-
Notifications
You must be signed in to change notification settings - Fork 0
/
fig_5B.Rmd
207 lines (169 loc) · 7.01 KB
/
fig_5B.Rmd
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
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
---
title: "Fig_5B"
author: "Max Schubert"
date: "6/18/2019"
output: html_document
editor_options:
chunk_output_type: console
---
```{r setup, include=FALSE}
knitr::opts_chunk$set(echo = TRUE)
library(data.table)
library(plyr)
library(gridExtra)
require(ggplot2)
require(data.table)
require(scales)
#library(ggpubr)
#library(plotly)
library(ggrepel)
library(R.utils)
library(RColorBrewer) #install.packages("RColorBrewer")
parent_folder = here::here('fig_5B')
source(here::here('constants.R'))
#set global variables for shifting plotting:
ori_pos = 3900000
ter_pos = 1700000
shift_over_value = 1e6
genome_size = 4641652
```
# data for enrichment of alleles,
```{r get_enriched_SNP_data}
SNP_table = "a3a4.csv"
SNP_path = paste(parent_folder, SNP_table, sep = "/")
SNP_file_dt = data.table(fread(SNP_path))
SNP_file_dt = Filter(function(x)!all(is.na(x)), SNP_file_dt) #kills columns with all NA
SNP_file_trimmed_dt = SNP_file_dt[,c( "UID", "POSITION",
"REF", "ALT",
"EXPERIMENT_SAMPLE_LABEL", "DP",
"INFO_EFF_CONTEXT","INFO_EFF_EFFECT",
"INFO_EFF_AA","INFO_EFF_GT",
"INFO_EFF_CLASS", "INFO_EFF_GENE")] #keeps only specified columns
```
#unzip coverage files
```{r unzip coverage files}
gunzip_dp <- function(x){
dp_name = paste(parent_folder, '/', 's',
as.character(x), '_depths.gz', sep = "")
#print(dp_name)
gunzip(dp_name, remove = FALSE)
}
gunzip_dp(4)
```
```{r before_coverage_data}
#note, could add more samples later
samplenum = 's4'
#depthspath <- "/Users/Max_Schubert/dropbox_hms/active_seq_reads/NovNextseq_again/FC_04398/Unaligned_1234_PF_mm1/Data/bwa_sam_bam_depths/"
path_cov <- paste(parent_folder,"/",samplenum, "_depths", sep = "")
cov <- fread(path_cov)
names(cov) <- c('chr','pos','count')
#slice into windows, label window with middle base of window
window_size <- 1000
cov[, window := cut(pos,
breaks=c(seq(0, max(pos), window_size),
max(pos)),
labels=c(seq(window_size/2, max(pos)-window_size/2, window_size),
max(pos)-window_size/2))]
#calculate average depth per window
#wcov <- cov[, window_dp_mean := mean(count), by=window]
wcov_new <- cov[, list(mean_window_count=mean(count)), by=window]
wcov_new[, window := as.numeric(window)*window_size] #change to number
#wcov_new[, position_modulus := (window+shift_over_value)%%(genome_size - shift_over_value)]
#calculate coverage depth as a factor relative to the mean depth
wcov_new[, dp_rel_mean := mean_window_count/mean(mean_window_count)]
wcov_new[, dp_rel_median := mean_window_count/median(mean_window_count)]
# plot coverage at windows
#wcov <- wcov[count > 1000]
SNP_file_trimmed_dt[, dp_rel_mean_log := log10(DP/mean(DP)), by='EXPERIMENT_SAMPLE_LABEL']
SNP_file_trimmed_dt[, dp_rel_mean_log := DP/mean(DP), by='EXPERIMENT_SAMPLE_LABEL']
```
```{r calc_relative_depth_of_snps}
#calculating SNP depth relative to maximum
SNP_file_trimmed_dt[, dp_rel_max := DP/max(DP), by='EXPERIMENT_SAMPLE_LABEL']
#average replicates into new column
SNP_file_trimmed_dt[, mean_dp_rel_max := mean(dp_rel_max), by = UID]
#calculating coverage depth relative to maximum
wcov_new[, dp_rel_max := mean_window_count/max(mean_window_count)]
```
# figure 5B
### 5B setup
```{r 5B_setup}
