diff --git a/articles/docker.html b/articles/docker.html index cc99108..feb0953 100644 --- a/articles/docker.html +++ b/articles/docker.html @@ -89,7 +89,7 @@
vignettes/docker.Rmd
@@ -165,7 +165,7 @@
utils::sessionInfo()
-## R version 4.4.0 (2024-04-24)
+## R Under development (unstable) (2024-03-28 r86224)
## Platform: x86_64-pc-linux-gnu
## Running under: Ubuntu 22.04.4 LTS
##
@@ -191,55 +191,59 @@ Session Info## [1] MotifPeeker_0.99.0
##
## loaded via a namespace (and not attached):
-## [1] tidyselect_1.2.1 viridisLite_0.4.2
-## [3] dplyr_1.1.4 blob_1.2.4
-## [5] viridis_0.6.5 filelock_1.0.3
-## [7] Biostrings_2.73.1 bitops_1.0-7
-## [9] fastmap_1.2.0 lazyeval_0.2.2
-## [11] BiocFileCache_2.13.0 GenomicAlignments_1.41.0
-## [13] digest_0.6.35 lifecycle_1.0.4
-## [15] RSQLite_2.3.7 magrittr_2.0.3
-## [17] compiler_4.4.0 rlang_1.1.4
-## [19] sass_0.4.9 tools_4.4.0
-## [21] utf8_1.2.4 yaml_2.3.8
-## [23] data.table_1.15.4 knitr_1.47
-## [25] S4Arrays_1.5.1 htmlwidgets_1.6.4
-## [27] bit_4.0.5 curl_5.2.1
-## [29] DelayedArray_0.31.3 abind_1.4-5
-## [31] BiocParallel_1.39.0 purrr_1.0.2
-## [33] BiocGenerics_0.51.0 desc_1.4.3
-## [35] grid_4.4.0 stats4_4.4.0
-## [37] fansi_1.0.6 colorspace_2.1-0
-## [39] ggplot2_3.5.1 MASS_7.3-60.2
-## [41] scales_1.3.0 SummarizedExperiment_1.35.0
-## [43] cli_3.6.2 rmarkdown_2.27
-## [45] crayon_1.5.2 ragg_1.3.2
-## [47] generics_0.1.3 emoji_15.0
-## [49] httr_1.4.7 DBI_1.2.3
-## [51] cachem_1.1.0 stringr_1.5.1
-## [53] zlibbioc_1.51.1 parallel_4.4.0
-## [55] XVector_0.45.0 universalmotif_1.23.0
-## [57] matrixStats_1.3.0 vctrs_0.6.5
-## [59] Matrix_1.7-0 jsonlite_1.8.8
-## [61] IRanges_2.39.0 S4Vectors_0.43.0
-## [63] bit64_4.0.5 systemfonts_1.1.0
-## [65] plotly_4.10.4 tidyr_1.3.1
-## [67] jquerylib_0.1.4 glue_1.7.0
-## [69] pkgdown_2.0.9 codetools_0.2-20
-## [71] DT_0.33 stringi_1.8.4
-## [73] gtable_0.3.5 GenomeInfoDb_1.41.1
-## [75] GenomicRanges_1.57.1 UCSC.utils_1.1.0
-## [77] munsell_0.5.1 tibble_3.2.1
-## [79] pillar_1.9.0 htmltools_0.5.8.1
-## [81] GenomeInfoDbData_1.2.12 R6_2.5.1
-## [83] dbplyr_2.5.0 textshaping_0.4.0
-## [85] evaluate_0.24.0 tidyverse_2.0.0
-## [87] Biobase_2.65.0 lattice_0.22-6
-## [89] Rsamtools_2.21.0 memoise_2.0.1
-## [91] bslib_0.7.0 Rcpp_1.0.12
-## [93] gridExtra_2.3 SparseArray_1.5.10
-## [95] xfun_0.44 fs_1.6.4
-## [97] MatrixGenerics_1.17.0 pkgconfig_2.0.3
+## [1] tidyselect_1.2.1 viridisLite_0.4.2
+## [3] dplyr_1.1.4 blob_1.2.4
+## [5] viridis_0.6.5 filelock_1.0.3
+## [7] Biostrings_2.73.1 bitops_1.0-7
+## [9] fastmap_1.2.0 lazyeval_0.2.2
+## [11] RCurl_1.98-1.14 BiocFileCache_2.13.0
