Integrative machine learning identifies robust inflammation-related diagnostic biomarkers and stratifies immune-heterogeneous subtypes in Kawasaki disease.

IF 2.8 3区医学 Q1 PEDIATRICS

Pediatric Rheumatology Pub Date : 2025-06-02 DOI:10.1186/s12969-025-01114-2

Xia Wang, Lin Zhang

{"title":"Integrative machine learning identifies robust inflammation-related diagnostic biomarkers and stratifies immune-heterogeneous subtypes in Kawasaki disease.","authors":"Xia Wang, Lin Zhang","doi":"10.1186/s12969-025-01114-2","DOIUrl":null,"url":null,"abstract":"Background: Kawasaki disease (KD), a pediatric systemic vasculitis, lacks reliable diagnostic biomarkers and exhibits immune heterogeneity, complicating clinical management. Current therapies face challenges in targeting specific immune pathways and predicting treatment responses.Methods: Multi-cohort transcriptomic data were integrated to identify inflammation-related genes (IRGs). Differential analysis, weighted gene co-expression network analysis (WGCNA), and machine learning algorithms (LASSO, Boruta, SVM-RFE, Random Forest) were applied to screen diagnostic biomarkers. Immune infiltration and molecular subtyping based on diagnostic biomarkers were analyzed, complemented by regulatory network analysis to explore transcriptional, pharmacological, and miRNA interactions.Results: Six robust diagnostic biomarkers (ADM, ALPL, FCGR1A, HP, S100A12, SLC22A4) were identified, achieving AUC > 0.9 in cohorts. KD exhibited elevated neutrophils, monocytes, and Tregs but reduced CD8 + T cells and cytolytic activity. Consensus clustering stratified KD into two immune-heterogeneous subtypes: Cluster1 (neutrophil/Treg-dominant, enriched in TLR signaling) and Cluster2 (B cell/CD8 + T cell-dominant, linked to cytolytic activity). Regulatory networks revealed subtype-specific transcriptional regulators and therapeutic agents.Conclusion: This study establishes inflammation-related diagnostic biomarkers and immune-stratified subtypes for KD, offering a framework for precision immunomodulatory therapies.","PeriodicalId":54630,"journal":{"name":"Pediatric Rheumatology","volume":"23 1","pages":"61"},"PeriodicalIF":2.8000,"publicationDate":"2025-06-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12128390/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Pediatric Rheumatology","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1186/s12969-025-01114-2","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"PEDIATRICS","Score":null,"Total":0}

引用次数: 0

Abstract

Background: Kawasaki disease (KD), a pediatric systemic vasculitis, lacks reliable diagnostic biomarkers and exhibits immune heterogeneity, complicating clinical management. Current therapies face challenges in targeting specific immune pathways and predicting treatment responses.

Methods: Multi-cohort transcriptomic data were integrated to identify inflammation-related genes (IRGs). Differential analysis, weighted gene co-expression network analysis (WGCNA), and machine learning algorithms (LASSO, Boruta, SVM-RFE, Random Forest) were applied to screen diagnostic biomarkers. Immune infiltration and molecular subtyping based on diagnostic biomarkers were analyzed, complemented by regulatory network analysis to explore transcriptional, pharmacological, and miRNA interactions.

Results: Six robust diagnostic biomarkers (ADM, ALPL, FCGR1A, HP, S100A12, SLC22A4) were identified, achieving AUC > 0.9 in cohorts. KD exhibited elevated neutrophils, monocytes, and Tregs but reduced CD8 + T cells and cytolytic activity. Consensus clustering stratified KD into two immune-heterogeneous subtypes: Cluster1 (neutrophil/Treg-dominant, enriched in TLR signaling) and Cluster2 (B cell/CD8 + T cell-dominant, linked to cytolytic activity). Regulatory networks revealed subtype-specific transcriptional regulators and therapeutic agents.

Conclusion: This study establishes inflammation-related diagnostic biomarkers and immune-stratified subtypes for KD, offering a framework for precision immunomodulatory therapies.

查看原文本刊更多论文

综合机器学习识别强大的炎症相关诊断生物标志物，并在川崎病中分层免疫异质亚型。

背景：川崎病（Kawasaki disease， KD）是一种小儿全身性血管炎，缺乏可靠的诊断生物标志物，且表现出免疫异质性，使临床治疗复杂化。目前的治疗方法在靶向特定免疫途径和预测治疗反应方面面临挑战。方法：整合多队列转录组学数据，鉴定炎症相关基因（IRGs）。采用差异分析、加权基因共表达网络分析（WGCNA）和机器学习算法（LASSO、Boruta、SVM-RFE、Random Forest）筛选诊断性生物标志物。研究人员分析了基于诊断性生物标志物的免疫浸润和分子分型，并辅以调控网络分析来探索转录、药理学和miRNA相互作用。结果：鉴定出6个可靠的诊断性生物标志物（ADM、ALPL、FCGR1A、HP、S100A12、SLC22A4），在队列中达到了AUC (AUC) 0.9。KD表现出中性粒细胞、单核细胞和treg升高，但CD8 + T细胞和细胞溶解活性降低。共识聚类将KD分为两种免疫异质性亚型：Cluster1（中性粒细胞/ treg主导，富含TLR信号）和Cluster2 （B细胞/CD8 + T细胞主导，与细胞溶解活性相关）。调控网络揭示了亚型特异性转录调控因子和治疗剂。结论：本研究建立了KD的炎症相关诊断生物标志物和免疫分层亚型，为精确免疫调节治疗提供了框架。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Pediatric Rheumatology PEDIATRICS-RHEUMATOLOGY

CiteScore

4.10

自引率

8.00%

发文量

审稿时长

>12 weeks

期刊介绍： Pediatric Rheumatology is an open access, peer-reviewed, online journal encompassing all aspects of clinical and basic research related to pediatric rheumatology and allied subjects. The journal’s scope of diseases and syndromes include musculoskeletal pain syndromes, rheumatic fever and post-streptococcal syndromes, juvenile idiopathic arthritis, systemic lupus erythematosus, juvenile dermatomyositis, local and systemic scleroderma, Kawasaki disease, Henoch-Schonlein purpura and other vasculitides, sarcoidosis, inherited musculoskeletal syndromes, autoinflammatory syndromes, and others.