Injury prevents Ras mutant cell expansion in mosaic skin

Abstract

Healthy skin is a mosaic of wild-type and mutant clones^1,2. Although injury can cooperate with mutated Ras family proteins to promote tumorigenesis^3-12, the consequences in genetically mosaic skin are unknown. Here we show that after injury, wild-type cells suppress aberrant growth induced by oncogenic Ras. Hras^G12V/+ and Kras^G12D/+ cells outcompete wild-type cells in uninjured, mosaic tissue but their expansion is prevented after injury owing to an increase in the fraction of proliferating wild-type cells. Mechanistically, we show that, unlike Hras^G12V/+ cells, wild-type cells respond to autocrine and paracrine secretion of EGFR ligands, and this differential activation of the EGFR pathway explains the competitive switch during injury repair. Inhibition of EGFR signalling via drug or genetic approaches diminishes the proportion of dividing wild-type cells after injury, leading to the expansion of Hras^G12V/+ cells. Increased proliferation of wild-type cells via constitutive loss of the cell cycle inhibitor p21 counteracts the expansion of Hras^G12V/+ cells even in the absence of injury. Thus, injury has a role in switching the competitive balance between oncogenic and wild-type cells in genetically mosaic skin.

Fig. 1. Injury-induced aberrant growth of Hras^G12V/+ cells is suppressed in mosaic skin.

a, Left, cartoon depicting the 4-mm full-thickness wound (W) on a mouse ear and the imaged area. Centre, top-down (x–y; top) and transverse (x–z; bottom) views of a two-photon image of the skin epithelium at 14 days PWI from a Krt14-CreER; LSL-tdTomato; Krt14-H2B–GFP mouse (asterisks, hair canals; dashed lines, basement membrane in x–z view and wound edge in x–y view). Centre middle, cartoon schematic of wild-type (green) and recombined cells (red) after tamoxifen injection around the injury. Right, magnification of top-down (x–y) and transverse (x–z) views of the skin epithelium show epithelial cell nuclei (Krt14-H2B–GFP) in green and recombined cells expressing tdTomato in red (dashed lines mark the transversal section in the x–y view and the basement membrane in the x–z view). b, The initial tdTomato⁺ area 3 days PWI (n = 4 wild-type mosaic and Hras^G12V/+ mosaic mice and n = 5 Hras^G12V/+ max mice). At least three independent areas of approximately 300 μm² were analysed for each mouse (Methods). Data are mean ± s.d. c, Heat maps of the top-down (x–y) view of representative two-photon images adjacent to the injury at 14 days PWI (dashed lines highlight the wound edge). Colour represents the thickness of the epithelium and identifies the presence of aberrant growth. d, The thickness of the epithelium at 14 days PWI around the wound. Solid lines represent means and dashed lines show s.d. n = 4 wild-type mosaic and Hras^G12V/+ mosaic mice and n = 5 Hras^G12V/+ max mice. Source Data

Fig. 2. Injury repair alters the competitive balance between wild-type and Hras^G12V/+ cells in mosaic skin.

a, Schematic of the experimental design using the injury repair model. b, Representative two-photon revisit images of the basal stem cell layer of the epidermis. White lines highlight the boundaries between tdTomato⁺ and tdTomato⁻ populations. Epithelial nuclei are in green (Krt14-H2B–GFP) and recombined cells are in red (LSL-tdTomato). c, The increase in tdTomato⁺ area over time in the uninjured condition. n = 3 mice. d, Representative two-photon revisit images of the basal stem cell layer of the epidermis during injury repair. e, The increase in tdTomato⁺ area over time in the injured condition. n = 4 mice. Unpaired, two-tailed t-test comparing wild-type with Hras^G12V/+ mice at different time points in uninjured and injured conditions. P values are shown. At least three independent areas of approximately 300 µm² were analysed for each mouse (Methods). Data are mean ± s.d. *P < 0.05, **P < 0.01, ***P < 0.001, ****P < 0.0001; NS, not significant. Source Data

Fig. 3. Injury selectively induces the proliferation of wild-type cells in Hras^G12V/+ mosaic skin.

