Abstract
Rheumatoid arthritis (RA) is a long-term autoimmune disease that severely affects physical function and quality of life. Patients diagnosed with RA are usually treated with anti-tumor necrosis factor (anti-TNF), which in certain cases do not contribute to reach remission. Consequently, there is a need to develop models that can predict therapy response, thus preventing disability, maintain life quality, and decrease cost treatment. Transcriptomic data are emerging as valuable information to predict RA pathogenesis and therapy outcome. The aim of this study is to find gene signatures in RA patients that help to predict the response to anti-TNF treatment. RNA-sequencing of whole blood samples dataset from RA patients at baseline and following 3 months of therapy were used. A methodology based on sparse logistic regression was employed to obtain predictive models which allowed to find 20 genes consensually associated with therapy response, some known to be related with RA. Gene expression levels at 3 months of therapy showed no added value in the prediction of response to therapy when compared with the baseline. The analysis using Bayesian network learning unveiled significant protein-protein interactions in both good and non-responders, further confirmed using the STRING database. Structured sparse regression coupled with Bayesian learning can support the identification of disease biomarkers and generate hypotheses to be further analysed by clinicians.
Partially funded by FCT (PTDC/CCI-CIF/29877/2017, UIDB/50021/2020, UIDB/50008/2020).
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Neumann, E., Frommer, K., Diller, M., Müller-Ladner, U.: Zeitschrift für Rheumatologie 77(9), 769–775 (2018). https://doi.org/10.1007/s00393-018-0500-z
Radner, H., Aletaha, D.: Anti-TNF in rheumatoid arthritis: an overview. Wien. Med. Wochenschr. 165(1), 3–9 (2015). https://doi.org/10.1007/s10354-015-0344-y
Smolen, J.S., Landewé, R., Breedveld, F.C., et al.: EULAR recommendations for the management of rheumatoid arthritis with synthetic and biological disease-modifying antirheumatic drugs. Ann. Rheum. Dis. 69(6), 964–975 (2010). https://doi.org/10.1136/ard.2009.126532
Wijbrandts, C.A., Tak, P.P.: Prediction of response to targeted treatment in rheumatoid arthritis. Mayo Clin. Proc. 92(7), 1129–1143 (2017). https://doi.org/10.1016/j.mayocp.2017.05.009
Cuppen, B.V., et al.: Personalized biological treatment for rheumatoid arthritis: a systematic review with a focus on clinical applicability. Rheumatology 55(5), 826–839 (2016). https://doi.org/10.1093/rheumatology/kev421
Oswald, M., et al.: Modular analysis of peripheral blood gene expression in rheumatoid arthritis captures reproducible gene expression changes in tumor necrosis factor responders. Arthritis Rheumatol. 67(2), 344–351 (2015). https://doi.org/10.1002/art.38947
Farutin, V., et al.: Molecular profiling of rheumatoid arthritis patients reveals an association between innate and adaptive cell populations and response to anti-tumor necrosis factor. Arthritis Res Ther. 21(1), 216 (2019). https://doi.org/10.1186/s13075-019-1999-3
Barracchia, E.P., Pio, G., D’Elia, D., Ceci, M.: Prediction of new associations between ncRNAs and diseases exploiting multi-type hierarchical clustering. BMC Bioinf. 21(1), 1–24 (2020). https://doi.org/10.1186/s12859-020-3392-2
Pio, G., Ceci, M., Prisciandaro, F., Malerba, D.: Exploiting causality in gene network reconstruction based on graph embedding. Mach. Learn. 109(6), 1231–1279 (2019). https://doi.org/10.1007/s10994-019-05861-8
