Machine learning framework develops neutrophil extracellular traps model for clinical outcome and immunotherapy response in lung adenocarcinoma
Apoptosis · 2024
DOI: 10.1007/s10495-024-01947-4 ↗Kurz gefasst
Fachartikel in der Zeitschrift Apoptosis, 2024. Verfasst von A Xuan Han und 9 weiteren Autor:innen. Beteiligte Einrichtung: Department of General Surgery, Aerospace Central Hospital, 15 Yuquan Road, Haidian District, Beijing, China. Hauptthemen laut MEDLINE: Extracellular Traps, Adenocarcinoma of Lung, Machine Learning, Lung Neoplasms. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 56 Literaturangaben. Gefördert von: Military Health Special Research Project, key project of the National Health Commission.
Abstract (Originalsprache)
Neutrophil extracellular traps (NETs) are novel inflammatory cell death in neutrophils. Emerging studies demonstrated NETs contributed to cancer progression and metastases in multiple ways. This study intends to provide a prognostic NETs signature and therapeutic target for lung adenocarcinoma (LUAD) patients. Consensus cluster analysis performed by 38 reported NET-related genes in TCGA-LUAD cohorts. Then, WGCNA network was conducted to investigate characteristics genes in clusters. Seven machine learning algorithms were assessed for training of the model, the optimal model was picked by C-index and 1-, 3-, 5-year ROC value. Then, we constructed a NETs signature to predict the overall survival of LUAD patients. Moreover, multi-omics validation was performed based on NETs signature. Finally, we constructed stable knockdown critical gene LUAD cell lines to verify biological functions of Phospholipid Scramblase 1 (PLSCR1) in vitro and in vivo. Two NETs-related clusters were identified in LUAD patients. Among them, C2 cluster was provided as "hot" tumor phenotype and exhibited a better prognosis. Then, WGCNA network identified 643 characteristic genes in C2 cluster. Then, Coxboost algorithm proved its optimal performance and provided a prognostic NETs signature. Multi-omics revealed that NETs signature was involved in an immunosuppressive microenvironment and predicted immunotherapy efficacy. In vitro and in vivo experiments demonstrated that knockdown of PLSCR1 inhibited tumor growth and EMT ability. Besides, cocultural assay indicated that the knockdown of PLSCR1 impaired the ability of neutrophils to generate NETs. Finally, tissue microarray (TMA) for LUAD patients verified the prognostic value of PLSCR1 expression. In this study, we focus on emerging hot topic NETs in LUAD. We provide a prognostic NETs signature and identify PLSCR1 with multiple roles in LUAD. This work can contribute to risk stratification and screen novel therapeutic targets for LUAD patients.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Department of General Surgery, Aerospace Central Hospital, 15 Yuquan Road, Haidian District, Beijing, China.
- Department of Medical Oncology, Senior Department of Oncology, Fengtai District, The Fifth Medical Center of PLA General Hospital, No. 100, West Fourth Ring Middle Road, Beijing, 100039, China.
- School of Medicine, Nankai University, Nankai District, 94 Weijin Road, Tianjin, 300071, China.
- Medical School of Chinese People's Liberation Army (PLA), Haidian District, 28 Fuxing Road, Beijing, 100853, People's Republic of China.
- Institute of Oncology, The First Medical Center of Chinese, PLA General Hospital, Beijing, 100853, China.
- Department of Medical Oncology, Senior Department of Oncology, Fengtai District, The Fifth Medical Center of PLA General Hospital, No. 100, West Fourth Ring Middle Road, Beijing, 100039, China. dr_liuqiaowei@126.com.
Förderung
- Military Health Special Research Project
- key project of the National Health Commission
Zitieren
APA
Han, A. X., Long, B. Y., Li, C. Y., Huang, D. D., Xiong, E. Q., Li, F. J., Wu, G. L., Liu, Q., Yang, G. B., & Hu, H. Y. (2024). Machine learning framework develops neutrophil extracellular traps model for clinical outcome and immunotherapy response in lung adenocarcinoma. Apoptosis. https://doi.org/10.1007/s10495-024-01947-4
Vancouver
Han AX, Long BY, Li CY, Huang DD, Xiong EQ, Li FJ, et al. Machine learning framework develops neutrophil extracellular traps model for clinical outcome and immunotherapy response in lung adenocarcinoma. Apoptosis. 2024. doi:10.1007/s10495-024-01947-4
BibTeX
@article{Han2024,
author = {Han, A Xuan and Long, B Yaping and Li, C Yao and Huang, D Di and Xiong, E Qi and Li, F Jinfeng and Wu, G Liangliang and Liu, Qiaowei and Yang, G Bo and Hu, H Yi},
title = {Machine learning framework develops neutrophil extracellular traps model for clinical outcome and immunotherapy response in lung adenocarcinoma},
journal = {Apoptosis},
year = {2024},
doi = {10.1007/s10495-024-01947-4}
}
EUVIMED