• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利：CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法，用中文像聊天一样搜索，搜遍4000万医学文献。AI智能推荐，让科研检索更轻松。

立即免费搜索

文件翻译

保留排版，准确专业，支持PDF/Word/PPT等文件格式，支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述，25分钟生成高质量综述，智能提取关键信息，辅助科研写作。

立即免费体验

将机器学习与非靶向血浆脂质组学相结合，探索代谢综合征前和代谢综合征的脂质特征。

Integrating machine learning and nontargeted plasma lipidomics to explore lipid characteristics of premetabolic syndrome and metabolic syndrome.

机构信息

The Affiliated Fuzhou Center for Disease Control and Prevention of Fujian Medical University, Fuzhou, China.

School of Public Health, Fujian Medical University, Fuzhou, China.

出版信息

Front Endocrinol (Lausanne). 2024 Mar 15;15:1335269. doi: 10.3389/fendo.2024.1335269. eCollection 2024.

DOI:10.3389/fendo.2024.1335269
PMID:38559697
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC10979736/
Abstract

OBJECTIVE

To identify plasma lipid characteristics associated with premetabolic syndrome (pre-MetS) and metabolic syndrome (MetS) and provide biomarkers through machine learning methods.

METHODS

Plasma lipidomics profiling was conducted using samples from healthy individuals, pre-MetS patients, and MetS patients. Orthogonal partial least squares-discriminant analysis (OPLS-DA) models were employed to identify dysregulated lipids in the comparative groups. Biomarkers were selected using support vector machine recursive feature elimination (SVM-RFE), random forest (rf), and least absolute shrinkage and selection operator (LASSO) regression, and the performance of two biomarker panels was compared across five machine learning models.

RESULTS

In the OPLS-DA models, 50 and 89 lipid metabolites were associated with pre-MetS and MetS patients, respectively. Further machine learning identified two sets of plasma metabolites composed of PS(38:3), DG(16:0/18:1), and TG(16:0/14:1/22:6), TG(16:0/18:2/20:4), and TG(14:0/18:2/18:3), which were used as biomarkers for the pre-MetS and MetS discrimination models in this study.

CONCLUSION

In the initial lipidomics analysis of pre-MetS and MetS, we identified relevant lipid features primarily linked to insulin resistance in key biochemical pathways. Biomarker panels composed of lipidomics components can reflect metabolic changes across different stages of MetS, offering valuable insights for the differential diagnosis of pre-MetS and MetS.

摘要

目的

通过机器学习方法，确定与前代谢综合征（pre-MetS）和代谢综合征（MetS）相关的血浆脂质特征，并提供生物标志物。

方法

对健康个体、前 MetS 患者和 MetS 患者的样本进行血浆脂质组学分析。采用正交偏最小二乘判别分析（OPLS-DA）模型对比较组中失调的脂质进行鉴定。采用支持向量机递归特征消除（SVM-RFE）、随机森林（rf）和最小绝对收缩和选择算子（LASSO）回归选择生物标志物，并在五种机器学习模型中比较两个生物标志物组合的性能。

结果

在 OPLS-DA 模型中，分别有 50 种和 89 种脂质代谢物与前 MetS 和 MetS 患者相关。进一步的机器学习确定了两组由 PS（38:3）、DG（16:0/18:1）和 TG（16:0/14:1/22:6）、TG（16:0/18:2/20:4）和 TG（14:0/18:2/18:3）组成的血浆代谢物，这些代谢物被用作本研究中前 MetS 和 MetS 鉴别模型的生物标志物。

