Sears Timothy, Pagadala Meghana, Castro Andrea, Lee Ko-Han, Kong JungHo, Tanaka Kairi, Lippman Scott, Zanetti Maurizio, Carter Hannah
Bioinformatics and Systems Biology Program, University of California San Diego, La Jolla, CA USA.
Biomedical Sciences Program, University of California San Diego, La Jolla, CA,, USA.
bioRxiv. 2024 Jan 15:2024.01.12.575430. doi: 10.1101/2024.01.12.575430.
Immune Checkpoint Blockade (ICB) has revolutionized cancer treatment, however 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 T follicular helper infiltrates were robust to defects in the class-I Major Histocompatibility Complex (MHC-I). Further investigation uncovered different ICB responses in MHC-I versus MHC-II neoantigen reliant tumors across patients. 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.
免疫检查点阻断（ICB）彻底改变了癌症治疗方式，然而，决定患者反应的机制仍知之甚少。在此，我们使用机器学习从种系和体细胞生物标志物预测ICB反应，并解读所学习的模型以揭示驱动卓越疗效的假定机制。具有较高T滤泡辅助细胞浸润的患者对I类主要组织相容性复合体（MHC-I）缺陷具有较强的耐受性。进一步研究发现，不同患者的MHC-I与MHC-II新抗原依赖性肿瘤对ICB的反应不同。尽管反应率相似，但MHC-II依赖性反应与显著更长的持久临床获益相关（发现：中位总生存期=63.6个月对34.5个月，P=0.0074；验证：中位总生存期=37.5个月对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，对免疫检查点的分析显示，LAG3是MHC-II依赖性反应而非MHC-I依赖性反应的潜在靶点。本研究强调了可解释机器学习模型在阐明治疗反应生物学基础方面的价值。
