library("easylift")
#> Loading required package: GenomicRanges
#> Loading required package: stats4
#> Loading required package: BiocGenerics
#> Loading required package: generics
#>
#> Attaching package: 'generics'
#> The following objects are masked from 'package:base':
#>
#> as.difftime, as.factor, as.ordered, intersect, is.element, setdiff,
#> setequal, union
#>
#> Attaching package: 'BiocGenerics'
#> The following objects are masked from 'package:generics':
#>
#> intersect, setdiff, setequal, union
#> 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, saveRDS, setdiff,
#> setequal, table, tapply, union, unique, unsplit, which.max,
#> which.min
#> Loading required package: S4Vectors
#> Warning: multiple methods tables found for 'setequal'
#>
#> 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
#> Warning: replacing previous import 'BiocGenerics::setequal' by
#> 'S4Vectors::setequal' when loading 'IRanges'
#> Loading required package: GenomeInfoDb
#> Warning: replacing previous import 'BiocGenerics::setequal' by
#> 'S4Vectors::setequal' when loading 'GenomeInfoDb'
#> Warning: replacing previous import 'BiocGenerics::setequal' by
#> 'S4Vectors::setequal' when loading 'GenomicRanges'
#> Warning: replacing previous import 'BiocGenerics::setequal' by
#> 'S4Vectors::setequal' when loading 'XVector'
#> Loading required package: BiocFileCache
#> Loading required package: dbplyr
#> Warning: replacing previous import 'BiocGenerics::setequal' by
#> 'S4Vectors::setequal' when loading 'rtracklayer'
#> Warning: replacing previous import 'BiocGenerics::setequal' by
#> 'S4Vectors::setequal' when loading 'Biostrings'
#> Warning: multiple methods tables found for 'setequal'
#> Warning: replacing previous import 'BiocGenerics::setequal' by
#> 'S4Vectors::setequal' when loading 'GenomicAlignments'
#> Warning: replacing previous import 'BiocGenerics::setequal' by
#> 'S4Vectors::setequal' when loading 'SummarizedExperiment'
#> Warning: replacing previous import 'BiocGenerics::setequal' by
#> 'S4Vectors::setequal' when loading 'S4Arrays'
#> Warning: replacing previous import 'BiocGenerics::setequal' by
#> 'S4Vectors::setequal' when loading 'DelayedArray'
#> Warning: replacing previous import 'BiocGenerics::setequal' by
#> 'S4Vectors::setequal' when loading 'SparseArray'
#> Warning: replacing previous import 'S4Arrays::read_block' by
#> 'DelayedArray::read_block' when loading 'SummarizedExperiment'Create a GRanges object, assign a genome to it, and
specify chain file
gr <- GRanges(
seqname = Rle(
c("chr1", "chr2"),
c(100000, 100000)
),
ranges = IRanges(
start = 1, end = 200000
)
)
# Here, "hg19" is the source genome
genome(gr) <- "hg19"
# Here, we use the `system.file()` function because the chain file is in the
# package (however if you need to point to any other file on your machine,
# just do 'chain <- "path/to/your/hg19ToHg38.over.chain.gz"'):
chain <- system.file("extdata", "hg19ToHg38.over.chain.gz", package = "easylift")
gr
#> GRanges object with 200000 ranges and 0 metadata columns:
#> seqnames ranges strand
#> <Rle> <IRanges> <Rle>
#> [1] chr1 1-200000 *
#> [2] chr1 1-200000 *
#> [3] chr1 1-200000 *
#> [4] chr1 1-200000 *
#> [5] chr1 1-200000 *
#> ... ... ... ...
#> [199996] chr2 1-200000 *
#> [199997] chr2 1-200000 *
#> [199998] chr2 1-200000 *
#> [199999] chr2 1-200000 *
#> [200000] chr2 1-200000 *
#> -------
#> seqinfo: 2 sequences from hg19 genome; no seqlengthsCall easylift with GRanges object, target
genome and the chain file.
# Here, "hg38" is the target genome
easylift(gr, "hg38", chain)
#> GRanges object with 300000 ranges and 0 metadata columns:
#> seqnames ranges strand
#> <Rle> <IRanges> <Rle>
#> [1] chr1 10001-177376 *
#> [2] chr19 242824-242864 *
#> [3] chr1 10001-177376 *
#> [4] chr19 242824-242864 *
#> [5] chr1 10001-177376 *
#> ... ... ... ...
