中草药

基于机器学习与实验验证的缺血性卒中核心机制解析及中药防治策略预测

PDF下载

中草药 | 数据挖掘与循证医学 2026,57(7): 2640-2654

收起

中草药 |数据挖掘与循证医学 2026 , 57 (7) : 2640 -2654

基于机器学习与实验验证的缺血性卒中核心机制解析及中药防治策略预测

全屏

廖昊森^1,2, 陈翠兰¹, 马月辉^1,2, 顿玲露¹, 符钰岚^2,3, 晏洪恩^1,2, 周哲屹¹

作者信息

通讯作者:

周哲屹

作者简介:

廖昊森: 廖昊森,博士研究生,研究方向为脑系病证防治研究。E-mail:liaohaosen16@163.com

Analysis of core mechanisms of ischemic stroke based on machine learning and experimental verification and prediction of traditional Chinese medicine prevention and treatment strategies

LIAO Haosen, CHEN Cuilan, MA Yuehui, DUN Linglu, FU Yulan, YAN Hongen, ZHOU Zheyi

Affiliations

doi: 10.7501/j.issn.0253-2670.2026.07.018

文章导航

摘要

收起

目的通过整合多组学与机器学习方法，筛选缺血性卒中（ischemic stroke，IS）关键基因并解析其机制，预测其潜在的中医药防治靶点。方法整合GEO数据库中IS转录组数据，经差异表达、加权基因共表达网络分析（weighted gene co-expression network analysis，WGCNA）及蛋白互作网络分析筛选候选基因。运用包括最小绝对收缩和选择算子（logistic least absolute shrinkage and selection operator，LASSO）、随机森林等在内的多种机器学习算法构建诊断模型，并通过交叉验证确定最优基因集。通过构建大鼠大脑中动脉栓塞（middle cerebral artery occlusion，MCAO）模型，以贝德森（Bederson）评分、HE染色及实时荧光定量聚合酶链反应（real-time quantitative polymerase chain reaction，RT-qPCR）进一步验证。利用CIBERSORTx分析免疫浸润，并基于Coremine Medical数据库反向匹配潜在中药。结果确定8个核心基因ARG1、CLEC4E、CLEC5A、FCAR、FCGR1A、IRAK3、MCEMP1、TLR5，其诊断模型在训练与验证队列中均表现良好［曲线下面积（area under curve，AUC）＞0.7］。动物实验证实上述基因在IS模型大鼠皮层组织中表达显著上调，且与M0型巨噬细胞、中性粒细胞等免疫细胞浸润水平密切相关。基于上述靶点预测出59味潜在中药，四气多属寒、温、平，五味多属苦、甘，归经主要集中在肝、肾和脾经，其性味归经与IS“肝肾阴虚、瘀热内蕴”病机相符。结论通过整合生物信息学、机器学习与实验验证，系统筛选并验证了8个参与卒中后免疫微环境重塑的关键基因，可作为IS的潜在诊断生物标志物。中药预测分析提示靶向这些基因的中药性味归经特点与IS病机相符，为从免疫调控角度开展IS的中医药防治提供了理论依据。

关键词

缺血性卒中 / 机器学习 / 分子机制 / 中药防治策略 / 药性

Abstract

收起

Objective To screen key genes of ischemic stroke (IS) and analyze their mechanisms by integrating multi-omics and machine learning methods, and predict their potential targets for traditional Chinese medicine prevention and treatment. Methods IS transcriptome data from GEO database was integrated, and candidate genes were screened through differential expression, weighted gene co-expression network analysis (WGCNA) and protein interaction network analysis. A variety of machine learning algorithms including logistic least absolute shrinkage and selection operator (Lasso), random forest, etc. were used to construct a diagnostic model, and the optimal gene set is determined through cross-verification. An middle cerebral artery occlusion (MCAO) model was constructed and further verified by Bederson scoring, HE staining and real-time quantitative polymerase chain reaction (RT-qPCR). Immune infiltration was analyzed using CIBERSORTx and potential traditional Chinese medicines were reverse-matched based on Coremine Medical database. Results Eight core genes (ARG1, CLEC4E, CLEC5A, FCAR, FCGR1A, IRAK3, MCEMP1, TLR5) were identified, and their diagnostic models performed well in both the training and verification cohorts [area under curve (AUC) > 0.7]. Animal experiments had confirmed that the expression of these genes was significantly up-regulated in the cortical tissue of IS model rats, and was closely related to the infiltration level of immune cells such as M0-type macrophages and neutrophils. Based on the above targets, 59 potential traditional Chinese medicines were predicted. Most of the four qi were cold, warm and calm, and most of the five are bitter and sweet. The meridian tropism was mainly concentrated in the liver, kidney and spleen meridians. The medicinal properties and meridian tropism were consistent with the pathogenesis of IS “liver and kidney yin deficiency, and stasis and heat accumulation”. Conclusion By integrating bioinformatics, machine learning and experimental validation, this study systematically identified and validated eight key genes involved in the remodelling of the post-stroke immune microenvironment, which may serve as potential diagnostic biomarkers for IS. Predictive analysis of traditional Chinese medicine suggests that the pharmacological properties—including taste, nature and meridian tropism—of drugs targeting these genes are consistent with the pathogenesis of IS, thereby providing a theoretical basis for the prevention and treatment of IS using traditional Chinese medicine from the perspective of immune regulation.