结论

在前 MetS 和 MetS 的初始脂质组学分析中，我们确定了与关键生化途径中胰岛素抵抗相关的相关脂质特征。由脂质组学成分组成的生物标志物组合可以反映 MetS 不同阶段的代谢变化，为前 MetS 和 MetS 的鉴别诊断提供有价值的见解。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/797f/10979736/e640402c2eae/fendo-15-1335269-g006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/797f/10979736/7f6a54439c79/fendo-15-1335269-g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/797f/10979736/73cc758ab508/fendo-15-1335269-g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/797f/10979736/2255fd5be586/fendo-15-1335269-g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/797f/10979736/e2a61dbb30d7/fendo-15-1335269-g004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/797f/10979736/64064865abc2/fendo-15-1335269-g005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/797f/10979736/e640402c2eae/fendo-15-1335269-g006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/797f/10979736/7f6a54439c79/fendo-15-1335269-g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/797f/10979736/73cc758ab508/fendo-15-1335269-g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/797f/10979736/2255fd5be586/fendo-15-1335269-g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/797f/10979736/e2a61dbb30d7/fendo-15-1335269-g004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/797f/10979736/64064865abc2/fendo-15-1335269-g005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/797f/10979736/e640402c2eae/fendo-15-1335269-g006.jpg

相似文献

1
Integrating machine learning and nontargeted plasma lipidomics to explore lipid characteristics of premetabolic syndrome and metabolic syndrome.将机器学习与非靶向血浆脂质组学相结合，探索代谢综合征前和代谢综合征的脂质特征。
Front Endocrinol (Lausanne). 2024 Mar 15;15:1335269. doi: 10.3389/fendo.2024.1335269. eCollection 2024.
2
Machine learning of plasma metabolome identifies biomarker panels for metabolic syndrome: findings from the China Suboptimal Health Cohort.基于血浆代谢组学的机器学习方法鉴定出代谢综合征的生物标志物组合：来自中国亚健康队列研究的发现。
Cardiovasc Diabetol. 2022 Dec 23;21(1):288. doi: 10.1186/s12933-022-01716-0.
3
Integrative Lipidomics and Metabolomics for System-Level Understanding of the Metabolic Syndrome in Long-Term Treated HIV-Infected Individuals.整合脂质组学和代谢组学研究以深入了解长期接受抗 HIV 治疗的个体中的代谢综合征。
Front Immunol. 2022 Jan 12;12:742736. doi: 10.3389/fimmu.2021.742736. eCollection 2021.
4
Lipidomics random forest algorithm of seminal plasma is a promising method for enhancing the diagnosis of necrozoospermia.精液脂质组学随机森林算法是提高死精子症诊断的有前途的方法。
Metabolomics. 2024 May 21;20(3):57. doi: 10.1007/s11306-024-02118-x.
5
Identification of three potential novel biomarkers for early diagnosis of acute ischemic stroke via plasma lipidomics.通过血浆脂质组学鉴定三种用于急性缺血性脑卒中早期诊断的潜在新型生物标志物。
Metabolomics. 2023 Mar 30;19(4):32. doi: 10.1007/s11306-023-01990-3.
6
Combining metabolome and clinical indicators with machine learning provides some promising diagnostic markers to precisely detect smear-positive/negative pulmonary tuberculosis.将代谢组学和临床指标与机器学习相结合，为精确检测菌阳/菌阴肺结核提供了一些有前途的诊断标志物。
BMC Infect Dis. 2022 Aug 25;22(1):707. doi: 10.1186/s12879-022-07694-8.
7
Targeted quantitative lipidomic uncovers lipid biomarkers for predicting the presence of compensated cirrhosis and discriminating decompensated cirrhosis from compensated cirrhosis.靶向定量脂质组学揭示了预测代偿性肝硬化和区分失代偿性肝硬化与代偿性肝硬化的脂质生物标志物。
Clin Chem Lab Med. 2023 Nov 6;62(3):506-521. doi: 10.1515/cclm-2023-0798. Print 2024 Feb 26.
8
Discovery of metabolite profiles of metabolic syndrome using untargeted and targeted LC-MS based lipidomics approach.采用非靶向和靶向 LC-MS 脂质组学方法发现代谢综合征的代谢物特征。
J Pharm Biomed Anal. 2020 Jan 5;177:112848. doi: 10.1016/j.jpba.2019.112848. Epub 2019 Aug 29.
9
n-3 PUFA and caloric restriction diet alters lipidomic profiles in obese men with metabolic syndrome: a preliminary open study.n-3 多不饱和脂肪酸和热量限制饮食改变代谢综合征肥胖男性的脂质组学谱：初步开放研究。
Eur J Nutr. 2020 Oct;59(7):3103-3112. doi: 10.1007/s00394-019-02149-4. Epub 2019 Dec 21.
10
Combining lipidomics and machine learning to measure clinical lipids in dried blood spots.运用脂质组学和机器学习技术测定干血斑中的临床脂质。
Metabolomics. 2020 Jul 24;16(8):83. doi: 10.1007/s11306-020-01703-0.

