免疫检查点阻断 (ICB) 彻底改变了癌症治疗，但决定患者反应的机制仍知之甚少。在这里，我们使用机器学习来预测种系和体细胞生物标志物的 ICB 反应，并解释学习的模型以揭示推动卓越结果的推定机制。即使 I 类主要组织相容性复合体 (MHC-I) 存在缺陷，滤泡辅助 T 细胞浸润较高的患者也能产生反应。进一步的研究发现，当反应依赖于 MHC-I 和 MHC-II 新抗原时，肿瘤中的 ICB 反应不同。尽管缓解率相似，但 MHC-II 依赖的缓解与明显更长的持久临床获益相关（发现：中位 OS=63.6 个月与 34.5 个月 P=0.0074；验证：中位 OS=37.5 个月与 33.1 个月，P=0.040）。肿瘤免疫微环境的特征反映了 MHC 新抗原依赖性，免疫检查点分析表明 LAG3 是 MHC-II 的潜在靶点，但不是 MHC-I 依赖性反应的潜在靶点。这项研究强调了可解释的机器学习模型在阐明治疗反应的生物学基础方面的价值。

Immune Checkpoint Blockade (ICB) has revolutionized cancer treatment, however the mechanisms determining patient response remain poorly understood. Here, we used machine learning to predict ICB response from germline and somatic biomarkers and interpreted the learned model to uncover putative mechanisms driving superior outcomes. Patients with higher infiltration of T follicular helper cells had responses even in the presence of defects in the class-I Major Histocompatibility Complex (MHC-I). Further investigation uncovered different ICB responses in tumors when responses were reliant on MHC-I versus MHC-II neoantigens. Despite similar response rates, MHC-II reliant responses were associated with significantly longer durable clinical benefit (Discovery: Median OS=63.6 vs. 34.5 months P=0.0074; Validation: Median OS=37.5 vs. 33.1 months, P=0.040). Characteristics of the tumor immune microenvironment reflected MHC neoantigen reliance, and analysis of immune checkpoints revealed LAG3 as a potential target in MHC-II but not MHC-I reliant responses. This study highlights the value of interpretable machine learning models in elucidating the biological basis of therapy responses.