Mattern Sven, Hollfoth Vanessa, Bag Eyyub, Ali Arslan, Riemenschneider Philip, Jarboui Mohamed A, Boldt Karsten, Sulyok Mihaly, Dickemann Anabel, Luibrand Julia, Fusco Stefano, Franz-Wachtel Mirita, Singer Kerstin, Goeppert Benjamin, Schilling Oliver, Malek Nisar, Fend Falko, Macek Boris, Ueffing Marius, Singer Stephan
Department of Pathology and Neuropathology, University of Tübingen, Tübingen, Germany.
Center for Personalized Medicine (ZPM), Tübingen, Germany.
EMBO Mol Med. 2025 Mar;17(3):441-468. doi: 10.1038/s44321-025-00194-7. Epub 2025 Feb 3.
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.
食管炎是一种常见疾病,但在分子水平上其特征尚不明确,病因和治疗方法多样。由于组织学特征部分重叠,正确诊断具有挑战性。通过对代表对照、反流性(GERD)、嗜酸性(EoE)、克罗恩病(CD)、单纯疱疹(HSV)和念珠菌(CA)性食管炎的常规诊断FFPE活检标本(n = 55)进行液相色谱-串联质谱(DIA)蛋白质组分析,我们确定了不同的特征和功能网络(如线粒体翻译(EoE)、免疫蛋白酶体、补体和凝血系统(CD)、核糖体生物合成(GERD)),以及HSV和CA的病原体特异性蛋白质。此外,在机器学习模型中将这些特征与组织学参数相结合,实现了较高的诊断准确性(训练集为100%,测试集为93.8%),并为临界/具有挑战性的病例的诊断决策提供了支持。将其应用于一名代表用例的年轻患者,GERD的外部诊断可修订为CD,并且ICAM1被确定为高度丰富的治疗靶点。这导致环孢素A成为当地多学科分子炎症委员会的个性化治疗建议。我们整合的人工智能辅助形态蛋白质组学方法能够更深入地了解疾病特异性分子改变,是食管炎相关精准医学中一种很有前景的工具。