WGCNA与机器学习算法识别结直肠癌发病机制中潜在PANoptosis关键基因-东南大学学报医学版

WGCNA与机器学习算法识别结直肠癌发病机制中潜在PANoptosis关键基因

单位：1. 贵州医科大学, 贵州贵阳 550000;
2. 六盘水市人民医院消化内科, 贵州六盘水 553000

分类号：R714.255

出版年·卷·期（页码）：2023·42·第五期（688-696）

摘要：

目的:利用生物信息学与机器学习算法筛选结直肠癌(CRC)发病机制中的PANoptosis关键基因,开发并验证与CRC相关的多基因预测模型。方法:基于基因表达综合数据库(GEO)中CRC基因芯片筛选CRC组织与正常组织差异表达基因(DEGs)。利用加权基因共表达网络分析(WGCNA)筛选疾病特征模块基因。采用最小绝对值收敛和选择算子(LASSO)算法、支持向量机-递归特征消除(SVM-RFE)和随机森林算法获得枢纽基因,并取PANoptosis相关基因的交集,获得PANoptosis关键基因,构建预测CRC的列线图模型。使用受试者工作特征(ROC)曲线确定PANoptosis关键基因及列线图模型的诊断价值。结果:共获得4个PANoptosis关键基因,即细胞周期蛋白依赖性激酶1(CDK1)、二肽酶1(DPEP1)、半胱氨酸天冬氨酸蛋白水解酶 7(CASP7)和半胱氨酸天冬氨酸蛋白水解酶 8(CASP8)。基于4个PANoptosis关键基因,在训练集构建nomogram图,其校准预测曲线与标准曲线贴合较好,且在预测CRC发生的临床效能上表现良好。在验证集也证实了上述结果。在训练集和验证集中均发现基于4个PANoptosis关键基因的预测模型能够准确地区分正常和肿瘤组织样本。结论:利用WGCNA和机器学习算法得到与PANoptosis相关的4个基因并构建列线图模型,可能成为诊断CRC的有价值工具。

Objective: To screen PANoptosis key genes in colorectal cancer(CRC) pathogenesis using bioinformatics and machine learning algorithms, and to develop and validate a multigene prediction model related to CRC. Methods: CRC genes were screened for differentially expressed genes(DEGs) between colorectal cancer tissues and normal tissues based on the CRC GeneChip in the Gene Expression Omnibus(GEO) database. Weighted gene co-expression network analysis(WGCNA) was used to screen the genes of the disease characterization module. The Least Absolute Value Convergence and Selection Operator(LASSO) algorithm, Support Vector Machine-Recursive Feature Elimination(SVM-RFE) and Random Forest algorithms were used to obtain pivotal genes, and the intersection of PANoptosis-related genes was taken to obtain the key genes of PANoptosis, and to construct a column-line graph model for predicting CRC. The diagnostic value of the PANoptosis key genes and the column-line diagram model was determined using the subject's work characteristics(ROC) curve. Results: A total of 4 PANoptosis key genes were obtained, i.e., cyclin-dependent kinase 1(CDK1), Dipeptidase 1(DPEP1), Caspase 7(CASP7), and Caspase 8(CASP8).Based on the 4 PANoptosis key genes, a nomogram model was constructed in the training set, and their calibrated prediction curves fit well with the standard curves and performed well in predicting the clinical efficacy of CRC occurrence.The above results were also confirmed in the validation set. The prediction model based on the four PANoptosis key genes was found to accurately discriminate between normal and tumor tissue samples in both the training and validation sets. Conclusion: Constructing a nomogrammodel based on the 4 genes associated with PANoptosis obtained from WGCNA and machine learning algorithms may be a valuable tool for the diagnosis of CRC.

