Scholarlink

<p>Given that glutamine metabolism (GM) reprogramming has been recognized as a metabolic modulator, there is a need to evaluate the prognostic significance, immunotherapeutic response, and sensitivity to drugs in lung adenocarcinoma (LUAD) patients according to the expression patterns of GM-related genes (GMRGs). In this study, we first identified differentially expressed GMRGs (DEGMRGs) in the TCGA-LUAD cohort, and used all DEGMRGs for molecular typing of LUAD patients. We then used machine learning framework to develop a glutamine metabolism immunity index (GMII) for LUAD patients, and validated it with GEO cohorts (GSE72094, and GSE37745). As a result, the GMII was an excellent prognostic model consisting of eight gene (LDHA, CYP17A1, PCSK9, MMACHC, GPD1, ALDOA, SLCO1B1, and CPS1), and LUAD patients were categorized into high-GMII and low-GMII groups. Survival analysis indicated that high-GMII patients experienced a poorer prognosis within the TCGA-LUAD cohort (<i>P</i> &lt; 0.001), a finding that was also confirmed in the GSE72094 cohort (<i>P</i> &lt; 0.001) and GSE37745 cohort (<i>P</i> = 0.047). The high-GMII patients exhibited elevated TIDE scores and diminished IPS scores, suggesting that high-GMII patients may be more susceptible to immune escape and benefit less from immunotherapy. In addition, we found that the high-GMII patients may be more sensitive to Axitinib, AZD1208, BMS-754,807, Daporinad, Doramapimod, Elephantin, GSK269962A, JQ1, LY2109761, and MK-2206, but the latter, including 5-Fluorouracil, AZD6738, Docetaxel, ERK_6604, and Erlotinib may be less sensitive. Consequently, GMII serves as a potential clinical classifier, offering novel insights for the precise treatment of LUAD patients.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

A machine learning computational framework develops a glutamine metabolism immunity index for improving clinical outcomes in lung adenocarcinoma

  • 期刊论文

  • 发表日期：

    2025年12月27日

查看全文
  • Chunhong Li,
  • Haiyin Tan,
  • Yuhua Mao,
  • Yi Liu,
  • Jiahua Hu,
  • Xiaoping Pang,
  • Xianliang Hou,
  • Minglin Ou

摘要

Given that glutamine metabolism (GM) reprogramming has been recognized as a metabolic modulator, there is a need to evaluate the prognostic significance, immunotherapeutic response, and sensitivity to drugs in lung adenocarcinoma (LUAD) patients according to the expression patterns of GM-related genes (GMRGs). In this study, we first identified differentially expressed GMRGs (DEGMRGs) in the TCGA-LUAD cohort, and used all DEGMRGs for molecular typing of LUAD patients. We then used machine learning framework to develop a glutamine metabolism immunity index (GMII) for LUAD patients, and validated it with GEO cohorts (GSE72094, and GSE37745). As a result, the GMII was an excellent prognostic model consisting of eight gene (LDHA, CYP17A1, PCSK9, MMACHC, GPD1, ALDOA, SLCO1B1, and CPS1), and LUAD patients were categorized into high-GMII and low-GMII groups. Survival analysis indicated that high-GMII patients experienced a poorer prognosis within the TCGA-LUAD cohort (P < 0.001), a finding that was also confirmed in the GSE72094 cohort (P < 0.001) and GSE37745 cohort (P = 0.047). The high-GMII patients exhibited elevated TIDE scores and diminished IPS scores, suggesting that high-GMII patients may be more susceptible to immune escape and benefit less from immunotherapy. In addition, we found that the high-GMII patients may be more sensitive to Axitinib, AZD1208, BMS-754,807, Daporinad, Doramapimod, Elephantin, GSK269962A, JQ1, LY2109761, and MK-2206, but the latter, including 5-Fluorouracil, AZD6738, Docetaxel, ERK_6604, and Erlotinib may be less sensitive. Consequently, GMII serves as a potential clinical classifier, offering novel insights for the precise treatment of LUAD patients.