nach oben

Clinical Rheumatology

Erschienen in:

12.11.2021 | Original Article

Machine learning to identify immune-related biomarkers of rheumatoid arthritis based on WGCNA network

verfasst von: Yulan Chen, Ruobing Liao, Yuxin Yao, Qiao Wang, Lingyu Fu

Erschienen in: Clinical Rheumatology | Ausgabe 4/2022

Einloggen, um Zugang zu erhalten

Abstract

Objectives

This study was designed to identify the potential diagnostic biomarkers of rheumatoid arthritis (RA) and to explore the potential pathological relevance of immune cell infiltration in this disease.

Methods

Three previously published datasets containing gene expression data from 35 RA patients and 29 controls (GSE55235, GSE55457, and GSE12021) were downloaded from the GEO database, after which a weighted correlation network analysis (WGCNA) approach was utilized to clarify differentially abundant genes. Candidate biomarkers of RA were then identified via the use of a LASSO regression model and support vector machine recursive feature elimination (SVM-RFE) analyses. Data were validated based upon the area under the receiver operating characteristic curve (AUC) values, with hub genes being identified as those with an AUC > 85% and a P value < 0.05. Lastly, the CIBERSORT algorithm was used to assess immune cell infiltration of RA tissues, and correlations between immune cell infiltration and disease-related diagnostic biomarkers were assessed.

Results

The green–yellow module containing 87 genes was found to be highly correlated with RA positivity. FADD, CXCL2, and CXCL8 were identified as potential RA diagnostic biomarkers (AUC > 0.85), and these results were validated using the GSE77298 dataset. Immune cell infiltration analyses revealed the expression of hub genes to be correlated with mast cells, monocytes, activated NK cells, CD8 T cells, resting dendritic cells, and plasma cells.

Conclusion

These data indicate that FADD, CXCL2, and CXCL8 are valuable diagnostic biomarkers of RA, offering new insight that can guide future studies of RA incidence and progression.

Key Points

• Using the WGCNA approach and machine learning analyses to identify the hub genes in 64 samples.

• Identifying the hub genes FADD, CXCL2, and CXCL8 as RA diagnostic biomarkers and confirming it in validation data.

• Assessing the immune infiltration of RA tissues and correlations between hub genes and immune infiltration by CIBERSORT algorithm.

Nur mit Berechtigung zugänglich

Sparks JA (2019) Rheumatoid arthritis. Ann Internal Med 170(1):Itc1-itc16. https://doi.org/10.7326/aitc201901010CrossRef

van der Woude D, van der Helm-van Mil AHM (2018) Update on the epidemiology, risk factors, and disease outcomes of rheumatoid arthritis. Best Pract Res Clin Rheumatol 32(2):174–187. https://doi.org/10.1016/j.berh.2018.10.005CrossRefPubMed

Smolen JS, Aletaha D, Barton A, Burmester GR, Emery P, Firestein GS, Kavanaugh A, McInnes IB, Solomon DH, Strand V, Yamamoto K (2018) Rheumatoid arthritis. Nature reviews. Dis Primers 418001. https://doi.org/10.1038/nrdp.2018.1

Courvoisier DS, Chatzidionysiou K, Mongin D, Lauper K, Mariette X, Morel J, Gottenberg JE, Bergstra SA, Suarez MP, Codreanu C, Kvien TK, Santos MJ, Pavelka K, Hetland ML, Askling J, Turesson C, Kubo S, Tanaka Y, Iannone F, Choquette D, Nordström DC, Rotar Z, Lukina G, Gabay C, Van Vollenhoven R, Finckh A (2021) The impact of seropositivity on the effectiveness of biologic anti-rheumatic agents: results from a collaboration of 16 registries. Rheumatology (Oxford) 60(2):820–828. https://doi.org/10.1093/rheumatology/keaa393CrossRef

Laborde CM, Castro-Santos P, Díaz-Peña R (2020) Contribution of multiplex immunoassays to rheumatoid arthritis management: from biomarker discovery to personalized medicine. J Personal Med 10(4). https://doi.org/10.3390/jpm10040202

