RoseTTAFold diffusion-guided short peptide design: a case study of binders against Keap1/Nrf2

Area of Science:

• Computational biology
• Drug discovery
• Bioinformatics

Background:

• The Keap1/Nrf2 pathway is crucial for cellular antioxidant response.
• Designing targeted peptide therapeutics remains a challenge.

Purpose of the Study:

• To develop a computational framework for accelerated discovery of bioactive peptides.
• To design peptides targeting specific binding sites in Keap1 (Kelch-like ECH-associated protein 1).

Main Methods:

• Utilized RFdiffusion for protein design and ProteinMPNN for sequence optimization.
• Integrated machine learning models to predict peptide properties (toxicity, stability, allergenicity).
• Employed molecular dynamics simulations for validation of top peptide candidates.

Main Results:

• Identified eight high-affinity peptide candidates with favorable biophysical properties.
• Validated strong binding interactions and structural stability of designed peptides.
• Demonstrated the framework's efficacy using Keap1 as a target protein.

Conclusions:

• The integrated computational framework enables rapid design of therapeutic peptides.
• The modular approach is adaptable for various protein targets in drug development.
• This methodology significantly enhances the potential for new drug discovery.