Skip to content
Snippets Groups Projects
Commit 883e5ba2 authored by lecook's avatar lecook
Browse files

duplicate file

parent 65bae9dc
No related branches found
No related tags found
No related merge requests found
library(liftOver)
library(ChIPpeakAnno)
###################################################################################################
###################################### COMPARING PEAKS ############################################
###################################################################################################
## All peaks
system("less enhancers/dunnart_enhancer_peaks.narrowPeak | awk '{print $1,$2,$3}' > dunnart.enhancer_peaks_coord.bed",intern=TRUE)
system("less promoters/clustered/dunnart.clustered.narrowPeak | awk '{print $1,$2,$3}' > promoters/clustered/dunnart.promoter_peaks_coord.bed",intern=TRUE)
system("liftOver enhancers/dunnart.enhancer_peaks_coord.bed ../smiCra1TOmm10_patched_sorted_repFil_chainCl_preNet_chainNet_stitched.chain dunnart.enhancer_smiCraTOmm10.bed enhancer_smiCraTOmm10_unmapped.bed",intern=TRUE)
system("liftOver promoters/clustered/dunnart.promoter_peaks_coord.bed ../smiCra1TOmm10_patched_sorted_repFil_chainCl_preNet_chainNet_stitched.chain dunnart.promoter_smiCraTOmm10.bed promoter_smiCraTOmm10_unmapped.bed",intern=TRUE)
# enhancer = 437 peaks
# promoter = 48 peaks
## LiftOver peaks allowing for multiple matches
## Minimum target size is 50bp
## Minimum query size is 50bp
system("liftOver -bedPlus=3 -multiple -minChainT=100 -minChainQ=100 enhancers/dunnart_enhancer_peaks.narrowPeak ../smiCra1TOmm10_patched_sorted_repFil_chainCl_preNet_chainNet_stitched.chain enhancers/dunnart.enhancer_smiCraTOmm10.bed enhancers/enhancer_smiCraTOmm10_unmapped.bed",intern=TRUE)
## 29347
system("liftOver -bedPlus=3 -multiple -minChainT=100 -minChainQ=100 promoters/clustered/dunnart.clustered.narrowPeak ../smiCra1TOmm10_patched_sorted_repFil_chainCl_preNet_chainNet_stitched.chain promoters/clustered/dunnart.promoter_smiCraTOmm10.bed promoters/clustered/promoter_smiCraTOmm10_unmapped.bed",intern=TRUE)
## 20191
# Import output files
enh = fread("enhancers/dunnart.enhancer_smiCraTOmm10.bed")
prom = fread("promoters/clustered/dunnart.promoter_smiCraTOmm10.bed")
data = list(enh, prom)
names(data) = c("enhancers", "promoters")
data = Map(mutate, data, cre = names(data))
data = lapply(data, function(x) x[order(V4),])
data = lapply(data, function(x) x=x[,width:=V3-V2])
data = rbindlist(data,)
###################################################################################################
################################### EXTRACT PEAK SUMMITS ########################################
###################################################################################################
# make list of peaks enhancer and promoter groups
system("less enhancers/dunnart_enhancer_peaks.narrowPeak | awk -F '\t' '{print $4}' | sort > enhancers/enhancer_peak_IDs.txt", intern=TRUE)
system("less promoters/clustered/dunnart.clustered.narrowPeak | awk -F '\t' '{print $4}' | sort > promoters/clustered/promoter_peak_IDs.txt", intern=TRUE)
system("cat /data/projects/punim0586/lecook/chipseq-pipeline/dunnart/results_10M/macs2/H3K4me3_pooled_macs2_summits.bed /data/projects/punim0586/lecook/chipseq-pipeline/dunnart/results_10M/macs2/H3K27ac_pooled_macs2_summits.bed > H3K4me3_H3K27ac_combinedSummits.bed", intern=TRUE)
system("less E10.5_enhancer_peaks.narrowPeak | awk -F '\t' '{print $4}' > E10.5_enhancer_peaks_IDs.txt",intern=TRUE)
system("less E11.5_enhancer_peaks.narrowPeak | awk -F '\t' '{print $4}' > E11.5_enhancer_peaks_IDs.txt",intern=TRUE)
system("less E12.5_enhancer_peaks.narrowPeak | awk -F '\t' '{print $4}' > E12.5_enhancer_peaks_IDs.txt",intern=TRUE)
system("less E13.5_enhancer_peaks.narrowPeak | awk -F '\t' '{print $4}' > E13.5_enhancer_peaks_IDs.txt",intern=TRUE)
system("less E14.5_enhancer_peaks.narrowPeak | awk -F '\t' '{print $4}' > E14.5_enhancer_peaks_IDs.txt",intern=TRUE)
system("less E15.5_enhancer_peaks.narrowPeak | awk -F '\t' '{print $4}' > E15.5_enhancer_peaks_IDs.txt",intern=TRUE)
system("less E10.5.clustered.narrowPeak | awk -F '\t' '{print $4}' > promoters/clustered/E10.5_promoter_peaks_IDs.txt",intern=TRUE)
system("less E11.5.clustered.narrowPeak | awk -F '\t' '{print $4}' > promoters/clustered/E11.5_promoter_peaks_IDs.txt",intern=TRUE)
system("less E12.5.clustered.narrowPeak | awk -F '\t' '{print $4}' > promoters/clustered/E12.5_promoter_peaks_IDs.txt",intern=TRUE)
system("less E13.5.clustered.narrowPeak | awk -F '\t' '{print $4}' > promoters/clustered/E13.5_promoter_peaks_IDs.txt",intern=TRUE)
system("less E14.5.clustered.narrowPeak | awk -F '\t' '{print $4}' > promoters/clustered/E14.5_promoter_peaks_IDs.txt",intern=TRUE)
system("less E15.5.clustered.narrowPeak | awk -F '\t' '{print $4}' > promoters/clustered/E15.5_promoter_peaks_IDs.txt",intern=TRUE)
setwd("/data/projects/punim0586/lecook/chipseq-pipeline/mouse/results_10M/macs2")
system("cat E10.5_H3K27ac.pooled.macs2_summits.bed E10.5_H3K4me3.pooled.macs2_summits.bed > ../../../cross_species/peakAnnotation/consensus/E10.5_H3K27ac_H3K4me3.pooled.macs2_summits.bed", intern=TRUE)
system("cat E11.5_H3K27ac.pooled.macs2_summits.bed E11.5_H3K4me3.pooled.macs2_summits.bed > ../../../cross_species/peakAnnotation/consensus/E11.5_H3K27ac_H3K4me3.pooled.macs2_summits.bed", intern=TRUE)
system("cat E12.5_H3K27ac.pooled.macs2_summits.bed E12.5_H3K4me3.pooled.macs2_summits.bed > ../../../cross_species/peakAnnotation/consensus/E12.5_H3K27ac_H3K4me3.pooled.macs2_summits.bed", intern=TRUE)
system("cat E13.5_H3K27ac.pooled.macs2_summits.bed E13.5_H3K4me3.pooled.macs2_summits.bed > ../../../cross_species/peakAnnotation/consensus/E13.5_H3K27ac_H3K4me3.pooled.macs2_summits.bed", intern=TRUE)
system("cat E14.5_H3K27ac.pooled.macs2_summits.bed E14.5_H3K4me3.pooled.macs2_summits.bed > ../../../cross_species/peakAnnotation/consensus/E14.5_H3K27ac_H3K4me3.pooled.macs2_summits.bed", intern=TRUE)
system("cat E15.5_H3K27ac.pooled.macs2_summits.bed E15.5_H3K4me3.pooled.macs2_summits.bed > ../../../cross_species/peakAnnotation/consensus/E15.5_H3K27ac_H3K4me3.pooled.macs2_summits.bed", intern=TRUE)
# in R extract rows from summits file based on the list of peaks in overlap file for both enhancers and promoters
## Dunnart
summits <- read.table("H3K4me3_H3K27ac_combinedSummits.bed")
reps1 <- scan("enhancers/enhancer_peak_IDs.txt", what="", sep="\n")
reps2 <- scan("promoters/clustered/promoter_peak_IDs.txt", what="", sep="\n")
enh_summits <- subset(summits, V4 %in% reps1)
pro_summits <- subset(summits, V4 %in% reps2)
write.table(enh_summits, "dunnart.enhancer_overlap_summits.bed", quote=FALSE, col.names=FALSE, row.names=FALSE, sep="\t")
write.table(pro_summits, "dunnart.promoter_overlap_summits.bed", quote=FALSE, col.names=FALSE, row.names=FALSE, sep="\t")
## Mouse
setwd("/data/projects/punim0586/lecook/chipseq-pipeline/cross_species/peakAnnotation/consensus")
E10 <- read.table("E10.5_H3K27ac_H3K4me3.pooled.macs2_summits.bed")
E11<- read.table("E11.5_H3K27ac_H3K4me3.pooled.macs2_summits.bed")
E12<- read.table("E12.5_H3K27ac_H3K4me3.pooled.macs2_summits.bed")
E13<- read.table("E13.5_H3K27ac_H3K4me3.pooled.macs2_summits.bed")
E14<- read.table("E14.5_H3K27ac_H3K4me3.pooled.macs2_summits.bed")
E15<- read.table("E15.5_H3K27ac_H3K4me3.pooled.macs2_summits.bed")
p10 <- scan("promoters/clustered/E10.5_promoter_peaks_IDs.txt", what="", sep="\n")
p11 <- scan("promoters/clustered/E11.5_promoter_peaks_IDs.txt", what="", sep="\n")
p12 <- scan("promoters/clustered/E12.5_promoter_peaks_IDs.txt", what="", sep="\n")
p13 <- scan("promoters/clustered/E13.5_promoter_peaks_IDs.txt", what="", sep="\n")
p14 <- scan("promoters/clustered/E14.5_promoter_peaks_IDs.txt", what="", sep="\n")
p15 <- scan("promoters/clustered/E15.5_promoter_peaks_IDs.txt", what="", sep="\n")
e10 <- scan("enhancers/E10.5_enhancer_peaks_IDs.txt", what="", sep="\n")
e11 <- scan("enhancers/E11.5_enhancer_peaks_IDs.txt", what="", sep="\n")
e12 <- scan("enhancers/E12.5_enhancer_peaks_IDs.txt", what="", sep="\n")
e13 <- scan("enhancers/E13.5_enhancer_peaks_IDs.txt", what="", sep="\n")
e14 <- scan("enhancers/E14.5_enhancer_peaks_IDs.txt", what="", sep="\n")
e15 <- scan("enhancers/E15.5_enhancer_peaks_IDs.txt", what="", sep="\n")
