Prediction of protein structural classes using hybrid propertiesReport as inadecuate

Prediction of protein structural classes using hybrid properties - Download this document for free, or read online. Document in PDF available to download.

Molecular Diversity

, Volume 12, Issue 3–4, pp 171–179

First Online: 25 October 2008Received: 05 August 2008Accepted: 25 September 2008


In this paper, amino acid compositions are combined with some protein sequence properties physiochemical properties to predict protein structural classes. We are able to predict protein structural classes using a mathematical model that combines the nearest neighbor algorithm NNA, mRMR minimum redundancy, maximum relevance, and feature forward searching strategy. Jackknife cross-validation is used to evaluate the prediction accuracy. As a result, the prediction success rate improves to 68.8%, which is better than the 62.2% obtained when using only amino acid compositions. Therefore, we conclude that the physiochemical properties are factors that contribute to the protein folding phenomena and the most contributing features are found to be the amino acid composition. We expect that prediction accuracy will improve further as more sequence information comes to light. A web server for predicting the protein structural classes is available at

KeywordsProtein structural class Nearest neighbor algorithm mRMR Minimum Redundancy, Maximum Relevance Physiochemical properties Amino acid compositions Electronic supplementary materialThe online version of this article doi:10.1007-s11030-008-9093-9 contains supplementary material, which is available to authorized users.

Download to read the full article text

Author: Wenjin Li - Kao Lin - Kaiyan Feng - Yudong Cai


Related documents