# HG changeset patch # User mingchen0919 # Date 1543554776 18000 # Node ID a9b160a97a5e650e09aaaf4aaed198ab3ceece53 # Parent 3fc7079a1f0658e61bdad2840c4b758a569bb247 planemo upload commit bd7e129777e3ef6403f055251e17b541d222d7d0-dirty diff -r 3fc7079a1f06 -r a9b160a97a5e 01_skewer_analysis.Rmd --- a/01_skewer_analysis.Rmd Sat Jun 09 22:32:27 2018 -0400 +++ b/01_skewer_analysis.Rmd Fri Nov 30 00:12:56 2018 -0500 @@ -24,3 +24,42 @@ ``` +# Results summary + +## Reads processing summary + +```{r echo=TRUE} +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, ]) +``` + +## Length distribution of reads after trimming + +```{r echo=TRUE, message=FALSE, warning=FALSE} +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) +``` \ No newline at end of file diff -r 3fc7079a1f06 -r a9b160a97a5e rmarkdown_report.xml --- a/rmarkdown_report.xml Sat Jun 09 22:32:27 2018 -0400 +++ b/rmarkdown_report.xml Fri Nov 30 00:12:56 2018 -0500 @@ -6,6 +6,7 @@ r-getopt r-rmarkdown skewer + r-plotly