Machine learning applied to atopic dermatitis transcriptome reveals distinct therapy‐dependent modification of the keratinocyte immunophenotype*
Open accessPublished version of a preprint
Abstract
BACKGROUND: Atopic dermatitis (AD) arises from a complex interaction between an impaired epidermal barrier, environmental exposures, and the infiltration of T helper (Th)1/Th2/Th17/Th22 T cells. Transcriptomic analysis has advanced our understanding of gene expression in cells and tissues. However, molecular quantitation of cytokine transcripts does not predict the importance of a specific pathway in AD or cellular responses to different inflammatory stimuli. OBJECTIVES: To understand changes in keratinocyte transcriptomic programmes in human cutaneous disease during development of inflammation and in response to treatment. METHODS: We performed in silico deconvolution of the whole-skin transcriptome. Using co-expression clustering and machine-learning tools, we resolved the gene expression of bulk skin (seven datasets, n = 406 samples), firstly, into keratinocyte phenotypes identified by unsupervised clustering and, secondly, into 19 cutaneous cell signatures of purified populations from publicly available datasets. RESULTS: We identify three unique transcriptomic programmes in keratinocytes - KC1, KC2 and KC17 - characteristic of immune signalling from disease-associated Th cells. We cross-validate those signatures across different skin inflammatory conditions and disease stages and demonstrate that the keratinocyte response during treatment is therapy dependent. Broad-spectrum treatment with ciclosporin ameliorated the KC17 response in AD lesions to a nonlesional immunophenotype, without altering KC2. Conversely, the specific anti-Th2 therapy, dupilumab, reversed the KC2 immunophenotype. CONCLUSIONS: Our analysis of transcriptomic signatures in cutaneous disease biopsies reveals the effect of keratinocyte programming in skin inflammation and suggests that the perturbation of a single axis of immune signal alone may be insufficient to resolve keratinocyte immunophenotype abnormalities.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Clayton et al clustered 406 skin transcriptome samples from patients with AD, identifying 3 unique keratinocyte activation programs and therapy-dependent modifications.
“For instance, Clayton et al (2021) clustered 406 skin transcriptome samples from patients with AD, identifying 3 unique keratinocyte activation programs and therapy-dependent modifications.”
From Artificial intelligence–enabled precision medicine for inflammatory skin diseases (2026) · cites this paper as Clayton et al, 2021
The Abstract reports analysis of 406 bulk-skin transcriptome samples, identifies three keratinocyte programmes (KC1, KC2 and KC17), and describes therapy-dependent responses. But the 406 samples were not all from patients with AD: the Discussion also identifies healthy controls and patients with psoriasis among the samples analysed. (LLM, conf=0.90)
Experimental — accuracy not yet measuredCyclosporine primarily affected keratinocytes responding to IL-17A, whereas dupilumab specifically reversed the IL-4- and IL-13-responsive keratinocyte profile.
“For instance, they identified that cyclosporine primarily affected keratinocytes responding to IL-17A, whereas dupilumab specifically reversed the IL-4— and IL-13—responsive keratinocyte profile (Clayton et al, 2021).”
From Artificial intelligence–enabled precision medicine for inflammatory skin diseases (2026) · cites this paper as Clayton et al, 2021
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Guilloteau, K., Paris, I., Pedretti, N., Boniface, K., Juchaux, F., Huguier, V., Guillet, G., Bernard, F.-X., Lecron, J.-C., & Morel, F. (2010) · The Journal of Immunology · doi:10.4049/jimmunol.0902464 · Cited by 353 · see citing works
Cytokines IL-17 and IL-22 in the host response to infection
Valeri, M., & Raffatellu, M. (2016) · Pathogens and Disease · doi:10.1093/femspd/ftw111 · Cited by 202 · see citing works
Flagged first, then by citations
Research works printed but not linked: 40
- Biedermann T, Skabytska Y, Kaesler S, Volz T. Regulation of T cell immunity in atopic dermatitis by microbes: the yin and yang of cutaneous inflammation. Front Immunol 2015; 6:353.
- Ungar B, Garcet S, Gonzalez J et al. An integrated model of atopic dermatitis biomarkers highlights the systemic nature of the disease. J Invest Dermatol 2017; 137:603-13.
- Su arez-Fariñas M, Tintle SJ, Shemer A et al. Nonlesional atopic der- matitis skin is characterized by broad terminal differentiation defects and variable immune abnormalities. J Allergy Clin Immunol 2011; 127:954-64.e1-4.
- Guttman-Yassky E, Bissonnette R, Ungar B et al. Dupilumab pro- gressively improves systemic and cutaneous abnormalities in patients with atopic dermatitis. J Allergy Clin Immunol 2019; 143:155-72.
- Gittler JK, Shemer A, Su arez-Fariñas M et al. Progressive activation of T(H)2/T(H)22 cytokines and selective epidermal proteins char- acterizes acute and chronic atopic dermatitis. J Allergy Clin Immunol 2012; 130:1344-54.
