Identification of potential biomarkers of lupus nephritis based on machine learning and weighted gene co-expression network analysis_West China Medical Journal

Authors：

BAI Zhixun ¹ , WANG Yanping ² , YANG Jie ³ ,  TAN Zhouke ¹

1. Organ Transplantation Center, Affiliated Hospital of Zunyi Medical University, Zunyi, Guizhou 563000, P. R. China;
2. Clinical College, Zunyi Medical University, Zunyi, Guizhou 563000, P. R. China;
3. Department of Laboratory, the Second Affiliated Hospital of Zunyi Medical University, Zunyi, Guizhou 563000, P. R. China;

Corresponding author：

TAN Zhouke, Email: tanzhouke@zmu.edu.cn

Keywords：

Hub gene; weighted gene co-expression network analysis; potential biomarker; lupus nephritis

DOI：

10.7507/1002-0179.202306132

Video：

Export PDF Favorites Scan Get Citation

Abstract Full text Figures/Tables Video References Cited by

Objective To explore the potential mechanism of the occurrence and development of lupus nephritis (LN) and identify key biomarkers and immune-related pathways associated with the progression of LN. Methods We downloaded a dataset from the Gene Expression Omnibus database. By analyzing the differential expression of genes and performing weighted gene co-expression network analysis (WGCNA), as well as Gene Ontology enrichment, Disease Ontology enrichment, and Kyoto Encyclopedia of Genes and Genomes pathway enrichment, we explored the biological functions of differentially expressed genes in LN. Using three machine learning models, namely LASSO regression, support vector machine, and random forest, we identified the hub genes in LN, and constructed a line diagram diagnosis model based on the hub genes. The diagnostic accuracies of the hub genes were evaluated using the receiver operating characteristic curve, and the relationship between known marker gene sets and hub gene expression was analyzed using single sample gene set enrichment analysis. Results We identified a total of 2297 differentially expressed genes. WGCNA generated 7 co-expression modules, among which the cyan module had the highest correlation with LN. We obtained 347 target genes by combining differential genes. Using the three machine learning methods, LASSO regression, support vector machine, and random forest, we identified three hub genes (CLC, ADGRE4P, and CISD2) that could serve as potential biomarkers for LN. The area under the receiver operating characteristic curve (AUC) analysis showed that these three hub genes had significant diagnostic value (AUC_CLC=0.718, AUC_ADGRE4P=0.813, AUC_CISD2=0.718). According to single sample gene set enrichment analysis, the hub genes were mainly associated with apoptosis, glycolysis, metabolism, hypoxia, and tumor necrosis factor-α-nuclear factor-κB-related pathways. Conclusions By combining WGCNA and machine learning techniques, three hub genes (CLC, ADGRE4P, and CISD2) that may be involved in the occurrence and development of LN are identified. These genes have the potential to aid in the early clinical diagnosis of LN and provide insight into the mechanisms underlying LN progression.

Citation： BAI Zhixun, WANG Yanping, YANG Jie, TAN Zhouke. Identification of potential biomarkers of lupus nephritis based on machine learning and weighted gene co-expression network analysis. West China Medical Journal, 2023, 38(7): 996-1005. doi: 10.7507/1002-0179.202306132 Copy

