Vignettes:
N.B. delta=0.25, p.threshold=0.0001
library(DSS)
## Loading required package: Biobase
## Loading required package: BiocGenerics
##
## Attaching package: 'BiocGenerics'
## The following objects are masked from 'package:stats':
##
## IQR, mad, sd, var, xtabs
## The following objects are masked from 'package:base':
##
## anyDuplicated, aperm, append, as.data.frame, basename, cbind,
## colnames, dirname, do.call, duplicated, eval, evalq, Filter, Find,
## get, grep, grepl, intersect, is.unsorted, lapply, Map, mapply,
## match, mget, order, paste, pmax, pmax.int, pmin, pmin.int,
## Position, rank, rbind, Reduce, rownames, sapply, setdiff, sort,
## table, tapply, union, unique, unsplit, which.max, which.min
## Welcome to Bioconductor
##
## Vignettes contain introductory material; view with
## 'browseVignettes()'. To cite Bioconductor, see
## 'citation("Biobase")', and for packages 'citation("pkgname")'.
## Loading required package: BiocParallel
## Loading required package: bsseq
## Loading required package: GenomicRanges
## Loading required package: stats4
## Loading required package: S4Vectors
##
## Attaching package: 'S4Vectors'
## The following objects are masked from 'package:base':
##
## expand.grid, I, unname
## Loading required package: IRanges
## Loading required package: GenomeInfoDb
## Loading required package: SummarizedExperiment
## Loading required package: MatrixGenerics
## Loading required package: matrixStats
##
## Attaching package: 'matrixStats'
## The following objects are masked from 'package:Biobase':
##
## anyMissing, rowMedians
##
## Attaching package: 'MatrixGenerics'
## The following objects are masked from 'package:matrixStats':
##
## colAlls, colAnyNAs, colAnys, colAvgsPerRowSet, colCollapse,
## colCounts, colCummaxs, colCummins, colCumprods, colCumsums,
## colDiffs, colIQRDiffs, colIQRs, colLogSumExps, colMadDiffs,
## colMads, colMaxs, colMeans2, colMedians, colMins, colOrderStats,
## colProds, colQuantiles, colRanges, colRanks, colSdDiffs, colSds,
## colSums2, colTabulates, colVarDiffs, colVars, colWeightedMads,
## colWeightedMeans, colWeightedMedians, colWeightedSds,
## colWeightedVars, rowAlls, rowAnyNAs, rowAnys, rowAvgsPerColSet,
## rowCollapse, rowCounts, rowCummaxs, rowCummins, rowCumprods,
## rowCumsums, rowDiffs, rowIQRDiffs, rowIQRs, rowLogSumExps,
## rowMadDiffs, rowMads, rowMaxs, rowMeans2, rowMedians, rowMins,
## rowOrderStats, rowProds, rowQuantiles, rowRanges, rowRanks,
## rowSdDiffs, rowSds, rowSums2, rowTabulates, rowVarDiffs, rowVars,
## rowWeightedMads, rowWeightedMeans, rowWeightedMedians,
## rowWeightedSds, rowWeightedVars
## The following object is masked from 'package:Biobase':
##
## rowMedians
## Loading required package: parallel
library(plotly)
## Loading required package: ggplot2
##
## Attaching package: 'plotly'
## The following object is masked from 'package:ggplot2':
##
## last_plot
## The following object is masked from 'package:IRanges':
##
## slice
## The following object is masked from 'package:S4Vectors':
##
## rename
## The following object is masked from 'package:stats':
##
## filter
## The following object is masked from 'package:graphics':
##
## layout
library(ggplot2)
library(scales)
source("~/Transgenerational/EMSeq/NewData_fromLaSitua/Methylation_helper.R")
##
## Attaching package: 'tidyr'
## The following object is masked from 'package:S4Vectors':
##
## expandInputFolder <- params$InputFolder
OutputFolder <- params$OutputFolderLoading of bsseq object with CpGs shared by at least 75% of samples.
