Identification and validation of interferon-stimulated gene 15 as a biomarker for dermatomyositis - integrated bioinformatics analysis and machine learning

Aug 5, 2026

Upload by Noah

Dermatomyositis (DM) is an autoimmune disease affecting skin and muscles and may progress to fatal complications, making early diagnosis dependent on reliable biomarkers. This study integrates bioinformatics analysis with clinical sample validation to identify and confirm interferon-stimulated gene 15 (ISG15) as a diagnostic marker. Gene expression datasets were merged, hub genes were prioritized using machine learning and WGCNA, and diagnostic performance was assessed by ROC analysis, immunohistochemistry, immune infiltration inference, pathway enrichment, and drug-gene interaction prediction.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages14

Reading Time35 min

AccessFree to download

Background

Disease burden and diagnostic challenges

Type I interferon pathway and ISG15

Methods

Dataset integration and differential expression

Enrichment and hub gene identification

Validation by ROC and immunohistochemistry

Immune infiltration, GSEA, and drug-gene interactions

Results

ISG15 identification and diagnostic performance

Histological validation and immune/pathway associations

Predicted drug targets and docking support

Conclusion

TYPE Original Research PUBLISHED 04 November 2024 DOI 10.3389/fimmu.2024.1429817 OPEN ACCESS EDITED BY Joerg Wenzel, University Hospital Bonn, Germany REVIEWED BY Shuwen Ge, University of Lübeck, Germany Takemichi Fukasawa, The University of Tokyo Graduate School of Medicine, Japan *CORRESPONDENCE Xingwang Wang [1057600702@qq.com](1057600702@qq.com)[ ](1057600702@qq.com)Jianyong Fan [1804508644@qq.com](1804508644@qq.com) †These authors have contributed equally to this work RECEIVED 08 May 2024 ACCEPTED 14 October 2024 PUBLISHED 04 November 2024 CITATION Wang X, Hu H, Yan G, Zheng B, Luo J and Fan J (2024) Identiﬁcation and validation of interferon-stimulated gene 15 as a biomarker for dermatomyositis by integrated bioinformatics analysis and machine learning. Front. Immunol. 15:1429817 . doi: 10.3389/fimmu.2024.1429817 COPYRIGHT © 2024 Wang, Hu, Yan, Zheng, Luo and Fan. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY) . The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms. Identiﬁcation and validation of interferon-stimulated gene 15 asa biomarker for dermatomyositis by integrated bioinformatics analysis and machine learning Xingwang Wang 1*†, Hao Hu 2†, Guangning Yan 3†, Bo Zheng 1, Jinxia Luo 3 and Jianyong Fan 1* 1 Department of Dermatology, General Hospital of Southern Theater Command, Guangzhou, China, 2 Department of Radiation Therapy, General Hospital of Southern Theater Command, Guangzhou, China, 3 Department of Pathology, General Hospital of Southern Theater Command, Guangzhou, China Background: Dermatomyositis (DM) is an autoimmune disease that primarily affects the skin and muscles. It can lead to increased mortality, particularly when patients develop associated malignancies or experience fatal complications such as pulmonary ﬁbrosis. Identifying reliable biomarkers is essential for the early diagnosis and treatment of DM. This study aims to identify and validate pivotal diagnostic biomarker for DM through integrated bioinformatics analysis and clinical sample validation. Methods: Gene expression datasets GSE46239 and GSE142807 from the Gene Expression Omnibus (GEO) database were merged for analysis. Differentially expressed genes (DEGs) were identiﬁed and subjected to enrichment analysis. Advanced machine learning methods were utilized to further pinpoint hub genes. Weighted gene co‐expression network analysis (WGCNA) was also conducted to discover key gene modules. Subsequently, we derived intersection gene from these methods. The diagnostic performance of the candidate biomarker was evaluated using analysis with dataset GSE128314 and conﬁrmed by immunohistochemistry (IHC) in skin lesion biopsy specimens. The CIBERSORT algorithm was used to analyze immune cell inﬁltration patterns in DM, then the association between the hub gene and immune cells was investigated. Gene set enrichment analysis (GSEA) was performed to understand the biomarker ’s biological functions. Finally, the drug-gene interactions were predicted using the DrugRep server. Results: Interferon-stimulated gene 15 (ISG15) was identiﬁed by intersecting DEGs, advanced machine learning-selected genes and key module genes from WGCNA. ROC analysis showed ISG15 had a high Area under the curve (AUC) of 0.950. IHC ﬁndings conﬁrmed uniformly positive expression of ISG15, particularly in perivascular regions and lymphocytes, contrasting with universally negative expression in controls. Further analysis revealed that ISG15 is involved in abnormalities in various immune cells and inﬂammation-related pathways. We also predicted three drugs targeting ISG15, supported

FAQs

What is the main goal of this study for dermatomyositis?

To identify and validate ISG15 as a pivotal diagnostic biomarker for dermatomyositis by combining integrated bioinformatics with clinical sample validation.

How were candidate genes identified and prioritized?

Differentially expressed genes from merged GEO datasets were analyzed with enrichment methods, advanced machine learning, and weighted gene co-expression network analysis (WGCNA) to select hub genes, followed by intersection of results.

How was ISG15 validated as a diagnostic biomarker?

Diagnostic performance was evaluated using ROC analysis, and immunohistochemistry on skin lesion biopsy specimens confirmed uniformly positive ISG15 expression in DM compared with negative controls.

Aug 5, 2026

Upload by Noah