An optimised tissue disaggregation and data processing pipeline for characterising fibroblast phenotypes using single-cell RNA sequencing

Abstract

Single-cell RNA sequencing (scRNA-Seq) provides a valuable platform for characterising multicellular ecosystems. Fibroblasts are a heterogeneous cell type involved in many physiological and pathological processes, but remain poorly-characterised. Analysis of fibroblasts is challenging: these cells are difficult to isolate from tissues, and are therefore commonly under-represented in scRNA-seq datasets. Here, we describe an optimised approach for fibroblast isolation from human lung tissues. We demonstrate the potential for this procedure in characterising stromal cell phenotypes using scRNA-Seq, analyse the effect of tissue disaggregation on gene expression, and optimise data processing to improve clustering quality. We also assess the impact of in vitro culture conditions on stromal cell gene expression and proliferation, showing that altering these conditions can skew phenotypes.

Figure 1

Disaggregation enzymes and incubation times have a significant impact on stromal cell isolation. (a) Representative pie charts for each disaggregation time and enzyme cocktail. (b–d) Dot plots showing cell-type fractions isolated by different disaggregation procedures across human patient samples (n = 5): fibroblasts (CD45-EpCAM-CD31-CD90+: b), Immune cells (CD45+: c), and epithelial cells (CD45-EpCAM+: d; *p < 0.05, unpaired two-tailed t-test). Further data associated with this figure can be found in Figs S1–4.

Figure 2

Standardised quality-control metrics improve clustering quality of scRNA-seq data. tSNE plots showing principle component-based clustering and average silhouette width for: (a) unfiltered data, (b) data filtered using widely-used quality-control metrics and (c) the optimised approach described here (shown in d–g). Each point represents an individual cell, groups of cells with similar transcriptomes are referred to as a ‘cluster’ and distinguished by colour. Fibroblast populations are encircled in black. (d–g) Cell filtering using our optimised processing pipeline: (d) Multi-way importance plot showing the relative importance of each metric in distinguishing between low-quality events and droplets, (e) Plot of log(nGene) vs. log(nUMI). Data points identified as low-quality events are highlighted in red, (f) Plot of nUMI vs. nGene. The red line indicates the upper nGene threshold (defined as 2.5 MAD above the median) and (g) Plot of nGene vs. percent mito. The red line indicates the upper threshold (defined as 2.5 MAD above the median). Further data associated with this figure can be found in Fig. S5.

Figure 3

Longer tissue disaggregation enables detection of more cell types, with concomitant increases in disaggregation-associated changes in gene expression. (a) Stacked barplot showing cell type fractions generated by disaggregation for 15 and 60 minutes. (b) Venn diagram showing overlap between murine disaggregation-associated signature (Murine DAG), human disaggregation-associated signature (Lung DAG) and cell type markers. The 11 genes comprising the refined signature (highlighted in bold) are shown on the right. (c) and (d) Density plots showing percentage expression of the murine disaggregation signature (c) and the refined disaggregation signature (d), in human lung tissue disaggregated for 15 and 60 minutes. Further data associated with this figure can be found in Fig. S6.

Figure 4

In vitro culture alters fibroblast transcriptomes. (a) Volcano plot of genes differentially expressed (log(fold change) >1) between in vitro and ex vivo fibroblasts. Genes selected for analysis at real time-PCR are highlighted in red. (b) Dendrogram showing unsupervised hierarchical clustering of average gene expression for the four cell populations. (c–g) Dot plots showing changes in gene expression (real-time PCR) in primary lung fibroblasts following culture on plastic or in 3D (collagen:Matrigel gels): (c) ACTA2, (d) COL1A1, (e) COL3A1, (f) IL6, (g) CFD and (h) MGP. Gene expression levels expressed as the log2 fold change relative to mean expression across all samples (n = 4). ▲: NOF, ♦: CAF. *p < 0.05, ***p < 0.001, ****p < 0.0001, unpaired or Welch’s t-tests. Further data associated with this figure can be found in Figs S7–S9.