get_ers defines expressed regions across an inputted range of mean
coverage cut-offs (MCCs) and max region gaps (MRGs) from the coverage.
get_strand_ers defines ERs across an inputted range of mean coverage
cut-offs (MCCs) and max region gaps (MRGs) from the coverage.
get_ers(coverage, mccs, mrgs)
get_strand_ers(
bw_pos,
bw_neg,
auc_raw_pos,
auc_raw_neg,
auc_target,
chrs,
mccs,
mrgs,
bw_chr = "chr"
)| coverage | the coverage of the bigwig files passed into
|
|---|---|
| mccs | mean coverage cut-offs to apply. |
| mrgs | max region gaps to apply. |
| bw_pos | positive strand bigwig file |
| bw_neg | negative strand bigwig file |
| auc_raw_pos | vector containing AUCs(Area Under Coverage) matching the order of the positive bigwig paths. |
| auc_raw_neg | vector containing AUCs(Area Under Coverage) matching the order of the negative bigwig paths. |
| auc_target | total AUC to normalise all samples to. E.g. 40e6 * 100 would be the estimated total auc for sample sequenced to 40 million reads of 100bp in length. |
| chrs | chromosomes to obtain mean coverage for, default is "" giving every chromosome. Can take UCSC format(chrs = "chr1") or just the chromosome i.e. chrs = c(1,X) |
| bw_chr | specifies whether the bigwig files has the chromosomes labelled with a "chr" preceding the chromosome i.e. "chr1" vs "1". Can be either "chr" or "nochr" with "chr" being the default. |
list containing sets of ERs, each generated using a particular combination of MCC and MRG.
list containing sets of stranded ERs, each generated using a particular combination of MCC and MRG.
get_strand_ers: Method for getting ers from stranded BigWig files
data(gtex_SRP012682_SRX222703_lung_coverage_1, package = "ODER")
eg_ers <- get_ers(
coverage = gtex_SRP012682_SRX222703_lung_coverage_1,
mccs = c(5, 10),
mrgs = c(10, 20)
)
#> 2021-10-08 16:10:22 - Generating ERs for chr21
#> 2021-10-08 16:10:23 - Generating ERs for chr22
eg_ers
#> $mcc_5
#> $mcc_5$mrg_10
#> GRanges object with 26459 ranges and 0 metadata columns:
#> seqnames ranges strand
#> <Rle> <IRanges> <Rle>
#> [1] chr21 5026470-5026525 *
#> [2] chr21 5027955-5028030 *
#> [3] chr21 5032160-5032217 *
#> [4] chr21 5033408-5033441 *
#> [5] chr21 5034694-5034787 *
#> ... ... ... ...
#> [26455] chr22 50799669-50799744 *
#> [26456] chr22 50799915-50799990 *
#> [26457] chr22 50800460-50800587 *
#> [26458] chr22 50802354-50802398 *
#> [26459] chr22 50802615-50802631 *
#> -------
#> seqinfo: 2 sequences from an unspecified genome; no seqlengths
#>
#> $mcc_5$mrg_20
#> GRanges object with 24404 ranges and 0 metadata columns:
#> seqnames ranges strand
#> <Rle> <IRanges> <Rle>
#> [1] chr21 5026470-5026525 *
#> [2] chr21 5027955-5028030 *
#> [3] chr21 5032160-5032217 *
#> [4] chr21 5033408-5033441 *
#> [5] chr21 5034694-5034787 *
#> ... ... ... ...
#> [24400] chr22 50799669-50799744 *
#> [24401] chr22 50799915-50799990 *
#> [24402] chr22 50800460-50800587 *
#> [24403] chr22 50802354-50802398 *
#> [24404] chr22 50802615-50802631 *
#> -------
#> seqinfo: 2 sequences from an unspecified genome; no seqlengths
#>
#>
#> $mcc_10
#> $mcc_10$mrg_10
#> GRanges object with 17761 ranges and 0 metadata columns:
#> seqnames ranges strand
#> <Rle> <IRanges> <Rle>
#> [1] chr21 5032176-5032217 *
#> [2] chr21 5033408-5033425 *
#> [3] chr21 5034717-5034756 *
#> [4] chr21 5035188-5035189 *
#> [5] chr21 5036577-5036581 *
#> ... ... ... ...
#> [17757] chr22 50799209-50799264 *
#> [17758] chr22 50799283-50799284 *
#> [17759] chr22 50799669-50799688 *
#> [17760] chr22 50799717-50799744 *
#> [17761] chr22 50800460-50800587 *
#> -------
#> seqinfo: 2 sequences from an unspecified genome; no seqlengths
#>
#> $mcc_10$mrg_20
#> GRanges object with 15977 ranges and 0 metadata columns:
#> seqnames ranges strand
#> <Rle> <IRanges> <Rle>
#> [1] chr21 5032176-5032217 *
#> [2] chr21 5033408-5033425 *
#> [3] chr21 5034717-5034756 *
#> [4] chr21 5035188-5035189 *
#> [5] chr21 5036577-5036581 *
#> ... ... ... ...
