TTAgP

TTAgP predicts tumor-specific antigens presented by MHC class I molecules that can be recognized by T cells to support cancer immunotherapy research.

Key Features:

• Algorithmic approach: TTAgP uses the Random Forest algorithm for peptide classification.
• Training dataset: The predictive model was trained on a dataset of 922 peptides annotated for presentation by MHC class I molecules.
• Focus on MHC class I: Predictions specifically target peptides presented by MHC class I to identify T cell-recognized antigens.
• Validation metrics: Model performance during validation was reported as sensitivity = 0.89, specificity = 0.92, accuracy = 0.90, and Matthews correlation coefficient (MCC) = 0.79.

Scientific Applications:

• Antigen discovery: Identification of tumor-specific peptides that are potential targets of T cell responses.
• Vaccine design: Informing the selection of candidate peptides for personalized cancer vaccine development.
• Peptide-based therapeutics: Supporting design of peptide-based therapies aimed at eliciting cytotoxic T cell responses against tumors.

Methodology:

Random Forest classification trained on 922 peptides annotated for MHC class I presentation, with model validation reporting sensitivity = 0.89, specificity = 0.92, accuracy = 0.90, and MCC = 0.79.