Modeling functional changes to Escherichia coli thymidylate synthase upon single residue replacements: a structure-based approach

Fitness of unregulated human Ras mutants modeled by implementing computational mutagenesis and machine learning techniques

Ras proteins play a pivotal role as oncogenes by participating in diverse signaling events, including those linked to cell growth, differentiation, and proliferation. Using experimental fitness data and implementing artificial intelligence and a computational mutagenesis technique, we developed models that reliably predict fitness for all single residue mutants of H-ras proto-oncogene protein p21. The computational mutagenesis generated a feature vector of protein structural changes for each variant, and these data correlated well with fitness. Random forest classification and tree regression machine learning algorithms were implemented for training predictive models. Cross-validations were used to evaluate model performance, and control experiments were performed to assess statistical significance. Classification models revealed a balanced accuracy rate as high as 82%, with a Matthew's correlation of 0.63, and an area under ROC curve of 0.90. Similarly, regression models displayed Pearson's correlation reaching 0.79. On the other hand, control data sets led to performance values consistent with random guessing. Comparisons with several related state-of-the-art methods reflected favorably on our trained models. This H-Ras proof-of-principle study suggests a complementary approach for understanding mechanisms with which other proteins are involved in oncogenesis, including related Ras isoforms, and for providing useful insights into designing future diagnostic and treatment modalities.

Modeling transcriptional activation changes to Gal4 variants via structure-based computational mutagenesis

As a DNA binding transcriptional activator, Gal4 promotes the expression of genes responsible for galactose metabolism. The Gal4 protein from Saccharomyces cerevisiae (baker’s yeast) has become a model for studying eukaryotic transcriptional activation in general because its regulatory properties mirror those of several eukaryotic organisms, including mammals. Given the availability of a crystallographic structure for Gal4, here we implement an in silico mutagenesis technique that makes use of a four-body knowledge-based energy function, in order to empirically quantify the structural impacts associated with single residue substitutions on the Gal4 protein. These results were used to examine the structure-function relationship in Gal4 based on a recently published experimental mutagenesis study, whereby functional changes to a uniformly distributed set of 1,068 single residue Gal4 variants were obtained by measuring their transcriptional activation levels relative to wild-type. A significant correlation was observed between computed (scalar) structural effect data and measured activity values for this collection of single residue Gal4 variants. Additionally, attribute vectors quantifying position-specific environmental impacts were generated for each of the Gal4 variants via computational mutagenesis, and we implemented supervised classification and regression statistical machine learning algorithms to train predictive models of variant Gal4 activity based on these structural changes. All models performed well under cross-validation testing, with balanced accuracy reaching 91% among the classification models, and with the actual and predicted activity values displaying a correlation as high as r = 0.80 for the regression models. Reliable predictions of transcriptional activation levels for Gal4 variants that have yet to be studied can be instantly generated by submitting their respective structure-based feature vectors to the trained models for testing. Such a computational pre-screening of Gal4 variants may potentially reduce costs associated with running large-scale mutagenesis experiments.