--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/05_per_base_sequence_content.Rmd	Tue Nov 07 16:52:24 2017 -0500
@@ -0,0 +1,47 @@
+---
+title: 'Per base sequence content'
+output:
+    html_document:
+      number_sections: true
+      toc: true
+      theme: cosmo
+      highlight: tango
+---
+
+```{r setup, include=FALSE, warning=FALSE, message=FALSE}
+knitr::opts_chunk$set(
+  echo = ECHO,
+  error = TRUE
+)
+```
+
+### Per base sequence content
+
+```{r 'Per base sequence content', fig.width=10}
+## reads 1
+pbsc_1 = extract_data_module('REPORT_DIR/reads_1_fastqc_data.txt', 'Per base sequence content')
+pbsc_1$id = 1:length(pbsc_1$X.Base)
+
+melt_pbsc_1 = melt(pbsc_1, id=c('X.Base', 'id'))
+melt_pbsc_1$trim = 'before'
+
+
+## reads 2
+pbsc_2 = extract_data_module('REPORT_DIR/reads_2_fastqc_data.txt', 'Per base sequence content')
+pbsc_2$id = 1:length(pbsc_2$X.Base)
+
+melt_pbsc_2 = melt(pbsc_2, id=c('X.Base', 'id'))
+melt_pbsc_2$trim = 'after'
+
+comb_pbsc = rbind(melt_pbsc_1, melt_pbsc_2)
+comb_pbsc$trim = factor(levels = c('before', 'after'), comb_pbsc$trim)
+
+p = ggplot(data = comb_pbsc, aes(x = id, y = value, color = variable)) +
+  geom_line() +
+  facet_grid(. ~ trim) +
+  xlim(min(comb_pbsc$id), max(comb_pbsc$id)) + 
+  ylim(0, 100) +
+  xlab('Position in read (bp)') +
+  ylab('')
+ggplotly(p)
+```
\ No newline at end of file