Table1_Immune-related gene signature to predict TACE refractoriness in patients with hepatocellular carcinoma based on artificial neural network.XLSX

Background: Transarterial chemoembolization (TACE) is the standard treatment option for intermediate-stage hepatocellular carcinoma (HCC), while response varies among patients. This study aimed to identify novel immune-related genes (IRGs) and establish a prediction model for TACE refractoriness in HCC patients based on machine learning methods.
Methods: Gene expression data were downloaded from GSE104580 dataset of Gene Expression Omnibus (GEO) database, differential analysis was first performed to screen differentially expressed genes (DEGs). The least absolute shrinkage and selection operator (LASSO) regression analysis was performed to further select significant DEGs. Weighted gene co-expression network analysis (WGCNA) was utilized to build a gene co-expression network and filter the hub genes. Final signature genes were determined by the intersection of LASSO analysis results, WGCNA results and IRGs list. Based on the above results, the artificial neural network (ANN) model was constructed in the training cohort and verified in the validation cohort. Receiver operating characteristics (ROC) analysis was used to assess the prediction accuracy. Correlation of signature genes with tumor microenvironment scores, immune cells and immune checkpoint molecules were further analyzed. The tumor immune dysfunction and exclusion (TIDE) score was used to evaluate the response to immunotherapy.
Results: One hundred and forty-seven samples were included in this study, which was randomly divided into the training cohort (n = 103) and validation cohort (n = 44). In total, 224 genes were identified as DEGs. Further LASSO regression analysis screened out 25 genes from all DEGs. Through the intersection of LASSO results, WGCNA results and IRGs list, S100A9, TREM1, COLEC12, and IFIT1 were integrated to construct the ANN model. The areas under the curves (AUCs) of the model were .887 in training cohort and .765 in validation cohort. The four IRGs also correlated with tumor microenvironment scores, infiltrated immune cells and immune checkpoint genes in various degrees. Patients with TACE-Response, lower expression of COLEC12, S100A9, TREM1 and higher expression of IFIT1 had better response to immunotherapy.
Conclusion: This study constructed and validated an IRG signature to predict the refractoriness to TACE in patients with HCC, which may have the potential to provide insights into the TACE refractoriness in HCC and become the immunotherapeutic targets for HCC patients with TACE refractoriness.

背景：经动脉化疗栓塞术（Transarterial chemoembolization, TACE）是中期肝细胞癌（hepatocellular carcinoma, HCC）的标准治疗方案，但不同患者的治疗应答存在个体差异。本研究旨在筛选新型免疫相关基因（immune-related genes, IRGs），并基于机器学习方法构建肝细胞癌患者经动脉化疗栓塞术难治性的预测模型。
方法：从基因表达综合数据库（Gene Expression Omnibus, GEO）的GSE104580数据集下载基因表达数据，首先开展差异分析以筛选差异表达基因（differentially expressed genes, DEGs）。随后进行最小绝对收缩和选择算子（least absolute shrinkage and selection operator, LASSO）回归分析，进一步筛选具有统计学意义的差异表达基因。采用加权基因共表达网络分析（weighted gene co-expression network analysis, WGCNA）构建基因共表达网络并筛选核心枢纽基因。通过将LASSO分析结果、WGCNA分析结果与免疫相关基因列表取交集，确定最终的特征基因。基于上述结果，在训练队列中构建人工神经网络（artificial neural network, ANN）模型，并在验证队列中完成模型验证。采用受试者工作特征（Receiver operating characteristics, ROC）分析评估模型的预测准确率。进一步分析特征基因与肿瘤微环境评分、浸润免疫细胞及免疫检查点分子的相关性。使用肿瘤免疫功能异常与排斥（tumor immune dysfunction and exclusion, TIDE）评分评估患者的免疫治疗应答情况。
结果：本研究共纳入147例样本，按随机分配原则分为训练队列（n=103）与验证队列（n=44）。最终共筛选出224个差异表达基因。经LASSO回归分析，从全部差异表达基因中筛选出25个候选基因。通过将LASSO分析结果、WGCNA分析结果与免疫相关基因列表取交集，最终整合S100A9、TREM1、COLEC12及IFIT1构建人工神经网络模型。该模型在训练队列与验证队列中的曲线下面积（areas under the curves, AUCs）分别为0.887与0.765。上述4个免疫相关基因均在不同程度上与肿瘤微环境评分、浸润免疫细胞及免疫检查点基因存在相关性。在经动脉化疗栓塞术应答患者中，COLEC12、S100A9、TREM1低表达且IFIT1高表达的患者对免疫治疗的应答效果更佳。
结论：本研究构建并验证了一款免疫相关基因特征模型，可用于预测肝细胞癌患者的经动脉化疗栓塞术难治性，该模型或可为肝细胞癌经动脉化疗栓塞术难治性的机制研究提供新思路，并有望成为经动脉化疗栓塞术难治性肝细胞癌患者的免疫治疗靶点。