[1]高梓扬,赵崇玉,成 龙,等.基于机器学习的肥胖相关基因特征预测胃癌患者的预后和治疗反应[J].医学信息,2026,39(10):32-39.[doi:10.3969/j.issn.1006-1959.2026.10.005]
　GAO Ziyang,ZHAO Chongyu,CHENG Long,et al.Obesity-related Gene Features Based on Machine Learning in Predicting the Prognosisand Treatment Response of Patients with Gastric Cancer[J].Journal of Medical Information,2026,39(10):32-39.[doi:10.3969/j.issn.1006-1959.2026.10.005]
点击复制

基于机器学习的肥胖相关基因特征预测胃癌患者的预后和治疗反应()

医学信息[ISSN:1006-1959/CN:61-1278/R]

卷:
39卷
期数:
2026年10期
页码:
32-39
栏目:
临床信息学
出版日期:
2026-05-15

文章信息/Info

Title:
Obesity-related Gene Features Based on Machine Learning in Predicting the Prognosisand Treatment Response of Patients with Gastric Cancer
文章编号:
1006-1959（2026）10-0032-08
作者:
高梓扬1; 赵崇玉2; 成 龙3; 蓝 煜4; 陈承业1 ; 陈俊良1
1.肇庆市第一人民医院肿瘤科，广东 肇庆 526000；2.暨南大学附属第一医院外科，广东 广州 510630；3.广州医科大学附属惠州医院外科，广东 惠州 516000；4.中山大学肿瘤防治中心内科，广东 广州 510000
Author(s):
GAO Ziyang1;  ZHAO Chongyu2;  CHENG Long3;  LAN Yu4;  CHEN Chengye1;  CHEN Junliang1
1.Department of Medical Oncology, the First People′s Hospital of Zhaoqing, Zhaoqing 526000, Guangdong, China;2.Department of Surgery, the First Affiliated Hospital of Jinan University, Guangzhou 510630, Guangdong, China;3.Department of Surgery, Huizhou Hospital Affiliated to Guangzhou Medical University, Huizhou 516000, Guangdong, China;4.Department of Internal Medicine, Sun Yat-sen University Cancer Center, Guangzhou 510000, Guangdong, China
关键词:
胃癌; 肥胖; 机器学习; 预后
Keywords:
Gastric cancer;  Obesity;  Machine learning;  Prognosis
分类号:
R735.2
DOI:
10.3969/j.issn.1006-1959.2026.10.005
文献标志码:
A
摘要:
目的 探索与胃癌预后相关的肥胖基因，并构建预测模型以评估患者的预后和治疗反应。方法 基于TCGA和GEO数据库的胃癌转录组数据以及GeneCards中的肥胖相关基因，筛选出与胃癌相关的肥胖基因，并通过单因素Cox回归分析确定58个预后相关基因。使用101种机器学习模型（包括Enet、RSF等）通过10折交叉验证构建预后预测模型，选取Enet[alpha=0.1]模型为最佳方案。通过Kaplan-Meier分析对高低风险组的生存差异进行评估。GSE84437数据集用于模型验证，Cox回归分析进一步评估风险评分的独立性。通过肿瘤突变负荷（TMB）和免疫反应评分（TIDE）评估免疫治疗反应，采用药物敏感性评估比较两组对常见化疗药物的反应，通过细胞实验验证肥胖基因在胃癌细胞中的差异表达。结果 筛选出239个与肥胖相关的基因，并确定58个与胃癌预后相关的肥胖基因。基于这些基因，构建的Enet[alpha=0.1]模型将患者分为高、低风险组，且高风险组生存期较低风险组显著缩短。该模型预测胃癌患者1、3、5年总体生存率的AUC分别为0.713、0.705、0.712，表现优异。整合临床因素的预后列线图C指数为0.706，预测能力良好。免疫分析显示低风险组的TMB高于高风险组，且TIDE评分较低，提示低风险组对免疫治疗更敏感。药物敏感性评估显示高风险组可能更易从化疗和靶向治疗中获益。细胞实验验证了CARTPT和APOE在胃癌细胞中的高表达，而PDSS1表达下调。结论 本次构建的肥胖基因特征模型可有效预测胃癌患者的预后、免疫反应及治疗反应，可为临床决策提供支持。
Abstract:
Objective To explore the obesity-related genes associated with the prognosis of gastric cancer, and to construct a prediction model to evaluate the prognosis and treatment response of patients. Methods Based on the transcriptome data of gastric cancer in TCGA and GEO databases and obesity-related genes in GeneCards, obesity genes associated with gastric cancer were screened, and 58 prognostic genes were identified by univariate Cox regression analysis. The 101 machine learning models (including Enet, RSF, etc.) were used to construct a prognostic prediction model through 10-fold cross-validation, and the Enet [alpha=0.1] model was selected as the best solution. Kaplan-Meier analysis was used to evaluate the survival differences between the high-risk group and low-risk group. The GSE84437 data set was used for model validation, and Cox regression analysis further assessed the independence of the risk score. Immunotherapy response was evaluated by tumor mutation burden (TMB) and immune response score (TIDE). Drug sensitivity assessment was used to compare the response of the two groups to common chemotherapy drugs. The differential expression of obesity genes in gastric cancer cells was verified by cell experiments. Results A total of 239 obesity-related genes were screened, and 58 obesity-related genes were identified for the prognosis of gastric cancer. Based on these genes, the constructed Enet [alpha=0.1] model divided patients into high-risk group and low-risk groups, and the survival time of the high-risk group was significantly shorter than that of the low-risk group. The AUC of the model for predicting the 1-, 3-, and 5-year overall survival rates of gastric cancer patients was 0.713, 0.705, and 0.712,respectively, showing excellent performance. The prognostic nomogram C index integrating clinical factors was 0.706, and the predictive ability was good. Immunological analysis showed that the TMB of the low-risk group was higher than that of the high-risk group, and the TIDE score was lower, suggesting that the low-risk group was more sensitive to immunotherapy. Drug sensitivity assessment showed that high-risk groups might be more likely to benefit from chemotherapy and targeted therapy. Cell experiments verified the high expression of CARTPT and APOE in gastric cancer cells, while the expression of PDSS1 was down-regulated. Conclusion The constructed obesity gene characteristic model can effectively predict the prognosis, immune response and treatment response of patients with gastric cancer, and can provide support for clinical decision-making.