a, Representative two-photon images of the epidermal preparation, immunostained for p-histone H3 (highlighted by white dashed circle). b, Quantification of p-histone H3-positive (p-H3⁺) cells in tdTomato⁺ and tdTomato⁻ populations in injured (I) and uninjured (U) skin. n = 4 mice. c,d, Quantification of mitotic cells in uninjured (c) and uninjured (d) ears. n = 4 mice. e, Representative two-photon images of the epidermal preparation, immunostained for keratin-10 (white). f, Quantification of keratin-10-positive (KRT10⁺) cells in tdTomato⁺ and tdTomato⁻ populations in injured and uninjured skin. n = 3 mice. b–d,f, Paired or unpaired two-tailed t-test for comparison between tdTomato⁺ and tdTomato⁻ populations in the same group or in different groups of mice. At least three independent areas of approximately 300 µm² were analysed for each mouse (Methods). KRT10, keratin-10. g, Uniform manifold approximation and projection (UMAP) showing epidermal keratinocyte clusters from uninjured and injured conditions. h, Violin plots (left) showing gene expression in clusters from g, together with the gene expression superimposed on the UMAP (right). i, Cell classification into homeostatic and injury-responsive populations based on clustering and gene expression, overlaid on the UMAP. g–i, n = 12 mice. j, Quantification of wild-type and Hras^G12V/+ cells as a proportion of tdTomato⁺ cells in basal non-committed and basal committed groups for homeostatic and injury-responsive cells. Data are averaged results for each biological replicate. One-sided t-test with Holm–Sidak correction. k, Violin plots showing Krt6a and Krt10 expression in cells grouped as in j. In h,k, internal box plots denote the 25th, 50th and 75th centiles, with whiskers depicting minima and maxima, excluding outliers that are beyond 1.5× the interquartile range. j,k, Homeostatic cells from n = 12 mice and injury-responsive cells from n = 6 mice. P values are shown. Data are mean ± s.d. Source Data

Fig. 4. Kras^G12D/+ cells lose their competitive advantage during injury repair of mosaic skin.

a, Representative two-photon revisit images of the epidermal basal stem cell layer. White lines mark borders between mutant and wild-type cells. b, The increase in tdTomato⁺ area in uninjured and injured conditions following induction with tamoxifen (uninjured Kras^G12D/+ mosaic, n = 4 mice; injured Kras^G12D/+ mosaic, n = 5 mice). c, Quantification of mitotic cells in tdTomato⁺ and tdTomato⁻ areas. Uninjured Kras^G12D/+ mosaic, n = 4 mice; injured Kras^G12D/+ mosaic, n = 5 mice. d, Heat maps of the top-down (x–y) view of representative two-photon images around the injury at 14 days PWI. Colour represents the thickness of the epithelium. e, Average epithelial thickness at 14 days PWI around the wound in wild-type (n = 3 mice), Kras^G12D/+ mosaic (n = 4 mice) and Kras^G12D/+ max (n = 3 mice). Solid lines represent means and dashed lines show s.d. b,c, Paired two-tailed t-test comparing tdTomato⁺ and tdTomato⁻ populations in the same group of mice. Unpaired two-tailed t-test comparing tdTomato⁺ and tdTomato⁻ populations in different groups of mice and Kras^G12D/+ mutant mice in uninjured and injured conditions at different time points. P values are shown. At least three independent areas of approximately 300 µm² were analysed for each mouse (Methods). Data are mean ± s.d. Source Data

Fig. 5. Increased proliferation of wild-type cells is sufficient to counteract expansion of Hras^G12V/+ cells in mosaic skin.