本文引用的文献

1
Plasma metabolic fingerprints for large-scale screening and personalized risk stratification of metabolic syndrome.血浆代谢指纹图谱用于代谢综合征的大规模筛查和个体化风险分层。
Cell Rep Med. 2023 Jul 18;4(7):101109. doi: 10.1016/j.xcrm.2023.101109.
2
Investigation of prodromal features in metabolic syndrome based on transcriptome analysis.基于转录组分析对代谢综合征前驱特征的研究。
Genes Dis. 2022 Aug 19;10(3):708-711. doi: 10.1016/j.gendis.2022.07.021. eCollection 2023 May.
3
Machine learning-based predictive model for prevention of metabolic syndrome.
基于机器学习的代谢综合征预防预测模型。
PLoS One. 2023 Jun 2;18(6):e0286635. doi: 10.1371/journal.pone.0286635. eCollection 2023.
4
Untargeted Lipidomic Profiling Reveals Lysophosphatidylcholine and Ceramide as Atherosclerotic Risk Factors in Knockout Mice.非靶向脂质组学分析揭示溶血磷脂酰胆碱和神经酰胺是敲除小鼠的动脉粥样硬化风险因子。
Int J Mol Sci. 2023 Apr 9;24(8):6956. doi: 10.3390/ijms24086956.
5
Mass-Spectrometry-Based Lipidomics Discriminates Specific Changes in Lipid Classes in Healthy and Dyslipidemic Adults.基于质谱的脂质组学可区分健康和血脂异常成年人脂质类别的特定变化。
Metabolites. 2023 Feb 3;13(2):222. doi: 10.3390/metabo13020222.
6
siMS score- method for quantification of metabolic syndrome, confirms co-founding factors of metabolic syndrome.siMS评分——代谢综合征的量化方法，确定了代谢综合征的共同致病因素。
Front Genet. 2023 Jan 4;13:1041383. doi: 10.3389/fgene.2022.1041383. eCollection 2022.
7
The association between metabolic syndrome and heart failure in middle-aged male and female: Korean population-based study of 2 million individuals.代谢综合征与中年男女心力衰竭的关联：基于韩国 200 万人群的研究。
Epidemiol Health. 2022;44:e2022078. doi: 10.4178/epih.e2022078. Epub 2022 Sep 21.
8
Prediction of metabolic and pre-metabolic syndromes using machine learning models with anthropometric, lifestyle, and biochemical factors from a middle-aged population in Korea.使用来自韩国中年人群的人体测量学、生活方式和生化因素的机器学习模型预测代谢和前代谢综合征。
BMC Public Health. 2022 Apr 6;22(1):664. doi: 10.1186/s12889-022-13131-x.
9
Selected Organ and Endocrine Complications According to BMI and the Metabolic Category of Obesity: A Single Endocrine Center Study.根据 BMI 和肥胖代谢类别选择的器官和内分泌并发症：单一生殖内分泌中心研究。
Nutrients. 2022 Mar 20;14(6):1307. doi: 10.3390/nu14061307.
10
The maternal blood lipidome is indicative of the pathogenesis of severe preeclampsia.母体血液脂质组学可提示重度子痫前期的发病机制。
J Lipid Res. 2021;62:100118. doi: 10.1016/j.jlr.2021.100118. Epub 2021 Sep 20.