Chapter 7 Lawlor human pancreas (SMARTer)
7.1 Introduction
This performs an analysis of the Lawlor et al. (2017) dataset, consisting of human pancreas cells from various donors.
7.3 Quality control
library(scater)
stats <- perCellQCMetrics(sce.lawlor,
subsets=list(Mito=which(rowData(sce.lawlor)$SEQNAME=="MT")))
qc <- quickPerCellQC(stats, percent_subsets="subsets_Mito_percent",
batch=sce.lawlor$`islet unos id`)
sce.lawlor <- sce.lawlor[,!qc$discard]colData(unfiltered) <- cbind(colData(unfiltered), stats)
unfiltered$discard <- qc$discard
gridExtra::grid.arrange(
plotColData(unfiltered, x="islet unos id", y="sum", colour_by="discard") +
scale_y_log10() + ggtitle("Total count") +
theme(axis.text.x = element_text(angle = 90)),
plotColData(unfiltered, x="islet unos id", y="detected",
colour_by="discard") + scale_y_log10() + ggtitle("Detected features") +
theme(axis.text.x = element_text(angle = 90)),
plotColData(unfiltered, x="islet unos id", y="subsets_Mito_percent",
colour_by="discard") + ggtitle("Mito percent") +
theme(axis.text.x = element_text(angle = 90)),
ncol=2
)
Figure 7.1: Distribution of each QC metric across cells from each donor of the Lawlor pancreas dataset. Each point represents a cell and is colored according to whether that cell was discarded.
Figure 7.2: Percentage of mitochondrial reads in each cell in the 416B dataset compared to the total count. Each point represents a cell and is colored according to whether that cell was discarded.
## low_lib_size low_n_features high_subsets_Mito_percent
## 9 5 25
## discard
## 347.4 Normalization
library(scran)
set.seed(1000)
clusters <- quickCluster(sce.lawlor)
sce.lawlor <- computeSumFactors(sce.lawlor, clusters=clusters)
sce.lawlor <- logNormCounts(sce.lawlor)## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.295 0.781 0.963 1.000 1.182 2.629plot(librarySizeFactors(sce.lawlor), sizeFactors(sce.lawlor), pch=16,
xlab="Library size factors", ylab="Deconvolution factors", log="xy")
Figure 7.3: Relationship between the library size factors and the deconvolution size factors in the Lawlor pancreas dataset.
7.5 Variance modelling
Using age as a proxy for the donor.
dec.lawlor <- modelGeneVar(sce.lawlor, block=sce.lawlor$`islet unos id`)
chosen.genes <- getTopHVGs(dec.lawlor, n=2000)par(mfrow=c(4,2))
blocked.stats <- dec.lawlor$per.block
for (i in colnames(blocked.stats)) {
current <- blocked.stats[[i]]
plot(current$mean, current$total, main=i, pch=16, cex=0.5,
xlab="Mean of log-expression", ylab="Variance of log-expression")
curfit <- metadata(current)
curve(curfit$trend(x), col='dodgerblue', add=TRUE, lwd=2)
}
Figure 7.4: Per-gene variance as a function of the mean for the log-expression values in the Lawlor pancreas dataset. Each point represents a gene (black) with the mean-variance trend (blue) fitted separately for each donor.
7.7 Clustering
snn.gr <- buildSNNGraph(sce.lawlor, use.dimred="PCA")
colLabels(sce.lawlor) <- factor(igraph::cluster_walktrap(snn.gr)$membership)##
## Acinar Alpha Beta Delta Ductal Gamma/PP None/Other Stellate
## 1 1 0 0 13 2 16 2 0
## 2 0 1 76 1 0 0 0 0
## 3 0 161 1 0 0 1 2 0
## 4 0 1 0 1 0 0 5 19
## 5 0 0 175 4 1 0 1 0
## 6 22 0 0 0 0 0 0 0
## 7 0 75 0 0 0 0 0 0
## 8 0 0 0 1 20 0 2 0##
## ACCG268 ACCR015A ACEK420A ACEL337 ACHY057 ACIB065 ACIW009 ACJV399
## 1 8 2 2 4 4 4 9 1
## 2 14 3 2 33 3 2 4 17
## 3 36 23 14 13 14 14 21 30
## 4 7 1 0 1 0 4 9 4
## 5 34 10 4 39 7 23 24 40
## 6 0 2 13 0 0 0 5 2
## 7 32 12 0 5 6 7 4 9
## 8 1 1 2 1 2 1 12 3gridExtra::grid.arrange(
plotTSNE(sce.lawlor, colour_by="label"),
plotTSNE(sce.lawlor, colour_by="islet unos id"),
ncol=2
)
Figure 5.3: Obligatory \(t\)-SNE plots of the Lawlor pancreas dataset. Each point represents a cell that is colored by cluster (left) or batch (right).
