Setup
Fragment files
a5_frags <- "/data1/shahs3/isabl_data_lake/analyses/86/75/28675/TCGA-06-A5U0-01A-31-A615-42-X011-S07_aliquot/outs/fragments.tsv.gz"
aa_frags <- "/data1/shahs3/isabl_data_lake/analyses/86/67/28667/TCGA-4W-AA9S-01A-22-A617-42-X015-S12_aliquot/outs/fragments.tsv.gz"
cbs1 <- read.csv("/data1/shahs3/isabl_data_lake/analyses/86/75/28675/TCGA-06-A5U0-01A-31-A615-42-X011-S07_aliquot/outs/singlecell.csv")
cbs2 <- read.csv("/data1/shahs3/isabl_data_lake/analyses/86/67/28667/TCGA-4W-AA9S-01A-22-A617-42-X015-S12_aliquot/outs/singlecell.csv")
sample_list <- list(
"A5U0" = list(
"fragments_file" = a5_frags,
"cells" = cbs1$barcode[cbs1$is__cell_barcode == 1]
),
"AA9S" = list(
"fragments_file" = aa_frags,
"cells" = cbs2$barcode[cbs2$is__cell_barcode == 1]
)
)Generate bins object
bins <- get_tiled_bins(bs_genome = BSgenome.Hsapiens.UCSC.hg38, tilewidth = 1e7)Get blacklist
blacklist <- get_blacklist(genome = "hg38")Load WGS derived CNV calls
a5u0_wgs <- read.table(file = "/data1/shahs3/junobackup/users/mcphera1/projects/gdan_atac/from_shahab/TCGA-06-A5U0-allelic-CN.tsv", header = T, sep = "\t")
aa9s_wgs <- read.table(file = "/data1/shahs3/junobackup/users/zatzmanm/repos/scatac_awg/R/eventual_bookdown/pt_vignettes/TCGA-4W-AA9S-allelic-CN.tsv", header = T, sep = "\t")
wgs_ascn <- list(A5U0 = a5u0_wgs, AA9S = aa9s_wgs)Process with SCATools
sce_list <- lapply(names(sample_list), FUN = function(sample_id) {
cli::cli_alert_info("Running {sample_id}")
sce <- run_scatools(
sample_id = sample_id,
fragment_file = sample_list[[sample_id]]$fragments_file,
cells = sample_list[[sample_id]]$cells,
bins = bins,
blacklist = blacklist,
outdir = file.path("results", sample_id),
verbose = TRUE,
overwrite = FALSE,
segment = FALSE,
ncores = 16,
save_h5ad = FALSE
)
# Depth based clustering
sce <- cluster_seurat(sce, assay_name = "counts_gc_modal_smoothed_ratios", suffix = "_depth", resolution = 0.4, verbose = FALSE)
# Relevel clones
if (sample_id == "A5U0") {
sce$clusters_depth <- factor(sce$clusters_depth, levels = c(0, 1, 3, 2), labels = c("A", "B", "C", "N"))
}
})Integrate WGS derived CNV data
sce_list <- lapply(names(sce_list), FUN = function(sample_id) {
sce <- sce_list[[sample_id]]
# Integrate WGS derived CNV data
df_wgs <- wgs_ascn[[sample_id]] %>%
mutate(
total = 2 * (CN_MAJOR + CN_MINOR),
major = 2 * CN_MAJOR,
minor = 2 * CN_MINOR,
chr = factor(CONTIG, levels = gtools::mixedsort(unique(CONTIG)))
) %>%
dplyr::rename("af" = "ALLELIC_FRACTION") %>%
mutate(
ai = abs(af - 0.5) / 0.5,
ai2 = 0.5 - abs(af - 0.5)
)
df_grange <- df_wgs %>%
makeGRangesFromDataFrame(seqnames.field = "chr", keep.extra.columns = T)
# Integrate with our scATAC data
int_granges <- integrate_segments(x = rowRanges(sce), y = df_grange, granges_signal_colname = c("total", "major", "minor", "af", "ai", "ai2"))
