From b5c9ff2e57c26389f1b20a7d7c1db124d14a41b4 Mon Sep 17 00:00:00 2001
From: s181385 <spencer.barnes@utsouthwestern.edu>
Date: Mon, 3 Aug 2020 17:30:45 -0500
Subject: [PATCH] fix peak annotation r script
---
workflow/scripts/annotate_peaks.R | 5 +++--
1 file changed, 3 insertions(+), 2 deletions(-)
diff --git a/workflow/scripts/annotate_peaks.R b/workflow/scripts/annotate_peaks.R
index 853f7aa..40aabbf 100644
--- a/workflow/scripts/annotate_peaks.R
+++ b/workflow/scripts/annotate_peaks.R
@@ -43,13 +43,14 @@ names(files) <- design$Condition
peaks <- lapply(files, readPeakFile, as = "GRanges", header = FALSE)
peakAnnoList <- lapply(peaks, annotatePeak, TxDb=txdb, tssRegion=c(-3000, 3000), verbose=FALSE)
-column_names <- c("chr", "start", "end", "width", "strand_1", "name", "score", "strand", "signalValue",
+column_names <- c("geneId","chr", "start", "end", "width", "strand_1", "name", "score", "strand", "signalValue",
"pValue", "qValue", "peak", "annotation", "geneChr", "geneStart", "geneEnd",
- "geneLength" ,"geneStrand", "geneId", "transcriptId", "distanceToTSS", "symbol")
+ "geneLength" ,"geneStrand", "transcriptId", "distanceToTSS", "symbol")
for(index in c(1:length(peakAnnoList))) {
filename <- paste(names(peaks)[index], ".chipseeker_annotation.tsv", sep="")
df <- as.data.frame(peakAnnoList[[index]])
+ df$geneId <- sapply(strsplit(as.character(df$geneId), split = "\\."), "[[", 1)
df_final <- merge(df, sym, by.x="geneId", by.y="ensembl", all.x=T)
colnames(df_final) <- column_names
write.table(df_final[ , !(names(df_final) %in% c('strand_1'))], filename, sep="\t" ,quote=F, row.names=F)
--
GitLab