Cell Hashing with barcoded antibodies enables multiplexing and doublet detection for single cell genomics

Abstract

Despite rapid developments in single cell sequencing, sample-specific batch effects, detection of cell multiplets, and experimental costs remain outstanding challenges. Here, we introduce Cell Hashing, where oligo-tagged antibodies against ubiquitously expressed surface proteins uniquely label cells from distinct samples, which can be subsequently pooled. By sequencing these tags alongside the cellular transcriptome, we can assign each cell to its original sample, robustly identify cross-sample multiplets, and "super-load" commercial droplet-based systems for significant cost reduction. We validate our approach using a complementary genetic approach and demonstrate how hashing can generalize the benefits of single cell multiplexing to diverse samples and experimental designs.

Fig. 1

Sample multiplexing using DNA-barcoded antibodies. a Schematic overview of sample multiplexing by Cell Hashing. Cells from different samples are incubated with DNA-barcoded antibodies recognizing ubiquitous cell surface proteins. Distinct barcodes (referred to as hashtag-oligos, HTO) on the antibodies allow pooling of multiple samples into one scRNA-seq experiment. After sequencing, cells can be assigned to their sample of origin based on HTO levels (“Methods” section). b Representative scatter plot showing raw counts for HTO A and HTO B across all cell barcodes. Both axes are clipped at 99.9% quantiles to exclude visual outliers. c Heatmap of scaled (z-scores) normalized HTO values based on our classifications. Multiplets express more than one HTO. Negative populations contain HEK293T and mouse NIH-3T3 cells that were spiked into the experiments as negative controls. d tSNE embedding of the HTO dataset. Cells are colored and labeled based on our classifications. Eight singlet clusters and all 28 cross-sample doublet clusters are clearly present. e Distribution of RNA UMIs per cell barcode in cells that were characterized as singlets (red), multiplets (violet) or negatives (grey). f Transcriptome-based clustering of single-cell expression profiles reveals distinct immune cell populations interspersed across donors. B, B cells; T, T cells; NK, natural killer cells; mono, monocytes; DC, dendritic cells. Cells are colored based on their HTO classification (donor ID), as in d

Fig. 2

Validation of Cell Hashing using demuxlet. a Row-normalized “confusion matrix” comparing demuxlet and HTO classifications. Each value on the diagonal represents the fraction of barcodes for a given HTO classification that received an identical classification from demuxlet. b Count distribution of the most highly expressed HTO for groups of concordant and discordant singlets. Both groups have identical classification strength based on Cell Hashing. c Discordant singlets have lower UMI counts, suggesting that a lack of sequencing depth contributed to “ambiguous” calls from demuxlet. d RNA UMI distributions for discordant and concordant multiplets. Only concordant multiplets exhibit increased molecular complexity, suggesting that both methods are conservatively overcalling multiplets in discordant cases. e In support of this, demuxlet assigns lower multiplets posterior probabilities to discordant calls

Fig. 3

Cell Hashing enables efficient experimental optimization and identification of low-quality cells. a–c We performed a titration series to assess optimal staining concentrations for a panel of CITE-seq immunophenotyping antibodies. Normalized ADT counts for CD8 (a), CD45RA (b), and CD4 (c) are depicted for the different concentrations used per test. d Titration curve depicting the staining index (SI; “Methods” section) for these three antibodies across the titration series. The signal/noise ratio for these antibodies begins to saturate at levels similar to manufacturer recommended staining concentrations typical for flow cytometry antibodies. e Cells with low UMI counts can be distinguished from ambient RNA using HTO classifications. Classified singlets group into canonical hematopoietic populations. f Barcodes classified as “negative” do not group into clusters and likely represent “empty” droplets containing only ambient RNA