1.	Hanly JG, O’Keeffe AG, Su L, et al. The frequency and outcome of lupus nephritis: results from an international inception cohort study. Rheumatology (Oxford), 2016, 55(2): 252-262.
2.	Maria NI, Davidson A. Protecting the kidney in systemic lupus erythematosus: from diagnosis to therapy. Nat Rev Rheumatol, 2020, 16(5): 255-267.
3.	Li LS, Liu ZH. Epidemiologic data of renal diseases from a single unit in China: analysis based on 13, 519 renal biopsies. Kidney Int, 2004, 66(3): 920-923.
4.	Faurschou M, Dreyer L, Kamper AL, et al. Long-term mortality and renal outcome in a cohort of 100 patients with lupus nephritis. Arthritis Care Res (Hoboken), 2010, 62(6): 873-880.
5.	Wang LH, Wang WM, Lin SH, et al. Bidirectional relationship between systemic lupus erythematosus and non-Hodgkin’s lymphoma: a nationwide population-based study. Rheumatology (Oxford), 2019, 58(7): 1245-1249.
6.	Gayed M, Bernatsky S, Ramsey-Goldman R, et al. Lupus and cancer. Lupus, 2009, 18(6): 479-485.
7.	Mugnaini EN, Ghosh N. Lymphoma. Prim Care, 2016, 43(4): 661-675.
8.	Armitage JO, Gascoyne RD, Lunning MA, et al. Non-Hodgkin lymphoma. Lancet, 2017, 390(10091): 298-310.
9.	Mellemkjaer L, Andersen V, Linet MS, et al. Non-Hodgkin’s lymphoma and other cancers among a cohort of patients with systemic lupus erythematosus. Arthritis Rheum, 1997, 40(4): 761-768.
10.	Boddu P, Mohammed AS, Annem C, et al. SLE and non-Hodgkin’s lymphoma: a case series and review of the literature. Case Rep Rheumatol, 2017, 2017: 1658473.
11.	Ouyang S, Liu Y, Xiao C, et al. Identification of latent diagnostic biomarkers and biological pathways in dermatomyositis based on WGCNA. J Oncol, 2021, 2021: 1920111.
12.	Bian W, Wang Z, Li X, et al. Identification of vital modules and genes associated with heart failure based on weighted gene coexpression network analysis. ESC Heart Fail, 2022, 9(2): 1370-1379.
13.	Zhou J, Zhang W, Wei C, et al. Weighted correlation network bioinformatics uncovers a key molecular biosignature driving the left-sided heart failure. BMC Med Genomics, 2020, 13(1): 93.
14.	McEligot AJ, Poynor V, Sharma R, et al. Logistic LASSO regression for dietary intakes and breast cancer. Nutrients, 2020, 12(9): 2652.
15.	Zhu YX, Huang JQ, Ming YY, et al. Screening of key biomarkers of tendinopathy based on bioinformatics and machine learning algorithms. PLoS One, 2021, 16(10): e0259475.
16.	Hanko M, Grendár M, Snopko P, et al. Random forest-based prediction of outcome and mortality in patients with traumatic brain injury undergoing primary decompressive craniectomy. World Neurosurg, 2021, 148: e450-e458.
17.	Cao J, Liu Z, Liu J, et al. Bioinformatics analysis and identification of genes and pathways in ischemic cardiomyopathy. Int J Gen Med, 2021, 14: 5927-5937.
18.	Jiang Y, Chen L, Chao Z, et al. Ferroptosis related genes in ischemic and idiopathic cardiomyopathy: screening for potential pharmacological targets. Front Cell Dev Biol, 2022, 10: 817819.
19.	Song H, Chen S, Zhang T, et al. Integrated strategies of diverse feature selection methods identify aging-based reliable gene signatures for ischemic cardiomyopathy. Front Mol Biosci, 2022, 9: 805235.
20.	Xia M, Liu CJ, Zhang Q, et al. GEDS: a gene expression display server for mRNAs, miRNAs and proteins. Cells, 2019, 8(7): 675.
21.	Raimbourg Q, Daugas É. Lupus nephritis. Nephrol Ther, 2019, 15(3): 174-189.
22.	Anders HJ, Saxena R, Zhao MH, et al. Lupus nephritis. Nat Rev Dis Primers, 2020, 6(1): 7.
23.	Kiriakidou M, Ching CL. Systemic lupus erythematosus. Ann Intern Med, 2020, 172(11): ITC81-ITC96.
24.	Kong F, Yan Z, Lan N, et al. Construction and validation of gastric cancer diagnosis model based on machine learning. Explor Med, 2022, 3: 300-313.
25.	Li YR, Meng K, Yang G, et al. Diagnostic genes and immune infiltration analysis of colorectal cancer determined by LASSO and SVM machine learning methods: a bioinformatics analysis. J Gastrointest Oncol, 2022, 13(3): 1188-1203.
26.	Liu J, Liu L, Antwi PA, et al. Identification and validation of the diagnostic characteristic genes of ovarian cancer by bioinformatics and machine learning. Front Genet, 2022, 13: 858466.
27.	Lai YL, Liu CH, Wang SC, et al. Identification of a steroid hormone-associated gene signature predicting the prognosis of prostate cancer through an integrative bioinformatics analysis. Cancers (Basel), 2022, 14(6): 1565.
28.	Jiang Z, Shao M, Dai X, et al. Identification of diagnostic biomarkers in systemic lupus erythematosus based on bioinformatics analysis and machine learning. Front Genet, 2022, 13: 865559.
29.	Zhou Y, Shi W, Zhao D, et al. Identification of immune-associated genes in diagnosing aortic valve calcification with metabolic syndrome by integrated bioinformatics analysis and machine learning. Front Immunol, 2022, 13: 937886.
30.	Xiong T, Han S, Pu L, et al. Bioinformatics and machine learning methods to identify fn1 as a novel biomarker of aortic valve calcification. Front Cardiovasc Med, 2022, 9: 832591.
31.	Li C, Tian C, Zeng Y, et al. Machine learning and bioinformatics analysis revealed classification and potential treatment strategy in stage 3-4 NSCLC patients. BMC Med Genomics, 2022, 15(1): 33.
32.	Kalafi EY, Nor NAM, Taib NA, et al. Machine learning and deep learning approaches in breast cancer survival prediction using clinical data. Folia Biol (Praha), 2019, 65(5/6): 212-220.
33.	Kwakkenbos MJ, Kop EN, Stacey M, et al. The EGF-TM7 family: a postgenomic view. Immunogenetics, 2004, 55(10): 655-666.
34.	Kramer EB, Farabaugh PJ. The frequency of translational misreading errors in E. coli is largely determined by tRNA competition. RNA, 2007, 13(1): 87-96.
35.	Bernatsky S, Ramsey-Goldman R, Joseph L, et al. Lymphoma risk in systemic lupus: effects of disease activity versus treatment. Ann Rheum Dis, 2014, 73(1): 138-142.

