Many groups have, thus, compiled over the years datasets of experimentally determined stability changes upon mutation, where the effect is quantified mainly as the change in thermodynamic stability, i.e., in (un)folding free energy (ΔΔGu) or as the change in melting temperature (ΔTm). Although it is not clear how large is enough, datasets likely need to properly represent all possible amino acid substitutions and cover a vast range of structural scenarios. Developing such predictive models requires sufficiently large training datasets describing the quantitative effects of mutations on protein stability. Quantitative prediction of the effects of mutations on protein stability is a yet unsolved problem of key relevance in structural biology, molecular evolution, and protein biotechnology and part of the larger problem of predicting the phenotypic effects of genomic variation. We leave our interactive interface for analysis available online at so that users can further explore the dataset and baseline predictions, possibly serving as a tool useful in the context of structural biology and protein biotechnology research and as material for education in protein biophysics. Based on these observations, additional analyses, and a review of recent literature, we propose recommendations for developers of stability prediction methods and for efforts aimed at improving the datasets used for training. The corrections are very different for each specific case and arise from fine structural details which are not well represented in the dataset and which, despite appearing reasonable upon visual inspection of the structures, are hard to encode and parametrize. We pose that the ΔTm predictions of our network, and also likely those of other programs, account only for a baseline-like general effect of each type of amino acid substitution which then requires substantial corrections to reproduce the actual stability changes. After examining the composition of this dataset to discuss imbalances and biases, we inspect several of its entries assisted by an online app for data navigation and structure display and aided by a neural network that predicts ΔTm with accuracy close to that of programs available to this end. Here, we review these and other issues by analyzing one of the most detailed, carefully curated datasets of melting temperature change (ΔTm) upon mutation for proteins with high-resolution structures. Many articles discuss the limitations of prediction methods and of the datasets used to train them, which result in low reliability for actual applications despite globally capturing trends. Predicting the effects of mutations on protein stability is a key problem in fundamental and applied biology, still unsolved even for the relatively simple case of small, soluble, globular, monomeric, two-state-folder proteins.
0 kommentar(er)
