journal article Open Access Jan 06, 2019

Efficacy of Integrating a Novel 16-Gene Biomarker Panel and Intelligence Classifiers for Differential Diagnosis of Rheumatoid Arthritis and Osteoarthritis

View at Publisher Save 10.3390/jcm8010050
Abstract
Introducing novel biomarkers for accurately detecting and differentiating rheumatoid arthritis (RA) and osteoarthritis (OA) using clinical samples is essential. In the current study, we searched for a novel data-driven gene signature of synovial tissues to differentiate RA from OA patients. Fifty-three RA, 41 OA, and 25 normal microarray-based transcriptome samples were utilized. The area under the curve random forests (RF) variable importance measurement was applied to seek the most influential differential genes between RA and OA. Five algorithms including RF, k-nearest neighbors (kNN), support vector machines (SVM), naïve-Bayes, and a tree-based method were employed for the classification. We found a 16-gene signature that could effectively differentiate RA from OA, including TMOD1, POP7, SGCA, KLRD1, ALOX5, RAB22A, ANK3, PTPN3, GZMK, CLU, GZMB, FBXL7, TNFRSF4, IL32, MXRA7, and CD8A. The externally validated accuracy of the RF model was 0.96 (sensitivity = 1.00, specificity = 0.90). Likewise, the accuracy of kNN, SVM, naïve-Bayes, and decision tree was 0.96, 0.96, 0.96, and 0.91, respectively. Functional meta-analysis exhibited the differential pathological processes of RA and OA; suggested promising targets for further mechanistic and therapeutic studies. In conclusion, the proposed genetic signature combined with sophisticated classification methods may improve the diagnosis and management of RA patients.
Topics

No keywords indexed for this article. Browse by subject →

References
59
[1]
Neogi "The epidemiology and impact of pain in osteoarthritis" Osteoarthr. Cartil. (2013) 10.1016/j.joca.2013.03.018
[2]
Woolf "Burden of major musculoskeletal conditions" Bull. World Health Organ. (2003)
[3]
Lee "Abnormal networks of immune response-related molecules in bone marrow cells from patients with rheumatoid arthritis as revealed by DNA microarray analysis" Arthritis Res. Ther. (2011) 10.1186/ar3364
[4]
Barr "Osteoarthritis" Nat. Rev. Dis. Prim. (2016) 10.1038/nrdp.2016.72
[5]
Scott "Rheumatoid arthritis" Lancet (2010) 10.1016/s0140-6736(10)60826-4
[6]
Palmer "Osteoarthritis" Lancet (2015) 10.1016/s0140-6736(14)60802-3
[7]
Sokolove "Role of inflammation in the pathogenesis of osteoarthritis: Latest findings and interpretations" Ther. Adv. Musculoskelet. Dis. (2013) 10.1177/1759720x12467868
[8]
Withrow "Extracellular vesicles in the pathogenesis of rheumatoid arthritis and osteoarthritis" Arthritis Res. Ther. (2016) 10.1186/s13075-016-1178-8
[9]
Woetzel "Identification of rheumatoid arthritis and osteoarthritis patients by transcriptome-based rule set generation" Arthritis Res. Ther. (2014) 10.1186/ar4526
[10]
Finckh "Early inflammatory arthritis versus rheumatoid arthritis" Curr. Opin. Rheumatol. (2009) 10.1097/bor.0b013e3283235ac4
[11]
Pincus "Laboratory tests to assess patients with rheumatoid arthritis: Advantages and limitations" Rheum. Dis. Clin. N. Am. (2009) 10.1016/j.rdc.2009.10.007
[12]
Bresnihan "Are synovial biopsies of diagnostic value?" Arthritis Res. Ther. (2003) 10.1186/ar1003
[13]
Orr "Synovial tissue research: A state-of-the-art review" Nat. Rev. Rheumatol. (2017) 10.1038/nrrheum.2017.115
[14]
Benito "Synovial tissue inflammation in early and late osteoarthritis" Ann. Rheum. Dis. (2005) 10.1136/ard.2004.025270
[15]
Baeten "Immunopathology of synovitis: From histology to molecular pathways" Rheumatology (2016) 10.1093/rheumatology/kev330
[16]
Baeten "Diagnostic classification of spondylarthropathy and rheumatoid arthritis by synovial histopathology: A prospective study in 154 consecutive patients" Arthritis Rheum. (2004) 10.1002/art.20476
[17]
Najm "Success Rate and Utility of Ultrasound-guided Synovial Biopsies in Clinical Practice" J. Rheumatol. (2016) 10.3899/jrheum.151441
[18]
Du "lumi: A pipeline for processing Illumina microarray" Bioinformatics (2008) 10.1093/bioinformatics/btn224
[19]
Gautier "Affy—Analysis of Affymetrix GeneChip data at the probe level" Bioinformatics (2004) 10.1093/bioinformatics/btg405
[20]
Xia "NetworkAnalyst for statistical, visual and network-based meta-analysis of gene expression data" Nat. Protoc. (2015) 10.1038/nprot.2015.052
[21]
Strobl, C., Boulesteix, A.L., Kneib, T., Augustin, T., and Zeileis, A. (2008). Conditional variable importance for random forests. BMC Bioinform., 9. 10.1186/1471-2105-9-307
[22]
Lever "Points of Significance: Principal component analysis" Nat. Meth. (2017) 10.1038/nmeth.4346
[23]
Xia "MetaboAnalyst 3.0—Making metabolomics more meaningful" Nucleic Acids Res. (2015) 10.1093/nar/gkv380
[24]
Kassambara, A. (2019, January 06). ggpubr: ‘ggplot2’ Based Publication Ready Plots. Available online: https://CRAN.R-project.org/package=ggpubr.
[25]
Josse "FactoMineR: An R Package for Multivariate Analysis" J. Stat. Softw. (2008)
[26]
Kassambara, A., and Mundt, F. (2019, January 06). Factoextra: Extract and Visualize the Results of Multivariate Data Analyses. Available online: https://rdrr.io/cran/factoextra/.
[27]
Building Predictive Models in R Using the caret Package

