Extract a character column into multiple columns using regular expression groups

Source: R/tidyr_methods.R

[Superseded]

extract() has been superseded in favour of separate_wider_regex() because it has a more polished API and better handling of problems. Superseded functions will not go away, but will only receive critical bug fixes.

Given a regular expression with capturing groups, extract() turns each group into a new column. If the groups don't match, or the input is NA, the output will be NA.

# S3 method for class 'SpatialExperiment'
extract(
  data,
  col,
  into,
  regex = "([[:alnum:]]+)",
  remove = TRUE,
  convert = FALSE,
  ...
)

Arguments

data

A data frame.

col

<tidy-select> Column to expand.

into

Names of new variables to create as character vector. Use NA to omit the variable in the output.

regex

A string representing a regular expression used to extract the desired values. There should be one group (defined by ()) for each element of into.

remove

If TRUE, remove input column from output data frame.

convert

If TRUE, will run type.convert() with as.is = TRUE on new columns. This is useful if the component columns are integer, numeric or logical.

NB: this will cause string "NA"s to be converted to NAs.

...

Additional arguments passed on to methods.

Value

tidySpatialExperiment

See also

separate() to split up by a separator.

Examples

example(read10xVisium)
#> 
#> rd10xV> dir <- system.file(
#> rd10xV+   file.path("extdata", "10xVisium"), 
#> rd10xV+   package = "SpatialExperiment")
#> 
#> rd10xV> sample_ids <- c("section1", "section2")
#> 
#> rd10xV> samples <- file.path(dir, sample_ids, "outs")
#> 
#> rd10xV> list.files(samples[1])
#> [1] "raw_feature_bc_matrix" "spatial"              
#> 
#> rd10xV> list.files(file.path(samples[1], "spatial"))
#> [1] "scalefactors_json.json"    "tissue_lowres_image.png"  
#> [3] "tissue_positions_list.csv"
#> 
#> rd10xV> file.path(samples[1], "raw_feature_bc_matrix")
#> [1] "/__w/_temp/Library/SpatialExperiment/extdata/10xVisium/section1/outs/raw_feature_bc_matrix"
#> 
#> rd10xV> (spe <- read10xVisium(samples, sample_ids, 
#> rd10xV+   type = "sparse", data = "raw", 
#> rd10xV+   images = "lowres", load = FALSE))
#> # A SpatialExperiment-tibble abstraction: 99 × 7
#> # Features = 50 | Cells = 99 | Assays = counts
#>    .cell              in_tissue array_row array_col sample_id pxl_col_in_fullres
#>    <chr>              <lgl>         <int>     <int> <chr>                  <int>
#>  1 AAACAACGAATAGTTC-1 FALSE             0        16 section1                2312
#>  2 AAACAAGTATCTCCCA-1 TRUE             50       102 section1                8230
#>  3 AAACAATCTACTAGCA-1 TRUE              3        43 section1                4170
#>  4 AAACACCAATAACTGC-1 TRUE             59        19 section1                2519
#>  5 AAACAGAGCGACTCCT-1 TRUE             14        94 section1                7679
#>  6 AAACAGCTTTCAGAAG-1 FALSE            43         9 section1                1831
#>  7 AAACAGGGTCTATATT-1 FALSE            47        13 section1                2106
#>  8 AAACAGTGTTCCTGGG-1 FALSE            73        43 section1                4170
#>  9 AAACATGGTGAGAGGA-1 FALSE            62         0 section1                1212
#> 10 AAACATTTCCCGGATT-1 FALSE            61        97 section1                7886
#> # ℹ 89 more rows
#> # ℹ 1 more variable: pxl_row_in_fullres <int>
#> 
#> rd10xV> # base directory 'outs/' from Space Ranger can also be omitted
#> rd10xV> samples2 <- file.path(dir, sample_ids)
#> 
#> rd10xV> (spe2 <- read10xVisium(samples2, sample_ids, 
#> rd10xV+   type = "sparse", data = "raw", 
#> rd10xV+   images = "lowres", load = FALSE))
#> # A SpatialExperiment-tibble abstraction: 99 × 7
#> # Features = 50 | Cells = 99 | Assays = counts
#>    .cell              in_tissue array_row array_col sample_id pxl_col_in_fullres
#>    <chr>              <lgl>         <int>     <int> <chr>                  <int>
#>  1 AAACAACGAATAGTTC-1 FALSE             0        16 section1                2312
#>  2 AAACAAGTATCTCCCA-1 TRUE             50       102 section1                8230
#>  3 AAACAATCTACTAGCA-1 TRUE              3        43 section1                4170
#>  4 AAACACCAATAACTGC-1 TRUE             59        19 section1                2519
#>  5 AAACAGAGCGACTCCT-1 TRUE             14        94 section1                7679
#>  6 AAACAGCTTTCAGAAG-1 FALSE            43         9 section1                1831
#>  7 AAACAGGGTCTATATT-1 FALSE            47        13 section1                2106
#>  8 AAACAGTGTTCCTGGG-1 FALSE            73        43 section1                4170
#>  9 AAACATGGTGAGAGGA-1 FALSE            62         0 section1                1212
#> 10 AAACATTTCCCGGATT-1 FALSE            61        97 section1                7886
#> # ℹ 89 more rows
#> # ℹ 1 more variable: pxl_row_in_fullres <int>
#> 
#> rd10xV> # tabulate number of spots mapped to tissue
#> rd10xV> cd <- colData(spe)
#> 
#> rd10xV> table(
#> rd10xV+   in_tissue = cd$in_tissue, 
#> rd10xV+   sample_id = cd$sample_id)
#>          sample_id
#> in_tissue section1 section2
#>     FALSE       28       27
#>     TRUE        22       22
#> 
#> rd10xV> # view available images
#> rd10xV> imgData(spe)
#> DataFrame with 2 rows and 4 columns
#>     sample_id    image_id   data scaleFactor
#>   <character> <character> <list>   <numeric>
#> 1    section1      lowres   ####   0.0510334
#> 2    section2      lowres   ####   0.0510334
spe |> 
    extract(col = array_row, into = "A", regex = "([[:digit:]]3)")
#> # A SpatialExperiment-tibble abstraction: 99 × 7
#> # Features = 50 | Cells = 99 | Assays = counts
#>    .cell              in_tissue A     array_col sample_id pxl_col_in_fullres
#>    <chr>              <lgl>     <chr>     <int> <chr>                  <int>
#>  1 AAACAACGAATAGTTC-1 FALSE     NA           16 section1                2312
#>  2 AAACAAGTATCTCCCA-1 TRUE      NA          102 section1                8230
#>  3 AAACAATCTACTAGCA-1 TRUE      NA           43 section1                4170
#>  4 AAACACCAATAACTGC-1 TRUE      NA           19 section1                2519
#>  5 AAACAGAGCGACTCCT-1 TRUE      NA           94 section1                7679
#>  6 AAACAGCTTTCAGAAG-1 FALSE     43            9 section1                1831
#>  7 AAACAGGGTCTATATT-1 FALSE     NA           13 section1                2106
#>  8 AAACAGTGTTCCTGGG-1 FALSE     73           43 section1                4170
#>  9 AAACATGGTGAGAGGA-1 FALSE     NA            0 section1                1212
#> 10 AAACATTTCCCGGATT-1 FALSE     NA           97 section1                7886
#> # ℹ 89 more rows
#> # ℹ 1 more variable: pxl_row_in_fullres <int>