1. Hanly JG, O’Keeffe AG, Su L, et al. The frequency and outcome of lupus nephritis: results from an international inception cohort study. Rheumatology (Oxford), 2016, 55(2): 252-262.
2. Maria NI, Davidson A. Protecting the kidney in systemic lupus erythematosus: from diagnosis to therapy. Nat Rev Rheumatol, 2020, 16(5): 255-267.
3. Li LS, Liu ZH. Epidemiologic data of renal diseases from a single unit in China: analysis based on 13, 519 renal biopsies. Kidney Int, 2004, 66(3): 920-923.
4. Faurschou M, Dreyer L, Kamper AL, et al. Long-term mortality and renal outcome in a cohort of 100 patients with lupus nephritis. Arthritis Care Res (Hoboken), 2010, 62(6): 873-880.
5. Wang LH, Wang WM, Lin SH, et al. Bidirectional relationship between systemic lupus erythematosus and non-Hodgkin’s lymphoma: a nationwide population-based study. Rheumatology (Oxford), 2019, 58(7): 1245-1249.
6. Gayed M, Bernatsky S, Ramsey-Goldman R, et al. Lupus and cancer. Lupus, 2009, 18(6): 479-485.
7. Mugnaini EN, Ghosh N. Lymphoma. Prim Care, 2016, 43(4): 661-675.
8. Armitage JO, Gascoyne RD, Lunning MA, et al. Non-Hodgkin lymphoma. Lancet, 2017, 390(10091): 298-310.
9. Mellemkjaer L, Andersen V, Linet MS, et al. Non-Hodgkin’s lymphoma and other cancers among a cohort of patients with systemic lupus erythematosus. Arthritis Rheum, 1997, 40(4): 761-768.
10. Boddu P, Mohammed AS, Annem C, et al. SLE and non-Hodgkin’s lymphoma: a case series and review of the literature. Case Rep Rheumatol, 2017, 2017: 1658473.
11. Ouyang S, Liu Y, Xiao C, et al. Identification of latent diagnostic biomarkers and biological pathways in dermatomyositis based on WGCNA. J Oncol, 2021, 2021: 1920111.
12. Bian W, Wang Z, Li X, et al. Identification of vital modules and genes associated with heart failure based on weighted gene coexpression network analysis. ESC Heart Fail, 2022, 9(2): 1370-1379.
13. Zhou J, Zhang W, Wei C, et al. Weighted correlation network bioinformatics uncovers a key molecular biosignature driving the left-sided heart failure. BMC Med Genomics, 2020, 13(1): 93.
14. McEligot AJ, Poynor V, Sharma R, et al. Logistic LASSO regression for dietary intakes and breast cancer. Nutrients, 2020, 12(9): 2652.
15. Zhu YX, Huang JQ, Ming YY, et al. Screening of key biomarkers of tendinopathy based on bioinformatics and machine learning algorithms. PLoS One, 2021, 16(10): e0259475.
16. Hanko M, Grendár M, Snopko P, et al. Random forest-based prediction of outcome and mortality in patients with traumatic brain injury undergoing primary decompressive craniectomy. World Neurosurg, 2021, 148: e450-e458.
17. Cao J, Liu Z, Liu J, et al. Bioinformatics analysis and identification of genes and pathways in ischemic cardiomyopathy. Int J Gen Med, 2021, 14: 5927-5937.
18. Jiang Y, Chen L, Chao Z, et al. Ferroptosis related genes in ischemic and idiopathic cardiomyopathy: screening for potential pharmacological targets. Front Cell Dev Biol, 2022, 10: 817819.
19. Song H, Chen S, Zhang T, et al. Integrated strategies of diverse feature selection methods identify aging-based reliable gene signatures for ischemic cardiomyopathy. Front Mol Biosci, 2022, 9: 805235.
