---
title: "03-methylation"
format: html
editor: visual
---


Sam did extraction...

```
${bismark_dir}/bismark_methylation_extractor \
--bedGraph \
--counts \
--scaffolds \
--parallel 10 \
--output_dir ${output_dir_top} \
--samtools_path ${samtools_dir} \
--gzip \
--paired-end \
--zero_based \
--buffer_size 50% \
--cytosine_report \
--genome_folder ${genome_dir} \
*deduplicated.bam
```

```{bash}
wget -r \
--no-directories --no-parent \
-P ../output/02.20-bismark-methylation-extraction/ \
-A "*cov.gz" https://gannet.fish.washington.edu/Atumefaciens/gitrepos/ceasmallr/output/02.20-bismark-methylation-extraction/

```


```{bash}
ls ../output/02.20-bismark-methylation-extraction/*cov.gz
```

```{bash}
# Set the paths for Bismark, Bowtie2, and genome folder
bismark_dir="/home/shared/Bismark-0.24.0"
bowtie2_dir="/home/shared/bowtie2-2.4.4-linux-x86_64/"
genome_folder="../data/genome/"
output_dir="../output/03-methylation"

# Create the output directory if it doesn't exist
mkdir -p "$output_dir"

# Find files and process each with coverage2cytosine
find ../output/02.20-bismark-methylation-extraction/*_R1_001.fastp-trim.20220827_bismark_bt2_pe.deduplicated.bismark.cov.gz \
| while read -r file; do
    # Get the sample name by stripping the suffix
    sample_name=$(basename "$file" "_R1_001.fastp-trim.20220827_bismark_bt2_pe.deduplicated.bismark.cov.gz")

    # Define log file for capturing stdout and stderr
    log_file="$output_dir/${sample_name}_coverage2cytosine.log"

    # Run coverage2cytosine command and redirect stdout and stderr to the log file
    "${bismark_dir}/coverage2cytosine" \
    --genome_folder "${genome_folder}" \
    -o "$output_dir/$sample_name" \
    --merge_CpG \
    --zero_based \
    "$file" > "$log_file" 2>&1

    echo "Processed $sample_name, output in $log_file"
done
```


```{bash}
# Set the base directory containing the Bismark subdirectories
base_dir="/output"
# Set the output directory for all Bismark reports
output_dir="../output/03-methylation"

# Create the output directory if it doesn't exist
mkdir -p "$output_dir"

# Loop through each subdirectory
for dir in "$base_dir"/*/; do
  # Check if the directory exists
  if [ -d "$dir" ]; then
    echo "Processing directory: $dir"
    
    # Extract the subdirectory name
    sub_dir_name=$(basename "$dir")
    
    # Run bismark2report and redirect output
    "${dir}/bismark2report" > "$output_dir/${sub_dir_name}_report.txt"
    
    # Run bismark2summary and redirect output
    "${dir}/bismark2summary" > "$output_dir/${sub_dir_name}_summary.txt"
  fi
done
```