TCRBinder: Unified pre-trained language model with paired-chain synergy for predicting T-cell receptor binding specificity (opens in new tab)

Author summary T-cell receptors (TCRs) play a central role in adaptive immunity by recognizing peptide-HLA complexes, but predicting their binding specificity has remained a formidable challenge due to sequence diversity and the cooperative action of α and β chains. Existing computational methods often rely on limited CDR3β information or single-chain inputs, which restrict predictive accuracy and generalization. To address this, we developed TCRBinder, a unified deep learning framework that ...