Mo XB, Zhang YH, Lei SF (2021) Integrative analysis identifies potential causal methylation-mRNA regulation chains for rheumatoid arthritis. Mol Immunol 131:89–96. https://doi.org/10.1016/j.molimm.2020.12.021CrossRefPubMed

Cai W, Li H, Zhang Y, Han G (2020) Identification of key biomarkers and immune infiltration in the synovial tissue of osteoarthritis by bioinformatics analysis. PeerJ 8e8390. https://doi.org/10.7717/peerj.8390

Huang Y, Zheng S, Wang R, Tang C, Zhu J, Li J (2019) CCL5 and related genes might be the potential diagnostic biomarkers for the therapeutic strategies of rheumatoid arthritis. Clin Rheumatol 38(9):2629–2635. https://doi.org/10.1007/s10067-019-04533-1CrossRefPubMed

Tibshirani R (1996) Regression shrinkage and selection via the LASSO. J Royal Stat Soc B 58267-288. https://doi.org/10.2307/2346178

10.

Suzuki T, Kano S, Suzuki M, Yasukawa S, Mizumachi T, Tsushima N, Hatanaka KC, Hatanaka Y, Matsuno Y, Homma A (2020) Enhanced angiogenesis in salivary duct carcinoma ex-pleomorphic adenoma. Front Oncol 10603717. https://doi.org/10.3389/fonc.2020.603717

11.

Gutiérrez-Gómez L, Vohryzek J, Chiêm B, Baumann PS, Conus P, Cuenod KD, Hagmann P, Delvenne JC (2020) Stable biomarker identification for predicting schizophrenia in the human connectome. NeuroImage Clin 27102316. https://doi.org/10.1016/j.nicl.2020.102316

12.

Yap HY, Tee SZ, Wong MM, Chow SK, Peh SC, Teow SY (2018) Pathogenic role of immune cells in rheumatoid arthritis: implications in clinical treatment and biomarker development. Cells 7(10). https://doi.org/10.3390/cells7100161

13.

Leek JT, Johnson WE, Parker HS, Jaffe AE, Storey JD (2012) The sva package for removing batch effects and other unwanted variation in high-throughput experiments. Bioinformatics (Oxford, England) 28(6):882–883. https://doi.org/10.1093/bioinformatics/bts034CrossRef

14.

Langfelder P, Horvath S (2008) WGCNA: an R package for weighted correlation network analysis. BMC Bioinformatics 9559. https://doi.org/10.1186/1471-2105-9-559

15.

Yu G, Wang LG, Han Y, He QY (2012) clusterProfiler: an R package for comparing biological themes among gene clusters. OMICS 16(5):284–287. https://doi.org/10.1089/omi.2011.0118CrossRefPubMedPubMedCentral

16.

Friedman J, Hastie T, Tibshirani R (2010) Regularization paths for generalized linear models via coordinate descent. J Stat Softw 33(1):1–22CrossRefPubMedPubMedCentral

17.

Huang ML, Hung YH, Lee WM, Li RK, Jiang BR (2014) SVM-RFE based feature selection and Taguchi parameters optimization for multiclass SVM classifier. Sci World J 2014795624. https://doi.org/10.1155/2014/795624

18.

Newman AM, Liu CL, Green MR, Gentles AJ, Feng W, Xu Y, Hoang CD, Diehn M, Alizadeh AA (2015) Robust enumeration of cell subsets from tissue expression profiles. Nat Methods 12(5):453–457. https://doi.org/10.1038/nmeth.3337CrossRefPubMedPubMedCentral

19.

Darrah E, Andrade F (2018) Rheumatoid arthritis and citrullination. Curr Opin Rheumatol 30(1):72–78. https://doi.org/10.1097/bor.0000000000000452CrossRefPubMedPubMedCentral

20.

