Regex 删除括号中的字符串并将其作为新列添加
可能重复 我有一个两列的数据框。我想删除括号中的字符串并将其作为新列添加。数据框显示在下面Regex 删除括号中的字符串并将其作为新列添加,regex,r,substring,Regex,R,Substring,可能重复 我有一个两列的数据框。我想删除括号中的字符串并将其作为新列添加。数据框显示在下面 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),
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")
，我尝试了一些类似于
df$Symbol的方法，我想我采取了简单的方法，但是如果你能侥幸逃脱，只需匹配括号中看起来像基因符号的东西，即，只有大写字母和数字
dd <- structure(list(ID = 1:12, Gene.Name = structure(c(3L, 11L, 9L, 5L, 1L, 8L, 2L, 4L, 6L, 12L, 10L, 7L), .Label = c(" ATP synt, H+ tran, O subunit (oligomycin sensitivity conferring protein) (ATP5O), mRNA", " heterogeneous nuclear ribonucleoprotein F (HNRPF), mRNA", " NADH (ubiquinone) 1 alpha subcomplex, 4 (9kD, MLRQ) (NDUFA4), mRNA", " ribosomal protein L34 (RPL34), transcript variant 1, mRNA", " ribosomal protein S11 (RPS11), mRNA", "ATP synthase, H+ tran, mitochondrial F0, subunit c (subunit 9) isoform 3 (ATP5G3), mRNA", "clone MGC:10120 IMAGE:3900723, mRNA, complete cds", "cytidine monophosphate N-acetylneuraminic acid synthetase (CMAS), mRNA", "farnesyl-diphosphate farnesyltransferase 1 (FDFT1), mRNA", "homeobox protein from AL590526 (LOC84528), mRNA", "mitochondrial S33 (MRPS33), transcript variant 1, nuclear gene, mRNA", "ribosomal protein S15a (RPS15A), mRNA"), class = "factor")), .Names = c("ID", "Gene.Name"), row.names = c(NA, -12L), class = "data.frame")
dd$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$Gene.Name, mm)
dd <- cbind(dd, case2 = sapply(mm, function(x) ifelse(length(x), x, NA)))
dd[, c(1,4)]
# ID case2
# 1 1 NDUFA4
# 2 2 MRPS33
# 3 3 FDFT1
# 4 4 RPS11
# 5 5 ATP5O
# 6 6 CMAS
# 7 7 HNRPF
# 8 8 RPL34
# 9 9 ATP5G3
# 10 10 RPS15A
# 11 11 LOC84528
# 12 12 <NA>
dd使用sub
获取字符串末尾圆括号内的单词的选项
Symbol <- sub('.*\\(([^\\)]+)\\)[^\\(]+$', '\\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
@akrun可能是，但我在这里提到了两个案例，我只是想展示案例2的输出。R3.1.2可用的qdapRegex
可以正常工作，而不是（9kD，MLRQ）
给出了9kD，MLRQ
正确的结果。抱歉打扰了。你检查过更新的问题了吗，案例1输出了很多汉克斯。完美。@Hashim我认为案例1更加直截了当，请参见编辑
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>
Symbol <- sub('.*\\(([^\\)]+)\\)[^\\(]+$', '\\1',df1[,2])
df1$Symbol <- Symbol[1:nrow(df1)*NA^(!grepl('\\(',df1[,2]))]
df1$Symbol
#[1] "NDUFA4" "MRPS33" "FDFT1" "RPS11" "ATP5O" "CMAS"
#[7] "HNRPF" "RPL34" "ATP5G3" "RPS15A" "LOC84528" NA
library(qdapRegex)
df1$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>