The nullrangesData package provides datasets for the nullranges package vignette, in particular example datasets for exclusion regions, DNase hypersensitivity sites (DHS), Single Cell Multiome ATAC and Gene Expression assay, 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, 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 object is masked from 'package:utils':
## 
##     findMatches
## 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
suppressPackageStartupMessages(library(GenomicRanges))
suppressPackageStartupMessages(library(InteractionSet))

A549 DHS peaks (see ?DHSA549Hg38 for details).

dhs <- DHSA549Hg38()
## see ?nullrangesData and browseVignettes('nullrangesData') for documentation
## loading from cache
dhs
## 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 genome

Chromium Single Cell Multiome ATAC + Gene Expression assay. See corresponding man pages for details..

data("sc_rna")
data("sc_promoter")
sc_rna
## GRanges object with 28225 ranges and 2 metadata columns:
##           seqnames            ranges strand |        gene
##              <Rle>         <IRanges>  <Rle> | <character>
##       [1]     chr1     120931-133723      * |  AL627309.1
##       [2]     chr1     140338-140339      * |  AL627309.2
##       [3]     chr1     149706-173862      * |  AL627309.5
##       [4]     chr1     160445-160446      * |  AL627309.4
##       [5]     chr1     266854-266855      * |  AP006222.2
##       ...      ...               ...    ... .         ...
##   [28221]    chr22 50597151-50597152      * |    U62317.3
##   [28222]    chr22 50600792-50600793      * |    MAPK8IP2
##   [28223]    chr22 50628151-50628173      * |        ARSA
##   [28224]    chr22 50674641-50729572      * |      SHANK3
##   [28225]    chr22 50783620-50783663      * |      RABL2B
##                                        counts1
##                                  <NumericList>
##       [1]    -0.227594, 0.249144, 0.419668,...
##       [2]    -0.267261,-0.267261,-0.267261,...
##       [3]       -0.39115,-0.10318, 1.02400,...
##       [4]  0.1516318,-0.0605821, 1.9885284,...
##       [5]    -0.267261,-0.267261,-0.267261,...
##       ...                                  ...
##   [28221]    -0.267261,-0.267261,-0.267261,...
##   [28222]     0.701249,-0.546908,-0.546908,...
##   [28223]    -0.509022, 0.201242, 1.618880,...
##   [28224]    -0.267261,-0.267261,-0.267261,...
##   [28225]  0.9252646,-0.0774203,-0.2877604,...
##   -------
##   seqinfo: 22 sequences from an unspecified genome; no seqlengths
sc_promoter
## GRanges object with 15561 ranges and 2 metadata columns:
##           seqnames            ranges strand |                   peak
##              <Rle>         <IRanges>  <Rle> |            <character>
##       [1]     chr1     777634-779926      * |     chr1:777634-779926
##       [2]     chr1     816881-817647      * |     chr1:816881-817647
##       [3]     chr1     826612-827979      * |     chr1:826612-827979
##       [4]     chr1     869449-870383      * |     chr1:869449-870383
##       [5]     chr1     903617-907386      * |     chr1:903617-907386
##       ...      ...               ...    ... .                    ...
##   [15557]    chr22 50580287-50583942      * | chr22:50580287-50583..
##   [15558]    chr22 50599877-50602115      * | chr22:50599877-50602..
##   [15559]    chr22 50625295-50629340      * | chr22:50625295-50629..
##   [15560]    chr22 50671698-50675683      * | chr22:50671698-50675..
##   [15561]    chr22 50783058-50784322      * | chr22:50783058-50784..
##                                        counts2
##                                  <NumericList>
##       [1]       1.143068,0.383233,0.342632,...
##       [2]    -0.618560,-0.415192, 1.277454,...
##       [3]    -1.162635,-0.571467, 1.045412,...
##       [4]     0.923427, 0.797197,-1.394984,...
##       [5]     0.337377,-0.727911, 1.501327,...
##       ...                                  ...
##   [15557]     1.068434, 0.345541,-0.229966,...
##   [15558]     0.500332, 0.458059,-1.085105,...
##   [15559]  0.2946085,-0.0665503,-0.6663091,...
##   [15560]     0.705884,-0.272306,-0.326069,...
##   [15561]     0.149851, 0.460193,-0.192810,...
##   -------
##   seqinfo: 22 sequences from an unspecified genome; no seqlengths

CTCF 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 cache
binPairs <- hg19_10kb_ctcfBoundBinPairs()
## see ?nullrangesData and browseVignettes('nullrangesData') for documentation
## loading from cache
bins
## 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 genome
binPairs
## 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 genome

Session information

sessionInfo()
## 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] nullrangesData_1.10.0       InteractionSet_1.32.0      
##  [3] SummarizedExperiment_1.34.0 Biobase_2.64.0             
##  [5] MatrixGenerics_1.16.0       matrixStats_1.3.0          
##  [7] GenomicRanges_1.56.0        GenomeInfoDb_1.40.0        
##  [9] IRanges_2.38.0              S4Vectors_0.42.0           
## [11] ExperimentHub_2.12.0        AnnotationHub_3.12.0       
## [13] BiocFileCache_2.12.0        dbplyr_2.5.0               
## [15] BiocGenerics_0.50.0        
## 
## loaded via a namespace (and not attached):
##  [1] KEGGREST_1.44.0         xfun_0.43               bslib_0.7.0            
##  [4] lattice_0.22-6          vctrs_0.6.5             tools_4.4.0            
##  [7] generics_0.1.3          curl_5.2.1              tibble_3.2.1           
## [10] fansi_1.0.6             AnnotationDbi_1.66.0    RSQLite_2.3.6          
## [13] blob_1.2.4              pkgconfig_2.0.3         Matrix_1.7-0           
## [16] lifecycle_1.0.4         GenomeInfoDbData_1.2.12 compiler_4.4.0         
## [19] Biostrings_2.72.0       htmltools_0.5.8.1       sass_0.4.9             
## [22] yaml_2.3.8              pillar_1.9.0            crayon_1.5.2           
## [25] jquerylib_0.1.4         DelayedArray_0.30.0     cachem_1.0.8           
## [28] abind_1.4-5             mime_0.12               tidyselect_1.2.1       
## [31] digest_0.6.35           purrr_1.0.2             dplyr_1.1.4            
## [34] BiocVersion_3.19.1      grid_4.4.0              fastmap_1.1.1          
## [37] SparseArray_1.4.0       cli_3.6.2               magrittr_2.0.3         
## [40] S4Arrays_1.4.0          utf8_1.2.4              withr_3.0.0            
## [43] filelock_1.0.3          UCSC.utils_1.0.0        rappdirs_0.3.3         
## [46] bit64_4.0.5             rmarkdown_2.26          XVector_0.44.0         
## [49] httr_1.4.7              bit_4.0.5               png_0.1-8              
## [52] memoise_2.0.1           evaluate_0.23           knitr_1.46             
## [55] rlang_1.1.3             Rcpp_1.0.12             glue_1.7.0             
## [58] DBI_1.2.2               BiocManager_1.30.22     jsonlite_1.8.8         
## [61] R6_2.5.1                zlibbioc_1.50.0