Research Article
Deep Learning Models for Vaccinology: Predicting T-cell Epitopes in C57BL/6 Mice
@INPROCEEDINGS{10.1007/978-3-031-44668-9_14, author={Zitian Zhen and Yuhe Wang and Derin B. Keskin and Vladimir Brusic and Lou Chitkushev and Guang Lan Zhang}, title={Deep Learning Models for Vaccinology: Predicting T-cell Epitopes in C57BL/6 Mice}, proceedings={Computer Science and Education in Computer Science. 19th EAI International Conference, CSECS 2023, Boston, MA, USA, June 28--29, 2023, Proceedings}, proceedings_a={CSECS}, year={2023}, month={10}, keywords={Bioinformatics System Deep Learning Prediction Tool T-cell Epitope MHC Binding C57BL/6 Mice}, doi={10.1007/978-3-031-44668-9_14} }- Zitian Zhen
Yuhe Wang
Derin B. Keskin
Vladimir Brusic
Lou Chitkushev
Guang Lan Zhang
Year: 2023
Deep Learning Models for Vaccinology: Predicting T-cell Epitopes in C57BL/6 Mice
CSECS
Springer
DOI: 10.1007/978-3-031-44668-9_14
Abstract
The C57 Black 6 (C57BL/6) mice are one the earliest and most widely used inbred laboratory animals in biomedical research and vaccine development. We propose developing a bioinformatics system for the identification of T-cell epitopes in C57BL/6 mice by integrating multiple contributing factors critical to the antigen processing and recognition pathway. The interaction between peptides and MHC molecules is a highly specific step in the antigen processing pathway and T-cell mediated immunity. As the first step of the project, we built a computational tool for predicting MHC class I binding peptides for the C57BL/6 mice. Utilizing deep learning methods, we trained and rigorously validated the prediction models using naturally eluted MHC ligands. The prediction models are of high accuracy.