Song Y, Jo S, Chung JY, Oh Y, Yoon S, Lee YL, Kim SS, Yang JH, Jang K, Yang CS, Kim TH, Kim YH (2021) RNA interference-mediated suppression of TNF-α converting enzyme as an alternative anti-TNF-α therapy for rheumatoid arthritis. J Controlled Release 3301300-1312. https://doi.org/10.1016/j.jconrel.2020.11.041

21.

Kenna TJ, Brown MA (2013) The role of IL-17-secreting mast cells in inflammatory joint disease. Nat Rev Rheumatol 9(6):375–379. https://doi.org/10.1038/nrrheum.2012.205CrossRefPubMed

22.

Zhang Q, Liao Y, Liu Z, Dai Y, Li Y, Li Y, Tang Y (2021) Interleukin-17 and ischaemic stroke. Immunology 162(2):179–193. https://doi.org/10.1111/imm.13265CrossRefPubMed

23.

Ma X, Xu S (2013) TNF inhibitor therapy for rheumatoid arthritis. Biomedical reports 1(2):177–184. https://doi.org/10.3892/br.2012.42CrossRefPubMed

24.

Zamri F, de Vries TJ (2020) Use of TNF inhibitors in rheumatoid arthritis and implications for the periodontal status: for the benefit of both? Front Immunol 11591365. https://doi.org/10.3389/fimmu.2020.591365

25.

Blanco FJ, Möricke R, Dokoupilova E, Codding C, Neal J, Andersson M, Rohrer S, Richards H (2017) Secukinumab in active rheumatoid arthritis: a phase III randomized, double-blind, active comparator- and placebo-controlled study. Arthritis Rheumatol (Hoboken, N.J.) 69(6):1144–1153. https://doi.org/10.1002/art.40070CrossRef

26.

Ma C, Lv Q, Teng S, Yu Y, Niu K, Yi C (2017) Identifying key genes in rheumatoid arthritis by weighted gene co-expression network analysis. Int J Rheum Dis 20(8):971–979. https://doi.org/10.1111/1756-185x.13063CrossRefPubMed

27.

Ren C, Li M, Du W, Lü J, Zheng Y, Xu H, Quan R (2020) Comprehensive bioinformatics analysis reveals hub genes and inflammation state of rheumatoid arthritis. BioMed Res Int 20206943103. https://doi.org/10.1155/2020/6943103

28.

Gómez-Angelats M, Cidlowski JA (2003) Molecular evidence for the nuclear localization of FADD. Cell Death Differ 10(7):791–797. https://doi.org/10.1038/sj.cdd.4401237CrossRefPubMed

29.

Tourneur L, Chiocchia G (2010) FADD: a regulator of life and death. Trends Immunol 31(7):260–269. https://doi.org/10.1016/j.it.2010.05.005CrossRefPubMed

30.

Okamoto K, Kobayashi T, Kobata T, Hasunuma T, Kato T, Sumida T, Nishioka K (2000) Fas-associated death domain protein is a Fas-mediated apoptosis modulator in synoviocytes. Rheumatology (Oxford) 39(5):471–480. https://doi.org/10.1093/rheumatology/39.5.471CrossRef

31.

Chinnaiyan AM, O’Rourke K, Tewari M, Dixit VM (1995) FADD, a novel death domain-containing protein, interacts with the death domain of Fas and initiates apoptosis. Cell 81(4):505–512. https://doi.org/10.1016/0092-8674(95)90071-3CrossRefPubMed

32.

Kobayashi T, Okamoto K, Kobata T, Hasunuma T, Kato T, Hamada H, Nishioka K (2000) Differential regulation of Fas-mediated apoptosis of rheumatoid synoviocytes by tumor necrosis factor alpha and basic fibroblast growth factor is associated with the expression of apoptosis-related molecules. Arthritis Rheum 43(5):1106–1114. https://doi.org/10.1002/1529-0131(200005)43:5%3c1106::AID-ANR21%3e3.0.CO;2-FCrossRefPubMed

33.

