EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Urine IRF4/PENK/PXDN Methylation Signatures Enable Machine Learning-Driven Bladder Cancer Detection and Microenvironment Dissection

Urine-IRF4/PENK/PXDN-Methylierungssignaturen ermöglichen eine maschinelles Lernen gestützte Blasenkrebs-Erkennung und Analyse der Tumormikroumgebung

Yi He, Wenhua Xie, Wei Chen, Shengjie Dai, Xintao Wang, Xiaokai Zhao, Siyu Lei, Wei Zhu, Yi Qian, Jinpeng Feng, Ziying Gong, Jieyi Li und 6 weitere

Technology in Cancer Research & Treatment · 2026-06 · 25

DOI: 10.1177/15330338261453486 ↗

Auf einen Blick

In einer prospektiven Kohorte verbesserte ein Urin-Test mit maschinellem Lernen die Erkennung von Blasenkrebs. Das Modell zeigte eine sehr gute Trennschärfe gegenüber Nicht-BC.

Fragestellung

Kann ein urinbasierter Methylierungstest mit maschinellem Lernen Blasenkrebs zuverlässig von Nicht-Blasenkrebs unterscheiden?

Methode

Prospektive Kohorte an einem Krankenhaus (Mai 2022 bis November 2023); 155 Personen; Urin-DNA-Analyse an 44 CpG-Stellen in IRF4, PENK und PXDN; random forest.

Ergebnisse

155 Urinproben (68 BC, 87 non-BC). IRF4, PENK und PXDN waren bei BC stärker methyliert (P < 0,0001). Das BladderCando-Modell erreichte AUC 0,9783 und F1 0,9773 und war der Urinzytologie bei Low-grade-BC überlegen.

Schlussfolgerung der Autor:innen

Die Autor:innen schließen, dass die Urin-Methylierung von IRF4, PENK und PXDN robuste molekulare Signaturen für die BC-Diagnose sind und die maschinelle Lernintegration die diagnostische Präzision deutlich erhöht.

Kernaussagen

  • IRF4, PENK und PXDN waren bei BC stärker methyliert
  • BladderCando: AUC 0,9783; F1 0,9773
  • Besser als Urinzytologie bei Low-grade-BC

Deutsche Zusammenfassung: KI-gestützt aus dem Original-Abstract erstellt; alle Zahlen wurden automatisch mit dem Original abgeglichen. Maßgeblich ist der Original-Abstract.

Kurz gefasst

Fachartikel in der Zeitschrift Technology in Cancer Research & Treatment, online erschienen am 11.06.2026. Verfasst von Yi He und 17 weiteren Autor:innen. Beteiligte Einrichtung: Department of Urology, The Affiliated Hospital of Jiaxing University, Jiaxing, China. Hauptthemen laut MEDLINE: DNA Methylation, Interferon Regulatory Factors, Urinary Bladder Neoplasms, Machine Learning. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: Yi He, Daoyun Zhang.

Auf einen BlickAbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Introduction

Cystoscopy-based diagnosis and surveillance of bladder cancer (BC) remain challenging. This study presents a urine-based assay that enriches DNA-methylation signals via PCR enrichment and applies a machine-learning model to enable cost-effective early detection.

Methods

In a prospective cohort at hospital (May 2022-November 2023), 155 individuals were enrolled, BC was diagnosed and confirmed by cystoscopy-guided biopsy and histopathology. Targeted next-generation sequencing of urine DNA quantified methylation at 44 CpG sites within IRF4, PENK and PXDN. Supervised classifiers trained on these features distinguished tumor from non-tumor urine samples. Systems analyses around IRF4/PENK/PXDN mapped signaling pathways, protein interaction modules and tumor-microenvironment contexts in BC.

