Integrating multiple machine learning methods to construct glutamine metabolism-related signatures in lung adenocarcinoma

Aug 5, 2026

Upload by Himbo

Glutamine metabolism plays a critical role in cancer development, yet its specific contribution to lung adenocarcinoma (LUAD) remains incompletely understood. This study uses machine learning on glutamine metabolism-related genes to build prognostic models and identify targets for LUAD treatment. AUCell and WGCNA with single-cell and bulk RNA-seq data screen key genes, followed by model development, external validation, and comparison of tumor microenvironment, mutation features, pathways, and immunotherapy response across risk groups. In vitro and in vivo experiments further confirm LGALS3’s functional role.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages18

Reading Time45 min

AccessFree to download

Introduction

Methods

Data and feature identification

Model construction and validation

Results

Prognostic signatures and performance

Tumor microenvironment and immunotherapy response

Experimental validation of LGALS3

Conclusion

TYPE Original Research PUBLISHED 17 May 2023 DOI 10.3389/fendo.2023.1196372 OPEN ACCESS EDITED BY Qun Zhao, Fourth Hospital of Hebei Medical University, China REVIEWED BY Zhenyu Wu, First People’s Hospital of Foshan, China Yinhui Yao, Afﬁliated Hospital of Chengde Medical University, China Guo Liu, Shenzhen University, China *CORRESPONDENCE Haoran Lin [njlinhaoran@163.com](njlinhaoran@163.com)[ ](njlinhaoran@163.com)Mingjun Du [dumingjun1989@163.com](dumingjun1989@163.com)[ ](dumingjun1989@163.com)Jiaheng Xie [xiejiaheng@njmu.edu.cn](xiejiaheng@njmu.edu.cn) †These authors have contributed equally to this work and share ﬁrst authorship RECEIVED 29 March 2023 ACCEPTED 04 May 2023 PUBLISHED 17 May 2023 CITATION Zhang P, Pei S, Wu L, Xia Z, Wang Q, Huang X, Li Z, Xie J, Du M and Lin H (2023) Integrating multiple machine learning methods to construct glutamine metabolism-related signatures in lung adenocarcinoma. Front. Endocrinol. 14:1196372 . doi: 10.3389/fendo.2023.1196372 COPYRIGHT © 2023 Zhang, Pei, Wu, Xia, Wang, Huang, Li, Xie, Du and Lin. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY) . The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms. Integrating multiple machine learning methods to construct glutamine metabolism-related signatures in lung adenocarcinoma Pengpeng Zhang 1†, Shengbin Pei 2†, Leilei Wu 3†, Zhijia Xia 4†, Qi Wang 5, Xufeng Huang 6, Zhangzuo Li 7, Jiaheng Xie 8*, Mingjun Du 1* and Haoran Lin 1* 1 Department of Thoracic Surgery, The First Afﬁliated Hospital of Nanjing Medical University, Nanjing, China, 2 Department of Breast Surgery, The First Afﬁliated Hospital of Nanjing Medical University, Nanjing, China, 3 Department of Radiation Oncology, Shanghai Pulmonary Hospital, Tongji University School of Medicine, Shanghai, China, 4 Department of General, Visceral, and Transplant Surgery, Ludwig-Maximilians-University Munich, Munich, Germany, 5 Department of Gastroenterology, Afﬁliated Hospital of Jiangsu University, Jiangsu University, Zhenjiang, China, 6 Faculty of Dentistry, University of Debrecen, Debrecen, Hungary, 7 Department of Cell Biology, School of Medicine, Jiangsu University, Zhenjiang, China, 8 Department of Burns and Plastic Surgery, The First Afﬁliated Hospital of Nanjing Medical University, Nanjing, China Background: Glutamine metabolism (GM) is known to play a critical role in cancer development, including in lung adenocarcinoma (LUAD), although the exact contribution of GM to LUAD remains incompletely understood. In this study, we aimed to discover new targets for the treatment of LUAD patients by using machine learning algorithms to establish prognostic models based on GMrelated genes (GMRGs) . Methods: We used the AUCell and WGCNA algorithms, along with single-cell and bulk RNA-seq data, to identify the most prominent GMRGs associated with LUAD. Multiple machine learning algorithms were employed to develop risk models with optimal predictive performance. We validated our models using multiple external datasets and investigated disparities in the tumor microenvironment (TME), mutation landscape, enriched pathways, and response to immunotherapy across various risk groups. Additionally, we conducted in vitro and in vivo experiments to conﬁrm the role of LGALS3 in LUAD. Results: We identiﬁed 173 GMRGs strongly associated with GM activity and selected the Random Survival Forest (RSF) and Supervised Principal Components (SuperPC) methods to develop a prognostic model. Our model ’s performance was validated using multiple external datasets. Our analysis revealed that the low-risk group had hi

FAQs

What biological process and cancer type does the study focus on?

The study focuses on glutamine metabolism in lung adenocarcinoma (LUAD) and aims to clarify how glutamine metabolism-related genes contribute to disease progression.

How were the prognostic signatures constructed and validated?

The work identifies prominent glutamine metabolism-related genes using AUCell and WGCNA applied to single-cell and bulk RNA-seq data, then builds risk models using multiple machine learning methods. Model performance is validated on multiple external datasets.

What immune-related findings were observed across risk groups?

The low-risk group showed higher immune cell infiltration and increased expression of immune checkpoints, suggesting greater receptiveness to immunotherapy.

What experimental evidence supports LGALS3 as a therapeutic target?

In vitro and in vivo experiments indicate that LGALS3 promotes proliferation, invasion, and migration of LUAD cells, supporting its potential therapeutic relevance.

Aug 5, 2026

Upload by Himbo