Pan Chaohu, Tang Hongzhen, Wang Wei, Wu Dongfang, Luo Haitao, Xu Libin, Lin Xue-Jia
The First Affiliated Hospital, Jinan University, Guangzhou, Guangdong, China.
Zhuhai Institute of Translational Medicine, Zhuhai People's Hospital (Zhuhai Hospital Affiliated with Jinan University), Jinan University, Zhuhai, Guangdong, China.
Front Oncol. 2023 Jan 17;12:1077477. doi: 10.3389/fonc.2022.1077477. eCollection 2022.
Programmed death ligand 1 (PD-L1) and tumor mutation burden (TMB) have been developed as biomarkers for the treatment of immune checkpoint inhibitors (ICIs). However, some patients who are TMB-high or PD-L1-high remained resistant to ICIs therapy. Therefore, a more clinically applicable and effective model for predicting the efficacy of ICIs is urgently needed.
In this study, genomic data for 466 patients with melanoma treated with ICIs from seven independent cohorts were collected and used as training and validation cohorts (training cohort n = 300, validation cohort1 n = 61, validation cohort2 n = 105). Ten machine learning classifiers, including Random Forest classifier, Stochastic Gradient Descent (SGD) classifier and Linear Support Vector Classifier (SVC), were subsequently evaluated.
The Linear SVC with a 186-gene mutation-based set was screened to construct the durable clinical benefit (DCB) model. Patients predicted to have DCB (pDCB) were associated with a better response to the treatment of ICIs in the validation cohort1 (AUC=0.838) and cohort2 (AUC=0.993). Compared with TMB and other reported genetic mutation-based signatures, the DCB model showed greater predictive power. Furthermore, we explored the genomic features in determining the benefits of ICIs treatment and found that patients with pDCB were associated with higher tumor immunogenicity.
The DCB model constructed in this study can effectively predict the efficacy of ICIs treatment in patients with melanoma, which will be helpful for clinical decision-making.
程序性死亡配体1（PD-L1）和肿瘤突变负荷（TMB）已被开发作为免疫检查点抑制剂（ICI）治疗的生物标志物。然而，一些TMB高或PD-L1高的患者对ICI治疗仍有抗性。因此，迫切需要一种更具临床适用性和有效性的模型来预测ICI的疗效。
在本研究中，收集了来自七个独立队列的466例接受ICI治疗的黑色素瘤患者的基因组数据，并用作训练和验证队列（训练队列n = 300，验证队列1 n = 61，验证队列2 n = 105）。随后评估了十种机器学习分类器，包括随机森林分类器、随机梯度下降（SGD）分类器和线性支持向量分类器（SVC）。
筛选出基于186个基因突变集的线性SVC来构建持久临床获益（DCB）模型。预测有DCB（pDCB）的患者在验证队列1（AUC = 0.838）和队列2（AUC = 0.993）中对ICI治疗的反应更好。与TMB和其他报道的基于基因突变的特征相比，DCB模型显示出更大的预测能力。此外，我们探索了决定ICI治疗获益的基因组特征，发现pDCB患者与更高的肿瘤免疫原性相关。
本研究构建的DCB模型可以有效预测黑色素瘤患者ICI治疗的疗效，这将有助于临床决策。
