Dongsup Kim

TAPAS: Learned integration of AlphaFold3 confidence and geometric features for TCR-pMHC binding prediction

TAPAS integrates AlphaFold3 confidence and geometric features with sequence embeddings to improve TCR-pMHC binding prediction, outperforming individual metrics across benchmarks.

TSpred: a robust prediction framework for TCR-epitope interactions based on an ensemble deep learning approach using paired chain TCR sequence data

TSpred is a deep learning framework for predicting TCR-epitope interactions using paired chain TCR data, achieving state-of-the-art performance in both seen and unseen epitope predictions.