逐列减去数据帧的行，保留多因子列

2 回答

• 2

  在IIUC中， df_1 和 df_2 中有相同名称的列（例如 int_samp_X 表示某个整数 X ），并且您希望获得匹配列名称的差异，按 gene_nm 分组（例如 df_1[df_1$gene_nm == 'A', int_samp_1] - df_2[df_2$gene_nm == 'A', int_samp_1] ） .

  我们可以使用 tidyverse 系列包来解决这个问题，特别是 dplyr 和 purrr .

  首先，将 df_1 和 df_2 与 left_join 合并，以确保_865874中的所有多个条目在与 df_2 中的基因级条目匹配时保留：

  library(tidyverse)
  
  df_3 <- df_1 %>% left_join(df_2, by = "gene_nm")
  
  df_3
                 pep_seq int_samp_1.x int_samp_2.x int_samp_3.x gene_nm int_samp_1.y int_samp_2.y int_samp_3.y
  1            aaaaaaaaa      2421432           NA        11351       A      2421432           NA        11351
  2           ababababba     24242424      5342353           NA       A      2421432           NA        11351
  3           dfsfsfsfds           NA     14532556           NA       A      2421432           NA        11351
  4          xbbcbcncncc   4684757849        43566           NA       A      2421432           NA        11351
  5          fbbdsgffhhh           NA     46367367   1354151345       A      2421432           NA        11351
  6      dggdgdgegeggerr     10485040    768769769   1351351354       A      2421432           NA        11351
  7           dfgthrgfgf           NA       797899       314534       B     24242424      5342353           NA
  8            wegregegg      6849400           NA         1535       B     24242424      5342353           NA
  9        egegegergewge        40300           NA      3145354       B     24242424      5342353           NA
  10         sfngegebser           NA           NA      4353455       C           NA     14532556           NA
  11          qegqeefbew           NA       686899       324535       C           NA     14532556           NA
  12          qegqetegqt           NA      7898979      3543445       C           NA     14532556           NA
  13            qwtqtewr    556456466       678568        34535       C           NA     14532556           NA
  14           etghsfrgf   4646456466           NA     34535534       C           NA     14532556           NA
  15 sfsdfbdfbergeagaegr    246464266        68886           NA       C           NA     14532556           NA
  16    wasfqertsdfaefwe   4564242646          488           NA       C           NA     14532556           NA
  

  然后在感兴趣的列名称上 map ，从每个列对中获取差异 . （请注意，您需要先将 int_samp 列从 factor 转换为 numeric . ）

  Update （根据OP评论）：要在计算差异之前将 NA 转换为 0 ，我们可以使用 mutate_if() 和 replace() ，将以下内容添加到方法链中：

  mutate_if(is.numeric,  funs(replace(., is.na(.), 0)))
  

  最后， join 回到 df_1 ：

  var_names <- df_1 %>% select(starts_with("int_samp")) %>% names()
  
  var_names # [1] "int_samp_1" "int_samp_2" "int_samp_3"
  
  var_names %>%
    map_dfc(~df_3 %>%
              mutate_at(vars(matches(.x)), funs(as.numeric(as.character(.)))) %>%
              mutate_if(is.numeric,  funs(replace(., is.na(.), 0))) %>%
              select(matches(.x)) %>%
              reduce(`-`)) %>%
    set_names(paste0(var_names, "_diff")) %>%
    bind_cols(df_1)
  

