如何在 R 中的多个列表中创建新列？

Question

我是 R 新手，我不太清楚要使用什么结构以及它们的正确语法。

我有列表（更像是带有列和列名的表）。我想对多个列表执行相同的功能。我认为使用 for 循环是合理的。

我的功能是

1) 使用列计算新列。 （根据 log2foldchange 计算倍数变化）

2) 使用旧列表的子集创建一个新列表，并将其命名为调整原始列表名称的名称

以下是分别适用于这些表的代码行。

#take values from the log2FoldChange column and calculate Fold Change
resCondition_anno$FoldChange <- 2^resCondition_anno$log2FoldChange 


#subset my dataset based on the values for each row in the padj column    
resCondition_anno_padj05 <- subset(resCondition_anno, resCondition$padj <= 0.05) 

我想对多个表执行这些功能。

当我尝试在 for 循环中执行此操作时

resfiles1 <- c(resCondition_anno,resVirus_anno,resInter_anno)

for (i in resfiles1){

 i$FoldChange <- 2^i$log2FoldChange # I was trying to calculate a new column based on log2FoldChange column

  i_with_padj05 <- paste(i,"_padj05") # I was trying to create a new name like resCondition_anno_padj05
  i_with_padj05 <- subset(i, i[[padj]] <= 0.05) # I was trying to subset my dataset based on values in the padj column
}

我尝试使用 $ 访问我的表的列，结果给了我

Error: $ operator is invalid for atomic vectors

我尝试使用 [padj] 访问我的表的列，我明白了

Error in subset.default(i, i[padj] <= 0.05) : object 'padj' not found

当我尝试使用 `[[padj]] 访问表的列时，出现以下错误

Error in subset.default(i, i[[padj]] <= 0.05) : object 'padj' not found

我是不是完全走错了路？ for 循环是实现我的目标的合理方法吗？我知道应用函数存在，但是当我尝试将多个文件输入其中时，我很难从中获取输出文件，所以我想尝试一下 for 循环。

我希望有一个代码适用于随机表并执行这些操作，然后我可以弄清楚我的表是否很奇怪。

 dput(head(resCondition_anno))
structure(list(ensembl = c("ENSMUSG00000051951", "ENSMUSG00000102331", 
"ENSMUSG00000025902", "ENSMUSG00000104238", "ENSMUSG00000102269", 
"ENSMUSG00000096126"), baseMean = c(2.34691358937965, 0.169507902147731, 
49.4591642836684, 0.253911076708937, 3.27439052075304, 0.258178295608587
), log2FoldChange = c(1.04699290132002, 1.89907052894015, 0.629095304499277, 
0.0597400040882164, -0.291997327218544, 1.97984690635658), lfcSE = c(1.09309963258445, 
4.36961772602319, 0.291712394209747, 4.37647193807779, 1.21524080418346, 
4.3263845102792), stat = c(0.95782019324678, 0.434607933236415, 
2.15656008104662, 0.0136502655411644, -0.240279396654017, 0.457621577937096
), pvalue = c(0.338153434807336, 0.66384703564954, 0.0310399577136823, 
0.989109002094381, 0.810113666298446, 0.647224338296786), padj = c(NA, 
NA, 0.106540309680362, NA, 0.911344697137259, NA), mgi_symbol = c("Xkr4", 
"Gm19938", "Sox17", "Gm37587", "Gm7357", "Gm22307"), gene_biotype = c("protein_coding", 
"sense_intronic", "protein_coding", "processed_transcript", "processed_pseudogene", 
"snRNA")), class = c("data.table", "data.frame"), row.names = c(NA, 
-6L), .internal.selfref = <pointer: 0x0000027bef7e1ef0>)`