+## [13] GenomicAlignments_1.41.0 XML_3.99-0.17
+## [15] digest_0.6.36 lifecycle_1.0.4
+## [17] RSQLite_2.3.7 magrittr_2.0.3
+## [19] compiler_4.5.0 rlang_1.1.4
+## [21] sass_0.4.9 tools_4.5.0
+## [23] utf8_1.2.4 yaml_2.3.8
+## [25] data.table_1.15.4 rtracklayer_1.65.0
+## [27] knitr_1.47 S4Arrays_1.5.1
+## [29] htmlwidgets_1.6.4 bit_4.0.5
+## [31] curl_5.2.1 DelayedArray_0.31.3
+## [33] abind_1.4-5 BiocParallel_1.39.0
+## [35] purrr_1.0.2 BiocGenerics_0.51.0
+## [37] desc_1.4.3 grid_4.5.0
+## [39] stats4_4.5.0 fansi_1.0.6
+## [41] colorspace_2.1-0 ggplot2_3.5.1
+## [43] MASS_7.3-60.2 scales_1.3.0
+## [45] SummarizedExperiment_1.35.0 cli_3.6.3
+## [47] rmarkdown_2.27 crayon_1.5.3
+## [49] ragg_1.3.0 generics_0.1.3
+## [51] tzdb_0.4.0 httr_1.4.7
+## [53] rjson_0.2.21 DBI_1.2.3
+## [55] cachem_1.1.0 ggseqlogo_0.2
+## [57] zlibbioc_1.51.1 parallel_4.5.0
+## [59] universalmotif_1.23.0 XVector_0.45.0
+## [61] restfulr_0.0.15 matrixStats_1.3.0
+## [63] vctrs_0.6.5 Matrix_1.7-0
+## [65] jsonlite_1.8.8 hms_1.1.3
+## [67] IRanges_2.39.0 S4Vectors_0.43.0
+## [69] bit64_4.0.5 systemfonts_1.0.6
+## [71] plotly_4.10.4 tidyr_1.3.1
+## [73] jquerylib_0.1.4 glue_1.7.0
+## [75] pkgdown_2.0.9 memes_1.12.0
+## [77] codetools_0.2-19 DT_0.33
+## [79] gtable_0.3.5 GenomeInfoDb_1.41.1
+## [81] BiocIO_1.15.0 GenomicRanges_1.57.1
+## [83] UCSC.utils_1.1.0 munsell_0.5.1
+## [85] tibble_3.2.1 pillar_1.9.0
+## [87] htmltools_0.5.8.1 GenomeInfoDbData_1.2.12
+## [89] BSgenome_1.73.0 R6_2.5.1
+## [91] dbplyr_2.5.0 textshaping_0.3.7
+## [93] evaluate_0.24.0 Biobase_2.65.0
+## [95] lattice_0.22-6 readr_2.1.5
+## [97] Rsamtools_2.21.0 memoise_2.0.1
+## [99] bslib_0.7.0 Rcpp_1.0.12
+## [101] gridExtra_2.3 SparseArray_1.5.10
+## [103] xfun_0.45 fs_1.6.4
+## [105] MatrixGenerics_1.17.0 pkgconfig_2.0.3
vignettes/templateR.Rmd
@@ -110,7 +110,7 @@
utils::sessionInfo()
-## R version 4.4.0 (2024-04-24)
+## R Under development (unstable) (2024-03-28 r86224)
## Platform: x86_64-pc-linux-gnu
## Running under: Ubuntu 22.04.4 LTS
##
@@ -136,55 +136,59 @@ Session Info## [1] MotifPeeker_0.99.0
##
## loaded via a namespace (and not attached):
-## [1] tidyselect_1.2.1 viridisLite_0.4.2
-## [3] dplyr_1.1.4 blob_1.2.4
-## [5] viridis_0.6.5 filelock_1.0.3
-## [7] Biostrings_2.73.1 bitops_1.0-7
-## [9] fastmap_1.2.0 lazyeval_0.2.2
-## [11] BiocFileCache_2.13.0 GenomicAlignments_1.41.0
-## [13] digest_0.6.35 lifecycle_1.0.4
-## [15] RSQLite_2.3.7 magrittr_2.0.3
-## [17] compiler_4.4.0 rlang_1.1.4
-## [19] sass_0.4.9 tools_4.4.0
-## [21] utf8_1.2.4 yaml_2.3.8
-## [23] data.table_1.15.4 knitr_1.47
-## [25] S4Arrays_1.5.1 htmlwidgets_1.6.4
-## [27] bit_4.0.5 curl_5.2.1
-## [29] DelayedArray_0.31.3 abind_1.4-5
-## [31] BiocParallel_1.39.0 purrr_1.0.2
-## [33] BiocGenerics_0.51.0 desc_1.4.3
-## [35] grid_4.4.0 stats4_4.4.0
-## [37] fansi_1.0.6 colorspace_2.1-0
-## [39] ggplot2_3.5.1 MASS_7.3-60.2
-## [41] scales_1.3.0 SummarizedExperiment_1.35.0
-## [43] cli_3.6.2 rmarkdown_2.27
-## [45] crayon_1.5.2 ragg_1.3.2
-## [47] generics_0.1.3 emoji_15.0
-## [49] httr_1.4.7 DBI_1.2.3
-## [51] cachem_1.1.0 stringr_1.5.1
-## [53] zlibbioc_1.51.1 parallel_4.4.0
-## [55] XVector_0.45.0 universalmotif_1.23.0
-## [57] matrixStats_1.3.0 vctrs_0.6.5
-## [59] Matrix_1.7-0 jsonlite_1.8.8
-## [61] IRanges_2.39.0 S4Vectors_0.43.0
-## [63] bit64_4.0.5 systemfonts_1.1.0
-## [65] plotly_4.10.4 tidyr_1.3.1
-## [67] jquerylib_0.1.4 glue_1.7.0
-## [69] pkgdown_2.0.9 codetools_0.2-20
-## [71] DT_0.33 stringi_1.8.4
-## [73] gtable_0.3.5 GenomeInfoDb_1.41.1
-## [75] GenomicRanges_1.57.1 UCSC.utils_1.1.0
-## [77] munsell_0.5.1 tibble_3.2.1
-## [79] pillar_1.9.0 htmltools_0.5.8.1
-## [81] GenomeInfoDbData_1.2.12 R6_2.5.1
-## [83] dbplyr_2.5.0 textshaping_0.4.0
-## [85] evaluate_0.24.0 tidyverse_2.0.0
-## [87] Biobase_2.65.0 lattice_0.22-6
-## [89] Rsamtools_2.21.0 memoise_2.0.1
-## [91] bslib_0.7.0 Rcpp_1.0.12
-## [93] gridExtra_2.3 SparseArray_1.5.10
-## [95] xfun_0.44 fs_1.6.4
-## [97] MatrixGenerics_1.17.0 pkgconfig_2.0.3
+## [1] tidyselect_1.2.1 viridisLite_0.4.2
+## [3] dplyr_1.1.4 blob_1.2.4
+## [5] viridis_0.6.5 filelock_1.0.3
+## [7] Biostrings_2.73.1 bitops_1.0-7
+## [9] fastmap_1.2.0 lazyeval_0.2.2
+## [11] RCurl_1.98-1.14 BiocFileCache_2.13.0
+## [13] GenomicAlignments_1.41.0 XML_3.99-0.17
+## [15] digest_0.6.36 lifecycle_1.0.4
+## [17] RSQLite_2.3.7 magrittr_2.0.3
+## [19] compiler_4.5.0 rlang_1.1.4
+## [21] sass_0.4.9 tools_4.5.0
+## [23] utf8_1.2.4 yaml_2.3.8
+## [25] data.table_1.15.4 rtracklayer_1.65.0
+## [27] knitr_1.47 S4Arrays_1.5.1
+## [29] htmlwidgets_1.6.4 bit_4.0.5
+## [31] curl_5.2.1 DelayedArray_0.31.3
+## [33] abind_1.4-5 BiocParallel_1.39.0
+## [35] purrr_1.0.2 BiocGenerics_0.51.0
+## [37] desc_1.4.3 grid_4.5.0
+## [39] stats4_4.5.0 fansi_1.0.6
+## [41] colorspace_2.1-0 ggplot2_3.5.1
+## [43] MASS_7.3-60.2 scales_1.3.0
+## [45] SummarizedExperiment_1.35.0 cli_3.6.3
+## [47] rmarkdown_2.27 crayon_1.5.3
+## [49] ragg_1.3.0 generics_0.1.3
+## [51] tzdb_0.4.0 httr_1.4.7
+## [53] rjson_0.2.21 DBI_1.2.3
+## [55] cachem_1.1.0 ggseqlogo_0.2
+## [57] zlibbioc_1.51.1 parallel_4.5.0
+## [59] universalmotif_1.23.0 XVector_0.45.0
+## [61] restfulr_0.0.15 matrixStats_1.3.0
+## [63] vctrs_0.6.5 Matrix_1.7-0
+## [65] jsonlite_1.8.8 hms_1.1.3
+## [67] IRanges_2.39.0 S4Vectors_0.43.0
+## [69] bit64_4.0.5 systemfonts_1.0.6
+## [71] plotly_4.10.4 tidyr_1.3.1
+## [73] jquerylib_0.1.4 glue_1.7.0
+## [75] pkgdown_2.0.9 memes_1.12.0
+## [77] codetools_0.2-19 DT_0.33
+## [79] gtable_0.3.5 GenomeInfoDb_1.41.1
+## [81] BiocIO_1.15.0 GenomicRanges_1.57.1
+## [83] UCSC.utils_1.1.0 munsell_0.5.1
+## [85] tibble_3.2.1 pillar_1.9.0
+## [87] htmltools_0.5.8.1 GenomeInfoDbData_1.2.12
+## [89] BSgenome_1.73.0 R6_2.5.1
+## [91] dbplyr_2.5.0 textshaping_0.3.7
+## [93] evaluate_0.24.0 Biobase_2.65.0
+## [95] lattice_0.22-6 readr_2.1.5
+## [97] Rsamtools_2.21.0 memoise_2.0.1
+## [99] bslib_0.7.0 Rcpp_1.0.12
+## [101] gridExtra_2.3 SparseArray_1.5.10
+## [103] xfun_0.45 fs_1.6.4
+## [105] MatrixGenerics_1.17.0 pkgconfig_2.0.3
utils::sessionInfo()
## R version 4.4.0 (2024-04-24)
+## R Under development (unstable) (2024-03-28 r86224)
## Platform: x86_64-pc-linux-gnu
## Running under: Ubuntu 22.04.4 LTS
##
@@ -158,7 +158,7 @@ Session Info##
## loaded via a namespace (and not attached):
## [1] gtable_0.3.5 jsonlite_1.8.8 renv_1.0.7
-## [4] dplyr_1.1.4 compiler_4.4.0 BiocManager_1.30.23
+## [4] dplyr_1.1.4 compiler_4.5.0 BiocManager_1.30.23
## [7] tidyselect_1.2.1 rvcheck_0.2.1 scales_1.3.0
## [10] yaml_2.3.8 fastmap_1.2.0 here_1.0.1
## [13] ggplot2_3.5.1 R6_2.5.1 generics_0.1.3
@@ -166,12 +166,12 @@ Session Info## [19] desc_1.4.3 dlstats_0.1.7 rprojroot_2.0.4
## [22] munsell_0.5.1 pillar_1.9.0 RColorBrewer_1.1-3
## [25] rlang_1.1.4 utf8_1.2.4 cachem_1.1.0
-## [28] badger_0.2.4 xfun_0.44 fs_1.6.4
-## [31] memoise_2.0.1 cli_3.6.2 magrittr_2.0.3
-## [34] rworkflows_1.0.1 digest_0.6.35 grid_4.4.0
+## [28] badger_0.2.4 xfun_0.45 fs_1.6.4
+## [31] memoise_2.0.1 cli_3.6.3 magrittr_2.0.3
+## [34] rworkflows_1.0.1 digest_0.6.36 grid_4.5.0
## [37] lifecycle_1.0.4 vctrs_0.6.5 data.table_1.15.4
## [40] evaluate_0.24.0 glue_1.7.0 fansi_1.0.6
-## [43] colorspace_2.1-0 tools_4.4.0 pkgconfig_2.0.3
+## [43] colorspace_2.1-0 tools_4.5.0 pkgconfig_2.0.3
## [46] htmltools_0.5.8.1
An integer specifying the width of the sequence to +extract around the summit (default = NULL). This sequence is used to search +for de novo motifs. If not provided, the entire peak region will be used. +This parameter is intended to reduce the search space and speed up motif +discovery; therefore, a value less than the average peak width is +recommended. Peaks are trimmed symmetrically around the summit while +respecting the peak bounds.