a, Violin plots showing cell scoring based on expression of EGFR ligands (Extended Data Fig. 6i), separated by cell type and genotype. Two-tailed t-test comparing the averages of biological replicates according to conditions (fibroblasts: n = 3 wild-type mosaic and n = 6 Hras^G12V/+ mosaic; epithelial cells n = 6 mice per genotype), P values are shown. Internal box plots denote the 25th, 50th and 75th centiles, with whiskers depicting minima and maxima, excluding outliers that are beyond 1.5× the interquartile range. b, Western blot analysis (left) and quantification (middle) of phosphorylated EGFR (p-EGFR) and total EGFR in injured and uninjured conditions (n = 3 mice). Paired, two-tailed t-test. Pairs of coloured dots represent ratios for individual mice. Right, western blot analysis of total EGFR normalized to GAPDH (n = 3 mice). Blots were processed at the same time. Unpaired, two-tailed t-test. c, Quantification of mitotic cells in tdTomato⁺ and tdTomato⁻ areas. d, Left, representative two-photon revisit images following injury. Right, the increase in tdTomato⁺ area after tamoxifen induction. In c,d, vehicle, n = 3 mice; Gefitinib, n = 4 mice. e, Quantification of mitotic cells in tdTomato⁺ and tdTomato⁻ areas in wild-type mosaic (n = 3 mice), Hras^G12V/+ mosaic (n = 3 mice) and constitutive p21-null Hras^G12V/+ mosaic (n = 4 mice). f, Quantification of p-histone H3-positive cells in tdTomato⁺ and tdTomato⁻ areas (n = 6 mice). g, Representative two-photon revisit images following injury in wild-type mosaic, Hras^G12V/+ mosaic and constitutive p21^null-Hras^G12V/+ mosaic mice. h, The increase in tdTomato⁺ area. Unpaired, ordinary one-way ANOVA comparing wild-type mosaic, Hras^G12V/+ mosaic and constitutive p21^null-Hras^G12V/+ mosaic at different time points in the uninjured condition. In g,h, n = 3 wild-type mosaic mice, n = 3 Hras^G12V/+ mosaic mice and n = 4 constitutive p21^null-Hras^G12V/+ mosaic mice. c–f, Unpaired or paired two-tailed t-test for comparisons between different groups or within the same group of mice. P values are shown. At least three independent areas of approximately 300 µm² were analysed for each mouse (Methods). Data are mean ± s.d. Source Data

Extended Data Fig. 1. Injury induces tumors only in Hras^G12V/+-max models.

a) Skin tissue architecture cartoon schematic. b, c, d) H&E staining of uninjured and injured ear skin within 2 weeks PWI with magnified insets. n = 5 wild-type, n = 5 Hras^G12V/+-max and n = 4 Hras^G12V/+-mosaic. b) Wild-type tissue exhibits normal histology (left) and injured tissues (right) demonstrates mixed inflammatory infiltrate and increased fibroblast number consistent with early scar tissue. c) Hras^G12V/+-mosaic uninjured tissue (left) shows normal histology. Injured ear (right) exhibits dermal fibrosis consistent with normal scar tissue. d) Hras^G12V/+-max uninjured tissue (left) with normal epithelial thickness and differentiation with mild orthokeratotic hyperkeratosis (stratum corneum thickening with normal basket-weave appearance). In the Hras^G12V/+-max injured ear (right) adjacent to the wound there is notable acanthosis and hypergranulosis of the epithelium with compact orthokeratotic hyperkeratosis. Cytologic atypia is present. e) Aberrant growth in the injured-Hras^G12V/+-max model in contrast to the normal epithelium in the injured-Hras^G12V/+-mosaic model (day-14 PWI). f) (right) Heat maps of epithelial thickness in the top-down (x-y) view of representative two-photon images adjacent to injury in the back skin of Hras^G12V/+-mosaic and Hras^G12V/+-max identifying aberrant growth. Scale bar, 100 μm. (left) Quantification of average epithelial thickness 14 days PWI at different distances from wound edge in Hras^G12V/+-mosaic and Hras^G12V/+-max. n = 3 mice (mean±s.d.). g, h) H&E staining of injured back skin within two weeks PWI. n = 3 mice. g) Hras^G12V/+-mosaic injured back shows skin dermal fibrosis with vertically oriented blood vessels consistent with scar. The overlying epidermis is normal thickness with orthokeratosis. h) Hras^G12V/+-max injured back skin with dermal scar and the overlying epidermis is characterized by hyperkeratosis and papillomatosis. i) Aberrant growth around the wound of the Hras^G12V/+-max model in contrast to the normal epithelium of the Hras^G12V/+-mosaic model. Source Data

