diff 02_per_base_sequence_quality.Rmd @ 11:507eec497730 draft

update fastqc site

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/02_per_base_sequence_quality.Rmd	Tue Nov 07 16:52:24 2017 -0500
@@ -0,0 +1,47 @@
+---
+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$X.Base)
+
+melt_pbsq_1 = filter(melt(pbsq_1, id=c('X.Base', 'id')), variable == 'Mean')
+melt_pbsq_1$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)
+
+melt_pbsq_2 = filter(melt(pbsq_2, id=c('X.Base', 'id')), variable == 'Mean')
+melt_pbsq_2$trim = 'after'
+
+comb_pbsq = rbind(melt_pbsq_1, melt_pbsq_2)
+comb_pbsq$trim = factor(levels = c('before', 'after'), comb_pbsq$trim)
+
+p = ggplot(data = comb_pbsq) +
+  geom_line(mapping = aes(x = id, y = value, group = variable, color = variable)) +
+  scale_x_continuous(breaks = pbsq_2$id, labels = pbsq_2$X.Base) + 
+  facet_grid(. ~ trim) + 
+  ylim(0, max(comb_pbsq$value) + 5) +
+  theme(axis.text.x = element_text(angle=45))
+ggplotly(p)
+
+```
\ No newline at end of file