参考文献/References:

[1]Bray F,Laversanne M,Sung H,et al.Global cancer statistics 2022: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries[J].CA Cancer J Clin,2024,74(3):229-263.[2]Van Cutsem E,Sagaert X,Topal B,et al.Gastric cancer[J].Lancet,2016,388(10060):2654-2664.[3]Abdel-Qadir H,Austin PC,Lee DS,et al.A population-based study of cardiovascular mortality following early-stage breast cancer[J].JAMA cardiology,2017,2(1):88-93.[4]Medipally M,Avasia A,Parasnis M.Obesity in Primary Care: A Comprehensive Approach for Family Physicians[J].Cureus,2025,17(8):e90742.[5]Lagarde CB,Thapa K,Cullen NM,et al.Obesity and leptin in breast cancer angiogenesis[J].Front Endocrinol(Lausanne),2024,15:1465727.[6]Avogaro A.Diabetes and obesity: the role of stress in the development of cancer[J].Endocrine,2024,86(1):48-57.[7]Saha PK,Sharp R,Cox AR,et al.The microRNA miR-30a blocks adipose tissue fibrosis accumulation in obesity[J].J Clin Invest,2025,135(15):e175566.[8]Patterson A,Auslander N.Mutated processes predict immune checkpoint inhibitor therapy benefit in metastatic melanoma[J].Nat Commun,2022,13(1):5151.[9]Smyth EC,Nilsson M,Grabsch HI,et al.Gastric cancer[J].Lancet,2020,396(10251):635-648.[10]Yamada K,Saito M,Ando M,et al.Reduced Number and Immune Dysfunction of CD4+ T Cells in Obesity Accelerate Colorectal Cancer Progression[J].Cells,2022,12(1):86.[11]Rosario SR,Smith RJJr,Patnaik SK,et al.Altered acetyl-CoA metabolism presents a new potential immunotherapy target in the obese lung microenvironment[J].Cancer Metab,2022,10(1):17.[12]Rakib A,Mamun MAA,Mandal M,et al.Obesity-cancer axis crosstalk: Molecular insights and therapeutic approaches[J].Acta Pharm Sin B,2025,15(6):2930-2944.[13]Desharnais L,Walsh LA,Quail DF.Exploiting the obesity-associated immune microenvironment for cancer therapeutics[J].Pharmacol Ther,2022,229:107923.[14]Palmeri M,Mehnert J,Silk AW,et al.Real-world application of tumor mutational burden-high (TMB-high) and microsatellite instability (MSI) confirms their utility as immunotherapy biomarkers[J].ESMO Open,2022,7(1):100336.[15]Jiang P,Gu S,Pan D,et al.Signatures of T cell dysfunction and exclusion predict cancer immunotherapy response[J].Nat Med,2018,24(10):1550-1558.[16]Zhou Y,Chen Y,Shi Y,et al.FAM117B promotes gastric cancer growth and drug resistance by targeting the KEAP1/NRF2 signaling pathway[J].J Clin Invest,2023,133(3):e158705.[17]He B,Hu Y,Wu Y,et al.Helicobacter pylori CagA elevates FTO to induce gastric cancer progression via a "hit-and-run" paradigm[J].Cancer Commun (Lond),2025,45(5):608-631.[18]Steinhoff JS,Lass A,Schupp M.Biological Functions of RBP4 and Its Relevance for Human Diseases[J].Front Physiol,2021,12:659977.[19]Yu Y,Zhang C,Sun Q,et al.Retinol Binding Protein 4 Serves as a Potential Tumor Biomarker and Promotes Malignant Behavior in Gastric Cancer[J].Cancer Manag Res,2024,16:891-908.[20]Feng L,Li G,Li D,et al.Cuproptosis-related gene SERPINE1 is a prognostic biomarker and correlated with immune infiltrates in gastric cancer[J].J Cancer Res Clin Oncol,2023,149(12):10851-10865.[21]Farup PG,Rootwelt H,Hestad K.APOE-a genetic marker of comorbidity in subjects with morbid obesity[J].BMC Med Genet,2020,21(1):146.[22]Jones NS,Watson KQ,Rebeck GW.High-fat diet increases gliosis and immediate early gene expression in APOE3 mice, but not APOE4 mice[J].J Neuroinflammation,2021,18(1):214.[23]Li WF,Que CR,Xu DB,et al.Impact of visceral fat distribution on postoperative complications in high-aged patients undergoing gastric cancer surgery: A cross-sectional study[J].World J Gastroenterol,2025,31(22):105201.[24]Samson WK,Salvemini D,Yosten GLC.Overcoming Stress, Hunger, and Pain: Cocaine- and Amphetamine-Regulated Transcript Peptide′s Promise[J].Endocrinology,2021,162(8):bqab108.

相似文献/References:

