关键词： AUC, Area under the curve CIs, Confidence intervals CTL, Cytotoxic T-lymphocyte infiltration Cancer GEO, Gene Expression Omnibus GO, Gene Ontology GSEA, Gene set enrichment analysis GSVA, Gene set variation analysis HLAs, Human leukocyte antigens HRs, Hazard ratios Immunotherapy KEGG, Kyoto Encyclopedia of Genes and Genomes LASSO, Penalized logistic least absolute shrinkage and selector operation Machine learning NSCLC, Non-small cell lung cancer OS, Overall survival PCA, Principal componentanalysis PD-L1, Programmed death ligand-1 PFS, Profession-free survival RNA-seq, Transcriptome RNA sequencing ROC, receiver operating characteristic curves TCGA, The Cancer Genome Atlas TMB, Tumor mutation burden TME, Tumor immunemicroenvironment Tumor immune microenvironment WGCNA, Weighted gene co-expression network analysis lncRNA, Long non-coding RNA

来  源：   DOI：10.1016/j.heliyon.2023.e14450   PDF(Pubmed)

Abstract：
Although immunotherapy has revolutionized cancer management, most patients do not derive benefits from it. Aiming to explore an appropriate strategy for immunotherapy efficacy prediction, we collected 6251 patients\' transcriptome data from multicohort population and analyzed the data using a machine learning algorithm. In this study, we found that patients from three immune gene clusters had different overall survival when treated with immunotherapy (P < 0.001), and that these clusters had differential states of hypoxia scores and metabolism functions. The immune gene score showed good immunotherapy efficacy prediction (AUC was 0.737 at 20 months), which was well validated. The immune gene score, tumor mutation burden, and long non-coding RNA score were further combined to build a tumor immune microenvironment signature, which correlated more strongly with overall survival (AUC, 0.814 at 20 months) than when using a single variable. Thus, we recommend using the characterization of the tumor immune microenvironment associated with immunotherapy efficacy via a multi-omics analysis of cancer.
摘要：
尽管免疫疗法彻底改变了癌症管理，大多数患者并没有从中获益。旨在探索一种合适的免疫治疗疗效预测策略,我们从多队列人群中收集了6251例患者的转录组数据,并使用机器学习算法对数据进行了分析.在这项研究中,我们发现，来自三个免疫基因簇的患者在接受免疫治疗治疗时具有不同的总生存期（P<0.001），并且这些簇具有不同的缺氧评分和代谢功能状态。免疫基因评分显示良好的免疫治疗疗效预测(20个月AUC为0.737),这得到了很好的验证。免疫基因评分，肿瘤突变负荷，和长链非编码RNA评分进一步结合构建肿瘤免疫微环境特征，与总生存率的相关性更强(AUC，20个月时为0.814)，而不是使用单个变量时。因此，我们建议通过对癌症进行多组学分析,对与免疫治疗疗效相关的肿瘤免疫微环境进行表征.
公众号