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

被引:117
作者
Pinal-Fernandez, Iago [1 ,2 ,3 ,4 ]
Casal-Dominguez, Maria [1 ,2 ]
Derfoul, Assia [1 ]
Pak, Katherine [1 ]
Miller, Frederick W. [5 ]
Milisenda, Jose Cesar [6 ]
Grau-Junyent, Josep Maria [6 ]
Selva-O'Callaghan, Albert [7 ]
Carrion-Ribas, Carme [3 ]
Paik, Julie J. [8 ]
Albayda, Jemima [8 ]
Christopher-Stine, Lisa [2 ,8 ]
Lloyd, Thomas E. [2 ]
Corse, Andrea M. [2 ]
Mammen, Andrew L. [1 ,2 ,8 ]
机构
[1] NIAMSD, Muscle Dis Unit, Lab Muscle Stem Cells & Gene Regulat, NIH, Bethesda, MD 20892 USA
[2] Johns Hopkins Univ, Sch Med, Dept Neurol, Baltimore, MD 21205 USA
[3] Univ Oberta Catalunya, Fac Hlth Sci, Barcelona, Spain
[4] Univ Oberta Catalunya, Fac Comp Sci Multimedia & Telecommun, Barcelona, Spain
[5] NIEHS, Enivironmental Autoimmun Grp, NIH, Bethesda, MD USA
[6] Hosp Clin Barcelona, Internal Med, Barcelona, Catalunya, Spain
[7] Univ Autonoma Barcelona, Vall dHebron Gen Hosp, Internal Med, Barcelona, Spain
[8] Johns Hopkins Univ, Sch Med, Dept Med, Div Rheumatol, Baltimore, MD 21205 USA
基金
美国国家卫生研究院;
关键词
INCLUSION-BODY MYOSITIS; INFLAMMATORY MYOPATHIES; CLASSIFICATION; AUTOANTIBODIES; FEATURES; DEFINE;
D O I
10.1136/annrheumdis-2019-216599
中图分类号
R5 [内科学];
学科分类号
1002 ; 100201 ;
摘要
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-C oA reductase (HMGCR) myopathy, and MADCAM1 (mucosal vascular addressin cell adhesion molecule 1), which is only expressed in anti-i2-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.
引用
收藏
页码:1234 / 1242
页数:9
相关论文
共 32 条
[1]   Th1 Response and Systemic Treg Deficiency in Inclusion Body Myositis [J].
Allenbach, Yves ;
Chaara, Wahiba ;
Rosenzwajg, Michelle ;
Six, Adrien ;
Prevel, Nicolas ;
Mingozzi, Federico ;
Wanschitz, Julia ;
Musset, Lucile ;
Charuel, Jean-Luc ;
Eymard, Bruno ;
Salomon, Benoit ;
Duyckaerts, Charles ;
Maisonobe, Thierry ;
Dubourg, Odile ;
Herson, Serge ;
Klatzmann, David ;
Benveniste, Olivier .
PLOS ONE, 2014, 9 (03)
[2]   Calcium dysregulation, functional calpainopathy, and endoplasmic reticulum stress in sporadic inclusion body myositis [J].
Amici, David R. ;
Pinal-Fernandez, Iago ;
Mazala, Davi A. G. ;
Lloyd, Thomas E. ;
Corse, Andrea M. ;
Christopher-Stine, Lisa ;
Mammen, Andrew L. ;
Chin, Eva R. .
ACTA NEUROPATHOLOGICA COMMUNICATIONS, 2017, 5 :24
[3]   ALPHA-4-BETA-7-INTEGRIN MEDIATES LYMPHOCYTE BINDING TO THE MUCOSAL VASCULAR ADDRESSIN MADCAM-1 [J].
BERLIN, C ;
BERG, EL ;
BRISKIN, MJ ;
ANDREW, DP ;
KILSHAW, PJ ;
HOLZMANN, B ;
WEISSMAN, IL ;
HAMANN, A ;
BUTCHER, EC .
CELL, 1993, 74 (01) :185-195
[4]   Myositis-specific autoantibodies: an important tool to support diagnosis of myositis [J].
Betteridge, Z. ;
McHugh, N. .
JOURNAL OF INTERNAL MEDICINE, 2016, 280 (01) :8-23
[5]   Interstitial Lung Disease Associated With the Idiopathic Inflammatory Myopathies What Progress Has Been Made in the Past 35 Years? [J].
Connors, Geoffrey R. ;
Christopher-Stine, Lisa ;
Oddis, Chester V. ;
Danoff, Sonye K. .
CHEST, 2010, 138 (06) :1464-1474
[6]  
DCunha J, 1996, J IMMUNOL, V157, P4100
[7]   Mechano-regulated Tenascin-C orchestrates muscle repair [J].
Flueck, Martin ;
Mund, Sonja I. ;
Schittny, Johannes C. ;
Klossner, Stephan ;
Durieux, Anne-Cecile ;
Giraud, Marie-Noelle .
PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA, 2008, 105 (36) :13662-13667
[8]   Plasma cells in muscle in inclusion body myositis and polymyositis [J].
Greenberg, SA ;
Bradshaw, EM ;
Pinkus, JL ;
Pinkus, GS ;
Burleson, T ;
Due, B ;
Bregoli, LS ;
O'Connor, KC ;
Amato, AA .
NEUROLOGY, 2005, 65 (11) :1782-1787
[9]   Interferon-α/β-mediated innate immune mechanisms in dermatomyositis [J].
Greenberg, SA ;
Pinkus, JL ;
Pinkus, GS ;
Burleson, T ;
Sanoudou, D ;
Tawil, R ;
Barohn, RJ ;
Saperstein, DS ;
Briemberg, HR ;
Ericsson, M ;
Park, P ;
Amato, AA .
ANNALS OF NEUROLOGY, 2005, 57 (05) :664-678
[10]   Molecular profiles of inflammatory myopathies [J].
Greenberg, SA ;
Sanoudou, D ;
Haslett, JN ;
Kohane, IS ;
Kunkel, LM ;
Beggs, AH ;
Amato, AA .
NEUROLOGY, 2002, 59 (08) :1170-1182