20. Xia M, Liu CJ, Zhang Q, et al. GEDS: a gene expression display server for mRNAs, miRNAs and proteins. Cells, 2019, 8(7): 675.
21. Raimbourg Q, Daugas É. Lupus nephritis. Nephrol Ther, 2019, 15(3): 174-189.
22. Anders HJ, Saxena R, Zhao MH, et al. Lupus nephritis. Nat Rev Dis Primers, 2020, 6(1): 7.
23. Kiriakidou M, Ching CL. Systemic lupus erythematosus. Ann Intern Med, 2020, 172(11): ITC81-ITC96.
24. Kong F, Yan Z, Lan N, et al. Construction and validation of gastric cancer diagnosis model based on machine learning. Explor Med, 2022, 3: 300-313.
25. Li YR, Meng K, Yang G, et al. Diagnostic genes and immune infiltration analysis of colorectal cancer determined by LASSO and SVM machine learning methods: a bioinformatics analysis. J Gastrointest Oncol, 2022, 13(3): 1188-1203.
26. Liu J, Liu L, Antwi PA, et al. Identification and validation of the diagnostic characteristic genes of ovarian cancer by bioinformatics and machine learning. Front Genet, 2022, 13: 858466.
27. Lai YL, Liu CH, Wang SC, et al. Identification of a steroid hormone-associated gene signature predicting the prognosis of prostate cancer through an integrative bioinformatics analysis. Cancers (Basel), 2022, 14(6): 1565.
28. Jiang Z, Shao M, Dai X, et al. Identification of diagnostic biomarkers in systemic lupus erythematosus based on bioinformatics analysis and machine learning. Front Genet, 2022, 13: 865559.
29. Zhou Y, Shi W, Zhao D, et al. Identification of immune-associated genes in diagnosing aortic valve calcification with metabolic syndrome by integrated bioinformatics analysis and machine learning. Front Immunol, 2022, 13: 937886.
30. Xiong T, Han S, Pu L, et al. Bioinformatics and machine learning methods to identify fn1 as a novel biomarker of aortic valve calcification. Front Cardiovasc Med, 2022, 9: 832591.
31. Li C, Tian C, Zeng Y, et al. Machine learning and bioinformatics analysis revealed classification and potential treatment strategy in stage 3-4 NSCLC patients. BMC Med Genomics, 2022, 15(1): 33.
32. Kalafi EY, Nor NAM, Taib NA, et al. Machine learning and deep learning approaches in breast cancer survival prediction using clinical data. Folia Biol (Praha), 2019, 65(5/6): 212-220.
33. Kwakkenbos MJ, Kop EN, Stacey M, et al. The EGF-TM7 family: a postgenomic view. Immunogenetics, 2004, 55(10): 655-666.
34. Kramer EB, Farabaugh PJ. The frequency of translational misreading errors in E. coli is largely determined by tRNA competition. RNA, 2007, 13(1): 87-96.
35. Bernatsky S, Ramsey-Goldman R, Joseph L, et al. Lymphoma risk in systemic lupus: effects of disease activity versus treatment. Ann Rheum Dis, 2014, 73(1): 138-142.

Previous Article
Visual analysis of the current state and trends of global research in continuous renal replacement therapy

West China Medical Journal

Identification of potential biomarkers of lupus nephritis based on machine learning and weighted gene co-expression network analysis

Abstract Full text Figures/Tables Video References Cited by

Previous Article

Format

Content