bsseq_obj <- readRDS("/group/testa/Project/PGCLC/emseq_rebuttal/2.PreliminaryAnalysis/bsseq_obj_sharedby75ofall.rds") #getting bsseq object where sample selection and CpG filtering were already performed
bsseq_obj
## An object of type 'BSseq' with
## 3644178 methylation loci
## 18 samples
## has not been smoothed
## All assays are in-memoryPCA plot
This PCA is done on the new filtered BSseq object (different from the one in the preliminary exploration script!)
cellTypes_colors <- c(hiPSCs ="#dd1c77", iMeLCs ="#377eb8", hPGCLCs ="#4daf4a", hEGCLCs_p5 = "#ff7f00", hEGCLCs_p10 = "#ffc400")pca_res <- do_PCA(getMeth(BSseq = bsseq_obj, type = "raw"))
plot_PCA(pca_res = pca_res, anno = pData(bsseq_obj), col_anno = "Type", shape_anno = NULL, custom_colors = cellTypes_colors, point_size = 5)plot_PCA(pca_res = pca_res, anno = pData(bsseq_obj), col_anno = "Type", shape_anno = NULL, pc_x = "PC2", pc_y = "PC3", custom_colors = cellTypes_colors, point_size = 5)Loading results obtained with DSS::DMLtest function
dml_tests_files <- list.files(path = InputFolder, pattern = '*\\.rds', full.names = TRUE)
#dml_tests_files <- dml_tests_files[-1]
dml_tests_files
## [1] "/group/testa/Project/PGCLC/Rebuttal_paperEG2025/Output_DM/hEGCLCs_p10vshEGCLCs_p5.rds"
## [2] "/group/testa/Project/PGCLC/Rebuttal_paperEG2025/Output_DM/hEGCLCs_p10vshiPSCs.rds"
## [3] "/group/testa/Project/PGCLC/Rebuttal_paperEG2025/Output_DM/hEGCLCs_p10vshPGCLCs.rds"
## [4] "/group/testa/Project/PGCLC/Rebuttal_paperEG2025/Output_DM/hEGCLCs_p10vsiMeLCs.rds"
## [5] "/group/testa/Project/PGCLC/Rebuttal_paperEG2025/Output_DM/hEGCLCs_p5vshiPSCs.rds"
## [6] "/group/testa/Project/PGCLC/Rebuttal_paperEG2025/Output_DM/hEGCLCs_p5vshPGCLCs.rds"
## [7] "/group/testa/Project/PGCLC/Rebuttal_paperEG2025/Output_DM/hiPSCsvshPGCLCs.rds"
## [8] "/group/testa/Project/PGCLC/Rebuttal_paperEG2025/Output_DM/hiPSCsvsiMeLCs.rds"
## [9] "/group/testa/Project/PGCLC/Rebuttal_paperEG2025/Output_DM/iMeLCsvshEGCLCs_p5.rds"
## [10] "/group/testa/Project/PGCLC/Rebuttal_paperEG2025/Output_DM/iMeLCsvshPGCLCs.rds"Storing DMRs and DMLs Plotting number of DMRs
nr_tests <- length(dml_tests_files)
DM_tests_Res <- list()
DMR_Res <- list()
DML_Res <- list()
for(i in 1:nr_tests){
DM_tests_Res[[i]] <- readRDS(dml_tests_files[i])
DMR_Res[[i]] <- list()
DML_Res[[i]] <- list()
names(DM_tests_Res)[i] <- sub(".rds", "", basename(dml_tests_files))[i]
