Interferon and biologic signatures in dermatomyositis skin: specificity and heterogeneity across diseases

Abstract

Background: Dermatomyositis (DM) is an autoimmune disease that mainly affects the skin, muscle, and lung. The pathogenesis of skin inflammation in DM is not well understood.

Methodology and findings: We analyzed genome-wide expression data in DM skin and compared them to those from healthy controls. We observed a robust upregulation of interferon (IFN)-inducible genes in DM skin, as well as several other gene modules pertaining to inflammation, complement activation, and epidermal activation and differentiation. The interferon (IFN)-inducible genes within the DM signature were present not only in DM and lupus, but also cutaneous herpes simplex-2 infection and to a lesser degree, psoriasis. This IFN signature was absent or weakly present in atopic dermatitis, allergic contact dermatitis, acne vulgaris, systemic sclerosis, and localized scleroderma/morphea. We observed that the IFN signature in DM skin appears to be more closely related to type I than type II IFN based on in vitro IFN stimulation expression signatures. However, quantitation of IFN mRNAs in DM skin shows that the majority of known type I IFNs, as well as IFN g, are overexpressed in DM skin. In addition, both IFN-beta and IFN-gamma (but not other type I IFN) transcript levels were highly correlated with the degree of the in vivo IFN transcriptional response in DM skin.

Conclusions and significance: As in the blood and muscle, DM skin is characterized by an overwhelming presence of an IFN signature, although it is difficult to conclusively define this response as type I or type II. Understanding the significance of the IFN signature in this wide array of inflammatory diseases will be furthered by identification of the nature of the cells that both produce and respond to IFN, as well as which IFN subtype is biologically active in each diseased tissue.

Figure 1. Visualization and validation of DM gene expression on HEEBO oligonucleotide arrays.

RNA was prepared from skin biopsies as detailed in Methods, and the same source was used for both gene expression array (A) and QRT-PCR experiments (B). A. Experimental hierarchical clustering dendrogram. Two-dimensional hierarchical clustering was performed on gene expression data from active DM skin lesions and skin from healthy controls. A set of 946 genes whose average expression significantly differed between DM and healthy controls (the “DM module) was used to group sample expression data; 646 genes were upregulated (red bar on left) and 300 genes were downregulated (green bar on left) in DM patients relative to control biopsies. All values are in log₂ space and are mean-centered across each gene. Colored bars on right indicate gene clusters evident on dendrogram: yellow bar—epidermal activation; green bar—leukocyte function; light blue bar—IFN signature; red bar—epidermal differentiation; lavender bar—immunoglobulin; brown bar—ribosome; dark purple bar-lipid metabolism. A larger view of the dendrogram and more complete lists of genes in these clusters can be found in Supplementary Figure S2. B. Validation of array data using TaqMan QRT-PCR of selected transcripts. QRT-PCR was performed (see Methods) on 9 DM skin RNA samples and 8 control skin RNA samples for four selected transcripts that were either found to be upregulated (OAS2, IFIT3) or downregulated (FADS1, HMGCS1) in DM skin. Shown are the mean values (with SEM) for each transcript in DM skin relative to the mean value in control skin. Relative transcript values for each of the 4 genes across the 9 DM samples showed a high correlation (Pearson's r = 0.71 to 0.86) between the HEEBO array and QRT-PCR.

Figure 2. DM skin module map.

Module map of the Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) Biological Processes differentially expressed among the active DM samples is shown. Each column represents a single microarray (e.g. patient) and each row represents a single GO or KEGG biological process. Only modules that were significantly enriched (minimum 2-fold change, p = 0.05) on at least 4 microarrays are shown. The average expression of the gene hits from each enriched gene set is displayed here. Only gene sets that show significant differences after multiple hypothesis testing were included. Selected GO or KEGG biological processes are shown. The entire figure with all biological processes can be viewed in Supplementary Figure S3.

Figure 3. Mapping the DM module across different inflammatory disease tissues.

