Single-nucleus and single-cell transcriptomes compared in matched cortical cell types

Abstract

Transcriptomic profiling of complex tissues by single-nucleus RNA-sequencing (snRNA-seq) affords some advantages over single-cell RNA-sequencing (scRNA-seq). snRNA-seq provides less biased cellular coverage, does not appear to suffer cell isolation-based transcriptional artifacts, and can be applied to archived frozen specimens. We used well-matched snRNA-seq and scRNA-seq datasets from mouse visual cortex to compare cell type detection. Although more transcripts are detected in individual whole cells (~11,000 genes) than nuclei (~7,000 genes), we demonstrate that closely related neuronal cell types can be similarly discriminated with both methods if intronic sequences are included in snRNA-seq analysis. We estimate that the nuclear proportion of total cellular mRNA varies from 20% to over 50% for large and small pyramidal neurons, respectively. Together, these results illustrate the high information content of nuclear RNA for characterization of cellular diversity in brain tissues.

Fig 1. Identification of an expression-matched set of single nuclei and whole cells from mouse primary visual cortex (VISp).

(A) Whole brains were dissected from transgenic mice, sectioned into coronal slices, and individual layers of VISp were microdissected. Nuclei were dissociated from layer 5, stained with DAPI and against the neuronal marker NeuN. Single NeuN-positive nuclei were isolated by fluorescence-activated cell sorting (FACS). In parallel, whole cells were dissociated from all layers, and single td-Tomato-positive cells were isolated from multiple different Cre-driver lines. Single nucleus and cell mRNA were reverse-transcribed, amplified, and sequenced to measure genome-wide gene expression levels. (B) Left: 463 nuclei from layer 5 and 12,866 whole cells from all layers, which passed quality control metrics were used to determine expression correlation between each nucleus and every other nucleus and cell. Expression similarity can vary based on sample quality, so nuclei were compared to each other to provide a baseline expected similarity. For each nucleus, the best matching nucleus and cell were selected based on maximal correlation. Right: Cells and nuclei displayed comparable expression similarities to all nuclei, with average correlation equal to 0.70 and 95% of correlations between 0.63 and 0.78. This suggested that nuclei and cells were well matched. (C) Chromogenic RNA in situ hybridization (ISH) for tdTomato mRNA in VISp of transgenic mice (Cre-lines crossed to Ai14 Cre reporter [21]). Shown are the tissue sections from 4 Cre-driver lines from which the majority of the best-matching cells to L5 nuclei were derived. As expected, all Cre-lines label cells in layer 5 and adjacent layers.

Fig 2. Comparison of nuclear and whole cell transcriptomes.

(A) Left: Percentage of RNA-seq reads mapping to genomic regions for cells, nuclei, and whole-brain control RNA. Bars indicate median and 25^th and 75^th quantiles. Among cells, exonic and intronic read percentages display bimodal distributions. Right: Gene detection (counts per million, CPM > 0) based on read mapping to exons, introns, or both introns and exons. (B) Left: The most similar pair of cells have more highly correlated gene expression (r = 0.92) than the most similar pair of nuclei (r = 0.76), due to fewer gene dropouts in cells. Right: Cells have consistently more similar expression to each other than nuclei, even after correcting for gene dropouts based on expression noise models. (C) Left: Binned scatter plot showing all genes are detected (CPM > 0) with equal or greater reliability in cells than in nuclei. Black lines show the variation in detection that is expected by chance (95% confidence interval). Right: Binned scatter plot showing 0.4% of genes are significantly more highly expressed in nuclei, and 20.5% of genes are more highly expressed in cells (for both comparisons, fold change > 1.5, adjusted P-value < 0.05). The log-transformed color scale indicates the number of genes in each bin. (D) Examples of nucleus-enriched transcripts involved in neuronal connectivity, synaptic transmission, and intrinsic firing properties and cell-enriched transcripts related to mRNA processing and protein translation and degradation. In addition, expression of immediate early genes is up to 10-fold higher in cells.

Fig 3. Single nuclei provide comparable clustering resolution to cells when intronic reads are included.

