annotate 06_per_sequence_gc_content.Rmd @ 12:68ea2ebbf866 draft

add boxplot for per base sequence quality
author mingchen0919
date Thu, 09 Nov 2017 09:23:43 -0500
parents 507eec497730
children
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
11
507eec497730 update fastqc site
mingchen0919
parents:
diff changeset
1 ---
507eec497730 update fastqc site
mingchen0919
parents:
diff changeset
2 title: 'Per sequence GC content'
507eec497730 update fastqc site
mingchen0919
parents:
diff changeset
3 output:
507eec497730 update fastqc site
mingchen0919
parents:
diff changeset
4 html_document:
507eec497730 update fastqc site
mingchen0919
parents:
diff changeset
5 number_sections: true
507eec497730 update fastqc site
mingchen0919
parents:
diff changeset
6 toc: true
507eec497730 update fastqc site
mingchen0919
parents:
diff changeset
7 theme: cosmo
507eec497730 update fastqc site
mingchen0919
parents:
diff changeset
8 highlight: tango
507eec497730 update fastqc site
mingchen0919
parents:
diff changeset
9 ---
507eec497730 update fastqc site
mingchen0919
parents:
diff changeset
10
507eec497730 update fastqc site
mingchen0919
parents:
diff changeset
11 ```{r setup, include=FALSE, warning=FALSE, message=FALSE}
507eec497730 update fastqc site
mingchen0919
parents:
diff changeset
12 knitr::opts_chunk$set(
507eec497730 update fastqc site
mingchen0919
parents:
diff changeset
13 echo = ECHO,
507eec497730 update fastqc site
mingchen0919
parents:
diff changeset
14 error = TRUE
507eec497730 update fastqc site
mingchen0919
parents:
diff changeset
15 )
507eec497730 update fastqc site
mingchen0919
parents:
diff changeset
16 ```
507eec497730 update fastqc site
mingchen0919
parents:
diff changeset
17
507eec497730 update fastqc site
mingchen0919
parents:
diff changeset
18 ### Per sequence GC content
507eec497730 update fastqc site
mingchen0919
parents:
diff changeset
19
507eec497730 update fastqc site
mingchen0919
parents:
diff changeset
20 ```{r 'Per sequence GC content', fig.width=10}
507eec497730 update fastqc site
mingchen0919
parents:
diff changeset
21 ## reads 1
507eec497730 update fastqc site
mingchen0919
parents:
diff changeset
22 psGCc_1 = extract_data_module('REPORT_DIR/reads_1_fastqc_data.txt', 'Per sequence GC content')
507eec497730 update fastqc site
mingchen0919
parents:
diff changeset
23 psGCc_1$trim = 'before'
507eec497730 update fastqc site
mingchen0919
parents:
diff changeset
24
507eec497730 update fastqc site
mingchen0919
parents:
diff changeset
25 ## reads 2
507eec497730 update fastqc site
mingchen0919
parents:
diff changeset
26 psGCc_2 = extract_data_module('REPORT_DIR/reads_2_fastqc_data.txt', 'Per sequence GC content')
507eec497730 update fastqc site
mingchen0919
parents:
diff changeset
27 psGCc_2$trim = 'after'
507eec497730 update fastqc site
mingchen0919
parents:
diff changeset
28
507eec497730 update fastqc site
mingchen0919
parents:
diff changeset
29 comb_psGCc = rbind(psGCc_1, psGCc_2)
507eec497730 update fastqc site
mingchen0919
parents:
diff changeset
30 comb_psGCc$trim = factor(levels = c('before', 'after'), comb_psGCc$trim)
507eec497730 update fastqc site
mingchen0919
parents:
diff changeset
31
507eec497730 update fastqc site
mingchen0919
parents:
diff changeset
32 p = ggplot(data = comb_psGCc, aes(x = X.GC.Content, y = Count)) +
507eec497730 update fastqc site
mingchen0919
parents:
diff changeset
33 geom_line(color = 'red') +
507eec497730 update fastqc site
mingchen0919
parents:
diff changeset
34 facet_grid(. ~ trim) +
507eec497730 update fastqc site
mingchen0919
parents:
diff changeset
35 xlab('Mean Sequence Qaulity (Phred Score)') +
507eec497730 update fastqc site
mingchen0919
parents:
diff changeset
36 ylab('')
507eec497730 update fastqc site
mingchen0919
parents:
diff changeset
37 ggplotly(p)
507eec497730 update fastqc site
mingchen0919
parents:
diff changeset
38 ```