Machine learning integration of scleroderma histology and gene expression identifies fibroblast polarisation as a hallmark of clinical severity and improvement.

TitleMachine learning integration of scleroderma histology and gene expression identifies fibroblast polarisation as a hallmark of clinical severity and improvement.
Publication TypeJournal Article
Year of Publication2021
AuthorsShowalter K, Spiera R, Magro C, Agius P, Martyanov V, Franks JM, Sharma R, Geiger H, Wood TA, Zhang Y, Hale CR, Finik J, Whitfield ML, Orange DE, Gordon JK
JournalAnn Rheum Dis
Volume80
Issue2
Pagination228-237
Date Published2021 02
ISSN1468-2060
KeywordsActins, Adult, Antigens, CD34, Clinical Trials as Topic, Collagen, Female, Fibroblasts, Forearm, Gene Expression, Humans, Machine Learning, Male, Middle Aged, Scleroderma, Diffuse, Severity of Illness Index, Skin
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.

DOI10.1136/annrheumdis-2020-217840
Alternate JournalAnn Rheum Dis
PubMed ID33028580
Grant ListP50 AR060780 / AR / NIAMS NIH HHS / United States
Related Faculty: 
Cynthia M. Magro, M.D.

Pathology & Laboratory Medicine 1300 York Avenue New York, NY 10065 Phone: (212) 746-6464
Surgical Pathology: (212) 746-2700