(A) Co-clustering heatmaps show the proportion of 100 clustering iterations that each pair of nuclei were assigned to the same cluster. Clustering was performed using gene expression quantified with exonic reads or intronic plus exonic reads for two key clustering steps: selecting significantly differentially expressed (DE) genes and calculating pairwise similarities between nuclei. Co-clustering heatmaps were generated for each combination of gene expression values, and blue boxes highlight 11 clusters of nuclei that consistently co-clustered using introns and exons (upper left heatmap) and were overlaid on the remaining heatmaps. The row and column order of nuclei is the same for all heatmaps. (B) Co-clustering heatmaps were generated for cells as described for nuclei in (A), and blue boxes highlight 11 clusters of cells. (C) Cluster cohesion (average within cluster co-clustering) and separation (difference between within cluster co-clustering and maximum between cluster co-clustering) are plotted for nuclei and cells and all combinations of reads. Including introns in gene expression quantification dramatically increases cohesion and separation of nuclei but not cell clusters.

Fig 4. Similar neuronal cell types identified with nuclei and cells.

(A) Cluster dendrograms for nuclei and cells based on hierarchical clustering of average expression of the top 1200 cluster marker genes. 11 clusters are labeled based on dendrogram leaf order and the closest matching mouse VISp cell type described in based on correlated marker gene expression (see S4 Fig). (B) Pairwise correlations between nuclear and cell clusters using average cluster expression of the top 490 shared marker genes. (C) Violin plots of cell type specific marker genes expressed in matching nuclear and cell clusters. Plots are on a linear scale, max CPM indicates the maximum expression of each gene, and black dots indicate median expression. (D) Hierarchical clustering of nuclear and cell clusters using the top 1200 marker genes with expression quantified by intronic or exonic reads. Intronic reads group nine matching nuclear and cell clusters together at the leaves, while two closely related deep layer 5 excitatory neuron types group by sample type. In contrast, exonic reads completely segregate clusters by sample type. (E) Box plots of cluster separations for all samples in matched nuclear and cell clusters. Clusters are equally well separated for all but two cell types, L4 Arf5 and L5b Cdh13, that are moderately but significantly (Wilcoxon signed rank unpaired tests; Bonferroni corrected P-value < 0.05) more distinct with cells than nuclei. (F) Cell type marker genes are consistently detected in both nuclei and cells, although marker scores (see Methods) are on average 15% higher for cells.

Fig 5. Nuclear transcript content varies among cell types and genes.

(A) Box plots showing median (bars), 25^th and 75^th quantiles (boxes), and range (whiskers) of percentages of reads mapping to introns for matched nuclei and cell clusters. (B) Box plots of log₂-transformed expression of the nuclear non-coding RNA, Malat1, in matched nuclei and cell clusters. (C) The nuclear fraction of transcripts in cell types was estimated with two methods: the ratio of intronic read percentages in cells compared to nuclei; and the average ratio of expression in cells compared to nuclei of three highly expressed genes (Snhg11, Meg3, and Malat1) that are localized to the nucleus. The relative ranking of nuclear fractions was consistent (Spearman rank correlation = 0.84), although estimates based on the intronic read ratio were consistently 50% higher. (D) Estimated nuclear proportion (ratio of nucleus and soma volume) of neurons labeled by three mouse Cre-lines in Layers 4 and 5 (see S5D Fig). Single neuron measurements (grey points) were summarized as violin plots, and average nuclear proportions (black points) were compared to the range of estimated proportions (blue lines) based on intronic read ratios and nuclear gene expression. (E) Histograms of nuclear fraction estimates for 11,932 genes expressed (CPM > 1) in at least one nuclear or cell cluster and grouped by type of gene. (F) Violin plots of marker score distributions with median and inter-quartile intervals. Non-coding genes and pseudogenes are on average better markers of cell types than protein-coding genes. Kruskal–Wallis rank sum test, post hoc Wilcoxon signed rank unpaired tests: *P < 1 x 10⁻⁵⁰ (Bonferroni-corrected), NS, not significant. (G) Box plots of cell type marker scores for genes grouped by estimated nuclear transcript proportion. (H) Validation of the estimated nuclear proportion of transcripts for Calb1, Grik1, and Pvalb using multiplex fluorescent in situ hybridization (mFISH). Top: For each gene, transcripts were labeled with fluorescent probes and counted in the nucleus (white) and soma (yellow). Bottom: Probe counts in the nucleus and soma across all cells with linear regression fits to estimate nuclear transcript proportions for each gene. Estimated proportions based on mFISH and RNA-seq data are summarized on the right.