  输出：

  int_samp_1_diff int_samp_2_diff int_samp_3_diff pep_seq             int_samp_1 int_samp_2 int_samp_3 gene_nm
               <dbl>           <dbl>           <dbl> <fct>               <fct>      <fct>      <fct>      <fct>  
   1              0.              0.              0. aaaaaaaaa           2421432    NA         11351      A      
   2       21820992.        5342353.         -11351. ababababba          24242424   5342353    NA         A      
   3       -2421432.       14532556.         -11351. dfsfsfsfds          NA         14532556   NA         A      
   4     4682336417.          43566.         -11351. xbbcbcncncc         4684757849 43566      NA         A      
   5       -2421432.       46367367.     1354139994. fbbdsgffhhh         NA         46367367   1354151345 A      
   6        8063608.      768769769.     1351340003. dggdgdgegeggerr     10485040   768769769  1351351354 A      
   7      -24242424.       -4544454.         314534. dfgthrgfgf          NA         797899     314534     B      
   8      -17393024.       -5342353.           1535. wegregegg           6849400    NA         1535       B      
   9      -24202124.       -5342353.        3145354. egegegergewge       40300      NA         3145354    B      
  10              0.      -14532556.        4353455. sfngegebser         NA         NA         4353455    C      
  11              0.      -13845657.         324535. qegqeefbew          NA         686899     324535     C      
  12              0.       -6633577.        3543445. qegqetegqt          NA         7898979    3543445    C      
  13      556456466.      -13853988.          34535. qwtqtewr            556456466  678568     34535      C      
  14     4646456466.      -14532556.       34535534. etghsfrgf           4646456466 NA         34535534   C      
  15      246464266.      -14463670.              0. sfsdfbdfbergeagaegr 246464266  68886      NA         C      
  16     4564242646.      -14532068.              0. wasfqertsdfaefwe    4564242646 488        NA         C
  

  注意：这个答案主要来自akrun的答案here .

  回复于 2024-05-02T19:47:16+08:00
• 2

  一个选项可以是使用 dplyr 连接 df_1 和 df_2 然后执行简单的矩阵减法 .

  Note: 数据框得到强度读数因子 . 当你期望进行减法时，我认为保持测量因素并不是一个好主意 . 因此我把它们转换成 integer .

  library(dplyr)
  
  # The NA values from df_2 has been changed to 0 since keeping those NA, will
  # turn values in df_A NA for no reason. 
  mod <- df_1 %>% left_join(df_2, by= c("gene_nm" = "gene_nm.a")) %>% # join on gene
    mutate_at(vars(starts_with("int_samp")), funs(as.integer(as.character(.)))) %>%
    mutate_at(vars(ends_with("a")), funs(ifelse(is.na(.),0L,.))) #Values are converted
  
  # The modified data.frame got columns from both df_1 and df_2
  mod[,grepl("^int_samp_\\d+$", names(mod))] <- 
                  mod[,grepl("^int_samp_\\d+$", names(mod))] -  
                  mod[,grepl("^int_samp_\\d+[a-z]+$", names(mod))]
  
  # Take columns from df_1. 
  mod[names(df_1)]
  #                pep_seq int_samp_1 int_samp_2 int_samp_3 gene_nm
  # 1            aaaaaaaaa          0         NA          0       A
  # 2           ababababba   21820992    5342353         NA       A
  # 3           dfsfsfsfds         NA   14532556         NA       A
  # 4          xbbcbcncncc         NA      43566         NA       A
  # 5          fbbdsgffhhh         NA   46367367 1354139994       A
  # 6      dggdgdgegeggerr    8063608  768769769 1351340003       A
  # 7           dfgthrgfgf         NA   -4544454     314534       B
  # 8            wegregegg  -17393024         NA       1535       B
  # 9        egegegergewge  -24202124         NA    3145354       B
  # 10         sfngegebser         NA         NA    4353455       C
  # 11          qegqeefbew         NA  -13845657     324535       C
  # 12          qegqetegqt         NA   -6633577    3543445       C
  # 13            qwtqtewr  556456466  -13853988      34535       C
  # 14           etghsfrgf         NA         NA   34535534       C
  # 15 sfsdfbdfbergeagaegr  246464266  -14463670         NA       C
  # 16    wasfqertsdfaefwe         NA  -14532068         NA       C
  

  回复于 2024-05-02T19:47:16+08:00