annotate mirdeep2.Rmd @ 0:963905bcb754 draft

planemo upload for repository https://github.com/statonlab/docker-GRReport/tree/master/my_tools/rmarkdown_mirdeep2 commit 29e8b40899c71ca12fd07b2bb530b0ee65037588-dirty

---
title: 'Mirdeep2'
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
)
```

# Job command line

```{r 'build PATH', echo=FALSE}
# set PATH environment.
PATH = system('pwd', intern = TRUE) %>% 
  (function(x) {
    paste0('/home/galaxy/mirdeep2/bin:', x)
  }) %>%
    (function(x) {
    paste0('/home/galaxy/mirdeep2_patch:', x)
  }) %>%
  paste0(':$PATH') 
```

## Build job command line.

```{r 'build command line'}
# change directory to OUTPUT DIR
command_line = paste0('cd OUTPUT_DIR &&') %>%
  # PATH and other environment variables
  paste0('export PATH=', PATH, ' && ') %>%
  (function(x) {
    paste0(x, 'export PERL_MB_OPT="--install_base /home/galaxy/perl5" &&
           export PERL_MM_OPT="INSTALL_BASE=/home/galaxy/perl5" &&
           export PERL5LIB=/home/galaxy/mirdeep2/lib/perl5 && ')
  }) %>%
  # link collapsed reads and reads mapping files
  (function(x) {
    paste0(x, 'ln -s COLLAPSED_READS reads_collapsed.fa && ')
  }) %>%
  (function(x) {
    paste0(x, 'ln -s READS_MAPPING reads_collapsed_vs_genome.arf && ')
  }) %>%
  paste0(' miRDeep2.pl ') %>%
  # collapsed reads
  (function(x) {
    paste0(x, ' reads_collapsed.fa ')
  }) %>%
  # reference genome
  (function(x) {
    paste0(x, ' REFERENCE_GENOME ')
  }) %>%
  # reads mapping
  (function(x) {
    paste0(x, ' reads_collapsed_vs_genome.arf ')
  }) %>%
  # mature miRNA for this species
  (function(x) {
    if('SPECIES_MATURE_MIRNA' == 'None') {
      paste0(x, tolower('SPECIES_MATURE_MIRNA'), ' ')
    } else {
      paste0(x, ' SPECIES_MATURE_MIRNA ')
    }
  }) %>%
  # mature miRNA from related species
  (function(x) {
    if('SPECIES_RELATED_MATURE_MIRNA' == 'None') {
      paste0(x, tolower('SPECIES_RELATED_MATURE_MIRNA'), ' ')
    } else {
      paste0(x, 'SPECIES_RELATED_MATURE_MIRNA ')
    }
  }) %>%
  # precursor sequences
  (function(x) {
    if('PRECURSOR_SEQUENCES' == 'None') {
      paste0(x, tolower('PRECURSOR_SEQUENCES'), ' ')
    } else {
      paste0(x, 'PRECURSOR_SEQUENCES ')
    }
  }) %>%
  # min read stack height
  (function(x) {
    ifelse('MIN_READ_STACK_HEIGHT' == 'TRUE', x, paste0(x, ' -a MIN_READ_STACK_HEIGHT '))
  }) %>%
  # min score cutoff
  (function(x) {
    paste0(x, '-b MIN_SCORE_CUTOFF ')
  }) %>%
  # disable randfold analysis
  (function(x) {
    ifelse(RANDFOLD_ANALYSIS, paste0(x, '-c '), x)
  }) %>%
  # max precursors number
  (function(x) {
    paste0(x, ' -g MAX_PRECURSOR_NUMBER ')
  }) %>%
  # species
  (function(x) {
    ifelse('SPECIES' == 'all', x, paste0(x, ' -t SPECIES '))
  }) %>%
  # switch
  (function(x) {
    ifelse(SWITCH, x, paste0(x, ' -P '))
  }) %>%
  # write stdout to reprot.log
  (function(x) {
    paste0(x, ' >report.log 2>&1 ')
  })
  
command_line

## run job
system(command_line)
```

## Results

```{r echo=TRUE}
system('cp OUTPUT_DIR/result*.html result.html')
system('cp OUTPUT_DIR/result*.csv result.csv')
system('cp OUTPUT_DIR/report.log report.log')
system('mv OUTPUT_DIR/pdfs_* OUTPUT_DIR/pdfs')

## check if OUTPUT DIR has results that we want.
system('ls OUTPUT_DIR', intern = TRUE)
```

### PDF files

```{r echo=TRUE}
pdf_report_list = list()
pdf_files = list.files('OUTPUT_DIR/pdfs', pattern = '.*pdf')
pdf_files
for (i in pdf_files) {
  # note that the root directory is OUTPUT_DIR, all the file links should be a relative path to the root directory!
  pdf_report_list[[i]] = tags$li(tags$a(href=paste0('pdfs/', i), i))
}
tags$ul(pdf_report_list)
```