---
title: 'Per base sequence quality'
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 sequence quality

```{r 'per base sequence quality', fig.width=10}
## reads 1
pbsq_1 = extract_data_module('REPORT_DIR/reads_1_fastqc_data.txt', 'Per base sequence quality')
pbsq_1$id = 1:length(pbsq_1$X.Base)
pbsq_1$trim = 'before'

## reads 2
pbsq_2 = extract_data_module('REPORT_DIR/reads_2_fastqc_data.txt', 'Per base sequence quality')
pbsq_2$id = 1:length(pbsq_2$X.Base)
pbsq_2$trim = 'after'

comb_pbsq = rbind(pbsq_1, pbsq_2)
comb_pbsq$trim = factor(levels = c('before', 'after'), comb_pbsq$trim)

p = ggplot(data = comb_pbsq) +
  geom_boxplot(mapping = aes(x = id, 
                             lower = Lower.Quartile, 
                             upper = Upper.Quartile, 
                             middle = Median, 
                             ymin = X10th.Percentile, 
                             ymax = X90th.Percentile,
                             fill = "yellow"),
               stat = 'identity') +
  geom_line(mapping = aes(x = id, y = Mean, color = "red")) +
  scale_x_continuous(breaks = pbsq_2$id, labels = pbsq_2$X.Base) +
  scale_fill_identity() +
  scale_color_identity() + 
  ylim(0, max(comb_pbsq$Upper.Quartile) + 5) +
  xlab('Position in read (bp)') +
  facet_grid(. ~ trim) +
  theme(axis.text.x = element_text(angle=45))
p

```