Prediction of protein folding rates from hybrid primary sequences and its protein structure attributes

Although understanding the overall folding mechanisms help to predict protein folding rates, successful predictions can also be obtained from the sequence. Pseudo amino acid component is suggested, for the prediction of protein folding rates together with protein sequences and its protein structure attributes. A support vector regression model is implemented for two-state and multi-state proteins. The proposed features provides predictions characterized by strong correlations with the experimental folding rates, which equal 0.8392 for the two -state proteins and 0.8225 for the multi-state proteins, when evaluated with out-of-sample jackknife test.