Search

Motivation It has been proven that only a small fraction of the neoantigens presented by major histocompatibility complex (MHC) class I molecules on the cell surface can elicit T cells. This restriction can be attributed to the binding specificity of T cell receptor (TCR) and peptide-MHC complex (pMHC). Computational prediction of T cells binding to neoantigens is a challenging and unresolved task. Results In this paper, we proposed an attention-aware contrastive learning model, ATMTCR, to infer the TCR–pMHC binding specificity. For each TCR sequence, we used a transformer encoder to transform it to latent representation, and then masked a percentage of amino acids guided by attention weights to generate its contrastive view. Compared to fully-supervised baseline model, we verified that contrastive learning-based pretraining on large-scale TCR sequences significantly improved the prediction performance of downstream tasks. Interestingly, masking a percentage of amino acids with low attention weights yielded best performance compared to other masking strategies. Comparison experiments on two independent datasets demonstrated our method achieved better performance than other existing algorithms. Moreover, we identified important amino acids and their positional preference through attention weights, which indicated the potential interpretability of our proposed model. [ABSTRACT FROM AUTHOR]

Summary: Ageing dramatically affects number and function of both innate and adaptive arms of immune system, particularly T cell subsets, contributing to reduced vaccination efficacy, decreased resistance to infections and increased prevalence of cancer in older people. In the present paper, we analysed the age‐related changes in the absolute number of lymphocytes in 214 Sicilian subjects, and in the percentages of T and natural killer (NK) cells in a subcohort of donors. We compared these results with the immunophenotype of the oldest living Italian supercentenarian (aged 111 years). The results were also sorted by gender. The correlation between number/percentage of cells and age in all individuals. and separately in males and females, was examined using a simple linear regression analysis. We did not record the increase in the rate of inversion of the CD4/CD8 ratio, frequently reported as being associated with ageing in literature. Our observation was the direct consequence of a flat average trend of CD4+ and CD8+ T cell percentages in ageing donors, even when gender differences were included. Our results also suggest that CD4+ and CD8+ subsets are not affected equally by age comparing females with males, and we speculated that gender may affect the response to cytomegalovirus (CMV) infection. The supercentenarian showed a unique immunophenotypic signature regarding the relative percentages of her T cell subsets, with CD4+ and CD8+ T cell percentages and CD4+ naive T cell values in line with those recorded for the octogenarian subjects. This suggests that the supercentenarian has a naive 'younger' T cell profile comparable to that of a >80‐year‐old female. [ABSTRACT FROM AUTHOR]