Xu Ruiling, Shao Jing, Liu Jingyang, Qu Bo, Liu Jing
Department of Gastroenterology, Second Affiliated Hospital of Harbin Medical University, Harbin, China.
J Gastrointest Oncol. 2024 Aug 31;15(4):1836-1846. doi: 10.21037/jgo-24-93. Epub 2024 Aug 22.
Pancreatic ductal adenocarcinoma (PDAC) is a highly fatal, aggressive cancer due to limited response chemotherapy. The tumor microenvironment (TME) has emerged as a key player in the development of chemoresistance and in malignant progression. In this study, we hypothesized that chemotherapy response is predictable by chemotherapy-related cell types and their differentially expressed genes (DEGs).
DEGs of chemoresistance cell types were identified via single cell analysis and Wilcoxon test. A chemotherapy response signature was established using a random forest model and validated with public datasets. Bulk cell fraction was analyzed using BayesPrism algorithms. Log-rank test was used to analyze survival of PDAC patients.
We found that natural killer (NK) cells, myeloid cells, and erythroid cells were highly infiltrated in chemo-resistant TME. A total of 36 chemoresistance-related DEGs of chemo-resistant cells were identified in chemo-resistant PDAC. Functional enrichment analysis showed that chemoresistance upregulated various inflammation-related pathways, including TGF-β signaling. Based on these features, we constructed a random forest model to predict the response and survival for PDAC patients, which accurately distinguished high-risk and chemoresistant patients with significantly poorer prognosis in both the training and independent validation datasets. Cox regression analysis indicated that predicted labels were an independent prognostic factor in PDAC. Moreover, deconvolution of TME confirmed higher infiltration levels of M2 macrophage and NK cells in predicted chemoresistance. When combined with chemotherapy response related tumor mutations, the model showed excellent ability in predicting chemotherapy response and survival.
The TME was closely associated with the chemotherapy response and prognosis of PDAC. Our TME-based random forest model predicted chemotherapy response with complementary knowledge to the response-related genetic mutations.
胰腺导管腺癌（PDAC）是一种高度致命的侵袭性癌症，因为化疗反应有限。肿瘤微环境（TME）已成为化疗耐药性发展和恶性进展的关键因素。在本研究中，我们假设化疗反应可通过化疗相关细胞类型及其差异表达基因（DEG）来预测。
通过单细胞分析和Wilcoxon检验鉴定化疗耐药细胞类型的DEG。使用随机森林模型建立化疗反应特征，并通过公共数据集进行验证。使用BayesPrism算法分析细胞比例。采用对数秩检验分析PDAC患者的生存率。
我们发现自然杀伤（NK）细胞、髓样细胞和红细胞在化疗耐药的TME中高度浸润。在化疗耐药的PDAC中总共鉴定出36个与化疗耐药相关的化疗耐药细胞DEG。功能富集分析表明，化疗耐药上调了各种炎症相关途径，包括TGF-β信号通路。基于这些特征，我们构建了一个随机森林模型来预测PDAC患者的反应和生存情况，该模型在训练和独立验证数据集中均能准确区分高危和化疗耐药患者，其预后明显较差。Cox回归分析表明，预测标签是PDAC的独立预后因素。此外，TME反卷积证实了预测的化疗耐药中M2巨噬细胞和NK细胞的浸润水平较高。当与化疗反应相关的肿瘤突变相结合时，该模型在预测化疗反应和生存方面表现出优异的能力。
TME与PDAC的化疗反应和预后密切相关。我们基于TME的随机森林模型通过对反应相关基因突变的补充知识来预测化疗反应。
