Contents

1 Introduction

In this vignette, we provide an overview of the basic functionality and usage of the scds package, which interfaces with SingleCellExperiment objects.

2 Installation

Install the scds package using Bioconductor:

if (!requireNamespace("BiocManager", quietly = TRUE))
    install.packages("BiocManager")
BiocManager::install("scds", version = "3.9")

Or from github:

library(devtools)
devtools::install_github('kostkalab/scds')

3 Quick start

scds takes as input a SingleCellExperiment object (see here SingleCellExperiment), where raw counts are stored in a counts assay, i.e. assay(sce,"counts"). An example dataset created by sub-sampling the cell-hashing cell-lines data set (see https://satijalab.org/seurat/hashing_vignette.html) is included with the package and accessible via data("sce").Note that scds is designed to workd with larger datasets, but for the purposes of this vignette, we work with a smaller example dataset. We apply scds to this data and compare/visualize reasults:

3.1 Example data set

Get example data set provided with the package.

library(scds)
library(scater)
library(rsvd)
library(Rtsne)
library(cowplot)
set.seed(30519)
data("sce_chcl")
sce = sce_chcl #- less typing
dim(sce)
## [1] 2000 2000

We see it contains 2,000 genes and 2,000 cells, 216 of which are identified as doublets:

table(sce$hto_classification_global)
## 
##  Doublet Negative  Singlet 
##      216       83     1701

We can visualize cells/doublets after projecting into two dimensions:

logcounts(sce) = log1p(counts(sce))
vrs            = apply(logcounts(sce),1,var)
pc             = rpca(t(logcounts(sce)[order(vrs,decreasing=TRUE)[1:100],]))
ts             = Rtsne(pc$x[,1:10],verb=FALSE)

reducedDim(sce,"tsne") = ts$Y; rm(ts,vrs,pc)
plotReducedDim(sce,"tsne",col="hto_classification_global")

3.2 Computational doublet annotation

We now run the scds doublet annotation approaches. Briefly, we identify doublets in two complementary ways: cxds is based on co-expression of gene pairs and works with absence/presence calls only, while bcds uses the full count information and a binary classification approach using artificially generated doublets. cxds_bcds_hybrid combines both approaches, for more details please consult (this manuscript). Each of the three methods returns a doublet score, with higher scores indicating more “doublet-like” barcodes.

#- Annotate doublet using co-expression based doublet scoring:
sce = cxds(sce,retRes = TRUE)
sce = bcds(sce,retRes = TRUE,verb=TRUE)
## [18:45:23] WARNING: amalgamation/../src/learner.cc:1095: Starting in XGBoost 1.3.0, the default evaluation metric used with the objective 'binary:logistic' was changed from 'error' to 'logloss'. Explicitly set eval_metric if you'd like to restore the old behavior.
sce = cxds_bcds_hybrid(sce)
par(mfcol=c(1,3))
boxplot(sce$cxds_score   ~ sce$doublet_true_labels, main="cxds")
boxplot(sce$bcds_score   ~ sce$doublet_true_labels, main="bcds")
boxplot(sce$hybrid_score ~ sce$doublet_true_labels, main="hybrid")

3.3 Visualizing gene pairs

For cxds we can identify and visualize gene pairs driving doublet annoataions, with the expectation that the two genes in a pair might mark different types of cells (see manuscript). In the following we look at the top three pairs, each gene pair is a row in the plot below:

scds =
top3 = metadata(sce)$cxds$topPairs[1:3,]
rs   = rownames(sce)
hb   = rowData(sce)$cxds_hvg_bool
ho   = rowData(sce)$cxds_hvg_ordr[hb]
hgs  = rs[ho]

l1 =  ggdraw() + draw_text("Pair 1", x = 0.5, y = 0.5)
p1 = plotReducedDim(sce,"tsne",col=hgs[top3[1,1]])
p2 = plotReducedDim(sce,"tsne",col=hgs[top3[1,2]])

l2 =  ggdraw() + draw_text("Pair 2", x = 0.5, y = 0.5)
p3 = plotReducedDim(sce,"tsne",col=hgs[top3[2,1]])
p4 = plotReducedDim(sce,"tsne",col=hgs[top3[2,2]])

l3 = ggdraw() + draw_text("Pair 3", x = 0.5, y = 0.5)
p5 = plotReducedDim(sce,"tsne",col=hgs[top3[3,1]])
p6 = plotReducedDim(sce,"tsne",col=hgs[top3[3,2]])

plot_grid(l1,p1,p2,l2,p3,p4,l3,p5,p6,ncol=3, rel_widths = c(1,2,2))

4 Session Info

sessionInfo()
## R version 4.1.0 (2021-05-18)
## Platform: x86_64-pc-linux-gnu (64-bit)
## Running under: Ubuntu 20.04.2 LTS
## 
## Matrix products: default
## BLAS:   /home/biocbuild/bbs-3.13-bioc/R/lib/libRblas.so
## LAPACK: /home/biocbuild/bbs-3.13-bioc/R/lib/libRlapack.so
## 
## locale:
##  [1] LC_CTYPE=en_US.UTF-8       LC_NUMERIC=C              
##  [3] LC_TIME=en_GB              LC_COLLATE=C              
##  [5] LC_MONETARY=en_US.UTF-8    LC_MESSAGES=en_US.UTF-8   
##  [7] LC_PAPER=en_US.UTF-8       LC_NAME=C                 
##  [9] LC_ADDRESS=C               LC_TELEPHONE=C            
## [11] LC_MEASUREMENT=en_US.UTF-8 LC_IDENTIFICATION=C       
## 
## attached base packages:
## [1] parallel  stats4    stats     graphics  grDevices utils     datasets 
## [8] methods   base     
## 
## other attached packages:
##  [1] cowplot_1.1.1               Rtsne_0.15                 
##  [3] rsvd_1.0.5                  scater_1.20.0              
##  [5] ggplot2_3.3.3               scuttle_1.2.0              
##  [7] SingleCellExperiment_1.14.0 SummarizedExperiment_1.22.0
##  [9] Biobase_2.52.0              GenomicRanges_1.44.0       
## [11] GenomeInfoDb_1.28.0         IRanges_2.26.0             
## [13] S4Vectors_0.30.0            BiocGenerics_0.38.0        
## [15] MatrixGenerics_1.4.0        matrixStats_0.58.0         
## [17] scds_1.8.0                  BiocStyle_2.20.0           
## 
## loaded via a namespace (and not attached):
##  [1] viridis_0.6.1             sass_0.4.0               
##  [3] BiocSingular_1.8.0        viridisLite_0.4.0        
##  [5] jsonlite_1.7.2            DelayedMatrixStats_1.14.0
##  [7] bslib_0.2.5.1             assertthat_0.2.1         
##  [9] highr_0.9                 BiocManager_1.30.15      
## [11] vipor_0.4.5               GenomeInfoDbData_1.2.6   
## [13] yaml_2.2.1                pillar_1.6.1             
## [15] lattice_0.20-44           glue_1.4.2               
## [17] beachmat_2.8.0            pROC_1.17.0.1            
## [19] digest_0.6.27             XVector_0.32.0           
## [21] colorspace_2.0-1          htmltools_0.5.1.1        
## [23] Matrix_1.3-3              plyr_1.8.6               
## [25] pkgconfig_2.0.3           magick_2.7.2             
## [27] bookdown_0.22             zlibbioc_1.38.0          
## [29] purrr_0.3.4               scales_1.1.1             
## [31] ScaledMatrix_1.0.0        BiocParallel_1.26.0      
## [33] tibble_3.1.2              farver_2.1.0             
## [35] generics_0.1.0            xgboost_1.4.1.1          
## [37] ellipsis_0.3.2            withr_2.4.2              
## [39] magrittr_2.0.1            crayon_1.4.1             
## [41] evaluate_0.14             fansi_0.4.2              
## [43] beeswarm_0.3.1            tools_4.1.0              
## [45] data.table_1.14.0         lifecycle_1.0.0          
## [47] stringr_1.4.0             munsell_0.5.0            
## [49] DelayedArray_0.18.0       irlba_2.3.3              
## [51] compiler_4.1.0            jquerylib_0.1.4          
## [53] rlang_0.4.11              grid_4.1.0               
## [55] RCurl_1.98-1.3            BiocNeighbors_1.10.0     
## [57] labeling_0.4.2            bitops_1.0-7             
## [59] rmarkdown_2.8             gtable_0.3.0             
## [61] DBI_1.1.1                 R6_2.5.0                 
## [63] gridExtra_2.3             knitr_1.33               
## [65] dplyr_1.0.6               utf8_1.2.1               
## [67] stringi_1.6.2             ggbeeswarm_0.6.0         
## [69] Rcpp_1.0.6                vctrs_0.3.8              
## [71] tidyselect_1.1.1          xfun_0.23                
## [73] sparseMatrixStats_1.4.0