EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Use of Multiple Machine Learning Approaches for Selecting Urothelial Cancer-Specific DNA Methylation Biomarkers in Urine

Christina U Köhler iD, Karin Schork iD, Michael Turewicz iD, Martin Eisenacher iD, Florian Roghmann iD, Joachim Noldus, Katrin Marcus iD, Thomas Brüning, Heiko U Käfferlein

International Journal of Molecular Sciences · 2024

DOI: 10.3390/ijms25020738 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Molecular Sciences, 2024. Verfasst von Christina U Köhler und 8 weiteren Autor:innen. Beteiligte Einrichtung: Institute for Prevention and Occupational Medicine of the German Social Accident Insurance, Ruhr University Bochum (IPA), Bürkle-de-la-Camp Platz 1, …. Hauptthemen laut MEDLINE: Body Fluids, Neoplasms, Hair Diseases, Langer-Giedion Syndrome. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 48 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: German Network for Bioinformatics Infrastructure (de.NBI), a project of the German Federal Ministry of Education and Research (BMBF), Northrhine-Westphalia, German Network for Bioinformatics Infrastructure (de.NBI).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Diagnosing urothelial cancer (UCa) via invasive cystoscopy is painful, specifically in men, and can cause infection and bleeding. Because the UCa risk is higher for male patients, urinary non-invasive UCa biomarkers are highly desired to stratify men for invasive cystoscopy. We previously identified multiple DNA methylation sites in urine samples that detect UCa with a high sensitivity and specificity in men. Here, we identified the most relevant markers by employing multiple statistical approaches and machine learning (random forest, boosted trees, LASSO) using a dataset of 251 male UCa patients and 111 controls. Three CpG sites located in ALOX5, TRPS1 and an intergenic region on chromosome 16 have been concordantly selected by all approaches, and their combination in a single decision matrix for clinical use was tested based on their respective thresholds of the individual CpGs. The combination of ALOX5 and TRPS1 yielded the best overall sensitivity (61%) at a pre-set specificity of 95%. This combination exceeded both the diagnostic performance of the most sensitive bioinformatic approach and that of the best single CpG. In summary, we showed that overlap analysis of multiple statistical approaches identifies the most reliable biomarkers for UCa in a male collective. The results may assist in stratifying men for cystoscopy.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Body FluidsNeoplasmsHair DiseasesLanger-Giedion SyndromeMaleHumansBiomarkers, TumorDNA MethylationMachine LearningDNA, NeoplasmRepressor ProteinsFingersNose

Stichwörter der Autor:innen

DNA methylation biomarkerLASSOboosted treesrandom foresturothelial cancer

Substanzen

Biomarkers, TumorDNA, NeoplasmTRPS1 protein, humanRepressor Proteins

Autor:innen und Institutionen

  • Institute for Prevention and Occupational Medicine of the German Social Accident Insurance, Ruhr University Bochum (IPA), Bürkle-de-la-Camp Platz 1, 44789 Bochum, Germany.
  • Medizinisches Proteom-Center, Medical Faculty, Ruhr-University Bochum and Medical Proteome Analysis, Center for Protein Diagnostics (PRODI), Gesundheitscampus 4, 44081 Bochum, Germany.
  • Department of Urology, Marien Hospital Herne, University Hospital of the Ruhr University Bochum, Hölkeskampring 40, 44625 Herne, Germany.

ORCID-Profile: Christina U Köhler, Karin Schork, Michael Turewicz, Martin Eisenacher, Florian Roghmann, Katrin Marcus

Förderung

  • German Network for Bioinformatics Infrastructure (de.NBI), a project of the German Federal Ministry of Education and Research (BMBF)
  • Northrhine-Westphalia
  • German Network for Bioinformatics Infrastructure (de.NBI)
  • PURE and VALIBIO
  • CUBiMed.RUB

Zitieren

APA

Köhler, C. U., Schork, K., Turewicz, M., Eisenacher, M., Roghmann, F., Noldus, J., Marcus, K., Brüning, T., & Käfferlein, H. U. (2024). Use of Multiple Machine Learning Approaches for Selecting Urothelial Cancer-Specific DNA Methylation Biomarkers in Urine. International Journal of Molecular Sciences. https://doi.org/10.3390/ijms25020738

Vancouver

Köhler CU, Schork K, Turewicz M, Eisenacher M, Roghmann F, Noldus J, et al. Use of Multiple Machine Learning Approaches for Selecting Urothelial Cancer-Specific DNA Methylation Biomarkers in Urine. International Journal of Molecular Sciences. 2024. doi:10.3390/ijms25020738

BibTeX
@article{Khler2024,
  author = {Köhler, Christina U and Schork, Karin and Turewicz, Michael and Eisenacher, Martin and Roghmann, Florian and Noldus, Joachim and Marcus, Katrin and Brüning, Thomas and Käfferlein, Heiko U},
  title = {Use of Multiple Machine Learning Approaches for Selecting Urothelial Cancer-Specific DNA Methylation Biomarkers in Urine},
  journal = {International Journal of Molecular Sciences},
  year = {2024},
  doi = {10.3390/ijms25020738}
}
Kostenlos starten →