write.table(subset(E10, V4 %in% p10), "promoters/clustered/E10_promoter_overlap_summits.bed", quote=FALSE, col.names=FALSE, row.names=FALSE, sep="\t")
write.table(subset(E11, V4 %in% p11), "promoters/clustered/E11_promoter_overlap_summits.bed", quote=FALSE, col.names=FALSE, row.names=FALSE, sep="\t")
write.table(subset(E12, V4 %in% p12), "promoters/clustered/E12_promoter_overlap_summits.bed", quote=FALSE, col.names=FALSE, row.names=FALSE, sep="\t")
write.table(subset(E13, V4 %in% p13), "promoters/clustered/E13_promoter_overlap_summits.bed", quote=FALSE, col.names=FALSE, row.names=FALSE, sep="\t")
write.table(subset(E14, V4 %in% p14), "promoters/clustered/E14_promoter_overlap_summits.bed", quote=FALSE, col.names=FALSE, row.names=FALSE, sep="\t")
write.table(subset(E15, V4 %in% p15), "promoters/clustered/E15_promoter_overlap_summits.bed", quote=FALSE, col.names=FALSE, row.names=FALSE, sep="\t")
write.table(subset(E10, V4 %in% e10), "enhancers/E10_enhancer_overlap_summits.bed", quote=FALSE, col.names=FALSE, row.names=FALSE, sep="\t")
write.table(subset(E11, V4 %in% e11), "enhancers/E11_enhancer_overlap_summits.bed", quote=FALSE, col.names=FALSE, row.names=FALSE, sep="\t")
write.table(subset(E12, V4 %in% e12), "enhancers/E12_enhancer_overlap_summits.bed", quote=FALSE, col.names=FALSE, row.names=FALSE, sep="\t")
write.table(subset(E13, V4 %in% e13), "enhancers/E13_enhancer_overlap_summits.bed", quote=FALSE, col.names=FALSE, row.names=FALSE, sep="\t")
write.table(subset(E14, V4 %in% e14), "enhancers/E14_enhancer_overlap_summits.bed", quote=FALSE, col.names=FALSE, row.names=FALSE, sep="\t")
write.table(subset(E15, V4 %in% e15), "enhancers/E15_enhancer_overlap_summits.bed", quote=FALSE, col.names=FALSE, row.names=FALSE, sep="\t")
# in bash use bedtools to extend the summits 25bp in both directions to have 50bp
system("bedtools slop -i enhancers/dunnart.enhancer_overlap_summits.bed -b 25 -g smiCra1.chrom.sizes > enhancers/enhancer_overlap_50bpsummits.bed", intern=TRUE)
system("bedtools slop -i promoters/clustered/dunnart.promoter_overlap_summits.bed -b 25 -g smiCra1.chrom.sizes > promoters/clustered/promoter_overlap_50bpsummits.bed", intern=TRUE)
system("bedtools slop -i enhancers/E10_enhancer_overlap_summits.bed -b 25 -g mm10.chrom.sizes > enhancers/E10_enhancer_overlap_50bpsummits.bed", intern=TRUE)
system("bedtools slop -i enhancers/E11_enhancer_overlap_summits.bed -b 25 -g mm10.chrom.sizes > enhancers/E11_enhancer_overlap_50bpsummits.bed", intern=TRUE)
system("bedtools slop -i enhancers/E12_enhancer_overlap_summits.bed -b 25 -g mm10.chrom.sizes > enhancers/E12_enhancer_overlap_50bpsummits.bed", intern=TRUE)
system("bedtools slop -i enhancers/E13_enhancer_overlap_summits.bed -b 25 -g mm10.chrom.sizes > enhancers/E13_enhancer_overlap_50bpsummits.bed", intern=TRUE)
system("bedtools slop -i enhancers/E14_enhancer_overlap_summits.bed -b 25 -g mm10.chrom.sizes > enhancers/E14_enhancer_overlap_50bpsummits.bed", intern=TRUE)
system("bedtools slop -i enhancers/E15_enhancer_overlap_summits.bed -b 25 -g mm10.chrom.sizes > enhancers/E15_enhancer_overlap_50bpsummits.bed", intern=TRUE)
system("bedtools slop -i promoters/clustered/E10_promoter_overlap_summits.bed -b 25 -g mm10.chrom.sizes > promoters/clustered/E10_promoter_overlap_50bpsummits.bed", intern=TRUE)
system("bedtools slop -i promoters/clustered/E11_promoter_overlap_summits.bed -b 25 -g mm10.chrom.sizes > promoters/clustered/E11_promoter_overlap_50bpsummits.bed", intern=TRUE)
system("bedtools slop -i promoters/clustered/E12_promoter_overlap_summits.bed -b 25 -g mm10.chrom.sizes > promoters/clustered/E12_promoter_overlap_50bpsummits.bed", intern=TRUE)
system("bedtools slop -i promoters/clustered/E13_promoter_overlap_summits.bed -b 25 -g mm10.chrom.sizes > promoters/clustered/E13_promoter_overlap_50bpsummits.bed", intern=TRUE)
system("bedtools slop -i promoters/clustered/E14_promoter_overlap_summits.bed -b 25 -g mm10.chrom.sizes > promoters/clustered/E14_promoter_overlap_50bpsummits.bed", intern=TRUE)
system("bedtools slop -i promoters/clustered/E15_promoter_overlap_summits.bed -b 25 -g mm10.chrom.sizes > promoters/clustered/E15_promoter_overlap_50bpsummits.bed", intern=TRUE)
###################################################################################################
################################### LIFTOVER PEAK SUMMITS ########################################
###################################################################################################
#### COMBINED PEAKS - ACTIVE IN BOTH DUNNART AND MOUSE ####
# LiftOver dunnart peaks to mouse genome
system("liftOver enhancers/enhancer_overlap_50bpsummits.bed ../smiCra1TOmm10_patched_sorted_repFil_chainCl_preNet_chainNet_stitched.chain enhancers/enhancer_summit50bp_smiCraTOmm10.bed enhancers/enhancer_summit50bp_smiCraTOmm10_unmapped.bed",intern=TRUE)
system("liftOver promoters/clustered/promoter_overlap_50bpsummits.bed ../smiCra1TOmm10_patched_sorted_repFil_chainCl_preNet_chainNet_stitched.chain promoters/clustered/promoter_summit50bp_smiCraTOmm10.bed promoters/clustered/promoter_summit50bp_smiCraTOmm10_unmapped.bed",intern=TRUE)
## Intersect dunnart CREs with mouse CREs.
system("bedtools intersect -a promoters/clustered/promoter_summit50bp_smiCraTOmm10.bed -b promoters/clustered/E10.5.clustered.narrowPeak -wo > promoters/clustered/E10.5_promoterOverlapmm10_50bpsummits.bed",intern=TRUE)
system("bedtools intersect -a promoters/clustered/promoter_summit50bp_smiCraTOmm10.bed -b promoters/clustered/E11.5.clustered.narrowPeak -wo > promoters/clustered/E11.5_promoterOverlapmm10_50bpsummits.bed",intern=TRUE)
system("bedtools intersect -a promoters/clustered/promoter_summit50bp_smiCraTOmm10.bed -b promoters/clustered/E12.5.clustered.narrowPeak -wo > promoters/clustered/E12.5_promoterOverlapmm10_50bpsummits.bed",intern=TRUE)
system("bedtools intersect -a promoters/clustered/promoter_summit50bp_smiCraTOmm10.bed -b promoters/clustered/E13.5.clustered.narrowPeak -wo > promoters/clustered/E13.5_promoterOverlapmm10_50bpsummits.bed",intern=TRUE)
system("bedtools intersect -a promoters/clustered/promoter_summit50bp_smiCraTOmm10.bed -b promoters/clustered/E14.5.clustered.narrowPeak -wo > promoters/clustered/E14.5_promoterOverlapmm10_50bpsummits.bed",intern=TRUE)
system("bedtools intersect -a promoters/clustered/promoter_summit50bp_smiCraTOmm10.bed -b promoters/clustered/E15.5.clustered.narrowPeak -wo > promoters/clustered/E15.5_promoterOverlapmm10_50bpsummits.bed",intern=TRUE)
system("bedtools intersect -a enhancer_summit50bp_smiCraTOmm10.bed -b E10.5_enhancer_peaks.narrowPeak -wo > E10.5_enhancerOverlapmm10_50bpsummits.bed",intern=TRUE)
system("bedtools intersect -a enhancer_summit50bp_smiCraTOmm10.bed -b E11.5_enhancer_peaks.narrowPeak -wo > E11.5_enhancerOverlapmm10_50bpsummits.bed",intern=TRUE)
system("bedtools intersect -a enhancer_summit50bp_smiCraTOmm10.bed -b E12.5_enhancer_peaks.narrowPeak -wo > E12.5_enhancerOverlapmm10_50bpsummits.bed",intern=TRUE)
system("bedtools intersect -a enhancer_summit50bp_smiCraTOmm10.bed -b E13.5_enhancer_peaks.narrowPeak -wo > E13.5_enhancerOverlapmm10_50bpsummits.bed",intern=TRUE)
system("bedtools intersect -a enhancer_summit50bp_smiCraTOmm10.bed -b E14.5_enhancer_peaks.narrowPeak -wo > E14.5_enhancerOverlapmm10_50bpsummits.bed",intern=TRUE)
system("bedtools intersect -a enhancer_summit50bp_smiCraTOmm10.bed -b E15.5_enhancer_peaks.narrowPeak -wo > E15.5_enhancerOverlapmm10_50bpsummits.bed",intern=TRUE)
## Lift dunnart peaks back over to the dunnart genome
system("liftOver -bedPlus=4 promoters/clustered/E10.5_promoterOverlapmm10_50bpsummits.bed ../mm10TOsmiCra1_patched_sorted_repFil_chainCl_preNet_chainNet_stitched.chain promoters/clustered/E10.5_promoterOverlapmm10_50bpsummits_backTOsmiCra.bed promoters/clustered/E10.5_promoterOverlapmm10_50bpsummits_backTOsmiCra_unmapped.bed",intern=TRUE)
system("liftOver -bedPlus=4 promoters/clustered/E11.5_promoterOverlapmm10_50bpsummits.bed ../mm10TOsmiCra1_patched_sorted_repFil_chainCl_preNet_chainNet_stitched.chain promoters/clustered/E11.5_promoterOverlapmm10_50bpsummits_backTOsmiCra.bed promoters/clustered/E11.5_promoterOverlapmm10_50bpsummits_backTOsmiCra_unmapped.bed",intern=TRUE)