Key words

ischemic stroke / machine learning / molecular mechanisms / strategies for prevention and treatment with traditional Chinese medicine / medicinal properties

引用本文

廖昊森, 陈翠兰, 马月辉, 顿玲露, 符钰岚, 晏洪恩, 周哲屹. 基于机器学习与实验验证的缺血性卒中核心机制解析及中药防治策略预测. 中草药, 2026 , 57 (7) : 2640 -2654 . DOI: 10.7501/j.issn.0253-2670.2026.07.018

LIAO Haosen, CHEN Cuilan, MA Yuehui, DUN Linglu, FU Yulan, YAN Hongen, ZHOU Zheyi. Analysis of core mechanisms of ischemic stroke based on machine learning and experimental verification and prediction of traditional Chinese medicine prevention and treatment strategies[J]. Chinese Traditional and Herbal Drugs, 2026 , 57 (7) : 2640 -2654 . DOI: 10.7501/j.issn.0253-2670.2026.07.018

基金

收起

国家自然科学项目基金 (82560989); 柳州市科技项目 (2024YB0103B011); 广西青年岐黄学者培养计划 (GXQH202414); 八桂青年拔尖人才项目 (桂人才办[2025]1号)

参考文献

收起

文献

收起

参考文献引证文献

排序方式：

He M L, Zhang S, Liu X, et al. Global, regional, and national epidemiology of ischemic stroke in young adults,1990-2021[J]. J Neurol, 2025, 272(5):354.
Hou S, Zhang Y F, Xia Y L, et al. Global, regional, and national epidemiology of ischemic stroke from 1990 to2021[J]. Eur J Neurol, 2024, 31(12):e16481.
Jia J, Jiao W J, Wang G, et al. Drugs/agents for the treatment of ischemic stroke:Advances and perspectives[J]. Med Res Rev, 2024, 44(3):975-1012.
Mosconi M G, Paciaroni M. Treatments in ischemic stroke:Current and future[J]. Eur Neurol, 2022, 85(5):349-366.
Yin X Y, Li S T, Wang J W, et al. Research progress of active compounds from traditional Chinese medicine in the treatment of stroke[J]. Eur J Med Chem, 2025, 291:117599.
Long J X, Tian M Z, Chen X Y, et al. The role of NLRP3inflammasome-mediated pyroptosis in ischemic stroke and the intervention of traditional Chinese medicine[J].Front Pharmacol, 2023, 14:1151196.
Liu Y Q, Ye Y, Bai L, et al. Exploring research trends and hotspots in PI3K/Akt signaling pathway in ischemic stroke:A bibliometric analysis[J]. Front Mol Neurosci,2025, 18:1613702.
Li W T, Shao C Y, Zhou H F, et al. Multi-omics research strategies in ischemic stroke:A multidimensional perspective[J]. Ageing Res Rev, 2022, 81:101730.
Jia J, Niu L, Feng P, et al. Identification of novel biomarkers for ischemic stroke through integrated bioinformatics analysis and machine learning[J]. J Mol Neurosci, 2025, 75(1):13.
Zhang H P, Wu T, Li X H, et al. Machine learning identifies neutrophil extracellular traps-related biomarkers for acute ischemic stroke diagnosis[J]. Front Neurol, 2025, 16:1611776.
Li Q, Tian Y, Niu J Y, et al. Identification of diagnostic signatures for ischemic stroke by machine learning algorithm[J]. J Stroke Cerebrovasc Dis, 2024, 33(3):107564.
Gu Y X, Sun Z J, Li T, et al. Huanglian Jiedu decoction treats ischemic stroke by regulating pyroptosis:Insights from multi-omics and drug-target relationship analysis[J].Pharmaceuticals, 2025, 18(6):775.
Ren M H, Li Y, Yuan J M, et al. The mechanism of Bovis Culus Sativus protecting BBB damage in stroke:Insights from network pharmacology, bioinformatics, and experiments[J]. J Ethnopharmacol, 2025, 342:119390.
Inagaki T, Etgen A M. Neuroprotective action of acute estrogens:Animal models of brain ischemia and clinical implications[J]. Steroids, 2013, 78(6):597-606.
徐小雯.电针调控AMPK/mTOR/ULK1信号通路改善MCAO/R大鼠神经功能损伤的机制研究[D].广州:广州中医药大学, 2024.
Yamasaki S, Ishikawa E, Sakuma M, et al. Mincle is an ITAM-coupled activating receptor that senses damaged cells[J]. Nat Immunol, 2008, 9(10):1179-1188.
Zhang L, Yue L, Jia P, et al. Comprehensive transcriptomic analysis integrating bulk and single-cell RNA-seq with machine learning to identify and validate mitochondrial unfolded protein response biomarkers in patients with ischemic stroke[J]. Front Cell Dev Biol, 2025, 13:1582252.
Iadecola C, Anrather J. The immunology of stroke:From mechanisms to translation[J]. Nat Med, 2011, 17(7):796-808.
Seok J, Warren H S, Cuenca A G, et al. Genomic responses in mouse models poorly mimic human inflammatory diseases[J]. Proc Natl Acad Sci USA, 2013, 110(9):3507-3512.
