AI/ML-empowered approaches for predicting T Cell-mediated immunity and beyond.

Area of Science:

• Immunology
• Computational Biology
• Structural Biology

Background:

• T cells have dual roles in immunity and autoimmunity, necessitating precise regulation of T cell receptor (TCR)-peptide/major histocompatibility complex (pMHC) interactions.
• Accurate prediction of TCR-pMHC specificity is vital for developing effective treatments for cancer, infections, and autoimmune diseases.
• Current predictive models for TCR-pMHC specificity are still in early development stages.

Purpose of the Study:

• To evaluate the potential of AlphaFold 3 (AF3) for predicting TCR epitope specificity.
• To explore the application of deep learning-based structural modeling in understanding TCR-pMHC interactions.

Main Methods:

• Utilized AlphaFold 3 for AI-driven computation of TCR-pMHC interactions.
• Assessed the accuracy of AlphaFold 3 in distinguishing valid from invalid epitopes.
• Employed in silico high-throughput processes for epitope identification.

Main Results:

• AlphaFold 3 demonstrated the capability to model TCR-pMHC interactions.
• The model showed increasing accuracy in differentiating immunogenic epitopes.
• Successfully identified potential epitopes for vaccine development and therapeutic T cell design.

Conclusions:

• Deep learning-based structural modeling, exemplified by AlphaFold 3, shows promise for generalizable TCR-pMHC interaction prediction.
• Accurate TCR-pMHC prediction models can significantly advance T-cell-mediated immunotherapy and drug design.
• Precise prediction of T-cell immunogenicity holds substantial therapeutic potential for various diseases.