Job script

skewer \
    /export/galaxy-central/database/files/000/dataset_7.dat \
    /export/galaxy-central/database/files/000/dataset_8.dat \
    -m head \
    -r 0.1 \
    -d 0.03 \
    -q 0 \
    -Q 0 \
    -l 18 \
    -f auto \
    -o trim > skewer.log.txt 2>&1

Results summary

Reads processing summary

log = readLines(paste0(Sys.getenv('REPORT_FILES_PATH'), '/trim-trimmed.log'))
start_line = grep('read.+processed; of these:', log)
end_line = grep('untrimmed.+available after processing', log)
processing_summary = gsub('(\\d+) ', '\\1\t', log[start_line:end_line])
processing_summary_df = do.call(rbind, strsplit(processing_summary, '\t'))
colnames(processing_summary_df) = c('Total reads:', processing_summary_df[1,1])
knitr::kable(processing_summary_df[-1, ])
Total reads: 250000
0 ( 0.00%) short read pairs filtered out after trimming by size control
0 ( 0.00%) empty read pairs filtered out after trimming by size control
250000 (100.00%) read pairs available; of these:
10328 ( 4.13%) trimmed read pairs available after processing
239672 (95.87%) untrimmed read pairs available after processing

Length distribution of reads after trimming

start_line = grep('length   count   percentage', log)
len_dist = log[(start_line):length(log)]
len_dist = do.call(rbind, strsplit(len_dist, '\t'))
columns = len_dist[1, ]
len_dist = as.data.frame(len_dist[-1, ])
colnames(len_dist) = columns

library(plotly)
library(ggplot2)
len_dist$count = as.numeric(len_dist$count)
labels = as.character(len_dist$length)
len_dist$length = 1:nrow(len_dist)
pp = ggplot(data = len_dist, aes(length, count)) +
  geom_line(color='red') +
  scale_x_continuous(name = 'Length',
                   breaks = 1:nrow(len_dist),
                   labels = labels) +
  theme(axis.text.x = element_text(angle = 90, hjust = 1)) +
  ylab('Count') +
  ggtitle('Length distribution')
ggplotly(pp)