system("liftOver -bedPlus=4 promoters/clustered/E12.5_promoterOverlapmm10_50bpsummits.bed ../mm10TOsmiCra1_patched_sorted_repFil_chainCl_preNet_chainNet_stitched.chain promoters/clustered/E12.5_promoterOverlapmm10_50bpsummits_backTOsmiCra.bed promoters/clustered/E12.5_promoterOverlapmm10_50bpsummits_backTOsmiCra_unmapped.bed",intern=TRUE)
system("liftOver -bedPlus=4 promoters/clustered/E13.5_promoterOverlapmm10_50bpsummits.bed ../mm10TOsmiCra1_patched_sorted_repFil_chainCl_preNet_chainNet_stitched.chain promoters/clustered/E13.5_promoterOverlapmm10_50bpsummits_backTOsmiCra.bed promoters/clustered/E13.5_promoterOverlapmm10_50bpsummits_backTOsmiCra_unmapped.bed",intern=TRUE)
system("liftOver -bedPlus=4 promoters/clustered/E14.5_promoterOverlapmm10_50bpsummits.bed ../mm10TOsmiCra1_patched_sorted_repFil_chainCl_preNet_chainNet_stitched.chain promoters/clustered/E14.5_promoterOverlapmm10_50bpsummits_backTOsmiCra.bed promoters/clustered/E14.5_promoterOverlapmm10_50bpsummits_backTOsmiCra_unmapped.bed",intern=TRUE)
system("liftOver -bedPlus=4 promoters/clustered/E15.5_promoterOverlapmm10_50bpsummits.bed ../mm10TOsmiCra1_patched_sorted_repFil_chainCl_preNet_chainNet_stitched.chain promoters/clustered/E15.5_promoterOverlapmm10_50bpsummits_backTOsmiCra.bed promoters/clustered/E15.5_promoterOverlapmm10_50bpsummits_backTOsmiCra_unmapped.bed",intern=TRUE)
system("liftOver -bedPlus=4 enhancers/E10.5_enhancerOverlapmm10_50bpsummits.bed ../mm10TOsmiCra1_patched_sorted_repFil_chainCl_preNet_chainNet_stitched.chain enhancers/E10.5_enhancerOverlapmm10_50bpsummits_backTOsmiCra.bed enhancers/E10.5_enhancerOverlapmm10_50bpsummits_backTOsmiCra_unmapped.bed",intern=TRUE)
system("liftOver -bedPlus=4 enhancers/E11.5_enhancerOverlapmm10_50bpsummits.bed ../mm10TOsmiCra1_patched_sorted_repFil_chainCl_preNet_chainNet_stitched.chain enhancers/E11.5_enhancerOverlapmm10_50bpsummits_backTOsmiCra.bed enhancers/E11.5_enhancerOverlapmm10_50bpsummits_backTOsmiCra_unmapped.bed",intern=TRUE)
system("liftOver -bedPlus=4 enhancers/E12.5_enhancerOverlapmm10_50bpsummits.bed ../mm10TOsmiCra1_patched_sorted_repFil_chainCl_preNet_chainNet_stitched.chain enhancers/E12.5_enhancerOverlapmm10_50bpsummits_backTOsmiCra.bed enhancers/E12.5_enhancerOverlapmm10_50bpsummits_backTOsmiCra_unmapped.bed",intern=TRUE)
system("liftOver -bedPlus=4 enhancers/E13.5_enhancerOverlapmm10_50bpsummits.bed ../mm10TOsmiCra1_patched_sorted_repFil_chainCl_preNet_chainNet_stitched.chain enhancers/E13.5_enhancerOverlapmm10_50bpsummits_backTOsmiCra.bed enhancers/E13.5_enhancerOverlapmm10_50bpsummits_backTOsmiCra_unmapped.bed",intern=TRUE)
system("liftOver -bedPlus=4 enhancers/E14.5_enhancerOverlapmm10_50bpsummits.bed ../mm10TOsmiCra1_patched_sorted_repFil_chainCl_preNet_chainNet_stitched.chain enhancers/E14.5_enhancerOverlapmm10_50bpsummits_backTOsmiCra.bed enhancers/E14.5_enhancerOverlapmm10_50bpsummits_backTOsmiCra_unmapped.bed",intern=TRUE)
system("liftOver -bedPlus=4 enhancers/E15.5_enhancerOverlapmm10_50bpsummits.bed ../mm10TOsmiCra1_patched_sorted_repFil_chainCl_preNet_chainNet_stitched.chain enhancers/E15.5_enhancerOverlapmm10_50bpsummits_backTOsmiCra.bed enhancers/E15.5_enhancerOverlapmm10_50bpsummits_backTOsmiCra_unmapped.bed",intern=TRUE)
awk 'x[$9]++ == 1 { print $9 " is duplicated"}' E10.5_enhancerOverlapmm10_50bpsummits_backTOsmiCra.bed
awk 'x[$9]++ == 1 { print $9 " is duplicated"}' E11.5_enhancerOverlapmm10_50bpsummits_backTOsmiCra.bed
awk 'x[$9]++ == 1 { print $9 " is duplicated"}' E12.5_enhancerOverlapmm10_50bpsummits_backTOsmiCra.bed
awk 'x[$9]++ == 1 { print $9 " is duplicated"}' E13.5_enhancerOverlapmm10_50bpsummits_backTOsmiCra.bed
awk 'x[$9]++ == 1 { print $9 " is duplicated"}' E15.5_enhancerOverlapmm10_50bpsummits_backTOsmiCra.bed
awk 'x[$9]++ == 1 { print $9 " is duplicated"}' E14.5_enhancerOverlapmm10_50bpsummits_backTOsmiCra.bed
# E11.5_H3K27ac.pooled.macs2_peak_13476 is duplicated
# scaffold00030_pilon_pilon 15206485 15206536 H3K27ac_pooled_macs2_peak_99049 13.07934 chr16 44615130 44617625 E11.5_H3K27ac.pooled.macs2_peak_13476 269 . 10.16625 26.91089 23.58920 1194 51
# scaffold00030_pilon_pilon 15207575 15207626 H3K27ac_pooled_macs2_peak_99050 28.62918 chr16 44615130 44617625 E11.5_H3K27ac.pooled.macs2_peak_13476 269 . 10.16625 26.91089 23.58920 1194 51
# E11.5_H3K27ac.pooled.macs2_peak_10317 is duplicated
# scaffold00002_pilon_pilon 130541237 130541288 H3K27ac_pooled_macs2_peak_13645 10.08028 chr14 24825909 24828470 E11.5_H3K27ac.pooled.macs2_peak_10317 372 . 12.48566 37.24145 33.69604 1973 52
# scaffold00164_pilon_pilon 1438896 1438947 H3K27ac_pooled_macs2_peak_150856 6.25556 chr14 24825909 24828470 E11.5_H3K27ac.pooled.macs2_peak_10317 372 . 12.48566 37.24145 33.69604 1973 51
# E12.5_H3K27ac.pooled.macs2_peak_25988 is duplicated
# scaffold00030_pilon_pilon 15206485 15206536 H3K27ac_pooled_macs2_peak_99049 13.07934 chr16 44615052 44618395 E12.5_H3K27ac.pooled.macs2_peak_25988 428 . 14.73608 42.88547 39.11777 1216 51
# scaffold00030_pilon_pilon 15207575 15207626 H3K27ac_pooled_macs2_peak_99050 28.62918 chr16 44615052 44618395 E12.5_H3K27ac.pooled.macs2_peak_25988 428 . 14.73608 42.88547 39.11777 1216 51
# E13.5_H3K27ac.pooled.macs2_peak_35104 is duplicated
# scaffold00030_pilon_pilon 15206485 15206536 H3K27ac_pooled_macs2_peak_99049 13.07934 chr16 44615114 44617699 E13.5_H3K27ac.pooled.macs2_peak_35104 357 . 9.00248 35.75615 32.52668 1721 51
# scaffold00030_pilon_pilon 15207575 15207626 H3K27ac_pooled_macs2_peak_99050 28.62918 chr16 44615114 44617699 E13.5_H3K27ac.pooled.macs2_peak_35104 357 . 9.00248 35.75615 32.52668 1721 51
# E13.5_H3K27ac.pooled.macs2_peak_26554 is duplicated
# scaffold00002_pilon_pilon 130541237 130541288 H3K27ac_pooled_macs2_peak_13645 10.08028 chr14 24825799 24828390 E13.5_H3K27ac.pooled.macs2_peak_26554 324 . 11.76375 32.42406 29.25455 758 52
# scaffold00164_pilon_pilon 1438896 1438947 H3K27ac_pooled_macs2_peak_150856 6.25556 chr14 24825799 24828390 E13.5_H3K27ac.pooled.macs2_peak_26554 324 . 11.76375 32.42406 29.25455 758 51
# E14.5_H3K27ac.pooled.macs2_peak_24514 is duplicated
# scaffold00030_pilon_pilon 15206485 15206536 H3K27ac_pooled_macs2_peak_99049 13.07934 chr16 44614943 44618063 E14.5_H3K27ac.pooled.macs2_peak_24514 544 . 11.99538 54.44302 51.09379 1990 51
# scaffold00030_pilon_pilon 15207575 15207626 H3K27ac_pooled_macs2_peak_99050 28.62918 chr16 44614943 44618063 E14.5_H3K27ac.pooled.macs2_peak_24514 544 . 11.99538 54.44302 51.09379 1990 51
# E14.5_H3K27ac.pooled.macs2_peak_18551 is duplicated
# scaffold00002_pilon_pilon 130541237 130541288 H3K27ac_pooled_macs2_peak_13645 10.08028 chr14 24825764 24828307 E14.5_H3K27ac.pooled.macs2_peak_18551 263 . 10.19783 26.37918 23.49332 1742 52
# scaffold00164_pilon_pilon 1438896 1438947 H3K27ac_pooled_macs2_peak_150856 6.25556 chr14 24825764 24828307 E14.5_H3K27ac.pooled.macs2_peak_18551 263 . 10.19783 26.37918 23.49332 1742 51
# E15.5_H3K27ac.pooled.macs2_peak_20587 is duplicated
# scaffold00030_pilon_pilon 15206485 15206536 H3K27ac_pooled_macs2_peak_99049 13.07934 chr16 44615161 44617589 E15.5_H3K27ac.pooled.macs2_peak_20587 254 . 10.70462 25.49718 22.21071 1155 51
# scaffold00030_pilon_pilon 15207575 15207626 H3K27ac_pooled_macs2_peak_99050 28.62918 chr16 44615161 44617589 E15.5_H3K27ac.pooled.macs2_peak_20587 254 . 10.70462 25.49718 22.21071 1155 51
awk 'x[$9]++ == 1 { print $9 " is duplicated"}' E10.5_promoterOverlapmm10_50bpsummits_backTOsmiCra.bed
awk 'x[$9]++ == 1 { print $9 " is duplicated"}' E11.5_promoterOverlapmm10_50bpsummits_backTOsmiCra.bed
awk 'x[$9]++ == 1 { print $9 " is duplicated"}' E12.5_promoterOverlapmm10_50bpsummits_backTOsmiCra.bed
awk 'x[$9]++ == 1 { print $9 " is duplicated"}' E13.5_promoterOverlapmm10_50bpsummits_backTOsmiCra.bed
awk 'x[$9]++ == 1 { print $9 " is duplicated"}' E15.5_promoterOverlapmm10_50bpsummits_backTOsmiCra.bed
awk 'x[$9]++ == 1 { print $9 " is duplicated"}' E14.5_promoterOverlapmm10_50bpsummits_backTOsmiCra.bed
# E14.5_H3K4me3.pooled.macs2_peak_8068 is duplicated
# scaffold00098_pilon_pilon 5322430 5322481 H3K4me3_pooled_macs2_peak_110310 7.99621 chr15 8443049 8445832 E14.5_H3K4me3.pooled.macs2_peak_8068 3775 . 73.91695 377.57697 372.49487 1968 51
# scaffold00200_pilon_pilon 318471 318522 H3K4me3_pooled_macs2_peak_125887 197.97865 chr15 8443049 8445832 E14.5_H3K4me3.pooled.macs2_peak_8068 3775. 73.91695 377.57697 372.49487 1968 53