Heuser S K, Li J J, Pudewell S, et al. Biochemistry,pharmacology, and in vivo function of arginases[J].Pharmacol Rev, 2025, 77(1):100015.
Wang X, Liu X Y. Exploration of the shared gene signatures and molecular mechanisms between cardioembolic stroke and ischemic stroke[J]. Front Neurol, 2025, 16:1567902.
Chen Z J, Pan C F, Chen X X, et al. CLEC5A knockdown reduces oxidative stress and inflammation caused by lipopolysaccharide in renal tubular epithelial cells via the NF-κB/NLRP3 signaling pathway[J]. Arch Immunol Ther Exp, 2025, doi:10.2478/aite-2026-0001.
Qi D X, Wang F, Zhang X K, et al. Epigenetic upregulation of CLEC5A contributes to monocyte/macrophage dysfunction in coronary artery disease[J]. Int J Biol Macromol, 2025, 308(Pt 2):142471.
Shimokawa T, Ra C. C/EBPalpha functionally and physically interacts with GABP to activate the human myeloid IgA Fc receptor(Fc alphaR, CD89)gene promoter[J]. Blood, 2005, 106(7):2534-2542.
Liu M, Fan X H, Chen D Y, et al. FCGR1A alleviates ischemic stroke-induced injury by promoting antiinflammatory microglial polarization via the AMPKm TOR signaling pathway[J]. Front Biosci, 2025, 30(5):26614.
Cao C, Ding J S, Cao D M, et al. TREM2 modulates neuroinflammation with elevated IRAK3 expression and plays a neuroprotective role after experimental SAH in rats[J]. Neurobiol Dis, 2022, 171:105809.
Raman K, O’Donnell M J, Czlonkowska A, et al.Peripheral blood MCEMP1 gene expression as a biomarker for stroke prognosis[J]. Stroke, 2016, 47(3):652-658.
Wang H D, Li J, Wu G Y, et al. Activated sympathetic nerve post stroke downregulates Toll-like receptor 5 and disrupts the gut mucosal barrier[J]. Cell Rep Med, 2024,5(10):101754.
Qiao H M, Zhang X J, Zhu C H, et al. Luteolin downregulates TLR4, TLR5, NF-κB and p-p38MAPK expression, upregulates the p-ERK expression, and protects rat brains against focal ischemia[J]. Brain Res,2012, 1448:71-81.
Seo B, Lim M Y. Balancing harm and harmony:Evolutionary dynamics between gut microbiota-derived flagellin and TLR5-mediated host immunity and metabolism[J]. Virulence, 2025, 16(1):2512035.
Fan L, Sun Y, Lou F Z, et al. Pp6-Pfkfb1 axis modulates intracellular bacterial proliferation by orchestrating hostpathogen metabolic crosstalk[J]. PLoS Pathog, 2025,21(12):e1013304.
Stegmann F, Diersing C, Lepenies B. Legionella pneumophila modulates macrophage functions through epigenetic reprogramming via the C-type lectin receptor Mincle[J]. i Science, 2024, 27(9):110700.
Legaki E, Koutouratsas T, Theocharopoulos C, et al.Polymorphisms in CLEC5A and CLEC7A genes modify risk for inflammatory bowel disease[J]. Ann Gastroenterol, 2024, 37(1):64-70.
Liu C Y, Peng C F, Jia X D, et al. Determining the biomarkers and pathogenesis of myocardial infarction combined with ankylosing spondylitis via a systems biology approach[J]. Front Med, 2025, 19(3):507-522.
Gu L, Huang J Y, Tan J J, et al. Impact of TLR5 rs5744174on stroke risk, gene expression and on inflammatory cytokines, and lipid levels in stroke patients[J]. Neurol Sci,2016, 37(9):1537-1544.
李佳鑫,王世伟.虎杖生品及其3种炮制品的肝毒性比较研究[J].中国药房, 2025, 36(24):3060-3065.
StyczeńA, Krysa M, Mertowska P, et al. The role of Tolllike receptors and viral infections in the pathogenesis and progression of pulmonary arterial hypertension-a narrative review[J]. Int J Mol Sci, 2025, 26(22):11143.
王越欣,王梅,李宁,等.连翘抗炎活性成分及作用机制研究进展[J].中华中医药学刊, 2022, 40(1):115-120.
Jiang W L, Tian J W, Fu F H, et al. Neuroprotective efficacy and therapeutic window of Forsythoside B:In a rat model of cerebral ischemia and reperfusion injury[J].Eur J Pharmacol, 2010, 640(1/2/3):75-81.
韩斌宝,邵碧晨,潘丽玲,等.天然小分子化合物对阿尔茨海默病改善作用及机制研究进展[J].中草药,2025, 56(24):9211-9223.
蔡明,熊梦琪,夏文文,等.基于多角度数据挖掘与整合探讨中医药治疗糖尿病脑病的核心方证规律及分子机制[J].中草药, 2025, 56(24):9076-9089.
任小巧.探析中医“整体观念”在“脑卒中”防治中的价值[J].中国中医基础医学杂志, 2019, 25(7):880-882.
迟显苏,梁晓,刘红喜,等.基于“脾肾-脑相通”理论从核心认知域视角分期论治卒中后认知障碍[J].中医杂志, 2023, 64(2):128-131.
陈丽斌,纪立金,冯珂.从“脾脉相关”理论论治缺血性脑卒中[J].中华中医药杂志, 2021, 36(9):5253-5255.