rowRanges(sce) <- int_granges
rownames(sce) <- rowData(sce)$ID
return(sce)
})
names(sce_list) <- names(sample_list)Plotting
col_clones <- function(clones) {
c(dittoColors()[1:length(unique(clones[clones != "N"]))], "black")
}
pls <- imap(sce_list, .f = function(sce, sample_id) {
pl_cols <- col_clones(sce$clusters)
names(pl_cols) <- levels(sce$clusters)
p1 <- dittoDimPlot(sce, var = "clusters", reduction.use = "UMAP") + scale_color_manual(values = pl_cols) +
theme(aspect.ratio = 1) +
labs(color = "Copy Number Cluster", title = NULL) +
theme(legend.position = "none")
rowRanges(sce)$WGS <- rowRanges(sce)$total
ht1 <- cloneCnaHeatmap(sce, assay_name = "segment_merged_logratios", clone_name = "clusters", bulk_cn_col = "WGS", col_clones = col_clones(sce$clusters), legend_name = "logr", col_fun = logr_col_fun(breaks = c(-0.6, -0.1, 0.1, 0.6), colors = c("blue", "white", "white", "red"))) %>%
as.ggplot()
pcomb <- p1 + ht1 + plot_layout(widths = c(3, 10))
return(pcomb)
})
names(pls) <- names(sample_list)
Session Info
Session Info
devtools::session_info()## ─ Session info ───────────────────────────────────────────────────────────────────────────────────────
## setting value
## version R version 4.3.2 (2023-10-31)
## os Ubuntu 22.04.3 LTS
## system x86_64, linux-gnu
## ui RStudio
## language (EN)
## collate en_US.UTF-8
## ctype en_US.UTF-8
## tz Etc/UTC
## date 2024-07-09
## rstudio 2023.12.0+369 Ocean Storm (server)
## pandoc 3.1.11.1 @ /data1/shahs3/users/zatzmanm/work/envs/miniforge3/bin/ (via rmarkdown)
##
## ─ Packages ───────────────────────────────────────────────────────────────────────────────────────────
## ! package * version date (UTC) lib source
## P abind 1.4-5 2016-07-21 [?] RSPM
## AnnotationDbi 1.64.1 2023-11-03 [1] Bioconductor
## P beachmat 2.18.1 2024-02-14 [?] Bioconduc~
## P Biobase * 2.62.0 2023-10-24 [?] Bioconductor
## BiocFileCache 2.10.2 2024-03-27 [1] Bioconductor 3.18 (R 4.3.2)
## P BiocGenerics * 0.48.1 2023-11-01 [?] Bioconductor
## P BiocIO * 1.12.0 2023-10-24 [?] Bioconductor
## P BiocManager 1.30.23 2024-05-04 [?] RSPM
## P BiocParallel 1.36.0 2023-10-24 [?] Bioconductor
## biomaRt 2.58.2 2024-01-30 [1] Bioconductor 3.18 (R 4.3.2)
## P Biostrings * 2.70.3 2024-03-13 [?] Bioconduc~
## P bit 4.0.5 2022-11-15 [?] RSPM (R 4.3.0)
## P bit64 4.0.5 2020-08-30 [?] RSPM (R 4.3.0)
## P bitops 1.0-7 2021-04-24 [?] RSPM
## P blob 1.2.4 2023-03-17 [?] RSPM (R 4.3.0)
## P BSgenome * 1.70.2 2024-02-08 [?] Bioconductor 3.18 (R 4.3.2)
## P BSgenome.Hsapiens.UCSC.hg38 * 1.4.5 2024-02-20 [?] Bioconductor
## P cachem 1.1.0 2024-05-16 [?] RSPM
## P Cairo 1.6-2 2023-11-28 [?] RSPM
## P callr 3.7.6 2024-03-25 [?] RSPM
## P circlize 0.4.16 2024-02-20 [?] RSPM
