Transcriptional Programming of Normal and Inflamed Human Epidermis at Single-Cell Resolution

Abstract

Perturbations in the transcriptional programs specifying epidermal differentiation cause diverse skin pathologies ranging from impaired barrier function to inflammatory skin disease. However, the global scope and organization of this complex cellular program remain undefined. Here we report single-cell RNA sequencing profiles of 92,889 human epidermal cells from 9 normal and 3 inflamed skin samples. Transcriptomics-derived keratinocyte subpopulations reflect classic epidermal strata but also sharply compartmentalize epithelial functions such as cell-cell communication, inflammation, and WNT pathway modulation. In keratinocytes, ∼12% of assessed transcript expression varies in coordinate patterns, revealing undescribed gene expression programs governing epidermal homeostasis. We also identify molecular fingerprints of inflammatory skin states, including S100 activation in the interfollicular epidermis of normal scalp, enrichment of a CD1C⁺CD301A⁺ myeloid dendritic cell population in psoriatic epidermis, and IL1β^hiCCL3^hiCD14⁺ monocyte-derived macrophages enriched in foreskin. This compendium of RNA profiles provides a critical step toward elucidating epidermal diseases of development, differentiation, and inflammation.

Keywords: epidermis; keratinocyte; single-cell RNA-seq; skin.

Figure 1.. Unbiased Classification of Epidermal Cell Subpopulations in Human Skin

(A) t-SNE maps show the relatedness of epidermal cell groups distinguished by spectral clustering from three aggregated samples each from foreskin (26,174 cells), trunk (25,129 cells), and scalp (20,561 cells) (see also Figures S1, S4, and S5 and Data S1). Cells in eight of the 11 clusters express high levels of keratins, identifying them as keratinocytes. Two groups representing melanocytes are coded in brown, and the initial immune cell cluster is depicted in red. (B) Genes with log fold change > 1 in at least 1 cluster ordered by cluster (x axis) and fold change (y axis) (Tables S1, S2, S3, and S6). Genes only appear once, in the first cluster (from bottom to top), where their log fold change passes the threshold. Two genes with specificity for each cluster are named, and their respective coordinates are highlighted with black circles.

Figure 2.. Enrichment of WNTI and Follicular Clusters in Scalp Epidermis

(A) Fraction of cells from each anatomic site or psoriatic skin belonging to each cluster. (B) Log ratio of the observed number of cells from an anatomic site or psoriatic skin in the cluster to the expected number when sampling cells in cluster uniformly without replacement. Positive and negative log ratios indicate cluster enrichment and depletion for anatomic site or psoriatic skin. All tissue and cluster associations with solid fill bars are significant (p_adj < 0.05, Pearson’s chi-square test with Bonferroni adjustment).

Figure 3.. Coordinate, Finely Distinguished Kinetics of Gene Expression in Differentiating Scalp Keratinocytes

(A) Top left: the longest pseudotime reconstruction of differentiation (line ending in purple granular cells) defines basic keratinocyte differentiation used in the other panels. Other pseudotime lines show distinct differentiation pathways from basal cells to WNTI, follicular, and channel cells. In the remaining five panels, the leftmost section shows transcript abundance (in imputed counts/10,000, y axis) in about 21,000 pseudotime-ordered differentiating scalp keratinocytes on the x axis, from left to right. Also charted are transcript levels in WNTI, follicular, and channel cells in the remaining 3 sections. Left center and left bottom: genes distinguishing the WNTI and channel clusters, respectively. Right: distinct kinetics of differentiation-dependent transcript regulation. (B) RNA in situ hybridization staining (red channel) confirms the layer specificity of genes identified in this report: basal layer POSTN, spinous layer LY6D, and spinous and granular layer NUPR1. The blue channel represents DAPI staining. Scale bars, 50 μm. See also Figure S2.

Figure 4.. Distinctive Epidermal Cell Subpopulations in Human Scalp Corresponding to Follicular and Interfollicular Keratinocytes

The t-SNE map shows spectral clustering of scalp keratinocytes into 15 groups (Table S4), which reveal correlates of outer and inner bulge cells, sebaceous gland cells, upper follicular epithelium, and also recapitulation of multi-site interfollicular epithelium strata. *These cell clusters could not be confidently assigned locations and are not depicted in the follicle diagram. See also Figure S2 and Data S1.

Figure 5.. Inflammatory S100 and IFI27 Elevation in Human Scalp and Psoriatic Skin

(A–D) Heatmaps showing fold change of differential gene expression, by cluster, for (A) foreskin, (B) trunk, and (C) scalp, each relative to the other anatomic sites. In (D), psoriatic epidermal subpopulations are compared only with normal trunk. In each cluster, limma-trend was used to calculate the fold change and statistical significance of the difference in the mean expression of each gene for each tissue comparison based on non-imputed UMI counts per million (Table S5). Genes with a log₂ fold change (FC) greater than 1.5 (scalp and foreskin) or 2.5 (psoriasis) and false discovery rate (FDR) < 0.05 in at least one cluster are displayed (Experimental Procedures; Tables S5, S6, and S7). An elevated RPS4Y1 transcript in all foreskin clusters confirms Y chromosome-specific bias for sex.

Figure 6.. Unbiased Detection of T Cells, Macrophages, and Dendritic Cells in Normal and Inflamed Epidermis

The t-SNE map shows spectrally clustered hematopoietic cell populations from all 12 of our normal and inflamed epidermal samples. The spatial adjacency of Langerhans cells, dendritic cells, and macrophages illustrates their relatedness compared with T cells (purple) and a small number of keratinocytes expressing inflammatory transcripts and, thus, misclassified with immune cells (red). See also Table S8 and Data S1.

Figure 7.. Enriched Antigen-Presenting Cells in Psoriatic Epidermis and Macrophages in Foreskin

(A) A fraction of cells from each anatomic site or psoriatic skin belonging to each immune cluster. (B) Log ratio of the observed number of cells from anatomic site or psoriatic skin in cluster to the expected number when sampling cells in the cluster uniformly without replacement. Positive and negative log ratios indicate cluster enrichment and depletion for anatomic site or psoriatic skin. All tissue and cluster associations with solid fill bars are significant (p_adj < 0.05, Pearson’s chi-square test with Bonferroni adjustment). No trunk cells occurred in the macrophage cluster, so a pseudo-count of 1 cell was added to allow illustration of the log₂ fold depletion.