Quality control on Chromium CRISPR Guide Capture libraries
Kayla Jackson and A. Sina Booeshaghi
2023-11-30
Source:vignettes/vig12_crispr.Rmd
vig12_crispr.RmdIntroduction
The data in this vignette is shipped with the cellatlas
repository. The count matrix and metadata are provided in the
cellatlas/examples folder as an AnnData
object. We will begin by loading the object and converting it to a
SingleCellExperiment object.
library(stringr)
library(Matrix)
library(DropletUtils)
library(SpatialExperiment)
library(SpatialFeatureExperiment)
library(scater)
library(scuttle)
library(Voyager)
library(ggplot2)
theme_set(theme_bw())
if (!file.exists("10xcrispr.rds"))
download.file("https://github.com/pachterlab/voyager/raw/documentation-devel/vignettes/10xcrispr.rds", destfile = "10xcrispr.rds")
sce <- readRDS("10xcrispr.rds")
is_mito <- str_detect(rowData(sce)$gene_name, regex("^mt-", ignore_case=TRUE))
sum(is_mito)
#> [1] 0
sce <- addPerCellQCMetrics(sce, subsets = list(mito = is_mito))
names(colData(sce))
#> [1] "sum" "detected" "subsets_mito_sum"
#> [4] "subsets_mito_detected" "subsets_mito_percent" "total"
plotColData(sce, "sum") +
plotColData(sce, "detected")
plotColData(sce, x = "sum", y = "detected", bins = 100) +
scale_fill_distiller(palette = "Blues", direction = 1)
#> Scale for fill is already present.
#> Adding another scale for fill, which will replace the existing scale.
plotColData(sce, x = "sum", y = "subsets_mito_detected", bins = 100) +
scale_fill_distiller(palette = "Blues", direction = 1)
#> Scale for fill is already present.
#> Adding another scale for fill, which will replace the existing scale.
#> Warning: Computation failed in `stat_bin2d()`
#> Caused by error in `bin2d_breaks()`:
#> ! `origin` must be a number, not `NaN`.
bcrank <- barcodeRanks(counts(sce))
knee <- metadata(bcrank)$knee
inflection <- metadata(bcrank)$inflection
plot(bcrank$rank, bcrank$total, log="xy",
xlab="Rank", ylab="Total ClickTags count", cex.lab=1.2)
#> Warning in xy.coords(x, y, xlabel, ylabel, log): 3 y values <= 0 omitted from
#> logarithmic plot
abline(h=inflection, col="darkgreen", lty=2)
abline(h=knee, col="dodgerblue", lty=2)
sce <- sce[, which(sce$total > inflection)]
sce <- sce[rowSums(counts(sce)) > 0,]
sce
#> class: SingleCellExperiment
#> dim: 89 293
#> metadata(0):
#> assays(1): counts
#> rownames(89): Non-Targeting-5 Non-Targeting-7 ... HDAC1-1 HDAC1-2
#> rowData names(1): feature_name
#> colnames(293): AAAGAACAGAAACGAA AAAGAACGTTTGTCGA ... TTTGATCCAGGAGAAA
#> TTTGATCGTGGTAGTG
#> colData names(6): sum detected ... subsets_mito_percent total
#> reducedDimNames(0):
#> mainExpName: NULL
#> altExpNames(0):
sessionInfo()
#> R version 4.3.2 (2023-10-31)
#> Platform: x86_64-apple-darwin20 (64-bit)
#> Running under: macOS Ventura 13.6
#>
#> Matrix products: default
#> BLAS: /Library/Frameworks/R.framework/Versions/4.3-x86_64/Resources/lib/libRblas.0.dylib
#> LAPACK: /Library/Frameworks/R.framework/Versions/4.3-x86_64/Resources/lib/libRlapack.dylib; LAPACK version 3.11.0
#>
#> locale:
#> [1] en_US.UTF-8/en_US.UTF-8/en_US.UTF-8/C/en_US.UTF-8/en_US.UTF-8
#>
#> time zone: UTC
#> tzcode source: internal
#>
#> attached base packages:
#> [1] stats4 stats graphics grDevices utils datasets methods
#> [8] base
#>
#> other attached packages:
#> [1] Voyager_1.4.0 scater_1.30.0
#> [3] ggplot2_3.4.4 scuttle_1.12.0
#> [5] SpatialFeatureExperiment_1.3.0 SpatialExperiment_1.12.0
#> [7] DropletUtils_1.22.0 SingleCellExperiment_1.24.0
#> [9] SummarizedExperiment_1.32.0 Biobase_2.62.0
#> [11] GenomicRanges_1.54.1 GenomeInfoDb_1.38.1
#> [13] IRanges_2.36.0 S4Vectors_0.40.2
#> [15] BiocGenerics_0.48.1 MatrixGenerics_1.14.0
#> [17] matrixStats_1.1.0 Matrix_1.6-3
#> [19] stringr_1.5.1
#>
#> loaded via a namespace (and not attached):
#> [1] RColorBrewer_1.1-3 jsonlite_1.8.7
#> [3] wk_0.9.0 magrittr_2.0.3
#> [5] ggbeeswarm_0.7.2 magick_2.8.1
#> [7] farver_2.1.1 rmarkdown_2.25
#> [9] fs_1.6.3 zlibbioc_1.48.0
#> [11] ragg_1.2.6 vctrs_0.6.4
#> [13] spdep_1.3-1 memoise_2.0.1
#> [15] DelayedMatrixStats_1.24.0 RCurl_1.98-1.13
#> [17] terra_1.7-55 htmltools_0.5.7
#> [19] S4Arrays_1.2.0 BiocNeighbors_1.20.0
#> [21] Rhdf5lib_1.24.0 s2_1.1.4
#> [23] SparseArray_1.2.2 rhdf5_2.46.0
#> [25] sass_0.4.7 spData_2.3.0
#> [27] KernSmooth_2.23-22 bslib_0.6.0
#> [29] desc_1.4.2 cachem_1.0.8
#> [31] igraph_1.5.1 lifecycle_1.0.4
#> [33] pkgconfig_2.0.3 rsvd_1.0.5
#> [35] R6_2.5.1 fastmap_1.1.1
#> [37] GenomeInfoDbData_1.2.11 digest_0.6.33
#> [39] ggnewscale_0.4.9 colorspace_2.1-0
#> [41] patchwork_1.1.3 rprojroot_2.0.4
#> [43] dqrng_0.3.1 RSpectra_0.16-1
#> [45] irlba_2.3.5.1 textshaping_0.3.7
#> [47] beachmat_2.18.0 labeling_0.4.3
#> [49] fansi_1.0.5 abind_1.4-5
#> [51] compiler_4.3.2 proxy_0.4-27
#> [53] withr_2.5.2 BiocParallel_1.36.0
#> [55] viridis_0.6.4 DBI_1.1.3
#> [57] highr_0.10 HDF5Array_1.30.0
#> [59] R.utils_2.12.3 DelayedArray_0.28.0
#> [61] rjson_0.2.21 classInt_0.4-10
#> [63] bluster_1.12.0 tools_4.3.2
#> [65] units_0.8-4 vipor_0.4.5
#> [67] beeswarm_0.4.0 R.oo_1.25.0
#> [69] glue_1.6.2 rhdf5filters_1.14.1
#> [71] grid_4.3.2 sf_1.0-14
#> [73] cluster_2.1.4 generics_0.1.3
#> [75] gtable_0.3.4 R.methodsS3_1.8.2
#> [77] class_7.3-22 BiocSingular_1.18.0
#> [79] ScaledMatrix_1.10.0 sp_2.1-2
#> [81] utf8_1.2.4 XVector_0.42.0
#> [83] ggrepel_0.9.4 pillar_1.9.0
#> [85] limma_3.58.1 dplyr_1.1.4
#> [87] lattice_0.22-5 deldir_2.0-2
#> [89] tidyselect_1.2.0 locfit_1.5-9.8
#> [91] knitr_1.45 gridExtra_2.3
#> [93] edgeR_4.0.2 xfun_0.41
#> [95] statmod_1.5.0 stringi_1.8.2
#> [97] yaml_2.3.7 boot_1.3-28.1
#> [99] evaluate_0.23 codetools_0.2-19
#> [101] tibble_3.2.1 cli_3.6.1
#> [103] systemfonts_1.0.5 munsell_0.5.0
#> [105] jquerylib_0.1.4 Rcpp_1.0.11
#> [107] parallel_4.3.2 pkgdown_2.0.7
#> [109] sparseMatrixStats_1.14.0 bitops_1.0-7
#> [111] viridisLite_0.4.2 scales_1.2.1
#> [113] e1071_1.7-13 purrr_1.0.2
#> [115] crayon_1.5.2 scico_1.5.0
#> [117] rlang_1.1.2 cowplot_1.1.1