## cli 3.6.3 2024-06-21 [1] RSPM (R 4.3.0)
## P clue 0.3-65 2023-09-23 [?] RSPM (R 4.3.0)
## P cluster 2.1.6 2023-12-01 [?] RSPM (R 4.3.0)
## codetools 0.2-20 2024-03-31 [1] RSPM (R 4.3.0)
## P colorspace 2.1-0 2023-01-23 [?] RSPM
## P ComplexHeatmap 2.18.0 2023-10-24 [?] Bioconductor
## confintr 1.0.2 2023-06-04 [1] RSPM (R 4.3.0)
## P cowplot 1.1.3 2024-01-22 [?] RSPM (R 4.3.0)
## crayon 1.5.3 2024-06-20 [1] RSPM (R 4.3.0)
## P curl 5.2.1 2024-03-01 [?] RSPM
## P data.table 1.15.4 2024-03-30 [?] RSPM
## P DBI 1.2.3 2024-06-02 [?] RSPM
## dbplyr 2.5.0 2024-03-19 [1] RSPM (R 4.3.0)
## P DelayedArray 0.28.0 2023-10-24 [?] Bioconductor
## P DelayedMatrixStats 1.24.0 2023-10-24 [?] Bioconductor
## P desc 1.4.3 2023-12-10 [?] RSPM (R 4.3.0)
## P devtools 2.4.5 2022-10-11 [?] RSPM (R 4.3.0)
## digest 0.6.36 2024-06-23 [1] RSPM (R 4.3.0)
## P dittoSeq * 1.14.3 2024-03-20 [?] Bioconduc~
## P doParallel 1.0.17 2022-02-07 [?] RSPM (R 4.3.0)
## P dplyr * 1.1.4 2023-11-17 [?] RSPM
## P dqrng 0.4.1 2024-05-28 [?] RSPM
## P DropletUtils 1.22.0 2023-10-24 [?] Bioconductor
## P DT 0.33 2024-04-04 [?] RSPM
## P edgeR 4.0.16 2024-02-18 [?] Bioconduc~
## P ellipsis 0.3.2 2021-04-29 [?] RSPM (R 4.3.0)
## P evaluate 0.24.0 2024-06-10 [?] RSPM
## P fansi 1.0.6 2023-12-08 [?] RSPM
## P farver 2.1.2 2024-05-13 [?] RSPM
## P fastmap 1.2.0 2024-05-15 [?] RSPM
## P filelock 1.0.3 2023-12-11 [?] RSPM (R 4.3.0)
## P forcats * 1.0.0 2023-01-29 [?] RSPM (R 4.3.0)
## P foreach 1.5.2 2022-02-02 [?] RSPM (R 4.3.0)
## P fs 1.6.4 2024-04-25 [?] RSPM
## P generics 0.1.3 2022-07-05 [?] RSPM
## P GenomeInfoDb * 1.38.8 2024-03-15 [?] RSPM (R 4.3.2)
## P GenomeInfoDbData 1.2.11 2024-02-20 [?] Bioconductor
## P GenomicAlignments 1.38.2 2024-01-16 [?] Bioconduc~
## GenomicFeatures 1.54.4 2024-03-13 [1] Bioconductor 3.18 (R 4.3.2)
## P GenomicRanges * 1.54.1 2023-10-29 [?] Bioconductor
## P GetoptLong 1.0.5 2020-12-15 [?] RSPM (R 4.3.0)
## ggplot2 * 3.5.1 2024-04-23 [1] RSPM (R 4.3.0)
## ggplotify * 0.1.2 2023-08-09 [1] RSPM (R 4.3.0)
## ggpmisc 0.6.0 2024-06-28 [1] RSPM (R 4.3.0)
## ggpp 0.5.8-1 2024-07-01 [1] RSPM (R 4.3.0)
## P ggrepel 0.9.5 2024-01-10 [?] RSPM
## P ggridges 0.5.6 2024-01-23 [?] RSPM (R 4.3.0)
## P GlobalOptions 0.1.2 2020-06-10 [?] RSPM (R 4.3.0)
## P glue 1.7.0 2024-01-09 [?] RSPM
## P gridExtra 2.3 2017-09-09 [?] RSPM
## gridGraphics 0.5-1 2020-12-13 [1] RSPM (R 4.3.0)
## P gtable 0.3.5 2024-04-22 [?] RSPM
## P gtools 3.9.5 2023-11-20 [?] RSPM (R 4.3.0)
## P HDF5Array 1.30.1 2024-02-14 [?] Bioconductor 3.18 (R 4.3.2)
## P highr 0.11 2024-05-26 [?] RSPM
## P hms 1.1.3 2023-03-21 [?] RSPM (R 4.3.0)
## P htmltools 0.5.8.1 2024-04-04 [?] RSPM
## P htmlwidgets 1.6.4 2023-12-06 [?] RSPM (R 4.3.0)
## P httpuv 1.6.15 2024-03-26 [?] RSPM
