基于两列值的计算筛选数据表的优雅方法是什么？[R]

我有一个数据表，我们叫它

lung

：

> lung
                     variant_id             transcript_id is_NL counts nrows
     1: chr10_129450960_T_C_b38 chr10_129467297_129536240     0  33029   458
     2: chr10_129450960_T_C_b38 chr10_129467297_129536240     1   3477    54
     3: chr10_129450960_T_C_b38 chr10_129467297_129536240     2    130     3
     4: chr10_129450960_T_C_b38 chr10_129536378_129563778     0     51   458
     5: chr10_129450960_T_C_b38 chr10_129536378_129563778     1      8    54
    ---
500148:   chr9_34699703_G_C_b38    chr9_34649082_34649409     1   4214    57
500149:   chr9_34699703_G_C_b38    chr9_34649082_34649409     2    171     2
500150:   chr9_34699703_G_C_b38    chr9_34649565_34650368     0  48713   456
500151:   chr9_34699703_G_C_b38    chr9_34649565_34650368     1   4932    57
500152:   chr9_34699703_G_C_b38    chr9_34649565_34650368     2    208     2

我想过滤它，当

is_NL==0

时，只保留

计数/nrows<50

的行（

50

为任意数），当

is_NL

为

1

或

2

时，只保留

计数/nrows>50

的行

到目前为止，我只能得出以下结论：

> lung[which(lung[is_NL == 0][,counts]/lung[is_NL == 0][,nrows] < 50),]
                     variant_id             transcript_id is_NL counts nrows
     1: chr10_129450960_T_C_b38 chr10_129467297_129536240     1   3477    54
     2: chr10_129450960_T_C_b38 chr10_129536378_129563778     0     51   458
     3: chr10_129450960_T_C_b38 chr10_129536378_129563778     1      8    54
     4: chr10_129450960_T_C_b38 chr10_129536378_129707894     0  37918   458
     5: chr10_129450960_T_C_b38 chr10_129701913_129707894     0    188   458
    ---
147877:  chr17_45825156_G_A_b38   chr17_46148240_46152903     2     17    20
147878:  chr17_45825156_G_A_b38   chr17_46152967_46156773     0      3   336
147879:  chr17_45825156_G_A_b38   chr17_46152967_46169530     0      5   336
147880:  chr17_45825156_G_A_b38   chr17_46152967_46169530     1    137   159
147881:  chr17_45825156_G_A_b38   chr17_46156896_46170854     0     18   336
> lung[which(lung[is_NL > 0]$counts/lung[is_NL > 0]$nrows > 50),]
                    variant_id             transcript_id is_NL counts nrows
    1: chr10_129450960_T_C_b38 chr10_129467297_129536240     0  33029   458
    2: chr10_129450960_T_C_b38 chr10_129536378_129563778     1      8    54
    3: chr10_129450960_T_C_b38 chr10_129701913_129707894     1     24    54
    4: chr10_129450960_T_C_b38 chr10_129701913_129707894     2      2     3
    5: chr10_129450960_T_C_b38 chr10_129708044_129715519     2      0     3
   ---
50195:  chr17_46025930_T_C_b38   chr17_46039885_46050532     0  14129   337
50196:  chr17_46025930_T_C_b38   chr17_46050705_46066536     0  14106   337
50197:  chr17_46025930_T_C_b38   chr17_46050705_46066536     1   6658   158
50198:  chr17_46025930_T_C_b38   chr17_46050705_46066536     2    809    20
50199:  chr17_46025930_T_C_b38   chr17_46066733_46067548     0  12842   337

