为鉴定溃疡性结肠炎(ulcerative colitis,UC)中与能量代谢相关的关键基因,通过从GSE87466数据集中提取能量代谢相关基因的表达量并进行差异分析后对其进行富集分析,使用最小绝对收缩和选择算子(the least absolute shrinkage and se-lection operator,LASSO)算法和支持向量机器-递归特征消除(support vector machine-recursive feature elimination,SVM-RFE)算法识别UC能量代谢关键基因,对关键基因进行富集分析、免疫浸润分析、关键基因靶向药物预测和构建ceRNA网络,最后用GSE75214作为验证集对关键基因的表达进行验证.结果表明:共筛选出32个与能量代谢相关基因,通过LASSO和SVM算法鉴定出5个关键基因(SLC16A1、ACSF2、NR1H4、CHST11和CBR3).单基因富集结果显示关键基因通过糖酵解/葡萄糖新生、丁酸代谢、丙酮酸代谢等途径参与UC的发生发展.验证集GSE75214对关键基因进行验证发现表达均具有差异.为从能量代谢角度治疗溃疡性结肠炎提供了新的思路和方向.
Exploring Key Energy Metabolism-related Genes and Potential Mechanisms in Ulcerative Colitis Based on Bioinformatics and Machine Learning
In order to identify key genes related to energy metabolism in ulcerative colitis(UC),the expression of energy metabo-lism-related genes was extracted from the GSE87466 dataset and enriched by differential analysis,and the key genes were identified by using the least absolute shrinkage and selection operator(LASSO)algorithm and support vector machine recursive feature elimination(SVM-RFE)algorithm to identify the key genes of UC energy metabolism,and then enrichment analysis,immune infiltration analysis,prediction of key genes targeting drugs,and construction of ceRNA network were performed on the key genes.Finally,GSE75214 was used as a validation set to verify the expression of key genes.The results show that a total of 32 genes related to energy metabolism are screened,and 5 key genes(SLC16A1,ACSF2,NR1H4,CHST11 and CBR3)are identified by LASSO and SVM algorithms.The sin-gle gene enrichment results show that the key genes are involved in the development of UC through glycolysis/glucose de novo,butyric acid metabolism,and pyruvate metabolism.The validation set GSE75214 on the key genes reveals that the expressions are all differen-tial,providing new ideas and directions for the treatment of ulcerative colitis from the perspective of energy metabolism.
万方数据
维普