Zhang HW, Wang Q, Mei HX, Zheng SX, Ali AM, Wu QX, Ye Y, Xu HR, Xiang SY, Jin SW (2019) RvD1 ameliorates LPS-induced acute lung injury via the suppression of neutrophil infiltration by reducing CXCL2 expression and release from resident alveolar macrophages. Int Immunopharmacol 76105877. https://doi.org/10.1016/j.intimp.2019.105877

34.

Gang X, Sun Y, Li F, Yu T, Jiang Z, Zhu X, Jiang Q, Wang Y (2017) Identification of key genes associated with rheumatoid arthritis with bioinformatics approach. Medicine 96(31):e7673. https://doi.org/10.1097/md.0000000000007673CrossRefPubMedPubMedCentral

35.

Jacobs JP, Ortiz-Lopez A, Campbell JJ, Gerard CJ, Mathis D, Benoist C (2010) Deficiency of CXCR2, but not other chemokine receptors, attenuates autoantibody-mediated arthritis in a murine model. Arthritis Rheum 62(7):1921–1932. https://doi.org/10.1002/art.27470CrossRefPubMedPubMedCentral

36.

Wiegand P, Lupu L, Hüttmann N, Wack J, Rawer S, Przybylski M, Schmitz K (2020) Epitope identification and affinity determination of an inhibiting human antibody to interleukin IL8 (CXCL8) by SPR- biosensor-mass spectrometry combination. J Am Soc Mass Spectrom 31(1):109–116. https://doi.org/10.1021/jasms.9b00050CrossRefPubMed

37.

Kienhorst LB, van Lochem E, Kievit W, Dalbeth N, Merriman ME, Phipps-Green A, Loof A, van Heerde W, Vermeulen S, Stamp LK, van Koolwijk E, de Graaf J, Holzinger D, Roth J, Janssens HJ, Merriman TR, Broen JC, Janssen M, Radstake TR (2015) Gout is a chronic inflammatory disease in which high levels of interleukin-8 (CXCL8), myeloid-related protein 8/myeloid-related protein 14 complex, and an altered proteome are associated with diabetes mellitus and cardiovascular disease. Arthritis Rheumatol (Hoboken, N.J.) 67(12):3303–3313. https://doi.org/10.1002/art.39318CrossRef

38.

GowhariShabgah A, Shariati-Sarabi Z, Tavakkol-Afshari J, Ghoryani M, Mohammadi M (2019) Possible anti-inflammatory effects of mesenchymal stem cells transplantation via changes in CXCL8 levels in patients with refractory rheumatoid arthritis. Int J Mol Cell Med 8(3):191–199. https://doi.org/10.22088/IJMCM.BUMS.8.3.191CrossRef

39.

Krishnamurthy A, Joshua V, Haj Hensvold A, Jin T, Sun M, Vivar N, Ytterberg AJ, Engström M, Fernandes-Cerqueira C, Amara K, Magnusson M, Wigerblad G, Kato J, Jiménez-Andrade JM, Tyson K, Rapecki S, Lundberg K, Catrina SB, Jakobsson PJ, Svensson C, Malmström V, Klareskog L, Wähämaa H, Catrina AI (2016) Identification of a novel chemokine-dependent molecular mechanism underlying rheumatoid arthritis-associated autoantibody-mediated bone loss. Ann Rheum Dis 75(4):721–729. https://doi.org/10.1136/annrheumdis-2015-208093CrossRefPubMed

40.

McInnes IB, Schett G (2011) The pathogenesis of rheumatoid arthritis. N Engl J Med 365(23):2205–2219. https://doi.org/10.1056/NEJMra1004965CrossRefPubMed

41.

Schubert N, Dudeck J, Liu P, Karutz A, Speier S, Maurer M, Tuckermann J, Dudeck A (2015) Mast cell promotion of T cell-driven antigen-induced arthritis despite being dispensable for antibody-induced arthritis in which T cells are bypassed. Arthritis Rheumatol (Hoboken, N.J.) 67(4):903–913. https://doi.org/10.1002/art.38996CrossRef

42.