#### DUNNART SPECIFIC PEAKS - ACTIVE ONLY IN THE DUNNART ####
## Intersect dunnart CREs with mouse CREs keeping those that DO NOT overlap.
system("bedtools intersect -a promoters/clustered/promoter_summit50bp_smiCraTOmm10.bed -b promoters/clustered/E10.5.clustered.narrowPeak -v > promoters/clustered/E10.5.clustered_dunnart.specific_mm10_50bpsummits.bed",intern=TRUE)
system("bedtools intersect -a promoters/clustered/promoter_summit50bp_smiCraTOmm10.bed -b promoters/clustered/E11.5.clustered.narrowPeak -v > promoters/clustered/E11.5.clustered_dunnart.specific_mm10_50bpsummits.bed",intern=TRUE)
system("bedtools intersect -a promoters/clustered/promoter_summit50bp_smiCraTOmm10.bed -b promoters/clustered/E12.5.clustered.narrowPeak -v > promoters/clustered/E12.5.clustered_dunnart.specific_mm10_50bpsummits.bed",intern=TRUE)
system("bedtools intersect -a promoters/clustered/promoter_summit50bp_smiCraTOmm10.bed -b promoters/clustered/E13.5.clustered.narrowPeak -v > promoters/clustered/E13.5.clustered_dunnart.specific_mm10_50bpsummits.bed",intern=TRUE)
system("bedtools intersect -a promoters/clustered/promoter_summit50bp_smiCraTOmm10.bed -b promoters/clustered/E14.5.clustered.narrowPeak -v > promoters/clustered/E14.5.clustered_dunnart.specific_mm10_50bpsummits.bed",intern=TRUE)
system("bedtools intersect -a promoters/clustered/promoter_summit50bp_smiCraTOmm10.bed -b promoters/clustered/E15.5.clustered.narrowPeak -v > promoters/clustered/E15.5.clustered_dunnart.specific_mm10_50bpsummits.bed",intern=TRUE)
system("bedtools intersect -a enhancers/enhancer_summit50bp_smiCraTOmm10.bed -b enhancers/E10.5_enhancer_peaks.narrowPeak -v > enhancers/E10.5_enhancer_dunnart.specific_mm10_50bpsummits.bed",intern=TRUE)
system("bedtools intersect -a enhancers/enhancer_summit50bp_smiCraTOmm10.bed -b enhancers/E11.5_enhancer_peaks.narrowPeak -v > enhancers/E11.5_enhancer_dunnart.specific_mm10_50bpsummits.bed",intern=TRUE)
system("bedtools intersect -a enhancers/enhancer_summit50bp_smiCraTOmm10.bed -b enhancers/E12.5_enhancer_peaks.narrowPeak -v > enhancers/E12.5_enhancer_dunnart.specific_mm10_50bpsummits.bed",intern=TRUE)
system("bedtools intersect -a enhancers/enhancer_summit50bp_smiCraTOmm10.bed -b enhancers/E13.5_enhancer_peaks.narrowPeak -v > enhancers/E13.5_enhancer_dunnart.specific_mm10_50bpsummits.bed",intern=TRUE)
system("bedtools intersect -a enhancers/enhancer_summit50bp_smiCraTOmm10.bed -b enhancers/E14.5_enhancer_peaks.narrowPeak -v > enhancers/E14.5_enhancer_dunnart.specific_mm10_50bpsummits.bed",intern=TRUE)
system("bedtools intersect -a enhancers/enhancer_summit50bp_smiCraTOmm10.bed -b enhancers/E15.5_enhancer_peaks.narrowPeak -v > enhancers/E15.5_enhancer_dunnart.specific_mm10_50bpsummits.bed",intern=TRUE)
## Lift dunnart-specific peaks back over to the dunnart genome
system("liftOver -bedPlus=4 promoters/clustered/E10.5.clustered_dunnart.specific_mm10_50bpsummits.bed ../mm10TOsmiCra1_patched_sorted_repFil_chainCl_preNet_chainNet_stitched.chain promoters/clustered/E10.5.clustered_dunnart.specific_mm10_50bpsummits_backTOsmiCra.bed promoters/clustered/E10.5.clustered_dunnart.specific_mm10_50bpsummits_backTOsmiCra_unmapped.bed",intern=TRUE)
system("liftOver -bedPlus=4 promoters/clustered/E11.5.clustered_dunnart.specific_mm10_50bpsummits.bed ../mm10TOsmiCra1_patched_sorted_repFil_chainCl_preNet_chainNet_stitched.chain promoters/clustered/E11.5.clustered_dunnart.specific_mm10_50bpsummits_backTOsmiCra.bed promoters/clustered/E11.5.clustered_dunnart.specific_mm10_50bpsummits_backTOsmiCra_unmapped.bed",intern=TRUE)
system("liftOver -bedPlus=4 promoters/clustered/E12.5.clustered_dunnart.specific_mm10_50bpsummits.bed ../mm10TOsmiCra1_patched_sorted_repFil_chainCl_preNet_chainNet_stitched.chain promoters/clustered/E12.5.clustered_dunnart.specific_mm10_50bpsummits_backTOsmiCra.bed promoters/clustered/E12.5.clustered_dunnart.specific_mm10_50bpsummits_backTOsmiCra_unmapped.bed",intern=TRUE)
system("liftOver -bedPlus=4 promoters/clustered/E13.5.clustered_dunnart.specific_mm10_50bpsummits.bed ../mm10TOsmiCra1_patched_sorted_repFil_chainCl_preNet_chainNet_stitched.chain promoters/clustered/E13.5.clustered_dunnart.specific_mm10_50bpsummits_backTOsmiCra.bed promoters/clustered/E13.5.clustered_dunnart.specific_mm10_50bpsummits_backTOsmiCra_unmapped.bed",intern=TRUE)
system("liftOver -bedPlus=4 promoters/clustered/E14.5.clustered_dunnart.specific_mm10_50bpsummits.bed ../mm10TOsmiCra1_patched_sorted_repFil_chainCl_preNet_chainNet_stitched.chain promoters/clustered/E14.5.clustered_dunnart.specific_mm10_50bpsummits_backTOsmiCra.bed promoters/clustered/E14.5.clustered_dunnart.specific_mm10_50bpsummits_backTOsmiCra_unmapped.bed",intern=TRUE)
system("liftOver -bedPlus=4 promoters/clustered/E15.5.clustered_dunnart.specific_mm10_50bpsummits.bed ../mm10TOsmiCra1_patched_sorted_repFil_chainCl_preNet_chainNet_stitched.chain promoters/clustered/E15.5.clustered_dunnart.specific_mm10_50bpsummits_backTOsmiCra.bed promoters/clustered/E15.5.clustered_dunnart.specific_mm10_50bpsummits_backTOsmiCra_unmapped.bed",intern=TRUE)
system("liftOver -bedPlus=4 enhancers/E10.5_enhancer_dunnart.specific_mm10_50bpsummits.bed ../mm10TOsmiCra1_patched_sorted_repFil_chainCl_preNet_chainNet_stitched.chain enhancers/E10.5_enhancer_dunnart.specific_mm10_50bpsummits_backTOsmiCra.bed enhancers/E10.5_enhancer_dunnart.specific_mm10_50bpsummits_backTOsmiCra_unmapped.bed",intern=TRUE)
system("liftOver -bedPlus=4 enhancers/E11.5_enhancer_dunnart.specific_mm10_50bpsummits.bed ../mm10TOsmiCra1_patched_sorted_repFil_chainCl_preNet_chainNet_stitched.chain enhancers/E11.5_enhancer_dunnart.specific_mm10_50bpsummits_backTOsmiCra.bed enhancers/E11.5_enhancer_dunnart.specific_mm10_50bpsummits_backTOsmiCra_unmapped.bed",intern=TRUE)
system("liftOver -bedPlus=4 enhancers/E12.5_enhancer_dunnart.specific_mm10_50bpsummits.bed ../mm10TOsmiCra1_patched_sorted_repFil_chainCl_preNet_chainNet_stitched.chain enhancers/E12.5_enhancer_dunnart.specific_mm10_50bpsummits_backTOsmiCra.bed enhancers/E12.5_enhancer_dunnart.specific_mm10_50bpsummits_backTOsmiCra_unmapped.bed",intern=TRUE)
system("liftOver -bedPlus=4 enhancers/E13.5_enhancer_dunnart.specific_mm10_50bpsummits.bed ../mm10TOsmiCra1_patched_sorted_repFil_chainCl_preNet_chainNet_stitched.chain enhancers/E13.5_enhancer_dunnart.specific_mm10_50bpsummits_backTOsmiCra.bed enhancers/E13.5_enhancer_dunnart.specific_mm10_50bpsummits_backTOsmiCra_unmapped.bed",intern=TRUE)
system("liftOver -bedPlus=4 enhancers/E14.5_enhancer_dunnart.specific_mm10_50bpsummits.bed ../mm10TOsmiCra1_patched_sorted_repFil_chainCl_preNet_chainNet_stitched.chain enhancers/E14.5_enhancer_dunnart.specific_mm10_50bpsummits_backTOsmiCra.bed enhancers/E14.5_enhancer_dunnart.specific_mm10_50bpsummits_backTOsmiCra_unmapped.bed",intern=TRUE)
system("liftOver -bedPlus=4 enhancers/E15.5_enhancer_dunnart.specific_mm10_50bpsummits.bed ../mm10TOsmiCra1_patched_sorted_repFil_chainCl_preNet_chainNet_stitched.chain enhancers/E15.5_enhancer_dunnart.specific_mm10_50bpsummits_backTOsmiCra.bed enhancers/E15.5_enhancer_dunnart.specific_mm10_50bpsummits_backTOsmiCra_unmapped.bed",intern=TRUE)
#### MOUSE SPECIFIC PEAKS - ACTIVE ONLY IN THE MOUSE ####
# LiftOver mouse peaks to dunnart genome
system("liftOver enhancers/E10_enhancer_overlap_50bpsummits.bed ../mm10TOsmiCra1_patched_sorted_repFil_chainCl_preNet_chainNet_stitched.chain enhancers/E10_enhancer_summit50bp_mm10TOsmiCra.bed enhancers/E10_enhancer_summit50bp_mm10TOsmiCra_unmapped.bed",intern=TRUE)
system("liftOver enhancers/E11_enhancer_overlap_50bpsummits.bed ../mm10TOsmiCra1_patched_sorted_repFil_chainCl_preNet_chainNet_stitched.chain enhancers/E11_enhancer_summit50bp_mm10TOsmiCra.bed enhancers/E11_enhancer_summit50bp_mm10TOsmiCra_unmapped.bed",intern=TRUE)
