综合生物信息学与机器学习筛选非酒精性脂肪性肝炎的趋化因子相关核心基因

Integrated identification of the chemokine-related key genes underlying the progression of nonalcoholic steatohepatitis via bioinformatics and machine learning

目的综合运用生物信息学方法及机器学习算法筛选与非酒精性脂肪性肝炎相关的趋化因子核心基因。方法公共数据库GEO下载非酒精性脂肪性肝病芯片数据集GSE49541,采用R studio软件进行差异分析筛选差异基因,对差异基因进行GO功能注释和KEGG信号通路富集分析,将差异基因与趋化因子通路相关基因集取交集获取趋化因子相关差异基因,然后采用机器学习LASSO回归及SVM-RFE算法筛选核心基因,通过Genemania数据库构建核心基因互作网络图,构建核心基因列线图预测模型,并通过ROC曲线验证列线图效能。结果共筛选获取差异基因148个,GO及KEGG富集分析提示差异基因富集于脂质代谢、趋化因子、细胞外基质等。最后筛选获得核心基因CCL19、CD24、ROBO1、SLC12A2,构建核心基因互作网络图,基于核心基因建立NASH列线图预测模型,该模型ROC曲线的AUC=0.997,95%置信区间(confidence interval,CI)为0.988~1.000。结论CCL19、CD24、ROBO1、SLC12A2可能与非酒精性脂肪性肝炎发生与进展密切相关,有望成为诊断和精准治疗的潜在靶点。

Objective To integratedly identify the chemokine-related key genes underlying the progression of nonalcoholic steatohepatitis(NASH)via bioinformatics and machine learning.Methods The differentially expressed genes(DEGs)after download of NASH datasets GSE49541 from public database the Gene Expression Omnibus(GEO)were identified via R studio software.Further,the Gene Ontology(GO)functional annotation and Kyoto Encyclopedia of Genes and Genomes(KEGG)enrichment analyses were performed.The DEGs and chemokine-related gene sets were intersected to identity the differentially expressed chemokine-related genes.Identification of the key genes was applied via machine learning LASSO regression and support vector machines-recursive feature elimination(SVM-RFE).The key gene interaction network was established via the GeneMANIA database.Then the key gene nomogram models in prediction were constructed and the effectiveness of nomograms was validated by receiver operator characteristic(ROC)curve.Results A total of 148 DEGs were identified.GO and KEGG analyses revealed that DEGs were mainly enriched in fatty acid metabolic process,chemokine signaling pathway,and extracellular matrix.Moreover,four key genes,including CCL19,CD24,ROBO1,and SLC12A2,were identified,and a key gene interaction network diagram was constructed.Based on the key genes,a NASH nomogram prediction model was established,with the area under the ROC curve(AUC)of 997 and 95%confidence interval(CI)of 0.988-1.000.Conclusion CCL19,CD24,ROBO1,and SLC12A2 might be closely related to the occurrence and development of NASH,and are expected to become potential targets for its early diagnosis and precise treatment.