#> [299996] chr2 10001-200000 *
#> [299997] chr2 10001-200000 *
#> [299998] chr2 10001-200000 *
#> [299999] chr2 10001-200000 *
#> [300000] chr2 10001-200000 *
#> -------
#> seqinfo: 25 sequences (1 circular) from hg38 genomeTo use BiocFileCache for the chain file, add it to the
cache:
chain_file <- "/path/to/your/hg19ToHg38.over.chain.gz"
bfc <- BiocFileCache()
# Add chain file to cache if already not available
if (nrow(bfcquery(bfc, basename(chain_file))) == 0)
bfcadd(bfc, chain_file)Then, use it in easylift:
To cite package easylift in publications use:
Al Nahid A, Pagès H, Love M (2023). easylift: An R package to perform genomic liftover. R package version 1.0.0, https://github.com/nahid18/easylift.
A BibTeX entry for LaTeX users is
@Manual{,
title = {easylift: An R package to perform genomic liftover},
author = {Abdullah Al Nahid, Hervé Pagès, Michael Love},
year = {2023},
note = {R package version 1.0.0},
url = {https://github.com/nahid18/easylift},
}Please note that the easylift was only made possible
thanks to many other R and bioinformatics software authors, which are
cited either in the vignettes and/or the paper(s) describing this
package.
Please note that the easylift project is released with a
Contributor
Code of Conduct. By contributing to this project, you agree to abide
by its terms.
sessionInfo()
#> R version 4.4.1 (2024-06-14)
#> Platform: x86_64-pc-linux-gnu
#> Running under: Ubuntu 24.04.1 LTS
#>
#> Matrix products: default
#> BLAS: /usr/lib/x86_64-linux-gnu/openblas-pthread/libblas.so.3
#> LAPACK: /usr/lib/x86_64-linux-gnu/openblas-pthread/libopenblasp-r0.3.26.so; LAPACK version 3.12.0
#>
#> locale:
#> [1] LC_CTYPE=en_US.UTF-8 LC_NUMERIC=C
#> [3] LC_TIME=en_US.UTF-8 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: Etc/UTC
#> tzcode source: system (glibc)
#>
#> attached base packages:
#> [1] stats4 stats graphics grDevices utils datasets methods
#> [8] base
#>
#> other attached packages:
#> [1] easylift_1.5.0 BiocFileCache_2.15.0 dbplyr_2.5.0
#> [4] GenomicRanges_1.59.0 GenomeInfoDb_1.43.0 IRanges_2.41.0
#> [7] S4Vectors_0.45.0 BiocGenerics_0.53.1 generics_0.1.3
#> [10] BiocStyle_2.35.0
#>
#> loaded via a namespace (and not attached):
#> [1] SummarizedExperiment_1.37.0 rjson_0.2.23
#> [3] xfun_0.48 bslib_0.8.0
#> [5] lattice_0.22-6 Biobase_2.67.0
#> [7] vctrs_0.6.5 tools_4.4.1
#> [9] bitops_1.0-9 parallel_4.4.1
#> [11] curl_5.2.3 tibble_3.2.1
#> [13] fansi_1.0.6 RSQLite_2.3.7
#> [15] blob_1.2.4 pkgconfig_2.0.3
#> [17] R.oo_1.26.0 Matrix_1.7-1
#> [19] lifecycle_1.0.4 GenomeInfoDbData_1.2.13
#> [21] compiler_4.4.1 Rsamtools_2.23.0
#> [23] Biostrings_2.75.0 codetools_0.2-20
#> [25] htmltools_0.5.8.1 sys_3.4.3
#> [27] buildtools_1.0.0 sass_0.4.9
#> [29] RCurl_1.98-1.16 yaml_2.3.10
#> [31] pillar_1.9.0 crayon_1.5.3
#> [33] jquerylib_0.1.4 R.utils_2.12.3
#> [35] BiocParallel_1.41.0 DelayedArray_0.33.1
#> [37] cachem_1.1.0 abind_1.4-8
#> [39] tidyselect_1.2.1 digest_0.6.37
#> [41] dplyr_1.1.4 restfulr_0.0.15
#> [43] maketools_1.3.1 grid_4.4.1
#> [45] fastmap_1.2.0 SparseArray_1.7.0
#> [47] cli_3.6.3 magrittr_2.0.3
#> [49] S4Arrays_1.7.1 XML_3.99-0.17
#> [51] utf8_1.2.4 filelock_1.0.3
#> [53] UCSC.utils_1.3.0 bit64_4.5.2
#> [55] rmarkdown_2.28 XVector_0.47.0
#> [57] httr_1.4.7 matrixStats_1.4.1
#> [59] bit_4.5.0 R.methodsS3_1.8.2
#> [61] memoise_2.0.1 evaluate_1.0.1
#> [63] knitr_1.48 BiocIO_1.17.0
#> [65] rtracklayer_1.67.0 rlang_1.1.4
#> [67] glue_1.8.0 DBI_1.2.3
#> [69] BiocManager_1.30.25 jsonlite_1.8.9
#> [71] R6_2.5.1 MatrixGenerics_1.19.0
#> [73] GenomicAlignments_1.43.0 zlibbioc_1.51.2