摘要： 目的 探究衰老相关分泌表型（SASP）在骨关节炎（OA）中的预测标志物。方法 通过基因表达综合（GEO）数据库获取OA数据集，通过PubMed收集SASP基因。使用最小绝对收缩和选择算子（LASSO）、支持向量机递归特征消除（SVM-RFE）和随机森林（RF）3种机器学习算法筛选SASP在OA中候选预测标志物，将3种机器学习算法分别筛选出的候选预测标志物取交集得到共同基因，使用共同基因构建OA预测模型，采用受试者操作特征（ROC）曲线下面积（AUC）值评价模型的预测能力，并选取预测模型中最优基因（P < 0.001）进行动物实验验证。利用CIBERSORT探究OA数据集中OA患者外周血单核细胞样本和正常人外周血单核细胞样本的免疫浸润水平。使用Cytoscape可视化共同基因的miRNA-TF-mRNA调控网络。将12只SD大鼠分为OA组和正常组，每组6只，OA组采用前交叉韧带切断法构建OA模型，通过实时荧光定量PCR（RT-qPCR）对2组大鼠膝关节软骨组织中最优基因的表达进行验证。结果 通过GEO数据库获取1个OA数据集GSE48556，数据集中包括106个OA患者外周血单核细胞样本和33个正常人外周血单核细胞样本。通过PubMed收集125个SASP基因，并分离出与OA相关的125个SASP基因。通过LASSO、SVM-RFE和RF 3种机器学习算法共获得7个共同基因。使用7个共同基因构建的OA预测模型中最优基因为TNFRSF1A（P=0.000 875），AUC值为0.891。CIBERSORT免疫浸润结果显示，OA患者外周血单核细胞样本与正常人外周血单核细胞样本间浆细胞浸润水平存在显著差异（P=0.001 3）。RT-qPCR结果显示，OA组TNFRSF1A表达水平明显高于正常组（P < 0.000 1）。结论 TNFRSF1A在OA中高表达，极有可能成为OA潜在预测标志物。

基于综合生物信息学和机器学习算法构建衰老相关分泌表型的骨关节炎预测模型

刘孝生¹, 魏东升^1,2, 何信用¹, 方策³

1. 辽宁中医药大学研究生学院, 沈阳 110847;
2. 辽宁中医药大学中医脏象理论及应用教育部重点实验室, 沈阳 110847;
3. 抚顺市中医院骨伤一科, 辽宁 抚顺 113008

收稿日期:2023-03-31出版日期:2023-12-30发布日期:2023-12-12
通讯作者:方策E-mail:fushunzhongyigukefangce@163.com
作者简介:刘孝生(1994-),男,硕士研究生
基金资助:中国博士后科学基金（2021MD703841）


关键词: 骨关节炎, 衰老相关分泌表型, 免疫浸润, 机器学习算法, 预测模型
Abstract: Objective To explore the predictive markers of senescence-associated secretory phenotype (SASP) in osteoarthritis (OA).Methods OA datasets were screened by the Gene Expression Omnibus (GEO) database, while SASP-related genes were collected by PubMed. Three machine learning algorithms, including least absolute shrinkage and selection operator (LASSO), support vector machines recursive feature elimination (SVM-RFE), and random forest (RF), were used to screen the candidate predictive markers of SASP genes in OA, and the OA prediction model was constructed using the overlapping genes identified by the machine learning algorithms. CIBERSORT was used to explore the degree of peripheral blood immune cell infiltration in OA versus normal samples. The miRNA-transcription factor-mRNA regulatory network of the model genes was predicted using Cytoscape. The most valuable genes of the prediction model were experimentally verified by real-time quantitative polymerase chain reaction (RT-qPCR) in OA rats and normal control rats (n=6 per group).Results One OA dataset was screened by the GEO database, and 125 OA-related SASP genes were isolated. A total of seven intersection genes were obtained by the three machine learning algorithms. The area under the curve of the prediction model was 0.891. The CIBERSORT immune infiltration results showed a significant difference in plasma cell infiltration level between OA and normal samples (P=0.001 3). The RT-qPCR results showed that the expression level of TNFRSF1A was significantly higher in the OA versus normal group (P < 0.000 1).Conclusion TNFRSF1A is highly expressed in OA and may be a potential predictive marker for it.
Key words: osteoarthritis, senescence-associated secretory shenotype, immunoinfiltration, machine learning algorithm, prediction model
PDF全文下载地址:

https://journal.cmu.edu.cn/CN/article/downloadArticleFile.do?attachType=PDF&id=3331