Gene expression profiling of cutaneous wound healing

Abstract

Background: Although the sequence of events leading to wound repair has been described at the cellular and, to a limited extent, at the protein level this process has yet to be fully elucidated. Genome wide transcriptional analysis tools promise to further define the global picture of this complex progression of events.

Study design: This study was part of a placebo-controlled double-blind clinical trial in which basal cell carcinomas were treated topically with an immunomodifier--toll-like receptor 7 agonist: imiquimod. The fourteen patients with basal cell carcinoma in the placebo arm of the trial received placebo treatment consisting solely of vehicle cream. A skin punch biopsy was obtained immediately before treatment and at the end of the placebo treatment (after 2, 4 or 8 days). 17.5K cDNA microarrays were utilized to profile the biopsy material.

Results: Four gene signatures whose expression changed relative to baseline (before wound induction by the pre-treatment biopsy) were identified. The largest group was comprised predominantly of inflammatory genes whose expression was increased throughout the study. Two additional signatures were observed which included preferentially pro-inflammatory genes in the early post-treatment biopsies (2 days after pre-treatment biopsies) and repair and angiogenesis genes in the later (4 to 8 days) biopsies. The fourth and smallest set of genes was down-regulated throughout the study. Early in wound healing the expression of markers of both M1 and M2 macrophages were increased, but later M2 markers predominated.

Conclusion: The initial response to a cutaneous wound induces powerful transcriptional activation of pro-inflammatory stimuli which may alert the host defense. Subsequently and in the absence of infection, inflammation subsides and it is replaced by angiogenesis and remodeling. Understanding this transition which may be driven by a change from a mixed macrophage population to predominantly M2 macrophages, may help the interpretation of the cellular and molecular events occurring in the microenvironment of serially biopsied tissues.

Figure 1

Genes differentially expressed between pre and post wound skin biopsies. One skin punch biopsy was obtained pre wound and one either day 2, 4, or 8 post wound from 14 subjects. The 1,749 genes found to be differentially expressed using paired t-test comparison (p < 0.05) were analyzed by filtering (genes expressed in 80% of samples and at least more increased 2 or more fold) and this yielded 753 genes. Supervised hierarchical clustering analysis of Eisen of the 753 differentially expressed genes revealed 7 signature clusters (Figure 1a). The genes in the 7 clusters were combined and analyzed again by supervised hierarchical clustering (Figure 1b). The pre wound biopsies are indicated by the blue bar, the day 2 post wound biopsies by the yellow bar, the day 4 post wound biopsy by the purple bar, and the day 8 post wound biopsy by the orange bar (Figure 1c).

Figure 2

Signature clusters of genes whose expression was changed early in wound healing. Genes in signature clusters 3 and 4 whose expression was greatest on day 2 are shown. Pre and post wound biopsies are color coded by the horizontal bars as per figure 1.

Figure 3

Signature clusters of genes whose expression was changed late in wound healing. Genes in signature clusters 1, 5, 6, and 7 whose expression was greatest on days 4 and 8 are shown. Pre and post wound biopsies are color coded by the horizontal bars as per figure 1.

Figure 4

Genes whose post wound expression was decreased on all days. The expression of genes in signature cluster 2 were decreased on all days. Pre and post wound biopsies are color coded by the horizontal bars as per figure 1.

Figure 5

Supervised Eisen hierarchical clustering analysis of 133 differentially expressed genes between pre and post wound that were not included in the signature clusters. From the 753 differentially expressed genes, the genes in the signature clusters were removed and genes important in inflammation, immune response and wound healing were selected according to DAVID [13] and Gene Cards [14] and analyzed by supervised hierarchical clustering. Three clusters were identified; one whose expression was increased most on day 2, one on days 4 and 8, and another whose expression was increased on day 2–8. The specific genes are shown in additional file 2. Pre and post wound biopsies are color coded by the horizontal bars as per figure 1.

Figure 6

Analysis of the expression of macrophage genes. Genes characteristic of M1 and M2 macrophages were selected according to a list of transcripts reported in the literature [21,22,25] to be modulated by these cell subsets and were analyzed by supervised hierarchical clustering which revealed two clusters. The first cluster was a mix of M1 and M2 genes whose expression was greatest on day 2. The second cluster was predominantly M2 genes and their expression was greatest on day 4 and 8. Pre and post wound biopsies are color coded by the horizontal bars as per figure 1.