THLANet: A Deep Learning Framework for Predicting TCR-pHLA Binding in Immunotherapy Applications

Abstract Adaptive immunity is a targeted immune response that enables the body to identify and eliminate foreign pathogens, playing a critical role in the anti-tumor immune response. Tumor cell expression of antigens forms the foundation for inducing this adaptive response. However, the human leukocyte antigens (HLA)-restricted recognition of antigens by T-cell receptors (TCR) limits their ability to detect all neoantigens, with only a small subset capable of activating T-cells. Accurately predicting neoantigen binding to TCR is, therefore, crucial for assessing their immunogenic potential in clinical settings. We present THLANet, a deep learning model designed to predict the binding specificity of TCR to neoantigens presented by class I HLAs. THLANet employs evolutionary scale modeling-2 (ESM-2), replacing the traditional embedding methods to enhance sequence feature representation. Using scTCR-seq data, we obtained the TCR immune repertoire and constructed a TCR-pHLA binding database to validate THLANet’s clinical potential. The model’s performance was further evaluated using clinical cancer data across various cancer types. Additionally, by analyzing divided complementarity-determining region (CDR3) sequences and simulating alanine scanning of antigen sequences, we unveiled the 3D binding conformations of TCRs and antigens. Predicting TCR-neoantigen pairing remains a significant challenge in immunology, THLANet provides accurate predictions using only the TCR sequence (CDR3 β ), antigen sequence, and class I HLA, offering novel insights into TCR-antigen interactions. Author summary T-cell receptor (TCR) recognition of peptide-human leukocyte antigen (pHLA) complexes is fundamental to immune responses. However, predicting their binding poses a significant challenge due to the intricate dynamics of their interactions. We developed THLANet, a novel deep learning model, to address this challenge by integrating the ESM-2 and Transformer-Encoder modules. This approach enhances sequence feature encoding, improving the model’s generalization capability and enabling accurate predictions of TCR-pHLA binding in clinical datasets. Using data processed from open-source databases, THLANet outperformed existing methods, such as PanPep and pMTnet, in precision-recall metrics across multiple epitopes. Additionally, THLANet demonstrates superior capability in identifying critical binding sites within 3D structures, providing structural insights into TCR-pHLA interactions. THLANet offers a robust framework for advancing immunotherapy research, with potential applications in the development of personalized medicine.