Accurate modeling of peptide-MHC structures with AlphaFold

Area of Science:

• Structural immunology
• Computational biology
• Immunoinformatics

Background:

• Major histocompatibility complex (MHC) proteins are crucial for T-cell surveillance by presenting peptides on cell surfaces.
• Accurate in silico prediction of peptide-MHC interactions is vital for understanding immune responses and developing immunotherapies.
• Existing computational methods face limitations in predicting peptide presentation and T-cell receptor recognition.

Approach:

• An AlphaFold-based computational pipeline was developed to predict the three-dimensional structures of peptide-MHC complexes.
• The pipeline was validated for both class I and class II Major histocompatibility complex molecules.
• The method's performance was compared against existing computational tools for accuracy and precision.

Key Points:

• The AlphaFold-based pipeline achieves high accuracy in predicting peptide-MHC complex structures.
• The method demonstrates superior modeling precision for class I MHC and improved peptide register prediction for class II MHC compared to current tools.
• The developed pipeline shows promise for enhancing the prediction of peptide-MHC binding affinities.

Conclusions:

• This novel computational approach offers a significant advancement in modeling peptide-MHC complexes.
• The pipeline provides a powerful tool for structural immunology research, aiding in the understanding of T-cell recognition.
• Future applications include improving the prediction of peptide-MHC binding, with implications for vaccine design and cancer immunotherapy.