基于WGCNA和机器学习方法筛选冠脉搭桥术后氧化应激相关的核心基因

Identification of core genes associated with oxidative stress after coronary artery bypass grafting using WGCNA and machine learning methods

目的 利用加权基因共表达网络分析(WGCNA)和机器学习方法,筛选出冠脉搭桥(CABG)术后氧化应激(OS)相关的核心基因,并预测治疗心肌缺血再灌注损伤(MIRI)的靶向药物。方法 从GEO数据库CABG术前、术后心室组织表达谱,利用WGCNA得到术后最关联模块和基因,从而获得OS相关基因(OSRG),进一步富集分析。再通过最小绝对值收敛和选择算子(LASSO)回归和随机森林算法,筛选出冠脉搭桥术后核心OSRG,术前术后差异表达比较,预测靶向药物。结果 WGCNA结果得到32个CABG术后OSRG,富集分析结果显示这些基因主要参与细胞死亡调控、细胞程序性死亡、细胞凋亡、免疫过程以及多种信号通路的调节。机器学习筛选出3个核心OSRG:ATF3、JUN、VEGFA,其均在CABG术后上调表达(P<0.01)。并预测5种靶向药物。结论 本研究通过综合运用WGCNA和机器学习方法,成功筛选出CABG术后核心OSRG,这些核心基因术后均明显上调,通过诱导细胞死亡、免疫等方式,引起MIRI。

Objective This study aimed to use weighted gene co-expression network analysis(WGCNA)and machine learning methods to identify the core genes related to OS after CABG and predict targeted drugs for treating MIRI.Methods Gene expression profiles of pre-and post-operative ventricular tissues from the GEO database were analyzed using WGCNA to identify the most relevant modules and genes after surgery,resulting in OS-related genes(OSRG).Enrichment analysis was then performed.Subsequently,the least absolute shrinkage and selection operator(LASSO)regression and random forest algorithm were employed to screen for the core OSRG following CABG surgery.Differential expression analysis was conducted,and targeted drugs were predicted.Results WGCNA identified 32 OSRG after CABG surgery,and enrichment analysis revealed their involvement in cell death regulation,programmed cell death,apoptosis,immune processes,and regulation of various signaling pathways.Machine learning identified three core OSRG:ATF3,JUN,and VEGFA,all of which exhibited significant upregulation after CABG surgery(P<0.01).Additionally,five targeted drugs were predicted.Conclusion Through the integrated application of WGCNA and machine learning methods,this study successfully identified core OSRG after CABG surgery,which were significantly upregulated and involved in inducing cell death and immune responses,thereby contributing to MIRI.