Sven Mattern, Vanessa Hollfoth, Eyyub Bag, Arslan Ali, Philip Riemenschneider, Mohamed A Jarboui, Karsten Boldt, Mihaly Sulyok, Anabel Dickemann, Julia Luibrand, Stefano Fusco, Mirita Franz-Wachtel, Kerstin Singer, Benjamin Goeppert, Oliver Schilling, Nisar Malek, Falko Fend, Boris Macek, Marius Ueffing, Stephan Singer
{"title":"An AI-assisted morphoproteomic approach is a supportive tool in esophagitis-related precision medicine.","authors":"Sven Mattern, Vanessa Hollfoth, Eyyub Bag, Arslan Ali, Philip Riemenschneider, Mohamed A Jarboui, Karsten Boldt, Mihaly Sulyok, Anabel Dickemann, Julia Luibrand, Stefano Fusco, Mirita Franz-Wachtel, Kerstin Singer, Benjamin Goeppert, Oliver Schilling, Nisar Malek, Falko Fend, Boris Macek, Marius Ueffing, Stephan Singer","doi":"10.1038/s44321-025-00194-7","DOIUrl":null,"url":null,"abstract":"<p><p>Esophagitis is a frequent, but at the molecular level poorly characterized condition with diverse underlying etiologies and treatments. Correct diagnosis can be challenging due to partially overlapping histological features. By proteomic profiling of routine diagnostic FFPE biopsy specimens (n = 55) representing controls, Reflux- (GERD), Eosinophilic-(EoE), Crohn's-(CD), Herpes simplex (HSV) and Candida (CA)-esophagitis by LC-MS/MS (DIA), we identified distinct signatures and functional networks (e.g. mitochondrial translation (EoE), immunoproteasome, complement and coagulations system (CD), ribosomal biogenesis (GERD)), and pathogen-specific proteins for HSV and CA. Moreover, combining these signatures with histological parameters in a machine learning model achieved high diagnostic accuracy (100% training set, 93.8% test set), and supported diagnostic decisions in borderline/challenging cases. Applied to a young patient representing a use case, the external GERD diagnosis could be revised to CD and ICAM1 was identified as highly abundant therapeutic target. This resulted in CyclosporinA as a personalized treatment recommendation by the local multidisciplinary molecular inflammation board. Our integrated AI-assisted morphoproteomic approach allows deeper insights in disease-specific molecular alterations and represents a promising tool in esophagitis-related precision medicine.</p>","PeriodicalId":11597,"journal":{"name":"EMBO Molecular Medicine","volume":" ","pages":"441-468"},"PeriodicalIF":9.0000,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11903792/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"EMBO Molecular Medicine","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1038/s44321-025-00194-7","RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2025/2/3 0:00:00","PubModel":"Epub","JCR":"Q1","JCRName":"MEDICINE, RESEARCH & EXPERIMENTAL","Score":null,"Total":0}
引用次数: 0
摘要
食管炎是一种常见病,但在分子水平上特征不清,其潜在病因和治疗方法多种多样。由于组织学特征部分重叠,正确诊断具有挑战性。通过 LC-MS/MS (DIA) 对常规诊断性 FFPE 活检标本(n = 55)进行蛋白质组分析,我们发现了代表对照组、反流性(胃食管反流病)、嗜酸性(EoE)、克罗恩病(CD)、单纯疱疹(HSV)和念珠菌(CA)食管炎的不同特征和功能网络(如线粒体翻译)。如线粒体翻译(EoE)、免疫蛋白酶体、补体和凝血系统(CD)、核糖体生物发生(胃食管反流病))以及 HSV 和 CA 的病原体特异性蛋白。此外,在机器学习模型中将这些特征与组织学参数相结合,可获得很高的诊断准确率(100% 训练集,93.8% 测试集),并支持对边缘/疑难病例做出诊断决定。将该模型应用于代表用例的一名年轻患者,可将胃食管反流病的外部诊断修改为慢性胃食管炎,并确定 ICAM1 为高度丰富的治疗靶点。因此,当地多学科分子炎症委员会推荐使用环孢素 A 进行个性化治疗。我们的综合人工智能辅助形态蛋白组学方法可以深入了解疾病的特异性分子改变,是食管炎相关精准医疗领域前景广阔的工具。
An AI-assisted morphoproteomic approach is a supportive tool in esophagitis-related precision medicine.
Esophagitis is a frequent, but at the molecular level poorly characterized condition with diverse underlying etiologies and treatments. Correct diagnosis can be challenging due to partially overlapping histological features. By proteomic profiling of routine diagnostic FFPE biopsy specimens (n = 55) representing controls, Reflux- (GERD), Eosinophilic-(EoE), Crohn's-(CD), Herpes simplex (HSV) and Candida (CA)-esophagitis by LC-MS/MS (DIA), we identified distinct signatures and functional networks (e.g. mitochondrial translation (EoE), immunoproteasome, complement and coagulations system (CD), ribosomal biogenesis (GERD)), and pathogen-specific proteins for HSV and CA. Moreover, combining these signatures with histological parameters in a machine learning model achieved high diagnostic accuracy (100% training set, 93.8% test set), and supported diagnostic decisions in borderline/challenging cases. Applied to a young patient representing a use case, the external GERD diagnosis could be revised to CD and ICAM1 was identified as highly abundant therapeutic target. This resulted in CyclosporinA as a personalized treatment recommendation by the local multidisciplinary molecular inflammation board. Our integrated AI-assisted morphoproteomic approach allows deeper insights in disease-specific molecular alterations and represents a promising tool in esophagitis-related precision medicine.
期刊介绍:
EMBO Molecular Medicine is an open access journal in the field of experimental medicine, dedicated to science at the interface between clinical research and basic life sciences. In addition to human data, we welcome original studies performed in cells and/or animals provided they demonstrate human disease relevance.
To enhance and better specify our commitment to precision medicine, we have expanded the scope of EMM and call for contributions in the following fields:
Environmental health and medicine, in particular studies in the field of environmental medicine in its functional and mechanistic aspects (exposome studies, toxicology, biomarkers, modeling, and intervention).
Clinical studies and case reports - Human clinical studies providing decisive clues how to control a given disease (epidemiological, pathophysiological, therapeutic, and vaccine studies). Case reports supporting hypothesis-driven research on the disease.
Biomedical technologies - Studies that present innovative materials, tools, devices, and technologies with direct translational potential and applicability (imaging technologies, drug delivery systems, tissue engineering, and AI)