including those that generate real values and those that predict discrete states have been developed. The proposed method consists of two main steps: the first one, provided subset selection of quantitative features based on selected qualitative features and the second, dedicated to train a model with selected quantitative features for RSA prediction. The results show that the proposed method has an improvement in average prediction accuracy and training time. The proposed method can dig out all the valuable knowledge about which physicochemical features of amino acids are deemed more important in prediction of RSA without human supervision, which is of great importance for biologists and their future researches.

Article Details

How to Cite
Kashefi, A. H., Meshkin, A., Zargoosh, M., Zahiri, J., Taheri, M., & Ashtiani, S. (2013). Scatter-search with support vector machine for prediction of relative solvent accessibility. EXCLI Journal, 12, 52-63. Retrieved from https://www.excli.de/index.php/excli/article/view/1127
Section
Original articles