机器学习筛选脓毒症特征预测基因
摘要
目的：本研究通过生物信息学方法来寻找脓毒症特征预测基因，探讨机器学习在筛选脓毒症特征预测基因方面的应用。
方法与结果：1.从GEO数据库下载GSE26440、GSE54514、GSE57065三个脓毒症全血基因表达谱数据集。 2.将GSE26440和GSE57065数据集作为实验组进行两种算法进行特征基因筛选，运用Lasso算法共筛选19个脓毒症特征基因，运用SVM算法筛选出13个脓毒症特征基因，将Lasso与SVM算法筛选的脓毒症特征基因取交集，共得到5个脓毒症候选特征基因。3.将GSE54514做为验证组对5个脓毒症筛选特征基因进行验证，确定了MCEMP1、UPP1、CD177、CYSTM1和RAB13共5个DEmRNAs作为诊断基因生物标志物。4.对差异基因进行GO分析、KEGG分析，结果表明，参与炎症反应的差异基因包括T细胞激活、免疫反应调控信号通路、白细胞介导的免疫等。5.对差异基因使用CIBERSORT进行免疫细胞浸润分析，显示中性粒细胞、单核细胞、M0型巨噬细胞在脓毒症血液中表达水平明显较高。6.共筛选出MCEMP1、UPP1、CD177、CYSTM1、RAB13五个脓毒症特征预测基因。
结论：机器学习可以用来筛选脓毒症特征预测基因。MCEMP1、UPP1、CD177、CYSTM1、RAB13是脓毒症特征预测基因，可能为脓毒症的早期诊断及预后判断提供帮助。
关键词
参考
RITCHIE M E, PHIPSON B, WU D, et al. limma powers differential expression analyses for RNA-sequencing and microarray studies [J]. Nucleic Acids Res, 2015, 43(7): e47.
ASHBURNER M, BALL C A, BLAKE J A, et al. Gene ontology: tool for the unification of biology. The Gene Ontology Consortium [J]. Nat Genet, 2000, 25(1): 25-9.
KANEHISA M, GOTO S, FURUMICHI M, et al. KEGG for representation and analysis of molecular networks involving diseases and drugs [J]. Nucleic Acids Res, 2010, 38(Database issue): D355-60.
FRIEDMAN J, HASTIE T, TIBSHIRANI R. Regularization Paths for Generalized
Linear Models via Coordinate Descent [J]. J Stat Softw, 2010, 33(1): 1-22.
HUANG M L, HUNG Y H, LEE W M, et al. SVM-RFE based feature selection and Taguchi parameters optimization for multiclass SVM classifier[J]. Scientific World Journal, 2014, 2014: 795624.
BARICHELLO T, GENEROSO J S, SINGER M, et al. Biomarkers for sepsis: more than just fever and leukocytosis-a narrative review [J]. Crit Care, 2022, 26(1): 14.
LI K, WANG S W, LI Y, et al. Identification and expression of a new type II transmembrane protein in human mast cells [J]. Genomics, 2005, 86(1): 68-75.
RAMAN K, O'DONNELL M J, CZLONKOWSKA A, et al. Peripheral Blood MCEMP1 Gene Expression as a Biomarker for Stroke Prognosis [J]. Stroke, 2016, 47(3):652-8.
STRBIAN D, KARJALAINEN-LINDSBERG M L, TATLISUMAK T, et al. Cerebral mast cells regulate early ischemic brain swelling and neutrophil accumulation [J]. J Cereb Blood Flow Metab, 2006, 26(5): 605-12.
XIE W, CHEN L, CHEN L, et al. Silencing of long non-coding RNA MALAT1 suppresses inflammation in septic mice: role of microRNA-23a in the down-regulation of MCEMP1 expression [J]. Inflamm Res, 2020, 69(2): 179-90.
CHEN J X, XU X, ZHANG S. Silence of long noncoding RNA NEAT1 exerts suppressive effects on immunity during sepsis by promoting microRNA- 125-dependent MCEMP1 downregulation [J]. IUBMB Life, 2019, 71(7): 956-68.
WATANABE S, UCHIDA T. Cloning and expression of human uridine phosphorylase [J]. Biochem Biophys Res Commun, 1995, 216(1): 265-72.
