AlgoRxplorers | Precision in Mutation: Enhancing Drug Design with Advanced Protein Stability Prediction Tools

TL;DR

This paper introduces advanced deep learning models, especially ThermoMPNN+, that improve the prediction of protein stability changes caused by mutations, aiding drug design and understanding disease mechanisms.

Contribution

It presents a novel deep neural network approach using transfer learning and feature fusion to enhance accuracy in predicting protein stability changes, addressing data scarcity and model interpretability.

Findings

ThermoMPNN+ outperforms previous models in predicting ΔΔG.

Fusion of diverse features improves prediction accuracy.

Deep learning models can effectively interpret mutation impacts on stability.

Abstract

Predicting the impact of single-point amino acid mutations on protein stability is essential for understanding disease mechanisms and advancing drug development. Protein stability, quantified by changes in Gibbs free energy ($\Delta\Delta G$), is influenced by these mutations. However, the scarcity of data and the complexity of model interpretation pose challenges in accurately predicting stability changes. This study proposes the application of deep neural networks, leveraging transfer learning and fusing complementary information from different models, to create a feature-rich representation of the protein stability landscape. We developed four models, with our third model, ThermoMPNN+, demonstrating the best performance in predicting $\Delta\Delta G$ values. This approach, which integrates diverse feature sets and embeddings through latent transfusion techniques, aims to refine $\Delta\Delta G$ predictions and contribute to a deeper understanding of protein dynamics, potentially leading to advancements in disease research and drug discovery.