Challenges in predicting stabilizing variations: An exploration

Abstract

An open challenge of computational and experimental biology is understanding the impact of non-synonymous DNA variations on protein function and, subsequently, human health. The effects of these variants on protein stability can be measured as the difference in the free energy of unfolding (ΔΔG) between the mutated structure of the protein and its wild-type form. Throughout the years, bioinformaticians have developed a wide variety of tools and approaches to predict the ΔΔG. Although the performance of these tools is highly variable, overall they are less accurate in predicting ΔΔG stabilizing variations rather than the destabilizing ones. Here, we analyze the possible reasons for this difference by focusing on the relationship between experimentally-measured ΔΔG and seven protein properties on three widely-used datasets (S2648, VariBench, Ssym) and a recently introduced one (S669). These properties include protein structural information, different physical properties and statistical potentials. We found that two highly used input features, i.e., hydrophobicity and the Blosum62 substitution matrix, show a performance close to random choice when trying to separate stabilizing variants from either neutral or destabilizing ones. We then speculate that, since destabilizing variations are the most abundant class in the available datasets, the overall performance of the methods is higher when including features that improve the prediction for the destabilizing variants at the expense of the stabilizing ones. These findings highlight the need of designing predictive methods able to exploit also input features highly correlated with the stabilizing variants. New tools should also be tested on a not-artificially balanced dataset, reporting the performance on all the three classes (i.e., stabilizing, neutral and destabilizing variants) and not only the overall results.

Keywords: machine learning; protein stability; single-point mutation; stability predictors; stabilizing variants.

FIGURE 1

Venn diagrams showing the number of shared variants among the Ssym, VariBench, S2648 and S669 datasets.

FIGURE 2

Distribution of the experimental ΔΔG values in the Ssym, S669, S2648 and VariBench datasets.

FIGURE 3

Distributions of the features. Boxplots showing the distributions of the features on the three classes. The variations are considered neutral if ΔΔG ∈[−0.5, 0.5], stabilizing if ΔΔG <−0.5 and destabilizing if ΔΔG > 0.5. For each pair of classes we computed the Mann-Whitney-Wilcoxon test two-sided to establish the difference in the distributions. The p-values are reported here in a compact way: “ns” - p > 0.05, * - 0.01 < p ≤ 0.05, ** - 1.0e−03 < p ≤ 0.01, *** - 1.0e−04 < p ≤ 1.0e−03, **** - p ≤ 1.0e−04, the actual values of the p-values are in Tab.4.