EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Integrating Single‐Cell Autophagy Profiling With an Ensemble Machine Learning Framework to Refine Clinical Prognosis in Osteosarcoma

Haibo Zhao, Zhongchen Li, Yangyang Wang, Jiandong Guo, Ning Hu, Lian Xi, Qin Chen

International Journal of Clinical Practice · 2026-01 · 2026 (1)

DOI: 10.1155/ijcp/8886058 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Clinical Practice, online erschienen am 30.07.2026. Verfasst von Haibo Zhao und 6 weiteren Autor:innen. Die Arbeit nennt 46 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Osteosarcoma is an aggressive malignancy frequently accompanied by metastasis, which substantially diminishes therapeutic efficacy and contributes to poor clinical outcomes. Although autophagy has been implicated in tumor biology, its functional role in osteosarcoma remains incompletely understood. In this study, we analyzed publicly available single‐cell RNA sequencing datasets to characterize cellular heterogeneity within osteosarcoma and quantify autophagy activity across distinct cellular populations. Dimensionality reduction and cell‐type annotation enabled the precise evaluation of autophagy scores among different cell subtypes. Weighted gene coexpression network analysis (WGCNA), combined with differential expression analysis, was subsequently applied to identify key autophagy‐associated genes and investigate their biological functions. To establish a reliable prognostic framework, we implemented an integrative machine‐learning strategy incorporating 10 algorithms that generated 101 predictive models across multiple independent cohorts. Through systematic training and validation, a robust autophagy‐related gene signature was developed for prognostic prediction. The model demonstrated stable predictive performance and showed significant associations with clinical characteristics. Furthermore, a nomogram integrating the gene signature with clinical variables was constructed to improve individualized survival prediction accuracy. Functional enrichment and immune landscape analyses further revealed complex regulatory relationships linking autophagy‐related genes with multiple signaling pathways and the tumor immune microenvironment. Collectively, our findings provide novel insights into the role of autophagy in osteosarcoma and establish a computational framework that may facilitate prognostic evaluation and inform future therapeutic strategies.

Zitieren

APA

Zhao, H., Li, Z., Wang, Y., Guo, J., Hu, N., Xi, L., & Chen, Q. (2026). Integrating Single‐Cell Autophagy Profiling With an Ensemble Machine Learning Framework to Refine Clinical Prognosis in Osteosarcoma. International Journal of Clinical Practice, 2026(1). https://doi.org/10.1155/ijcp/8886058

Vancouver

Zhao H, Li Z, Wang Y, Guo J, Hu N, Xi L, et al. Integrating Single‐Cell Autophagy Profiling With an Ensemble Machine Learning Framework to Refine Clinical Prognosis in Osteosarcoma. International Journal of Clinical Practice. 2026;2026(1). doi:10.1155/ijcp/8886058

BibTeX
@article{Zhao2026,
  author = {Zhao, Haibo and Li, Zhongchen and Wang, Yangyang and Guo, Jiandong and Hu, Ning and Xi, Lian and Chen, Qin},
  title = {Integrating Single‐Cell Autophagy Profiling With an Ensemble Machine Learning Framework to Refine Clinical Prognosis in Osteosarcoma},
  journal = {International Journal of Clinical Practice},
  year = {2026},
  volume = {2026},
  number = {1},
  doi = {10.1155/ijcp/8886058}
}
Kostenlos starten →