Dhuvarakesh Karthikeyan

The paper predicts pMHC-I binding stability using a protein language model, showing improved performance over existing methods and demonstrating its utility in immunogenicity and antigen-presentation modeling.

This study identifies a stable immunodominance hierarchy of tumor antigens in a murine bladder cancer model under anti-PD1 and anti-CTLA4 therapy, suggesting broad antigen selection could improve immunotherapy.

TCR-TRANSLATE generates antigen-specific TCR sequences using seq2seq models, achieving validated CDR3β sequences for unseen antigens but with limitations in validation scope and focus.

ACE optimizes ELISpot assay design by using an epitope similarity model to reduce false positives and improve efficiency.