#> [15973] chr22 50798996-50799149 *
#> [15974] chr22 50799209-50799284 *
#> [15975] chr22 50799669-50799688 *
#> [15976] chr22 50799717-50799744 *
#> [15977] chr22 50800460-50800587 *
#> -------
#> seqinfo: 2 sequences from an unspecified genome; no seqlengths
#>
#>
library("magrittr")
gtex_metadata <- recount::all_metadata("gtex")
#> 2021-10-08 16:10:24 downloading the metadata to /tmp/Rtmp8R75GU/metadata_clean_gtex.Rdata
gtex_metadata <- gtex_metadata %>%
as.data.frame() %>%
dplyr::filter(project == "SRP012682")
rec_url <- recount::download_study(
project = "SRP012682",
type = "samples",
download = FALSE
)
# file_cache is an internal function to download a bigwig file from a link
# if the file has been downloaded recently, it will be retrieved from a cache
bw_plus <- file_cache(rec_url[58])
bw_minus <- file_cache(rec_url[84])
# As of rtracklayer 1.25.16, BigWig is not supported on Windows.
if (!xfun::is_windows()) {
stranded_ers <- get_strand_ers(
bw_pos = bw_plus, bw_neg = bw_minus,
auc_raw_pos = gtex_metadata[["auc"]][58],
auc_raw_neg = gtex_metadata[["auc"]][84], auc_target = 40e6 * 100,
chrs = "chr21", mccs = c(5, 10), mrgs = c(10, 20)
)
stranded_ers
}
#> 2021-10-08 16:10:26 - Obtaining mean coverage across 1 samples
#> 2021-10-08 16:10:26 - chr21
#> 2021-10-08 16:10:27 - Obtaining mean coverage across 1 samples
#> 2021-10-08 16:10:27 - chr21
#> 2021-10-08 16:10:27 - Generating ERs for chr21
#> 2021-10-08 16:10:28 - Generating ERs for chr21
#> $mcc_5
#> $mcc_5$mrg_10
#> GRanges object with 6355 ranges and 0 metadata columns:
#> seqnames ranges strand
#> <Rle> <IRanges> <Rle>
#> [1] chr21 5116346-5117232 +
#> [2] chr21 5117340-5117507 +
#> [3] chr21 5117539-5117558 +
#> [4] chr21 5117587-5117592 +
#> [5] chr21 5117605-5117611 +
#> ... ... ... ...
#> [6351] chr21 46668354-46668391 -
#> [6352] chr21 46668488-46668581 -
#> [6353] chr21 46690842-46691238 -
#> [6354] chr21 46691775-46691807 -
#> [6355] chr21 46692377-46692446 -
#> -------
#> seqinfo: 1 sequence from an unspecified genome; no seqlengths
#>
#> $mcc_5$mrg_20
#> GRanges object with 5503 ranges and 0 metadata columns:
#> seqnames ranges strand
#> <Rle> <IRanges> <Rle>
#> [1] chr21 5116346-5117232 +
#> [2] chr21 5117340-5117507 +
#> [3] chr21 5117539-5117558 +
#> [4] chr21 5117587-5117611 +
#> [5] chr21 5117670-5117817 +
#> ... ... ... ...
#> [5499] chr21 46668354-46668391 -
#> [5500] chr21 46668488-46668581 -
#> [5501] chr21 46690842-46691238 -
#> [5502] chr21 46691775-46691807 -
#> [5503] chr21 46692377-46692446 -
#> -------
#> seqinfo: 1 sequence from an unspecified genome; no seqlengths
#>
#>
#> $mcc_10
#> $mcc_10$mrg_10
#> GRanges object with 4293 ranges and 0 metadata columns:
#> seqnames ranges strand
#> <Rle> <IRanges> <Rle>
#> [1] chr21 5116356-5117231 +
#> [2] chr21 5117368-5117396 +
#> [3] chr21 5118691-5118847 +
#> [4] chr21 5120950-5120951 +
#> [5] chr21 5121718-5121803 +
#> ... ... ... ...
#> [4289] chr21 46665571-46665576 -
#> [4290] chr21 46665603-46665610 -
#> [4291] chr21 46690860-46691105 -
#> [4292] chr21 46691173-46691177 -
#> [4293] chr21 46691195-46691200 -
#> -------
#> seqinfo: 1 sequence from an unspecified genome; no seqlengths
#>
#> $mcc_10$mrg_20
#> GRanges object with 3814 ranges and 0 metadata columns:
#> seqnames ranges strand
#> <Rle> <IRanges> <Rle>
#> [1] chr21 5116356-5117231 +
#> [2] chr21 5117368-5117396 +
#> [3] chr21 5118691-5118847 +
#> [4] chr21 5120950-5120951 +
#> [5] chr21 5121718-5121803 +
#> ... ... ... ...
#> [3810] chr21 46665544-46665545 -
#> [3811] chr21 46665571-46665576 -
#> [3812] chr21 46665603-46665610 -
#> [3813] chr21 46690860-46691105 -
#> [3814] chr21 46691173-46691200 -
#> -------
#> seqinfo: 1 sequence from an unspecified genome; no seqlengths
#>
#>