Robust prediction of mutation-induced protein stability change by property encoding of amino acids

Current methods of predicting mutation-induced protein stability change are imprecise. Machine learning methods have been introduced for this prediction recently; however, the available experimental data used for training these predictors are biased. Abundant data are available for several frequently occurring amino acid substitutions, whereas only limited data have been accumulated for some other mutation types. Generally, current statistical models do not account for this bias toward the commoner amino acids during the encoding process and are thus less effective in making predictions on less frequently occurring mutations. In this paper, we propose a method based on support vector machines and property encoding of amino acids. The predictor we constructed outperforms other methods on the same data sets and is more robust with poor training data. The prediction accuracy for mutations with no training data exceeded 80%. This advantage is critical for practical application, where the prediction could be applied for any type of mutations. Further analysis demonstrates our model relies on biological significant features to make predictions. To overcome the drawbacks of classifying mutations into 'stabilizing' and 'destabilizing' ones, a three-class classification of mutations was also discussed, where our method obtained an overall accuracy of 79.1%.