Design of a Protein with Improved Thermal Stability by an Evolution-Based Generative Model

Area of Science:

• Protein Engineering
• Computational Biology
• Enzyme Inhibition

Background:

• Designing proteins with enhanced thermal stability is a significant challenge, particularly for diverse sequence variants.
• Evolutionary principles and fitness optimization offer a promising avenue for improving protein fold stability.

Purpose of the Study:

• To design artificial protein sequences for pectin methylesterase inhibitors using a generative evolution fitness model.
• To enhance the thermal stability and functionality of these protein inhibitors for industrial applications.

Main Methods:

• Utilized a generative evolution fitness model trained on natural sequence variations.
• Designed artificial sequences for pectin methylesterase inhibitors with up to 30% sequence divergence.
• Tested the functionality and thermal stability of the designed protein sequences.

Main Results:

• Six out of seven designed protein sequences were functional.
• Two of the designed sequences demonstrated improved thermal stability compared to existing inhibitors.
• The method successfully expanded the functional protein sequence space.

Conclusions:

• Generative evolution fitness modeling is an effective strategy for designing thermally stable functional proteins.
• This approach holds significant value for industrial applications, such as in food manufacturing and chemical processing.
• The developed method broadens possibilities in protein design for scientific research and biotechnology.