删除括号中的字符串并将其添加为新列

Question

可能重复的Here

我有两列的数据框架。我希望删除括号中的字符串，并将其添加为新列。数据帧显示在下面。

      structure(list(ID = 1:12, Gene.Name = structure(c(3L, 11L, 9L, 
5L, 1L, 8L, 2L, 4L, 6L, 12L, 10L, 7L), .Label = c(" ATP synt, H+ tran, O subunit (oligomycin sensitivity conferring protein) (ATP5O), mRNA", 
" heterogeneous nuclear ribonucleoprotein F (HNRPF), mRNA", " NADH (ubiquinone) 1 alpha subcomplex, 4 (9kD, MLRQ) (NDUFA4), mRNA", 
" ribosomal protein L34 (RPL34), transcript variant 1, mRNA", 
" ribosomal protein S11 (RPS11), mRNA", "ATP synthase, H+ tran, mitochondrial F0, subunit c (subunit 9) isoform 3 (ATP5G3), mRNA", 
"clone MGC:10120 IMAGE:3900723, mRNA, complete cds", "cytidine monophosphate N-acetylneuraminic acid synthetase (CMAS), mRNA", 
"farnesyl-diphosphate farnesyltransferase 1 (FDFT1), mRNA", "homeobox protein from AL590526 (LOC84528), mRNA", 
"mitochondrial  S33 (MRPS33), transcript variant 1, nuclear gene, mRNA", 
"ribosomal protein S15a (RPS15A), mRNA"), class = "factor")), .Names = c("ID", 
"Gene.Name"), row.names = c(NA, -12L), class = "data.frame")

如果没有找到括号中的字符串，则将该行保留为空。这里我有两个箱子

1)获取括号中的所有字符串，并将其添加为用,分隔的新列

2)括号中的最后一个字符串并将其添加为新列

我尝试了类似于df$Symbol <- sapply(df, function(x) sub("\\).*", "", sub(".*\\(", "", x)))的东西，但是没有给出适当的输出

案例1产出

ID  Gene.Name                                                                                    Symbol
1    NADH (ubiquinone) 1 alpha subcomplex, 4 (9kD, MLRQ) (NDUFA4), mRNA                       ubiquinone, (9kD, MLRQ),NDUFA4
2   mitochondrial  S33 (MRPS33), transcript variant 1, nuclear gene, mRNA                      MRPS33
3   farnesyl-diphosphate farnesyltransferase 1 (FDFT1), mRNA                                   FDFT1
4    ribosomal protein S11 (RPS11), mRNA                                                       RPS11
5    ATP synt, H+ tran, O subunit (oligomycin sensitivity conferring protein) (ATP5O), mRNA   oligomycin sensitivity conferring protein,ATP5O
6   cytidine monophosphate N-acetylneuraminic acid synthetase (CMAS), mRNA                     CMAS
7    heterogeneous nuclear ribonucleoprotein F (HNRPF), mRNA                                   HNRPF
8    ribosomal protein L34 (RPL34), transcript variant 1, mRNA                                 RPL34
9   ATP synthase, H+ tran, mitochondrial F0, subunit c (subunit 9) isoform 3 (ATP5G3), mRNA   subunit 9,ATP5G3
10  ribosomal protein S15a (RPS15A), mRNA                                                      RPS15A
11  homeobox protein from AL590526 (LOC84528), mRNA                                            LOC84528
12  clone MGC:10120 IMAGE:3900723, mRNA, complete cds                                          NA

案例2产出

ID                                                                               Gene.Name   Symbol
1                      NADH (ubiquinone) 1 alpha subcomplex, 4 (9kD, MLRQ) (NDUFA4), mRNA   NDUFA4
2                   mitochondrial  S33 (MRPS33), transcript variant 1, nuclear gene, mRNA   MRPS33
3                                farnesyl-diphosphate farnesyltransferase 1 (FDFT1), mRNA   FDFT1
4                                                     ribosomal protein S11 (RPS11), mRNA   RPS11
5  ATP synt, H+ tran, O subunit (oligomycin sensitivity conferring protein) (ATP5O), mRNA   ATP5O
6                  cytidine monophosphate N-acetylneuraminic acid synthetase (CMAS), mRNA   CMAS
7                                 heterogeneous nuclear ribonucleoprotein F (HNRPF), mRNA   HNRPF
8                               ribosomal protein L34 (RPL34), transcript variant 1, mRNA   RPL34
9 ATP synthase, H+ tran, mitochondrial F0, subunit c (subunit 9) isoform 3 (ATP5G3), mRNA   ATP5G3
10                                                   ribosomal protein S15a (RPS15A), mRNA  RPS15A
11                                         homeobox protein from AL590526 (LOC84528), mRNA  LOC84528
12                                       clone MGC:10120 IMAGE:3900723, mRNA, complete cds   <NA>