Extended Data Fig. 2. Injury suppresses Hras^G12V/+ cell expansion in mosaic skin with a low mutational burden.

a) Two-photon revisit images of the same area of the basal stem cell layer of the epidermis in wild-type-mosaic and Hras^G12V/+-mosaic at 3 and 14 days PWI. Dashed lines, wound edge; white squares, three representative regions tracked and quantified to measure the percent tdTomato+ area. The hair follicle pattern was used to revisit the exact same area of the skin (*=hair canals). Scale bar, 100 μm. b) Quantification of the initial percent tdTomato+ area 6 days post-tamoxifen injection in the uninjured condition. n = 3 mice. c) Representative two-photon revisit images of the same tdTomato+ clone revisited in the basal stem cell layer of the epidermis infected with lentiviral(LV)-CreER. d) Quantification of the relative ratio of the tdTomato+ area at different time points compared to the initial clone size at 6 days post-tamoxifen injection. Relative ratio was used to consider the different initial sizes of the analyzed clones. The initial clone size was between 2 to ~50 cells. n = 3 mice. e) Representative two-photon revisit images of the same tdTomato+ clone in the basal stem cell layer of the epidermis infected with LV-CreER. f) Same quantification as in d). n = 3 mice. (d, f) Statistics: Unpaired, two-tailed t-test between wild-type and mutant mice at different time points in uninjured and injured conditions. Exact p-value reported on the figure. ns indicates not statistically significant. At least three independent tdTomato+ clones were analysed for each mouse. Data are represented as means and standard deviations. Scale bar, 20 μm. Source Data

Extended Data Fig. 3. Selective increase of wild-type cell proliferation in the acute phase of injury-repair of mosaic skin.

a, b) Representative two-photon images of mitotic figures (white circles). c) Quantification of mitotic figures in tdTomato+ and tdTomato− areas in injured (I; n = 4 mice) and uninjured (U; n = 3 mice) wild-type and Hras^G12V/+-mosaic. d) Representative two-photon images of apoptotic bodies (white circles) and quantification in tdTomato+ and tdTomato− areas in injured (I) and uninjured (U) wild-type and Hras^G12V/+-mosaic. n = 4 mice. e) Representative two-photon images of the epidermal preparation immunofluorescence for active-Caspase-3 (white circle) and quantification of active-Caspase3+ cells in tdTomato+ and tdTomato− areas in injured (I) and uninjured (U) wild-type and Hras^G12V/+-mosaic. n = 3 mice. f) Quantification of apoptotic bodies over time in tdTomato+ and tdTomato− areas in uninjured ears. Statistic between wild-type-mosaic and Hras^G12V/+-mosaic in tdTomato− or tdTomato+ areas are represented with green or red dotted lines. g) Same quantification as in f) in injured ears. (f, g) n = 4 mice. h) β-galactosidase activity assay of epidermal preparations of uninjured and injured wild-type and Hras^G12V/+-mosaic and positive controls: pancreas, kidney and provided by the kit. n = 3 mice for epidermal preparations. i) Quantification of cells expressing Keratin10 in tdTomato+ and tdTomato− areas in injured (I) wild-type and Hras^G12V/+-mosaic. n = 3. Statistics: Paired, two-tailed t-test, comparing tdTomato+ and tdTomato− areas in the same group of mice. Unpaired, two-tailed t-test comparing tdTomato+ and tdTomato− populations in different groups of mice. Exact p-value reported on the figure. ns indicates not statistically significant. At least three independent areas of approximately 300 μm² were analysed for each mouse (see Methods). Data are represented as means and standard deviations. Scale bar, 20 μm. Source Data

Extended Data Fig. 4. Characterization of scRNA-seq datasets of wild-type-mosaic and Hras^G12V/+-mosaic cells in uninjured or injured condition.

