view 07_per_base_n_content.Rmd @ 12:68ea2ebbf866 draft

add boxplot for per base sequence quality

---
title: 'Per base N content'
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
)
```

### Per base N content

```{r 'Per base N content', fig.width=10}
## reads 1
pbNc_1 = extract_data_module('REPORT_DIR/reads_1_fastqc_data.txt', 'Per base N content')
pbNc_1$id = 1:length(pbNc_1$X.Base)
pbNc_1$trim = 'before'

## reads 2
pbNc_2 = extract_data_module('REPORT_DIR/reads_2_fastqc_data.txt', 'Per base N content')
pbNc_2$id = 1:length(pbNc_2$X.Base)
pbNc_2$trim = 'after'

comb_pbNc = rbind(pbNc_1, pbNc_2)
comb_pbNc$trim = factor(levels = c('before', 'after'), comb_pbNc$trim)

p = ggplot(data = comb_pbNc, aes(x = id, y = N.Count)) +
  geom_line(color = 'red') +
  scale_x_continuous(breaks = pbNc_2$id, labels = pbNc_2$X.Base) + 
  facet_grid(. ~ trim) +
  ylim(0, 1) + 
  xlab('N-Count') +
  ylab('') + 
  theme(axis.text.x = element_text(angle=45))
ggplotly(p)
```