#calculating SNP depth relative to maximum
SNP_file_trimmed_dt[, dp_rel := DP/mean(DP), by='EXPERIMENT_SAMPLE_LABEL']
SNP_file_trimmed_dt[, dp_rel_max_mean := dp_rel/max(dp_rel), by='EXPERIMENT_SAMPLE_LABEL']
#average replicates into new column
SNP_file_trimmed_dt[, mean_dp_rel_max := mean(dp_rel_max), by = UID]
colors <- replicate_cols <- brewer.pal(n=9, name='YlGnBu')[c(5,8)]
y_offset = 0.02
genome_x = 4640000
total_x = genome_x + 170000
x_offset = 7000
genome_breaks = c(0.01E6,1E6, 2E6, 3E6, 4E6, genome_x)
genome_labels = c("", "1 Mb", "2 Mb", "3 Mb", "4 Mb","4.6 Mb / 0")
tick_dt = data.table(x_vals = genome_breaks, lab=genome_labels)
```
```{r execute_fig}
all_polar_plot <- ggplot() +
# white box containing data
annotate("rect", ymin=0, ymax=1-y_offset*2, xmin=1, xmax=total_x-1, fill='grey90', size=0.25) +
annotate("rect", ymin=1-y_offset*3, ymax=2, xmin=1, xmax=genome_x, fill=NA, color='grey50', size=0.25) +
#data for "before", offset by one to create a circle
geom_freqpoly(data = wcov_new, stat = "identity",
aes(y= dp_rel_max + 1 , x=window, color = "Library coverage, before treatment"), color='black', alpha = 0.4, size=0.25) +
#data for "after", offset by one to create a circle
geom_segment(aes(y=1, yend=1, x=1, xend=genome_x), color=colors[1], size=1, alpha=0.8) +
geom_segment(aes(y=1+y_offset, yend=1+y_offset, x=1, xend=genome_x), color=colors[2], size=1, alpha=0.8) +
geom_linerange(data = SNP_file_trimmed_dt,
aes(
x=POSITION+x_offset*(EXPERIMENT_SAMPLE_LABEL == '291_303'),
ymin=1+y_offset*(EXPERIMENT_SAMPLE_LABEL == '291_303'),
ymax = 1+dp_rel_max_mean, color=EXPERIMENT_SAMPLE_LABEL),
stat = "identity", size = 0.25) +
theme(text = element_text(size=18)) +
theme_minimal() +
labs( y = "",
x = "") +
scale_x_continuous(limits=c(0,total_x),
breaks = genome_breaks,
labels= genome_labels) +
scale_y_continuous(limits=c(0,2+y_offset),
expand=c(0,0),
breaks = c(1, 2),
labels = c('', '')) +
scale_color_manual(values=colors) +
# grey ticks and axis labels for y axis inside circle
geom_segment(data=data.table(y_vals = 1+seq(0,1,0.2), x_vals=total_x),
aes(y=y_vals, yend=y_vals, x=x_vals-25000, xend=x_vals-1), color='grey50') +
geom_text(data=data.table(y_vals = 1+seq(0,1,0.2), x_vals=total_x, lab=c(paste0(seq(0,80,20),'%'),'Max')),
aes(y=y_vals, x=x_vals-20000, label=lab), color='black', size=1.7, hjust=1.1) +
# label for genome positions
geom_text(data=tick_dt,
aes(y=0.8, x=x_vals, label=lab), color='black', size=1.7) +
geom_linerange(data=tick_dt, aes(ymin=0.88, ymax=.95, x=x_vals), color='grey50') +
theme(
#strip.background=element_blank(), strip.placement='outside',
strip.text=element_text(color='black'),
axis.title.x=element_text(margin = margin(1.2*fig_font_size,0,0,0, "pt")),
panel.border=element_blank(),
axis.text.x=element_blank(),
axis.ticks=element_blank(),
panel.grid.minor.x=element_blank(),
panel.grid.minor.y=element_blank(),
panel.grid.major.y=element_blank(),
axis.line=element_blank(), #+#+#,
legend.position = 'none') +
coord_polar()
all_polar_plot
```
```{r save_fig}
ggsave('fig_5B_out.pdf', plot=all_polar_plot, width=5, height=5.5, units='in', dpi=300, useDingbats = FALSE)
```
#optional: get rid of unzipped dp files
```{r delete_unzipped_tlen_files}
remove_dp <- function(x){
dp_name = paste(parent_folder,'/','s', as.character(x),
'_depths', sep = "")
file.remove(dp_name)
}
remove_dp(4)
```