view 09_sequence_duplication_levels.Rmd @ 12:68ea2ebbf866 draft

add boxplot for per base sequence quality

---
title: 'Sequence Duplication Levels'
output:
    html_document:
      number_sections: true
      toc: true
      theme: cosmo
      highlight: tango
---

```{r setup, include=FALSE, warning=FALSE, message=FALSE}
knitr::opts_chunk$set(
  echo = ECHO,
  error = TRUE
)
```

### Sequence Duplication Levels

```{r 'Sequence Duplication Levels', fig.width=10}
## reads 1
sdl_1 = extract_data_module('REPORT_DIR/reads_1_fastqc_data.txt', 'Sequence Duplication Levels', header = FALSE, comment.char = '#')
names(sdl_1) = c('Duplication_Level', 'Percentage_of_deduplicated', 'Percentage_of_total')
sdl_1$id = 1:length(sdl_1$Duplication_Level)

melt_sdl_1 = melt(sdl_1, id=c('Duplication_Level', 'id'))
melt_sdl_1$trim = 'before'


## reads 2
sdl_2 = extract_data_module('REPORT_DIR/reads_2_fastqc_data.txt', 'Sequence Duplication Levels', header = FALSE, comment.char = '#')
names(sdl_2) = c('Duplication_Level', 'Percentage_of_deduplicated', 'Percentage_of_total')
sdl_2$id = 1:length(sdl_2$Duplication_Level)

melt_sdl_2 = melt(sdl_2, id=c('Duplication_Level', 'id'))
melt_sdl_2$trim = 'after'

comb_sdl = rbind(melt_sdl_1, melt_sdl_2)
comb_sdl$trim = factor(levels = c('before', 'after'), comb_sdl$trim)

p = ggplot(data = comb_sdl, aes(x = id, y = value, color = variable)) +
  geom_line() +
  scale_x_continuous(breaks = sdl_2$id, labels = sdl_2$Duplication_Level) +
  facet_grid(. ~ trim) +
  xlab('Sequence Duplication Level') +
  ylab('') + 
  theme(axis.text.x = element_text(angle=45))
ggplotly(p)
```