NanoString technology distinguishes anti-TIF-1γ+ from anti-Mi-2+ dermatomyositis patients

Abstract

Dermatomyositis (DM) is a systemic idiopathic inflammatory disease affecting skeletal muscle and skin, clinically characterized by symmetrical proximal muscle weakness and typical skin lesions. Recently, myositis-specific autoantibodies (MSA) became of utmost importance because they strongly correlate with distinct clinical manifestations and prognosis. Antibodies against transcription intermediary factor 1γ (TIF-1γ) are frequently associated with increased risk of malignancy, a specific cutaneous phenotype and limited response to therapy in adult DM patients. Anti-Mi-2 autoantibodies, in contrast, are typically associated with classic DM rashes, prominent skeletal muscle weakness, better therapeutic response and prognosis, and less frequently with cancer. Nevertheless, the sensitivity of autoantibody testing is only moderate, and alternative reliable methods for DM patient stratification and prediction of cancer risk are needed. To further investigate these clinically distinct DM subgroups, we herein analyzed 30 DM patients (n = 15 Mi-2⁺ and n = 15 TIF-1 γ⁺ ) and n = 8 non-disease controls (NDC). We demonstrate that the NanoString technology can be used as a very sensitive method to clearly differentiate these two clinically distinct DM subgroups. Using the nCounter PanCancer Immune Profiling Panel™, we identified a set of significantly dysregulated genes in anti-TIF-1γ⁺ patient muscle biopsies including VEGFA, DDX58, IFNB1, CCL5, IL12RB2, and CD84. Investigation of type I IFN-regulated transcripts revealed a striking type I interferon signature in anti-Mi-2⁺ patient biopsies. Our results help to stratify both subgroups and predict, which DM patients require an intensified diagnostic procedure and might have a poorer outcome. Potentially, this could also have implications for the therapeutic approach.

Keywords: Mi-2; NanoString; TIF-1γ; dermatomyositis; myositis-specific antibody; skeletal muscle.

FIGURE 1

Genetic profiling of anti‐TIF‐1γ⁺ and ‐Mi‐2⁺ dermatomyositis patients’ skeletal muscle biopsies revealed subgroup‐specific signatures. (A) Experimental design and analysis workflow of the project. (B) Differential gene expression analysis from anti‐TIF‐1γ⁺ patients (n = 6) and non‐diseased controls (n = 2). (C) Differential gene expression analysis from anti‐Mi‐2⁺ patients (n = 6) and non‐diseased controls (n = 2). (D) Venn diagram comparing the differentially expressed genes (in skeletal muscle tissues) of anti‐TIF‐1γ⁺ patients vs. non‐diseased controls and anti‐Mi‐2⁺ patients vs. non‐diseased controls, identifying 207 commonly dysregulated genes, 20 TIF‐1γ subgroup‐specific genes and 118 Mi‐2 subgroup‐specific genes. The top 5 up‐ and downregulated genes specific for each subgroup are highlighted

FIGURE 2

NanoString^® analysis clearly distinguishes anti‐TIF‐1γ⁺ from ‐Mi‐2⁺ dermatomyositis patients. (A) Unsupervised clustering of patient samples using the NanoString^® pathway score analysis tool. Asterisk (*) indicate CAM+ patients. Hashtag (#) indicates CAM‐ patient. (B) Differential gene expression analysis of anti‐TIF‐1γ⁺ patients vs. ‐Mi‐2⁺ patients. The top 5 up‐ and downregulated genes are highlighted. (C) Gene expression levels detected by qPCR of DM patients (each subgroup n = 10) displayed as fold‐change vs. NDC (n = 3), upregulation is significant for DDX58, MST1R in anti‐Mi‐2⁺ patients as well as for MST1R in anti‐TIF‐1γ⁺ patients, no significance between both subgroups was detected (C, D)

FIGURE 3

Histological and immunofluorescent staining of VEGF in DM patients’ skeletal muscle samples. Anti‐TIF‐1γ⁺ DM patients show clearly enhanced expression of sarcolemmal VEGF in the perifascicular areas while anti‐Mi‐2⁺ DM patients show only single positive fibres (left panel). Double immune histochemistry identified multiple VEGF⁺ myofibres and a severe depletion of laminin‐α5⁺ capillaries in anti‐TIF‐1γ⁺, while laminin‐α5⁺ capillaries were less depleted in anti‐Mi‐2⁺ DM patients’ biopsies (middle panel). Double immunofluorescence showed that atrophic muscle fibres co‐stained with neonatal myosin heavy chain (nMyHc) and VEGF (orange arrow) both in TIF‐1γ⁺ and in Mi‐2⁺ cases, however, not all regenerating myofibres were also VEGF⁺ (right panel)