The nullrangesData package provides datasets for the nullranges package vignette, in particular example datasets for exclusion regions, DNase hypersensitivity sites (DHS), CTCF binding sites, and CTCF genomic interactions.
library(nullrangesData)## Loading required package: ExperimentHub## 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':
##
## Filter, Find, Map, Position, Reduce, anyDuplicated, aperm, append,
## as.data.frame, basename, cbind, colnames, dirname, do.call,
## duplicated, eval, evalq, get, grep, grepl, intersect, is.unsorted,
## lapply, mapply, match, mget, order, paste, pmax, pmax.int, pmin,
## pmin.int, rank, rbind, rownames, sapply, setdiff, sort, table,
## tapply, union, unique, unsplit, which.max, which.min## Loading required package: AnnotationHub## Loading required package: BiocFileCache## Loading required package: dbplyr## Loading required package: GenomicRanges## Loading required package: stats4## Loading required package: S4Vectors##
## Attaching package: 'S4Vectors'## The following objects are masked from 'package:base':
##
## I, expand.grid, unname## Loading required package: IRanges## Loading required package: GenomeInfoDb## Loading required package: InteractionSet## Loading required package: SummarizedExperiment## Loading required package: MatrixGenerics## Loading required package: matrixStats##
## 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## Loading required package: Biobase## Welcome to Bioconductor
##
## Vignettes contain introductory material; view with
## 'browseVignettes()'. To cite Bioconductor, see
## 'citation("Biobase")', and for packages 'citation("pkgname")'.##
## Attaching package: 'Biobase'## The following object is masked from 'package:MatrixGenerics':
##
## rowMedians## The following objects are masked from 'package:matrixStats':
##
## anyMissing, rowMedians## The following object is masked from 'package:ExperimentHub':
##
## cache## The following object is masked from 'package:AnnotationHub':
##
## cache## snapshotDate(): 2022-10-24suppressPackageStartupMessages(library(GenomicRanges))
suppressPackageStartupMessages(library(InteractionSet))A549 DHS peaks (see ?DHSA549Hg38 for details).
dhs <- DHSA549Hg38()## see ?nullrangesData and browseVignettes('nullrangesData') for documentation## loading from cachedhs## GRanges object with 177085 ranges and 6 metadata columns:
## seqnames ranges strand | name score
## <Rle> <IRanges> <Rle> | <character> <numeric>
## [1] chr1 10181-10330 * | <NA> 0
## [2] chr1 267990-268139 * | <NA> 0
## [3] chr1 629126-629275 * | <NA> 0
## [4] chr1 629306-629455 * | <NA> 0
## [5] chr1 629901-630170 * | <NA> 0
## ... ... ... ... . ... ...
## [177081] chrY 56873654-56873803 * | <NA> 0
## [177082] chrY 56874534-56874683 * | <NA> 0
## [177083] chrY 56883699-56883848 * | <NA> 0
## [177084] chrY 56885199-56885348 * | <NA> 0
## [177085] chrY 56886199-56886348 * | <NA> 0
## signalValue pValue qValue peak
## <numeric> <numeric> <numeric> <numeric>
## [1] 6 -1 -1 -1
## [2] 12 -1 -1 -1
## [3] 378 -1 -1 -1
## [4] 196 -1 -1 -1
## [5] 212 -1 -1 -1
## ... ... ... ... ...
## [177081] 12 -1 -1 -1
## [177082] 17 -1 -1 -1
## [177083] 19 -1 -1 -1
## [177084] 18 -1 -1 -1
## [177085] 14 -1 -1 -1
## -------
## seqinfo: 24 sequences from hg38 genomeCTCF binding sites, 10kb bins with CTCF and DHS peaks, and CTCF-bound genomics interactions. See corresponding man pages for details.
bins <- hg19_10kb_bins()## see ?nullrangesData and browseVignettes('nullrangesData') for documentation## loading from cachebinPairs <- hg19_10kb_ctcfBoundBinPairs()## see ?nullrangesData and browseVignettes('nullrangesData') for documentation
