Single cell profiling of capillary blood enables out of clinic human immunity studies

Abstract

An individual's immune system is driven by both genetic and environmental factors that vary over time. To better understand the temporal and inter-individual variability of gene expression within distinct immune cell types, we developed a platform that leverages multiplexed single-cell sequencing and out-of-clinic capillary blood extraction to enable simplified, cost-effective profiling of the human immune system across people and time at single-cell resolution. Using the platform, we detect widespread differences in cell type-specific gene expression between subjects that are stable over multiple days.

Figure 1

Experimental workflow and consistency of capillary blood sampling. (a) Experimental workflow for capillary blood immune profiling. 1. Blood is collected using the TAP device from the deltoid. 2. Capillary peripheral blood mononuclear cells (CPBMCs) are separated via centrifugation. 3. Red blood cells are lysed and removed, and samples from different subjects are pooled together. 4. Cell transcriptomes are sequenced using single-cell sequencing. (b) Time-course study design. CPBMCs are collected and profiled from 4 subjects (2 male, 2 female) each morning (AM) and afternoon (PM) for 3 consecutive days. (c) 2-dimensional t-SNE projection of the transcriptomes of all cells in all samples. Cells appear to cluster by major cell type (Fig. S6) (d) Immune cell type percentages across all samples shows stable cell type abundances (includes cells without subject labels). (e) Cell type ratios between capillary blood from this study, and venous blood from 3 other studies were the same, with the exception of CD14⁺ Monocytes, which are more abundant in venous blood (FDR < 0.05, 2-sided student t-test, multiple comparison corrected) The q-values are displayed for each cell type comparison.

Figure 2

Diurnal variability in subpopulations of capillary blood (a) Magnitude (Z-score) of the difference in AM vs PM gene expression across the whole population of cells (x) vs the cell type with the largest magnitude Z-score (y). Points above or below the significance lines (FDR < 0.05, multiple comparison correction) display different degrees of diurnality. The size of each marker indicates the abundance of the gene (the largest percent of cells in a subpopulation that express this gene). (b) Distribution of expression of DDIT4, a previously identified circadian rhythm gene, shows diurnal signal across all cells, as well as individual cell types, such as natural killer (NK) cells. u indicates the mean fraction of transcripts per cell (gene abundance). (c) Example of newly identified diurnal genes, LSP1 and IFI16 that could be missed if analyzed at the population level (d) Example of a gene, EAF2, that could be falsely classified as diurnal (i) without considering cell type subpopulations due to a diurnal B cell abundance shift (ii).

Figure 3

Subject variability in immune and disease-relevant genes and pathways. (a) Magnitude (log₂ F statistic) of the variability in expression of genes between different cell types (x) and between subjects (y). 1284/7034 (18.3%) of genes are above the subject specificity significance line (FDR < 0.05, multiple comparison correction) and are classified as subject-specific. Several MHC class II genes (HLA-X) are strongly subject-specific, consistent with previous findings. (b) KEGG pathways grouped into categories and their enrichment (Z-score from 2-proportion Z-test) among the top 250 diurnally and subject-varying genes vs all genes. Immune system and disease pathways are significantly enriched (p = 0.029), supportive of the conclusion that immune and disease-related genes are highly subject dependent. The large circles indicate the enrichment of the category overall, and the sizes of the smaller pathway points indicate the number of genes associated with the pathway. (c) Subject and cell type specific gene examples for each subject and cell type with the upper row displaying the trace of mean gene expression across time-points and the bottom row showing gene abundance shifts for the subjects of interest.