system("liftOver enhancers/E12_enhancer_overlap_50bpsummits.bed ../mm10TOsmiCra1_patched_sorted_repFil_chainCl_preNet_chainNet_stitched.chain enhancers/E12_enhancer_summit50bp_mm10TOsmiCra.bed enhancers/E12_enhancer_summit50bp_mm10TOsmiCra_unmapped.bed",intern=TRUE)
system("liftOver enhancers/E13_enhancer_overlap_50bpsummits.bed ../mm10TOsmiCra1_patched_sorted_repFil_chainCl_preNet_chainNet_stitched.chain enhancers/E13_enhancer_summit50bp_mm10TOsmiCra.bed enhancers/E13_enhancer_summit50bp_mm10TOsmiCra_unmapped.bed",intern=TRUE)
system("liftOver enhancers/E14_enhancer_overlap_50bpsummits.bed ../mm10TOsmiCra1_patched_sorted_repFil_chainCl_preNet_chainNet_stitched.chain enhancers/E14_enhancer_summit50bp_mm10TOsmiCra.bed enhancers/E14_enhancer_summit50bp_mm10TOsmiCra_unmapped.bed",intern=TRUE)
system("liftOver enhancers/E15_enhancer_overlap_50bpsummits.bed ../mm10TOsmiCra1_patched_sorted_repFil_chainCl_preNet_chainNet_stitched.chain enhancers/E15_enhancer_summit50bp_mm10TOsmiCra.bed enhancers/E15_enhancer_summit50bp_mm10TOsmiCra_unmapped.bed",intern=TRUE)
system("liftOver promoters/clustered/E10_promoter_overlap_50bpsummits.bed ../mm10TOsmiCra1_patched_sorted_repFil_chainCl_preNet_chainNet_stitched.chain promoters/clustered/E10_promoter_summit50bp_mm10TOsmiCra.bed promoters/clustered/E10_promoter_summit50bp_mm10TOsmiCra_unmapped.bed",intern=TRUE)
system("liftOver promoters/clustered/E11_promoter_overlap_50bpsummits.bed ../mm10TOsmiCra1_patched_sorted_repFil_chainCl_preNet_chainNet_stitched.chain promoters/clustered/E11_promoter_summit50bp_mm10TOsmiCra.bed promoters/clustered/E11_promoter_summit50bp_mm10TOsmiCra_unmapped.bed",intern=TRUE)
system("liftOver promoters/clustered/E12_promoter_overlap_50bpsummits.bed ../mm10TOsmiCra1_patched_sorted_repFil_chainCl_preNet_chainNet_stitched.chain promoters/clustered/E12_promoter_summit50bp_mm10TOsmiCra.bed promoters/clustered/E12_promoter_summit50bp_mm10TOsmiCra_unmapped.bed",intern=TRUE)
system("liftOver promoters/clustered/E13_promoter_overlap_50bpsummits.bed ../mm10TOsmiCra1_patched_sorted_repFil_chainCl_preNet_chainNet_stitched.chain promoters/clustered/E13_promoter_summit50bp_mm10TOsmiCra.bed promoters/clustered/E13_promoter_summit50bp_mm10TOsmiCra_unmapped.bed",intern=TRUE)
system("liftOver promoters/clustered/E14_promoter_overlap_50bpsummits.bed ../mm10TOsmiCra1_patched_sorted_repFil_chainCl_preNet_chainNet_stitched.chain promoters/clustered/E14_promoter_summit50bp_mm10TOsmiCra.bed promoters/clustered/E14_promoter_summit50bp_mm10TOsmiCra_unmapped.bed",intern=TRUE)
system("liftOver promoters/clustered/E15_promoter_overlap_50bpsummits.bed ../mm10TOsmiCra1_patched_sorted_repFil_chainCl_preNet_chainNet_stitched.chain promoters/clustered/E15_promoter_summit50bp_mm10TOsmiCra.bed promoters/clustered/E15_promoter_summit50bp_mm10TOsmiCra_unmapped.bed",intern=TRUE)
## Intersect dunnart CREs with mouse CREs keeping those that DO NOT overlap.
system("bedtools intersect -a promoters/clustered/E10_promoter_summit50bp_mm10TOsmiCra.bed -b promoters/clustered/dunnart.clustered.narrowPeak -v > promoters/clustered/E10.5_promoter_mouse.specific_smiCra_50bpsummits.bed",intern=TRUE)
system("bedtools intersect -a promoters/clustered/E11_promoter_summit50bp_mm10TOsmiCra.bed -b promoters/clustered/dunnart.clustered.narrowPeak -v > promoters/clustered/E11.5_promoter_mouse.specific_smiCra_50bpsummits.bed",intern=TRUE)
system("bedtools intersect -a promoters/clustered/E12_promoter_summit50bp_mm10TOsmiCra.bed -b promoters/clustered/dunnart.clustered.narrowPeak -v > promoters/clustered/E12.5_promoter_mouse.specific_smiCra_50bpsummits.bed",intern=TRUE)
system("bedtools intersect -a promoters/clustered/E13_promoter_summit50bp_mm10TOsmiCra.bed -b promoters/clustered/dunnart.clustered.narrowPeak -v > promoters/clustered/E13.5_promoter_mouse.specific_smiCra_50bpsummits.bed",intern=TRUE)
system("bedtools intersect -a promoters/clustered/E14_promoter_summit50bp_mm10TOsmiCra.bed -b promoters/clustered/dunnart.clustered.narrowPeak -v > promoters/clustered/E14.5_promoter_mouse.specific_smiCra_50bpsummits.bed",intern=TRUE)
system("bedtools intersect -a promoters/clustered/E15_promoter_summit50bp_mm10TOsmiCra.bed -b promoters/clustered/dunnart.clustered.narrowPeak -v > promoters/clustered/E15.5_promoter_mouse.specific_smiCra_50bpsummits.bed",intern=TRUE)
system("bedtools intersect -a enhancers/E10_enhancer_summit50bp_mm10TOsmiCra.bed -b enhancers/dunnart_enhancer_peaks.narrowPeak -v > enhancers/E10.5_enhancer_mouse.specific_smiCra_50bpsummits.bed",intern=TRUE)
system("bedtools intersect -a enhancers/E11_enhancer_summit50bp_mm10TOsmiCra.bed -b enhancers/dunnart_enhancer_peaks.narrowPeak -v > enhancers/E11.5_enhancer_mouse.specific_smiCra_50bpsummits.bed",intern=TRUE)
system("bedtools intersect -a enhancers/E12_enhancer_summit50bp_mm10TOsmiCra.bed -b enhancers/dunnart_enhancer_peaks.narrowPeak -v > enhancers/E12.5_enhancer_mouse.specific_smiCra_50bpsummits.bed",intern=TRUE)
system("bedtools intersect -a enhancers/E13_enhancer_summit50bp_mm10TOsmiCra.bed -b enhancers/dunnart_enhancer_peaks.narrowPeak -v > enhancers/E13.5_enhancer_mouse.specific_smiCra_50bpsummits.bed",intern=TRUE)
system("bedtools intersect -a enhancers/E14_enhancer_summit50bp_mm10TOsmiCra.bed -b enhancers/dunnart_enhancer_peaks.narrowPeak -v > enhancers/E14.5_enhancer_mouse.specific_smiCra_50bpsummits.bed",intern=TRUE)
system("bedtools intersect -a enhancers/E15_enhancer_summit50bp_mm10TOsmiCra.bed -b enhancers/dunnart_enhancer_peaks.narrowPeak -v > enhancers/E15.5_enhancer_mouse.specific_smiCra_50bpsummits.bed",intern=TRUE)
## Lift mouse-specific peaks back over to the mouse genome
system("liftOver -bedPlus=4 promoters/clustered/E10.5_promoter_mouse.specific_smiCra_50bpsummits.bed ../smiCra1TOmm10_patched_sorted_repFil_chainCl_preNet_chainNet_stitched.chain promoters/clustered/E10.5_promoter_mouse.specific_smiCra_50bpsummits_backTOmm10.bed promoters/clustered/E10.5_promoter_mouse.specific_smiCra_50bpsummits_backTOmm10_unmapped.bed",intern=TRUE)
system("liftOver -bedPlus=4 promoters/clustered/E11.5_promoter_mouse.specific_smiCra_50bpsummits.bed ../smiCra1TOmm10_patched_sorted_repFil_chainCl_preNet_chainNet_stitched.chain promoters/clustered/E11.5_promoter_mouse.specific_smiCra_50bpsummits_backTOmm10.bed promoters/clustered/E11.5_promoter_mouse.specific_smiCra_50bpsummits_backTOmm10_unmapped.bed",intern=TRUE)
system("liftOver -bedPlus=4 promoters/clustered/E12.5_promoter_mouse.specific_smiCra_50bpsummits.bed ../smiCra1TOmm10_patched_sorted_repFil_chainCl_preNet_chainNet_stitched.chain promoters/clustered/E12.5_promoter_mouse.specific_smiCra_50bpsummits_backTOmm10.bed promoters/clustered/E12.5_promoter_mouse.specific_smiCra_50bpsummits_backTOmm10_unmapped.bed",intern=TRUE)
system("liftOver -bedPlus=4 promoters/clustered/E13.5_promoter_mouse.specific_smiCra_50bpsummits.bed ../smiCra1TOmm10_patched_sorted_repFil_chainCl_preNet_chainNet_stitched.chain promoters/clustered/E13.5_promoter_mouse.specific_smiCra_50bpsummits_backTOmm10.bed promoters/clustered/E13.5_promoter_mouse.specific_smiCra_50bpsummits_backTOmm10_unmapped.bed",intern=TRUE)
system("liftOver -bedPlus=4 promoters/clustered/E14.5_promoter_mouse.specific_smiCra_50bpsummits.bed ../smiCra1TOmm10_patched_sorted_repFil_chainCl_preNet_chainNet_stitched.chain promoters/clustered/E14.5_promoter_mouse.specific_smiCra_50bpsummits_backTOmm10.bed promoters/clustered/E14.5_promoter_mouse.specific_smiCra_50bpsummits_backTOmm10_unmapped.bed",intern=TRUE)
system("liftOver -bedPlus=4 promoters/clustered/E15.5_promoter_mouse.specific_smiCra_50bpsummits.bed ../smiCra1TOmm10_patched_sorted_repFil_chainCl_preNet_chainNet_stitched.chain promoters/clustered/E15.5_promoter_mouse.specific_smiCra_50bpsummits_backTOmm10.bed promoters/clustered/E15.5_promoter_mouse.specific_smiCra_50bpsummits_backTOmm10_unmapped.bed",intern=TRUE)
