Article Text

Download PDFPDF
Machine learning predicts stem cell transplant response in severe scleroderma
  1. Jennifer M Franks1,2,
  2. Viktor Martyanov1,2,
  3. Yue Wang1,2,
  4. Tammara A Wood1,2,
  5. Ashley Pinckney3,
  6. Leslie J Crofford4,
  7. Lynette Keyes-Elstein3,
  8. Daniel E Furst5,
  9. Ellen Goldmuntz6,
  10. Maureen D Mayes7,
  11. Peter McSweeney8,
  12. Richard A Nash8,
  13. Keith M Sullivan9,
  14. Michael L Whitfield1,2
  1. 1Molecular and Systems Biology, Dartmouth College Geisel School of Medicine, Hanover, New Hampshire, USA
  2. 2Biomedical Data Science, Dartmouth College Geisel School of Medicine, Hanover, New Hampshire, USA
  3. 3Rho Federal Systems Division, Chapel Hill, North Carolina, USA
  4. 4Department of Medicine, Vanderbilt University Medical Center, Nashville, Tennessee, United States
  5. 5Department of Medicine, Division of Rheumatology, University of California at Los Angeles, Los Angeles, California, USA
  6. 6NIAID/NIH, Bethesda, Maryland, USA
  7. 7Rheumatology and Clinical Immunogenetics, The University of Texas Health Science Center Houston Medical School, Houston, Texas, USA
  8. 8Rocky Mountain Blood and Marrow Transplant Program, Colorado Blood Cancer Institute, Denver, Colorado, USA
  9. 9Duke University Medical Center, Durham, North Carolina, United States
  1. Correspondence to Dr Michael L Whitfield, Geisel School of Medicine at Dartmouth, Hanover, NH 03755, USA; michael.l.whitfield{at}


Objective The Scleroderma: Cyclophosphamide or Transplantation (SCOT) trial demonstrated clinical benefit of haematopoietic stem cell transplant (HSCT) compared with cyclophosphamide (CYC). We mapped PBC (peripheral blood cell) samples from the SCOT clinical trial to scleroderma intrinsic subsets and tested the hypothesis that they predict long-term response to HSCT.

Methods We analysed gene expression from PBCs of SCOT participants to identify differential treatment response. PBC gene expression data were generated from 63 SCOT participants at baseline and follow-up timepoints. Participants who completed treatment protocol were stratified by intrinsic gene expression subsets at baseline, evaluated for event-free survival (EFS) and analysed for differentially expressed genes (DEGs).

Results Participants from the fibroproliferative subset on HSCT experienced significant improvement in EFS compared with fibroproliferative participants on CYC (p=0.0091). In contrast, EFS did not significantly differ between CYC and HSCT arms for the participants from the normal-like subset (p=0.77) or the inflammatory subset (p=0.1). At each timepoint, we observed considerably more DEGs in HSCT arm compared with CYC arm with HSCT arm showing significant changes in immune response pathways.

Conclusions Participants from the fibroproliferative subset showed the most significant long-term benefit from HSCT compared with CYC. This study suggests that intrinsic subset stratification of patients may be used to identify patients with SSc who receive significant benefit from HSCT.

  • systemic sclerosis
  • cyclophosphamide
  • treatment
View Full Text

Statistics from


  • Handling editor Josef S Smolen

  • JMF and VM contributed equally.

  • Contributors JMF, VM and MLW designed research studies, conducted experiments and analysed data. TAW acquired data and provided the reagents. YW, AP and LK-E analysed and reviewed data. LJC, DEF, EG, MDM, PM, RAN and KMS collected samples and designed research studies. All authors reviewed, edited and wrote the final version of the manuscript. The authorship order among cofirst authors was determined alphabetically.

  • Funding Supported by awards from the Scleroderma Research Foundation (MLW), Burroughs-Wellcome PUP Big Data in the Life Sciences Training Program, the National Institutes of Health BD2K T32 5T32LM012204-03 (JMF), and the Dr Ralph and Marian Falk Medical Research Trust (MLW) to Dartmouth College, NIH NIAID grants (N01-AI05419 and HHSN272201100025C) to Duke University, and to Rho, the statistical and clinical coordinating center (N01-AI25481, HHSN272200900057C and 1UM2AI117870).

  • Competing interests 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, personal fees from Boehringer Ingelheim, outside the submitted work. MDM reports personal fees from Medtelligence, personal fees from Actelion Pharma, personal fees from Astellas, personal fees from Mitsubishi-Tanabe, grants from Bayer, grants from Reata, grants from Sanofi, grants from Corbus, grants and personal fees from Boehringer-Ingelheim, grants and personal fees from EICOS, grants and personal fees from Galapagos, grants from GSK, outside the submitted work. DEF reports grants from Actelion, grants and personal fees from Amgen, grants and personal fees from Bristol Myers Squibb, grants and personal fees from Galapagos, grants and personal fees from Novartis, grants and personal fees from Pfizer, grants from Sanofi, grants from Roche/Genentech, grants and personal fees from Corbus, grants from GSK, outside the submitted work. All other authors have nothing to disclose.

  • Patient and public involvement Patients participated in the clinical trial and the study was in part funded by the Scleroderma Research Foundation, which includes scleroderma patients and advocates.

  • Patient consent for publication Not required.

  • Ethics approval The SCOT study protocol was approved by the local Institutional Review Boards of the participating institutions.

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

  • Data availability statement Data are available in a public, open access repository. The gene expression data and related deidentified clinical information are available on the Gene Expression Omnibus (GEO) database-accession number: GSE134310.

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.