R 如何在不比较每个值的情况下有条件地选择每个组的最高值？

我掌握的数据如下：

  Group Gene      Score     direct_count   secondary_count 
    1   AQP11    0.5566507       4               5
    1   CLNS1A   0.2811747       0               2
    1   RSF1     0.5469924       3               6
    2   CFDP1    0.4186066       1               2
    2   CHST6    0.4295135       1               3
    3   ACE      0.634           1               1
    3   NOS2     0.6345          1               1
    4   Gene1    0.7             0               1
    4   Gene2    0.61            1               0
    4   Gene3    0.62            0               1          

我通过

组

列对基因进行分组，然后根据条件选择每组最佳基因：

如果得分最高的基因与组中所有其他基因之间的得分差异大于0.05，则选择得分最高的基因

---

如果一组中顶端基因和任何其他基因之间的得分差异，则可以使用两种不同的解决方案实现最终目标：使用

dplyr

和

数据。表

您不需要任何复杂的

ifelse

条件

解决方案 输入

dt%
分组依据（分组）%>%
过滤器（最大（分数）-分数%
切片最大值（直接计数，n=1）%>%
切片最大值（二次计数，n=1）%>%
解组（）
#>#A tibble:4 x 5
#>组基因得分直接计数二次计数
#>                        
#>1 AQP110.557 4 5
#>2 CHST6 0.430 1 3
#>3 ACE 0.634 1 1
#>4 NOS2 0.634 1 1

数据表

library(data.table)

dt <- dt[dt[, .I[(max(Score) - Score) < 0.05], by = Group]$V1]
dt <- dt[dt[, .I[direct_count == max(direct_count)], by = Group]$V1]
dt <- dt[dt[, .I[secondary_count == max(secondary_count)], by = Group]$V1]
dt
#>    Group  Gene     Score direct_count secondary_count
#> 1:     1 AQP11 0.5566507            4               5
#> 2:     2 CHST6 0.4295135            1               3
#> 3:     3   ACE 0.6340000            1               1
#> 4:     3  NOS2 0.6345000            1               1

库（data.table）
dt 2:2 CHST6 0.4295135 1 3
#>3:3 ACE 0.63400001
#>4:3 NOS2 0.6345000 1

---

你的编辑 与问题末尾的具体问题相关：这两种方法根据您编写的规则选择CHST6

dt%
分组依据（分组）%>%
过滤器（最大（分数）-分数%
切片最大值（直接计数，n=1）%>%
切片最大值（二次计数，n=1）%>%
解组（）
#>#A tible:1 x 5
#>组基因得分直接计数二次计数
#>                        
#>1 2 CHST6 0.599 1 6
##########数据表
库（数据表）
dt
df<- setDT(df)
new_df <- df[, 
   {d = dist(Score, method = 'manhattan')
   if (any(d > 0.05)) 
     ind = which.max(d)
   else if (sum(max(direct_count) == direct_count) == 1L) 
     ind = which.max(direct_count)
   else if (sum(max(secondary_count) == secondary_count) == 1L) 
     ind = which.max(secondary_count)
   else 
     ind = which((outer(direct_count, direct_count, '==') & outer(secondary_count, secondary_count, '=='))[1, ])
   
   .SD[ind]
   }
   , by = Group]


structure(list(Group = c(1L, 1L, 1L, 2L, 2L, 3L, 3L, 4L, 4L, 4L), Gene = c("AQP11", 
"CLNS1A", "RSF1", "CFDP1", "CHST6", "ACE", "NOS2", "Gene1","Gene2","Gene3"), Score = c(0.5566507, 
0.2811747, 0.5269924, 0.4186066, 0.4295135, 0.634, 0.6345, 0.7, 0.62, 0.61), direct_count = c(4L, 
0L, 3L, 1L, 1L, 1L, 1L, 0L, 1L, 0L), secondary_count = c(5L, 2L, 6L, 2L, 
3L, 1L, 1L, 0L, 0L, 1L)), row.names = c(NA, -10L), class = c("data.table", 
"data.frame"))

  Group Gene         Score      direct_count     secondary_count
1   2    CFDP1        0.5517401        1                  62
2   2    CHST6        0.5989186        1                   6
3   2    RNU6-758P    0.5644914        0                   1
4   2    Gene1        0.5672916        0                   1
5   2    TMEM170A     0.6167083        0                   2

structure(list(Group = c(2L, 2L, 2L, 2L, 2L), Gene = c("CFDP1", 
"CHST6", "RNU6-758P", "Gene1", "TMEM170A"), Score = c(0.551740109920502, 
0.598918557167053, 0.564491391181946, 0.567291617393494, 0.616708278656006
), direct_count = c(1, 1, 0, 0, 0), secondary_count = c(62, 
6, 1, 1, 2)), row.names = c(NA, -5L), class = c("data.table", 
"data.frame"))

dt <- structure(list(Group = c(1L, 1L, 1L, 2L, 2L, 3L, 3L), Gene = c("AQP11", 
                                                                           "CLNS1A", "RSF1", "CFDP1", "CHST6", "ACE", "NOS2"), Score = c(0.5566507, 
                                                                                                                                         0.2811747, 0.5269924, 0.4186066, 0.4295135, 0.634, 0.6345), direct_count = c(4L, 
                                                                                                                                                                                                                      0L, 3L, 1L, 1L, 1L, 1L), secondary_count = c(5L, 2L, 6L, 2L, 
                                                                                                                                                                                                                                                                   3L, 1L, 1L)), row.names = c(NA, -7L), class = c("data.table", 
                                                                                                                                                                                                                                                                                                                   "data.frame"))

library(dplyr)

dt %>% 
  group_by(Group) %>% 
  filter((max(Score) - Score)<0.05) %>% 
  slice_max(direct_count, n = 1) %>% 
  slice_max(secondary_count, n = 1) %>% 
  ungroup()
#> # A tibble: 4 x 5
#>   Group Gene  Score direct_count secondary_count
#>   <int> <chr> <dbl>        <int>           <int>
#> 1     1 AQP11 0.557            4               5
#> 2     2 CHST6 0.430            1               3
#> 3     3 ACE   0.634            1               1
#> 4     3 NOS2  0.634            1               1

library(data.table)

dt <- dt[dt[, .I[(max(Score) - Score) < 0.05], by = Group]$V1]
dt <- dt[dt[, .I[direct_count == max(direct_count)], by = Group]$V1]
dt <- dt[dt[, .I[secondary_count == max(secondary_count)], by = Group]$V1]
dt
#>    Group  Gene     Score direct_count secondary_count
#> 1:     1 AQP11 0.5566507            4               5
#> 2:     2 CHST6 0.4295135            1               3
#> 3:     3   ACE 0.6340000            1               1
#> 4:     3  NOS2 0.6345000            1               1