Table_1_Cuproptosis-related gene identification and immune infiltration analysis in systemic lupus erythematosus.xlsx

BackgroundSystemic lupus erythematosus (SLE) is an autoimmune disease characterized by loss of tolerance to self-antigen, autoantibody production, and abnormal immune response. Cuproptosis is a recently reported cell death form correlated with the initiation and development of multiple diseases. This study intended to probe cuproptosis-related molecular clusters in SLE and constructed a predictive model.

MethodsWe analyzed the expression profile and immune features of cuproptosis-related genes (CRGs) in SLE based on GSE61635 and GSE50772 datasets and identified core module genes associated with SLE occurrence using the weighted correlation network analysis (WGCNA). We selected the optimal machine-learning model by comparing the random forest (RF) model, support vector machine (SVM) model, generalized linear model (GLM), and the extreme gradient boosting (XGB) model. The predictive performance of the model was validated by nomogram, calibration curve, decision curve analysis (DCA), and external dataset GSE72326. Subsequently, a CeRNA network based on 5 core diagnostic markers was established. Drugs targeting core diagnostic markers were acquired using the CTD database, and Autodock vina software was employed to perform molecular docking.
ResultsBlue module genes identified using WGCNA were highly related to SLE initiation. Among the four machine-learning models, the SVM model presented the best discriminative performance with relatively low residual and root-mean-square error (RMSE) and high area under the curve (AUC = 0.998). An SVM model was constructed based on 5 genes and performed favorably in the GSE72326 dataset for validation (AUC = 0.943). The nomogram, calibration curve, and DCA validated the predictive accuracy of the model for SLE as well. The CeRNA regulatory network includes 166 nodes (5 core diagnostic markers, 61 miRNAs, and 100 lncRNAs) and 175 lines. Drug detection showed that D00156 (Benzo (a) pyrene), D016604 (Aflatoxin B1), D014212 (Tretinoin), and D009532 (Nickel) could simultaneously act on the 5 core diagnostic markers.
ConclusionWe revealed the correlation between CRGs and immune cell infiltration in SLE patients. The SVM model using 5 genes was selected as the optimal machine learning model to accurately evaluate SLE patients. A CeRNA network based on 5 core diagnostic markers was constructed. Drugs targeting core diagnostic markers were retrieved with molecular docking performed.

背景：系统性红斑狼疮（systemic lupus erythematosus, SLE）是一种自身免疫性疾病，以对自身抗原的免疫耐受丧失、自身抗体产生及异常免疫应答为特征。铜死亡（cuproptosis）是近年报道的一种细胞死亡形式，与多种疾病的发生发展密切相关。本研究旨在探究系统性红斑狼疮中与铜死亡相关的分子簇，并构建预测模型。

方法：本研究基于GSE61635与GSE50772数据集，分析了系统性红斑狼疮患者体内铜死亡相关基因（cuproptosis-related genes, CRGs）的表达谱与免疫特征，并通过加权基因共表达网络分析（weighted correlation network analysis, WGCNA）筛选出与系统性红斑狼疮发病相关的核心模块基因。通过对比随机森林（random forest, RF）模型、支持向量机（support vector machine, SVM）模型、广义线性模型（generalized linear model, GLM）以及极端梯度提升（extreme gradient boosting, XGB）模型，本研究选取了最优机器学习模型。通过列线图（nomogram）、校准曲线、决策曲线分析（decision curve analysis, DCA）以及外部数据集GSE72326对模型的预测性能进行验证。随后，构建了基于5个核心诊断标志物的内源竞争RNA（competing endogenous RNA, ceRNA）调控网络。利用CTD数据库获取靶向核心诊断标志物的候选药物，并采用Autodock vina软件完成分子对接。

结果：通过WGCNA筛选得到的蓝色模块基因与系统性红斑狼疮发病显著相关。在四种机器学习模型中，支持向量机（SVM）模型展现出最优的区分性能，其残差与均方根误差（root-mean-square error, RMSE）较低，曲线下面积（area under the curve, AUC = 0.998）较高。本研究基于5个基因构建了SVM预测模型，并在外部验证数据集GSE72326中取得了良好的预测效果（AUC = 0.943）。列线图、校准曲线与决策曲线分析同样验证了该模型对系统性红斑狼疮的预测准确性。该ceRNA调控网络共包含166个节点（5个核心诊断标志物、61个微小RNA（microRNA, miRNA）及100个长链非编码RNA（long non-coding RNA, lncRNA））与175条调控边。药物筛选结果显示，D00156（苯并[a]芘，Benzo(a)pyrene）、D016604（黄曲霉毒素B1，Aflatoxin B1）、D014212（维A酸，Tretinoin）以及D009532（镍，Nickel）可同时靶向这5个核心诊断标志物。

结论：本研究揭示了铜死亡相关基因与系统性红斑狼疮患者免疫细胞浸润的相关性。选取基于5个基因的SVM模型作为最优机器学习模型，可精准评估系统性红斑狼疮患者的病情。本研究构建了基于5个核心诊断标志物的ceRNA调控网络，并通过分子对接验证了靶向核心诊断标志物的候选药物。