Results

Using 155 urine samples (68 BC, 87 non-BC) with methylation and transcript expression data in TCGA-BLCA, we found significantly increased methylation of IRF4, PENK, and PXDN in BC (P < 0.0001). Corresponding mRNA levels of IRF4 and PENK were significantly downregulated in tumor tissues, with PXDN showing a declining trend. Methylation of IRF4 and PXDN negatively correlated with their expression (P < 0.0001). A 41-CpG-site random forest classifier targeting IRF4, PENK, and PXND (BladderCando model) demonstrated excellent performance in distinguishing BC from non-BC individuals (AUC = 0.9783, F1 = 0.9773), outperforming urine cytology for low-grade BC detection. Co-expression and enrichment analyses identified DCN as a central hub gene, primarily linked to ECM functions. High expression of PXDN, IRF4, and DCN correlated with upregulated immune checkpoint genes and increased immune cell infiltration. Single-cell sequencing revealed PXDN in fibroblasts and endothelial cells, DCN in fibroblasts, and IRF4 in T cells, with expression patterns in urine mirroring tumor tissue profiles.

Conclusion

This study establishes IRF4, PENK and PXDN methylation in urine as robust molecular signatures for BC detection, with machine-learning integration markedly enhancing diagnostic precision. Beyond early surveillance, these epigenetic alterations delineate tumor-microenvironment interactions that may inform future therapeutic strategies.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

DNA MethylationInterferon Regulatory FactorsUrinary Bladder NeoplasmsMachine LearningTumor MicroenvironmentBiomarkers, TumorHumansInterferon Regulatory Factor-4FemaleMaleAgedMiddle AgedGene Expression Regulation, NeoplasticProspective StudiesCpG Islands

Stichwörter der Autor:innen

DNA methylationbladder cancerimmune cell infiltrationtumor-microenvironmenturine

Substanzen

Interferon Regulatory FactorsInterferon Regulatory Factor-4Biomarkers, Tumor

Autor:innen und Institutionen

  • Department of Urology, The Affiliated Hospital of Jiaxing University, Jiaxing, China.
  • Jiaxing University Master Degree Cultivation Base, Zhejiang Chinese Medical University, Jiaxing, China.
  • Jiaxing Key Laboratory for Precision Diagnosis and Therapy of Urologic Oncology, The First Hospital of Jiaxing, Jiaxing, China.
  • Clinical Medicine Class, College of Xingshen, Jiaxing University, Jiaxing, China.
  • Jiaxing Key Laboratory of Precision Medicine and Companion Diagnostics, Jiaxing Yunying Medical Inspection Co., Ltd., Jiaxing, China.
  • Department of R&D, Shanghai Yunying Biopharmaceutical Technology Co., Ltd., Shanghai, China.

ORCID-Profile: Jing Jin

Förderung

  • Yi He
  • Daoyun Zhang

Zitieren

APA

He, Y., Xie, W., Chen, W., Dai, S., Wang, X., Zhao, X., Lei, S., Zhu, W., Qian, Y., Feng, J., Gong, Z., Li, J., Yang, P., Xu, X., Fei, W., Zhang, D., Cao, Y., & Jin, J. (2026). Urine IRF4/PENK/PXDN Methylation Signatures Enable Machine Learning-Driven Bladder Cancer Detection and Microenvironment Dissection. Technology in Cancer Research & Treatment, 25. https://doi.org/10.1177/15330338261453486

Vancouver

He Y, Xie W, Chen W, Dai S, Wang X, Zhao X, et al. Urine IRF4/PENK/PXDN Methylation Signatures Enable Machine Learning-Driven Bladder Cancer Detection and Microenvironment Dissection. Technology in Cancer Research & Treatment. 2026;25. doi:10.1177/15330338261453486

BibTeX
@article{He2026,
  author = {He, Yi and Xie, Wenhua and Chen, Wei and Dai, Shengjie and Wang, Xintao and Zhao, Xiaokai and Lei, Siyu and Zhu, Wei and Qian, Yi and Feng, Jinpeng and Gong, Ziying and Li, Jieyi and Yang, Pengmin and Xu, Xinyu and Fei, Wenjie and Zhang, Daoyun and Cao, Yifang and Jin, Jing},
  title = {Urine IRF4/PENK/PXDN Methylation Signatures Enable Machine Learning-Driven Bladder Cancer Detection and Microenvironment Dissection},
  journal = {Technology in Cancer Research & Treatment},
  year = {2026},
  volume = {25},
  doi = {10.1177/15330338261453486}
}
Kostenlos starten →