Deep2Full: Computational Model for Predicting Large Complementary Fraction of Deep Mutational Scan Outcomes

Abstract

Performing deep mutational scan with site-directed mutations of all the amino acid residues in a protein may not be practical, and may not even be required, especially if predictive computational models can be developed. Computational models are however naive to cellular response in the myriads of assay-conditions. We develop a realistic paradigm of assay context-aware predictive hybrid models. Combining minimal deep mutational studies with structure, sequence information and computational models, we predict the phenotypic outcomes quantitatively. It was demonstrated with predictions on the fitness outcomes for a few proteins. Phenotypic fitness data from as few as 15% of the mutations was sufficient for reliable prediction. Interestingly, the predictive capabilities are better with a random set of mutations rather than with a systematic substitution of all amino acids to alanine, asparagine and histidine (ANH). The model can potentially be extended for predicting the phenotypic outcomes at other concentrations of the stressor, such as in dose studies.