基于TCGA数据库代谢相关基因构建乳腺癌预后模型

Construction of a breast cancer prognostic model based on metabolism-related genes in the TCGA database

目的基于TCGA数据库构建乳腺癌代谢相关预后模型,揭示代谢与乳腺癌预后之间的关系。方法代谢相关基因从KEGG数据库中获取,limma包用于去筛选TCGA数据库中1109例乳腺癌样本和113例正常对照的代谢相关差异基因,随机抽取70%样本作为训练集,剩余30%样本作为验证集,单因素Cox回归用于筛选预后相关基因,基于glmnet包构建代谢相关预后模型,并通过单因素和多因素Cox回归对模型进行验证。结果本研究筛选出168个代谢相关差异基因,通过生存过滤及去掉过度拟合的基因后最终13个代谢相关的基因用作预后模型的构建,包括NMNAT2、NT5E、QPRT、UGP2、MTHFD2、TSTA3、TYMP、ALDH2、ALDH1A1、IDO1、IL4I1、INPP1和ENPP6。生存分析显示,高风险组患者生存时间显著长于低风险组(P<0.05)。单因素和多因素Cox回归结果表明构建的代谢相关预后模型的风险得分是乳腺癌患者的一个独立预后因素。结论本研究构建的预后模型揭示了代谢与乳腺癌预后之间的关系,为乳腺癌的诊断及研究提供了一个新的视角。

Objective The aims of this study were to construct a breast cancer metabolism-related prognostic model based on the TCGA database,and to reveal the relationship between metabolism and breast cancer prognosis.Methods Metabolism related genes were retrieved from KEGG database,and limma package was used to screen metabolism-related differential genes of 1109 breast cancer samples and 113 normal controls in the TCGA database.The 70%of samples were randomly selected as the training set,and the remaining 30%of the samples were used as the validation set.Univariate Cox regression was used to screen prognosis-related genes,a metabolism-related prognostic model was constructed based on glmnet package,and the model was validated by univariate and multivariate Cox regression.Results In this study,168 metabolically related differential genes were screened.After survival filtering and overfitted genes were removed,13 metabolically related genes were finally used for the construction of prognostic model,including NMNAT2、NT5E、QPRT、UGP2、MTHFD2、TSTA3、TYMP、ALDH2、ALDH1A1、IDO1、IL4I1、INPP1 and ENPP6.Survival analysis showed that the survival time of patients in the high-risk group was significantly longer than that in the low-risk group(P<0.05).Univariate and multivariate Cox regression results indicated that the risk score of the constructed metabolism related prognostic model was an independent prognostic factor for breast cancer patients.Conclusion The prognostic model constructed in this study revealed the relationship between metabolism and breast cancer prognosis,and provided a new perspective for breast cancer diagnosis and research of breast cancer.