>lung[which（lung[is_NL==0][，counts]/lung[is_NL==0][，nrows]<50]，]
变体id转录本id为nrows计数
1:chr10_129450960_T_C_b38 chr10_129467297_129536240 1347754
2:chr10_129450960_T_C_b38 chr10_129536378_129563778 0 51 458
3:chr10_129450960_T_C_b38 chr10_129536378_129563778 1 8 54
4:chr10_129450960_T_C_b38 chr10_129536378_129707894 0 37918 458
5:chr10_129450960_T_C_b38 chr10_129701913_129707894 0 188 458
---
147877:chr17\U 45825156\U G\U A\U b38 chr17\U 46148240\U 46152903 2 17 20
147878:chr17_45825156_G_A_b38 chr17_46152967_46156773 0336
147879:chr17_45825156_G_A_b38 chr17_46152967_461695300 5 336
147880:chr17_45825156_G_A_b38 chr17_46152967_46169530 1 137 159
147881:chr17_45825156_G_A_b38 chr17_46156896_46170854 0 18 336
>肺[其中（肺[为0]$counts/肺[为0]$nrows>50），]
变体id转录本id为nrows计数
1:chr10_129450960_T_C_b38 chr10_129467297_129536240 0 33029458
2:chr10_129450960_T_C_b38 chr10_129536378_129563778 1 8 54
3:chr10_129450960_T_C_b38 chr10_129701913_129707894 1 24 54
4:chr10_129450960_T_C_b38 chr10_129701913_129707894 2 3
5:chr10_129450960_T_C_b38 chr10_129708044_129715519 2 0 3
---
50195:chr17_46025930_T_C_b38 chr17_46039885_46050532 0 14129 337
50196:chr17_46025930_T_C_b38 chr17_46050705_46066536 0 14106 337
50197:chr17_46025930_T_C_b38 chr17_46050705_46066536 1 6658 158
50198:chr17_46025930_T_C_b38 chr17_46050705_46066536 2 809 20
50199:chr17_46025930_T_C_b38 chr17_46066733_46067548 0 12842 337

---

通过查看

is\NL

列可以看出，这不起作用。我可能会先将它们子集到两个不同的表中，应用比较过滤器（

50

），然后找出如何合并它们，但我觉得应该有一种更简单的方法来实现这一点，我不知道。

我会使用

tidyverse

创建一个标志：

lung %>% 
mutate(FLG = if_else(is_NL == 0 & counts/nrows < 50, 1 
             if_else(is_NL in (1,2) &counts/nrows >50, 1,0))) %>% 
filter(FLG == 1)

lung%>%
变异（FLG=if=else（is=0&counts/nrows<50，1
如果其他（在（1,2）&计数/nrows>50,1,0））%>%
过滤器（FLG==1）

如果你想用base R，那么

lung[which((is_NL == 0 & counts/nrows < 50)|(is_NL in (1,2) &counts/nrows >50)),]

lung[which（（is_NL==0&counts/nrows<50）|（is_NL in（1,2）&counts/nrows>50）），]

我将使用

tidyverse

创建一个标志：

lung %>% 
mutate(FLG = if_else(is_NL == 0 & counts/nrows < 50, 1 
             if_else(is_NL in (1,2) &counts/nrows >50, 1,0))) %>% 
filter(FLG == 1)

lung%>%
变异（FLG=if=else（is=0&counts/nrows<50，1
如果其他（在（1,2）&计数/nrows>50,1,0））%>%
过滤器（FLG==1）

如果你想用base R，那么

lung[which((is_NL == 0 & counts/nrows < 50)|(is_NL in (1,2) &counts/nrows >50)),]

lung[which（（is_NL==0&counts/nrows<50）|（is_NL in（1,2）&counts/nrows>50）），]

在base R中，您可以执行以下操作：

lung[with(lung, (is_NL == 0 & counts/nrows < 50) | 
                (is_NL %in% c(1,2) & counts/nrows > 50)),]
# output
               variant_id             transcript_id is_NL counts nrows
2 chr10_129450960_T_C_b38 chr10_129467297_129536240     1   3477    54
4 chr10_129450960_T_C_b38 chr10_129536378_129563778     0     51   458

---

在base R中，您可以执行以下操作：

lung[with(lung, (is_NL == 0 & counts/nrows < 50) | 
                (is_NL %in% c(1,2) & counts/nrows > 50)),]
# output
               variant_id             transcript_id is_NL counts nrows
2 chr10_129450960_T_C_b38 chr10_129467297_129536240     1   3477    54
4 chr10_129450960_T_C_b38 chr10_129536378_129563778     0     51   458

---

使用

数据表

library(data.table)
setDT(lung)[!is_NL & counts/.N < 50|(is_NL %in% c(1, 2) & counts/.N > 50)]

库（data.table）
setDT（lung）[！is_NL&counts/.N<50（is_NL%在%c（1,2）&counts/.N>50）]

使用

数据表

library(data.table)
setDT(lung)[!is_NL & counts/.N < 50|(is_NL %in% c(1, 2) & counts/.N > 50)]

库（data.table）
setDT（lung）[！is_NL&counts/.N<50（is_NL%在%c（1,2）&counts/.N>50）]