Mercurial > repos > davidvanzessen > mutation_analysis
comparison aa_histogram.r @ 0:8a5a2abbb870 draft default tip
Uploaded
author | davidvanzessen |
---|---|
date | Mon, 29 Aug 2016 05:36:10 -0400 |
parents | |
children |
comparison
equal
deleted
inserted
replaced
-1:000000000000 | 0:8a5a2abbb870 |
---|---|
1 library(ggplot2) | |
2 | |
3 args <- commandArgs(trailingOnly = TRUE) | |
4 | |
5 mutations.by.id.file = args[1] | |
6 absent.aa.by.id.file = args[2] | |
7 genes = strsplit(args[3], ",")[[1]] | |
8 genes = c(genes, "") | |
9 outdir = args[4] | |
10 | |
11 | |
12 print("---------------- read input ----------------") | |
13 | |
14 mutations.by.id = read.table(mutations.by.id.file, sep="\t", fill=T, header=T, quote="") | |
15 absent.aa.by.id = read.table(absent.aa.by.id.file, sep="\t", fill=T, header=T, quote="") | |
16 | |
17 for(gene in genes){ | |
18 | |
19 if(gene == ""){ | |
20 mutations.by.id.gene = mutations.by.id[!grepl("unmatched", mutations.by.id$best_match),] | |
21 absent.aa.by.id.gene = absent.aa.by.id[!grepl("unmatched", absent.aa.by.id$best_match),] | |
22 } else { | |
23 mutations.by.id.gene = mutations.by.id[grepl(paste("^", gene, sep=""), mutations.by.id$best_match),] | |
24 absent.aa.by.id.gene = absent.aa.by.id[grepl(paste("^", gene, sep=""), absent.aa.by.id$best_match),] | |
25 } | |
26 print(paste("nrow", gene, nrow(absent.aa.by.id.gene))) | |
27 if(nrow(mutations.by.id.gene) == 0){ | |
28 next | |
29 } | |
30 | |
31 mutations.at.position = colSums(mutations.by.id.gene[,-c(1,2)]) | |
32 aa.at.position = colSums(absent.aa.by.id.gene[,-c(1,2,3,4)]) | |
33 | |
34 dat_freq = mutations.at.position / aa.at.position | |
35 dat_freq[is.na(dat_freq)] = 0 | |
36 dat_dt = data.frame(i=1:length(dat_freq), freq=dat_freq) | |
37 | |
38 print("---------------- plot ----------------") | |
39 | |
40 m = ggplot(dat_dt, aes(x=i, y=freq)) + theme(axis.text.x = element_text(angle = 90, hjust = 1)) | |
41 m = m + geom_bar(stat="identity", colour = "black", fill = "darkgrey", alpha=0.8) + scale_x_continuous(breaks=dat_dt$i, labels=dat_dt$i) | |
42 m = m + annotate("segment", x = 0.5, y = -0.05, xend=26.5, yend=-0.05, colour="darkgreen", size=1) + annotate("text", x = 13, y = -0.1, label="FR1") | |
43 m = m + annotate("segment", x = 26.5, y = -0.07, xend=38.5, yend=-0.07, colour="darkblue", size=1) + annotate("text", x = 32.5, y = -0.15, label="CDR1") | |
44 m = m + annotate("segment", x = 38.5, y = -0.05, xend=55.5, yend=-0.05, colour="darkgreen", size=1) + annotate("text", x = 47, y = -0.1, label="FR2") | |
45 m = m + annotate("segment", x = 55.5, y = -0.07, xend=65.5, yend=-0.07, colour="darkblue", size=1) + annotate("text", x = 60.5, y = -0.15, label="CDR2") | |
46 m = m + annotate("segment", x = 65.5, y = -0.05, xend=104.5, yend=-0.05, colour="darkgreen", size=1) + annotate("text", x = 85, y = -0.1, label="FR3") | |
47 m = m + expand_limits(y=c(-0.1,1)) + xlab("AA position") + ylab("Frequency") + ggtitle(paste(gene, "AA mutation frequency")) | |
48 | |
49 print("---------------- write/print ----------------") | |
50 | |
51 png(filename=paste(outdir, "/aa_histogram_", gene, ".png", sep=""), width=1280, height=720) | |
52 print(m) | |
53 dev.off() | |
54 | |
55 dat.sums = data.frame(index=1:length(mutations.at.position), mutations.at.position=mutations.at.position, aa.at.position=aa.at.position) | |
56 | |
57 write.table(dat.sums, paste(outdir, "/aa_histogram_sum_", gene, ".txt", sep=""), sep="\t",quote=F,row.names=F,col.names=T) | |
58 write.table(mutations.by.id.gene, paste(outdir, "/aa_histogram_count_", gene, ".txt", sep=""), sep="\t",quote=F,row.names=F,col.names=T) | |
59 write.table(absent.aa.by.id.gene, paste(outdir, "/aa_histogram_absent_", gene, ".txt", sep=""), sep="\t",quote=F,row.names=F,col.names=T) | |
60 write.table(dat_dt, paste(outdir, "/aa_histogram_", gene, ".txt", sep=""), sep="\t",quote=F,row.names=F,col.names=T) | |
61 } |