参考文献：

[1] 田传鑫,赵磊.结直肠癌及结直肠癌肝转移流行病学特点[J].中华肿瘤防治杂志,2021,28(13):1033-1038.
[2] 邱海波,曹素梅,徐瑞华.基于2020年全球流行病学数据分析中国癌症发病率、死亡率和负担的时间趋势及与美国和英国数据的比较[J].癌症,2022,41(4):165-177.
[3] 陈玲玲,段晓侠,施彩虹,等.微视频结合关键点指导在老年患者结肠镜检查肠道准备中的应用[J].中华全科医学,2023,21(2):341-344.
[4] 刘锦燕,郑彧鸣,曹祎婕,等.结直肠癌诊断性生物标志物的研究进展[J].标记免疫分析与临床,2022,29(9):1592-1596.
[5] ZHENG M,KANNEGANTI T D.The regulation of the ZBP1-NLRP3 inflammasome and its implications in pyroptosis,apoptosis,and necroptosis(PANoptosis)[J].Immunol Rev,2020,297(1):26-38.
[6] HUANG X,LIU S,WU L,et al.High throughput single cell RNA sequencing,bioinformatics analysis and applications[J].Adv Exp Med Biol,2018,1068:33-43.
[7] LIANG W,SUN F,ZHAO Y,et al.Identification of susceptibility modules and genes for cardiovascular disease in diabetic patients using WGCNA analysis[J].J Diabetes Res,2020,2020:4178639.
[8] PEIFFER-SMADJA N,RAWSON T M,AHMAD R,et al.Machine learning for clinical decision support in infectious diseases:a narrative review of current applications[J].Clin Microbiol Infect,2020,26(5):584-595.
[9] ZHANG W,XIE X,HUANG Z,et al.The integration of single-cell sequencing,TCGA,and GEO data analysis revealed that PRRT3-AS1 is a biomarker and therapeutic target of SKCM[J].Front Immunol,2022,13:919145.
[10] 李飞,秦强强,谷战峰,等.基于生物信息学的结直肠癌枢纽基因与预后相关基因筛选[J].中华结直肠疾病电子杂志,2021,10(5):497-504.
[11] YANG Y,YI X,CAI Y,et al.Immune-associated gene signatures and subtypes to predict the progression of atherosclerotic plaques based on machine learning[J].Front Pharmacol,2022,13:865624.
[12] CHOI R Y,COYNER A S,KALPATHY-CRAMER J,et al.Introduction to machine learning,neural networks,and deep learning[J].Transl Vis Sci Technol,2020,9(2):14.
[13] OLCUM M,ROUHI L,FAN S,et al.PANoptosis is a prominent feature of desmoplakin cardiomyopathy[J].J Cardiovasc Aging,2023,3(1):3.
[14] SAMIR P,MALIREDDI R K S,KANNEGANTI T D.The PANoptosome:a deadly protein complex driving pyroptosis,apoptosis,and necroptosis(PANoptosis)[J].Front Cell Infect Microbiol,2020,10:238.
[15] PLACE D E,LEE S,KANNEGANTI T D.PANoptosis in microbial infection[J].Curr Opin Microbiol,2021,59:42-49.
[16] PAN H,PAN J,LI P,et al.Characterization of PANoptosis patterns predicts survival and immunotherapy response in gastric cancer[J].Clin Immunol,2022,238:109019.
[17] HUANG J,JIANG S,LIANG L,et al.Analysis of PANoptosis-related LncRNA-miRNA-mRNA network reveals LncRNA SNHG7 involved in chemo-resistance in colon adenocarcinoma[J].Front Oncol,2022,12:888105.
[18] 艾平平,谈顺.CDK1与结直肠癌的研究进展[J].临床与实验病理学杂志,2019,35(5):561-563.
[19] CHOUDHURY S R,BABES L,RAHN J J,et al.Dipeptidase-1 Is an adhesion receptor for neutrophil recruitment in lungs and liver[J].Cell,2019,178(5):1205-1221.e17.
[20] ZENG C,QI G,SHEN Y,et al.DPEP1 promotes drug resistance in colon cancer cells by forming a positive feedback loop with ASCL2[J].Cancer Med,2023,12(1):412-424.
[21] 黄金华,温小平,曾建强,等.DPEP1在结直肠上皮内瘤变组织中的表达及临床意义[J].现代肿瘤医学,2019,27(6):1024-1028.
[22] 尹露茜,金晶,谭文,等.凋亡通路基因的遗传变异与直肠癌患者术后同步放化疗不良反应有关[J].中华肿瘤杂志,2020,42(5):376-382.
[23] MALL R,BYNIGERI R R,KARKi R,et al.Pancancer transcriptomic profiling identifies key PANoptosis markers as therapeutic targets for oncology[J].NAR Cancer,2022,4(4):zcac033.
[24] CHEN D,LIU J,ZANG L,et al.Integrated machine learning and bioinformatic analyses constructed a novel stemness-related classifier to predict prognosis and immunotherapy responses for hepatocellular carcinoma patients[J].Int J Biol Sci,2022,18(1):360-373.
[25] LIU Z,MI M,LI X,et al.A lncRNA prognostic signature associated with immune infiltration and tumour mutation burden in breast cancer[J].J Cell Mol Med,2020,24(21):12444-12456.

服务与反馈：

【文章下载】【发表评论】【查看评论】【加入收藏】

提示：您还未登录，请登录！点此登录