Predicting the Effect of Single and Multiple Mutations on Protein Structural Stability

Abstract

Predicting how a point mutation alters a protein’s stability can guide pharmaceutical drug design initiatives which aim to counter the effects of serious diseases. Conducting mutagenesis studies in physical proteins can give insights about the effects of amino acid substitutions, but such wet-lab work is prohibitive due to the time as well as financial resources needed to assess the effect of even a single amino acid substitution. Computational methods for predicting the effects of a mutation on a protein structure can complement wet-lab work, and varying approaches are available with promising accuracy rates. In this work we compare and assess the utility of several machine learning methods and their ability to predict the effects of single and double mutations. We in silico generate mutant protein structures, and compute several rigidity metrics for each of them. We use these as features for our Support Vector Regression (SVR), Random Forest (RF), and Deep Neural Network (DNN) methods. We validate the predictions of our in silico mutations against experimental ΔΔG stability data, and attain Pearson Correlation values upwards of 0.71 for single mutations, and 0.81 for double mutations. We perform ablation studies to assess which features contribute most to a model’s success, and also introduce a voting scheme to synthesize a single prediction from the individual predictions of the three models.

Robust Prediction of Single and Multiple Point Protein Mutations Stability Changes

“…This poor performance is specially found on training datasets, which suggests that their hyper-parameter tuning processes normally underfits, rather than overfits their performance, in contrast with other methods such as Random Forest or Support Vector Machines. Consequently, semi-supervised methods or "a priori" parametrization of the model seems to be the best fit when approaching this problem, which agrees with Dehghanpoor et al [28]. Support Vector Machines.…”

“…Capriotti et al [9] and Chen et al [10] used Support Vector Machines to infer the sign of the stability change for a protein upon a single-site mutation. Dehghanpoor et al [28] predicted the effect of single site and multiple site mutations using Support Vector Machines and Random Forest. Furthermore, data from amino acid replacements that are tolerated within members of the same protein family were used to devise stability scores and implemented in an online web server [29][30][31].…”

“…Li et al [36] developed a Random Forest algorithm in order to predict stability changes due to single and multiple amino acid substitutions. This method was further improved by Dehghanpoor et al [28] by combining it with protein rigidity calculations to boost the prediction performance.…”

“…Remarkably, our methodology is distinguished from others since our machine learning-based method does not require the computation of energy or other physical properties. Therefore, like in the work of Dehghanpoor et al [28], it is possible to predict the effect of a mutation without the need of biophysical information and the method does not depend on hydrogen bond energies, van der Waals forces and generally no force field is needed. Our present study extends past work in this field by introducing the concepts of distribution of mutation energy and its uncertainty and by parametrization of a Neural Network in order to accurately predict the observed energy.…”

Assessing Protein-Drug Resistance Due to Mutations via a Rigidity Analysis in silico Approach

“…The output of rigidity analysis identifies atoms that are part of rigid clusters, which vary in size from just a few atoms, to the largest rigid cluster (LRC), which may encompass the majority of the atoms in a protein. In prior work we used rigidity analysis in combination with machine learning models to predict with almost 80% accuracy the effects of mutations on protein stability [5]. Most recently we have integrated rigidity analysis into an approach that reasons about mutations to a ligand, to infer which atoms of a drug are most responsible for the effect that the drug has on a protein target [20].…”