Question

我有一个数据框，有两列，一列用于基因符号，另一列用于功能途径。途径列具有重复值，因为存在许多属于每个途径的基因。我想重新排序这个数据集，以便每个列都是一个单独的路径，这些列中的每一行都是属于该路径的基因。

启动数据帧：

data.frame(pathway = c("p1", "p1", "p1", "p1", "p2", "p2", "p2"), 
gene.symbol = c("G1", "G2", "G3", "G4", "G33", "G43", "G10"))

所需数据框：

data.frame(p1 = c("G1", "G2", "G3", "G4"), p2 = c("G33", "G43", "G10", 
""))

我知道并非所有列都具有相同的长度，并且具有空白值优于NA。

Answer 1

这可能看起来有点复杂，但它通过首先转到列表而不是返回data.frame来实现所需的输出：

df$gene.symbol <- as.character(df$gene.symbol)

pw_list <- list()
for (pw in unique(df$pathway)) {
  pw_list[[pw]] <- df[df$pathway == pw, "gene.symbol"]
}
pw_list
$p1
[1] "G1" "G2" "G3" "G4"

$p2
[1] "G33" "G43" "G10"


reordered <- matrix("", nrow = max(sapply(pw_list, length)), ncol = length(pw_list))
colnames(reordered) <- names(pw_list)

for (pw in names(pw_list)){
  n <- length(pw_list[[pw]])
  reordered[1:n, pw] <- pw_list[[pw]]
}
reordered <- as.data.frame(reordered)
reordered
  p1  p2
1 G1 G33
2 G2 G43
3 G3 G10
4 G4

修改

稍微简洁的版本：

df$gene.symbol <- as.character(df$gene.symbol) pw_list <- list() for (pw in unique(df$pathway)) { pw_list[[pw]] <- df[df$pathway == pw, "gene.symbol"] } reordered <- as.data.frame(sapply(pw_list, "[", i = 1:max(sapply(pw_list, length))), stringsAsFactors = FALSE) reordered[is.na(reordered)] <- "" names(reordered) <- names(pw_list)

Answer 2

这是另一种选择。

使用path作为拆分元素拆分为列表
获取每个组的最大长度，并将所有其他组设置为相同的长度
将其转回数据框

这是代码。

mydf <- data.frame(pathway = c("p1", "p1", "p1", "p1", "p2", "p2", "p2"), 
           gene.symbol = c("G1", "G2", "G3", "G4", "G33", "G43", "G10"))

# function to run over each element in list
set_to_max_length <- function(x) {
  length(x) <- max.length
  return(x)
}

# 1. split into  list
mydf.split <- split(mydf$gene.symbol, mydf$pathway)

# 2.a get max length of all columns
max.length <- max(sapply(mydf.split, length))

# 2.b set each list element to max length
mydf.split.2 <- lapply(mydf.split, set_to_max_length)

# 3. combine back into df
data.frame(mydf.split.2)

修改

这是使用tidyverse的另一种选择 - 更简洁：

library(tidyverse) mydf <- data.frame(pathway = c("p1", "p1", "p1", "p1", "p2", "p2", "p2"), gene.symbol = c("G1", "G2", "G3", "G4", "G33", "G43", "G10")) mydf %>% group_by(pathway) %>% mutate(rownum = row_number()) %>% ungroup() %>% spread(pathway, gene.symbol) %>% select(-1)

使用重复

2 个答案: