Predicting protein stability changes upon mutation using a simple orientational potential.

Area of Science:

• Biophysics
• Computational Biology
• Protein Engineering

Background:

• Accurate prediction of protein stability changes upon mutation is essential for protein engineering, drug design, and understanding disease mechanisms.
• Existing methods often struggle with accuracy, efficiency, and overfitting due to data limitations.

Purpose of the Study:

• To develop a novel, accurate, and efficient method for predicting protein stability changes due to mutations.
• To validate the method's performance against state-of-the-art approaches using independent benchmark datasets.

Main Methods:

• Utilized a simple residue-based orientational potential focusing on three backbone atoms.
• Parametrized 12 amino acid-dependent weights via cross-validation on a curated dataset, minimizing biases.
• Applied the KORPM (Knowledge-Oriented Residue Potential Model) method for stability prediction.

Main Results:

• KORPM achieved high accuracy in predicting mutational effects on an independent benchmark dataset.
• The method demonstrated superior performance compared to state-of-the-art methods, showing the lowest RMSE and highest correlation with experimental ΔΔG.
• KORPM exhibited robust performance for both direct and reverse mutations and proved efficient with reduced overfitting.

Conclusions:

• The KORPM method offers a computationally efficient and accurate approach for predicting protein mutational effects on stability.
• This method holds promise for advancing protein engineering, disease mechanism studies, and drug resistance research.
• The approach performs competitively despite limitations in experimental mutation data, highlighting its potential for broader applications.