EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

10-Gene Prognostic Signature and Subtypes of Colon Adenocarcinoma via Multi-algorithm Consensus Learning

Yiming Wang

Health Medicine and Therapeutics · 09.04.2026 · 1 (3) · 71

DOI: 10.63313/hmt.9023 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Health Medicine and Therapeutics, online erschienen am 09.04.2026. Verfasst von Yiming Wang. Die Arbeit nennt 26 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Colon adenocarcinoma (COAD) exhibits profound molecular heterogeneity and limited targeted therapy options, necessitating precision medicine strategies based on tumor molecular profiles to improve advanced disease outcomes. Leveraging multi-omics data from TCGA-COAD, we integrated ten clustering algorithms with ten machine learning methods to develop a CMLS prognostic model. Multi-omics clustering stratified COAD into four subtypes, with CS2 demonstrating optimal survival. The ten-gene CMLS signature (GDI1, CLK1, SEMA4C, RBP7, HSPA1A, CALB2, DCBLD2, ITLN1, ATOH1, UQCRC1) enabled risk stratification by median scores, revealing superior survival. This study provides a valuable supplementary approach for the precise management of COAD, which is expected to enrich current clinical decision-making strategies.

Zitieren

APA

Wang, Y. (2026). 10-Gene Prognostic Signature and Subtypes of Colon Adenocarcinoma via Multi-algorithm Consensus Learning. Health Medicine and Therapeutics, 1(3), 71. https://doi.org/10.63313/hmt.9023

Vancouver

Wang Y. 10-Gene Prognostic Signature and Subtypes of Colon Adenocarcinoma via Multi-algorithm Consensus Learning. Health Medicine and Therapeutics. 2026;1(3):71. doi:10.63313/hmt.9023

BibTeX
@article{Wang2026,
  author = {Wang, Yiming},
  title = {10-Gene Prognostic Signature and Subtypes of Colon Adenocarcinoma via Multi-algorithm Consensus Learning},
  journal = {Health Medicine and Therapeutics},
  year = {2026},
  volume = {1},
  number = {3},
  pages = {71},
  doi = {10.63313/hmt.9023}
}
Kostenlos starten →