---
title: "00.00-heatwave-genetics-raw-FastQC-MultiQC"
author: "Sam White"
date: "2025-07-10"
output: 
  github_document:
    toc: true
    number_sections: true
  bookdown::html_document2:
    theme: cosmo
    toc: true
    toc_float: true
    number_sections: true
    code_folding: show
    code_download: true
  html_document:
    theme: cosmo
    toc: true
    toc_float: true
    number_sections: true
    code_folding: show
    code_download: true
bibliography: references.bib
---

# Background

This Rmd file will download raw FastQs for the heatwave genetics sub-project and evaluate them using [FastQC](https://github.com/s-andrews/FastQC) and [MultiQC](https://multiqc.info/) [@ewels2016].

```{r setup, include=FALSE}
library(knitr)
knitr::opts_chunk$set(
  echo = TRUE,         # Display code chunks
  eval = FALSE,        # Evaluate code chunks
  warning = FALSE,     # Hide warnings
  message = FALSE,     # Hide messages
  comment = ""         # Prevents appending '##' to beginning of lines in code output
)
```

# Create a Bash variables file

This allows usage of Bash variables across R Markdown chunks.

```{r save-bash-variables-to-rvars-file, engine='bash', eval=TRUE}
{
echo "#### Assign Variables ####"
echo ""

echo "# Data directories"
echo 'export repo_dir=/home/shared/8TB_HDD_01/sam/gitrepos/RobertsLab/project-cod-temperature'
echo 'export output_dir_top=${repo_dir}/output/00.00-heatwave-genetics-raw-FastQC-MultiQC'
echo 'export raw_fastqc_dir=${output_dir_top}'
echo 'export raw_reads_dir=${repo_dir}/data/raw-fastqs-heatwave-genetics'
echo 'export raw_reads_url="https://owl.fish.washington.edu/nightingales/G_macrocephalus/30-1149633765/00_fastq/"'
echo ""

echo "# Paths to programs"
echo 'export fastqc=/home/shared/FastQC-0.12.1/fastqc'
echo 'export multiqc=/home/sam/programs/mambaforge/bin/multiqc'
echo ""

echo "# Set FastQ filename patterns"
echo "export fastq_pattern='*.fastq.gz'"
echo "export R1_fastq_pattern='*_R1_*.fastq.gz'"
echo "export R2_fastq_pattern='*_R2_*.fastq.gz'"
echo ""

echo "# Set number of CPUs to use"
echo 'export threads=40'
echo ""


echo "## Inititalize arrays"
echo 'export fastq_array_R1=()'
echo 'export fastq_array_R2=()'
echo 'export raw_fastqs_array=()'
echo 'export R1_names_array=()'
echo 'export R2_names_array=()'
echo ""

echo "# Programs associative array"
echo "declare -A programs_array"
echo "programs_array=("
echo '[fastqc]="${fastqc}" \'
echo '[multiqc]="${multiqc}" \'
echo ")"
echo ""

echo "# Print formatting"
echo 'export line="--------------------------------------------------------"'
echo ""
} > .bashvars

cat .bashvars
```

# Download raw FastQs

Reads are downloaded from <https://owl.fish.washington.edu/nightingales/G_macrocephalus/30-1149633765/00_fastq/>



The `--cut-dirs 3` command cuts the preceding directory structure so that we just end up with the reads.


## Download raw reads

```{bash download-raw-reads, engine='bash', eval=TRUE}
# Load bash variables into memory
source .bashvars

# Make output directory if it doesn't exist
mkdir --parents ${raw_reads_dir}


# Run wget to retrieve FastQs and MD5 files
# Note: the --no-clobber command will skip re-downloading any files that are already present in the output directory
wget \
--directory-prefix ${raw_reads_dir} \
--recursive \
--no-check-certificate \
--continue \
--cut-dirs 3 \
--no-host-directories \
--no-parent \
--quiet \
--no-clobber \
${raw_reads_url}

ls -lh "${raw_reads_dir}"
```

## Verify raw read checksums

```{bash verify-raw-read-checksums, engine='bash', eval=TRUE}
# Load bash variables into memory
source .bashvars

cd "${raw_reads_dir}"

# Checksums file contains other files, so this just looks for the RNAseq files.
for file in *.md5
do
  md5sum --check "${file}"
done
```


# FastQC/MultiQC on raw reads

```{bash raw-fastqc-multiqc, engine='bash', eval=TRUE}
# Load bash variables into memory
source .bashvars

# Make output directory if it doesn't exist
mkdir --parents "${raw_fastqc_dir}"

############ RUN FASTQC ############


# Create array of trimmed FastQs
raw_fastqs_array=(${raw_reads_dir}/${fastq_pattern})

# Pass array contents to new variable as space-delimited list
raw_fastqc_list=$(echo "${raw_fastqs_array[*]}")

echo "Beginning FastQC on raw reads..."
echo ""

# Run FastQC
### NOTE: Do NOT quote raw_fastqc_list
${programs_array[fastqc]} \
--threads ${threads} \
--outdir ${raw_fastqc_dir} \
--quiet \
${raw_fastqc_list}

echo "FastQC on raw reads complete!"
echo ""

############ END FASTQC ############

############ RUN MULTIQC ############
echo "Beginning MultiQC on raw FastQC..."
echo ""

${programs_array[multiqc]} ${raw_fastqc_dir} -o ${raw_fastqc_dir}

echo ""
echo "MultiQC on raw FastQs complete."
echo ""

############ END MULTIQC ############

echo "Removing FastQC zip files."
echo ""
rm ${raw_fastqc_dir}/*.zip
echo "FastQC zip files removed."
echo ""
```

```{bash, eval=TRUE}
# Load bash variables into memory
source .bashvars

# View directory contents
ls -lh ${raw_fastqc_dir}

```