Replace a prefix of a string

Question

I have a data frame like this

> head(a[1:2,1:4])
   Tumor_Sample_Barcode Chromosome Position End_Position
1:                   A1       chr4 90169866     90169866
2:                   A1      chr11 60235747     60235747
    > dim(a)
[1] 753655    134
>
> unique(a$Tumor_Sample_Barcode)
 [1] "A1"  "A10" "A11" "A12" "A13" "A14" "A15" "A16" "A17" "A18" "A19" "A2"  "A20" "A21" "A22" "A23" "A24" "A25" "A26" "A27" "A28"
[22] "A29" "A3"  "A30" "A31" "A32" "A33" "A4"  "A5"  "A6"  "A7"  "A8"  "A9" 

I want to change a$Tumor_Sample_Barcode from A1:A21 to res1:res21 but I don't how to do that

Answer 1

I think you are looking for gsub function:

a$Tumor_Sample_Barcode <- gsub("A","res",a$Tumor_Sample_Barcode)

If you prefer, you can use the str_replace_all function from stringr package. But it tooks a little bit more time than gsub:

Dummy data

seq = as.factor(paste0("A",1:21))
library(data.table)
dt <- data.table(Barcode = rep(seq,10000),
                 Value = rnorm(210000))

Test of gsub vs str_replace_all

> system.time(dt$Barcode <- gsub("A","res",dt$Barcode))
   user  system elapsed 
  0.077   0.000   0.077 

> system.time(dt$Barcode <- str_replace_all(dt$Barcode,"A","res"))
   user  system elapsed 
  0.123   0.004   0.126 
```

Answer 2

Other options:

• Drop 1st character and prefix with "res"
• We get 5x speed up if we set fixed = TRUE for gsub.

microbenchmark::microbenchmark(
  # dc37 answer
  gsub("A","res", dt$Barcode),
  stringr::str_replace_all(dt$Barcode, "A", "res"),
  # other options
  paste0("res", substring(dt$Barcode, 2)),
  gsub("A","res",dt$Barcode, fixed = TRUE),

  # bench set up
  check = "identical", 
  unit = "relative"
  )

Unit: relative
                                             expr      min       lq     mean   median       uq      max neval
                     gsub("A", "res", dt$Barcode) 5.171682 5.132816 4.283014 5.033968 3.177772 2.545173   100
 stringr::str_replace_all(dt$Barcode, "A", "res") 6.914598 6.870849 5.747396 6.728126 4.809257 3.518024   100
          paste0("res", substring(dt$Barcode, 2)) 1.983757 1.991876 1.779557 1.968488 1.480892 3.415619   100
       gsub("A", "res", dt$Barcode, fixed = TRUE) 1.000000 1.000000 1.000000 1.000000 1.000000 1.000000   100