Blood and islet phenotypes indicate immunological heterogeneity in type 1 diabetes

Abstract

Studies in type 1 diabetes indicate potential disease heterogeneity, notably in the rate of β-cell loss, responsiveness to immunotherapies, and, in limited studies, islet pathology. We sought evidence for different immunological phenotypes using two approaches. First, we defined blood autoimmune response phenotypes by combinatorial, multiparameter analysis of autoantibodies and autoreactive T-cell responses in 33 children/adolescents with newly diagnosed diabetes. Multidimensional cluster analysis showed two equal-sized patient agglomerations characterized by proinflammatory (interferon-γ-positive, multiautoantibody-positive) and partially regulated (interleukin-10-positive, pauci-autoantibody-positive) responses. Multiautoantibody-positive nondiabetic siblings at high risk of disease progression showed similar clustering. Additionally, pancreas samples obtained post mortem from a separate cohort of 21 children/adolescents with recently diagnosed type 1 diabetes were examined immunohistologically. This revealed two distinct types of insulitic lesions distinguishable by the degree of cellular infiltrate and presence of B cells that we termed "hyper-immune CD20Hi" and "pauci-immune CD20Lo." Of note, subjects had only one infiltration phenotype and were partitioned by this into two equal-sized groups that differed significantly by age at diagnosis, with hyper-immune CD20Hi subjects being 5 years younger. These data indicate potentially related islet and blood autoimmune response phenotypes that coincide with and precede disease. We conclude that different immunopathological processes (endotypes) may underlie type 1 diabetes, carrying important implications for treatment and prevention strategies.

Figure 1

Cluster analysis of autoreactive T-cell and AAb responses in the blood close to diagnosis of type 1 diabetes. Blood samples from 33 children with newly diagnosed type 1 diabetes were analyzed for the quality (IFN-γ, IL-10, and AAbs) and specificity (proinsulin, insulin, IA-2, GAD65, and ZnT8) of autoimmune responses, generating results for 27 analytes summed to show responsiveness to the parent antigens. A: Dendrogram showing agglomerative hierarchical clustering analysis, which reveals two highly stable autoimmune response clusters (bootstrap support for the main nodes ≥95%), a combination of islet AAbs and IFN-γ responses to all antigens tested (right cluster) as distinct from IL-10 responses to all antigens tested (left cluster). B: Dendrogram showing agglomerative hierarchical clustering analysis in which patients with type 1 diabetes form two distinct clusters (bootstrap support for the main nodes ≥97%) of approximately equal size. C: Combined analysis of the patient and autoimmune response clusters using unbiased hierarchical clustering in a heat map illustrating that the major discriminating factor between the two patient agglomerations is the presence of an IL-10 response (cluster-1, bottom left). Yellow indicates a positive response to an analyte and blue a negative response. CD4 T-cell peptide-specific responses are summarized into proteins (IA-2, GAD, proinsulin, and insulin). D: Plots showing the two principal components (PCs) of autoreactive T-cell responses in patients with type 1 diabetes, each identified as circles. The color of the symbol indicates AAb positivity (open = no AAb; yellow = 1 AAb+; orange = 2 AAb+; red = 3 AAb+). Numbered arrows represent vectors indicating the influence of individual analyte responses on PC1 and PC2. The length of the arrow reflects the strength of the effect. Solid lines are IFN-γ responses and broken lines IL-10 responses. Numbers 1–12 are the peptide identifiers (Table 1). The ovals outline putative patient clusters, with cluster A predominantly reflecting IFN-γ and cluster B IL-10 responses. IFG, interferon-γ; Ins, insulin; PI, proinsulin.

Figure 2

Autoimmune inflammatory phenotypes in nondiabetic siblings of children with type 1 diabetes. Graphs compare frequency of response to islet autoantigens in siblings of type 1 diabetic patients collected in a cross-sectional study (y-axis) with that in type 1 diabetic patients matched for age and studied close to diagnosis (x-axis). Blue circles denote IL-10 responses, red IFN-γ responses, and green AAb responses. Filled circles indicate a statistically significant difference (P < 0.05) in the frequency of responses between the two groups. Gray lines are 95% CIs. Numbered symbols in A indicate individual autoantigen peptides (Table 1). A: Comparison of response frequency against single analytes. Islet AAbs, and especially IA-2Ab and ZnT8Ab, are strongly diabetes-associated measurements. B: Single T-cell analytes were summed to indicate a response to a single autoantigen. IFN-γ CD4 T-cell responses to specific antigens, notably insulin and proinsulin, are strong and significant. C: T-cell analytes were summed to show a positive response to any autoantigen, and AAb responses were summed to show positivity to any autoantigen; disease discrimination is comparable between AAbs and T-cell responses. Ins, insulin; PI, proinsulin.

Figure 3

Clustering analysis of autoimmune inflammatory phenotypes in siblings. Unbiased hierarchical clustering analysis of autoimmune CD4 T-cell and AAb responses are represented as heat maps. A: Analysis of unaffected siblings in an unbiased, cross-sectional study. B: Analysis of high-risk, unaffected siblings with multiple (two or more) islet AAb positivity showing two main clusters characterized by the presence of IL-10 with sparse IFN-γ (lower left) and the presence of IFN-γ with sparse IL-10 (upper right). Yellow indicates a positive response to an analyte and blue a negative response. CD4 T-cell peptide-specific responses are summarized into proteins (IA-2, GAD, PI, and Ins). C: Plots showing two principal components (PCs) for siblings with two or more islet AAbs and at high risk of progression to disease; each subject is identified by a diamond, the color of which indicates AAb positivity (open = no AAb; yellow = 1 AAb+; orange = 2 AAb+; red = 3 AAb+; brown = 4 AAb+). For explanation of arrows, see Fig. 1D legend. The same oval outlines as in Fig. 1D are overlaid, and the corresponding clusters A (IFN-γ dominated) and B (IL-10 dominated) are identifiable in high-risk subjects. The subjects identified by arrows a and bin cluster A developed type 1 diabetes (ages 6 and 10 years, respectively, at diagnosis); the subject identified by arrow c in cluster B developed type 1 diabetes at age 18 years. IFG, interferon-γ; Ins, insulin; PI, proinsulin.

Figure 4

Immunohistological analysis of pancreas from patients with type 1 diabetes reveals heterogeneity of insulitis. Staining shows CD20⁺ cells in three representative islets from a single patient with abundant positivity (nPOD 6052) (A–C) and a single patient with absence of positivity (nPOD 6070) (D–F). Staining patterns correspond to hyper-immune CD20Hi and pauci-immune CD20Lo, respectively. CD20 staining was used to subdivide 21 patients into CD20Hi and CD20Lo categories by using mean CD20⁺ cell counts above and below 3.7 cells/islet.