APTAnet: an atom-level peptide-TCR interaction affinity prediction model

Peng Xiong; Anyi Liang; Xunhui Cai; Tian Xia

doi:10.52601/bpr.2023.230037

APTAnet: an atom-level peptide-TCR interaction affinity prediction model

Biophys Rep. 2024 Feb 29;10(1):1-14. doi: 10.52601/bpr.2023.230037.

Authors

Peng Xiong¹, Anyi Liang¹, Xunhui Cai², Tian Xia^{1

2}

Affiliations

¹ School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan 430074, China.
² Institute of Pathology, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan 430030, China.

Abstract

The prediction of affinity between TCRs and peptides is crucial for the further development of TIL (Tumor-Infiltrating Lymphocytes) immunotherapy. Inspired by the broader research of drug-protein interaction (DPI), we propose an atom-level peptide-TCR interaction (PTI) affinity prediction model APTAnet using natural language processing methods. APTAnet model achieved an average ROC-AUC and PR-AUC of 0.893 and 0.877, respectively, in ten-fold cross-validation on 25,675 pairs of PTI data. Furthermore, experimental results on an independent test set from the McPAS database showed that APTAnet outperformed the current mainstream models. Finally, through the validation on 11 cases of real tumor patient data, we found that the APTAnet model can effectively identify tumor peptides and screen tumor-specific TCRs.

Keywords: Antigen; Immunotherapy; Natural language processing; TCR; Transfer learning.