|
11
|
1 ---
|
|
|
2 title: 'Sequence Duplication Levels'
|
|
|
3 output:
|
|
|
4 html_document:
|
|
|
5 number_sections: true
|
|
|
6 toc: true
|
|
|
7 theme: cosmo
|
|
|
8 highlight: tango
|
|
|
9 ---
|
|
|
10
|
|
|
11 ```{r setup, include=FALSE, warning=FALSE, message=FALSE}
|
|
|
12 knitr::opts_chunk$set(
|
|
|
13 echo = ECHO,
|
|
|
14 error = TRUE
|
|
|
15 )
|
|
|
16 ```
|
|
|
17
|
|
|
18 ### Sequence Duplication Levels
|
|
|
19
|
|
|
20 ```{r 'Sequence Duplication Levels', fig.width=10}
|
|
|
21 ## reads 1
|
|
|
22 sdl_1 = extract_data_module('REPORT_DIR/reads_1_fastqc_data.txt', 'Sequence Duplication Levels', header = FALSE, comment.char = '#')
|
|
|
23 names(sdl_1) = c('Duplication_Level', 'Percentage_of_deduplicated', 'Percentage_of_total')
|
|
|
24 sdl_1$id = 1:length(sdl_1$Duplication_Level)
|
|
|
25
|
|
|
26 melt_sdl_1 = melt(sdl_1, id=c('Duplication_Level', 'id'))
|
|
|
27 melt_sdl_1$trim = 'before'
|
|
|
28
|
|
|
29
|
|
|
30 ## reads 2
|
|
|
31 sdl_2 = extract_data_module('REPORT_DIR/reads_2_fastqc_data.txt', 'Sequence Duplication Levels', header = FALSE, comment.char = '#')
|
|
|
32 names(sdl_2) = c('Duplication_Level', 'Percentage_of_deduplicated', 'Percentage_of_total')
|
|
|
33 sdl_2$id = 1:length(sdl_2$Duplication_Level)
|
|
|
34
|
|
|
35 melt_sdl_2 = melt(sdl_2, id=c('Duplication_Level', 'id'))
|
|
|
36 melt_sdl_2$trim = 'after'
|
|
|
37
|
|
|
38 comb_sdl = rbind(melt_sdl_1, melt_sdl_2)
|
|
|
39 comb_sdl$trim = factor(levels = c('before', 'after'), comb_sdl$trim)
|
|
|
40
|
|
|
41 p = ggplot(data = comb_sdl, aes(x = id, y = value, color = variable)) +
|
|
|
42 geom_line() +
|
|
|
43 scale_x_continuous(breaks = sdl_2$id, labels = sdl_2$Duplication_Level) +
|
|
|
44 facet_grid(. ~ trim) +
|
|
|
45 xlab('Sequence Duplication Level') +
|
|
|
46 ylab('') +
|
|
|
47 theme(axis.text.x = element_text(angle=45))
|
|
|
48 ggplotly(p)
|
|
|
49 ``` |