system("liftOver -bedPlus=4 enhancers/E10.5_enhancer_mouse.specific_smiCra_50bpsummits.bed ../smiCra1TOmm10_patched_sorted_repFil_chainCl_preNet_chainNet_stitched.chain enhancers/E10.5_enhancer_mouse.specific_smiCra_50bpsummits_backTOmm10.bed enhancers/E10.5_enhancer_mouse.specific_smiCra_50bpsummits_backTOmm10_unmapped.bed",intern=TRUE)
system("liftOver -bedPlus=4 enhancers/E11.5_enhancer_mouse.specific_smiCra_50bpsummits.bed ../smiCra1TOmm10_patched_sorted_repFil_chainCl_preNet_chainNet_stitched.chain enhancers/E11.5_enhancer_mouse.specific_smiCra_50bpsummits_backTOmm10.bed enhancers/E11.5_enhancer_mouse.specific_smiCra_50bpsummits_backTOmm10_unmapped.bed",intern=TRUE)
system("liftOver -bedPlus=4 enhancers/E12.5_enhancer_mouse.specific_smiCra_50bpsummits.bed ../smiCra1TOmm10_patched_sorted_repFil_chainCl_preNet_chainNet_stitched.chain enhancers/E12.5_enhancer_mouse.specific_smiCra_50bpsummits_backTOmm10.bed enhancers/E12.5_enhancer_mouse.specific_smiCra_50bpsummits_backTOmm10_unmapped.bed",intern=TRUE)
system("liftOver -bedPlus=4 enhancers/E13.5_enhancer_mouse.specific_smiCra_50bpsummits.bed ../smiCra1TOmm10_patched_sorted_repFil_chainCl_preNet_chainNet_stitched.chain enhancers/E13.5_enhancer_mouse.specific_smiCra_50bpsummits_backTOmm10.bed enhancers/E13.5_enhancer_mouse.specific_smiCra_50bpsummits_backTOmm10_unmapped.bed",intern=TRUE)
system("liftOver -bedPlus=4 enhancers/E14.5_enhancer_mouse.specific_smiCra_50bpsummits.bed ../smiCra1TOmm10_patched_sorted_repFil_chainCl_preNet_chainNet_stitched.chain enhancers/E14.5_enhancer_mouse.specific_smiCra_50bpsummits_backTOmm10.bed enhancers/E14.5_enhancer_mouse.specific_smiCra_50bpsummits_backTOmm10_unmapped.bed",intern=TRUE)
system("liftOver -bedPlus=4 enhancers/E15.5_enhancer_mouse.specific_smiCra_50bpsummits.bed ../smiCra1TOmm10_patched_sorted_repFil_chainCl_preNet_chainNet_stitched.chain enhancers/E15.5_enhancer_mouse.specific_smiCra_50bpsummits_backTOmm10.bed enhancers/E15.5_enhancer_mouse.specific_smiCra_50bpsummits_backTOmm10_unmapped.bed",intern=TRUE)
## Lift dunnart-specific peaks and combined peaks back into mm10 coordinates for GREAT analysis
system("liftOver -bedPlus=4 promoters/clustered/E10.5.clustered_dunnart.specific_mm10_50bpsummits_backTOsmiCra.bed ../smiCra1TOmm10_patched_sorted_repFil_chainCl_preNet_chainNet_stitched.chain promoters/clustered/E10.5.clustered_dunnart.specific_mm10_50bpsummits_backTOsmiCra_backTOmm10.bed promoters/clustered/E10.5.clustered_dunnart.specific_mm10_50bpsummits_backTOsmiCra_backTOmm10_unmapped.bed",intern=TRUE)
system("liftOver -bedPlus=4 promoters/clustered/E11.5.clustered_dunnart.specific_mm10_50bpsummits_backTOsmiCra.bed ../smiCra1TOmm10_patched_sorted_repFil_chainCl_preNet_chainNet_stitched.chain promoters/clustered/E11.5.clustered_dunnart.specific_mm10_50bpsummits_backTOsmiCra_backTOmm10.bed promoters/clustered/E11.5.clustered_dunnart.specific_mm10_50bpsummits_backTOsmiCra_backTOmm10_unmapped.bed",intern=TRUE)
system("liftOver -bedPlus=4 promoters/clustered/E12.5.clustered_dunnart.specific_mm10_50bpsummits_backTOsmiCra.bed ../smiCra1TOmm10_patched_sorted_repFil_chainCl_preNet_chainNet_stitched.chain promoters/clustered/E12.5.clustered_dunnart.specific_mm10_50bpsummits_backTOsmiCra_backTOmm10.bed promoters/clustered/E12.5.clustered_dunnart.specific_mm10_50bpsummits_backTOsmiCra_backTOmm10_unmapped.bed",intern=TRUE)
system("liftOver -bedPlus=4 promoters/clustered/E13.5.clustered_dunnart.specific_mm10_50bpsummits_backTOsmiCra.bed ../smiCra1TOmm10_patched_sorted_repFil_chainCl_preNet_chainNet_stitched.chain promoters/clustered/E13.5.clustered_dunnart.specific_mm10_50bpsummits_backTOsmiCra_backTOmm10.bed promoters/clustered/E13.5.clustered_dunnart.specific_mm10_50bpsummits_backTOsmiCra_backTOmm10_unmapped.bed",intern=TRUE)
system("liftOver -bedPlus=4 promoters/clustered/E14.5.clustered_dunnart.specific_mm10_50bpsummits_backTOsmiCra.bed ../smiCra1TOmm10_patched_sorted_repFil_chainCl_preNet_chainNet_stitched.chain promoters/clustered/E14.5.clustered_dunnart.specific_mm10_50bpsummits_backTOsmiCra_backTOmm10.bed promoters/clustered/E14.5.clustered_dunnart.specific_mm10_50bpsummits_backTOsmiCra_backTOmm10_unmapped.bed",intern=TRUE)
system("liftOver -bedPlus=4 promoters/clustered/E15.5.clustered_dunnart.specific_mm10_50bpsummits_backTOsmiCra.bed ../smiCra1TOmm10_patched_sorted_repFil_chainCl_preNet_chainNet_stitched.chain promoters/clustered/E15.5.clustered_dunnart.specific_mm10_50bpsummits_backTOsmiCra_backTOmm10.bed promoters/clustered/E15.5.clustered_dunnart.specific_mm10_50bpsummits_backTOsmiCra_backTOmm10_unmapped.bed",intern=TRUE)
system("liftOver -bedPlus=4 enhancers/E10.5_enhancer_dunnart.specific_mm10_50bpsummits_backTOsmiCra.bed ../smiCra1TOmm10_patched_sorted_repFil_chainCl_preNet_chainNet_stitched.chain enhancers/E10.5_enhancer_dunnart.specific_mm10_50bpsummits_backTOsmiCra_backTOmm10.bed enhancers/E10.5_enhancer_dunnart.specific_mm10_50bpsummits_backTOsmiCra_backTOmm10_unmapped.bed",intern=TRUE)
system("liftOver -bedPlus=4 enhancers/E11.5_enhancer_dunnart.specific_mm10_50bpsummits_backTOsmiCra.bed ../smiCra1TOmm10_patched_sorted_repFil_chainCl_preNet_chainNet_stitched.chain enhancers/E11.5_enhancer_dunnart.specific_mm10_50bpsummits_backTOsmiCra_backTOmm10.bed enhancers/E11.5_enhancer_dunnart.specific_mm10_50bpsummits_backTOsmiCra_backTOmm10_unmapped.bed",intern=TRUE)
system("liftOver -bedPlus=4 enhancers/E12.5_enhancer_dunnart.specific_mm10_50bpsummits_backTOsmiCra.bed ../smiCra1TOmm10_patched_sorted_repFil_chainCl_preNet_chainNet_stitched.chain enhancers/E12.5_enhancer_dunnart.specific_mm10_50bpsummits_backTOsmiCra_backTOmm10.bed enhancers/E12.5_enhancer_dunnart.specific_mm10_50bpsummits_backTOsmiCra_backTOmm10_unmapped.bed",intern=TRUE)
system("liftOver -bedPlus=4 enhancers/E13.5_enhancer_dunnart.specific_mm10_50bpsummits_backTOsmiCra.bed ../smiCra1TOmm10_patched_sorted_repFil_chainCl_preNet_chainNet_stitched.chain enhancers/E13.5_enhancer_dunnart.specific_mm10_50bpsummits_backTOsmiCra_backTOmm10.bed enhancers/E13.5_enhancer_dunnart.specific_mm10_50bpsummits_backTOsmiCra_backTOmm10_unmapped.bed",intern=TRUE)
system("liftOver -bedPlus=4 enhancers/E14.5_enhancer_dunnart.specific_mm10_50bpsummits_backTOsmiCra.bed ../smiCra1TOmm10_patched_sorted_repFil_chainCl_preNet_chainNet_stitched.chain enhancers/E14.5_enhancer_dunnart.specific_mm10_50bpsummits_backTOsmiCra_backTOmm10.bed enhancers/E14.5_enhancer_dunnart.specific_mm10_50bpsummits_backTOsmiCra_backTOmm10_unmapped.bed",intern=TRUE)
system("liftOver -bedPlus=4 enhancers/E15.5_enhancer_dunnart.specific_mm10_50bpsummits_backTOsmiCra.bed ../smiCra1TOmm10_patched_sorted_repFil_chainCl_preNet_chainNet_stitched.chain enhancers/E15.5_enhancer_dunnart.specific_mm10_50bpsummits_backTOsmiCra_backTOmm10.bed enhancers/E15.5_enhancer_dunnart.specific_mm10_50bpsummits_backTOsmiCra_backTOmm10_unmapped.bed",intern=TRUE)
## Combined peaks
system("liftOver -bedPlus=4 promoters/clustered/E10.5_promoterOverlapmm10_50bpsummits_backTOsmiCra.bed ../smiCra1TOmm10_patched_sorted_repFil_chainCl_preNet_chainNet_stitched.chain promoters/clustered/E10.5_promoterOverlapmm10_50bpsummits_backTOsmiCra_backTOmm10.bed promoters/clustered/E10.5_promoterOverlapmm10_50bpsummits_backTOsmiCra_backTOmm10_unmapped.bed",intern=TRUE)
system("liftOver -bedPlus=4 promoters/clustered/E11.5_promoterOverlapmm10_50bpsummits_backTOsmiCra.bed ../smiCra1TOmm10_patched_sorted_repFil_chainCl_preNet_chainNet_stitched.chain promoters/clustered/E11.5_promoterOverlapmm10_50bpsummits_backTOsmiCra_backTOmm10.bed promoters/clustered/E11.5_promoterOverlapmm10_50bpsummits_backTOsmiCra_backTOmm10_unmapped.bed",intern=TRUE)
system("liftOver -bedPlus=4 promoters/clustered/E12.5_promoterOverlapmm10_50bpsummits_backTOsmiCra.bed ../smiCra1TOmm10_patched_sorted_repFil_chainCl_preNet_chainNet_stitched.chain promoters/clustered/E12.5_promoterOverlapmm10_50bpsummits_backTOsmiCra_backTOmm10.bed promoters/clustered/E12.5_promoterOverlapmm10_50bpsummits_backTOsmiCra_backTOmm10_unmapped.bed",intern=TRUE)
