在R中重新组织嵌套列表为数据框并转换数值为整数

我有一个包含字符向量（character vectors）和数值向量（numeric vectors）的长列表list_a，希望将其重新组织为数据框（data frame）格式，同时需要把这些数值转换为整数。以下是list_a前两个元素的结构示例：

list_a <- list(ENSG00000040608 = list(var = c("chr22_20230714_G_A_b38", 
"chr22_20230737_G_A_b38", "chr22_20231229_T_A_b38", "chr22_20231474_G_A_b38", 
"chr22_20231667_C_G_b38", "chr22_20231957_G_C_b38", "chr22_20231969_G_T_b38", 
"chr22_20232125_G_A_b38", "chr22_20232392_G_A_b38", "chr22_20232643_A_C_b38"
), coeff = c(0.0000953181301665087, -0.00124036704551427, 0.000808061558738542, 
0.000387528601423933, -0.000120624028990859, -0.00119982510044018, 
-0.000120623899338185, -0.000435011907222715, 0.000715410285903684, 
-0.000347899088267475)), ENSG00000040608 = list(var = c("chr22_20230714_G_A_b38", 
"chr22_20230737_G_A_b38", "chr22_20231229_T_A_b38", "chr22_20231474_G_A_b38", 
"chr22_20231667_C_G_b38", "chr22_20231957_G_C_b38", "chr22_20231969_G_T_b38", 
"chr22_20232125_G_A_b38", "chr22_20232392_G_A_b38", "chr22_20232643_A_C_b38"
), coeff = c(0.0000953181301665087, -0.00124036704551427, 0.000808061558738542, 
0.000387528601423933, -0.000120624028990859, -0.00119982510044018, 
-0.000120623899338185, -0.000435011907222715, 0.000715410285903684, 
-0.000347899088267475)))

期望输出为list_b，结构如下：

list_b <- list(ENSG00000040608 = structure(list(chr22_20230714_G_A_b38 = -0.000347899088267475, 
    chr22_20230737_G_A_b38 = 0.0000953181301665087, chr22_20231229_T_A_b38 = -0.00124036704551427, 
    chr22_20231474_G_A_b38 = 0.000808061558738542, chr22_20231667_C_G_b38 = 0.000387528601423933, 
    chr22_20231957_G_C_b38 = -0.000120624028990859, chr22_20231969_G_T_b38 = -0.00119982510044018, 
    chr22_20232125_G_A_b38 = -0.000120623899338185, chr22_20232392_G_A_b38 = -0.000435011907222715, 
    chr22_20232643_A_C_b38 = -0.000347899088267475), row.names = c(NA, 
-1L), class = c("tbl_df", "tbl", "data.frame")), ENSG00000040608 = structure(list(
    chr22_20230714_G_A_b38 = -0.000347899088267475, chr22_20230737_G_A_b38 = 0.0000953181301665087, 
    chr22_20231229_T_A_b38 = -0.00124036704551427, chr22_20231474_G_A_b38 = 0.000808061558738542, 
    chr22_20231667_C_G_b38 = 0.000387528601423933, chr22_20231957_G_C_b38 = -0.000120624028990859, 
    chr22_20231969_G_T_b38 = -0.00119982510044018, chr22_20232125_G_A_b38 = -0.000120623899338185, 
    chr22_20232392_G_A_b38 = -0.000435011907222715, chr22_20232643_A_C_b38 = -0.000347899088267475), row.names = c(NA, 
-1L), class = c("tbl_df", "tbl", "data.frame")))

关键注意点 #

原数据中的coeff是极小的小数，直接转换为整数会全部变为0，因此需要先乘以一个合适的倍数（比如1e6，即10的6次方），保留有效数字后再转整数，后续可根据需要还原。

方法一：使用purrr和tibble包（推荐） #

# 首次运行时安装所需包
install.packages(c("purrr", "tibble"))

# 加载包
library(purrr)
library(tibble)

# 处理list_a生成目标list_b
list_b <- map(list_a, function(sub_list) {
  # 将coeff乘以1e6后转为整数
  int_coeff <- as.integer(sub_list$coeff * 1e6)
  # 用var作为列名，将整数向量转为tibble（匹配期望输出的类结构）
  as_tibble(setNames(list(int_coeff), sub_list$var))
})

# 查看结果结构
str(list_b)

方法二：基础R实现（无需额外包） #

list_b <- lapply(list_a, function(sub_list) {
  # 转换整数
  int_coeff <- as.integer(sub_list$coeff * 1e6)
  # 创建命名向量并转置为数据框
  df <- as.data.frame(t(setNames(int_coeff, sub_list$var)))
  # 设置类为tbl_df、tbl、data.frame，匹配期望输出
  class(df) <- c("tbl_df", "tbl", "data.frame")
  df
})

结果说明 #

处理后的list_b中，每个元素都是tibble类型的数据框，列名为var中的字符值，对应的值为转换后的整数。如果需要调整整数精度，可修改乘以的倍数（比如1e5或1e7）。

内容的提问来源于stack exchange，提问作者Maya_Cent