机器学习筛选脓毒症特征预测基因

钱 义才, 钱 奇锋, 陈 启欣, 汪宇 扬通
安徽医科大学第一附属医院 安徽合肥 230032

摘要

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

关键词：脓毒症；生物信息学；生物标志物

参考

[1] 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.

[2] 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.

[3] 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.

[4] FRIEDMAN J, HASTIE T, TIBSHIRANI R. Regularization

Paths for Generalized

Linear Models via Coordinate Descent [J]. J Stat Softw, 2010, 33(1):

1-22.

[5] 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.

[6] 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.

[7] 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.

[8] 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.

[9] 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.

[10] 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.

[11] 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.

[12] WATANABE S, UCHIDA T. Cloning and expression of human

uridine phosphorylase [J]. Biochem Biophys Res Commun, 1995, 216(1):

265-72.

[13] 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.

[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.

[15] 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.

[16] 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.

[17] 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.

[18] 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.

[19] 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.

[20] 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.

[21] 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.

[22] 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.

[23] 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).

[24] 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.

[25] 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.

[26] 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.

[27] HALLORAN M C, WOLMAN M A. Repulsion or adhesion:

receptors make the call[J].Curr Opin Cell Biol, 2006, 18(5): 533-40.

[28] 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.

[29] 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.

[30] 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.

[31] 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.

基金项目：安徽省医学会急诊医学临床研究项目（Ky2021023）