Blood autoantibody and cytokine profiles predict response to anti-tumor necrosis factor therapy in rheumatoid arthritis

Abstract

Introduction: Anti-TNF therapies have revolutionized the treatment of rheumatoid arthritis (RA), a common systemic autoimmune disease involving destruction of the synovial joints. However, in the practice of rheumatology approximately one-third of patients demonstrate no clinical improvement in response to treatment with anti-TNF therapies, while another third demonstrate a partial response, and one-third an excellent and sustained response. Since no clinical or laboratory tests are available to predict response to anti-TNF therapies, great need exists for predictive biomarkers.

Methods: Here we present a multi-step proteomics approach using arthritis antigen arrays, a multiplex cytokine assay, and conventional ELISA, with the objective to identify a biomarker signature in three ethnically diverse cohorts of RA patients treated with the anti-TNF therapy etanercept.

Results: We identified a 24-biomarker signature that enabled prediction of a positive clinical response to etanercept in all three cohorts (positive predictive values 58 to 72%; negative predictive values 63 to 78%).

Conclusions: We identified a multi-parameter protein biomarker that enables pretreatment classification and prediction of etanercept responders, and tested this biomarker using three independent cohorts of RA patients. Although further validation in prospective and larger cohorts is needed, our observations demonstrate that multiplex characterization of autoantibodies and cytokines provides clinical utility for predicting response to the anti-TNF therapy etanercept in RA patients.

Figure 1

Workflow of experiments and types of analysis. Upper panel: in the discovery steps, synovial antigen microarrays and multiplex cytokine assays were employed to determine candidate molecules that are differentially expressed in pretreatment sera of etanercept responders (≥ ACR50) and nonresponders (< ACR20). Multiple array experiments were performed, each followed by significance analysis of microarrays (SAM) to identify the highest-scoring discriminators. Middle panel: further testing was performed with three independent cohorts using standard ELISAs, followed by prediction of response in three cohorts of etanercept-treated patients using prediction analysis of microarrays (PAM). Bottom panel: for training and testing, PAM was used to identify the best discriminators (training step; which identified a 24-biomarker panel) and then the utility of these discriminators for predicting response to etanercept was determined (testing). ACR, American College of Rheumatology response.

Figure 2

Rheumatoid arthritis antigen microarrays. Rheumatoid arthritis (RA) antigen microarrays were used for autoantibody profiling of sera derived from patients with RA prior to initiation of etanercept therapy. (a), (b) Array results from two representative RA patients. Yellow features are false-colored features utilized for array orientation, while green features represent autoantibody reactivities. Selected autoantibody reactivities are highlighted in colored boxes. (c) Quantification of the highlighted features. ApoE, apolipoprotein E; COMP, cartilage oligomeric matrix protein.

Figure 3

Elevated pretreatment autoantibody profiles in etanercept responders compared with nonresponders in the ABCoN cohort. Significance analysis of microarrays (SAM) and hierarchical clustering were applied to identify and display autoantibody profiles that differentiate etanercept responders from nonresponders; results from one of several representative experiments are presented. SAM was utilized to identify antigens with statistical differences in antibody reactivity between etanercept responders (≥ ACR50) and nonresponders (< ACR20), and the statistically significant hits are listed to the right of the heatmap (false discovery rate q < 4.3%). The SAM-identified variables and individual patients were then hierarchically clustered, and results presented in tree dendrograms that represent the relationships in reactivities between patients as well as between antigens. Red font, citrullinated antigens; black font, native antigens. Patients are listed across the top of the heatmap image, and the ACR response rate for each patient is indicated. Red bar, responder cluster; green bar, nonresponder cluster. Numbers of misclassified samples are shown for each cluster. Array fluorescence units are color coded and indicated in the bar in the right upper corner of the image. ACR, American College of Rheumatology response; CCP, cyclic citrullinated peptide.

Figure 4

Elevated pretreatment blood cytokines are associated with response to etanercept therapy. Logistic regression analysis was applied to cytokine measurements in 93 samples derived from three cohorts of etanercept new-start rheumatoid arthritis patients. Green circles, samples from the Japanese cohort; red circles, samples from the ABCoN cohort; blue circles, samples from the Swedish cohort; grey circles, the best-fit logistic regression curve; x values, actual cytokine concentrations; y values, an artificial noise value was added to achieve better visual separation of the actual cytokine values. P values are shown for each cytokine. The grey bar links the actual responder or nonresponder label of a sample with the logistic regression result of the same sample (probability of being a responder). For better readability, only six cytokines are shown. MCP-1, monocyte chemoattractant protein-1.

Figure 5

Identification of a 24-antibody and cytokine biomarker that differentiates pretreatment etanercept responders from nonresponders. Prediction analysis of microarrays (PAM) was applied to establish a rank list of the variables, by training PAM on all 93 samples. An overlay of error plots derived from PAM analysis of the 93 samples is displayed. First, PAM was trained on the multi-parameter biomarker; blue, training error graph. Second, internal cross-validation of the dataset was performed; red, overall error of the cross-validation. For better readability, error bars are shown for the cross-validation graph only. The number of markers is shown in ascending order from right to left across the top of the panel, and the selected PAM-derived threshold is indicated.

Figure 6

Prediction of responders and nonresponders. Calculations of classification errors for (a) the PAM training/cross-validation step on all cohorts combined, and (c) the PAM prediction steps for the three cohorts individually (top panel, ABCoN cohort; middle panel, Swedish cohort; bottom panel, Japanese cohort). R, responder; NR, nonresponder; NPV, negative predictive value; PPV, positive predictive value. (b) Complete biomarker of 24 discriminators listed according to rank order, with associated scores for nonresponders and responders in the right and far-right columns, respectively. ApoE, apolipoprotein E; COMP, cartilage oligomeric matrix protein; FGF-2, fibroblast growth factor-2; GM-CSF, granulocyte- macrophage colony-stimulating factor; IP-10, IFNγ-inducible protein 10; MCP-1, monocyte chemoattractant protein-1.