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 1 13 2 16 2 0
## 2 0 0 75 1 0 0 0 0
## 3 0 161 1 0 0 1 2 0
## 4 0 1 0 1 0 0 5 19
## 5 22 0 0 0 0 0 0 0
## 6 0 0 174 4 1 0 1 0
## 7 0 76 1 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 2
## 2 13 3 2 33 3 2 4 16
## 3 36 23 14 13 14 14 21 30
## 4 7 1 0 1 0 4 9 4
## 5 0 2 13 0 0 0 5 2
## 6 34 10 4 39 7 23 24 39
## 7 33 12 0 5 6 7 4 10
## 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 4.4.0 beta (2024-04-15 r86425)
Platform: x86_64-pc-linux-gnu
Running under: Ubuntu 22.04.4 LTS
Matrix products: default
BLAS: /home/biocbuild/bbs-3.19-bioc/R/lib/libRblas.so
LAPACK: /usr/lib/x86_64-linux-gnu/lapack/liblapack.so.3.10.0
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
time zone: America/New_York
tzcode source: system (glibc)
attached base packages:
[1] stats4 stats graphics grDevices utils datasets methods
[8] base
other attached packages:
[1] BiocSingular_1.20.0 scran_1.32.0
[3] scater_1.32.0 ggplot2_3.5.1
[5] scuttle_1.14.0 ensembldb_2.28.0
[7] AnnotationFilter_1.28.0 GenomicFeatures_1.56.0
[9] AnnotationDbi_1.66.0 AnnotationHub_3.12.0
[11] BiocFileCache_2.12.0 dbplyr_2.5.0
[13] scRNAseq_2.18.0 SingleCellExperiment_1.26.0
[15] SummarizedExperiment_1.34.0 Biobase_2.64.0
[17] GenomicRanges_1.56.0 GenomeInfoDb_1.40.0
[19] IRanges_2.38.0 S4Vectors_0.42.0
[21] BiocGenerics_0.50.0 MatrixGenerics_1.16.0
[23] matrixStats_1.3.0 BiocStyle_2.32.0
[25] rebook_1.14.0
loaded via a namespace (and not attached):
[1] jsonlite_1.8.8 CodeDepends_0.6.6
[3] magrittr_2.0.3 ggbeeswarm_0.7.2
[5] gypsum_1.0.0 farver_2.1.1
[7] rmarkdown_2.26 BiocIO_1.14.0
[9] zlibbioc_1.50.0 vctrs_0.6.5
[11] memoise_2.0.1 Rsamtools_2.20.0
[13] DelayedMatrixStats_1.26.0 RCurl_1.98-1.14
[15] htmltools_0.5.8.1 S4Arrays_1.4.0
[17] curl_5.2.1 BiocNeighbors_1.22.0
[19] Rhdf5lib_1.26.0 SparseArray_1.4.0
[21] rhdf5_2.48.0 sass_0.4.9
[23] alabaster.base_1.4.0 bslib_0.7.0
[25] alabaster.sce_1.4.0 httr2_1.0.1
[27] cachem_1.0.8 GenomicAlignments_1.40.0
[29] igraph_2.0.3 mime_0.12
[31] lifecycle_1.0.4 pkgconfig_2.0.3
[33] rsvd_1.0.5 Matrix_1.7-0
[35] R6_2.5.1 fastmap_1.1.1
[37] GenomeInfoDbData_1.2.12 digest_0.6.35
[39] colorspace_2.1-0 paws.storage_0.5.0
[41] dqrng_0.3.2 irlba_2.3.5.1
[43] ExperimentHub_2.12.0 RSQLite_2.3.6
[45] beachmat_2.20.0 labeling_0.4.3
[47] filelock_1.0.3 fansi_1.0.6
[49] httr_1.4.7 abind_1.4-5
[51] compiler_4.4.0 bit64_4.0.5
[53] withr_3.0.0 BiocParallel_1.38.0
[55] viridis_0.6.5 DBI_1.2.2
[57] highr_0.10 HDF5Array_1.32.0
[59] alabaster.ranges_1.4.0 alabaster.schemas_1.4.0
[61] rappdirs_0.3.3 DelayedArray_0.30.0
[63] bluster_1.14.0 rjson_0.2.21
[65] tools_4.4.0 vipor_0.4.7
[67] beeswarm_0.4.0 glue_1.7.0
[69] restfulr_0.0.15 rhdf5filters_1.16.0
[71] grid_4.4.0 Rtsne_0.17
[73] cluster_2.1.6 generics_0.1.3
[75] gtable_0.3.5 metapod_1.12.0
[77] ScaledMatrix_1.12.0 utf8_1.2.4
[79] XVector_0.44.0 ggrepel_0.9.5
[81] BiocVersion_3.19.1 pillar_1.9.0
[83] limma_3.60.0 dplyr_1.1.4
[85] lattice_0.22-6 rtracklayer_1.64.0
[87] bit_4.0.5 tidyselect_1.2.1
[89] paws.common_0.7.2 locfit_1.5-9.9
[91] Biostrings_2.72.0 knitr_1.46
[93] gridExtra_2.3 bookdown_0.39
[95] ProtGenerics_1.36.0 edgeR_4.2.0
[97] xfun_0.43 statmod_1.5.0
[99] UCSC.utils_1.0.0 lazyeval_0.2.2
[101] yaml_2.3.8 evaluate_0.23
[103] codetools_0.2-20 tibble_3.2.1
[105] alabaster.matrix_1.4.0 BiocManager_1.30.22
[107] graph_1.82.0 cli_3.6.2
[109] munsell_0.5.1 jquerylib_0.1.4
[111] Rcpp_1.0.12 dir.expiry_1.12.0
[113] png_0.1-8 XML_3.99-0.16.1
[115] parallel_4.4.0 blob_1.2.4
[117] sparseMatrixStats_1.16.0 bitops_1.0-7
[119] viridisLite_0.4.2 alabaster.se_1.4.0
[121] scales_1.3.0 purrr_1.0.2
[123] crayon_1.5.2 rlang_1.1.3
[125] cowplot_1.1.3 KEGGREST_1.44.0 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.