Department of Medical Oncology, West German Cancer Center, University Hospital Essen, University Duisburg-Essen, Hufelandstrasse 55, 45122 Essen, Germany; Division of Thoracic Oncology, University Medicine Essen - Ruhrlandklinik, University Duisburg-Essen, Tüschener Weg 40, 45239 Essen, Germany; Genome Informatics, Institute of Human Genetics, University Hospital Essen, University Duisburg -Essen, Hufelandstrasse 55, 45122 Essen, Germany.
Institute of Pathology, West German Cancer Center, University Hospital Essen, University Duisburg-Essen, Hufelandstrasse 55, 45122 Essen, Germany.
Eur J Cancer. 2020 Nov;140:76-85. doi: 10.1016/j.ejca.2020.09.015. Epub 2020 Oct 12.
Current predictive biomarkers for PD-1 (programmed cell death protein 1)/PD-L1 (programmed death-ligand 1)-directed immunotherapy in non-small cell lung cancer (NSCLC) mostly focus on features of tumour cells. However, the tumour microenvironment and immune context are expected to play major roles in governing therapy response. Against this background, we set out to apply context-sensitive feature selection and machine learning approaches on expression profiles of immune-related genes in diagnostic biopsies of patients with stage IV NSCLC.
RNA expression levels were determined using the NanoString nCounter platform in formalin-fixed paraffin-embedded tumour biopsies obtained during the diagnostic workup of stage IV NSCLC from two thoracic oncology centres. A 770-gene panel covering immune-related genes and control genes was used. We applied supervised machine learning methods for feature selection and generation of predictive models.
Feature selection and model creation were based on a training cohort of 55 patients with recurrent NSCLC treated with PD-1/PD-L1 antibody therapy. Resulting models identified patients with superior outcomes to immunotherapy, as validated in two subsequently recruited, separate patient cohorts (n = 67, hazard ratio = 0.46, p = 0.035). The predictive information obtained from these models was orthogonal to PD-L1 expression as per immunohistochemistry: Selecting by PD-L1 positivity at immunohistochemistry plus model prediction identified patients with highly favourable outcomes. Independence of PD-L1 positivity and model predictions were confirmed in multivariate analysis. Visualisation of the models revealed the predictive superiority of the entire 7-gene context over any single gene.
Using context-sensitive assays and bioinformatics capturing the tumour immune context allows precise prediction of response to PD-1/PD-L1-directed immunotherapy in NSCLC.
目前针对非小细胞肺癌（NSCLC）的 PD-1（程序性细胞死亡蛋白 1）/PD-L1（程序性死亡配体 1）导向免疫疗法的预测生物标志物主要集中在肿瘤细胞的特征上。然而，肿瘤微环境和免疫背景有望在控制治疗反应方面发挥重要作用。在此背景下，我们着手应用上下文敏感特征选择和机器学习方法对晚期 NSCLC 患者诊断性活检中的免疫相关基因表达谱进行分析。
使用两个胸肿瘤学中心在诊断晚期 NSCLC 过程中获得的福尔马林固定石蜡包埋肿瘤活检标本，通过 NanoString nCounter 平台测定 RNA 表达水平。使用涵盖免疫相关基因和对照基因的 770 基因芯片。我们应用监督机器学习方法进行特征选择和预测模型的生成。
特征选择和模型创建是基于 55 例接受 PD-1/PD-L1 抗体治疗的复发性 NSCLC 患者的训练队列。随后在两个招募的独立患者队列（n=67）中验证了这些模型，结果表明这些模型可以识别出免疫治疗效果更好的患者（风险比=0.46，p=0.035）。从这些模型中获得的预测信息与免疫组化检测的 PD-L1 表达是正交的：根据免疫组化检测的 PD-L1 阳性加上模型预测来选择，可以识别出具有高度有利预后的患者。多变量分析证实了 PD-L1 阳性和模型预测的独立性。模型的可视化显示，整个 7 基因背景的预测优势超过任何单个基因。
使用上下文敏感的检测和生物信息学方法来捕获肿瘤免疫背景，可以精确预测 NSCLC 对 PD-1/PD-L1 导向免疫疗法的反应。
