Take a subset of columns and create a new MTX file-set

Usage

mmutil_copy_selected_columns(
  mtx_file,
  row_file,
  col_file,
  r_selected,
  output,
  MAX_COL_WORD = 100L,
  COL_WORD_SEP = "@"
)

Arguments

mtx_file: data file
row_file: row file
col_file: column file
output: output header
MAX_COL_WORD: maximum words per line in col_file
COL_WORD_SEP: word separation character to replace white space
selected: selected column names

Examples


options(stringsAsFactors=FALSE)
rr <- rgamma(20, 1, 1)
mm <- matrix(rgamma(10 * 2, 1, 1), 10, 2)
src.hdr <- "test_org"
src.files <- mmutil_simulate_poisson(mm, rr, src.hdr)
Y <- Matrix::readMM(src.files$mtx)
colnames(Y) <- read.table(src.files$col)$V1
print(Y)
#> 10 x 17 sparse Matrix of class "dgTMatrix"
#>   [[ suppressing 17 column names ‘1’, ‘2’, ‘3’ ... ]]
#>                                             
#>  [1,] 2 . 2 .  1  . . .  4  2 .  1 . . . 3 2
#>  [2,] . . . .  .  1 . 1  2  . 1  1 . . . . .
#>  [3,] . 1 . .  .  2 1 .  1  . .  2 . . 1 1 .
#>  [4,] . 1 . .  1  1 . .  .  . .  . . . . . .
#>  [5,] . . . .  .  2 . .  .  . .  . 1 . . . .
#>  [6,] . . . .  .  . . .  .  1 .  . . . . 1 2
#>  [7,] 5 4 3 .  3  5 3 . 12  4 . 10 . 1 . 2 1
#>  [8,] . . . .  1  . . .  .  . .  . 2 . . . .
#>  [9,] 4 2 7 2 14 11 3 3 16 15 2 12 . . . 3 .
#> [10,] 1 . 1 1  1  1 . .  .  1 .  1 . . 1 . 4
sub.cols <- sort(read.table(src.files$col)$V1[sample(20,3)])
print(sub.cols)
#> [1]  1  5 11
tgt.hdr <- "test_sub"
tgt.files <- mmutil_copy_selected_columns(
                         src.files$mtx,
                         src.files$row,
                         src.files$col,
                         sub.cols, tgt.hdr)
Y <- Matrix::readMM(tgt.files$mtx)
colnames(Y) <- read.table(tgt.files$col)$V1
print(Y)
#> 10 x 3 sparse Matrix of class "dgTMatrix"
#>       1  5 11
#>  [1,] 2  1  .
#>  [2,] .  .  1
#>  [3,] .  .  .
#>  [4,] .  1  .
#>  [5,] .  .  .
#>  [6,] .  .  .
#>  [7,] 5  3  .
#>  [8,] .  1  .
#>  [9,] 4 14  2
#> [10,] 1  1  .
unlink(list.files(pattern = src.hdr))
unlink(list.files(pattern = tgt.hdr))