Transcriptomic Analysis Identifies A Tolerogenic Dendritic Cell Signature

Abstract

Dendritic cells (DC) are central to regulating innate and adaptive immune responses. Strategies that modify DC function provide new therapeutic opportunities in autoimmune diseases and transplantation. Current pharmacological approaches can alter DC phenotype to induce tolerogenic DC (tolDC), a maturation-resistant DC subset capable of directing a regulatory immune response that are being explored in current clinical trials. The classical phenotypic characterization of tolDC is limited to cell-surface marker expression and anti-inflammatory cytokine production, although these are not specific. TolDC may be better defined using gene signatures, but there is no consensus definition regarding genotypic markers. We address this shortcoming by analyzing available transcriptomic data to yield an independent set of differentially expressed genes that characterize human tolDC. We validate this transcriptomic signature and also explore gene differences according to the method of tolDC generation. As well as establishing a novel characterization of tolDC, we interrogated its translational utility in vivo, demonstrating this geneset was enriched in the liver, a known tolerogenic organ. Our gene signature will potentially provide greater understanding regarding transcriptional regulators of tolerance and allow researchers to standardize identification of tolDC used for cellular therapy in clinical trials.

Keywords: dendritic cell; gene expression profile analysis; human dendritic cell; liver; mature dendritic cells; mononuclear phagocyte cells; tolerogenic dendritic cell (tolDC); transcriptomic.

Figure 1

Dataset identification and workflow for tolDC gene analysis. (A) Flowchart demonstrating relevant GEO search with inclusion and exclusion criteria. (B) Pipeline for generating tolDC, AADC and mature DC gene signatures.

Figure 2

Generating a unique tolDC transcriptome. (A) Principal component analysis (PCA) plot characterizing change in gene expression profiles between immature DC (red), mature DC (green), tolDC (blue), or alternatively-activated tolerogenic DC (AADC, purple) in GSE52894. Each dot presents a sample, and each color represents a DC phenotype. (B) Heatmap representation of the top 20 differentially expressed genes (DEG) by tolDC. DEG were arranged by hierarchical clustering on the vertical axis. Datasets, also clustered by hierarchical clustering, are displayed on the horizontal axis. The p-value yielded from each study were converted to z-scores and plotted. (C) KEGG and (D) Gene Set Enrichment analyses. Each point on the dot plot represents the number of genes involved in the relevant pathway. The gene ratio is the proportion of DEG versus genes not differentially expressed. Each point was colored to represent the adjusted p-value using the Benjamini-Hochberg method.

Figure 3

Validation of tolDC transcriptome. Heatmap representation of upregulated and downregulated genes from the tolDC discovery gene set compared to expression in (A) GEO-derived or (B) ArrayDatabase validation gene set.

Figure 4

Identifying transcriptomic differences between subtypes of tolDC. (A) Heatmap representation of the top 39 DEG by AADC. (B) Fold change difference in expression of genes in AADC compared to tolDC. (C) KEGG and (D) Gene Set Enrichment analyses.

Figure 5

TolDC gene set is overexpressed in liver-resident DC. (A) UMAP plot displaying the clustering of harmony integrated scRNAseq samples. (B) UMAP plot of liver datasets annotated by cell type. (C) Dot plot displaying up- and down-regulated tolDC gene expression markers enriched within cell clusters. (D) UMAP plot demonstrating a joint density analysis of upregulated genes from the tolDC gene set. (E) Boxplot displaying the expression of the tolDC gene set across tissue-resident and circulating DC. ****p < 0.0001.

Figure 6

Generating a mature DC transcriptome. (A) Heatmap representation of the top 52 DEG within the mature DC phenotype. (B) KEGG and (C) Gene Set Enrichment Analyses. (D) Mature DC gene-set expression in myeloid cell subsets isolated from epithelial tissues. (E) Comparison of tolDC and mature DC gene signatures in peripheral blood immune cell subsets. (F) Boxplot displaying the expression of genes critical to mature DC across DC in liver, kidney and PBMC. (G) Comparison of tolDC and mature DC gene set expression in liver, kidney and PBMC. (H) Mononuclear phagocytes from epithelial and subepithelial tissues were isolated and classified as DC or macrophage. The average expression of the mature DC gene signature was plotted between cells. A two-sample t-test was performed to determine statistically significant differences in base mean expression of the mature DC gene set across MNP. *p < 0.05, **p < 0.01, ***p < 0.001, ****p < 0.0001.