Prediction of protein thermostability with a direction- and distance-dependent knowledge-based potential

Abstract

The increasing use of enzymes in industrial processes and the importance of understanding protein folding and stability have led to several attempts to predict and quantify the effect of every possible amino acid exchange (mutation) on the thermostability of proteins. In this article we describe a knowledge-based discrimination function that acts as a fast and reliable guide in protein engineering and optimization. The function used consists of two parts, a pairwise energy function based on a distance- and direction-dependent atomic description of the amino acid environment, and a torsion angle energy function. In a first step a training set of 11 proteins including 646 mutant proteins with experimentally determined thermostability was used to optimize the knowledge-based energy functions. The resulting potential function was then tested using a test mutant database consisting of 918 various point mutations introduced in 27 proteins. The best correlation coefficient obtained for the experimental data and the predicted thermostability for the training set is r = 0.81 (561 data points). A total of 76% of the mutations could be predicted correctly as being either stabilizing or destabilizing. The results for the test set are r = 0.74 (747 data points) and 72%, respectively. The global correlation over the combined data (1308 mutants) obtained is 0.78.

Figure 1.

Calculated stabilization energies Δ ΔG_calculated for the training data set with 646 data points compared to the experimental values Δ ΔG_experiment. The linear regression line was obtained for 561 data points after the outliers (> 2σ) were discarded (the equation is shown in the figure). Its correlation coefficient is r_cor = 0.81. The discarded mutations are indicated as squares, and the other mutants are shown with rhombic symbols.

Figure 2.

Calculated stabilization energies Δ ΔG_calculated for the test data set with 918 data points compared to the experimental values Δ ΔG_experiment. The linear regression line was obtained for 747 data points after the outliers (> 2σ) were discarded (the equation is shown in the figure). Its correlation coefficient is r_cor = 0.74. The discarded mutations are indicated as squares, and the other mutants are shown with rhombic symbols.