## P httr 1.4.7 2023-08-15 [?] RSPM (R 4.3.0)
## P IRanges * 2.36.0 2023-10-24 [?] Bioconductor
## P iterators 1.0.14 2022-02-05 [?] RSPM (R 4.3.0)
## P janitor 2.2.0 2023-02-02 [?] RSPM (R 4.3.0)
## P jsonlite 1.8.8 2023-12-04 [?] RSPM
## KEGGREST 1.42.0 2023-10-24 [1] Bioconductor
## knitr 1.48 2024-07-07 [1] RSPM (R 4.3.0)
## P labeling 0.4.3 2023-08-29 [?] RSPM
## P later 1.3.2 2023-12-06 [?] RSPM (R 4.3.0)
## lattice 0.22-6 2024-03-20 [1] RSPM (R 4.3.0)
## P lifecycle 1.0.4 2023-11-07 [?] RSPM
## P limma 3.58.1 2023-10-31 [?] Bioconductor
## locfit 1.5-9.10 2024-06-24 [1] RSPM (R 4.3.0)
## P logger 0.3.0 2024-03-05 [?] RSPM
## P lubridate * 1.9.3 2023-09-27 [?] RSPM (R 4.3.0)
## P magrittr 2.0.3 2022-03-30 [?] RSPM
## P MASS 7.3-60 2023-05-04 [?] CRAN (R 4.3.2)
## P Matrix 1.6-5 2024-01-11 [?] RSPM (R 4.3.0)
## P MatrixGenerics * 1.14.0 2023-10-24 [?] Bioconductor
## P MatrixModels 0.5-3 2023-11-06 [?] RSPM (R 4.3.0)
## P matrixStats * 1.3.0 2024-04-11 [?] RSPM
## P memoise 2.0.1 2021-11-26 [?] RSPM (R 4.3.0)
## mgcv 1.9-1 2023-12-21 [1] RSPM (R 4.3.0)
## P mime 0.12 2021-09-28 [?] RSPM (R 4.3.0)
## P miniUI 0.1.1.1 2018-05-18 [?] RSPM (R 4.3.0)
## P munsell 0.5.1 2024-04-01 [?] RSPM
## nlme 3.1-165 2024-06-06 [1] RSPM (R 4.3.0)
## P patchwork * 1.2.0 2024-01-08 [?] RSPM
## P pbmcapply 1.5.1 2022-04-28 [?] RSPM (R 4.3.0)
## P pheatmap 1.0.12 2019-01-04 [?] RSPM
## P pillar 1.9.0 2023-03-22 [?] RSPM
## P pkgbuild 1.4.4 2024-03-17 [?] RSPM (R 4.3.0)
## P pkgconfig 2.0.3 2019-09-22 [?] RSPM
## P pkgdown 2.1.0 2024-07-06 [?] RSPM
## P pkgload 1.3.4 2024-01-16 [?] RSPM (R 4.3.0)
## P png 0.1-8 2022-11-29 [?] RSPM
## P polynom 1.4-1 2022-04-11 [?] RSPM (R 4.3.0)
## P prettyunits 1.2.0 2023-09-24 [?] RSPM (R 4.3.0)
## P processx 3.8.4 2024-03-16 [?] RSPM
## P profvis 0.3.8 2023-05-02 [?] RSPM (R 4.3.0)
## P progress 1.2.3 2023-12-06 [?] RSPM (R 4.3.0)
## P promises 1.3.0 2024-04-05 [?] RSPM
## P ps 1.7.6 2024-01-18 [?] RSPM (R 4.3.0)
## P purrr * 1.0.2 2023-08-10 [?] RSPM
## P quantreg 5.98 2024-05-26 [?] RSPM
## P quarto 1.4 2024-03-06 [?] RSPM
## P R.cache 0.16.0 2022-07-21 [?] RSPM (R 4.3.0)
## P R.methodsS3 1.8.2 2022-06-13 [?] RSPM (R 4.3.0)
## P R.oo 1.26.0 2024-01-24 [?] RSPM (R 4.3.0)
## P R.utils 2.12.3 2023-11-18 [?] RSPM (R 4.3.0)
## P R6 2.5.1 2021-08-19 [?] RSPM
## P rappdirs 0.3.3 2021-01-31 [?] RSPM (R 4.3.0)
## P RColorBrewer 1.1-3 2022-04-03 [?] RSPM
## P Rcpp 1.0.12 2024-01-09 [?] RSPM
## P RCurl 1.98-1.14 2024-01-09 [?] RSPM
## P readr * 2.1.5 2024-01-10 [?] RSPM (R 4.3.0)
## P remotes 2.5.0 2024-03-17 [?] RSPM (R 4.3.0)
## P renv 1.0.7.9000 2024-07-09 [?] Github (rstudio/renv@4f911df)
## P restfulr 0.0.15 2022-06-16 [?] RSPM
## P rhdf5 2.46.1 2023-11-29 [?] Bioconductor 3.18 (R 4.3.2)
## P