A logical indicating whether to include download buttons for various files within the HTML report. (default = TRUE)
path to meme/bin/
(optional). Defaut: NULL
, searches
+"MEME_PATH" environment variable or "meme_path" option for path to "meme/bin/".
A character string specifying the directory to save the
output files. (default = tempdir()
) A sub-directory with the output
files will be created in this directory.
A logical indicating whether to save intermediate files +generated during the run, such as those from FIMO and AME. (default = FALSE)
A character vector specifying the display mode for the HTML report once it is generated. (default = NULL) Options are:
"browser"
: Open the report in the default web browser.
An integer specifying the number of cores to use for parallel -processing. (default = 1)
The number of workers to use for parallel processing.
Running de-novo motif discovery is computationally expensive and can
require from minutes to hours. denovo_motifs
can widely affect the
-runtime (higher values take longer).
trim_seq_width
to a lower
+value can also reduce the runtime significantly.
Light wrapper around BiocParallel
functions that
+automatically sets the appropriate parameters based on the number of workers
+specified.
bpapply(
+ X,
+ FUN,
+ apply_fun = BiocParallel::bplapply,
+ workers = 1,
+ progressbar = FALSE,
+ force_snowparam = FALSE,
+ verbose = FALSE,
+ ...
+)
Any object for which methods length
, [
, and
+ [[
are implemented.
The function
to be applied to each element of X
.
A BiocParallel
function to use
+for parallel processing. (default = BiocParallel::bplapply
)
The number of workers to use for parallel processing.
logical(1)
Enable progress bar (based on plyr:::progress_text).
A logical indicating whether to force the use of +SnowParam object.
A logical indicating whether to print verbose messages while +running the function. (default = FALSE)
Arguments passed on to BiocParallel::bplapply
, BiocParallel::bpmapply
BPPARAM
An optional BiocParallelParam
instance
+ determining the parallel back-end to be used during evaluation, or a
+ list
of BiocParallelParam
instances, to be applied in
+ sequence for nested calls to BiocParallel functions.
BPREDO
A list
of output from bplapply
with one or
+ more failed elements. When a list is given in BPREDO
,
+ bpok
is used to identify errors, tasks are rerun and inserted
+ into the original results.
BPOPTIONS
Additional options to control the behavior of the parallel evaluation, see bpoptions
.
MoreArgs
List of additional arguments to FUN
.
SIMPLIFY
If TRUE
the result will be simplified using
+ simplify2array
.
USE.NAMES
If TRUE
the result will be named.
Output relevant to the apply_fun
specified.
half_it <- function(arg1) return(arg1 / 2)
+x <- seq_len(10)
+
+res <- bpapply(x, half_it, workers = 2)
+print(res)
+#> [[1]]
+#> [1] 0.5
+#>
+#> [[2]]
+#> [1] 1
+#>
+#> [[3]]
+#> [1] 1.5
+#>
+#> [[4]]
+#> [1] 2
+#>
+#> [[5]]
+#> [1] 2.5
+#>
+#> [[6]]
+#> [1] 3
+#>
+#> [[7]]
+#> [1] 3.5
+#>
+#> [[8]]
+#> [1] 4
+#>
+#> [[9]]
+#> [1] 4.5
+#>
+#> [[10]]
+#> [1] 5
+#>
+
+
check_ENCODE("ENCFF109VAD", expect_format = "bam")
-#> BFC2
-#> "/github/home/.cache/R/BiocFileCache/bf341948dfe_ENCFF109VAD.bam"
+ if (requireNamespace("curl", quietly = TRUE) &&
+ requireNamespace("jsonlite", quietly = TRUE)) {
+ check_ENCODE("ENCFF109VAD", expect_format = "bam")
+}
+#> BFC2
+#> "/github/home/.cache/R/BiocFileCache/31184851a2e6_ENCFF109VAD.bam"
check_JASPAR("MA1930.2")
-#> BFC3
-#> "/github/home/.cache/R/BiocFileCache/bf32d5f43e1_MA1930.2.jaspar"
+#> BFC3
+#> "/github/home/.cache/R/BiocFileCache/31181ef1dbee_MA1930.2.jaspar"
R/confirm_meme_install.R
+ confirm_meme_install.Rd
Stop if MEME suite is not installed
+confirm_meme_install(meme_path = NULL)
path to meme/bin/
(optional). Defaut: NULL
, searches
+"MEME_PATH" environment variable or "meme_path" option for path to "meme/bin/".
Null
+get_JASPARCORE()
-#> BFC1
-#> "/github/home/.cache/R/BiocFileCache/bf3548b1acf_JASPAR2024_CORE_non-redundant_pfms_meme.txt"
+#> BFC1
+#> "/github/home/.cache/R/BiocFileCache/31182cb22f18_JASPAR2024_CORE_non-redundant_pfms_meme.txt"
Get appropriate parameters for BiocParallel
based on the
+number of workers specified. For less than 10 workers, the function returns a
+MulticoreParam
object. For 10 or more cores, the function
+returns a SnowParam
object. Since Windows supports
+neither, the function returns a SerialParam
object. As a
+result, Windows users do not benefit from parallel processing.
get_bpparam(
+ workers,
+ progressbar = workers > 1,
+ force_snowparam = FALSE,
+ verbose = FALSE
+)
The number of workers to use for parallel processing.
logical(1)
Enable progress bar (based on plyr:::progress_text).
A logical indicating whether to force the use of +SnowParam object.
A logical indicating whether to print verbose messages while +running the function. (default = FALSE)
A BPPARAM
object.
MotifPeeker()
Benchmark epigenomic profiling methods using motif enrichment
Use BiocParallel functions with appropriate parameters
motif_MA1930.2
Example CTCF JASPAR motif file
Calculate motif enrichment in a set of sequences
report_header()
Report header
Segregate input sequences into common and unique groups
Calculate the distance between peak summits and motifs
Convert ggplot2 objects to plotly
Trim sequences to a specified width around the summit
x <- data.frame(a = c(1,2,3), b = c(2,3,4))
p <- ggplot2::ggplot(x, ggplot2::aes(x = a, y = b)) + ggplot2::geom_point()
to_plotly(p, html_tags = FALSE)
-
-
+
+
Trim sequences to a specified width around the summit
+trim_seqs(peaks, peak_width, genome_build, respect_bounds = TRUE)
A GRanges object created using
+read_peak_file()
.
Total expected width of the peak.
The genome build that the peak sequences should be +derived from.
Logical indicating whether the peak width should be
+respected when trimming sequences. (default = TRUE) If TRUE
, the
+trimmed sequences will not extend beyond the peak boundaries.
A GRanges object with the trimmed sequences. The sequences are
+guaranteed to not exceed the peak width + 1
(peak width + the summit
+base).
data("CTCF_TIP_peaks", package = "MotifPeeker")
+peaks <- CTCF_TIP_peaks
+genome_build <- BSgenome.Hsapiens.UCSC.hg38::BSgenome.Hsapiens.UCSC.hg38
+
+trimmed_seqs <- trim_seqs(peaks, peak_width = 100,
+ genome_build = genome_build)
+summary(GenomicRanges::width(trimmed_seqs))
+#> Min. 1st Qu. Median Mean 3rd Qu. Max.
+#> 59.0 101.0 101.0 98.5 101.0 101.0
+
+