Find genes, exons, and introns in a gff3 file

If tsv files are written out by selecting "write_all" for `out_type`, they will overwrite any existing files with the same name in `out_dir`.

find_bed_regions(gff3_file, source_select = NULL, gene_label = "gene",
  exon_label = "exon", verbose = FALSE, prefix = NULL,
  out_dir = NULL, out_type = c("genes", "introns", "exons",
  "write_all"), ...)

Arguments

gff3_file	Path to input file in `gff3` format.
source_select	Character vector; only use regions from these sources. Must match values in `source` column of gff3 file. Optional.
gene_label	String; value used to indicate genes in gff3 file. Must match at least one value in `type` column of gff3 file. Default "gene".
exon_label	String; value used to indicate exons in gff3 file. Must match at least one value in `type` column of gff3 file. Default "exon".
verbose	Logical; should `bedr` functions output all messages?
prefix	String; prefix to attach to tsv files if `out_type` is "write_all".
out_dir	Directory to write tsv files if `out_type` is "write_all".
out_type	Type of output to return: "genes": dataframe in "bed" format of genes. "introns": dataframe in "bed" format of introns. "exons": dataframe in "bed" format of exons. "write_all": write tab-separated files for each of `genes`, `introns`, and `exons` to `out_dir`. The hash digest of the combined genes, introns, and exons will be returned.
...	Other arguments. Not used by this function, but meant to be used by drake_plan for tracking during workflows.

Value

Dataframe or character.

Examples

# Find genes

arabidopsis_gff_file <- system.file("extdata", "Arabidopsis_thaliana_TAIR10_40_small.gff3", package = "baitfindR", mustWork = TRUE)

genes <- find_bed_regions(
  gff3_file = arabidopsis_gff_file,
  source_select = "araport11",
  out_type = "genes"
)
head(genes)
#>               chr start   end
#> 1:3631-5899     1  3631  5899
#> 1:6788-9130     1  6788  9130
#> 1:11649-13714   1 11649 13714
#> 1:23121-33171   1 23121 33171
#> 1:33365-37871   1 33365 37871
#> 1:38444-41017   1 38444 41017

# Find introns
introns <- find_bed_regions(
  gff3_file = arabidopsis_gff_file,
  source_select = "araport11",
  out_type = "introns"
)
head(introns)
#>             chr start  end
#> 1:3913-3996   1  3913 3996
#> 1:4276-4486   1  4276 4486
#> 1:4605-4706   1  4605 4706
#> 1:5095-5174   1  5095 5174
#> 1:5326-5439   1  5326 5439
#> 1:7069-7157   1  7069 7157

# Find exons
exons <- find_bed_regions(
  gff3_file = arabidopsis_gff_file,
  source_select = "araport11",
  out_type = "exons"
)
head(exons)
#>             chr start  end
#> 1:3631-3913   1  3631 3913
#> 1:3996-4276   1  3996 4276
#> 1:4486-4605   1  4486 4605
#> 1:4706-5095   1  4706 5095
#> 1:5174-5326   1  5174 5326
#> 1:5439-5899   1  5439 5899

# NOT RUN {
# Write genes, introns, and exons out as tsv files
temp_dir <- tempdir()
find_bed_regions(
  gff3_file = arabidopsis_gff_file,
  source_select = "araport11",
  out_type = "write_all",
  out_dir = temp_dir,
  prefix = "arabidopsis"
)
# }