Session Info
R version 4.2.1 (2022-06-23)
Platform: x86_64-pc-linux-gnu (64-bit)
Running under: Ubuntu 20.04.5 LTS
Matrix products: default
BLAS: /home/biocbuild/bbs-3.16-bioc/R/lib/libRblas.so
LAPACK: /home/biocbuild/bbs-3.16-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] stats4 stats graphics grDevices utils datasets methods
[8] base
other attached packages:
[1] BiocSingular_1.14.0 scran_1.26.0
[3] scater_1.26.0 ggplot2_3.3.6
[5] scuttle_1.8.0 ensembldb_2.22.0
[7] AnnotationFilter_1.22.0 GenomicFeatures_1.50.0
[9] AnnotationDbi_1.60.0 AnnotationHub_3.6.0
[11] BiocFileCache_2.6.0 dbplyr_2.2.1
[13] scRNAseq_2.11.0 SingleCellExperiment_1.20.0
[15] SummarizedExperiment_1.28.0 Biobase_2.58.0
[17] GenomicRanges_1.50.0 GenomeInfoDb_1.34.0
[19] IRanges_2.32.0 S4Vectors_0.36.0
[21] BiocGenerics_0.44.0 MatrixGenerics_1.10.0
[23] matrixStats_0.62.0 BiocStyle_2.26.0
[25] rebook_1.8.0
loaded via a namespace (and not attached):
[1] igraph_1.3.5 lazyeval_0.2.2
[3] BiocParallel_1.32.0 digest_0.6.30
[5] htmltools_0.5.3 viridis_0.6.2
[7] fansi_1.0.3 magrittr_2.0.3
[9] memoise_2.0.1 ScaledMatrix_1.6.0
[11] cluster_2.1.4 limma_3.54.0
[13] Biostrings_2.66.0 prettyunits_1.1.1
[15] colorspace_2.0-3 blob_1.2.3
[17] rappdirs_0.3.3 ggrepel_0.9.1
[19] xfun_0.34 dplyr_1.0.10
[21] crayon_1.5.2 RCurl_1.98-1.9
[23] jsonlite_1.8.3 graph_1.76.0
[25] glue_1.6.2 gtable_0.3.1
[27] zlibbioc_1.44.0 XVector_0.38.0
[29] DelayedArray_0.24.0 scales_1.2.1
[31] edgeR_3.40.0 DBI_1.1.3
[33] Rcpp_1.0.9 viridisLite_0.4.1
[35] xtable_1.8-4 progress_1.2.2
[37] dqrng_0.3.0 bit_4.0.4
[39] rsvd_1.0.5 metapod_1.6.0
[41] httr_1.4.4 dir.expiry_1.6.0
[43] ellipsis_0.3.2 pkgconfig_2.0.3
[45] XML_3.99-0.12 farver_2.1.1
[47] CodeDepends_0.6.5 sass_0.4.2
[49] locfit_1.5-9.6 utf8_1.2.2
[51] labeling_0.4.2 tidyselect_1.2.0
[53] rlang_1.0.6 later_1.3.0
[55] munsell_0.5.0 BiocVersion_3.16.0
[57] tools_4.2.1 cachem_1.0.6
[59] cli_3.4.1 generics_0.1.3
[61] RSQLite_2.2.18 ExperimentHub_2.6.0
[63] evaluate_0.17 stringr_1.4.1
[65] fastmap_1.1.0 yaml_2.3.6
[67] knitr_1.40 bit64_4.0.5
[69] purrr_0.3.5 KEGGREST_1.38.0
[71] sparseMatrixStats_1.10.0 mime_0.12
[73] xml2_1.3.3 biomaRt_2.54.0
[75] compiler_4.2.1 beeswarm_0.4.0
[77] filelock_1.0.2 curl_4.3.3
[79] png_0.1-7 interactiveDisplayBase_1.36.0
[81] statmod_1.4.37 tibble_3.1.8
[83] bslib_0.4.0 stringi_1.7.8
[85] highr_0.9 bluster_1.8.0
[87] lattice_0.20-45 ProtGenerics_1.30.0
[89] Matrix_1.5-1 vctrs_0.5.0
[91] pillar_1.8.1 lifecycle_1.0.3
[93] BiocManager_1.30.19 jquerylib_0.1.4
[95] BiocNeighbors_1.16.0 cowplot_1.1.1
[97] bitops_1.0-7 irlba_2.3.5.1
[99] httpuv_1.6.6 rtracklayer_1.58.0
[101] R6_2.5.1 BiocIO_1.8.0
[103] bookdown_0.29 promises_1.2.0.1
[105] gridExtra_2.3 vipor_0.4.5
[107] codetools_0.2-18 assertthat_0.2.1
[109] rjson_0.2.21 withr_2.5.0
[111] GenomicAlignments_1.34.0 Rsamtools_2.14.0
[113] GenomeInfoDbData_1.2.9 parallel_4.2.1
[115] hms_1.1.2 grid_4.2.1
[117] beachmat_2.14.0 rmarkdown_2.17
[119] DelayedMatrixStats_1.20.0 Rtsne_0.16
[121] shiny_1.7.3 ggbeeswarm_0.6.0
[123] restfulr_0.0.15 References
Lawlor, N., J. George, M. Bolisetty, R. Kursawe, L. Sun, V. Sivakamasundari, I. Kycia, P. Robson, and M. L. Stitzel. 2017. “Single-cell transcriptomes identify human islet cell signatures and reveal cell-type-specific expression changes in type 2 diabetes.” Genome Res. 27 (2): 208–22.