In HIVDiversity/MotifBinner2: Processes NGS Primer ID Datasets

opts_chunk$set(echo=FALSE)
opts_chunk$set(warning=FALSE)
opts_chunk$set(fig.pos = 'H')

library(MotifBinner2)

if (!exists('result'))
{
  result <- all_results[[grep('ambigSeqs', names(all_results))[1]]]
}
if (class(result) != 'ambigSeqs')
{
  result <- all_results[[grep('ambigSeqs', names(all_results))[1]]]
}
figure_path <- paste('figure_', result$config$op_full_name, '/', sep = '')

r result$config$op_full_name

Removes sequences with more than a certain percentage (r round(result$config$op_args$threshold*100,1)%) of ambiguous characters.

fig.cap1 <- 'Figure: Histograms of the number of reads based on how many ambiguous bases they contain.'

options(scipen=99)
ambig_counts <- result$metrics$per_read_metrics
ticks <- 10^(0:12)
ticks <- ticks[ticks < nrow(ambig_counts)]
p1 <- 
ggplot(ambig_counts, aes(x=ambig, fill=seq_len)) +
  geom_histogram(bins=30) + 
  scale_y_continuous(trans="log1p", breaks = ticks) +
  ylab('Number of reads') +
  xlab('Number of ambiguous bases') +
  scale_fill_continuous(guide = FALSE)

p2 <-
ggplot(ambig_counts, aes(x=100*prop_ambig, fill=seq_len)) +
  geom_histogram(bins=30) + 
  scale_y_continuous(trans="log1p", breaks = ticks) +
  ylab('Number of reads') +
  xlab('Percentage of ambiguous bases') +
  scale_fill_continuous(guide = FALSE)

grid.arrange(p1, p2, ncol=2)

cat('\n\n')

kable_summary(result$summary)

timingTable(result)

cat('\n\n---\n\n')

HIVDiversity/MotifBinner2 documentation built on May 6, 2019, 6:44 p.m.