西黄丸治疗胃癌作用机制的网络药理学和机器学习探讨  

Exploring mechanism of Xihuang pills in treatment of gastric cancer based on network pharmacology and machine learning

作　　者：王励之 陈泓西 朱康莲 Wang Lizhi;Chen Hongxi;Zhu Kanglian(Department of Gastrointestinal Surgery,Hunan Provincial People's Hospital,First Hospital,Hunan Normal University,Changsha 410005,China;First Department of Ophthalmology and Stomatology,Hunan Provincial People's Hospital,First Hospital,Hunan Normal University,Changsha 410005,China)

机构地区：[1]湖南省人民医院(湖南师范大学附属第一医院)胃肠外科,长沙410005 [2]湖南省人民医院(湖南师范大学附属第一医院)眼口腔一科,长沙410005

出　　处：《国际医药卫生导报》2024年第23期3937-3946,共10页International Medicine and Health Guidance News

基　　金：湖南省卫健委科研项目(B20230401652)。

摘　　要：目的通过网络药理学和机器学习探讨西黄丸治疗胃癌的作用机制。方法所有数据采集和分析于2023年11月至2024年8月期间进行,研究的各阶段包括数据收集、基因靶点预测、网络模型构建及数据统计分析。利用中药系统药理学数据库(TCMSP)查询并提取西黄丸的化学成分数据,利用Swiss Target Prediction和HERB数据库预测活性成分靶点。使用Genecard收集疾病相关靶点,并筛选差异靶点。通过机器学习算法中的支持向量机进一步筛选疾病靶点基因。西黄丸治疗胃癌的潜在作用靶点是疾病靶点与活性成分靶点的交集。利用ClusterProfiler包进行潜在靶点的基因本体(GO)功能富集分析及京都基因与基因组百科全书(KEGG)通路富集分析。将活性成分与潜在作用靶点导入Cytoscape 3.10.0软件,构建“药物-活性成分-靶点”网络。拓扑分析获取西黄丸治疗胃癌的核心成分。利用LASSO回归筛选西黄丸治疗胃癌的核心靶点,Cibersort算法对核心靶点进行免疫浸润分析。数据通过R 4.2.1软件进行处理,采用t检验和单因素方差分析进行统计学检验。结果共选出有效活性成分41个,相关靶点182个,胃癌相关基因2410个,交集基因119个。通过GO富集分析,共识别出2049个GO条目(P<0.05);而信号通路富集分析则揭示了177条KEGG信号通路(P<0.05)。“药物-活性成分-靶点”网络分析发现,槲皮素是西黄丸治疗胃癌的核心成分。LASSO回归筛选出CD36、GJA1、SERPINE1基因可能是西黄丸治疗胃癌的核心作用靶点。数据分析结果显示,相较于正常样本,胃癌患者中GJA1和SERPINE1基因展现出较高的表达水平(均P<0.01),而CD36呈现低表达趋势(P<0.001),且均具有良好的诊断效能。预后分析结果表明,胃癌患者预后状况与核心靶点的表达水平呈负相关,即核心靶点表达水平越高,预后越不良。免疫浸润分析结果表明,胃癌的发生发展与多种免疫细胞失�Objective To explore the potential mechanism of Xihuang pills in the treatment of gastric cancer(GC)based on network pharmacology and machine learning.Methods All the data collection and analysis were conducted between November 2023 and August 2024.The study involved various stages,including data collection,gene target prediction,network model construction,and statistical analysis.The chemical composition data of Xihuang pills were retrieved from the Traditional Chinese Medicine Systems Pharmacology Database and Analysis Platform(TCMSP).The active ingredient targets were predicted using the Swiss Target Prediction and HERB databases.The disease-related targets were collected from GeneCard,and differential targets were filtered.The disease target genes were further filtered using the support vector machine(SVM)machine learning algorithm.The potential targets of Xihuang pills for gastric cancer were identified as the intersection of disease targets and active ingredient targets.Gene ontology(GO)enrichment analysis and Kyoto Encyclopedia of Genes and Genomes(KEGG)pathway enrichment analysis of the potential targets were performed using the clusterProfiler package.The active ingredients and potential targets were imported into the Cytoscape 3.10.0 software to construct a"drug-active ingredient-target"network.The topological analysis was performed to identify the core components of Xihuang pills in the treatment of gastric cancer.The LASSO regression was used to screen the core targets of Xihuang pills for gastric cancer.The Cibersort algorithm was employed for immune infiltration analysis of the core targets.The data were processed using the R 4.2.1 software,and statistical tests were conducted using t test and one-way analysis of variance.Results A total of 41 active ingredients and 182 related targets were identified,with 2410 gastric cancer-related genes and 119 intersecting genes.The GO enrichment analysis identified 2049 GO terms(P<0.05);the KEGG pathway enrichment analysis revealed 177 KEGG signaling pathways(P

关 键 词：西黄丸 胃癌 机器学习 网络药理学 免疫浸润 

分 类 号：R285[医药卫生—中药学]