中国组织工程研究 ›› 2025, Vol. 29 ›› Issue (在线): 1-15.

• •    

线粒体自噬视域下的类风湿关节炎:多机器学习算法构建预测模型及验证并免疫调控分析

李加根,陈跃平,黄柯琪,陈尚桐,黄川洪   

  1. 广西中医药大学附属瑞康医院,广西壮族自治区南宁市    530011
  • 出版日期:2025-01-08 发布日期:2024-09-18
  • 通讯作者: 陈跃平,博士,主任医师,博士生导师,广西中医药大学附属瑞康医院,广西壮族自治区南宁市 530011
  • 作者简介:李加根,男,1998年生,内蒙古自治区鄂尔多斯市人,汉族,广西中医药大学在读硕士,主要从事脊柱、骨关节创伤性疾病的防治研究。
  • 基金资助:
    国家自然科学基金项目(82360937),项目负责人:陈跃平;广西自然科学基金项目(2023JJA140318),项目负责人:陈跃平;广西中西医结合骨与关节退行性疾病多学科交叉创新团队(GZKJ2310),项目参与人:陈跃平;广西中医药大学研究生教育创新计划项目(YCSY2023040),项目负责人:李加根

The construction and validation of a prediction model based on multiple machine learning algorithms and the immunomodulatory analysis of rheumatoid arthritis from the perspective of mitophagy

Li Jiagen, Chen Yueping, Huang Keqi, Chen Shangtong, Huang Chuanhong   

  1. Ruikang Hospital Affiliated to Guangxi University of Chinese Medicine, Nanning, Guangxi 530011, Guangxi Zhuang Autonomous Region, China
  • Online:2025-01-08 Published:2024-09-18
  • Contact: Chen Yueping, Ph D, Chief physician, Professor, Doctoral supervisor, Ruikang Hospital Affiliated to Guangxi University of Chinese Medicine, Nanning 530011, Guangxi Zhuang Autonomous Region, China
  • About author:LI Jiagen, Master candidate, Ruikang Hospital Affiliated to Guangxi University of Chinese Medicine, Nanning 530011, Guangxi Zhuang Autonomous Region, China
  • Supported by:
    National Natural Science Foundation of China, No. 82360937 (to CYP); Natural Science Foundation of Guangxi Zhuang Autonomous Region, No. 2023JJA140318 (to CYP); Guangxi Integrated Bone and Joint Degenerative Disease Multidisciplinary Innovation Team Project, No. GZKJ2310 (to CYP [project participant]); Innovation Project of Guangxi Graduate Education of GXUCM, No. YCSY2023040 (to LJG)

摘要:

文题释义:
类风湿关节炎:是一种慢性、系统性的自身免疫性疾病,主要特征为多发对称性小关节炎症、疼痛和肿胀,疾病后期往往导致严重的关节畸形甚至功能丧失。
线粒体自噬:是一种选择性自噬,主要过程为异常的线粒体被包裹在自噬体内随之运输到溶酶体,从而被靶向降解和清除,以控制线粒体质量和功能的稳定,这一过程对维持细胞内能量平衡、减少氧化应激和维护细胞内稳态具有重要意义。

背景:类风湿关节炎发病机制至今尚未完全清晰,近来有研究表明线粒体自噬与类风湿关节炎存在关联性,但关键机制有待深入探究。
目的:利用多机器学习算法鉴定和验证类风湿关节炎中线粒体自噬过程核心互作基因并解析其免疫调控过程。
方法:从GEO数据库整理类风湿关节炎转录组表达数据集GSE15573作为独立训练集,GSE97779和GSE55235合集作为独立验证集。利用训练集筛选类风湿关节炎差异表达基因,同时进行“WGCNA”分析。然后从“MitoCarta3.0”数据库下载线粒体自噬相关基因,将其与类风湿关节炎差异基因和“WGCNA”分析模块基因取交集获得类风湿关节炎-线粒体自噬相关基因,同时将相关基因进行功能富集分析以明确细胞通路。随后利用“Random Forest”和“LASSO”两种机器学习算法分别筛选特征基因,并利用“GMM”机器学习算法对前两种机器学习算法筛选的交集基因拟合验证,以获得类风湿关节炎-线粒体自噬核心互作基因。进一步建立预测模型,并利用外部验证集验证。最后,采用“CIBERSORT”进行免疫浸润分析此过程中免疫细胞亚群占比及亚群之间关联性,并采用“ssGSEA”分析类风湿关节炎-线粒体自噬核心互作基因与免疫细胞亚群间关联性,同时分析核心互作基因的相关“GO”、“KEGG”生物学通路。
结果与结论:①差异分析获得807个类风湿关节炎差异表达基因,“WGCNA”分析筛选出2个特征模块含1 208个基因,线粒体基因数据库整理出1 136个基因,三部分基因取交集获得53个基因为类风湿关节炎-线粒体自噬相关基因;②相关基因的功能富集分析结果显示细胞过程主要与线粒体自噬、过氧化物酶体代谢、细胞衰老、坏死性凋亡相关;③3种机器学习算法鉴定出4个RA-Mitophagy核心互作基因(DNAJA3、C12orf65、AKR7A2、PDHB);④预测模型的风险评分受试者工作特征曲线下面积为0.989,外部患者样本的工作特征曲线验证类风湿关节炎-线粒体自噬核心互作基因的曲线下面积均大于0.7;⑤免疫调控分析显示类风湿关节炎中线粒体自噬过程与记忆B细胞、M0型巨噬细胞、活化的记忆性CD4 T细胞、静息态记忆性CD4 T细胞密切相关。⑥生物学通路分析结果显示核心互作基因与821条“GO”通路强相关( |cor| > 0.8,P < 0.001),与48条“KEGG”通路强相关( |cor| > 0.8,P < 0.001),其中关键生物学过程与线粒体DNA代谢、线粒体DNA修复、线粒体DNA复制、线粒体基因组维护、线粒体去极化的正向调控和参与凋亡信号通路的线粒体外膜通透性的正向调控有关。⑦上述结果证实,DNAJA3、C12orf65、AKR7A2、PDHB是类风湿关节炎中线粒体自噬过程的核心互作基因,通过参与特定免疫过程在疾病进展中发挥关键作用,对类风湿关节炎的诊断具有精准的预测效果。

