Comprehensive Integration of Multiple Single-Cell Transcriptomic Data Sets Defines Distinct Cell Populations and Their Phenotypic Changes in Murine Atherosclerosis

Abstract

Background: The application of single-cell transcriptomic (single-cell RNA sequencing) analysis to the study of atherosclerosis has provided unique insights into the molecular and genetic mechanisms that mediate disease risk and pathophysiology. However, nonstandardized methodologies and relatively high costs associated with the technique have limited the size and replication of existing data sets and created disparate or contradictory findings that have fostered misunderstanding and controversy.

Methods: To address these uncertainties, we have performed a conservative integration of multiple published single-cell RNA sequencing data sets into a single meta-analysis, performed extended analysis of native resident vascular cells, and used in situ hybridization to map the disease anatomic location of the identified cluster cells. To investigate the transdifferentiation of smooth muscle cells to macrophage phenotype, we have developed a classifying algorithm based on the quantification of reporter transgene expression.

Results: The reporter gene expression tool indicates that within the experimental limits of the examined studies, transdifferentiation of smooth muscle cell to the macrophage lineage is extremely rare. Validated transition smooth muscle cell phenotypes were defined by clustering, and the location of these cells was mapped to lesion anatomy with in situ hybridization. We have also characterized 5 endothelial cell phenotypes and linked these cellular species to different vascular structures and functions. Finally, we have identified a transcriptomically unique cellular phenotype that constitutes the aortic valve.

Conclusions: Taken together, these analyses resolve a number of outstanding issues related to differing results reported with vascular disease single-cell RNA sequencing studies, and significantly extend our understanding of the role of resident vascular cells in anatomy and disease.

Keywords: algorithms; aortic valve; disease; gene expression; phenotype.

Figure 1.

Integration of scRNAseq datasets using reference-based integration. A) Unsupervised clustering of different transcriptomic datasets using Seurat at resolution 0.2. Data dimensionality reduction and two-dimensional representation is shown by UMAP. Major cell types were annotated manually from the integrated UMAP. B) Dataset distribution of cells over the 2-dimensional UMAP. C) UMAP showing data from different timepoints included in the integrated object. D) UMAP representing gene knockout cells included in the object. E) FeaturePlots showing expression of markers from major cell types. F) DotPlot showing the expression of top three markers from the major cell-type groups, with size of the dot showing percent of cells expressing the markers.

Figure 2.

Investigation of possible SMC transdifferentiation to macrophages, employing datasets from Cheng et al (A - E), Pan et al (F - J) and Newman et al (K - M). A) UMAP showing SMC (red) and non-SMC (grey) at baseline as identified with Myh11 expression for Cheng et al dataset. B) Histogram showing the expression of tdTomato in SMC vs non-SMC at baseline. The dotted line shows the cut-off identified with the AUC curve. C) UMAP showing expression of tdTomato gene in Cheng et al 16-week timepoint with cut-off 1.8. Cutoff corresponds to the AUC in panel ‘B.’ D) UMAP showing FACS labeled cells in Cheng et al 16-week time-point. Metadata represents assignment of lineage tracing as per fluorescent gating in these studies. E) Expression of the canonical macrophage marker Cd68 at the 16-week time-point. F) Expression of Zsgreen1 in SMC (red) vs non-SMC (grey) at 0-week time point identified with Myh11 expression. G) Histogram showing the expression distribution of Zsgreen1 in SMC vs non-SMC cells at 0 week with dotted line representing the cut-off identified with AUC curve. H) Expression of Zsgreen1 at 16 - and 22 - week time-point from Pan et al with cut-off 1.3. I) UMAP showing FACS data with labeled SMC and non-SMC in Pan et al. Metadata represents assignment of lineage tracing as per fluorescent gating in these studies. J) UMAP showing expression of Cd68 marking the macrophage cluster at 16-week and 22-week. K) Histogram showing expression distribution of eYFP in SMC vs non- SMC in Newman et al dataset identified with Myh11 expression. L) Expression of eYFP and M) Cd68.

Figure 3.

Sub-clustering of wild-type smooth muscle cells. A) UMAP of cells from unsupervised clustering using Seurat at resolution 0.15. B) Dataset-wise distribution of cells across 2-dimensional UMAP. C) Heatmap showing differential expressed genes in smooth muscle cell clusters. Representative genes are identified for each cluster. D) Pathway enrichment analysis for top 30 genes in each cluster identified with clusterProfiler. E) Feature plot for specific markers for each cluster. F) Cells highlighted for each dataset in the integrated wild-type smooth muscle cell UMAP, highlighted in green in the integrated UMAP.

Figure 4.

Validation of selected markers for distinct smooth muscle cell populations using immunohistochemistry and RNAscope. A) Tagln and B) Cnn1 immune labeling for these quiescent smooth muscle cell markers. C) RNAscope for fibromyocyte marker Vcam1, D) chondromyocyte markers Col2a1 and E) Ibsp, and F, G) cluster 5 marker OSR1. In situ reaction is visualized as red color.

Figure 5.

Distinct clustering of endothelial cell population in wild-type datasets. A) Unsupervised clustering using Seurat at resolution 0.15. B) Dataset-wise distribution of cells across 2-dimensional UMAP. C) Heatmap showing top 30 markers for each cluster at resolution 0.15. D) Pathway enrichment analysis for top 30 genes from the heatmap using clusterProfiler. Pathways are identified by the first digit representing the cluster number and a decimal assigned sequentially for individual clusters. E) Violin plots show specific markers in endothelial cell clusters. F) Feature plots showing the expression of gene markers selected for validation.

Figure 6.

In situ hybridization localization of endothelial cell clusters. Individual marker genes were identified with the “findmarker” algorithm in Seurat, and tissue hybridization performed with RNAscope. For each cluster and marker, RNAscope hybridization, cluster assignment, and feature plots are shown. Anatomical locations of cells expressing cluster markers were identified as follows: cluster 0, marker Car4, interstitial microvascular EC; cluster 1, marker Edn1, modulated EC in disease plaque; cluster 2, marker Klk10, large vessel luminal endothelial cells; cluster 3, marker Lyve1 in the adventitia and marker Prox1, lymphatic EC in the adventitia, and aortic valve fibroblasts; cluster 4, Tmem108 and Prox1, endocardial EC and valve cells. In situ reaction is visualized as red color.

Figure 7.

Identification and localization of aortic valve cells. A, B) Fibroblast cluster 5 marker genes Tbx20 and Igf1 were enriched in valve interstitial cells. Valve commissure cells were marked by FMC / CMC genes Spp1 and Tnfrsf11b. Cell-specific expression of these markers was characterized by RNAscope studies of valve tissues.