Answer 1

使用sub获取字符串末尾圆括号中的单词的选项。

 Symbol <- sub('.*\\(([^\\)]+)\\)[^\\(]+$', '\\1',df1[,2])
 df1$Symbol <- Symbol[1:nrow(df1)*NA^(!grepl('\\(',df1[,2]))]
 df1$Symbol
 #[1] "NDUFA4"   "MRPS33"   "FDFT1"    "RPS11"    "ATP5O"    "CMAS"    
 #[7] "HNRPF"    "RPL34"    "ATP5G3"   "RPS15A"   "LOC84528" NA   

更新

第一个案子.提取圆括号中的所有字符并使用,将它们粘贴到一起，其中一个选项是从qdapRegex中提取rm_round。rm_round的输出是list。因此，我们使用lapply/sapply循环通过list。在其中包含,的字符串用grep分隔，我们用圆括号分隔，然后将字符串与collapse=', '放在一起。一个方便的包装函数是toString。

 library(qdapRegex)
 df1$allSymbol <-  sapply(rm_round(df1[,2],extract=TRUE), function(x) {
                         indx <- grep(',', x)
                        x[indx] <-paste0("(", x[indx], ")")
                         toString(x)})

 is.na(df1$allSymbol) <- df1$allSymbol=='NA'
 df1[3:4]
 #                                          allSymbol   Symbol
 #1                   ubiquinone, (9kD, MLRQ), NDUFA4   NDUFA4
 #2                                            MRPS33   MRPS33
 #3                                             FDFT1    FDFT1
 #4                                             RPS11    RPS11
 #5  oligomycin sensitivity conferring protein, ATP5O    ATP5O
 #6                                              CMAS     CMAS
 #7                                             HNRPF    HNRPF
 #8                                             RPL34    RPL34
 #9                                 subunit 9, ATP5G3   ATP5G3
 #10                                           RPS15A   RPS15A
 #11                                         LOC84528 LOC84528
 #12                                             <NA>     <NA>

Answer 2

我想我找到了一条简单的出路，但如果你能逃脱的话，你只需要匹配括号中那些看起来像基因符号的东西，即只有大写字母和数字。

dd <- structure(list(ID = 1:12, Gene.Name = structure(c(3L, 11L, 9L, 5L, 1L, 8L, 2L, 4L, 6L, 12L, 10L, 7L), .Label = c(" ATP synt, H+ tran, O subunit (oligomycin sensitivity conferring protein) (ATP5O), mRNA", " heterogeneous nuclear ribonucleoprotein F (HNRPF), mRNA", " NADH (ubiquinone) 1 alpha subcomplex, 4 (9kD, MLRQ) (NDUFA4), mRNA", " ribosomal protein L34 (RPL34), transcript variant 1, mRNA", " ribosomal protein S11 (RPS11), mRNA", "ATP synthase, H+ tran, mitochondrial F0, subunit c (subunit 9) isoform 3 (ATP5G3), mRNA", "clone MGC:10120 IMAGE:3900723, mRNA, complete cds", "cytidine monophosphate N-acetylneuraminic acid synthetase (CMAS), mRNA", "farnesyl-diphosphate farnesyltransferase 1 (FDFT1), mRNA", "homeobox protein from AL590526 (LOC84528), mRNA", "mitochondrial  S33 (MRPS33), transcript variant 1, nuclear gene, mRNA", "ribosomal protein S15a (RPS15A), mRNA"), class = "factor")), .Names = c("ID", "Gene.Name"), row.names = c(NA, -12L), class = "data.frame")


dd$Gene.Name <- as.character(dd$Gene.Name)

## case 1
mm <- gregexpr('(?<=\\()(.*?)(?=\\))', dd$Gene.Name, perl = TRUE)
mm <- regmatches(dd$Gene.Name, mm)


dd <- cbind(dd, case1 = sapply(mm, function(x)
  ifelse(length(x), paste(x, collapse = ', '), NA)))
dd[, c(1,3)]

#    ID                                            case1
# 1   1                    ubiquinone, 9kD, MLRQ, NDUFA4
# 2   2                                           MRPS33
# 3   3                                            FDFT1
# 4   4                                            RPS11
# 5   5 oligomycin sensitivity conferring protein, ATP5O
# 6   6                                             CMAS
# 7   7                                            HNRPF
# 8   8                                            RPL34
# 9   9                                subunit 9, ATP5G3
# 10 10                                           RPS15A
# 11 11                                         LOC84528
# 12 12                                             <NA>

## case 2
mm <- gregexpr('(?<=\\()([A-Z0-9]+)(?=\\))', dd$Gene.Name, perl = TRUE)
mm <- regmatches(dd$Gene.Name, mm)


dd <- cbind(dd, case2 = sapply(mm, function(x) ifelse(length(x), x, NA)))
dd[, c(1,4)]

#    ID    case2
# 1   1   NDUFA4
# 2   2   MRPS33
# 3   3    FDFT1
# 4   4    RPS11
# 5   5    ATP5O
# 6   6     CMAS
# 7   7    HNRPF
# 8   8    RPL34
# 9   9   ATP5G3
# 10 10   RPS15A
# 11 11 LOC84528
# 12 12     <NA>