Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2020 Sep;79(9):1234-1242.
doi: 10.1136/annrheumdis-2019-216599. Epub 2020 Jun 16.

Machine learning algorithms reveal unique gene expression profiles in muscle biopsies from patients with different types of myositis

Iago Pinal-Fernandez  1   2   3   4 , Maria Casal-Dominguez  1   2 , Assia Derfoul  1 , Katherine Pak  1 , Frederick W Miller  5 , Jose César Milisenda  6 , Josep Maria Grau-Junyent  6 , Albert Selva-O'Callaghan  7 , Carme Carrion-Ribas  3 , Julie J Paik  8 , Jemima Albayda  8 , Lisa Christopher-Stine  2   8 , Thomas E Lloyd  2 , Andrea M Corse  2 , Andrew L Mammen  9   2   8
Affiliations

Machine learning algorithms reveal unique gene expression profiles in muscle biopsies from patients with different types of myositis

Iago Pinal-Fernandez et al. Ann Rheum Dis. 2020 Sep.

Abstract

Objectives: Myositis is a heterogeneous family of diseases that includes dermatomyositis (DM), antisynthetase syndrome (AS), immune-mediated necrotising myopathy (IMNM), inclusion body myositis (IBM), polymyositis and overlap myositis. Additional subtypes of myositis can be defined by the presence of myositis-specific autoantibodies (MSAs). The purpose of this study was to define unique gene expression profiles in muscle biopsies from patients with MSA-positive DM, AS and IMNM as well as IBM.

Methods: RNA-seq was performed on muscle biopsies from 119 myositis patients with IBM or defined MSAs and 20 controls. Machine learning algorithms were trained on transcriptomic data and recursive feature elimination was used to determine which genes were most useful for classifying muscle biopsies into each type and MSA-defined subtype of myositis.

Results: The support vector machine learning algorithm classified the muscle biopsies with >90% accuracy. Recursive feature elimination identified genes that are most useful to the machine learning algorithm and that are only overexpressed in one type of myositis. For example, CAMK1G (calcium/calmodulin-dependent protein kinase IG), EGR4 (early growth response protein 4) and CXCL8 (interleukin 8) are highly expressed in AS but not in DM or other types of myositis. Using the same computational approach, we also identified genes that are uniquely overexpressed in different MSA-defined subtypes. These included apolipoprotein A4 (APOA4), which is only expressed in anti-3-hydroxy-3-methylglutaryl-CoA reductase (HMGCR) myopathy, and MADCAM1 (mucosal vascular addressin cell adhesion molecule 1), which is only expressed in anti-Mi2-positive DM.

Conclusions: Unique gene expression profiles in muscle biopsies from patients with MSA-defined subtypes of myositis and IBM suggest that different pathological mechanisms underly muscle damage in each of these diseases.

Keywords: autoantibodies; autoimmune diseases; autoimmunity; dermatomyositis; polymyositis.

PubMed Disclaimer

Conflict of interest statement

Competing interests: None declared.

Figures

Figure 1.
Figure 1.. Expression levels of those genes most helpful to classify muscle biopsies into each type of myositis.
The expression levels of the top 3 genes used by the support vector machine model to classify muscle biopsies from normal tissue (NT), dermatomyositis (DM), immune-mediated necrotizing myositis (IMNM), antisynthetase syndrome (AS) or inclusion body myositis (IBM).
Figure 2.
Figure 2.. Genes selectively upregulated in different autoantibody-defined subtypes of myositis.
APOA4 and MADCAM1 are selectively overexpressed (log2[FPKM + 1]) in anti-HMGCR IMNM (q-value compared to SRP: 0.0009) and anti-Mi2 DM (q-value compared to other DM antibodies: 2.9E-9), respectively. Normal tissue: NT; inclusion body myositis: IBM; anti-SRP IMNM: SRP; anti-HMGCR IMNM: HMGCR; anti-Mi2 DM: Mi2; anti-NXP2 DM: NXP2; anti-TIF1γ DM: TIF1; anti-MDA5 DM: MDA5; anti-Jo1 AS: Jo1.
Figure 3.
Figure 3.. Pathway analysis in myositis and normal muscle biopsies.
The top 10 pathways of the different muscle biopsy groups are shown. NT, normal tissue; DM, dermatomyositis; IMNM, immune-mediated necrotizing myopathy; AS, antisynthetase syndrome; IBM, inclusion body myositis.
See this image and copyright information in PMC

Comment in

References

    1. Mariampillai K, Granger B, Amelin D, et al. Development of a New Classification System for Idiopathic Inflammatory Myopathies Based on Clinical Manifestations and Myositis-Specific Autoantibodies. JAMA Neurol 2018;75:1528–37. - PMC - PubMed
    1. Love LA, Leff RL, Fraser DD, et al. A new approach to the classification of idiopathic inflammatory myopathy: myositis-specific autoantibodies define useful homogeneous patient groups. Medicine; analytical reviews of general medicine, neurology, psychiatry, dermatology, and pediatries 1991;70:360–74. - PubMed
    1. Betteridge Z, McHugh N. Myositis-specific autoantibodies: an important tool to support diagnosis of myositis. Journal of internal medicine 2016;280:8–23. - PubMed
    1. Selva-O’Callaghan A, Pinal-Fernandez I, Trallero-Araguas E, et al. Classification and management of adult inflammatory myopathies. Lancet Neurol 2018;17:816–28. - PMC - PubMed
    1. Greenberg SA, Pinkus JL, Pinkus GS, et al. Interferon-alpha/beta-mediated innate immune mechanisms in dermatomyositis. Annals of Neurology 2005;57:664–78. - PubMed

Publication types

MeSH terms

Supplementary concepts