关键词: 线粒体自噬, 类风湿关节炎, 机器学习算法, 加权基因共表达网络分析, 预测模型, 外部验证, 免疫细胞, 生物学功能

Abstract: BACKGROUND: The pathogenesis of rheumatoid arthritis has not yet been fully clarified, and recent studies have shown that mitophagy is associated with rheumatoid arthritis, but the key mechanisms need to be explored in depth. 
OBJECTIVE: To identify and validate the core interaction genes of mitophagy in rheumatoid arthritis using multiple machine learning algorithms and to analyze its immunoregulatory process.
METHODS: The rheumatoid arthritis transcriptome expression dataset GSE15573 was retrieved from the GEO database as an independent training set, with the GSE97779 and GSE55235 collections used as independent validation sets. The RA differentially expressed genes were screened using the training set, and “WGCNA” analysis was also performed. Then we downloaded the mitophagy-related genes from the “MitoCarta3.0” database, and intersected them with the RA differentially expressed genes and the genes in the “WGCNA” analysis module to obtain the RA-Mitophagy-related genes, and then analyzed the related genes for functional enrichment to clarify the cellular pathways. Feature genes were initially identified using the “Random Forest” and “Lasso” algorithms. The overlapping genes from these two methods were further refined using the “GMM” algorithm to identify the core interaction genes between rheumatoid arthritis and mitophagy. A predictive model was then developed and validated using an external dataset. Finally, “CIBERSORT” was employed to analyze the proportions and interactions of immune cell subsets during immune infiltration, while “ssGSEA” was used to examine the associations between the rheumatoid arthritis-mitophagy core interaction genes and immune cell subsets. “ssGSEA” was also utilized to analyze the “GO” and “KEGG” biological pathways of the core interaction genes.
RESULTS AND CONCLUSION: 807 RA DEGs were obtained by differential analysis, 1208 genes were selected from two feature modules by “WGCNA” analysis, 1136 genes were sorted out from the MitoCarta 3.0 database, and 53 HUB genes were obtained from the intersection of the three genes as RA-Mitophagy related genes. The results of functional enrichment analysis of related genes showed that the cellular processes were mainly related to mitophagy-animal, peroxisome, cellular senescence, and necroptosis. The three machine learning algorithms identified four RA-Mitophagy core interaction genes (DNAJA3, C12orf65, AKR7A2, and PDHB). The AUC of nomoscore was 0.989, and the AUC values of RA-Mitophagy core interaction genes verified by the receiver operating characteristic curve of external patient samples were all greater than 0.7. Immunoregulatory analysis showed that the mitophagy process in rheumatoid arthritis was closely associated with memory B cells, M0 macrophages, activated memory CD4 T cells, and resting memory CD4 T cells. The biological pathway analysis revealed that the core interacting genes were strongly associated with 821 “GO” pathways (|cor| > 0.8, P < 0.001) and 48 “KEGG” pathways (|cor| > 0.8, P < 0.001). The key biological processes identified are related to mitochondrial DNA metabolic process, mitochondrial DNA repair, mitochondrial DNA replication, mitochondrial genome maintenance, positive regulation of mitochondrial depolarization, and positive regulation of mitochondrial outer membrane permeabilization involved in apoptotic signaling pathway. The conclusions showed that DNAJA3, C12orf65, AKR7A2, and PDHB are the core interaction genes of the mitophagy process in rheumatoid arthritis, which play key roles in disease progression by participating in specific immune processes and have precise and predictive effects on the diagnosis of rheumatoid arthritis.

Key words: mitophagy, rheumatoid arthritis, machine learning algorithm, weighted gene co-expression network analysis, predictive model, external validation, immune cells, biological function

中图分类号: