Extract and replace all subsequences from a bstr sequences

Extract and replace all subsequences from a bstr sequences

bstr_sub_all(bstrobj, from = list(1L), to = list(-1L), length)

bstr_sub_all(bstrobj, from = list(1L), to = list(-1L), length, omit_na = FALSE) <- value

bstr_sub_replace_all(..., replacement, value = replacement)

bstr_sub_all_replace(..., replacement, value = replacement)

Arguments

bstrobj	bstr class object or character vector
from	a list of integer vectors giving the start indexes or a list of two-column matrices, each of type cbind(from, to)
to	a list of integer vectors giving the end indexes
length	a list of integer vectors giving the substring lengths
omit_na	a single logical value; indicates whether missing values in any of the indexes or in value leave the part of the corresponding input string unchanged [replacement function only]
value	a list of character vectors defining the replacement strings [replacement function only]
...	arguments to be passed to bstr_sub_all<-
replacement	alias of value [wherever applicable]

Examples

(temp <- dstr_rand_seq(3, 20, "[AT]", seed = 1))
#> class: dstr,bstr,character 
#> number of sequences: 3 
#> [1]      no name 1      : AATTATTTTAAATATATTAT                     20 
#> [2]      no name 2      : TATAAAAATAATAATTTATA                     20 
#> [3]      no name 3      : TTTTTTAATTATAAAAATTA                     20 

(pos_A_trails <- stringr::str_locate_all(temp, "A{2,}"))
#> [[1]]
#>      start end
#> [1,]     1   2
#> [2,]    10  12
#> 
#> [[2]]
#>      start end
#> [1,]     4   8
#> [2,]    10  11
#> [3,]    13  14
#> 
#> [[3]]
#>      start end
#> [1,]     7   8
#> [2,]    13  17
#> 

# Extract all A trails
bstr_sub_all(temp, pos_A_trails)
#> $`no name 1`
#> class: bstr,character 
#> number of sequences: 2 
#> [1]     no name 1 1     : AA                                       2 
#> [2]     no name 1 2     : AAA                                      3 
#> 
#> $`no name 2`
#> class: bstr,character 
#> number of sequences: 3 
#> [1]     no name 2 1     : AAAAA                                    5 
#> [2]     no name 2 2     : AA                                       2 
#> [3]     no name 2 3     : AA                                       2 
#> 
#> $`no name 3`
#> class: bstr,character 
#> number of sequences: 2 
#> [1]     no name 3 1     : AA                                       2 
#> [2]     no name 3 2     : AAAAA                                    5 
#> 

# Substitute all A trails by x
bstr_sub_all(temp, pos_A_trails) <- "x"
temp
#> class: dstr,bstr,character 
#> number of sequences: 3 
#> [1]      no name 1      : xTTATTTTxTATATTAT                        17 
#> [2]      no name 2      : TATxTxTxTTTATA                           14 
#> [3]      no name 3      : TTTTTTxTTATxTTA                          15 

# Substitute all A trails by case switched ones
original <- change <- dstr_rand_seq(2, 10, "[AaT]", seed = 1)
pos_A_trails <- stringr::str_locate_all(change, "[Aa]{2,}")
switched_A_trails <-
  bstr_sub_all(change, pos_A_trails) %>%
  lapply(bstr_switch_case)
bstr_sub_all(change, pos_A_trails) <- switched_A_trails
c(original[1], change[1], original[2], change[2])
#> class: bstr,character 
#> number of sequences: 4 
#> [1]      no name 1      : ATTaAaaTTA                               10 
#> [2]      no name 1      : ATTAaAATTA                               10 
#> [3]      no name 2      : AAaTaTaaTa                               10 
#> [4]      no name 2      : aaATaTAATa                               10