Prediction of MHC II antigen peptide-T cell receptors binding based on foundation model.
10.7507/1001-5515.202405024
- Author:
Minrui XU
1
;
Siwen ZHANG
2
;
Manman LU
3
;
Yuan GAO
1
;
Menghuan ZHANG
4
;
Yong LIN
1
;
Lu XIE
3
Author Information
1. School of Health Science and Engineering, University of Shanghai for Science and Technology, Shanghai 200093, P. R. China.
2. Shanghai Institute for Biomedical and Pharmaceutical Technologies, Fudan University, Shanghai 200237, P. R. China.
3. Shanghai-MOST Key Laboratory of Health and Disease Genomics, Shanghai Institute for Biomedical and Pharmaceutical Technologies, Shanghai 200237, P. R. China.
4. School of Life Science and Technology, Tongji University, Shanghai 200092, P. R. China.
- Publication Type:Journal Article
- Keywords:
Foundation model;
Immunotherapy;
Prediction of MHC Ⅱ antigen peptide-T cell receptors binding;
ProtT5 model
- MeSH:
Receptors, Antigen, T-Cell/immunology*;
Histocompatibility Antigens Class II/metabolism*;
Humans;
Neural Networks, Computer;
Peptides/metabolism*;
Protein Binding
- From:
Journal of Biomedical Engineering
2024;41(6):1243-1249
- CountryChina
- Language:Chinese
-
Abstract:
The specific binding of T cell receptors (TCRs) to antigenic peptides plays a key role in the regulation and mediation of the immune process and provides an essential basis for the development of tumour vaccines. In recent years, studies have mainly focused on TCR prediction of major histocompatibility complex (MHC) class I antigens, but TCR prediction of MHC class II antigens has not been sufficiently investigated and there is still much room for improvement. In this study, the combination of MHC class II antigen peptide and TCR prediction was investigated using the ProtT5 grand model to explore its feature extraction capability. In addition, the model was fine-tuned to retain the underlying features of the model, and a feed-forward neural network structure was constructed for fusion to achieve the prediction model. The experimental results showed that the method proposed in this study performed better than the traditional methods, with a prediction accuracy of 0.96 and an AUC of 0.93, which verifies the effectiveness of the model proposed in this paper.
