R 获取表中每一行的文本，在另一个表中匹配这些文本，并创建一个包含所有匹配项的新表

让我用一个例子来解释这个问题。我有两个数据帧：

  df1 <- data.frame(Gene=c(1,2,3,4,5,6,7,8),
                 Description=c("ribonuclease HII", "Leucyl-tRNA synthetase", "Arginyl-tRNA synthetase (EC 6.1.1.19) 17855:19195", "Arginyl-tRNA synthetase (EC 6.1.1.19)", "PAS domain S-box protein", "ribonuclease HII", "Isoleucyl-tRNA synthetase", "Succinyl-CoA ligase"),
                 Species=c("aa", "bb","aa","cc","ee","ff","aa","dd"),
                 Number1= c(1,0,3,20,99,100,31,123),
                 Number2 =c(1000, 12636,12,455,231,454,123,1), stringsAsFactors = FALSE)

   > df1
  Gene                                       Description Species Number1 Number2
1    1                                  ribonuclease HII      aa       1    1000
2    2                            Leucyl-tRNA synthetase      bb       0   12636
3    3 Arginyl-tRNA synthetase (EC 6.1.1.19) 17855:19195      aa       3      12
4    4             Arginyl-tRNA synthetase (EC 6.1.1.19)      cc      20     455
5    5                          PAS domain S-box protein      ee      99     231
6    6                                  ribonuclease HII      ff     100     454
7    7                         Isoleucyl-tRNA synthetase      aa      31     123
8    8                               Succinyl-CoA ligase      dd     123       1

我曾尝试在for循环中使用grep函数，但未能成功。这里有一个棘手的部分：当搜索“精氨酰tRNA合成酶（EC 6.1.1.19）”时，它还应该捕获“精氨酰tRNA合成酶（EC 6.1.1.19）17855:19195”。但是，当函数搜索“亮氨酸tRNA合成酶”时，不应使用“Iso亮氨酸tRNA合成酶”，它包含与“亮氨酸tRNA合成酶”相同的措辞

---

提前谢谢。我也愿意听取你对文章标题和编辑的建议

您可以从

dplyr

使用

lejf\u join

功能：

library(dplyr)
df1 <- data.frame(Gene=c(1,2,3,4,5,6,7,8),
                  Description=c("ribonuclease HII", "Leucyl-tRNA synthetase", "Arginyl-tRNA synthetase (EC 6.1.1.19) 17855:19195", "Arginyl-tRNA synthetase (EC 6.1.1.19)", "PAS domain S-box protein", "ribonuclease HII", "Isoleucyl-tRNA synthetase", "Succinyl-CoA ligase"),
                  Species=c("aa", "bb","aa","cc","ee","ff","aa","dd"),
                  Number1= c(1,0,3,20,99,100,31,123),
                  Number2 =c(1000, 12636,12,455,231,454,123,1), stringsAsFactors = FALSE)

df2 <- data.frame(Description=c("ribonuclease HII", "Leucyl-tRNA synthetase","Arginyl-tRNA synthetase (EC 6.1.1.19) 17855:19195", "Arginyl-tRNA synthetase (EC 6.1.1.19)"), stringsAsFactors = FALSE)

left_join(df2, df1, by = "Description") %>% select(Gene, everything())

祝你好运

您可以使用

grepl（）

获得所需的结果。首先，创建一个搜索模式（它没有单词边界（

“\\b”

），所以它只会查找匹配项）。然后使用

gsub（）

对除

“|”

以外的所有元字符进行转义，然后使用

grepl（）

对

df1

中的行进行子集化：

new_pat <-paste0(df2$Description, collapse = "|")
new_pat <- gsub("([][{}().+*^$\\?])", "\\\\\\1", new_pat)

df1[grepl(new_pat, df1$Description), ]
  Gene                                       Description Species Number1 Number2
1    1                                  ribonuclease HII      aa       1    1000
2    2                            Leucyl-tRNA synthetase      bb       0   12636
3    3 Arginyl-tRNA synthetase (EC 6.1.1.19) 17855:19195      aa       3      12
4    4             Arginyl-tRNA synthetase (EC 6.1.1.19)      cc      20     455
6    6                                  ribonuclease HII      ff     100     454

new\u pat
library(dplyr)
df1 <- data.frame(Gene=c(1,2,3,4,5,6,7,8),
                  Description=c("ribonuclease HII", "Leucyl-tRNA synthetase", "Arginyl-tRNA synthetase (EC 6.1.1.19) 17855:19195", "Arginyl-tRNA synthetase (EC 6.1.1.19)", "PAS domain S-box protein", "ribonuclease HII", "Isoleucyl-tRNA synthetase", "Succinyl-CoA ligase"),
                  Species=c("aa", "bb","aa","cc","ee","ff","aa","dd"),
                  Number1= c(1,0,3,20,99,100,31,123),
                  Number2 =c(1000, 12636,12,455,231,454,123,1), stringsAsFactors = FALSE)

df2 <- data.frame(Description=c("ribonuclease HII", "Leucyl-tRNA synthetase","Arginyl-tRNA synthetase (EC 6.1.1.19) 17855:19195", "Arginyl-tRNA synthetase (EC 6.1.1.19)"), stringsAsFactors = FALSE)

left_join(df2, df1, by = "Description") %>% select(Gene, everything())

  Gene                                       Description Species Number1 Number2
1    1                                  ribonuclease HII      aa       1    1000
2    6                                  ribonuclease HII      ff     100     454
3    2                            Leucyl-tRNA synthetase      bb       0   12636
4    3 Arginyl-tRNA synthetase (EC 6.1.1.19) 17855:19195      aa       3      12
5    4             Arginyl-tRNA synthetase (EC 6.1.1.19)      cc      20     455

new_pat <-paste0(df2$Description, collapse = "|")
new_pat <- gsub("([][{}().+*^$\\?])", "\\\\\\1", new_pat)

df1[grepl(new_pat, df1$Description), ]
  Gene                                       Description Species Number1 Number2
1    1                                  ribonuclease HII      aa       1    1000
2    2                            Leucyl-tRNA synthetase      bb       0   12636
3    3 Arginyl-tRNA synthetase (EC 6.1.1.19) 17855:19195      aa       3      12
4    4             Arginyl-tRNA synthetase (EC 6.1.1.19)      cc      20     455
6    6                                  ribonuclease HII      ff     100     454