-
Notifications
You must be signed in to change notification settings - Fork 12
/
Copy pathnorm_counts_deseq.R
60 lines (45 loc) · 1.93 KB
/
norm_counts_deseq.R
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
# PiGx RNAseq Pipeline.
#
# Copyright © 2019 Bora Uyar <[email protected]>
#
# This file is part of the PiGx RNAseq Pipeline.
#
# This program is free software: you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation, either version 3 of the License, or
# (at your option) any later version.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with this program. If not, see <http://www.gnu.org/licenses/>.
# R script takes as input a BAM file and exports a coverage track
# in bigwig format
args <- commandArgs(trailingOnly = TRUE)
countsFile <- args[1]
colDataFile <- args[2]
outDir <- args[3]
counts <- read.table(countsFile, check.names = FALSE)
colData <- read.table(colDataFile)
common <- intersect(colnames(counts), rownames(colData))
if(length(common) < ncol(counts)) {
stop("Not all samples in the counts table can be found in the
colData table")
}
# update counts and colData to respect the order of common samples
colData <- colData[common,]
counts <- counts[,common]
dds <- DESeq2::DESeqDataSetFromMatrix(countData = counts,
colData = colData,
design = ~1)
dds <- DESeq2::estimateSizeFactors(dds)
size_factor <- DESeq2::sizeFactors(dds)
normCountsFile <- file.path(outDir, "deseq_normalized_counts.tsv")
sizeFactorsFile <- file.path(outDir, "deseq_size_factors.txt")
write.table(x = as.data.frame(size_factor), file = sizeFactorsFile,
quote = FALSE, sep = '\t')
write.table(x = DESeq2::counts(dds, normalized = TRUE), file = normCountsFile,
quote = FALSE, sep = '\t')