names(DMR_Res)[i] <- sub(".rds", "", basename(dml_tests_files))[i]
names(DML_Res)[i] <- sub(".rds", "", basename(dml_tests_files))[i]
DMR_Res[[i]] <- callDMR(DM_tests_Res[[i]], delta=0.25, p.threshold=0.0001)
DML_Res[[i]] <- callDML(DM_tests_Res[[i]], delta=0.25, p.threshold=0.0001)
}DMRbarplot(DMR=DMR_Res, comparison=1, y_lim = c(0,3300), interactive=TRUE)DMRbarplot_length(DMR=DMR_Res, comparison=1)DMRbarplot(DMR=DMR_Res, comparison=2, y_lim = c(0,3300), interactive=TRUE)DMRbarplot_length(DMR=DMR_Res, comparison=2)DMRbarplot(DMR=DMR_Res, comparison=3, y_lim = c(0,3300), interactive=TRUE)DMRbarplot_length(DMR=DMR_Res, comparison=3)DMRbarplot(DMR=DMR_Res, comparison=4, y_lim = c(0,3300), interactive=TRUE)DMRbarplot_length(DMR=DMR_Res, comparison=4)Barplot with all together
comparisons <- c("hEGCLCs_p10vshiPSCs", "hEGCLCs_p10vsiMeLCs", "hEGCLCs_p10vshPGCLCs", "hEGCLCs_p10vshEGCLCs_p5") #ordered with criteria
new_ylabel <- c("hEGCLCs_p10vshiPSCs" = "hiPSCs vs hEGCLCs_p10",
"hEGCLCs_p10vsiMeLCs" = "iMeLCs vs hEGCLCs_p10",
"hEGCLCs_p10vshPGCLCs" = "hPGCLCs vs hEGCLCs_p10",
"hEGCLCs_p10vshEGCLCs_p5" = "hEGCLCs_p5 vs hEGCLCs_p10")
DMRbarplot_all(DMR=DMR_Res, comparisons_ordered=comparisons, label_y=new_ylabel, y_lim = 3300, interactive=TRUE)comparisons <- c("hEGCLCs_p10vshiPSCs", "hEGCLCs_p10vshPGCLCs", "hEGCLCs_p10vshEGCLCs_p5") #ordered with criteria
new_ylabel <- c("hEGCLCs_p10vshiPSCs" = "hiPSCs vs hEGCLCs_p10",
"hEGCLCs_p10vshPGCLCs" = "hPGCLCs vs hEGCLCs_p10",
"hEGCLCs_p10vshEGCLCs_p5" = "hEGCLCs_p5 vs hEGCLCs_p10")
DMRbarplot_all(DMR=DMR_Res, comparisons_ordered=comparisons, label_y=new_ylabel, y_lim = 3300, interactive=TRUE)comparisons <- c("hEGCLCs_p10vshiPSCs", "hEGCLCs_p10vshEGCLCs_p5") #ordered with criteria
new_ylabel <- c("hEGCLCs_p10vshiPSCs" = "hiPSCs vs hEGCLCs_p10",
"hEGCLCs_p10vshEGCLCs_p5" = "hEGCLCs_p5 vs hEGCLCs_p10")
DMRbarplot_all(DMR=DMR_Res, comparisons_ordered=comparisons, label_y=new_ylabel, y_lim = 1000, interactive=TRUE)N.B: Q: Why doesn’t callDMR function return FDR for identified DMRs?
A: In DMR calling, the statistical test is perform for each CpG, and then the significant CpG are merged into regions. It is very difficult to estimate FDR at the region-level, based on the site level test results (p-values or FDR). This is a difficult question for all types of genome-wide assays such as the ChIP-seq. So I rather not to report a DMR-level FDR if it’s not accurate.
