Integrative transcriptomic and machine learning analyses identify DDX47 as a candidate diagnostic biomarker in acute myeloid leukemia
Frontiers in Oncology · 19.11.2026 · 16
DOI: 10.3389/fonc.2026.1964212 ↗Kurz gefasst
Fachartikel in der Zeitschrift Frontiers in Oncology, online erschienen am 19.11.2026. Verfasst von Xunxun Zhu und 4 weiteren Autor:innen. Die Arbeit nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Background
Acute myeloid leukemia (AML) is a highly heterogeneous hematological malignancy, and challenges remain in clinical diagnosis and the assessment of treatment response. This study aimed to identify candidate diagnostic biomarkers for AML and investigate their associations with the immune microenvironment and treatment response.
Methods
Transcriptomic profiles from The Cancer Genome Atlas (TCGA) and Genotype-Tissue Expression (GTEx) databases were integrated to identify candidate genes through differential expression analysis, weighted gene co-expression network analysis (WGCNA), and three machine learning algorithms. Diagnostic performance was evaluated using receiver operating characteristic (ROC) curve analysis, with external validation performed using the independent GSE9476 cohort. Associations between the candidate gene and immune cell infiltration and predicted drug sensitivity were further investigated. Its clinical relevance and potential functional role were subsequently evaluated through expression analyses of bone marrow samples from patients with AML and experiments involving AML cell lines treated with venetoclax following DDX47 knockdown.
Results
DDX47 was consistently identified as a candidate feature gene by three machine learning algorithms. DDX47 expression was significantly elevated in AML samples, with areas under the ROC curve (AUCs) of 0.824 in the discovery cohort and 0.862 in the independent validation cohort. DDX47 expression was associated with selected immune cell infiltration characteristics and the predicted sensitivity to multiple drugs. Analysis of clinical bone marrow samples further confirmed elevated DDX47 expression in patients with AML. In Molm-13 and THP-1 cells, DDX47 knockdown reduced venetoclax-induced cytotoxicity and apoptosis, suggesting that DDX47 may be involved in the response of AML cells to venetoclax.
Conclusion
This study identifies DDX47 as a candidate diagnostic biomarker for AML and revealed associations between its expression, immune microenvironment characteristics, and venetoclax response. These findings provide a basis for further investigation of the potential clinical relevance of DDX47 in AML diagnosis.
Zitieren
APA
Zhu, X., Fang, M., Wang, H., Zhang, H., & Zhang, M. (2026). Integrative transcriptomic and machine learning analyses identify DDX47 as a candidate diagnostic biomarker in acute myeloid leukemia. Frontiers in Oncology, 16. https://doi.org/10.3389/fonc.2026.1964212
Vancouver
Zhu X, Fang M, Wang H, Zhang H, Zhang M. Integrative transcriptomic and machine learning analyses identify DDX47 as a candidate diagnostic biomarker in acute myeloid leukemia. Frontiers in Oncology. 2026;16. doi:10.3389/fonc.2026.1964212
BibTeX
@article{Zhu2026,
author = {Zhu, Xunxun and Fang, Min and Wang, Hui and Zhang, Hao and Zhang, Mingyan},
title = {Integrative transcriptomic and machine learning analyses identify DDX47 as a candidate diagnostic biomarker in acute myeloid leukemia},
journal = {Frontiers in Oncology},
year = {2026},
volume = {16},
doi = {10.3389/fonc.2026.1964212}
}
EUVIMED