- Mansouri Y, Guttman-Yassky E. Immune pathways in atopic der- matitis, and definition of biomarkers through broad and targeted therapeutics. J Clin Med 2015; 4:858-73.
- Ari€ ens LFM, Gadkari A, van Os-Medendorp H et al. Dupilumab ver- sus cyclosporine for the treatment of moderate-to-severe atopic dermatitis in adults: indirect comparison using the Eczema Area and Severity Index. Acta Derm Venereol 2019; 99:851-7.
- Brunner PM, Guttman-Yassky E, Leung DYM. The immunology of atopic dermatitis and its reversibility with broad-spectrum and tar- geted therapies. J Allergy Clin Immunol 2017; 139:S65-76.
- H€ onzke S, Wallmeyer L, Ostrowski A et al. Influence of Th2 cytoki- nes on the cornified envelope, tight junction proteins, and b-de- fensins in filaggrin-deficient skin equivalents. J Invest Dermatol 2016; 136:631-9.
- Nestle FO, Di Meglio P, Qin J-Z, Nickoloff BJ. Skin immune sen- tinels in health and disease. Nat Rev Immunol 2009; 9:679-91.
- Pfalzgraff A, Brandenburg K, Weindl G. Antimicrobial peptides and their therapeutic potential for bacterial skin infections and wounds. Front Pharmacol 2018; 9:281.
- Colombo I, Sangiovanni E, Maggio R et al. HaCaT cells as a reliable in vitro differentiation model to dissect the inflammatory/repair response of human keratinocytes. Mediators Inflamm 2017; 2017:1-12.
- Nakagawa S, Matsumoto M, Katayama Y et al. Staphylococcus aureus virulent PSMa peptides induce keratinocyte alarmin release to orchestrate IL-17-dependent skin inflammation. Cell Host Microbe 2017; 22:667-77.e5.
- Lai Y, Gallo RL. AMPed up immunity: how antimicrobial peptides have multiple roles in immune defense. Trends Immunol 2009; 30:131-41.
- Selsted ME, Ouellette AJ. Mammalian defensins in the antimicro- bial immune response. Nat Immunol 2005; 6:551-7.
- Nickoloff BJ, Turka LA. Immunological functions of non-profes- sional antigen-presenting cells: new insights from studies of T-cell interactions with keratinocytes. Immunol Today 1994; 15:464-9.
- Archer NK, Adappa ND, Palmer JN et al. Interleukin-17A (IL-17A) and IL-17F are critical for antimicrobial peptide production and clearance of Staphylococcus aureus nasal colonization. Infect Immun 2016; 84:3575-83.
- Dixon BREA, Radin JN, Piazuelo MB et al. IL-17a and IL-22 induce expression of antimicrobials in gastrointestinal epithelial cells and may contribute to epithelial cell defense against Helicobacter pylori. PLoS One 2016; 11:e0148514.
- Yano S, Banno T, Walsh R, Blumenberg M. Transcriptional responses of human epidermal keratinocytes to cytokine inter- leukin-1. J Cell Physiol 2008; 214:1-13.
- Sa SM, Valdez PA, Wu J et al. The effects of IL-20 subfamily cytokines on reconstituted human epidermis suggest potential roles in cutaneous innate defense and pathogenic adaptive immu- nity in psoriasis. J Immunol 2007; 178:2229-40.
- Guttman-Yassky E, Lowes MA, Fuentes-Duculan J et al. Low expression of the IL-23/Th17 pathway in atopic dermatitis com- pared to psoriasis. J Immunol 2008; 181:7420-7.
- Guttman-Yassky E, Krueger JG. Atopic dermatitis and psoriasis: two different immune diseases or one spectrum? Curr Opin Immunol 2017; 48:68-73.
- Freeman TC, Goldovsky L, Brosch M et al. Construction, visualisa- tion, and clustering of transcription networks from microarray expression data. PLoS Comput Biol 2007; 3:2032-42.
- Theocharidis A, van Dongen S, Enright AJ, Freeman TC. Network visualization and analysis of gene expression data using BioLayout Express(3D). Nat Protoc 2009; 4:1535-50.
- Chen J, Bardes EE, Aronow BJ, Jegga AG. ToppGene suite for gene list enrichment analysis and candidate gene prioritization. Nucleic Acids Res 2009; 37:W305-11.
- Supek F, Bo snjak M, Skunca N, Smuc T. REVIGO summarizes and visualizes long lists of gene ontology terms. PLoS One 2011; 6:e21800.
- Zaba LC, Su arez-Fariñas M, Fuentes-Duculan J et al. Effective treat- ment of psoriasis with etanercept is linked to suppression of IL-17 signaling, not immediate response TNF genes. J Allergy Clin Immunol 2009; 124:1022-30.e395.
