Mercurial > repos > mingchen0919 > aurora_fastqc_site

annotate 02_per_base_sequence_quality.Rmd @ 2:c64267b9f754 draft default tip

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload commit 841d8b22bf9f1aaed6bfe8344b60617f45b275b2-dirty
author mingchen0919
date Sun, 30 Dec 2018 12:48:14 -0500
parents b7c115edd970
children
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
0
b7c115edd970 planemo upload
mingchen0919
parents:
diff changeset
1 ---
b7c115edd970 planemo upload
mingchen0919
parents:
diff changeset
2 output: html_document
b7c115edd970 planemo upload
mingchen0919
parents:
diff changeset
3 ---
b7c115edd970 planemo upload
mingchen0919
parents:
diff changeset
4
b7c115edd970 planemo upload
mingchen0919
parents:
diff changeset
5 ```{r setup, include=FALSE, warning=FALSE, message=FALSE}
2
c64267b9f754 planemo upload commit 841d8b22bf9f1aaed6bfe8344b60617f45b275b2-dirty
mingchen0919
parents: 0
diff changeset
6 knitr::opts_knit$set(progress = FALSE)
c64267b9f754 planemo upload commit 841d8b22bf9f1aaed6bfe8344b60617f45b275b2-dirty
mingchen0919
parents: 0
diff changeset
7 knitr::opts_chunk$set(error = TRUE, echo = FALSE)
0
b7c115edd970 planemo upload
mingchen0919
parents:
diff changeset
8 ```
b7c115edd970 planemo upload
mingchen0919
parents:
diff changeset
9
2
c64267b9f754 planemo upload commit 841d8b22bf9f1aaed6bfe8344b60617f45b275b2-dirty
mingchen0919
parents: 0
diff changeset
10 ### Per base sequence quality
0
b7c115edd970 planemo upload
mingchen0919
parents:
diff changeset
11
b7c115edd970 planemo upload
mingchen0919
parents:
diff changeset
12 ```{r 'per base sequence quality', fig.width=10}
b7c115edd970 planemo upload
mingchen0919
parents:
diff changeset
13 ## reads 1
b7c115edd970 planemo upload
mingchen0919
parents:
diff changeset
14 pbsq_1 = extract_data_module(paste0(opt$X_d, '/read_1_fastqc/fastqc_data.txt'), 'Per base sequence quality')
b7c115edd970 planemo upload
mingchen0919
parents:
diff changeset
15 pbsq_1$id = 1:length(pbsq_1$X.Base)
b7c115edd970 planemo upload
mingchen0919
parents:
diff changeset
16 pbsq_1$trim = 'before'
b7c115edd970 planemo upload
mingchen0919
parents:
diff changeset
17
b7c115edd970 planemo upload
mingchen0919
parents:
diff changeset
18 ## reads 2
b7c115edd970 planemo upload
mingchen0919
parents:
diff changeset
19 pbsq_2 = extract_data_module(paste0(opt$X_d, '/read_2_fastqc/fastqc_data.txt'), 'Per base sequence quality')
b7c115edd970 planemo upload
mingchen0919
parents:
diff changeset
20 pbsq_2$id = 1:length(pbsq_2$X.Base)
b7c115edd970 planemo upload
mingchen0919
parents:
diff changeset
21 pbsq_2$trim = 'after'
b7c115edd970 planemo upload
mingchen0919
parents:
diff changeset
22
b7c115edd970 planemo upload
mingchen0919
parents:
diff changeset
23 comb_pbsq = rbind(pbsq_1, pbsq_2)
b7c115edd970 planemo upload
mingchen0919
parents:
diff changeset
24 comb_pbsq$trim = factor(levels = c('before', 'after'), comb_pbsq$trim)
b7c115edd970 planemo upload
mingchen0919
parents:
diff changeset
25
b7c115edd970 planemo upload
mingchen0919
parents:
diff changeset
26 p = ggplot(data = comb_pbsq) +
b7c115edd970 planemo upload
mingchen0919
parents:
diff changeset
27 geom_boxplot(mapping = aes(x = id,
b7c115edd970 planemo upload
mingchen0919
parents:
diff changeset
28 lower = Lower.Quartile,
b7c115edd970 planemo upload
mingchen0919
parents:
diff changeset
29 upper = Upper.Quartile,
b7c115edd970 planemo upload
mingchen0919
parents:
diff changeset
30 middle = Median,
b7c115edd970 planemo upload
mingchen0919
parents:
diff changeset
31 ymin = X10th.Percentile,
b7c115edd970 planemo upload
mingchen0919
parents:
diff changeset
32 ymax = X90th.Percentile,
b7c115edd970 planemo upload
mingchen0919
parents:
diff changeset
33 fill = "yellow"),
b7c115edd970 planemo upload
mingchen0919
parents:
diff changeset
34 stat = 'identity') +
b7c115edd970 planemo upload
mingchen0919
parents:
diff changeset
35 geom_line(mapping = aes(x = id, y = Mean, color = "red")) +
2
c64267b9f754 planemo upload commit 841d8b22bf9f1aaed6bfe8344b60617f45b275b2-dirty
mingchen0919
parents: 0
diff changeset
36 scale_x_continuous(name = 'Position in read (bp)', breaks = pbsq_2$id, labels = pbsq_2$X.Base) +
c64267b9f754 planemo upload commit 841d8b22bf9f1aaed6bfe8344b60617f45b275b2-dirty
mingchen0919
parents: 0
diff changeset
37 scale_y_continuous(limits = c(0, max(comb_pbsq$Upper.Quartile) + 5)) +
0
b7c115edd970 planemo upload
mingchen0919
parents:
diff changeset
38 scale_fill_identity() +
b7c115edd970 planemo upload
mingchen0919
parents:
diff changeset
39 scale_color_identity() +
b7c115edd970 planemo upload
mingchen0919
parents:
diff changeset
40 facet_grid(. ~ trim) +
2
c64267b9f754 planemo upload commit 841d8b22bf9f1aaed6bfe8344b60617f45b275b2-dirty
mingchen0919
parents: 0
diff changeset
41 theme(axis.text.x = element_text(size = 5),
c64267b9f754 planemo upload commit 841d8b22bf9f1aaed6bfe8344b60617f45b275b2-dirty
mingchen0919
parents: 0
diff changeset
42 panel.background = element_rect(fill = NA),
c64267b9f754 planemo upload commit 841d8b22bf9f1aaed6bfe8344b60617f45b275b2-dirty
mingchen0919
parents: 0
diff changeset
43 panel.grid.major.y = element_line(color = 'blue', size = 0.1))
0
b7c115edd970 planemo upload
mingchen0919
parents:
diff changeset
44 p
2
c64267b9f754 planemo upload commit 841d8b22bf9f1aaed6bfe8344b60617f45b275b2-dirty
mingchen0919
parents: 0
diff changeset
45 ```
0
b7c115edd970 planemo upload
mingchen0919
parents:
diff changeset
46