rhdf5filters 1.14.1 2023-11-06 [?] Bioconductor
## P Rhdf5lib 1.24.2 2024-02-07 [?] Bioconductor 3.18 (R 4.3.2)
## P rjson 0.2.21 2022-01-09 [?] RSPM
## P rlang 1.1.4 2024-06-04 [?] RSPM
## P rmarkdown 2.27 2024-05-17 [?] RSPM
## P rprojroot 2.0.4 2023-11-05 [?] RSPM (R 4.3.0)
## P Rsamtools 2.18.0 2023-10-24 [?] Bioconductor
## P RSQLite 2.3.7 2024-05-27 [?] RSPM
## P rstudioapi 0.16.0 2024-03-24 [?] RSPM
## rtracklayer * 1.62.0 2023-10-24 [1] Bioconductor
## P S4Arrays 1.2.1 2024-03-04 [?] Bioconduc~
## P S4Vectors * 0.40.2 2023-11-23 [?] Bioconduc~
## P scales 1.3.0 2023-11-28 [?] RSPM
## scatools * 0.1.1.9000 2024-07-09 [1] Github (mjz1/scatools@bd8df13)
## P scuttle 1.12.0 2023-10-24 [?] Bioconductor
## P sessioninfo 1.2.2 2021-12-06 [?] RSPM (R 4.3.0)
## P shape 1.4.6.1 2024-02-23 [?] RSPM
## P shiny 1.8.1.1 2024-04-02 [?] RSPM
## P SingleCellExperiment * 1.24.0 2023-10-24 [?] Bioconductor
## P snakecase 0.11.1 2023-08-27 [?] RSPM (R 4.3.0)
## P SparseArray 1.2.4 2024-02-11 [?] Bioconduc~
## SparseM 1.84 2024-06-25 [1] RSPM (R 4.3.0)
## P sparseMatrixStats 1.14.0 2023-10-24 [?] Bioconductor
## P statmod 1.5.0 2023-01-06 [?] RSPM
## P stringi 1.8.4 2024-05-06 [?] RSPM
## P stringr * 1.5.1 2023-11-14 [?] RSPM
## P styler 1.10.3 2024-04-07 [?] RSPM
## SummarizedExperiment * 1.32.0 2023-10-24 [1] Bioconductor
## survival 3.7-0 2024-06-05 [1] RSPM (R 4.3.0)
## P tibble * 3.2.1 2023-03-20 [?] RSPM
## P tidyr * 1.3.1 2024-01-24 [?] RSPM
## P tidyselect 1.2.1 2024-03-11 [?] RSPM
## tidyverse * 2.0.0 2023-02-22 [1] RSPM (R 4.3.0)
## P timechange 0.3.0 2024-01-18 [?] RSPM (R 4.3.0)
## P tzdb 0.4.0 2023-05-12 [?] RSPM (R 4.3.0)
## P urlchecker 1.0.1 2021-11-30 [?] RSPM (R 4.3.0)
## P usethis 2.2.3 2024-02-19 [?] RSPM
## P utf8 1.2.4 2023-10-22 [?] RSPM
## P vctrs 0.6.5 2023-12-01 [?] RSPM
## P viridisLite 0.4.2 2023-05-02 [?] RSPM
## P vroom 1.6.5 2023-12-05 [?] RSPM (R 4.3.0)
## P whisker 0.4.1 2022-12-05 [?] RSPM (R 4.3.0)
## P withr 3.0.0 2024-01-16 [?] RSPM
## xfun 0.45 2024-06-16 [1] RSPM (R 4.3.0)
## XML 3.99-0.17 2024-06-25 [1] RSPM (R 4.3.0)
## P xml2 1.3.6 2023-12-04 [?] RSPM (R 4.3.0)
## P xtable 1.8-4 2019-04-21 [?] RSPM (R 4.3.0)
## P XVector * 0.42.0 2023-10-24 [?] Bioconductor
## yaml 2.3.9 2024-07-05 [1] RSPM (R 4.3.0)
## yulab.utils 0.1.4 2024-01-28 [1] RSPM (R 4.3.0)
## P zlibbioc 1.48.2 2024-03-13 [?] Bioconduc~
##
## [1] /data1/shahs3/users/zatzmanm/work/.cache/R/renv/library/scatools-34e0c720/linux-ubuntu-jammy/R-4.3/x86_64-pc-linux-gnu
## [2] /data1/shahs3/users/zatzmanm/work/.cache/R/renv/sandbox/linux-ubuntu-jammy/R-4.3/x86_64-pc-linux-gnu/25ebdc09
##
## P ── Loaded and on-disk path mismatch.
##
## ──────────────────────────────────────────────────────────────────────────────────────────────────────