Integrating machine learning algorithms and single-cell analysis to identify gut microbiota-related macrophage biomarkers in atherosclerotic plaques

被引:0
|
作者
Ke, Yin [1 ,2 ]
Yue, Jian [3 ]
He, Jiaming [4 ]
Liu, Guojing [1 ]
机构
[1] Chongqing Med Univ, Dept Neurosurg, Univ Town Hosp, Chongqing, Peoples R China
[2] Maternal & Child Hlth Hosp Yong Chuan, Dept Nursing, Chongqing, Peoples R China
[3] Gaozhou Peoples Hosp, Dept Breast Surg, Gaozhou, Peoples R China
[4] Chongqing Med Univ, Inst Life Sci, Chongqing, Peoples R China
关键词
gut microbiota; macrophage; machine learning; atherosclerotic plaques; bioinformatics; IMMUNOMETABOLISM; INFLAMMATION;
D O I
10.3389/fcimb.2024.1395716
中图分类号
R392 [医学免疫学]; Q939.91 [免疫学];
学科分类号
100102 ;
摘要
Objective The relationship between macrophages and the gut microbiota in patients with atherosclerosis remains poorly defined, and effective biological markers are lacking. This study aims to elucidate the interplay between gut microbial communities and macrophages, and to identify biomarkers associated with the destabilization of atherosclerotic plaques. The goal is to enhance our understanding of the underlying molecular pathways and to pave new avenues for diagnostic approaches and therapeutic strategies in the disease.Methods This study employed Weighted Gene Co-expression Network Analysis (WGCNA) and differential expression analysis on atherosclerosis datasets to identify macrophage-associated genes and quantify the correlation between these genes and gut microbiota gene sets. The Random Forest algorithm was utilized to pinpoint PLEK, IRF8, BTK, CCR1, and CD68 as gut microbiota-related macrophage genes, and a nomogram was constructed. Based on the top five genes, a Non-negative Matrix Factorization (NMF) algorithm was applied to construct gut microbiota-related macrophage clusters and analyze their potential biological alterations. Subsequent single-cell analyses were conducted to observe the expression patterns of the top five genes and the interactions between immune cells. Finally, the expression profiles of key molecules were validated using clinical samples from atherosclerosis patients.Results Utilizing the Random Forest algorithm, we ultimately identified PLEK, IRF8, CD68, CCR1, and BTK as gut microbiota-associated macrophage genes that are upregulated in atherosclerotic plaques. A nomogram based on the expression of these five genes was constructed for use as an auxiliary tool in clinical diagnosis. Single-cell analysis confirmed the specific expression of gut microbiota-associated macrophage genes in macrophages. Clinical samples substantiated the high expression of PLEK in unstable atherosclerotic plaques.Conclusion Gut microbiota-associated macrophage genes (PLEK, IRF8, CD68, CCR1, and BTK) may be implicated in the pathogenesis of atherosclerotic plaques and could serve as diagnostic markers to aid patients with atherosclerosis.
引用
收藏
页数:12
相关论文
共 50 条
  • [41] Identification of Disulfidptosis-Related Genes in Ischemic Stroke by Combining Single-Cell Sequencing, Machine Learning Algorithms, and In Vitro Experiments
    Zhao, Songyun
    Zhuang, Hao
    Ji, Wei
    Cheng, Chao
    Liu, Yuankun
    NEUROMOLECULAR MEDICINE, 2024, 26 (01)
  • [42] Impact of Mitophagy-Related Genes on the Diagnosis and Development of Esophageal Squamous Cell Carcinoma via Single-Cell RNA-seq Analysis and Machine Learning Algorithms
    Mo, Xuzhi
    Ji, Feng
    Chen, Jianguang
    Yi, Chengcheng
    Wang, Fang
    JOURNAL OF MICROBIOLOGY AND BIOTECHNOLOGY, 2024, 34 (11) : 2362 - 2375
  • [43] Phosphorylation-related genes in lupus nephritis: Single-cell and machine learning insights
    Mou, Lisha
    Chen, Zhihao
    Tian, Xinran
    Lai, Yupeng
    Pu, Zuhui
    Wang, Meiying
    GENES & DISEASES, 2025, 12 (03)
  • [44] Machine Learning Approaches Identify Genes Containing Spatial Information From Single-Cell Transcriptomics Data
    Loher, Phillipe
    Karathanasis, Nestoras
    FRONTIERS IN GENETICS, 2021, 11
  • [45] Machine Learning and Single-Cell Analysis Identify Molecular Features of IPF-Associated Fibroblast Subtypes and Their Implications on IPF Prognosis
    Hou, Jiwei
    Yang, Yanru
    Han, Xin
    Lisi, Sabrina
    Sisto, Margherita
    INTERNATIONAL JOURNAL OF MOLECULAR SCIENCES, 2024, 25 (01)
  • [46] Single-cell Transcriptomics and Machine Learning Approach to Identify Novel Targets to Treat Right Ventricle Hypertrophy
    Dekan, A. A.
    Niihori, M.
    James, J.
    Rafikov, R.
    Rafikova, O.
    AMERICAN JOURNAL OF RESPIRATORY AND CRITICAL CARE MEDICINE, 2023, 207
  • [47] Integrating single-cell analysis and machine learning to create glycosylation-based gene signature for prognostic prediction of uveal melanoma
    Liu, Jianlan
    Zhang, Pengpeng
    Yang, Fang
    Jiang, Keyu
    Sun, Shiyi
    Xia, Zhijia
    Yao, Gang
    Tang, Jian
    FRONTIERS IN ENDOCRINOLOGY, 2023, 14
  • [48] Analysis of transcriptome of single-cell RNA sequencing data using machine learning
    Rajesh, Mothe
    Martha, Sheshikala
    SOFT COMPUTING, 2023, 27 (13) : 9131 - 9141
  • [49] Integrating single-cell RNA-Seq and machine learning to dissect tryptophan metabolism in ulcerative colitis
    Chen, Guorong
    Qi, Hongying
    Jiang, Li
    Sun, Shijie
    Zhang, Junhai
    Yu, Jiali
    Liu, Fang
    Zhang, Yanli
    Du, Shiyu
    JOURNAL OF TRANSLATIONAL MEDICINE, 2024, 22 (01)
  • [50] Integrating single-cell sequencing and machine learning to uncover the role of mitophagy in subtyping and prognosis of esophageal cancer
    Tian, Feng
    He, Xinyang
    Wang, Saiwei
    Liang, Yiwei
    Wang, Zijie
    Hu, Minxuan
    Gao, Yaxian
    APOPTOSIS, 2025, : 1021 - 1041