Identification of distinct immune signatures in inclusion body myositis by peripheral blood immunophenotyping using machine learning models

IF 4.6 2区 医学 Q2 IMMUNOLOGY
Emily McLeish, Anuradha Sooda, Nataliya Slater, Kelly Beer, Ian Cooper, Frank L Mastaglia, Merrilee Needham, Jerome D Coudert
{"title":"Identification of distinct immune signatures in inclusion body myositis by peripheral blood immunophenotyping using machine learning models","authors":"Emily McLeish,&nbsp;Anuradha Sooda,&nbsp;Nataliya Slater,&nbsp;Kelly Beer,&nbsp;Ian Cooper,&nbsp;Frank L Mastaglia,&nbsp;Merrilee Needham,&nbsp;Jerome D Coudert","doi":"10.1002/cti2.1504","DOIUrl":null,"url":null,"abstract":"<div>\n \n \n <section>\n \n <h3> Objective</h3>\n \n <p>Inclusion body myositis (IBM) is a progressive late-onset muscle disease characterised by preferential weakness of quadriceps femoris and finger flexors, with elusive causes involving immune, degenerative, genetic and age-related factors. Overlapping with normal muscle ageing makes diagnosis and prognosis problematic.</p>\n </section>\n \n <section>\n \n <h3> Methods</h3>\n \n <p>We characterised peripheral blood leucocytes in 81 IBM patients and 45 healthy controls using flow cytometry. Using a random forest classifier, we identified immune changes in IBM compared to HC. K-means clustering and the random forest one-versus-rest model classified patients into three immunophenotypic clusters. Functional outcome measures including mTUG, 2MWT, IBM-FRS, EAT-10, knee extension and grip strength were assessed across clusters.</p>\n </section>\n \n <section>\n \n <h3> Results</h3>\n \n <p>The random forest model achieved a 94% AUC ROC with 82.76% specificity and 100% sensitivity. Significant differences were found in IBM patients, including increased CD8<sup>+</sup> T-bet<sup>+</sup> cells, CD4<sup>+</sup> T cells skewed towards a Th1 phenotype and altered γδ T cell repertoire with a reduced proportion of Vγ9<sup>+</sup>Vδ2<sup>+</sup> cells. IBM patients formed three clusters: (i) activated and inflammatory CD8<sup>+</sup> and CD4<sup>+</sup> T-cell profile and the highest proportion of anti-cN1A-positive patients in cluster 1; (ii) limited inflammation in cluster 2; (iii) highly differentiated, pro-inflammatory T-cell profile in cluster 3. Additionally, no significant differences in patients' age and gender were detected between immunophenotype clusters; however, worsening trends were detected with several functional outcomes.</p>\n </section>\n \n <section>\n \n <h3> Conclusion</h3>\n \n <p>These findings unveil distinct immune profiles in IBM, shedding light on underlying pathological mechanisms for potential immunoregulatory therapeutic development.</p>\n </section>\n </div>","PeriodicalId":152,"journal":{"name":"Clinical & Translational Immunology","volume":"13 4","pages":""},"PeriodicalIF":4.6000,"publicationDate":"2024-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/cti2.1504","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Clinical & Translational Immunology","FirstCategoryId":"3","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1002/cti2.1504","RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"IMMUNOLOGY","Score":null,"Total":0}
引用次数: 0

Abstract

Objective

Inclusion body myositis (IBM) is a progressive late-onset muscle disease characterised by preferential weakness of quadriceps femoris and finger flexors, with elusive causes involving immune, degenerative, genetic and age-related factors. Overlapping with normal muscle ageing makes diagnosis and prognosis problematic.

Methods

We characterised peripheral blood leucocytes in 81 IBM patients and 45 healthy controls using flow cytometry. Using a random forest classifier, we identified immune changes in IBM compared to HC. K-means clustering and the random forest one-versus-rest model classified patients into three immunophenotypic clusters. Functional outcome measures including mTUG, 2MWT, IBM-FRS, EAT-10, knee extension and grip strength were assessed across clusters.

Results

The random forest model achieved a 94% AUC ROC with 82.76% specificity and 100% sensitivity. Significant differences were found in IBM patients, including increased CD8+ T-bet+ cells, CD4+ T cells skewed towards a Th1 phenotype and altered γδ T cell repertoire with a reduced proportion of Vγ9+Vδ2+ cells. IBM patients formed three clusters: (i) activated and inflammatory CD8+ and CD4+ T-cell profile and the highest proportion of anti-cN1A-positive patients in cluster 1; (ii) limited inflammation in cluster 2; (iii) highly differentiated, pro-inflammatory T-cell profile in cluster 3. Additionally, no significant differences in patients' age and gender were detected between immunophenotype clusters; however, worsening trends were detected with several functional outcomes.

Conclusion

These findings unveil distinct immune profiles in IBM, shedding light on underlying pathological mechanisms for potential immunoregulatory therapeutic development.

Abstract Image

利用机器学习模型通过外周血免疫分型鉴定包涵体肌炎的独特免疫特征
目的 包涵体肌炎(IBM)是一种渐进性晚发肌肉疾病,以股四头肌和手指屈肌无力为特征,病因难以捉摸,涉及免疫、退行性、遗传和年龄相关因素。该病与正常肌肉老化重叠,因此诊断和预后存在问题。 方法 我们使用流式细胞术鉴定了 81 名 IBM 患者和 45 名健康对照者的外周血白细胞。使用随机森林分类器,我们确定了 IBM 与 HC 相比的免疫变化。K-means 聚类和随机森林单对单模型将患者分为三个免疫表型群。对不同群组的功能结果进行评估,包括 mTUG、2MWT、IBM-FRS、EAT-10、膝关节伸展和握力。 结果 随机森林模型的 AUC ROC 为 94%,特异性为 82.76%,灵敏度为 100%。在 IBM 患者中发现了显著差异,包括 CD8+ T-bet+ 细胞增加、CD4+ T 细胞偏向 Th1 表型、γδ T 细胞群发生改变,Vγ9+Vδ2+ 细胞比例降低。IBM 患者形成了三个群:(i) 活化和炎症性 CD8+ 和 CD4+ T 细胞谱,抗 N1A 阳性患者比例最高的是第 1 群;(ii) 局限性炎症的是第 2 群;(iii) 高分化、促炎症性 T 细胞谱的是第 3 群。此外,免疫表型群组之间在患者年龄和性别方面没有发现明显差异;但在几种功能结果方面发现了恶化趋势。 结论 这些发现揭示了 IBM 患者不同的免疫特征,为潜在免疫调节疗法的开发揭示了潜在的病理机制。
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
Clinical & Translational Immunology
Clinical & Translational Immunology Medicine-Immunology and Allergy
CiteScore
12.00
自引率
1.70%
发文量
77
审稿时长
13 weeks
期刊介绍: Clinical & Translational Immunology is an open access, fully peer-reviewed journal devoted to publishing cutting-edge advances in biomedical research for scientists and physicians. The Journal covers fields including cancer biology, cardiovascular research, gene therapy, immunology, vaccine development and disease pathogenesis and therapy at the earliest phases of investigation.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信