Created
May 10, 2024 12:12
-
-
Save mikelove/cbbc84634b6854c865cb5eb08ad9b245 to your computer and use it in GitHub Desktop.
Example of producing simple segmentation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
library(plyranges) | |
library(nullranges) | |
x <- data.frame( | |
seqnames=rep(c("1","2","3"), each=10), | |
start=rep(c(0:4, 10:14) * 1000 + 1, times=3), | |
width=100) |> | |
as_granges() | |
seqlengths(x) <- c("1"=20123, "2"=20123, "3"=20123) | |
isCircular(x) <- rep(FALSE,3) | |
genome(x) <- "abcd" | |
seqinfo(x) | |
# for real genomic data, tiles on the order of 1 Mb, and larger than block size | |
tiles <- tileGenome(seqlengths(x), tilewidth=5000, cut.last.tile.in.chrom=TRUE) | |
tiles <- tiles %>% | |
mutate(num_olaps = count_overlaps(., x)) | |
cut <- exp(mean(log(tiles$num_olaps+1))) | |
library(dplyr) | |
seg <- tiles |> | |
mutate(state = case_when( | |
num_olaps > cut ~ 1, | |
num_olaps <= cut ~ 2)) | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment