EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

CEACAM6 as a machine learning derived immune biomarker for predicting neoadjuvant chemotherapy response in HR+/HER2− breast cancer

Dalang Fang, Jie Lin, Jin Wang, Qingxiao Nong, Shouwen Tao, Bimin Lu, Yanrong Yu, Hao Peng, Yingying Tian, Qunying Su, Yanfei Ma, Yuanlu Huang

Frontiers in Immunology · 27.08.2025 · 16

DOI: 10.3389/fimmu.2025.1662004 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Frontiers in Immunology, online erschienen am 27.08.2025. Verfasst von Dalang Fang und 11 weiteren Autor:innen. Beteiligte Einrichtung: Department of Gland Surgery, Affiliated Hospital of Youjiang Medical University for Nationalities, Key Laboratory of Tumor Molecular Pathology of Bai…. Hauptthemen laut MEDLINE: Breast Neoplasms, Machine Learning, Biomarkers, Tumor, Antigens, CD. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 53 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Hormone receptor-positive/human epidermal growth factor receptor 2-negative (HR+/HER2−) breast cancer is the most common subtype, characterized by heterogeneous neoadjuvant chemotherapy (NAC) responses and low pCR rates. Existing biomarkers have limited predictive accuracy, hindering personalized treatment. This study aimed to identify predictive biomarkers for NAC response and explore their therapeutic potential in HR+/HER2− breast cancer.

Methods

We integrated 497 HR+/HER2− samples from TCGA and 956 from nine GEO datasets (training set: n=708; test set: n=248). Differentially expressed genes (DEGs) between tumors and normal tissues (TCGA) and between pCR and residual disease (RD) groups (GEO) were identified. Overlapping DEGs were further screened using LASSO, random forest, and SVM-RFE algorithms. Predictive models were constructed with 10 machine learning algorithms and interpreted using SHAP. Gene set enrichment analysis (GSEA), CIBERSORT-based immune infiltration, and drug sensitivity prediction using oncoPredict and GDSC2 were performed. Immunohistochemistry (IHC) was conducted on paired pre/post-NAC samples (n=9). Clinical correlation was analyzed in a retrospective cohort of 106 HR+/HER2− NAC patients.

Results

Thirty-eight overlapping DEGs were identified, and four key genes (CEACAM6, MELK, RARRES1, BIRC5) were selected. NeuralNet showed the best model performance (AUC=0.816). CEACAM6 was the top-ranked SHAP feature, with high expression predicting RD and was associated with poor survival (p=0.014). GSEA revealed CEACAM6-high tumors were enriched in drug resistance pathways (such as oxidative phosphorylation), while low expression correlated with immune activation. Immune analysis showed pCR tumors had more effector cells (Tfh, γδ T cells, M1 macrophages), whereas RD tumors were enriched in Tregs and resting mast cells. CEACAM6 positively correlated with Tregs and naïve CD4+ T cells, and negatively with CD8+ T cells and M1 macrophages. CEACAM6-high tumors had higher IC50 for six NAC-related drugs. IHC confirmed persistent CEACAM6 expression in RD tumors post-NAC. Clinically, pCR patients had higher lymphocyte counts and more frequent N2–N3 nodal status.

Conclusion

CEACAM6 is a promising predictive biomarker in HR+/HER2− breast cancer, associated with chemoresistance and immune suppression. Machine learning models integrating immune signatures and pathway features may optimize personalized NAC strategies.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Breast NeoplasmsMachine LearningBiomarkers, TumorAntigens, CDHumansFemaleNeoadjuvant TherapyErb-b2 Receptor Tyrosine KinasesGPI-Linked ProteinsReceptors, EstrogenGene Expression Regulation, NeoplasticPrognosisReceptors, ProgesteroneGene Expression ProfilingTreatment OutcomeCell Adhesion Molecules

Stichwörter der Autor:innen

CEACAM6HR+/HER2-breast cancerimmune infiltrationmachine learningneoadjuvant chemotherapy (NAC)

Substanzen

Biomarkers, TumorErb-b2 Receptor Tyrosine KinasesGPI-Linked ProteinsReceptors, EstrogenAntigens, CDReceptors, ProgesteroneCell Adhesion MoleculesCEACAM6 protein, humanERBB2 protein, human

Autor:innen und Institutionen

  • Department of Gland Surgery, Affiliated Hospital of Youjiang Medical University for Nationalities, Key Laboratory of Tumor Molecular Pathology of Baise, Baise, Guangxi, China.
  • Department of Pathology, Affiliated Hospital of Youjiang Medical University for Nationalities, Baise, Guangxi, China.
  • Department of Gland Surgery, Baise People's Hospital, Baise, Guangxi, China.

Zitieren

APA

Fang, D., Lin, J., Wang, J., Nong, Q., Tao, S., Lu, B., Yu, Y., Peng, H., Tian, Y., Su, Q., Ma, Y., & Huang, Y. (2025). CEACAM6 as a machine learning derived immune biomarker for predicting neoadjuvant chemotherapy response in HR+/HER2− breast cancer. Frontiers in Immunology, 16. https://doi.org/10.3389/fimmu.2025.1662004

Vancouver

Fang D, Lin J, Wang J, Nong Q, Tao S, Lu B, et al. CEACAM6 as a machine learning derived immune biomarker for predicting neoadjuvant chemotherapy response in HR+/HER2− breast cancer. Frontiers in Immunology. 2025;16. doi:10.3389/fimmu.2025.1662004

BibTeX
@article{Fang2025,
  author = {Fang, Dalang and Lin, Jie and Wang, Jin and Nong, Qingxiao and Tao, Shouwen and Lu, Bimin and Yu, Yanrong and Peng, Hao and Tian, Yingying and Su, Qunying and Ma, Yanfei and Huang, Yuanlu},
  title = {CEACAM6 as a machine learning derived immune biomarker for predicting neoadjuvant chemotherapy response in HR+/HER2− breast cancer},
  journal = {Frontiers in Immunology},
  year = {2025},
  volume = {16},
  doi = {10.3389/fimmu.2025.1662004}
}
Kostenlos starten →