Neoantigens are promising targets for immunotherapy by eliciting immune response and removing cancer cells with high specificity, low toxicity and ease of personalization. However, identifying effective neoantigens remains difficult because of the complex interactions among T cell receptors, antigens and human leucocyte antigen sequences. In this study, we integrate important physical and biological priors with the Transformer model and propose the physics-inspired sliding transformer (PISTE). In PISTE, the conventional, data-driven attention mechanism is replaced with physics-driven dynamics that steers the positioning of amino acid residues along the gradient field of their interactions. This allows navigating the intricate landscape of biosequence interactions intelligently, leading to improved accuracy in T cell receptor–antigen–human leucocyte antigen binding prediction and robust generalization to rare sequences. Furthermore, PISTE effectively recovers residue-level contact relationships even in the absence of three-dimensional structure training data. We applied PISTE in a multitude of immunogenic tumour types to pinpoint neoantigens and discern neoantigen-reactive T cells. In a prospective study of prostate cancer, 75% of the patients elicited immune responses through PISTE-predicted neoantigens.

新抗原具有高特异性、低毒性和易于个性化的特点，通过引发免疫反应和去除癌细胞，成为免疫治疗的有希望的靶标。然而，由于 T 细胞受体、抗原和人类白细胞抗原序列之间复杂的相互作用，识别有效的新抗原仍然很困难。在这项研究中，我们将重要的物理和生物先验与 Transformer 模型相结合，并提出了受物理启发的滑动变压器（PISTE）。在 PISTE 中，传统的数据驱动的注意力机制被物理驱动的动力学所取代，该动力学引导氨基酸残基沿着其相互作用的梯度场定位。这使得能够智能地导航生物序列相互作用的复杂景观，从而提高T细胞受体-抗原-人白细胞抗原结合预测的准确性以及对稀有序列的稳健泛化。此外，即使在没有三维结构训练数据的情况下，PISTE 也能有效地恢复残基级别的接触关系。我们在多种免疫原性肿瘤类型中应用 PISTE 来查明新抗原并辨别新抗原反应性 T 细胞。在一项前列腺癌前瞻性研究中，75% 的患者通过 PISTE 预测的新抗原引发了免疫反应。