- Correa da Rosa J, Kim J, Tian S et al. Shrinking the psoriasis assess- ment gap: early gene-expression profiling accurately predicts response to long-term treatment. J Invest Dermatol 2017; 137:305-12.
- Esaki H, Ewald DA, Ungar B et al. Identification of novel immune and barrier genes in atopic dermatitis by means of laser capture microdissection. J Allergy Clin Immunol 2015; 135:153-63.
- Simpson EL, Imafuku S, Poulin Y et al. A phase 2 randomized trial of apremilast in patients with atopic dermatitis. J Invest Dermatol 2019; 139:1063-72.
- Pavel AB, Song T, Kim HJ et al. Oral janus kinase/SYK inhibition (ASN002) suppresses inflammation and improves epidermal bar- rier markers in patients with atopic dermatitis. J Allergy Clin Immunol 2019; 144:1011-24.
- Bigler J, Rand HA, Kerkof K et al. Cross-study homogeneity of pso- riasis gene expression in skin across a large expression range. PLoS One 2013; 8:e52242.
- Khattri S, Shemer A, Rozenblit M et al. Cyclosporine in patients with atopic dermatitis modulates activated inflammatory pathways and reverses epidermal pathology. J Allergy Clin Immunol 2014; 133:1626-34.
- Hamilton JD, Su arez-Fariñas M, Dhingra N et al. Dupilumab improves the molecular signature in skin of patients with moder- ate-to-severe atopic dermatitis. J Allergy Clin Immunol 2014; 134:1293-300.
- Brunner PM, Pavel AB, Khattri S et al. Baseline IL-22 expression in patients with atopic dermatitis stratifies tissue responses to fezak- inumab. J Allergy Clin Immunol 2019; 143:142-54.
- Newman AM, Liu CL, Green MR et al. Robust enumeration of cell sub- sets from tissue expression profiles. Nat Methods 2015; 12:453-7.
- Brunner PM, Emerson RO, Tipton C et al. Nonlesional atopic der- matitis skin shares similar T-cell clones with lesional tissues. Allergy 2017; 72:2017-25.
- Tang TS, Bieber T, Williams HC. Are the concepts of induction of remission and treatment of subclinical inflammation in atopic der- matitis clinically useful? J Allergy Clin Immunol 2014; 133:1615-25.e1.
- Lessard JC, Piña-Paz S, Rotty JD et al. Keratin 16 regulates innate immunity in response to epidermal barrier breach. Proc Natl Acad Sci U S A 2013; 110:19537-42.
- Rorke EA, Adhikary G, Young CA et al. Structural and biochemical changes underlying a keratoderma-like phenotype in mice lacking suprabasal AP1 transcription factor function. Cell Death Dis 2015; 6: e1647.
Cited by
Sorted by citations
Artificial intelligence–enabled precision medicine for inflammatory skin diseases
Tang, A. S., Wei, M. L., Haemel, A., La, C., Sirota, M., & Lee, E. Y. (2026) · Journal of Investigative Dermatology · doi:10.1016/j.jid.2025.10.596 · Cited by 6 · see citing works
- Authors
- Clayton, K., Vallejo, A., Sirvent, S., Davies, J., Porter, G., Reading, I. C., Lim, F., Ardern‐Jones, M. R., & Polak, M. E.
- Affiliations
- University of Southampton (GB)
- National Institute for Health and Care Research (GB)
- Unilever (United Kingdom) (GB)
- University Hospital Southampton NHS Foundation Trust (GB)
- Corresponding author
- Polak, M.E.
- Venue
- British Journal of Dermatology
- Publisher
- Oxford University Press (OUP)
- Published
- 2020-09-20
- Volume
- 184
- Issue
- 5
- Pages
- 913-922
- ISSN
- 0007-0963 (ISSN-L)
- 1365-2133
- OpenAlex
- W3046538729
- Cited by
- 28
- References
- 2
- Citations by year
- 2026: 7 · 2025: 6 · 2024: 4 · 2023: 4 · 2022: 3 · 2021: 2 · 2020: 2
- FWCI
- 2.01
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Locations
- British Journal of Dermatology (publishedVersion, cc-by)
- medRxiv (acceptedVersion)
- PubMed (publishedVersion)
- ePrints Soton (University of Southampton) (acceptedVersion)
- Funders
- Medical Research Council (MR/N014308/1)
- Topics
- Health Sciences › Medicine › Dermatology › Dermatology and Skin Diseases
- Life Sciences › Immunology and Microbiology › Immunology › Psoriasis: Treatment and Pathogenesis
- Health Sciences › Medicine › Physiology › Asthma and respiratory diseases
- Keywords
- atopic dermatitis, keratinocytes, skin transcriptome, cytokine gene expression, cyclosporine, dupilumab, skin inflammation, gene expression signatures, machine learning
- MeSH terms
- Machine Learning, Dermatitis, Atopic, Humans, Skin, Keratinocytes, Th2 Cells, Transcriptome
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
