#!/bin/sh

#SBATCH --job-name=bismark_array          # Job name
#SBATCH --output=%x_%A_%a.out             # Standard output and error log
#SBATCH --error=%x_%A_%a.err              # Error log
#SBATCH --account=srlab
#SBATCH --partition=ckpt #update this line - use hyakalloc to find partitions you can use
#SBATCH --time=04-02:00:00
#SBATCH --ntasks=1                        # Run a single task
#SBATCH --cpus-per-task=30                # Number of CPU cores per task
#SBATCH --array=0-47                      # Array range (adjust based on the number of samples)
#SBATCH --mem=100G                         # Memory per node
#SBATCH --chdir=/gscratch/scrubbed/sr320/github/project-mytilus-methylation/output/02-bismark-klone-array/

# Exit script if any command fails
#set -e

# Get most recent container git hash
git_commit_hash=$(find /gscratch/srlab/containers/ \
-name "srlab-bioinformatics-container*" \
-printf "%T+ %p\n" \
| sort -n \
| awk -F[-.] 'NR == 1 {print $7}')

# Load modules
module load apptainer

# Execute Roberts Lab bioinformatics container
# Binds home directory
# Binds /gscratch directory
# Directory bindings allow outputs to be written to the hard drive.
apptainer exec \
--home "$PWD" \
--bind /mmfs1/home/ \
--bind /mmfs1/gscratch/ \
/gscratch/srlab/containers/srlab-bioinformatics-container-"${git_commit_hash}".sif



# Set directories and files
reads_dir="/gscratch/scrubbed/sr320/github/project-mytilus-methylation/data/raw-wgbs/"
#bismark_dir="/path/to/bismark/"
#bowtie2_dir="/path/to/bowtie2/"
genome_folder="/gscratch/scrubbed/sr320/github/project-mytilus-methylation/output/01-bismark-init/"
output_dir="/gscratch/scrubbed/sr320/github/project-mytilus-methylation/output/02-bismark-klone-array/"
checkpoint_file="/gscratch/scrubbed/sr320/github/project-mytilus-methylation/output/02-bismark-klone-array/completed_samples.log"

# Create the checkpoint file if it doesn't exist
touch ${checkpoint_file}

# Get the list of sample files and corresponding sample names
files=(${reads_dir}*_1.fastq.gz)
file=${files[$SLURM_ARRAY_TASK_ID]}
sample_name=$(basename "$file" _1.fastq.gz)

# Check if the sample has already been processed
if grep -q "^${sample_name}$" ${checkpoint_file}; then
    echo "Sample ${sample_name} already processed. Skipping..."
    exit 0
fi

# Define log files for stdout and stderr
stdout_log="${output_dir}${sample_name}_stdout.log"
stderr_log="${output_dir}${sample_name}_stderr.log"

# Run Bismark for this sample
bismark \
    -genome ${genome_folder} \
    -p 30 \
    -score_min L,0,-0.6 \
    --non_directional \
    -1 ${reads_dir}${sample_name}_1.fastq.gz \
    -2 ${reads_dir}${sample_name}_2.fastq.gz \
    -o ${output_dir} \
    > ${stdout_log} 2> ${stderr_log}

# Check if the command was successful
if [ $? -eq 0 ]; then
    # Append the sample name to the checkpoint file
    echo ${sample_name} >> ${checkpoint_file}
    echo "Sample ${sample_name} processed successfully."
else
    echo "Sample ${sample_name} failed. Check ${stderr_log} for details."
fi