R data frame manipulation - r

Question

Suppose I have a data frame that looks like this.
# start end motif
# 2 6 a
# 10 15 b
# 30 35 c
How would I create a data frame that fills in the remaining start and end locations like so up to a certain number Max_end:
Max_end <- 33
# start end motif
# 0 2 na # <- 0-2 are filled in because it is not in the original data frame
# 2 6 a # <- 2-6 are in the original
# 6 10 na # <- 6-10 is not
# 10 15 b # <- 10-15 is
# 15 30 na # and so on
# 30 33 c
And further, calculates the distance between the start and end locations and creates a one column data frame.
# Length motif
# 2 na
# 4 a
# 4 na
# 5 b
# 15 na
# 3 c
Currently this is how i am doing it: It is very inefficient
library(data.table)
library(stringi)
f <- fread('ABC.txt',header=F,skip=1)$V1
f <- paste(f, collapse = "")
motifs = c('GATC', 'CTGCAG', 'ACCACC', 'CC(A|T)GG', 'CCAC.{8}TGA(C|T)')
v <- na.omit(data.frame(do.call(rbind, lapply(stri_locate_all_regex(f, motifs), unlist))))
v <- v[order(v[,1]),]
v2difference <- "blah"
for(i in 2:nrow(v)){
if(v[i,1] > v[i-1,2]+2){v2difference[i] <- v[i,1]-v[i-1,2]-2}
}
v2difference[1] <- v[1,1]
v2 <- data.frame(Order=seq(1, 2*nrow(v), 2),Lengths=matrix(v2difference, ncol = 1),Motifs="na")
v1 <- data.frame(Order=seq(2, 2*nrow(v), 2),Lengths=(v$end-v$start+1),Motifs=na.omit(unlist(stri_extract_all_regex(f,motifs))))
V <- data.frame(Track=1,rbind(v1,v2))
V <- V[order(V$Order),]
B <- V[,!(names(V) %in% "Order")]

Answer 1

Max_end <- 33
breaks <- c(0, t(as.matrix(dat[,1:2])), Max_end) # get endpoints
breaks <- breaks[breaks <= Max_end]
merge(dat, data.frame(start=breaks[-length(breaks)], end=breaks[-1]), all=T)
# start end motif
# 1 0 2 <NA>
# 2 2 6 a
# 3 6 10 <NA>
# 4 10 15 b
# 5 15 30 <NA>
# 6 30 33 <NA>
# 7 30 35 c
To specify a start and endpoint, you could do
Max_end <- 33
Max_start <- 10
breaks <- unique(c(Max_start, t(as.matrix(dat[,1:2])), Max_end))
breaks <- breaks[breaks <= Max_end & breaks >= Max_start]
merge(dat, data.frame(start=breaks[-length(breaks)], end=breaks[-1]), all.y=T)
# start end motif
# 1 10 15 b
# 2 15 30 <NA>
# 3 30 33 <NA>
Note: this doesn't include "c" in the shortened final interval, you would need to decide if that values gets included or not when the interval changes.