[1]尹晓华,刘重元,黄 琳,等.胃癌中lncRNAs的研究进展[J].医学信息,2018,31(03):10.[doi:10.3969/j.issn.1006-1959.2018.03.004]
　YIN Xiao-hua,LIU Zhong-yuan,HUANG Lin,et al.Research Progress of lncRNAs in Gastric Cancer[J].Journal of Medical Information,2018,31(10):10.[doi:10.3969/j.issn.1006-1959.2018.03.004]
[2]芮昆昆,章 波,邰小华,等.基质金属蛋白酶2与蛋白磷酸酶2A的癌性抑制因子在胃癌中的研究进展[J].医学信息,2018,31(03):21.[doi:10.3969/j.issn.1006-1959.2018.03.007]
　RUI Kun-kun,ZHANG Bo,TAI Xiao-hua,et al.The Research Progress of Matrix Metalloproteinase 2 and Cancer Inhibitor of Protein Phosphatase 2A in Gastric Cancer[J].Journal of Medical Information,2018,31(10):21.[doi:10.3969/j.issn.1006-1959.2018.03.007]
[3]龙 颖,李运泽,汤中敏,等.非酒精性脂肪性肝病与血尿酸水平测定及其临床意义[J].医学信息,2018,31(07):92.[doi:10.3969/j.issn.1006-1959.2018.07.029]
　LONG Ying,LI Yun-ze,TANG Zhong-min,et al.Determination of Serum Uric Acid Level and its Clinical Significance in Non-alcoholic Fatty Liver Disease[J].Journal of Medical Information,2018,31(10):92.[doi:10.3969/j.issn.1006-1959.2018.07.029]
[4]段 巍.1例晚期胃癌化疗并发嗜血细胞综合征患者的护理[J].医学信息,2018,31(10):181.[doi:10.3969/j.issn.1006-1959.2018.10.063]
　DUAN Wei.Nursing Care of a Case of Advanced Gastric Carcinoma with Hemophagocytic Syndrome after Chemotherapy[J].Journal of Medical Information,2018,31(10):181.[doi:10.3969/j.issn.1006-1959.2018.10.063]
[5]潘理会,李育庄,李春辉.胃癌与高凝血状态关系的研究现状[J].医学信息,2018,31(11):15.[doi:10.3969/j.issn.1006-1959.2018.11.005]
　PAN Li-hui,LI Yu-zhuang,LI Chun-hui.Research Status of the Relationship between Gastric Carcinoma and Hypercoagulable State[J].Journal of Medical Information,2018,31(10):15.[doi:10.3969/j.issn.1006-1959.2018.11.005]
[6]崔姗姗,刘 英,江 霞.非酒精性脂肪性肝病与胰岛素抵抗的研究进展[J].医学信息,2022,35(10):66.[doi:10.3969/j.issn.1006-1959.2022.10.016]
　CUI Shan-shan,LIU Ying,JIANG Xia.Research Progress on Non-alcoholic Fatty Liver Disease and Insulin Resistance[J].Journal of Medical Information,2022,35(10):66.[doi:10.3969/j.issn.1006-1959.2022.10.016]
[7]向姣姣,李国娟,杨通艳,等.肠道菌群与肥胖发病机制的研究[J].医学信息,2022,35(10):70.[doi:10.3969/j.issn.1006-1959.2022.10.017]
　XIANG Jiao-jiao,LI Guo-juan,YANG Tong-yan,et al.Study on Intestinal Flora and Pathogenesis of Obesity[J].Journal of Medical Information,2022,35(10):70.[doi:10.3969/j.issn.1006-1959.2022.10.017]
[8]刘 静.利拉鲁肽联合基础胰岛素对初诊2型糖尿病合并肥胖患者 血糖控制及体质量指数的影响[J].医学信息,2018,31(13):137.[doi:10.3969/j.issn.1006-1959.2018.13.040]
　LIU Jing.Effect of Liraglutide Combined with Basal Insulin on Blood Glucose Control and Body Mass Index in Newly Diagnosed Type 2 Diabetes Patients with Obesity[J].Journal of Medical Information,2018,31(10):137.[doi:10.3969/j.issn.1006-1959.2018.13.040]
[9]李虹霞,刘伏山.慢性萎缩性胃炎的中西医治疗[J].医学信息,2022,35(11):29.[doi:10.3969/j.issn.1006-1959.2022.11.009]
　LI Hong-Xia,LIU Fu-shan.Treatment of Chronic Atrophic Gastritis with Traditional Chinese and Western Medicine[J].Journal of Medical Information,2022,35(10):29.[doi:10.3969/j.issn.1006-1959.2022.11.009]
[10]曾利文,陈 静,张 晔,等.多囊卵巢综合征患者的糖代谢特点分析[J].医学信息,2019,32(02):103.[doi:10.3969/j.issn.1006-1959.2019.02.029]
　ZENG Li-wen,CHEN Jing,ZHANG Ye,et al.Analysis of Characteristics of Glucose Metabolism in Patients with Polycystic Ovarian Syndrome[J].Journal of Medical Information,2019,32(10):103.[doi:10.3969/j.issn.1006-1959.2019.02.029]

更新日期/Last Update: 1900-01-01