Identifying T cell antigen at the atomic level with graph convolutional network
Jinhao Que, Guangfu Xue, Tao Wang, Xiyun Jin, Zuxiang Wang, Yideng Cai, Wenyi Yang, Meng Luo, Qian Ding, Jinwei Zhang, Yilin Wang, Yuexin Yang, Fenglan Pang, Yi Hui, Zheng Wei, Jun Xiong, Shouping Xu, Lin Yi, Haoxiu Sun, Pingping Wang, Zhaochun Xu, Qinghua Jiang
Abstract
Precise identification of T cell antigens in silico is crucial for the development of cancer mRNA vaccines. However, current computational methods only utilize sequence-level rather than atomic level features to identify T cell antigens, which results in poor representation of those that activate immune responses. Here we propose deepAntigen, a graph convolutional network-based framework, to identify T cell antigens at the atomic level. deepAntigen achieves excellent performance both in the prediction of antigen-human leukocyte antigen (HLA) binding and antigen-T cell receptor (TCR) interactions, which can provide comprehensive guidance for identification of T cell antigens. The tumor neoantigens predicted by deepAntigen in lung, breast and pancreatic cancer patients are experimentally validated through ELISPOT assays, which detect successful activation of CD8+ T cells to release IFN-γ. Overall, deepAntigen can accurately identify T cell antigens at the atomic level, which could accelerate the development of personalized neoantigen targeted immunotherapies for cancer patients. Sequence-based algorithms to identify T cell antigens often miss targets that are activating the immune response. Here authors show that a computational method they developed, which uses atomic level features as input, can identify antigens that trigger cytokine release in cognate T cells.