PON-Tm: A Sequence-Based Method for Prediction of Missense Mutation Effects on Protein Thermal Stability Changes

Area of Science:

• Biochemistry and Molecular Biology
• Computational Biology
• Protein Science

Background:

• Proteins are essential macromolecules with diverse biological functions.
• Predicting protein thermal stability changes from mutations is critical for biomedical and industrial applications.
• Current experimental and structure-based prediction methods have limitations in cost, labor, and computational resources.

Purpose of the Study:

• To develop a novel, sequence-based method for predicting mutation-induced changes in protein thermal stability.
• To improve the accuracy and efficiency of predicting protein thermostability variations.

Main Methods:

• Introduced PON-Tm, a novel sequence-based prediction method.
• Incorporated features from protein language models and environmental factors (pH, wild-type thermostability).
• Evaluated PON-Tm's performance against four established prediction methods.

Main Results:

• PON-Tm demonstrated superior predictive capabilities compared to existing methods.
• The method effectively utilizes sequence-based features and environmental context.
• A user-friendly web server was developed for accessibility.

Conclusions:

• PON-Tm offers a highly effective and accessible approach for predicting mutation-induced thermal stability changes.
• The developed method advances computational tools for protein engineering and research.
• The web server facilitates broader application of accurate thermostability predictions.