Deconvolution of blood microarray data identifies cellular activation patterns in systemic lupus erythematosus

Abstract

Systemic Lupus Erythematosus (SLE) is a systemic autoimmune disease with a complex spectrum of cellular and molecular characteristics including several dramatic changes in the populations of peripheral leukocytes. These changes include general leukopenia, activation of B and T cells, and maturation of granulocytes. The manifestation of SLE in peripheral blood is central to the disease but is incompletely understood. A technique for rigorously characterizing changes in mixed populations of cells, microarray expression deconvolution, has been applied to several areas of biology but not to SLE or to blood. Here we demonstrate that microarray expression deconvolution accurately quantifies the constituents of real blood samples and mixtures of immune-derived cell lines. We characterize a broad spectrum of peripheral leukocyte cell types and states in SLE to uncover novel patterns including: specific activation of NK and T helper lymphocytes, relationships of these patterns to each other, and correlations to clinical variables and measures. The expansion and activation of monocytes, NK cells, and T helper cells in SLE at least partly underlie this disease's prominent interferon signature. These and other patterns of leukocyte dynamics uncovered here correlate with disease severity and treatment, suggest potential new treatments, and extend our understanding of lupus pathology as a complex autoimmune disease involving many arms of the immune system.

Figure 1. Expression deconvolution was characterized using mixtures of cell lines.

(a) Two-dimensional hierarchical clustering of pure cell line samples and the probesets used as bases in deconvolution show strong segregation of cell lines and clear patterns to support deconvolution. (b) Plotting of proportions of cell lines determined from deconvolution vs. proportions of the cell lines actually mixed shows strong congruence (RMS error = 0.028).

Figure 2. Deconvolution performance was confirmed using T cell subsets.

(a) Two-dimensional hierarchical clustering of PBMC and purified T cell samples and the probesets used as bases in deconvolution. (b) Proportions of T cell subsets determined by deconvolution are similar (RMS error = 0.0138) to proportions determined by fluorescence-activated cell sorting.

Figure 3. Expression profiles of exemplar probesets in surveyed cell types show strong differences.

Microarray expression data for selected basis probesets illustrate expression differences between immune cell types that enable expression deconvolution. Selection of probesets was performed manually to highlight the varying specificity of different genes for different cell types. Data plotted is the mean expression signal of at least three biological replicates. Complete data are available in Table S1.

Figure 4. Performance of expression deconvolution on purified leukocytes supports using it on whole blood.

Purification and expression deconvolution of an independent test set of leukocytes from whole blood demonstrates that various cell types are properly deconvolved. Plotted data is the calculated fraction of that cell type in the whole sample produced by deconvolution of each of the five purified cell types. Data points are each from different donors.

Figure 5. Complete leukocyte deconvolution of healthy or SLE whole blood shows significant differences.

(a) Deconvolved relative abundance of different leukocyte cell types and activation states exhibit statistically significant differences between healthy donors and SLE patients in many (noted by “*”; p-values are 8.6e-07, 3.1e-10, 3.5e-04, 1.5e-09, 1,1e-03, 1.6e-15, 2.2e-16, 6.9e-06, 1.1e-08, respectively). Quantile boxes and tails are 10%ile, 25%ile, 50%ile, 75%ile, and 90%ile. (b) Determination in healthy or SLE blood of relative abundance of total lymphocytes, monocytes, or neutrophils by CBC differential compared to determination of relative abundance by deconvolution. Diagonal lines are y = x, shown for reference, highlight the agreement between the two methods.

Figure 6. FACS counting validates key findings from expression deconvolution.

Quantifying levels of resting or activated lymphocytes from a separate validation cohort by purifying and staining with markers of activation validates the two most significant findings from microarray deconvolution of healthy and SLE patients' blood. (a) NK cells purified and stained for the classical NK activation marker CD62 show significant activation in two patients and mild trend towards activation in a third. (b) CD4+ T helper cells purified and stained for the marker of naïve T cells CD62L show significant downregulation, indicating activation and suggesting a transition to a memory phenotype. (c) CD19+ B cells purified and stained for the marker of activated B cells CD80 show mixed results: no change in one patient, mild upregulation in another, and strong upregulation in the third.

Figure 7. Significant relationships exist between activation patterns of different cell populations.

Visual analysis of T or NK cell types' abundance from individual donors of the main cohort reveals further patterns. (a) Plotting of resting vs. activated NK cells shows that activation of NK cells occurs to all NK cells simultaneously. (b) Plotting of resting vs. activated T helper cells shows that likewise activation of T cells occurs to all T cells simultaneously. (c) Plotting of activated NK cells vs. activated T helper cells shows that most patients' populations of these two cells appear to lie along a negatively sloped line. Linear least squares fitting to those samples yields a line of slope −1.00078. (d) Levels of resting and activated monocytes show a negative relationship with each other in both SLE and healthy donors.

Figure 8. Disease activity is related to changes in cell populations.

SLE disease activity index (SLEDAI) scores from the main SLE patient cohort are significantly correlated with activated NK cell or activated dendritic cell relative abundance. Diagonal lines and statistical metrics are from the linear least squares fit to the plotted data.

Figure 9. Medical treatment is related to changes in cell populations.

Relative abundance of selected cell types for SLE patients from the main cohort segregated by whether the patient was currently on corticosteroid, azathioprine, or mycophenolate treatment. Fold changes shown are fold change of the mean of the data. P-values shown are from two-tailed Wilcoxon Rank Sum test. Quantile boxes and tails are 10%ile, 25%ile, 50%ile, 75%ile, and 90%ile.