Predicting Protein Folding Rates Using Pseudo Amino Acid Composition

Abstract

Prediction of protein folding rate from amino acid sequences is one of the most important challenges in computational and molecular biology. Over the past few years, many methods have been developed to reflect the correlation between folding rates and protein structures and sequences. In this paper, based on the concept of Chou's pseudo-amino acid composition, we presents an effective method to predict protein folding rates from amino acid sequences, without any knowledge of the tertiary or secondary structures, or structural class information. The originality of the work presented in this paper is that it tackles the effect of sequence order information. The proposed method provides a good correlation between predicted and experimental folding rates, which equal 0.67 for 76 proteins when evaluated with leave-one-out jackknife test. The comparative results demonstrate that our approach is better than most of other methods.