Machine learning‐based identification of a cell death‐related signature associated with prognosis and immune infiltration in glioma
Journal of Cellular and Molecular Medicine · 2024
DOI: 10.1111/jcmm.18463 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Cellular and Molecular Medicine, 2024. Verfasst von Quanwei Zhou und 6 weiteren Autor:innen. Beteiligte Einrichtung: The National Key Clinical Specialty, Department of Neurosurgery, Zhujiang Hospital, Southern Medical University, Guangzhou, China. Hauptthemen laut MEDLINE: Glioma, Machine Learning, Nomograms, Gene Expression Regulation, Neoplastic. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 62 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, China Postdoctoral Science Foundation, Natural Science Foundation of Hunan Province.
Abstract (Originalsprache)
Accumulating evidence suggests that a wide variety of cell deaths are deeply involved in cancer immunity. However, their roles in glioma have not been explored. We employed a logistic regression model with the shrinkage regularization operator (LASSO) Cox combined with seven machine learning algorithms to analyse the patterns of cell death (including cuproptosis, ferroptosis, pyroptosis, apoptosis and necrosis) in The Cancer Genome Atlas (TCGA) cohort. The performance of the nomogram was assessed through the use of receiver operating characteristic (ROC) curves and calibration curves. Cell‐type identification was estimated by using the cell‐type identification by estimating relative subsets of known RNA transcripts (CIBERSORT) and single sample gene set enrichment analysis methods. Hub genes associated with the prognostic model were screened through machine learning techniques. The expression pattern and clinical significance of MYD88 were investigated via immunohistochemistry (IHC). The cell death score represents an independent prognostic factor for poor outcomes in glioma patients and has a distinctly superior accuracy to that of 10 published signatures. The nomogram performed well in predicting outcomes according to time‐dependent ROC and calibration plots. In addition, a high‐risk score was significantly related to high expression of immune checkpoint molecules and dense infiltration of protumor cells, these findings were associated with a cell death‐based prognostic model. Upregulated MYD88 expression was associated with malignant phenotypes and undesirable prognoses according to the IHC. Furthermore, high MYD88 expression was associated with poor clinical outcomes and was positively related to CD163, PD‐L1 and vimentin expression in the in‐horse cohort. The cell death score provides a precise stratification and immune status for glioma. MYD88 was found to be an outstanding representative that might play an important role in glioma.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- The National Key Clinical Specialty, Department of Neurosurgery, Zhujiang Hospital, Southern Medical University, Guangzhou, China.
- Department of Neurosurgery, Xiangya Hospital, Central South University, Changsha, China.
- NHC Key Laboratory of Birth Defect for Research and Prevention, Hunan Provincial Maternal and Child Health Care Hospital, Changsha, Hunan, China.
ORCID-Profile: Xuejun Yan, Yiquan Ke
Förderung
- National Natural Science Foundation of China
- China Postdoctoral Science Foundation
- Natural Science Foundation of Hunan Province
Zitieren
APA
Zhou, Q., Wu, F., Zhang, W., Guo, Y., Jiang, X., Yan, X., & Ke, Y. (2024). Machine learning‐based identification of a cell death‐related signature associated with prognosis and immune infiltration in glioma. Journal of Cellular and Molecular Medicine. https://doi.org/10.1111/jcmm.18463
Vancouver
Zhou Q, Wu F, Zhang W, Guo Y, Jiang X, Yan X, et al. Machine learning‐based identification of a cell death‐related signature associated with prognosis and immune infiltration in glioma. Journal of Cellular and Molecular Medicine. 2024. doi:10.1111/jcmm.18463
BibTeX
@article{Zhou2024,
author = {Zhou, Quanwei and Wu, Fei and Zhang, Wenlong and Guo, Youwei and Jiang, Xingjun and Yan, Xuejun and Ke, Yiquan},
title = {Machine learning‐based identification of a cell death‐related signature associated with prognosis and immune infiltration in glioma},
journal = {Journal of Cellular and Molecular Medicine},
year = {2024},
doi = {10.1111/jcmm.18463}
}
EUVIMED