Skip to content

GitLab

Commit b5c9ff2e authored by Spencer Barnes's avatar Spencer Barnes
Browse files

fix peak annotation r script

parent 27540804
Pipeline #7784 passed with stages
in 1052 minutes and 56 seconds
Hide whitespace changes
Inline Side-by-side
Showing with 3 additions and 2 deletions
workflow/scripts/annotate_peaks.R
View file @ b5c9ff2e
...@@ -43,13 +43,14 @@ names(files) <- design$Condition ...@@ -43,13 +43,14 @@ names(files) <- design$Condition
peaks <- lapply(files, readPeakFile, as = "GRanges", header = FALSE) peaks <- lapply(files, readPeakFile, as = "GRanges", header = FALSE)
peakAnnoList <- lapply(peaks, annotatePeak, TxDb=txdb, tssRegion=c(-3000, 3000), verbose=FALSE) peakAnnoList <- lapply(peaks, annotatePeak, TxDb=txdb, tssRegion=c(-3000, 3000), verbose=FALSE)
column_names <- c("chr", "start", "end", "width", "strand_1", "name", "score", "strand", "signalValue", column_names <- c("geneId","chr", "start", "end", "width", "strand_1", "name", "score", "strand", "signalValue",
"pValue", "qValue", "peak", "annotation", "geneChr", "geneStart", "geneEnd", "pValue", "qValue", "peak", "annotation", "geneChr", "geneStart", "geneEnd",
"geneLength" ,"geneStrand", "geneId", "transcriptId", "distanceToTSS", "symbol") "geneLength" ,"geneStrand", "transcriptId", "distanceToTSS", "symbol")
for(index in c(1:length(peakAnnoList))) { for(index in c(1:length(peakAnnoList))) {
filename <- paste(names(peaks)[index], ".chipseeker_annotation.tsv", sep="") filename <- paste(names(peaks)[index], ".chipseeker_annotation.tsv", sep="")
df <- as.data.frame(peakAnnoList[[index]]) df <- as.data.frame(peakAnnoList[[index]])
df$geneId <- sapply(strsplit(as.character(df$geneId), split = "\\."), "[[", 1)
df_final <- merge(df, sym, by.x="geneId", by.y="ensembl", all.x=T) df_final <- merge(df, sym, by.x="geneId", by.y="ensembl", all.x=T)
colnames(df_final) <- column_names colnames(df_final) <- column_names
write.table(df_final[ , !(names(df_final) %in% c('strand_1'))], filename, sep="\t" ,quote=F, row.names=F) write.table(df_final[ , !(names(df_final) %in% c('strand_1'))], filename, sep="\t" ,quote=F, row.names=F)
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment