PG2021 Day 1 – Process pbmc3k using Bioconductor OSCA

Summary

• Based on https://bioconductor.org/books/release/OSCA/unfiltered-human-pbmcs-10x-genomics.html

Load packages

library( "DropletUtils" )

Warning message:
In if (charToRaw(x) < 20) paste("\\u", toupper(format(as.hexmode(as.integer(charToRaw(x))),  :
  the condition has length > 1 and only the first element will be used

library( "scater" )
library( "scran" )

Prepare data

Load counts

sce <- read10xCounts( "/home/idies/workspace/practical_genomics/day1/pbmc3k/filtered_gene_bc_matrices/hg19/", col.names=TRUE )
rownames( sce ) <- rowData( sce )$Symbol

sce

class: SingleCellExperiment 
dim: 32738 2700 
metadata(1): Samples
assays(1): counts
rownames(32738): MIR1302-10 FAM138A ... AC002321.2
  AC002321.1
rowData names(2): ID Symbol
colnames(2700): AAACATACAACCAC-1 AAACATTGAGCTAC-1 ...
  TTTGCATGAGAGGC-1 TTTGCATGCCTCAC-1
colData names(2): Sample Barcode
reducedDimNames(0):
altExpNames(0):

Normalize

sce <- logNormCounts( sce )
sce

class: SingleCellExperiment 
dim: 32738 2700 
metadata(1): Samples
assays(2): counts logcounts
rownames(32738): MIR1302-10 FAM138A ... AC002321.2
  AC002321.1
rowData names(2): ID Symbol
colnames(2700): AAACATACAACCAC-1 AAACATTGAGCTAC-1 ...
  TTTGCATGAGAGGC-1 TTTGCATGCCTCAC-1
colData names(3): Sample Barcode sizeFactor
reducedDimNames(0):
altExpNames(0):

Find variable genes

dec <- modelGeneVar( sce )
hvg <- getTopHVGs( dec, prop=0.1 )

Reduce dimensions

sce <- runPCA( sce, ncomponents=25, subset_row=hvg )
sce <- runUMAP( sce, dimred="PCA", external_neighbors=TRUE )

Cluster

g <- buildSNNGraph( sce, use.dimred="PCA" )
colLabels( sce ) <- factor( igraph::cluster_louvain(g)$membership )

Find makers

markers <- findMarkers( sce )
data.frame( markers[[1]] )

Visualize cells

plotUMAP( sce, colour_by="label", text_by="label" )

plotUMAP( sce, colour_by="MS4A1" )

Visalize expression

goi <- c( "MS4A1", "GNLY", "CD3E", "CD14", "FCER1A", "FCGR3A", "LYZ", "PPBP", "CD8A" )
plotExpression( sce, x="label", features=goi )

plotGroupedHeatmap( sce, group="label", features=goi, scale="row" )

Save object

saveRDS( sce, "/home/idies/workspace/practical_genomics/day1/pbmc3k.rds" )

Document software

sessionInfo()

R version 4.0.3 (2020-10-10)
Platform: x86_64-pc-linux-gnu (64-bit)
Running under: CentOS Linux 8

Matrix products: default
BLAS:   /home/idies/R/lib64/R/lib/libRblas.so
LAPACK: /home/idies/R/lib64/R/lib/libRlapack.so

locale:
 [1] LC_CTYPE=en_US.UTF-8       LC_NUMERIC=C              
 [3] LC_TIME=en_US.UTF-8        LC_COLLATE=en_US.UTF-8    
 [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    
[7] datasets  methods   base     

other attached packages:
 [1] scran_1.18.7                scater_1.18.6              
 [3] ggplot2_3.3.3               DropletUtils_1.10.3        
 [5] SingleCellExperiment_1.12.0 SummarizedExperiment_1.20.0
 [7] Biobase_2.50.0              GenomicRanges_1.42.0       
 [9] GenomeInfoDb_1.26.7         IRanges_2.24.1             
[11] S4Vectors_0.28.1            BiocGenerics_0.36.1        
[13] MatrixGenerics_1.2.1        matrixStats_0.58.0         

loaded via a namespace (and not attached):
 [1] viridis_0.6.1             edgeR_3.32.1             
 [3] BiocSingular_1.6.0        jsonlite_1.7.2           
 [5] viridisLite_0.4.0         DelayedMatrixStats_1.12.3
 [7] scuttle_1.0.4             R.utils_2.10.1           
 [9] assertthat_0.2.1          statmod_1.4.35           
[11] dqrng_0.2.1               GenomeInfoDbData_1.2.4   
[13] vipor_0.4.5               yaml_2.2.1               
[15] pillar_1.6.0              lattice_0.20-41          
[17] glue_1.4.2                limma_3.46.0             
[19] beachmat_2.6.4            digest_0.6.27            
[21] RColorBrewer_1.1-2        XVector_0.30.0           
[23] colorspace_2.0-0          cowplot_1.1.1            
[25] htmltools_0.5.1.1         Matrix_1.2-18            
[27] R.oo_1.24.0               pkgconfig_2.0.3          
[29] pheatmap_1.0.12           zlibbioc_1.36.0          
[31] purrr_0.3.4               scales_1.1.1             
[33] RSpectra_0.16-0           HDF5Array_1.18.1         
[35] BiocParallel_1.24.1       tibble_3.1.1             
[37] farver_2.1.0              generics_0.1.0           
[39] ellipsis_0.3.2            withr_2.4.2              
[41] cli_2.5.0                 magrittr_2.0.1           
[43] crayon_1.4.1              evaluate_0.14            
[45] R.methodsS3_1.8.1         fansi_0.4.2              
[47] bluster_1.0.0             beeswarm_0.3.1           
[49] tools_4.0.3               lifecycle_1.0.0          
[51] Rhdf5lib_1.12.1           munsell_0.5.0            
[53] locfit_1.5-9.4            DelayedArray_0.16.3      
[55] irlba_2.3.3               compiler_4.0.3           
[57] rsvd_1.0.5                rlang_0.4.10             
[59] rhdf5_2.34.0              grid_4.0.3               
[61] RCurl_1.98-1.3            rstudioapi_0.13          
[63] rhdf5filters_1.2.0        BiocNeighbors_1.8.2      
[65] igraph_1.2.6              labeling_0.4.2           
[67] bitops_1.0-7              rmarkdown_2.7            
[69] gtable_0.3.0              DBI_1.1.1                
[71] R6_2.5.0                  gridExtra_2.3            
[73] knitr_1.33                dplyr_1.0.7              
[75] uwot_0.1.10               utf8_1.2.1               
[77] ggbeeswarm_0.6.0          Rcpp_1.0.6               
[79] vctrs_0.3.8               tidyselect_1.1.1         
[81] xfun_0.22                 sparseMatrixStats_1.2.1