我正在寻找类似于 [bedtools subtract](https://bedtools.readthedocs.io/en/latest/content/tools/subtract.html) 的东西，但是使用数据框。
例如，假设我有一个如下的范围数据框：
```r
起始   结束  值
0    100   P

起始   结束  值
10    25   A
50    63   B

起始   结束  值
 0     9   P1
10    25   A
26    49   P2
50    63   B
64   100   P3

data_range <- data.frame(start=0, end=100, value="P")
tofill_range <- data.frame(start=c(15, 51, 70),end = c(39, 62, 79), value = c("A","B","C"))

<details>
<summary>英文:</summary>
I&#39;m looking for something similar to [bedtools subtract](https://bedtools.readthedocs.io/en/latest/content/tools/subtract.html) but with dataframes.
For example, say I have the range as a dataframe here:

And I have another dataframe, which is sorted:

Would there be a way to fill this like so:

P1, P2 and P3 labels which are filled in to pad the 2nd dataframe so that the entire range of value gets covered.
I tried using Dplyr's Lag function and adding the padding values manually, but given that the range can change depending on the length of genomic feature (including the start and end co-ordinates), I wanted this range filling to be automatic.
Thank you!
For example, this is a small subset of the data:
```R
data_range<- data.frame(start=0, end=100, value="P")
tofill_range<- data.frame(start=c(15, 51, 70),end = c(39, 62, 79), value = c("A","B","C"))

库(dplyr)
calc_range <- function(df1, df2) {
  df3 <- df2 %>% 
    transmute(开始 = 结束 + 1,
              结束 = 开始 - 1) %>% 
    rename(开始 = 开始)
  
  开始_df <- bind_rows(df1, df2, df3)
  
  开始_df %>% 
    选择(!价值) %>% 
    unlist %>% 
    sort %>% 
    矩阵(列数 = 2, 按行 = TRUE) %>% 
    数据框() %>% 
    rename(开始 = X1, 结束 = X2) %>% 
    left_join(开始_df, by = c("开始", "结束")) %>% 
    mutate(价值 = ifelse(is.na(价值) | 价值 == "P",
                          paste0("P", cumsum(is.na(价值) | 价值 == "P")),
                          价值)) %>% 
    排序(开始)
}
# 测试 1
dfa <- tribble(
  ~开始, ~结束, ~价值,
  0, 100, "P"
)
dfb <- tribble(~开始, ~结束, ~价值,
               10, 25, "A",
               50, 63, "B")
calc_range(dfa, dfb)
#>   开始 结束 价值
#> 1   0   9  P1
#> 2  10  25   A
#> 3  26  49  P2
#> 4  50  63   B
#> 5  64 100  P3
# 测试 2 
数据范围 <- 数据框(开始=0, 结束=100, 价值="P")
填充范围 <- 数据框(开始=c(15, 51, 70),
                          结束 = c(39, 62, 79),
                          价值 = c("A","B","C"))
calc_range(数据范围, 填充范围)
#>   开始 结束 价值
#> 1   0  14  P1
#> 2  15  39   A
#> 3  40  50  P2
#> 4  51  62   B
#> 5  63  69  P3
#> 6  70  79   C
#> 7  80 100  P4

library(dplyr)
ranges <- rowSums(apply(tofill_range[,1:2], 1, function(x) 
  between(seq(data_range$start, data_range$end), x[1], x[2])))

as_tibble(cbind(ranges, grp = consecutive_id(ranges), 
            val = seq(data_range[,1], data_range[,2))) %>% 
  group_by(grp) %>% 
  filter(ranges == 0) %>% 
  summarize(start = first(val), 
            end = last(val), 
            value = paste0(data_range$value, cur_group_id())) %>% 
  select(-grp) %>% 
  bind_rows(., tofill_range) %>% 
  arrange(start)
# A tibble: 7 × 3
  start   end value
  <dbl> <dbl> <chr>
1     0    14 P1   
2    15    39 A    
3    40    50 P2   
4    51    62 B    
5    63    69 P3   
6    70    79 C    
7    80   100 P4

在基本的 R 中：
``` r
all_ranges <- function(df1, df2){
  a <- sort(c(t(df1[-3]), t(df2[-3]), t(df2[-3]) + c(-1,1)))
  b <- data.frame(t(matrix(a,2)))
  d <- merge(df2, setNames(b, names(df1)[-3]), all = TRUE)
  replace(d, is.na(d), paste0(df1[,3], seq(sum(is.na(d)))))
}
data_range<- data.frame(start=0, end=100, value="P")
tofill_range<- data.frame(start=c(15, 51, 70),end = c(39, 62, 79), value = c("A","B","C"))
all_ranges(data_range, tofill_range)
#>   start end value
#> 1     0  14    P1
#> 2    15  39     A
#> 3    40  50    P2
#> 4    51  62     B
#> 5    63  69    P3
#> 6    70  79     C
#> 7    80 100    P4

<details>
<summary>英文:</summary>
In base R:
``` r
all_ranges &lt;- function(df1, df2){
a &lt;- sort(c(t(df1[-3]), t(df2[-3]), t(df2[-3]) + c(-1,1)))
b &lt;- data.frame(t(matrix(a,2)))
d &lt;- merge(df2, setNames(b, names(df1)[-3]), all = TRUE)
replace(d, is.na(d), paste0(df1[,3], seq(sum(is.na(d)))))
}
data_range&lt;- data.frame(start=0, end=100, value=&quot;P&quot;)
tofill_range&lt;- data.frame(start=c(15, 51, 70),end = c(39, 62, 79), value = c(&quot;A&quot;,&quot;B&quot;,&quot;C&quot;))
all_ranges(data_range, tofill_range)
#&gt;   start end value
#&gt; 1     0  14    P1
#&gt; 2    15  39     A
#&gt; 3    40  50    P2
#&gt; 4    51  62     B
#&gt; 5    63  69    P3
#&gt; 6    70  79     C
#&gt; 7    80 100    P4

一个非常适合这个任务的包是“IRanges”：
    library(IRanges)
    r1 = IRanges(start = 0, end = 100, names = "P")
    r2 = IRanges(start = c(10, 50), end = c(25, 63), names = c("A", "B"))
    # 找到间隙
    dif = setdiff(r1, r2)
    names(dif) = sprintf("%s%d", names(r1), seq_len(length(dif)))
    # 合并并排序
    ans = sort(c(r2, dif))
    as.data.frame(ans)
    #  start end width names
    #1     0   9    10    P1
    #2    10  25    16     A
    #3    26  49    24    P2
    #4    50  63    14     B
    #5    64 100    37    P3