Shown is a hierarchical clustering dendrogram of gene expression data from DM and multiple other diseases. The genes visualized represent all of the genes of the DM module that are common to all of the array platforms used to generate the data shown. The expression pattern of this set of 490 genes across all of the disease states shown was clustered using average linkage clustering, while the columns (samples) were not clustered and grouped by disease and experimental dataset. Expression data for each gene is relative to the mean expression level for all healthy controls (red = upregulated; green = downregulated) within each dataset, with the exception that HSV-2 data is relative to uninvolved skin of diseased HSV-2 patients (see Methods). Each disease state is composed of five columns, representing five representative examples (patients) of each disease. DM (HEEBO) and DM (Affy) represent data from independent DM skin biopsies run on either HEEBO or Affymetrix arrays, respectively. The remaining datasets were obtained from publicly available GEO omnibus data (see Methods). All data are derived from skin biopsies with the exception of the three diseases on the right, as indicated. Colored bars on right indicate gene clusters of the DM module that were discussed in the text for Figure 1: yellow bar—epidermal barrier; green bar—leukocyte function; light blue bar—IFN signature; dark purple bar-lipid metabolism.

Figure 4. Visualizing the pattern and strength of the IFN signature expression across multiple disease states.

A. Heatmaps of gene expression of the IFN inducible genes both in vitro and in vivo across diseases. The expression of a set of 117 genes comprising the “core IFN signature” (labeled as “IFN inducible genes” in the figure) is shown following one-way hierarchical clustering (genes only) using the entire in vitro and in vivo dataset. The left panel shows the expression patterns of this IFN signature following various in vitro stimulations with IFN-alpha or IFN-gamma on different responding cell types, as indicated. The right panel shows the expression patterns of the IFN signature across multiple disease states. The data from the disease states were derived from publicly available data as described in Figure 3 and Methods. B. Comparing the strength of the IFN signature across disease states using an IFN score. The top 25 expressed IFN-inducible genes (a static list) was derived from the same in vitro data used to generate the core IFN signature as described in Methods. The median expression value (in linear space) of this set of 25 genes within each disease sample was defined as the IFN score for that sample. Shown is the mean and SEM for IFN scores calculated for each disease dataset represented in panel A.

Figure 5. Distinguishing between type I and II IFN expression patterns across disease states.

Two-dimensional PCA plot is shown using expression data derived from our data (DM, lupus) and publicly available datasets across the 117 gene “core IFN gene set” as described in Methods. Approximately 60% of the total data variation is summarized in these first two principal components.

Figure 6. Expression of IFN transcripts in DM skin and correlation with downstream response.

A. Upregulation of most IFN transcripts in DM skin. QRT-PCR analysis of different IFN transcripts in DM skin samples. TaqMan PCR was performed (see Methods) on 39 DM skin RNA samples and 4 control skin RNA samples for selected IFN transcripts. Shown are the mean values (with SEM) for each transcript in DM skin relative to the mean value in control skin. B. IFN transcripts are not co-regulated across DM skin samples. Hierarchical clustering dendrogram is shown for relative IFN transcript expression levels (using QRT-PCR) across 39 DM samples. Average linkage clustering was performed using correlation (uncentered) similarity metric. Similarity branches (length is inversely correlated with similarity of expression patterns) for IFN-α and IFN-ω are shown in red, IFN-beta in light blue, IFN-gamma in dark purple, and IFN-κ in green. C. IFN-beta and IFN-gammacorrelate most closely with the IFN score in DM skin. For each RNA sample made from 39 independent DM skin biopsies, an IFN score was calculated based on transcript levels of downstream IFN-inducible genes from array data (as described in Figure 4B and Methods) as well as a relative transcript level (using QRT-PCR) for several IFN transcripts (see panel A). Shown are correlation plots (for each of the 39 samples) of the IFN score and IFN transcript levels for IFN-a1, IFN-beta, IFN-gamma, and IFN-kappa.