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 4.6.0 RC (2026-04-17 r89917)
Platform: x86_64-pc-linux-gnu
Running under: Ubuntu 24.04.4 LTS
Matrix products: default
BLAS: /home/biocbuild/bbs-3.24-bioc/R/lib/libRblas.so
LAPACK: /usr/lib/x86_64-linux-gnu/lapack/liblapack.so.3.12.0 LAPACK version 3.12.0
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_1.29.0 scran_1.41.0
[3] scater_1.41.1 ggplot2_4.0.3
[5] scuttle_1.23.0 ensembldb_2.37.0
[7] AnnotationFilter_1.37.0 GenomicFeatures_1.65.0
[9] AnnotationDbi_1.75.0 AnnotationHub_4.3.0
[11] BiocFileCache_3.3.0 dbplyr_2.5.2
[13] scRNAseq_2.27.0 SingleCellExperiment_1.35.0
[15] SummarizedExperiment_1.43.0 Biobase_2.73.1
[17] GenomicRanges_1.65.0 Seqinfo_1.3.0
[19] IRanges_2.47.0 S4Vectors_0.51.1
[21] BiocGenerics_0.59.0 generics_0.1.4
[23] MatrixGenerics_1.25.0 matrixStats_1.5.0
[25] BiocStyle_2.41.0 rebook_1.23.0
loaded via a namespace (and not attached):
[1] RColorBrewer_1.1-3 jsonlite_2.0.0 CodeDepends_0.6.7
[4] magrittr_2.0.5 ggbeeswarm_0.7.3 gypsum_1.9.0
[7] farver_2.1.2 rmarkdown_2.31 BiocIO_1.23.3
[10] vctrs_0.7.3 memoise_2.0.1 Rsamtools_2.29.0
[13] RCurl_1.98-1.18 htmltools_0.5.9 S4Arrays_1.13.0
[16] BiocBaseUtils_1.15.0 curl_7.1.0 BiocNeighbors_2.7.0
[19] Rhdf5lib_2.1.0 SparseArray_1.13.2 rhdf5_2.57.0
[22] sass_0.4.10 alabaster.base_1.13.0 bslib_0.10.0
[25] alabaster.sce_1.13.0 httr2_1.2.2 cachem_1.1.0
[28] GenomicAlignments_1.49.0 igraph_2.3.1 lifecycle_1.0.5
[31] pkgconfig_2.0.3 rsvd_1.0.5 Matrix_1.7-5
[34] R6_2.6.1 fastmap_1.2.0 digest_0.6.39
[37] dqrng_0.4.1 irlba_2.3.7 ExperimentHub_3.3.0
[40] RSQLite_2.4.6 beachmat_2.29.0 labeling_0.4.3
[43] filelock_1.0.3 httr_1.4.8 abind_1.4-8
[46] compiler_4.6.0 bit64_4.8.0 withr_3.0.2
[49] S7_0.2.2 BiocParallel_1.47.0 viridis_0.6.5
[52] DBI_1.3.0 HDF5Array_1.41.0 alabaster.ranges_1.13.0
[55] alabaster.schemas_1.13.0 rappdirs_0.3.4 DelayedArray_0.39.1
[58] bluster_1.23.0 rjson_0.2.23 tools_4.6.0
[61] vipor_0.4.7 otel_0.2.0 beeswarm_0.4.0
[64] glue_1.8.1 h5mread_1.5.0 restfulr_0.0.16
[67] rhdf5filters_1.25.0 grid_4.6.0 Rtsne_0.17
[70] cluster_2.1.8.2 gtable_0.3.6 metapod_1.21.0
[73] ScaledMatrix_1.21.0 XVector_0.53.0 ggrepel_0.9.8
[76] BiocVersion_3.24.0 pillar_1.11.1 limma_3.69.0
[79] dplyr_1.2.1 lattice_0.22-9 rtracklayer_1.73.0
[82] bit_4.6.0 tidyselect_1.2.1 locfit_1.5-9.12
[85] Biostrings_2.81.1 knitr_1.51 gridExtra_2.3
[88] bookdown_0.46 ProtGenerics_1.45.0 edgeR_4.11.0
[91] xfun_0.57 statmod_1.5.1 UCSC.utils_1.9.0
[94] lazyeval_0.2.3 yaml_2.3.12 evaluate_1.0.5
[97] codetools_0.2-20 cigarillo_1.3.0 tibble_3.3.1
[100] alabaster.matrix_1.13.0 BiocManager_1.30.27 graph_1.91.0
[103] cli_3.6.6 jquerylib_0.1.4 dichromat_2.0-0.1
[106] Rcpp_1.1.1-1.1 GenomeInfoDb_1.49.0 dir.expiry_1.21.0
[109] png_0.1-9 XML_3.99-0.23 parallel_4.6.0
[112] blob_1.3.0 bitops_1.0-9 viridisLite_0.4.3
[115] alabaster.se_1.13.0 scales_1.4.0 purrr_1.2.2
[118] crayon_1.5.3 rlang_1.2.0 cowplot_1.2.0
[121] KEGGREST_1.53.0 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.