Schittenhelm L, Robertson J, Pratt AG, Hilkens CM, Morrison VL (2021) Dendritic cell integrin expression patterns regulate inflammation in the rheumatoid arthritis joint. Rheumatology (Oxford) 60(3):1533–1542. https://doi.org/10.1093/rheumatology/keaa686CrossRef

43.

Yamin R, Berhani O, Peleg H, Aamar S, Stein N, Gamliel M, Hindi I, Scheiman-Elazary A, Gur C (2019) High percentages and activity of synovial fluid NK cells present in patients with advanced stage active rheumatoid arthritis. Sci Rep 9(1):1351. https://doi.org/10.1038/s41598-018-37448-zCrossRefPubMedPubMedCentral

44.

Söderström K, Stein E, Colmenero P, Purath U, Müller-Ladner U, de Matos CT, Tarner IH, Robinson WH, Engleman EG (2010) Natural killer cells trigger osteoclastogenesis and bone destruction in arthritis. Proc Natl Acad Sci USA 107(29):13028–13033. https://doi.org/10.1073/pnas.1000546107CrossRefPubMed

Titel: Machine learning to identify immune-related biomarkers of rheumatoid arthritis based on WGCNA network
verfasst von: Yulan Chen
Ruobing Liao
Yuxin Yao
Qiao Wang
Lingyu Fu
Publikationsdatum: 12.11.2021
Verlag: Springer International Publishing
Erschienen in: Clinical Rheumatology / Ausgabe 4/2022
Print ISSN: 0770-3198
Elektronische ISSN: 1434-9949
DOI: https://doi.org/10.1007/s10067-021-05960-9

Leitlinien kompakt für die Innere Medizin

Mit medbee Pocketcards sicher entscheiden.

^{Seit 2022 gehört die medbee GmbH zum Springer Medizin Verlag}

Kostenlos registrieren

Update Innere Medizin

Bestellen Sie unseren Fach-Newsletter und bleiben Sie gut informiert.

Newsletter bestellen

Live-Webinar "Urologie und Sexualmedizin in der Praxis"

Springer Medizin

Machine learning to identify immune-related biomarkers of rheumatoid arthritis based on WGCNA network

Abstract

Objectives

Methods

Results

Conclusion

Leitlinien kompakt für die Innere Medizin

Neu im Fachgebiet Innere Medizin

Erhebliches Risiko für Kehlkopfkrebs bei mäßiger Dysplasie

Nach Herzinfarkt mit Typ-1-Diabetes schlechtere Karten als mit Typ 2?

15% bedauern gewählte Blasenkrebs-Therapie

Costims – das nächste heiße Ding in der Krebstherapie?

Update Innere Medizin

Live-Webinar "Urologie und Sexualmedizin in der Praxis"

Springer Medizin

Abstract

Objectives

Methods

Results

Conclusion

Bitte loggen Sie sich ein, um Zugang zu diesem Inhalt zu erhalten

Weitere Artikel der Ausgabe 4/2022

Comparison of chronic widespread pain prevalence with different criteria in two cohorts of rheumatoid arthritis

Clinical and psychological assessment of patients with rheumatoid arthritis and fibromyalgia: a real-world study

Prevalence of autoantibodies in pediatric patients with idiopathic pulmonary hemosiderosis: a scoping review of the literature in the period 1980–2021

Diminished natural killer T-like cells correlates with aggravated primary Sjögren’s syndrome

Correction to: Illness perception and treatment experience in patients with gout: a descriptive qualitative study

UBA1 gene mutation in giant cell arteritis

Leitlinien kompakt für die Innere Medizin

Neu im Fachgebiet Innere Medizin

Erhebliches Risiko für Kehlkopfkrebs bei mäßiger Dysplasie

Nach Herzinfarkt mit Typ-1-Diabetes schlechtere Karten als mit Typ 2?

15% bedauern gewählte Blasenkrebs-Therapie

Costims – das nächste heiße Ding in der Krebstherapie?

Update Innere Medizin