2026年第57卷第7期

PDF下载

引用本文

BibTeX

文章信息

doi: 10.7501/j.issn.0253-2670.2026.07.018

接收时间：2025-12-17
首发时间：2026-09-09

补充材料

相关文章

文章信息

作者

出版历史

收稿日期：2025-12-17

基金

作者信息

参考文献

分享链接

https://castjournals.cast.org.cn/joweb/zcy/CN/10.7501/j.issn.0253-2670.2026.07.018

分享至

全文二维码

扫描看全文

引用本文

BibTeX

本文的引用情况

2种不同金属材料的力学参数

科 Family	属数 Number of genus	种数 Number of species	占总种数比例 Percentage of total species (%)	属 Genus	种数 Number of species	占总种数比例 Percentage of total species (%)
鹅膏菌科Amanitaceae	2	11	5.26	鹅膏菌属 Amanita	10	4.78
小菇科 Mycenaceae	2	12	5.74	丝盖伞属 Inocybe	5	2.39
多孔菌科 Polyporaceae	8	14	6.70	蜡蘑属 Laccaria	5	2.39
红菇科 Russulaceae	3	23	11.00	小皮伞属 Marasmius	6	2.87
				小菇属 Mycena	11	5.26
				光柄菇属 Pluteus	5	2.39
				红菇属 Russula	17	8.13
				栓菌属 Trametes	5	2.39

关闭全屏

BibTeX
EndNote
RefWorks
TxT