system("liftOver -bedPlus=4 promoters/clustered/E13.5_promoterOverlapmm10_50bpsummits_backTOsmiCra.bed ../smiCra1TOmm10_patched_sorted_repFil_chainCl_preNet_chainNet_stitched.chain promoters/clustered/E13.5_promoterOverlapmm10_50bpsummits_backTOsmiCra_backTOmm10.bed promoters/clustered/E13.5_promoterOverlapmm10_50bpsummits_backTOsmiCra_backTOmm10_unmapped.bed",intern=TRUE)
system("liftOver -bedPlus=4 promoters/clustered/E14.5_promoterOverlapmm10_50bpsummits_backTOsmiCra.bed ../smiCra1TOmm10_patched_sorted_repFil_chainCl_preNet_chainNet_stitched.chain promoters/clustered/E14.5_promoterOverlapmm10_50bpsummits_backTOsmiCra_backTOmm10.bed promoters/clustered/E14.5_promoterOverlapmm10_50bpsummits_backTOsmiCra_backTOmm10_unmapped.bed",intern=TRUE)
system("liftOver -bedPlus=4 promoters/clustered/E15.5_promoterOverlapmm10_50bpsummits_backTOsmiCra.bed ../smiCra1TOmm10_patched_sorted_repFil_chainCl_preNet_chainNet_stitched.chain promoters/clustered/E15.5_promoterOverlapmm10_50bpsummits_backTOsmiCra_backTOmm10.bed promoters/clustered/E15.5_promoterOverlapmm10_50bpsummits_backTOsmiCra_backTOmm10_unmapped.bed",intern=TRUE)
system("liftOver -bedPlus=4 enhancers/E10.5_enhancerOverlapmm10_50bpsummits_backTOsmiCra.bed ../smiCra1TOmm10_patched_sorted_repFil_chainCl_preNet_chainNet_stitched.chain enhancers/E10.5_enhancerOverlapmm10_50bpsummits_backTOsmiCra_backTOmm10.bed enhancers/E10.5_enhancerOverlapmm10_50bpsummits_backTOsmiCra_backTOmm10_unmapped.bed",intern=TRUE)
system("liftOver -bedPlus=4 enhancers/E11.5_enhancerOverlapmm10_50bpsummits_backTOsmiCra.bed ../smiCra1TOmm10_patched_sorted_repFil_chainCl_preNet_chainNet_stitched.chain enhancers/E11.5_enhancerOverlapmm10_50bpsummits_backTOsmiCra_backTOmm10.bed enhancers/E11.5_enhancerOverlapmm10_50bpsummits_backTOsmiCra_backTOmm10_unmapped.bed",intern=TRUE)
system("liftOver -bedPlus=4 enhancers/E12.5_enhancerOverlapmm10_50bpsummits_backTOsmiCra.bed ../smiCra1TOmm10_patched_sorted_repFil_chainCl_preNet_chainNet_stitched.chain enhancers/E12.5_enhancerOverlapmm10_50bpsummits_backTOsmiCra_backTOmm10.bed enhancers/E12.5_enhancerOverlapmm10_50bpsummits_backTOsmiCra_backTOmm10_unmapped.bed",intern=TRUE)
system("liftOver -bedPlus=4 enhancers/E13.5_enhancerOverlapmm10_50bpsummits_backTOsmiCra.bed ../smiCra1TOmm10_patched_sorted_repFil_chainCl_preNet_chainNet_stitched.chain enhancers/E13.5_enhancerOverlapmm10_50bpsummits_backTOsmiCra_backTOmm10.bed enhancers/E13.5_enhancerOverlapmm10_50bpsummits_backTOsmiCra_backTOmm10_unmapped.bed",intern=TRUE)
system("liftOver -bedPlus=4 enhancers/E14.5_enhancerOverlapmm10_50bpsummits_backTOsmiCra.bed ../smiCra1TOmm10_patched_sorted_repFil_chainCl_preNet_chainNet_stitched.chain enhancers/E14.5_enhancerOverlapmm10_50bpsummits_backTOsmiCra_backTOmm10.bed enhancers/E14.5_enhancerOverlapmm10_50bpsummits_backTOsmiCra_backTOmm10_unmapped.bed",intern=TRUE)
system("liftOver -bedPlus=4 enhancers/E15.5_enhancerOverlapmm10_50bpsummits_backTOsmiCra.bed ../smiCra1TOmm10_patched_sorted_repFil_chainCl_preNet_chainNet_stitched.chain enhancers/E15.5_enhancerOverlapmm10_50bpsummits_backTOsmiCra_backTOmm10.bed enhancers/E15.5_enhancerOverlapmm10_50bpsummits_backTOsmiCra_backTOmm10_unmapped.bed",intern=TRUE)
###################################################################################################
################################### INTERSECT IDS FROM OVERLAPS ###################################
###################################################################################################
###################################################################################################
############################### GENE ONTOLOGY & PATHWAY ANALYSIS ##################################
###################################################################################################
## Using mouse coordinates for the peaks, use GREAT to look for the nearest gene TSS
## Then use clusterProfiler to look at Gene Ontology enrichment in the mouse, dunnart and combined peak sets
library(rGREAT)
library(clusterProfiler)
library(data.table)
great <- function(bedList){
bedFiles = list.files(bedList, pattern= ".bed", full.names=T) # create list of files in directory
bedFiles = as.list(bedFiles)
data = lapply(bedFiles, function(x) fread(x, header=TRUE, sep="\t", quote = "") %>% as.data.table()) # read in all files
data = lapply(data, function(x) submitGreatJob(x, species = "mm10")) # submit GREAT jobs
names(data) = c("E10:mouse", "E10:combined", "E10:dunnart", "E11:mouse", "E11:combined", "E11:dunnart",
"E12:mouse", "E12:combined", "E12:dunnart", "E13:mouse", "E13:combined", "E13:dunnart",
"E14:mouse", "E14:combined", "E14:dunnart", "E15:mouse", "E15:combined", "E15:dunnart")
data = Map(mutate, data, group = names(data)) ## add column with group names
databind = rbindlist(data,) #bind dataframes together
split_by_stage = databind[
,c("stage", "species") := tstrsplit(group, ":", fixed=TRUE)
][
,'group':=NULL
]
}
## For each mouse stage have a list of peak IDs
# ## Scan IDs into an object
# setwd("/data/projects/punim0586/lecook/chipseq-pipeline/cross_species/peakAnnotation/consensus/enhancers")
# E10 <- scan("E10.5_enhancerOverlapmm10_50bpsummitsIDs.txt", what="", sep="\n")
# E11 <- scan("E11.5_enhancerOverlapmm10_50bpsummitsIDs.txt", what="", sep="\n")
# E12 <- scan("E12.5_enhancerOverlapmm10_50bpsummitsIDs.txt", what="", sep="\n")
# E13 <- scan("E13.5_enhancerOverlapmm10_50bpsummitsIDs.txt", what="", sep="\n")
# E14 <- scan("E14.5_enhancerOverlapmm10_50bpsummitsIDs.txt", what="", sep="\n")
# E15 <- scan("E15.5_enhancerOverlapmm10_50bpsummitsIDs.txt", what="", sep="\n")
# ## Look for dunnart peak IDs that overlap with mouse embryonic stages in the mouse peaks that overlap with the dunnart peaks at P0
# # E10.5_enhancerOverlapsmiCra_50bpsummits.bed file:
# # chr8 121436317 121436374 H3K27ac_pooled_macs2_peak_644 9.64793 chr8 121436230 121436873 E10.5_H3K27ac.pooled.macs2_peak_77013 75 . 4.66414 7.52876 5.17964 305 57
# write.table(subset(read.table("E10.5_enhancerOverlapsmiCra_50bpsummits.bed", sep="\t", quote="", header=FALSE), unique(E10) %in% V4), file = "E10.5_enhancerOverlapmm10_smiCra1_50bpsummits.bed", quote=FALSE, col.names=FALSE, row.names=FALSE, sep="\t")
# write.table(subset(read.table("E11.5_enhancerOverlapsmiCra_50bpsummits.bed", sep="\t", quote="", header=FALSE), unique(E11) %in% V4), file = "E11.5_enhancerOverlapmm10_smiCra1_50bpsummits.bed", quote=FALSE, col.names=FALSE, row.names=FALSE, sep="\t")
# write.table(subset(read.table("E12.5_enhancerOverlapsmiCra_50bpsummits.bed", sep="\t", quote="", header=FALSE), unique(E12) %in% V4), file = "E12.5_enhancerOverlapmm10_smiCra1_50bpsummits.bed", quote=FALSE, col.names=FALSE, row.names=FALSE, sep="\t")
# write.table(subset(read.table("E13.5_enhancerOverlapsmiCra_50bpsummits.bed", sep="\t", quote="", header=FALSE), unique(E13) %in% V4), file = "E13.5_enhancerOverlapmm10_smiCra1_50bpsummits.bed", quote=FALSE, col.names=FALSE, row.names=FALSE, sep="\t")
# write.table(subset(read.table("E14.5_enhancerOverlapsmiCra_50bpsummits.bed", sep="\t", quote="", header=FALSE), unique(E14) %in% V4), file = "E14.5_enhancerOverlapmm10_smiCra1_50bpsummits.bed", quote=FALSE, col.names=FALSE, row.names=FALSE, sep="\t")
# write.table(subset(read.table("E15.5_enhancerOverlapsmiCra_50bpsummits.bed", sep="\t", quote="", header=FALSE), unique(E15) %in% V4), file = "E15.5_enhancerOverlapmm10_smiCra1_50bpsummits.bed", quote=FALSE, col.names=FALSE, row.names=FALSE, sep="\t")
# ## Mouse CREs with dunnart coordinates that aren't active in dunnart at P0
# ## Do I use only those that are reproducible (eg. found in both lists)or even those that I overlapped from mouse to dunnart but not in the finally overlap??