Max Kuhn

Journal of Statistical Software 2008 10.18637/jss.v028.i05
[28]
Random Forests

Leo Breiman

Machine Learning 2001 10.1023/a:1010933404324
[29]
Bergstra "Random search for hyper-parameter optimization" J. Mach. Learn. Res. (2012)
[30]
pROC: an open-source package for R and S+ to analyze and compare ROC curves

Xavier Robin, Natacha Turck, Alexandre Hainard et al.

BMC Bioinformatics 10.1186/1471-2105-12-77
[31]
Glaab, E., Garibaldi, J.M., and Krasnogor, N. (2009). ArrayMining: A modular web-application for microarray analysis combining ensemble and consensus methods with cross-study normalization. BMC Bioinform., 10. 10.1186/1471-2105-10-358
[32]
Pedersen, T.L., and Benesty, M. (2017). LIME: Local Interpretable Model-Agnostic Explanations, Cornell University.
[33]
The STRING database in 2017: quality-controlled protein–protein association networks, made broadly accessible

Damian Szklarczyk, John H Morris, Helen Cook et al.

Nucleic Acids Research 2017 10.1093/nar/gkw937
[34]
R Core Team (2017). R: A Language and Environment for Statistical Computing, R Foundation for Statistical Computing.
[35]
Diaz-Uriarte, R., and Alvarez de Andres, S. (2006). Gene selection and classification of microarray data using random forest. BMC Bioinform., 7. 10.1186/1471-2105-7-3
[36]
Janitza, S., Strobl, C., and Boulesteix, A.-L. (2013). An AUC-based permutation variable importance measure for random forests. BMC Bioinform., 14. 10.1186/1471-2105-14-119
[37]
Walsh, A.M., Wechalekar, M.D., Guo, Y., Yin, X., Weedon, H., Proudman, S.M., Smith, M.D., and Nagpal, S. (2017). Triple DMARD treatment in early rheumatoid arthritis modulates synovial T cell activation and plasmablast/plasma cell differentiation pathways. PLoS ONE, 12. 10.1371/journal.pone.0183928
[38]
Toes "ACPA (anti-citrullinated protein antibodies) and rheumatoid arthritis" Acta Reumatol. Port. (2011)
[39]
Yang "Serum connective tissue growth factor is a highly discriminatory biomarker for the diagnosis of rheumatoid arthritis" Arthritis Res. Ther. (2017) 10.1186/s13075-017-1463-1
[40]
Wu "Early detection of rheumatoid arthritis in rats and humans with 99mTc-3PRGD2 scintigraphy: Imaging synovial neoangiogenesis" Oncotarget (2017) 10.18632/oncotarget.13953
[41]
Kroot "Diagnostic value of blind synovial biopsy in clinical practice" Rheumatology (2005) 10.1093/rheumatology/kei117
[42]
Coiffier "Ultrasound-guided synovial biopsy improves diagnosis of septic arthritis in acute arthritis without enough analyzable synovial fluid: A retrospective analysis of 176 arthritis from a French rheumatology department" Clin. Rheumatol. (2018) 10.1007/s10067-018-4160-9
[43]
Burska "Gene expression analysis in RA: Towards personalized medicine" Pharmacogenomics J. (2014) 10.1038/tpj.2013.48
[44]
Tseng "Comprehensive literature review and statistical considerations for microarray meta-analysis" Nucleic Acids Res. (2012) 10.1093/nar/gkr1265
[45]
Yu "Protein Microarrays for Personalized Medicine" Clin. Chem. (2010) 10.1373/clinchem.2009.137158
[46]
You "Identification of key regulators for the migration and invasion of rheumatoid synoviocytes through a systems approach" Proc. Natl. Acad. Sci. USA (2014) 10.1073/pnas.1311239111
[47]
Pratt "A CD4 T cell gene signature for early rheumatoid arthritis implicates interleukin 6-mediated STAT3 signalling, particularly in anti-citrullinated peptide antibody-negative disease" Ann. Rheum. Dis. (2012) 10.1136/annrheumdis-2011-200968
[48]
Warnat, P., Eils, R., and Brors, B. (2005). Cross-platform analysis of cancer microarray data improves gene expression based classification of phenotypes. BMC Bioinform., 6. 10.1186/1471-2105-6-265
[49]
Shabalin "Merging two gene-expression studies via cross-platform normalization" Bioinformatics (2008) 10.1093/bioinformatics/btn083
[50]
Lazar "Batch effect removal methods for microarray gene expression data integration: A survey" Brief. Bioinform. (2013) 10.1093/bib/bbs037

Showing 50 of 59 references

Cited By
40
Metrics
40
Citations
59
References
Details
Published
Jan 06, 2019
Vol/Issue
8(1)
Pages
50
License
View
Funding
National Research Foundation of Korea Award: NRF-2012M3A9C4048796/2017R1E1A2A02022658/2018R1A5A2024425
Cite This Article
Nguyen Phuoc Long, Seongoh Park, Nguyen Hoang Anh, et al. (2019). Efficacy of Integrating a Novel 16-Gene Biomarker Panel and Intelligence Classifiers for Differential Diagnosis of Rheumatoid Arthritis and Osteoarthritis. Journal of Clinical Medicine, 8(1), 50. https://doi.org/10.3390/jcm8010050