a) Violin plots showing quality control metrics for each sample. All the box plots within violin plots denote the 25%, 50% and 75% quartiles with whiskers depicting the minima and maxima of the data, excluding outliers that are beyond 1.5x interquartile range. b) UMAP displaying the main cell populations of the integrated dataset (left), and dot-plot showing characteristic marker-gene expression (right). c) UMAPs showing the distribution of interfollicular epidermal (IFE) keratinocytes of the different conditions, coloured according to biological replicates. Grey cells denote all keratinocytes. d) Abstracted graph of neighbourhoods superimposed on IFE UMAP, showing differential abundance testing results from MiloR. Node sizes represent the size of the neighbourhood and edges indicate number of cells common between neighbourhoods. Neighbourhoods displaying significant differential abundance are coloured according to the log-foldchange of the differential abundance testing. e) Micrographs showing Keratin6a protein expression in uninjured and injured ear tissue. W – wound, scale bar, 500 μm. n = 3 mice. f, g, h) UMAPs showing cell classification into basal non-committed, basal committed, and delaminated populations (f), cell cycle phase (g) and cell classification based on tdTomato expression (h). i, j) Bar plots showing top GO terms (upper) for differentially up-regulated genes comparing Hras^G12V/+ and wild-type-mosaic cells in uninjured (i) or injured (j) condition. Respective differential gene expression analysis is shown on volcano plots (lower) with log2 fold-changes on x-axis and -log10(adjusted p-values) on y-axis. Genes were considered differentially expressed (orange dots) when they were expressed in >25% of cells in each of the compared biological replicate, had absolute log-foldchange > 0.5 and adjusted p-value < 0.05 (Wilcoxon rank-sum test with Benjamini-Hochberg correction). a-d, f-j) n = 12 independently sequenced mice (3 mice per condition and genotype). Source Data

Extended Data Fig. 5. Kras^G12D/+-max models display rapid oncogenic growth after injury.

a) Quantification of the initial percent tdTomato+ area in the first revisit of Kras^G12D/+-mosaic in uninjured (n = 4 mice) and injured (n = 5 mice) conditions and Kras^G12D/+-max in injured (n = 3 mice) condition. At least three independent areas of approximately 300 μm² were analysed for each mouse (Methods). Data are represented as means and standard deviations. b, c) Histopathologic examination via H&E staining of uninjured and injured ear skin within 2 weeks PWI. n = 4 Kras^G12D/+-mosaic, n = 5 Kras^G12D/+-max. b) Kras^G12D/+-mosaic (left) in uninjured ear skin with normal epithelium, dermis and cartilage and injured ear (right) showing mixed inflammatory cell infiltrate and increased number of fibroblasts consistent with early scar tissue. c) Kras^G12D/+-max uninjured ear (right) showing normal epithelial thickness and architecture. This is in comparison to the injured ear (left) showing significant expansion of the epithelial layer with hypergranulosis, focal parakeratosis alternative to the compact hyperkeratin. Focal cytologic atypia is present. Scale bars indicated on the figure. Magnified insets of the epidermis in the lower left corner of each image. d) Macroscopic image of the aberrant growth around the wound of the Kras^G12D/+-max model in contrast to the normal epithelium of the Kras^G12V/+-mosaic model. Source Data

Extended Data Fig. 6. scRNA-seq fibroblast subcluster analysis reveals increased EGFR-ligand expression upon injury.

a) Violin plots showing quality control metrics for each individual sample. b) Unsupervised clustering of sampled fibroblasts. c) Marker gene expression in fibroblast subclusters overlaid on UMAP. d) Distribution of cells from different mouse models among fibroblast clusters (n = 3 mice for each condition). Grey dots denote all cells. Hras^G12V/+ and wild-type models have a similar distribution of cells in four clusters, depending on the tamoxifen treatment and the presence or not of the wound. e) UMAP showing cell-cycle classification (left) and injury response status (right). f) Dot-plot showing marker gene expression for the fibroblast subclusters. g) Volcano plot of differential gene expression profiles between fibroblasts from homeostatic and injured conditions showing the magnitude on the x-axis (Log2 fold change) and significance on the y-axis (-Log10 adjusted p-value, Wilcoxon rank-sum test with Benjamini-Hochberg correction). Red dots mark the 50 highest differentially expressed genes. Red names highlight the highest differentially expressed growth factors that affect epithelial cell behaviors. Blue dots with blue names represent other growth factors that take part in injury-repair and black dots with black names indicate genes involved in cell proliferation. h) Violin plots of EGFR ligands that affect epithelial cell behaviors. Analysis is based on all mouse models combined. i) Violin plots that compare homeostatic and injury-responsive cells for the expression of EGFR ligands with a significantly different expression in (h). n = 3 mice per group. (a, h, i) Internal box plots denote the 25%, 50% and 75% quartiles with whiskers depicting the minima and maxima of the data, excluding outliers that are beyond 1.5x interquartile range. Statistics: two-tailed t-test comparing the averages of biological replicates according to conditions. (a-h) n = 24 independently sequenced mice (3 mice per condition and genotype, note that some samples did not contain fibroblasts; ‘mosaic samples’ are the same as in Extended Data Fig. 4).