Pappas, D.A., Kremer, J.M., Reed, G., Greenberg, J.D., Curtis, J.R.: Design characteristics of the corrona certain study: a comparative effectiveness study of biologic agents for rheumatoid arthritis patients. BMC Musculoskelet Disord. 15(1), 113 (2014). https://doi.org/10.1186/1471-2474-15-113
Fransen, J., van Riel, P.L.: The Disease activity score and the eular response criteria. Clin. Exp. Rheumatol. 23(5 Suppl 39), S93–S99 (2005)
Pua, Y.-H., et al.: Machine learning methods are comparable to logistic regression techniques in predicting severe walking limitation following total knee arthroplasty. Knee Surg. Sports Traumatol. Arthrosc. 28(10), 3207–3216 (2019). https://doi.org/10.1007/s00167-019-05822-7
Faisal, M., Scally, A., Howes, R., Beatson, K., Richardson, D., Mohammed, M.A.: A comparison of logistic regression models with alternative machine learning methods to predict the risk of in-hospital mortality in emergency medical admissions via external validation. Health Inf. J. 26(1), 34–44 (2020). https://doi.org/10.1177/1460458218813600
Kuhle, S., et al.: Comparison of logistic regression with machine learning methods for the prediction of fetal growth abnormalities: a retrospective cohort study. BMC Pregnancy and Childbirth 18(1), 333 (2018). https://doi.org/10.1186/s12884-018-1971-2
Tibshirani, R.: Regression shrinkage and selection via the Lasso. J. Royal Stat. Soc.: Series B 58(1), 267–288 (1996)
Hoerl, A.E., Kennard, R.W.: Ridge regression: biased estimation for nonorthogonal problems. Technometrics 12(1), 55–67 (1970)
Zou, H., Hastie, T.: Regularization and variable selection via the elastic net. J. Royal Stat. Soc. Series B 67(2), 301–320 (2005)
Aragam, B., Gu, J., Zhou, Q.: Learning large-scale bayesian networks with the sparsebn package. J. Stat. Software 91(11), 01–38 (2019). https://doi.org/10.18637/jss.v091.i11
Friedman, J., Hastie, T., Tibshirani, R.: Regularization paths for generalized linear models via coordinate descent. J. Stat. Software 33(1), 1–22 (2010)
Gao, S., Zhu, H., Zuo, X., Luo, H.: Cathepsin g and its role in inflammation and autoimmune diseases. Arch Rheumatol. 33(4), 498–504 (2018). https://doi.org/10.5606/ArchRheumatol.2018.6595
Karouzakis, E., et al.: Molecular characterization of human lymph node stromal cells during the earliest phases of rheumatoid arthritis. Front. Immunol. 10, 1863 (2016). https://doi.org/10.3389/fimmu.2019.01863
Fernandes, R.M., da Silva, N.P., Sato, E.I.: Increased myeloperoxidase plasma levels in rheumatoid arthritis. Rheumatol. Int. 32(6), 1605–1609 (2012). https://doi.org/10.1007/s00296-011-1810-5
Fukuda, K., Miura, Y., Maeda, T., Hayashi, S., Kuroda, R.: Expression profiling of genes in rheumatoid fibroblast-like synoviocytes regulated by tumor necrosis factor-like ligand 1A using cDNA microarray analysis. Biomed. Rep. 1(1), 1–5 (2019). https://doi.org/10.3892/br.2019.1216
Szklarczyk, D., et al.: STRING v10: protein-protein interaction networks, integrated over the tree of life. Nucleic Acids Res. 43, 447–452 (2015). https://doi.org/10.1093/nar/gku1003
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Constantino, C., Carvalho, A.M., Vinga, S. (2020). Sparse Consensus Classification for Discovering Novel Biomarkers in Rheumatoid Arthritis. In: Nicosia, G., et al. Machine Learning, Optimization, and Data Science. LOD 2020. Lecture Notes in Computer Science(), vol 12565. Springer, Cham. https://doi.org/10.1007/978-3-030-64583-0_13
Download citation
DOI: https://doi.org/10.1007/978-3-030-64583-0_13
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-64582-3
Online ISBN: 978-3-030-64583-0
eBook Packages: Computer ScienceComputer Science (R0)