view 01_evaluation_overview.Rmd @ 12:68ea2ebbf866 draft

add boxplot for per base sequence quality
author mingchen0919
date Thu, 09 Nov 2017 09:23:43 -0500
parents 507eec497730
children
line wrap: on
line source

---
title: 'Short reads evaluation with [FastQC](https://www.bioinformatics.babraham.ac.uk/projects/fastqc/)'
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
)
```


# Fastqc Evaluation

## Evaluation of reads before trimming

```{r}
if ('READS_1' == 'None') {
  stop("No pre-trimming reads provided!")
} else {
  ## run fastqc evaluation
  fastqc_command = paste0('fastqc ') %>% 
  (function(x) {
    ifelse('CONTAMINANTS' != 'None', paste0(x, '-c CONTAMINANTS '), x)
  }) %>% 
  (function(x) {
    ifelse('LIMITS' != 'None', paste0(x, '-l LIMITS '), x)
  }) %>% 
  (function(x) {
    paste0(x, '-o REPORT_DIR ')
  })
  fastqc_command_reads_1 = paste0(fastqc_command, 'READS_1 > /dev/null 2>&1')
  system(fastqc_command_reads_1, intern = TRUE)
  
  # Original html report
  reads_1_base = tail(strsplit('READS_1', '/')[[1]], 1)
  original_html = tags$a(href=paste0(reads_1_base, '_fastqc.html'), paste0('HTML report: ', opt$name_1))
  
  unzip(paste0('REPORT_DIR/', reads_1_base, '_fastqc.zip'), exdir = 'REPORT_DIR')
  reads_1_unzip = paste0('REPORT_DIR/', reads_1_base, '_fastqc/')
  # fastqc_data.txt
  file.copy(paste0(reads_1_unzip, 'fastqc_data.txt'), 'REPORT_DIR/reads_1_fastqc_data.txt')
  fastqc_data = tags$a(href='reads_1_fastqc_data.txt', paste0('fastqc_data.txt: ', opt$name_1))
  # summary.txt
  file.copy(paste0(reads_1_unzip, 'summary.txt'), 'REPORT_DIR/reads_1_summary.txt')
  summary_data = tags$a(href='reads_1_summary.txt', paste0('summary.txt: ', opt$name_1))
  
  tags$ul(
    tags$li(original_html),
    tags$li(fastqc_data),
    tags$li(summary_data)
  )
}
```


## Evaluation of reads after trimming

```{r}
if ('READS_2' == 'None') {
  stop("No pre-trimming reads provided!")
} else {
  ## run fastqc evaluation
  fastqc_command = paste0('fastqc ') %>% 
  (function(x) {
    ifelse('CONTAMINANTS' != 'None', paste0(x, '-c CONTAMINANTS '), x)
  }) %>% 
  (function(x) {
    ifelse('LIMITS' != 'None', paste0(x, '-l LIMITS '), x)
  }) %>% 
  (function(x) {
    paste0(x, '-o REPORT_DIR ')
  })
  fastqc_command_reads_2 = paste0(fastqc_command, 'READS_2 > /dev/null 2>&1')
  system(fastqc_command_reads_2, intern = TRUE)
  
  # Original html report
  reads_2_base = tail(strsplit('READS_2', '/')[[1]], 1)
  original_html = tags$a(href=paste0(reads_2_base, '_fastqc.html'), paste0('HTML report: ', opt$name_2))
  
  unzip(paste0('REPORT_DIR/', reads_2_base, '_fastqc.zip'), exdir = 'REPORT_DIR')
  reads_2_unzip = paste0('REPORT_DIR/', reads_2_base, '_fastqc/')
  # fastqc_data.txt
  file.copy(paste0(reads_2_unzip, 'fastqc_data.txt'), 'REPORT_DIR/reads_2_fastqc_data.txt')
  fastqc_data = tags$a(href='reads_2_fastqc_data.txt', paste0('fastqc_data.txt: ', opt$name_2))
  # summary.txt
  file.copy(paste0(reads_2_unzip, 'summary.txt'), 'REPORT_DIR/reads_2_summary.txt')
  summary_data = tags$a(href='reads_2_summary.txt', paste0('summary.txt: ', opt$name_2))
  
  tags$ul(
    tags$li(original_html),
    tags$li(fastqc_data),
    tags$li(summary_data)
  )
}
```



# Fastqc output visualization

## Overview

```{r}
reads_1_summary = read.csv('REPORT_DIR/reads_1_summary.txt', header = FALSE, sep = '\t')[, 2:1]
reads_2_summary = read.csv('REPORT_DIR/reads_2_summary.txt', header = FALSE, sep = '\t')[, 1]
combined_summary = cbind(reads_1_summary, reads_2_summary)
names(combined_summary) = c('MODULE', paste0(opt$name_1, '(before)'), paste0(opt$name_2, '(after)'))
combined_summary[combined_summary == 'FAIL'] = 'FAIL (X)'
combined_summary[combined_summary == 'WARN'] = 'WARN (!)'
knitr::kable(combined_summary)
```

# Session Info

```{r 'session info'}
sessionInfo()
```