Extended Data Fig. 7. scRNA-seq immune cell subcluster analysis shows limited EGFR-ligand expression upon injury.

a) Violin plots showing quality control metrics for each individual sample. b) Annotation of cluster identities based on marker gene expression. c) Unsupervised clustering of sampled immune cells (see Methods). d) Distribution of cells from different mouse models among the identified immune cell clusters (n = 3 mice for each condition). e) UMAP representations of cell cycle classification (top) and injury status of the dataset (bottom). f) Violin plots showing immune cell EGFR ligand expression for all datasets combined (n = 24 mice, top) and comparison between wild-type-mosaic and Hras^G12V/+-mosaic datasets (n = 6 mice per group, bottom). g) Violin plots showing epidermal (i.e.: IFE) EGFR ligand expression for all datasets combined (n = 12 mice, top) and comparison between wild-type-mosaic and Hras^G12V/+-mosaic datasets (n = 6 mice per group, bottom). (a, f, g) Internal box plots denote the 25%, 50% and 75% quartiles with whiskers depicting the minima and maxima of the data, excluding outliers that are beyond 1.5x interquartile range. (f, g) Statistics: two-tailed t-test comparing the means of biological replicates according to conditions. (a-f) n = 24 independently sequenced mice (3 mice per condition and genotype; ‘mosaic samples’ are the same as in Extended Data Figs. 4, 6).

Extended Data Fig. 8. EGFR/Ras pathway is required to selectively increase wild-type cell proliferation after injury.

a) Schematic representation of the EGFR signaling pathway. Hras^G12V is constitutively active and therefore less dependent on upstream activation of EGFR. b) Western blot analysis of p-EGFR(phospho-Tyr1068) normalized on total-EGFR (n = 6 mice) and of p-ERK1/2(phospho-Thr202/Tyr204) and p-AKT(phospho-Ser473) normalized on total-ERK1/2 and total-AKT (n = 3 mice). Unpaired, two-tailed t-test. c) Mitotic figure quantification in tdTomato+ and tdTomato− areas in Hras^G12V/+-mosaic without or with EGFR-Dominant Negative (DN) expression (EGFR-WT or EGFR-DN). n = 3 mice. Unpaired or Paired two-tailed t-test for comparison between different or the same groups of mice. d) Revisit images of the same area of the basal stem cell layer. (left) The increase of tdTomato+ area. n = 3 mice. Unpaired, two-tailed t-test. e) Initial percent tdTomato+ area in the first revisit of injured-Hras^G12V/+-mosaic treated with vehicle (n = 3 mice) or Gefitinib (n = 4 mice). f) Epidermal preparation immunofluorescence for phospho-Histone3 in wild-type (left) and constitutive-p21^null (right) at postnatal-day-25. g) Phospho-Histone3+ cell quantification in wild-type, constitutive-p21^null with or without LSL-tdTomato at postnatal-day-25 (n = 3 mice). Unpaired, two-tailed t-test. h) Whole mount immunofluorescence for phospho-Histone3 in wild-type (left) and constitutive-p21^null (right) at postnatal-day-25. Phospho-Histone3+ dermal cell quantification (n = 4 mice). Unpaired, two-tailed t-test. i) Initial percent tdTomato+ area in the first revisit of uninjured wild-type-mosaic (n = 3 mice), Hras^G12V/+-mosaic (n = 3 mice) and constitutive-p21^null-Hras^G12V/+-mosaic (n = 4 mice). j) Keratin10+ cell quantification in tdTomato+ and tdTomato− areas in Hras^G12V/+-mosaic and constitutive-p21^null-Hras^G12V/+-mosaic in uninjured(U) ears (n = 3 mice). Unpaired or Paired two-tailed t-test for comparison between different or the same groups of mice. Exact p-values reported on the figure. ns indicates not statistically significant. At least three independent areas of approximately 300 μm² were analysed for each mouse (Methods). Data are represented as means and standard deviations. Scale bar, 20 μm. Source Data