saveRDS(DM_tests_Res, paste0(OutputFolder, '/', 'DML_test_results.rds'))
saveRDS(DMR_Res, paste0(OutputFolder, '/', 'DMRs.rds'))
saveRDS(DML_Res, paste0(OutputFolder, '/', 'DMLs.rds'))SessionInfo <- sessionInfo()
Date <- date()Date
## [1] "Tue Aug 19 11:24:19 2025"
SessionInfo
## R version 4.2.1 (2022-06-23)
## Platform: x86_64-pc-linux-gnu (64-bit)
## Running under: Ubuntu 20.04.4 LTS
##
## Matrix products: default
## BLAS: /usr/lib/x86_64-linux-gnu/blas/libblas.so.3.9.0
## LAPACK: /usr/lib/x86_64-linux-gnu/lapack/liblapack.so.3.9.0
##
## locale:
## [1] LC_CTYPE=en_US.UTF-8 LC_NUMERIC=C
## [3] LC_TIME=en_US.UTF-8 LC_COLLATE=en_US.UTF-8
## [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] parallel stats4 stats graphics grDevices utils datasets
## [8] methods base
##
## other attached packages:
## [1] tidyr_1.3.0 scales_1.2.1
## [3] plotly_4.10.2 ggplot2_3.4.2
## [5] DSS_2.46.0 bsseq_1.34.0
## [7] SummarizedExperiment_1.28.0 MatrixGenerics_1.10.0
## [9] matrixStats_1.0.0 GenomicRanges_1.50.2
## [11] GenomeInfoDb_1.34.9 IRanges_2.32.0
## [13] S4Vectors_0.36.2 BiocParallel_1.32.6
## [15] Biobase_2.58.0 BiocGenerics_0.44.0
##
## loaded via a namespace (and not attached):
## [1] httr_1.4.6 sass_0.4.7
## [3] viridisLite_0.4.2 jsonlite_1.8.7
## [5] splines_4.2.1 DelayedMatrixStats_1.20.0
## [7] R.utils_2.12.2 gtools_3.9.4
## [9] bslib_0.5.0 highr_0.10
## [11] BSgenome_1.66.3 GenomeInfoDbData_1.2.9
## [13] Rsamtools_2.14.0 yaml_2.3.7
## [15] pillar_1.9.0 lattice_0.21-8
## [17] glue_1.6.2 limma_3.54.2
## [19] digest_0.6.33 RColorBrewer_1.1-3
## [21] XVector_0.38.0 colorspace_2.1-0
## [23] htmltools_0.5.5 Matrix_1.6-0
## [25] R.oo_1.25.0 XML_3.99-0.14
## [27] pkgconfig_2.0.3 zlibbioc_1.44.0
## [29] purrr_1.0.1 HDF5Array_1.26.0
## [31] tibble_3.2.1 farver_2.1.1
## [33] generics_0.1.3 ellipsis_0.3.2
## [35] withr_2.5.0 cachem_1.0.8
## [37] lazyeval_0.2.2 cli_3.6.1
## [39] magrittr_2.0.3 crayon_1.5.2
## [41] evaluate_0.21 R.methodsS3_1.8.2
## [43] fansi_1.0.4 tools_4.2.1
## [45] data.table_1.14.8 BiocIO_1.8.0
## [47] lifecycle_1.0.3 Rhdf5lib_1.20.0
## [49] munsell_0.5.0 locfit_1.5-9.7
## [51] DelayedArray_0.24.0 Biostrings_2.66.0
## [53] compiler_4.2.1 jquerylib_0.1.4
## [55] rlang_1.1.1 rhdf5_2.42.1
## [57] grid_4.2.1 RCurl_1.98-1.12
## [59] rhdf5filters_1.10.1 rstudioapi_0.15.0
## [61] htmlwidgets_1.6.2 rjson_0.2.21
## [63] crosstalk_1.2.0 labeling_0.4.2
## [65] bitops_1.0-7 rmarkdown_2.23
## [67] restfulr_0.0.15 gtable_0.3.3
## [69] codetools_0.2-19 R6_2.5.1
## [71] GenomicAlignments_1.34.1 knitr_1.43
## [73] dplyr_1.1.2 rtracklayer_1.58.0
## [75] fastmap_1.1.1 utf8_1.2.3
## [77] permute_0.9-7 Rcpp_1.0.11
## [79] vctrs_0.6.3 tidyselect_1.2.0
## [81] xfun_0.39 sparseMatrixStats_1.10.0