Machine-learning-driven biomarker discovery for the discrimination between allergic and irritant contact dermatitis.

Journal: Proceedings of the National Academy of Sciences of the United States of America
PMID: 33318199

Abstract

Contact dermatitis tremendously impacts the quality of life of suffering patients. Currently, diagnostic regimes rely on allergy testing, exposure specification, and follow-up visits; however, distinguishing the clinical phenotype of irritant and allergic contact dermatitis remains challenging. Employing integrative transcriptomic analysis and machine-learning approaches, we aimed to decipher disease-related signature genes to find suitable sets of biomarkers. A total of 89 positive patch-test reaction biopsies against four contact allergens and two irritants were analyzed via microarray. Coexpression network analysis and Random Forest classification were used to discover potential biomarkers and selected biomarker models were validated in an independent patient group. Differential gene-expression analysis identified major gene-expression changes depending on the stimulus. Random Forest classification identified , , , , , , , , , , , , , , , , , , , , , and as potential biomarkers to distinguish allergic and irritant contact dermatitis in human skin. Validation experiments and prediction performances on external testing datasets demonstrated potential applicability of the identified biomarker models in the clinic. Capitalizing on this knowledge, novel diagnostic tools can be developed to guide clinical diagnosis of contact allergies.

Authors

  • Vittorio Fortino
    Institute of Biomedicine, University of Eastern Finland, FI-70211 Kuopio, Finland.
  • Lukas Wisgrill
    Division of Neonatology, Pediatric Intensive Care, and Neuropediatrics, Comprehensive Center for Pediatrics, Department of Pediatrics and Adolescence Medicine, Medical University of Vienna, 1090 Vienna, Austria.
  • Paulina Werner
    Institute of Environmental Medicine, Karolinska Institutet, SE-171 77 Stockholm, Sweden.
  • Sari Suomela
    Occupational Medicine, Finnish Institute of Occupational Health, 00250 Helsinki, Finland.
  • Nina Linder
    Institute for Molecular Medicine Finland (FIMM), HiLIFE, University of Helsinki, Helsinki, Finland.
  • Erja Jalonen
    Skin and Allergy Hospital, Helsinki University Central Hospital (HUCH), 00029 HUS Helsinki, Finland.
  • Alina Suomalainen
    Department of Bacteriology and Immunology, Medicum, University of Helsinki, 00014 Helsinki, Finland.
  • Veer Marwah
    Faculty of Medicine and and Life Sciences, University of Tampere, 33520 Tampere, Finland.
  • Mia Kero
    HUSLAB, Helsinki University Hospital, 00029 HUS Helsinki, Finland.
  • Maria Pesonen
    Occupational Medicine, Finnish Institute of Occupational Health, 00250 Helsinki, Finland.
  • Johan Lundin
    Institute for Molecular Medicine Finland (FIMM), HiLIFE, University of Helsinki, Helsinki, Finland.
  • Antti Lauerma
    Skin and Allergy Hospital, Helsinki University Central Hospital (HUCH), 00029 HUS Helsinki, Finland.
  • Kristiina Aalto-Korte
    Occupational Medicine, Finnish Institute of Occupational Health, 00250 Helsinki, Finland.
  • Dario Greco
    Faculty of Medicine and Life Sciences, University of Tampere, Arvo Ylpön katu 34 - Arvo building, Tampere, FI-33014, Finland.
  • Harri Alenius
    Institute of Environmental Medicine, Karolinska Institutet, SE-171 77 Stockholm, Sweden.
  • Nanna Fyhrquist
    Institute of Environmental Medicine, Karolinska Institutet, SE-171 77 Stockholm, Sweden; nanna.fyhrquist@ki.se.

Keywords

External Resources

Popular Topics
Recent Journals