目标 1 的预期结果

> dput(head(resCondition_anno))
structure(list(ensembl = c("ENSMUSG00000051951", "ENSMUSG00000102331", 
"ENSMUSG00000025902", "ENSMUSG00000104238", "ENSMUSG00000102269", 
"ENSMUSG00000096126"), baseMean = c(2.34691358937965, 0.169507902147731, 
49.4591642836684, 0.253911076708937, 3.27439052075304, 0.258178295608587
), log2FoldChange = c(1.04699290132002, 1.89907052894015, 0.629095304499277, 
0.0597400040882164, -0.291997327218544, 1.97984690635658), lfcSE = c(1.09309963258445, 
4.36961772602319, 0.291712394209747, 4.37647193807779, 1.21524080418346, 
4.3263845102792), stat = c(0.95782019324678, 0.434607933236415, 
2.15656008104662, 0.0136502655411644, -0.240279396654017, 0.457621577937096
), pvalue = c(0.338153434807336, 0.66384703564954, 0.0310399577136823, 
0.989109002094381, 0.810113666298446, 0.647224338296786), padj = c(NA, 
NA, 0.106540309680362, NA, 0.911344697137259, NA), mgi_symbol = c("Xkr4", 
"Gm19938", "Sox17", "Gm37587", "Gm7357", "Gm22307"), gene_biotype = c("protein_coding", 
"sense_intronic", "protein_coding", "processed_transcript", "processed_pseudogene", 
"snRNA"), FoldChange = c(2.0662186086592, 3.72972827627808, 1.54659483966075, 
1.0422779093498, 0.816770504282921, 3.94451221821964)), class = c("data.table", 
"data.frame"), row.names = c(NA, -6L), .internal.selfref = <pointer: 0x0000027bef7e1ef0>)

aim2 的预期结果

> dput(head(resCondition_anno_padj05))
structure(list(ensembl = c("ENSMUSG00000103922", "ENSMUSG00000025907", 
"ENSMUSG00000061024", "ENSMUSG00000025911", "ENSMUSG00000025935", 
"ENSMUSG00000025937"), baseMean = c(7.45083924607695, 1035.42915800337, 
756.089939474399, 1510.50670239711, 2014.55644970672, 5206.99654662079
), log2FoldChange = c(3.31157886392159, -0.345358245876914, 0.340037961752993, 
-0.637902858828505, 0.592795289538968, 0.59912370697665), lfcSE = c(0.984296895396084, 
0.131191642000487, 0.0967702378760271, 0.120687031774959, 0.114283891072725, 
0.161639505766009), stat = c(3.36441055479404, -2.63247140298489, 
3.51386923517349, -5.28559572181691, 5.18704153292907, 3.70654255676794
), pvalue = c(0.000767073434065771, 0.00847661586751943, 0.000441630160084079, 
1.25296333033368e-07, 2.13661093734535e-07, 0.000210107944374613
), padj = c(0.00522376704325313, 0.0385092726153939, 0.00325683272694307, 
2.17721401368104e-06, 3.51690667040699e-06, 0.00168321660710376
), mgi_symbol = c("Gm6123", "Rb1cc1", "Rrs1", "Adhfe1", "Tram1", 
"Lactb2"), gene_biotype = c("processed_pseudogene", "protein_coding", 
"protein_coding", "protein_coding", "protein_coding", "protein_coding"
), FoldChange = c(9.92852128160573, 0.787112498791522, 1.26578990036559, 
0.642646438673565, 1.5081660610658, 1.51479619975327)), class = c("data.table", 
"data.frame"), row.names = c(NA, -6L), .internal.selfref = <pointer: 0x0000027bef7e1ef0>)

Answer 1

针对目标 1

library(dplyr)
resCondition_anno_dumb <- resCondition_anno # produce a similar list
resCondition_anno_dumb$log2FoldChange <- resCondition_anno$log2FoldChange*3 # make some changes

list_t   <- list(resCondition_anno, resCondition_anno_dumb) # here you enter your dataframes
# mutate adds a column to existing data sets, lapply makes it recursive
new_list <- lapply(list_t, function(x){x %>% mutate(FoldChange=2^log2FoldChange)})

对于目标 2 类似

new_list <- lapply(list_t, function(x){x %>% filter(padj<=0.05)})

或者你可以把它们放在一起：

new_list <- lapply(list_t, function(x){x %>% mutate(FoldChange=2^log2FoldChange) %>% filter (padj <=0.05)})