# write.table(subset(read.table("E10.5_enhancerOverlapsmiCra_50bpsummits.bed", sep="\t", quote="", header=FALSE), !(E10 %in% V4)), file = "E10.5_enhancerNoOverlapmm10_50bpsummits.bed", quote=FALSE, col.names=FALSE, row.names=FALSE, sep="\t")
# write.table(subset(read.table("E11.5_enhancerOverlapsmiCra_50bpsummits.bed", sep="\t", quote="", header=FALSE), !(E10 %in% V4)), file = "E11.5_enhancerNoOverlapmm10_50bpsummits.bed", quote=FALSE, col.names=FALSE, row.names=FALSE, sep="\t")
# write.table(subset(read.table("E12.5_enhancerOverlapsmiCra_50bpsummits.bed", sep="\t", quote="", header=FALSE), !(E10 %in% V4), file = "E12.5_enhancerNoOverlapmm10_50bpsummits.bed", quote=FALSE, col.names=FALSE, row.names=FALSE, sep="\t")
# write.table(subset(read.table("E13.5_enhancerOverlapsmiCra_50bpsummits.bed", sep="\t", quote="", header=FALSE), !(E10 %in% V4)), file = "E13.5_enhancerNoOverlapmm10_50bpsummits.bed", quote=FALSE, col.names=FALSE, row.names=FALSE, sep="\t")
# write.table(subset(read.table("E14.5_enhancerOverlapsmiCra_50bpsummits.bed", sep="\t", quote="", header=FALSE), !(E10 %in% V4)), file = "E14.5_enhancerNoOverlapmm10_50bpsummits.bed", quote=FALSE, col.names=FALSE, row.names=FALSE, sep="\t")
# write.table(subset(read.table("E15.5_enhancerOverlapsmiCra_50bpsummits.bed", sep="\t", quote="", header=FALSE), !(E10 %in% V4)), file = "E15.5_enhancerNoOverlapmm10_50bpsummits.bed", quote=FALSE, col.names=FALSE, row.names=FALSE, sep="\t")
# ## Not in list dunnart CREs
# write.table(subset(read.table("E10.5_enhancerOverlapsmiCra_50bpsummits.bed", sep="\t", quote="", header=FALSE), !(E10 %in% V4)), file = "E10.5_enhancerNoOverlasmiCra1_50bpsummits.bed", quote=FALSE, col.names=FALSE, row.names=FALSE, sep="\t")
# write.table(subset(read.table("E11.5_enhancerOverlapsmiCra_50bpsummits.bed", sep="\t", quote="", header=FALSE), !(V4 %in% E11)), file = "E11.5_enhancerNoOverlapmm10_50bpsummits.bed", quote=FALSE, col.names=FALSE, row.names=FALSE, sep="\t")
# write.table(subset(read.table("E12.5_enhancerOverlapsmiCra_50bpsummits.bed", sep="\t", quote="", header=FALSE), !(V4 %in% E12), file = "E12.5_enhancerNoOverlapmm10_50bpsummits.bed", quote=FALSE, col.names=FALSE, row.names=FALSE, sep="\t")
# write.table(subset(read.table("E13.5_enhancerOverlapsmiCra_50bpsummits.bed", sep="\t", quote="", header=FALSE), !(V4 %in% E13)), file = "E13.5_enhancerNoOverlapmm10_50bpsummits.bed", quote=FALSE, col.names=FALSE, row.names=FALSE, sep="\t")
# write.table(subset(read.table("E14.5_enhancerOverlapsmiCra_50bpsummits.bed", sep="\t", quote="", header=FALSE), !(V4 %in% E14)), file = "E14.5_enhancerNoOverlapmm10_50bpsummits.bed", quote=FALSE, col.names=FALSE, row.names=FALSE, sep="\t")
# write.table(subset(read.table("E15.5_enhancerOverlapsmiCra_50bpsummits.bed", sep="\t", quote="", header=FALSE), !(V4 %in% E15)), file = "E15.5_enhancerNoOverlapmm10_50bpsummits.bed", quote=FALSE, col.names=FALSE, row.names=FALSE, sep="\t")
# ## Promoters
# setwd("/data/projects/punim0586/lecook/chipseq-pipeline/cross_species/peakAnnotation/overlaps/promoters/clustered/")
# E10 <- scan("E10.5_promoterOverlapmm10_50bpsummitsIDs.txt", what="", sep="\n")
# E11 <- scan("E11.5_promoterOverlapmm10_50bpsummitsIDs.txt", what="", sep="\n")
# E12 <- scan("E12.5_promoterOverlapmm10_50bpsummitsIDs.txt", what="", sep="\n")
# E13 <- scan("E13.5_promoterOverlapmm10_50bpsummitsIDs.txt", what="", sep="\n")
# E14 <- scan("E14.5_promoterOverlapmm10_50bpsummitsIDs.txt", what="", sep="\n")
# E15 <- scan("E15.5_promoterOverlapmm10_50bpsummitsIDs.txt", what="", sep="\n")
# ## Look for dunnart peak IDs that overlap with mouse embryonic stages in the mouse peaks that overlap with the dunnart peaks at P0
# write.table(subset(read.table("E10.5_promoterOverlapsmiCra_50bpsummits.bed", sep="\t", quote="", header=FALSE), unique(E10) %in% V4), file = "E10.5_promoterOverlapmm10_smiCra1_50bpsummits.bed", quote=FALSE, col.names=FALSE, row.names=FALSE, sep="\t")
# write.table(subset(read.table("E11.5_promoterOverlapsmiCra_50bpsummits.bed", sep="\t", quote="", header=FALSE), unique(E11) %in% V4), file = "E11.5_promoterOverlapmm10_smiCra1_50bpsummits.bed", quote=FALSE, col.names=FALSE, row.names=FALSE, sep="\t")
# write.table(subset(read.table("E12.5_promoterOverlapsmiCra_50bpsummits.bed", sep="\t", quote="", header=FALSE), unique(E12) %in% V4), file = "E12.5_promoterOverlapmm10_smiCra1_50bpsummits.bed", quote=FALSE, col.names=FALSE, row.names=FALSE, sep="\t")
# write.table(subset(read.table("E13.5_promoterOverlapsmiCra_50bpsummits.bed", sep="\t", quote="", header=FALSE), unique(E13) %in% V4), file = "E13.5_promoterOverlapmm10_smiCra1_50bpsummits.bed", quote=FALSE, col.names=FALSE, row.names=FALSE, sep="\t")
# write.table(subset(read.table("E14.5_promoterOverlapsmiCra_50bpsummits.bed", sep="\t", quote="", header=FALSE), unique(E14) %in% V4), file = "E14.5_promoterOverlapmm10_smiCra1_50bpsummits.bed", quote=FALSE, col.names=FALSE, row.names=FALSE, sep="\t")
# write.table(subset(read.table("E15.5_promoterOverlapsmiCra_50bpsummits.bed", sep="\t", quote="", header=FALSE), unique(E15) %in% V4), file = "E15.5_promoterOverlapmm10_smiCra1_50bpsummits.bed", quote=FALSE, col.names=FALSE, row.names=FALSE, sep="\t")
# ## Check duplicates
# awk 'x[$4]++ == 1 { print $4 " is duplicated"}' E10.5_enhancerOverlapmm10_50bpsummits.bed
# awk 'x[$4]++ == 1 { print $4 " is duplicated"}' E11.5_enhancerOverlapmm10_50bpsummits.bed
# awk 'x[$4]++ == 1 { print $4 " is duplicated"}' E12.5_enhancerOverlapmm10_50bpsummits.bed
# awk 'x[$4]++ == 1 { print $4 " is duplicated"}' E13.5_enhancerOverlapmm10_50bpsummits.bed
# awk 'x[$4]++ == 1 { print $4 " is duplicated"}' E15.5_enhancerOverlapmm10_50bpsummits.bed
# awk 'x[$4]++ == 1 { print $4 " is duplicated"}' E14.5_enhancerOverlapmm10_50bpsummits.bed
# awk 'x[$9]++ == 1 { print $9 " is duplicated"}' E10.5_enhancerOverlapmm10_50bpsummits_backTOsmiCra.bed
\ No newline at end of file
0% Loading or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment