从具有逗号分隔值的列中提取多个字符串

. s到 [^,] ^ ,意思是匹配任何东西 这些角色。所以呢 [^,]+ 表示尽可能多地匹配非逗号的连续字符。

df = structure(list(mut = c("Q184H/CAA-CAT", "I219V/ATC-GTC",
                            "A314T/GCG-ACG, P373Q/CCG-CAG, A653E/GCG-GAA","0")),
               row.names = c(NA, -4L), class = c("tbl_df", "tbl", "data.frame"))
library(dplyr)
#> 
#> Attaching package: 'dplyr'
#> The following objects are masked from 'package:stats':
#> 
#>     filter, lag
#> The following objects are masked from 'package:base':
#> 
#>     intersect, setdiff, setequal, union
df %>%
    mutate(nt = gsub("[^,]+?/([^,]+?)", "\\1", mut),
           mut = gsub("([^/]+)/[^,]+", "\\1", mut))
#> # A tibble: 4 x 2
#>   mut                 nt                     
#>   <chr>               <chr>                  
#> 1 Q184H               CAA-CAT                
#> 2 I219V               ATC-GTC                
#> 3 A314T, P373Q, A653E GCG-ACG,CCG-CAG,GCG-GAA
#> 4 0                   0

^{于2018-10-10由 reprex package (第0.2.1版)}

不要 接受这个答案(@duckmayr做了regex调试)。发布这篇文章是为了向人们展示 stringi 我们可以得到自我记录的正则表达式,这样我们未来的自我就不会最终憎恨过去的自我:

library(stringi) # it's what stringr uses
library(tidyverse)

xdf <- structure(list(mut = c("Q184H/CAA-CAT", "I219V/ATC-GTC", "A314T/GCG-ACG, P373Q/CCG-CAG, A653E/GCG-GAA","0")), row.names = c(NA, -4L), class = c("tbl_df", "tbl", "data.frame"))

mutate(
  xdf, 
  nt = stri_replace_all_regex(
    str = mut,
    pattern = "
[^,]+?  # match anything but a comma and if there is one, match at most once
/       # followed by a forward slash
(       # start of match group
 [^,]+? # same as above
)       # end of match group
",
    replacement = "$1", # take the match group value as the value
    opts_regex = stri_opts_regex(comments=TRUE)
  ),
  mut = stri_replace_all_regex(
    str = mut,
    pattern = "
(      # start of match group
 [^/]+ # match anything but a forward slash
)      # end of match group
/      # followed by a forward slash
[^,]+  # match anything but a comma
",
    replacement = "$1", # take the match group value as the value
    opts_regex = stri_opts_regex(comments=TRUE)
  )
)