Machine learning applied to atopic dermatitis transcriptome reveals distinct therapy‐dependent modification of the keratinocyte immunophenotype
Machine learning applied to atopic dermatitis transcriptome reveals distinct therapy‐dependent modification of the keratinocyte immunophenotype
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.
913–922
Clayton, Kalum
499fec32-9297-45bd-9207-5ba699734844
Pulido, Andres Vallejo
27bc0b94-0c40-4fd1-9533-7e267d588c0a
Bernal, Sofia Sirvent
c8c68bc8-a5a7-456d-899d-6e48ccfac02f
Davies, James David
a93b4fc9-80a2-4620-ada6-c12f05c5ee38
Douilhet, Gemma
5f0c0ee9-ed05-41de-8552-8ad7390fc7a8
Reading, Isabel
6f832276-87b7-4a76-a9ed-b4b3df0a3f66
Lim, Fei Ling
5d565505-ce8e-40e3-8418-3e9875255629
Ardern-Jones, Michael
7ac43c24-94ab-4d19-ba69-afaa546bec90
Polak, Marta
e0ac5e1a-7074-4776-ba23-490bd4da612d
Clayton, Kalum
499fec32-9297-45bd-9207-5ba699734844
Pulido, Andres Vallejo
27bc0b94-0c40-4fd1-9533-7e267d588c0a
Bernal, Sofia Sirvent
c8c68bc8-a5a7-456d-899d-6e48ccfac02f
Davies, James David
a93b4fc9-80a2-4620-ada6-c12f05c5ee38
Douilhet, Gemma
5f0c0ee9-ed05-41de-8552-8ad7390fc7a8
Reading, Isabel
6f832276-87b7-4a76-a9ed-b4b3df0a3f66
Lim, Fei Ling
5d565505-ce8e-40e3-8418-3e9875255629
Ardern-Jones, Michael
7ac43c24-94ab-4d19-ba69-afaa546bec90
Polak, Marta
e0ac5e1a-7074-4776-ba23-490bd4da612d
Clayton, Kalum, Pulido, Andres Vallejo, Bernal, Sofia Sirvent, Davies, James David, Douilhet, Gemma, Reading, Isabel, Lim, Fei Ling, Ardern-Jones, Michael and Polak, Marta
(2021)
Machine learning applied to atopic dermatitis transcriptome reveals distinct therapy‐dependent modification of the keratinocyte immunophenotype.
British Journal of Dermatology, 184 (5), .
(doi:10.1111/bjd.19431).
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.
Text
bjd.19431
- Accepted Manuscript
Text
bjd0913
- Version of Record
More information
Accepted/In Press date: 30 July 2020
e-pub ahead of print date: 1 May 2021
Identifiers
Local EPrints ID: 443532
URI: http://eprints.soton.ac.uk/id/eprint/443532
ISSN: 0007-0963
PURE UUID: e93c6abb-be6e-4bd4-8091-d2dffa6ca688
Catalogue record
Date deposited: 28 Aug 2020 16:31
Last modified: 10 Apr 2024 04:02
Export record
Altmetrics
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics
