EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Identification and predictive machine learning model construction of gut microbiota associated with carcinoembryonic antigens in colorectal cancer

Yongzhi Wu iD, Zigui Huang, Yongqi Huang, Chuanbin Chen, Mingjian Qin, Zhen Wang iD, Fuhai He, Shenghai Liu, Rumao Zhong, Jun Liu, Chenyan Long, Jungang Liu iD und 1 weitere

mSphere · 2025

DOI: 10.1128/msphere.00454-25 ↗

Kurz gefasst

Fachartikel in der Zeitschrift mSphere, 2025. Verfasst von Yongzhi Wu und 12 weiteren Autor:innen. Beteiligte Einrichtung: Division of Colorectal & Anal Surgery, Department of Gastrointestinal Surgery, Guangxi Medical University Cancer Hospital, Nanning, The People's Repu…. Hauptthemen laut MEDLINE: Colorectal Neoplasms, Gastrointestinal Microbiome, Carcinoembryonic Antigen, Machine Learning. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 68 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: China Postdoctoral Science Foundation, Youth Science Foundation of Guangxi Medical University.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Carcinoembryonic antigen (CEA) is a critical colorectal cancer (CRC) biomarker, but its mechanistic link to gut microbiota remains unclear. This study characterized gut microbiota differences between high-CEA (H-CEA) and low-CEA (L-CEA) CRC patients and explored their associations with host immunity and tumor progression mechanisms. Stool samples from 187 CRC patients were subjected to 16S rRNA sequencing, identifying 30 differentially abundant bacteria using LEfSe analysis. Ruminococcus callidus was significantly enriched in H-CEA patients. Transcriptome sequencing of tumor tissues from 25 patients revealed distinct immune micro-environments: H-CEA patients showed elevated resting memory CD4 + T cells, while L-CEA patients showed increased T follicular helper cells. Functional enrichment analysis identified differential GO terms (26 in L-CEA; 31 in H-CEA) and KEGG pathways (three in H-CEA). R. callidus correlated positively with mast cell infiltration, CXCL1 chemokine, and long-chain fatty acid upregulation. The area under the curve (AUC) values of the subjects in the training set for the RF and XGBoost models constructed based on differential gut microbiota for predicting high and low CEA levels were 0.969 and 0.815, respectively, and the AUC for the test set were 0.715 and 0.639. These findings demonstrate that CEA-level-specific gut microbiota dysbiosis modulates CRC progression through immune micro-environment alterations and related biological pathway regulation. Gut microbiota, as a noninvasive biomarker, can be used to construct an effective machine learning (ML) model for predicting blood CEA levels. IMPORTANCE This study reveals R. callidus as a key gut microbiota species enriched in CRC patients with high CEA levels, demonstrating its novel pro-tumor associations through positive correlations with mast cell infiltration and CXCL1 chemokine and upregulation of long-chain fatty acid metabolism. Concurrently, we identify distinct immune micro-environments: elevated resting memory CD4+ T cells in high-CEA patients versus increased T follicular helper cells in low-CEA cohorts. Critically, by leveraging 30 differential microbial features, we develop ML models for noninvasive prediction of CEA levels. These findings establish gut microbiota as both a mechanistic mediator of CEA-driven CRC progression and a foundation for microbiome-based diagnostic tools.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Colorectal NeoplasmsGastrointestinal MicrobiomeCarcinoembryonic AntigenMachine LearningHumansFecesMaleRNA, Ribosomal, 16SFemaleMiddle AgedBacteriaAgedBiomarkers, TumorRuminococcus

Stichwörter der Autor:innen

16S rRNAcarcinoembryonic antigencolorectal cancerintestinal microbiologymachine learning

Substanzen

Carcinoembryonic AntigenRNA, Ribosomal, 16SBiomarkers, Tumor

Autor:innen und Institutionen

  • Division of Colorectal & Anal Surgery, Department of Gastrointestinal Surgery, Guangxi Medical University Cancer Hospital, Nanning, The People's Republic of China.
  • Guangxi Key Laboratory of Basic and Translational Research on Colorectal Cancer, Guangxi, The People's Republic of China.

ORCID-Profile: Yongzhi Wu, Zhen Wang, Jungang Liu, Xiaoliang Huang

Förderung

  • China Postdoctoral Science Foundation
  • Youth Science Foundation of Guangxi Medical University

Zitieren

APA

Wu, Y., Huang, Z., Huang, Y., Chen, C., Qin, M., Wang, Z., He, F., Liu, S., Zhong, R., Liu, J., Long, C., Liu, J., & Huang, X. (2025). Identification and predictive machine learning model construction of gut microbiota associated with carcinoembryonic antigens in colorectal cancer. mSphere. https://doi.org/10.1128/msphere.00454-25

Vancouver

Wu Y, Huang Z, Huang Y, Chen C, Qin M, Wang Z, et al. Identification and predictive machine learning model construction of gut microbiota associated with carcinoembryonic antigens in colorectal cancer. mSphere. 2025. doi:10.1128/msphere.00454-25

BibTeX
@article{Wu2025,
  author = {Wu, Yongzhi and Huang, Zigui and Huang, Yongqi and Chen, Chuanbin and Qin, Mingjian and Wang, Zhen and He, Fuhai and Liu, Shenghai and Zhong, Rumao and Liu, Jun and Long, Chenyan and Liu, Jungang and Huang, Xiaoliang},
  title = {Identification and predictive machine learning model construction of gut microbiota associated with carcinoembryonic antigens in colorectal cancer},
  journal = {mSphere},
  year = {2025},
  doi = {10.1128/msphere.00454-25}
}
Kostenlos starten →