AUTO-MUTE: web-based tools for predicting stability changes in proteins due to single amino acid replacements

Area of Science:

• Computational biology
• Biochemistry
• Bioinformatics

Background:

• Understanding protein stability is crucial for protein engineering and drug design.
• Predicting the impact of mutations on protein stability is a significant challenge in molecular biology.

Purpose of the Study:

• To develop accurate and accessible web-based tools for predicting stability changes in proteins upon single residue substitutions.
• To integrate computational mutagenesis with machine learning for enhanced prediction capabilities.

Main Methods:

• Development of three web-based tools utilizing supervised classification and regression algorithms.
• Application of a computational mutagenesis methodology based on a four-body statistical potential to represent mutant proteins.
• Integration of energy-based and machine learning approaches for attribute representation.

Main Results:

• The developed models achieved high accuracies, ranging from 87% to 94%, on independent mutant test sets.
• The web servers provide predictions for stability changes upon single residue substitutions in proteins with known native structures.
• The tools are freely accessible online with detailed datasets, documentation, and performance results.

Conclusions:

• The developed web-based tools offer a novel and accurate approach for predicting protein stability changes due to single residue substitutions.
• The integration of computational mutagenesis and machine learning provides a powerful framework for analyzing protein variants.
• These tools can significantly aid researchers in protein engineering, drug discovery, and understanding protein function.