1

我有这个对象：

nr.genes<-structure(c("0", "Pipas_chr3_1145", "Pipas_chr3_1145", "Pipas_chr1-4_0581", 
"Pipas_chr1-4_0582", "Pipas_chr1-4_0584", "Pipas_chr2-1_0006", 
"Pipas_chr2-2_0010", "Pipas_chr3_0002", "0", "0", "Pipas_c034_0013", 
"Pipas_chr1-4_0582", "Pipas_chr3_0002", "Pipas_chr4_0878", "Pipas_chr4_1001", 
"Pipas_chr4_0878", "Pipas_chr4_1001", "0", "Pipas_chr1-4_0581", 
"Pipas_chr1-4_0582", "Pipas_chr2-2_0010", "Pipas_chr3_0002", 
"Pipas_chr4_0878", "Pipas_chr4_1001", "0", "Pipas_c131_0003", 
"Pipas_chr1-1_0281", "Pipas_chr1-3_0004", "Pipas_chr3_1145", 
"Pipas_chr4_0003", "Pipas_c034_0013", "Pipas_c131_0003", "Pipas_chr1-3_0004", 
"Pipas_chr3_1145", "Pipas_chr4_0003", "0"), .Names = c("Nr11", 
"Nr12", "Nr13", "Nr141", "Nr142", "Nr143", "Nr144", "Nr145", 
"Nr146", "Nr21", "Nr22", "Nr23", "Nr241", "Nr242", "Nr311", "Nr312", 
"Nr321", "Nr322", "Nr33", "Nr341", "Nr342", "Nr343", "Nr344", 
"Nr345", "Nr346", "Nr41", "Nr421", "Nr422", "Nr423", "Nr424", 
"Nr425", "Nr431", "Nr432", "Nr433", "Nr434", "Nr435", "Nr44"))

我想用这个来改变名字：

nr.genes.names<-c("up.p33-dw.p33", "up.p33-dw.p38", "up.p33-dw.p52", "up.p33-dw.p64", 
"up.p38-dw.p33", "up.p38-dw.p38", "up.p38-dw.p52", "up.p38-dw.p64", 
"up.p52-dw.p33", "up.p52-dw.p38", "up.p52-dw.p52", "up.p52-dw.p64", 
"up.p64-dw.p33", "up.p64-dw.p38", "up.p64-dw.p52", "up.p64-dw.p64"
)

所以最终的结果nr.genes应该是

structure(c("0", "Pipas_chr3_1145", "Pipas_chr3_1145", "Pipas_chr1-4_0581", 
"Pipas_chr1-4_0582", "Pipas_chr1-4_0584", "Pipas_chr2-1_0006", 
"Pipas_chr2-2_0010", "Pipas_chr3_0002", "0", "0", "Pipas_c034_0013", 
"Pipas_chr1-4_0582", "Pipas_chr3_0002", "Pipas_chr4_0878", "Pipas_chr4_1001", 
"Pipas_chr4_0878", "Pipas_chr4_1001", "0", "Pipas_chr1-4_0581", 
"Pipas_chr1-4_0582", "Pipas_chr2-2_0010", "Pipas_chr3_0002", 
"Pipas_chr4_0878", "Pipas_chr4_1001", "0", "Pipas_c131_0003", 
"Pipas_chr1-1_0281", "Pipas_chr1-3_0004", "Pipas_chr3_1145", 
"Pipas_chr4_0003", "Pipas_c034_0013", "Pipas_c131_0003", "Pipas_chr1-3_0004", 
"Pipas_chr3_1145", "Pipas_chr4_0003", "0"), .Names = c("up.p33-dw.p33", 
"up.p33-dw.p38", "up.p33-dw.p52", "up.p33-dw.p64", "up.p33-dw.p64", 
"up.p33-dw.p64", "up.p33-dw.p64", "up.p33-dw.p64", "up.p33-dw.p64", 
"up.p38-dw.p33", "up.p38-dw.p38", "up.p38-dw.p52", "up.p38-dw.p64", 
"up.p38-dw.p64", "up.p52-dw.p33", "up.p52-dw.p33", "up.p52-dw.p38", 
"up.p52-dw.p38", "up.p52-dw.p52", "up.p52-dw.p64", "up.p52-dw.p64", 
"up.p52-dw.p64", "up.p52-dw.p64", "up.p52-dw.p64", "up.p52-dw.p64", 
"up.p64-dw.p33", "up.p64-dw.p38", "up.p64-dw.p38", "up.p64-dw.p38", 
"up.p64-dw.p38", "up.p64-dw.p38", "up.p64-dw.p52", "up.p64-dw.p52", 
"up.p64-dw.p52", "up.p64-dw.p52", "up.p64-dw.p52", "up.p64-dw.p64"
))

但是，如果我尝试使用这些表达式，我就不明白了： attr(nr.genes, "names") <- nr.genes.names[as.integer(gsub('^Nr[0-9]([0-9]).*','\\1',attr(nr.genes, "names")))]

我认为问题出在模式或替换中，因为我只是将前 4 个名称放在它们的位置，然后重复它们。我刚刚看到chartr()我不认为它会有所帮助。我该如何改进gsub？

编辑：我想改变

Nr11 by up.p33-dw.p33
Nr12 by up.p33-dw.p38
Nr13 by up.p33-dw.p52
Nr14 by up.p33-dw.p64
Nr21 by up.p38-dw.p33
Nr22 by up.p38-dw.p38
Nr23 by up.p38-dw.p52
Nr24 by up.p38-dw.p64
Nr31 by up.p52-dw.p33
Nr32 by up.p52-dw.p38
Nr33 by up.p52-dw.p52
Nr34 by up.p52-dw.p64
Nr41 by up.p64-dw.p33
Nr42 by up.p64-dw.p38
Nr43 by up.p64-dw.p52
Nr44 by up.p64-dw.p64
4

1 回答 1

2

没必要在regexp这里。你可以strtrim把你的名字命名为重要的字符，然后用来match 喜欢这个......

#  Get a vector of the unique elements of the bits of the old names we want to match against
idx <- sort( unique( strtrim(names(nr.genes),4) ) )
# [1] "Nr11" "Nr12" "Nr13" "Nr14" "Nr21" "Nr22" "Nr23" "Nr24" "Nr31" "Nr32" "Nr33" "Nr34" "Nr41" "Nr42"
#[15] "Nr43" "Nr44"

#  Match the old names to their position in the 'idx' vector, 
#  and use this as an index vector to select the new names
#  from 'nr.genes.names'.
#  This works because 'nr.gene.names' is sorted the same way
#  as 'idx', i.e. in ascending order.
new <- nr.genes.names[ match( strtrim(names(nr.genes),4) , idx ) ]

#  assign new names
names( nr.genes ) <- new
于 2013-10-31T10:12:46.853 回答