r - 如何通过匹配另一个数据框中的整个列中的字符串来检索一个数据框中的值？

Question

假设我有一个如下所示的数据框 df1:

> df1
          probe                         OMIM
1  1565034_s_at                       601464
2     201000_at 601065 /// 613287 /// 616339
3     204565_at                       615652
4     205355_at            600301 /// 610006
5   205734_s_at                       601464
6   205735_s_at                       601464
7     206527_at            137150 /// 613163
8     209173_at                       606358
9   209459_s_at            137150 /// 613163
10    209460_at            137150 /// 613163
11    215465_at                             
12    223864_at                       610856
13    224742_at            612674 /// 613599

还有第二个数据框，df2:

> df2
                                         platprobe   symbol
1   1565034_s_at,205734_s_at,242078_at,205735_s_at     AFF3
2                                        201000_at     AARS
3                                        201884_at   DNALI1
4                                      202779_s_at     PLK1
5                                        204565_at   ACOT13
6                              205355_at,226030_at   ACADSB
7      205808_at,207284_s_at,209135_at,210896_s_at   LIMCH1
8      206164_at,206165_s_at,206166_s_at,217528_at   SLC7A8
9                  206527_at,209459_s_at,209460_at     ABAT
10                             209173_at,228969_at     AGR2
11                                       215465_at   ABCA12
12                                     221024_s_at  TMEM144
13                                       223864_at ANKRD30A
14                 224742_at,228123_s_at,228124_at   ABHD12
15                           225421_at,225431_x_at   GALNT7
16                                       226120_at    PSAT1
17                                       228241_at     AGR3

我想向 df1 添加一个新列，df1$symbol，基于 df1$probe 值与 的匹配df2$platprobe。结果应该是这样的:

> df1
          probe                         OMIM    symbol
1  1565034_s_at                       601464      AFF3
2     201000_at 601065 /// 613287 /// 616339      AARS
3     204565_at                       615652    ACOT13
4     205355_at            600301 /// 610006    ACADSB
5   205734_s_at                       601464      AFF3
6   205735_s_at                       601464      AFF3
7     206527_at            137150 /// 613163      ABAT
8     209173_at                       606358      AGR2
9   209459_s_at            137150 /// 613163      ABAT
10    209460_at            137150 /// 613163      ABAT
11    215465_at                                 ABCA12
12    223864_at                       610856  ANKRD30A
13    224742_at            612674 /// 613599    ABHD12

对我来说具有挑战性的部分是 df2$platprobe 在许多情况下包含各种注释，而不是在 in df1$probe 中找到的注释。所以，如果我尝试:

#This will retrieve only perfect matches (where df2$platprobe contains only one possible value, such as ABCA12):
df1$symbol <- df2$symbol[df2$probe %in% df1$platprobe]

#And if I use 'grepl', that won't work:
#(The reason for using 'unlist' and 'strsplit' is because I thought that maybe breaking all possible
#values from the entire df2$platprobe into a object that would work. But it doesn't)

df1$symbol <- df2$symbol[grepl(df1$probe, unlist(strsplit(paste(df2$platprobe, sep=",", collapse=","), ",")))]

非常感谢任何帮助。

PS:另外，如果您对更多主题标题有更好的想法，非常欢迎。

更新谢谢@Anoushiravan R。很抱歉没有把可重现的 df 放在前面。现在，它们在这里:

df1 <- data.frame(probe=c("1565034_s_at", "201000_at", "204565_at", 
"205355_at", "205734_s_at", "205735_s_at", "206527_at", "209173_at", 
"209459_s_at", "209460_at", "215465_at", "223864_at", "224742_at"
), OMIM = c("601464", "601065 /// 613287 /// 616339", "615652", 
"600301 /// 610006", "601464", "601464", "137150 /// 613163", 
"606358", "137150 /// 613163", "137150 /// 613163", "", "610856", 
"612674 /// 613599"))

df2 <- data.frame(platprobe = c("1565034_s_at, 205734_s_at, 205735_s_at, 
227198_at, 242078_at, 243967_at", "201000_at", "201884_at", "202779_s_at",
"204565_at", "205355_at,226030_at", "205808_at, 207284_s_at, 209135_at, 
210896_s_at, 224996_at, 225008_at, 242037_at", "206164_at, 206165_s_at, 
206166_s_at, 217528_at", "206527_at, 209459_s_at,209460_at", "209173_at, 
228969_at", "215465_at", "221024_s_at", "223864_at","224742_at, 228123_s_at, 
228124_at", "225421_at,225431_x_at", "226120_at", "228241_at"), symbol=c("AFF3", 
"AARS", "DNALI1", "PLK1", "ACOT13", "ACADSB", "LIMCH1", "SLC7A8", "ABAT", "AGR2", 
"ABCA12", "TMEM144", "ANKRD30A", "ABHD12", "GALNT7", "PSAT1", "AGR3"))

Answer 1

虽然上面的答案达到了目的，但还表明它可以在没有 purrr 的情况下完成

library(dplyr)
library(tidyr)
library(stringr)

df1 %>% left_join(df2 %>% separate_rows(platprobe, sep = ',') %>%
                    mutate(platprobe = str_trim(platprobe)), by = c('probe' = 'platprobe'))

          probe                         OMIM   symbol
1  1565034_s_at                       601464     AFF3
2     201000_at 601065 /// 613287 /// 616339     AARS
3     204565_at                       615652   ACOT13
4     205355_at            600301 /// 610006   ACADSB
5   205734_s_at                       601464     AFF3
6   205735_s_at                       601464     AFF3
7     206527_at            137150 /// 613163     ABAT
8     209173_at                       606358     AGR2
9   209459_s_at            137150 /// 613163     ABAT
10    209460_at            137150 /// 613163     ABAT
11    215465_at                                ABCA12
12    223864_at                       610856 ANKRD30A
13    224742_at            612674 /// 613599   ABHD12