Extended Data Fig. 9. p21 expression is significantly reduced in Hras^G12V/+-mosaic models.

a) Representative two-photon images of the epidermal preparation immunofluorescence for p21 (white) in constitutive-p21^null (left), wild-type-mosaic (center) and Hras^G12V/+-mosaic (right). The basal cells expressing K14H2B-GFP are marked in magenta. Representative images show both the overlay (top) and separate channels for K14H2B-GFP expression (middle) and p21 immunolabeling (bottom). *=mitotic cells negative for p21 (background signal). b) Quantification of p21 immunolabeling in the nucleus of the basal cells in wild-type-mosaic and Hras^G12V/+-mosaic (n = 3 mice). Average of approximately 3,000 cells were analysed for each mouse. Unpaired, two-tailed t-test for the nuclear intensity of p21. Data are represented as means and standard deviations. c) p21 level quantification in the basal cells by using scRNA-seq datasets of wild-type-mosaic and Hras^G12V/+-mosaic with the selection of only tdTomato+ cells. d) Same quantification as in c) but with the selection of non-cycling and tdTomato+ cells. (c, d) n = 3 mice. Statistics on scRNA-seq analysis of p21 expression is based on the non-parametric Wilcoxon rank sum test performed by the Seurat package. Adjusted p-value is based on Bonferroni correction using all features in the dataset. Source Data

Extended Data Fig. 10. Injury-repair or p21^loss specifically increases phospho-ERK1/2 in wild-type cells.

a) Western blot analysis of p-ERK1/2(phospho-Thr202/Tyr204) normalized on total-ERK1/2. b) Western blot analysis of p-AKT(phospho-Ser473) normalized on total-AKT. (a, b) wild-type (n = 4 mice), Hras^G12V/+-mosaic (n = 3 mice), Hras^G12V/+-max (n=3 mice) and constitutive-p21^null (n = 3 mice). Unpaired, two-tailed t-test. Data are represented as means and standard deviations. c) Confocal representative images of the epidermal preparation immunofluorescence for p-ERK1/2 and phalloidin in Hras^G12V/+-mosaic. (left) Insets of p-ERK1/2+ cells: a) cells in interphase b) mitotic cell and c) footprint of a cell that is departing from the basal layer. d) Quantification of p-ERK1/2+ cells in tdTomato+ and tdTomato− areas in Hras^G12V/+-mosaic in injured/3 days PWI(I) and uninjured(U) ears. At least four independent 150 μm² areas were analysed for each mouse. (c, d) n = 3 mice. Unpaired or Paired two-tailed t-test for comparison between different or the same groups of mice. ns indicates not statistically significant. Data are represented as means and standard deviations. Scale bar, 20 μm. (a, b, c, d) Exact p-values reported on the figure. e) Final model. In the uninjured mosaic skin epidermis, Ras cells integrate and expand, outcompeting wild-type neighbors. During injury-repair of mosaic skin, the competitive advantage of Ras cells is suppressed, and oncogenic growths do not develop. EGFR signaling pathway is crucial for this selective increase of wild-type cell divisions that prevents Ras cell expansion during injury-repair. Inducing proliferation, via constitutive p21 loss, mimics the injury condition in uninjured skin, counteracting the competitive advantage of Ras cells. Our data support a model whereby injury-repair and p21 loss increase the activity of ERK1/2, a Ras downstream pathway that controls cell proliferation. This leads to comparable ERK1/2 levels between wild-type and Ras cells, resulting in an increase of dividing wild-type cells that effectively prevent Ras mutant cell expansion. Source Data