You are here

  • Home
  • Archive
  • Volume 80, Issue 2
  • Machine learning integration of scleroderma histology and gene expression identifies fibroblast polarisation as a hallmark of clinical severity and improvement

Article Text

Article menu
Download PDFPDF
Systemic sclerosis
Machine learning integration of scleroderma histology and gene expression identifies fibroblast polarisation as a hallmark of clinical severity and improvement
  1. Kimberly Showalter1,
  2. Robert Spiera1,
  3. Cynthia Magro2,
  4. Phaedra Agius3,
  5. Viktor Martyanov4,5,
  6. Jennifer M Franks4,5,
  7. Roshan Sharma3,
  8. Heather Geiger3,
  9. Tammara A Wood4,5,
  10. Yaxia Zhang6,
  11. Caryn R Hale7,
  12. Jackie Finik8,
  13. Michael L Whitfield4,5,
  14. Dana E Orange1,7,
  15. Jessica K Gordon1
  1. 1 Department of Medicine, Division of Rheumatology, Hospital for Special Surgery, New York, New York, USA
  2. 2 Department of Pathology and Laboratory Medicine, Weill Cornell Medicine, New York, New York, USA
  3. 3 New York Genome Center, New York, New York, USA
  4. 4 Molecular and Systems Biology, Dartmouth College Geisel School of Medicine, Hanover, New Hampshire, USA
  5. 5 Biomedical Data Science, Dartmouth College Geisel School of Medicine, Hanover, New Hampshire, USA
  6. 6 Department of Pathology, Hospital for Special Surgery, New York, New York, USA
  7. 7 Laboratory of Molecular Neuro-Oncology, The Rockefeller University, New York, New York, USA
  8. 8 Department of Medicine, Hospital for Special Surgery, New York, New York, USA
  1. Correspondence to Dr Kimberly Showalter, Department of Medicine, Division of Rheumatology, Hospital for Special Surgery, New York, NY 10021, USA; showalterk{at}hss.edu

Abstract

Objective We sought to determine histologic and gene expression features of clinical improvement in early diffuse cutaneous systemic sclerosis (dcSSc; scleroderma).

Methods Fifty-eight forearm biopsies were evaluated from 26 individuals with dcSSc in two clinical trials. Histologic/immunophenotypic assessments of global severity, alpha-smooth muscle actin (aSMA), CD34, collagen, inflammatory infiltrate, follicles and thickness were compared with gene expression and clinical data. Support vector machine learning was performed using scleroderma gene expression subset (normal-like, fibroproliferative, inflammatory) as classifiers and histology scores as inputs. Comparison of w-vector mean absolute weights was used to identify histologic features most predictive of gene expression subset. We then tested for differential gene expression according to histologic severity and compared those with clinical improvement (according to the Combined Response Index in Systemic Sclerosis).

Results aSMA was highest and CD34 lowest in samples with highest local Modified Rodnan Skin Score. CD34 and aSMA changed significantly from baseline to 52 weeks in clinical improvers. CD34 and aSMA were the strongest predictors of gene expression subset, with highest CD34 staining in the normal-like subset (p<0.001) and highest aSMA staining in the inflammatory subset (p=0.016). Analysis of gene expression according to CD34 and aSMA binarised scores identified a 47-gene fibroblast polarisation signature that decreases over time only in improvers (vs non-improvers). Pathway analysis of these genes identified gene expression signatures of inflammatory fibroblasts.

Conclusion CD34 and aSMA stains describe distinct fibroblast polarisation states, are associated with gene expression subsets and clinical assessments, and may be useful biomarkers of clinical severity and improvement in dcSSc.

  • scleroderma
  • systemic
  • fibroblasts
  • inflammation
  • autoimmune diseases

http://dx.doi.org/10.1136/annrheumdis-2020-217840

Statistics from Altmetric.com

    Request Permissions

    If you wish to reuse any or all of this article please use the link below which will take you to the Copyright Clearance Center’s RightsLink service. You will be able to get a quick price and instant permission to reuse the content in many different ways.

    View Full Text

    Footnotes

    • Handling editor Josef S Smolen

    • Twitter @danaorange

    • DEO and JKG contributed equally.

    • Correction notice This article has been corrected since it published Online First. An acknowledgement section has been added and figure 3 updated.

    • Contributors KS, RSpiera, CM, PA, RSharma, HG, JF, VM, CRH, MLW, DEO and JG contributed to the conception and study design. KS, RSpiera, CM, VM, JF, TAW, YZ, MLW, DEO and JG contributed to data collection. KS, RSpiera, PA, VM, RSharma, HG, YZ, CRH, JF, MLW, DEO and JG contributed to data analysis. KS, RSpiera, CM, PA, VM, RSharma, HG, YZ, CRH, JF, MLW, DEO and JG contributed to interpretation of the data. KS, DEO and JG wrote the first version of the manuscript. All authors read, critically revised and approved the final manuscript.

    • Funding This study was supported by the Hospital for Special Surgery Rheumatology Council (JG) and the Scleroderma Clinical Trials Consortium (SCTC) Working Group Grant (KS). This study uses data from the nilotinib and belimumab trials in systemic sclerosis that were investigator-initiated studies supported by research grants from Novartis and GlaxoSmithKline, respectively.

    • Competing interests RSpiera reports receiving funds for the following activities: Research support: GlaxoSmithKline, Genentech/Roche, Novartis, Corbus Pharmaceuticals, Cytori Therapeutics, Evidera, Actelion Pharmaceuticals, ChemoCentryx, Boehringer Ingelheim Pharmaceuticals, Forbius, InfaRx, Sanofi, Kiniksa Pharmaceuticals; Consulting: GlaxoSmithKline, Janssen Pharmaceuticals, Sanofi Aventis, ChemoCentryx, Forbius, CSL Behring; MLW reports grants and personal fees from Celdara Medical, grants and personal fees from Bristol Myers Squib, personal fees from Acceleron, personal fees from Abbvie, grants and personal fees from Corbus and other fees from Boehringer Ingelheim, outside the submitted work; DEO reports receiving funds from Pfizer and personal fees from Astra Zeneca, outside the submitted work; JG reports receiving funds for the following activities: Consulting: Eicos Sciences; Research Support: Corbus Pharmaceuticals, Cumberland Pharmaceuticals and Eicos Sciences, outside the submitted work.

    • Patient and public involvement Patients and/or the public were not involved in the design, or conduct, or reporting, or dissemination plans of this research.

    • Patient consent for publication Not required.

    • Ethics approval Hospital for Special Surgery Institutional Review Board approved this study (approval numbers: 2014-268 and 2019-0089), and patient informed consent was obtained.

    • Provenance and peer review Not commissioned; externally peer reviewed.

    • Data availability statement Data are available in a public, open access repository. All gene expression data have been deposited in Gene Expression Omnibus (GEO) (accession nos GSE65405 and GSE97248).