ROOSILD T P, CASTRONOVO S, FABBIANI M, et al. Implications of the structure of human uridine phosphorylase 1 on the development of novel inhibitors for improving the therapeutic window of fluoropyrimidine chemotherapy [J]. BMC Struct Biol, 2009, 9 : 14.
ZHANG D, CAO D, RUSSELL R, et al. p53-dependent suppression of uridine phosphorylase gene expression through direct promoter interaction [J]. Cancer Res, 2001, 61(18): 6899-905.
WANG J, XU S, LV W, et al. Uridine phosphorylase 1 is a novel immune-related target and predicts worse survival in brain glioma [J]. Cancer Med, 2020, 9(16):5940-7.
HAMASAKI M Y, SEVERINO P, PUGA R D, et al. Short-Term Effects of Sepsis and the Impact of Aging on the Transcriptional Profile of Different Brain Regions [J]. Inflammation, 2019, 42(3): 1023-31.
LONG G, YANG C. A six‑gene support vector machine classifier contributes to the diagnosis of pediatric septic shock [J]. Mol Med Rep, 2020, 21(3): 1561-71.
SACHS U J, ANDREI-SELMER C L, MANIAR A, et al. The neutrophil-specific antigen CD177 is a counter-receptor for platelet endothelial cell adhesion molecule- 1 (CD31) [J]. J Biol Chem, 2007, 282(32): 23603- 12.
WOLFF J C, GOEHRING K, HECKMANN M, et al. Sex-dependent up regulation of CD 177-specific mRNA expression in cord blood due to different stimuli [J]. Transfusion, 2006, 46(1): 132-6.
Gö HRING K, WOLFF J, DOPPL W, et al. Neutrophil CD177 (NB1 gp,HNA-2a)expression is increased in severe bacterial infections and polycythaemia vera [J]. Br J Haematol, 2004, 126(2): 252-4.
RASOOLI A, GHAFARI E, SAEDI H, et al. Expression changes of CD177 and MPO as novel biomarkers in lung tissue of CLP model rats [J]. Turk J Med Sci, 2018, 48(6): 1321.
DEMARET J, VENET F, PLASSAIS J, et al. Identification of CD177 as the most dysregulated parameter in a microarray study of purified neutrophils from septic shock patients [J]. Immunol Lett, 2016, 178: 122-30.
MARTí NEZ- PAZ P, ARAGó N-CAMINO M, G ó MEZ-Sá NCHEZ E, et al. Gene Expression Patterns Distinguish Mortality Risk in Patients with Postsurgical Shock [J].J Clin Med,2020,9(5).
MASTROKOLIAS A, ARIYUREK Y, GOEMAN J J, et al. Huntington's disease biomarker progression profile identified by transcriptome sequencing in peripheral blood [J]. Eur J Hum Genet, 2015, 23(10): 1349-56.
VENANCIO T M, ARAVIND L. CYSTM, a novel cysteine-rich transmembrane module with a role in stress tolerance across eukaryotes [J]. Bioinformatics, 2010, 26(2): 149-52.
NISHIKIMI A, ISHIHARA S, OZAWA M, et al. Rab13 acts downstream of the kinase Mst1 to deliver the integrin LFA-1 to the cell surface for lymphocyte trafficking [J]. Sci Signal, 2014, 7(336): ra72.
HALLORAN M C, WOLMAN M A. Repulsion or adhesion: receptors make the call[J].Curr Opin Cell Biol, 2006, 18(5): 533-40.
NISHIMURA N, SASAKI T. Regulation of epithelial cell adhesion and repulsion : role of endocytic recycling [J]. J Med Invest, 2008, 55(1-2): 9-16.
FAN Y, HAN Q, LI J, et al. Revealing potential diagnostic gene biomarkers of septic shock based on machine learning analysis [J]. BMC Infect Dis, 2022, 22(1):65.
ALI H R, PROVENZANO E, DAWSON S J, et al. Association between CD8+ T-cell infiltration and breast cancer survival in 12,439 patients [J]. Ann Oncol, 2014, 25(8): 1536-43.
CHEN B, KHODADOUST M S, LIU C L, et al. Profiling Tumor Infiltrating Immune Cells with CIBERSORT [J]. Methods Mol Biol, 2018, 1711: 243-59.