## loading from cachebins## GRanges object with 303641 ranges and 5 metadata columns:
## seqnames ranges strand | n_ctcf_sites ctcfSignal
## <Rle> <IRanges> <Rle> | <numeric> <numeric>
## [1] chr1 1-10000 * | 0 0
## [2] chr1 10001-20000 * | 0 0
## [3] chr1 20001-30000 * | 0 0
## [4] chr1 30001-40000 * | 0 0
## [5] chr1 40001-50000 * | 0 0
## ... ... ... ... . ... ...
## [303637] chrX 155230001-155240000 * | 0 0.00000
## [303638] chrX 155240001-155250000 * | 0 0.00000
## [303639] chrX 155250001-155260000 * | 1 4.09522
## [303640] chrX 155260001-155270000 * | 0 0.00000
## [303641] chrX 155270001-155270560 * | 0 0.00000
## n_dnase_sites dnaseSignal looped
## <factor> <numeric> <logical>
## [1] 0 0.00000 FALSE
## [2] 0 5.03572 FALSE
## [3] 0 0.00000 FALSE
## [4] 0 0.00000 FALSE
## [5] 0 0.00000 FALSE
## ... ... ... ...
## [303637] 0 8.42068 FALSE
## [303638] 0 4.08961 FALSE
## [303639] 0 6.00443 FALSE
## [303640] 0 8.07179 FALSE
## [303641] 0 0.00000 FALSE
## -------
## seqinfo: 23 sequences from hg19 genomebinPairs## StrictGInteractions object with 198120 interactions and 5 metadata columns:
## seqnames1 ranges1 seqnames2 ranges2 |
## <Rle> <IRanges> <Rle> <IRanges> |
## [1] chr1 230001-240000 --- chr1 520001-530000 |
## [2] chr1 230001-240000 --- chr1 710001-720000 |
## [3] chr1 230001-240000 --- chr1 800001-810000 |
## [4] chr1 230001-240000 --- chr1 840001-850000 |
## [5] chr1 230001-240000 --- chr1 870001-880000 |
## ... ... ... ... ... ... .
## [198116] chrX 154310001-154320000 --- chrX 154370001-154380000 |
## [198117] chrX 154310001-154320000 --- chrX 155250001-155260000 |
## [198118] chrX 154320001-154330000 --- chrX 154370001-154380000 |
## [198119] chrX 154320001-154330000 --- chrX 155250001-155260000 |
## [198120] chrX 154370001-154380000 --- chrX 155250001-155260000 |
## looped ctcfSignal n_sites distance convergent
## <logical> <numeric> <factor> <integer> <logical>
## [1] FALSE 5.18038 2 290000 FALSE
## [2] FALSE 5.46775 2 480000 TRUE
## [3] FALSE 7.30942 2 570000 FALSE
## [4] FALSE 7.34338 2 610000 FALSE
## [5] FALSE 6.31338 3 640000 TRUE
## ... ... ... ... ... ...
## [198116] FALSE 6.79246 2 60000 FALSE
## [198117] FALSE 6.12447 3 940000 TRUE
## [198118] FALSE 7.40868 2 50000 TRUE
## [198119] FALSE 7.00936 3 930000 FALSE
## [198120] FALSE 6.73402 3 880000 TRUE
## -------
## regions: 20612 ranges and 5 metadata columns
## seqinfo: 23 sequences from hg19 genomesessionInfo()## 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] nullrangesData_1.4.0 InteractionSet_1.26.0
## [3] SummarizedExperiment_1.28.0 Biobase_2.58.0
## [5] MatrixGenerics_1.10.0 matrixStats_0.62.0
## [7] GenomicRanges_1.50.0 GenomeInfoDb_1.34.0
## [9] IRanges_2.32.0 S4Vectors_0.36.0
## [11] ExperimentHub_2.6.0 AnnotationHub_3.6.0
## [13] BiocFileCache_2.6.0 dbplyr_2.2.1
## [15] BiocGenerics_0.44.0
##
## loaded via a namespace (and not attached):
## [1] Rcpp_1.0.9 lattice_0.20-45
## [3] png_0.1-7 Biostrings_2.66.0
## [5] assertthat_0.2.1 digest_0.6.30
## [7] utf8_1.2.2 mime_0.12
## [9] R6_2.5.1 RSQLite_2.2.18
## [11] evaluate_0.17 httr_1.4.4
## [13] pillar_1.8.1 zlibbioc_1.44.0
## [15] rlang_1.0.6 curl_4.3.3
## [17] jquerylib_0.1.4 blob_1.2.3
## [19] Matrix_1.5-1 rmarkdown_2.17
## [21] stringr_1.4.1 RCurl_1.98-1.9
## [23] bit_4.0.4 DelayedArray_0.24.0
## [25] shiny_1.7.3 compiler_4.2.1
## [27] httpuv_1.6.6 xfun_0.34
## [29] pkgconfig_2.0.3 htmltools_0.5.3
## [31] tidyselect_1.2.0 KEGGREST_1.38.0
## [33] tibble_3.1.8 GenomeInfoDbData_1.2.9
## [35] interactiveDisplayBase_1.36.0 fansi_1.0.3
## [37] withr_2.5.0 crayon_1.5.2
## [39] dplyr_1.0.10 later_1.3.0
## [41] bitops_1.0-7 rappdirs_0.3.3
## [43] grid_4.2.1 jsonlite_1.8.3
## [45] xtable_1.8-4 lifecycle_1.0.3
## [47] DBI_1.1.3 magrittr_2.0.3
## [49] cli_3.4.1 stringi_1.7.8
## [51] cachem_1.0.6 XVector_0.38.0
## [53] promises_1.2.0.1 bslib_0.4.0
## [55] ellipsis_0.3.2 filelock_1.0.2
## [57] generics_0.1.3 vctrs_0.5.0
## [59] tools_4.2.1 bit64_4.0.5
## [61] glue_1.6.2 purrr_0.3.5
## [63] BiocVersion_3.16.0 fastmap_1.1.0
## [65] yaml_2.3.6 AnnotationDbi_1.60.0
## [67] BiocManager_1.30.19 memoise_2.0.1
## [69] knitr_1.40 sass_0.4.2