01_Preprocessing

#!/bin/bash
#SBATCH --job-name=bwa_preprocess_job
#SBATCH --output=bwa_preprocess.out
#SBATCH --error=bwa_preprocess.err
#SBATCH --ntasks=1
#SBATCH --cpus-per-task=4
#SBATCH --mem=50G
#SBATCH --time=02:00:00
#SBATCH --partition=open


source path/to/conda.sh
conda activate processing_atac-seq

# Specify the destination directory 
DEST_DIR="/Input/Your/Directory"

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

# Navigate to the destination directory
cd "$DEST_DIR" || exit

# Download the hg38 genome
# Change to you reference genome 
echo "Downloading hg38.fa.gz..."
wget http://hgdownload.soe.ucsc.edu/goldenPath/hg38/bigZips/hg38.fa.gz

# Unzip the file
echo "Unzipping hg38.fa.gz..."
gunzip hg38.fa.gz

# Index the fasta file using BWA
echo "Indexing hg38.fa using bwa..."
bwa index hg38.fa

echo "Download, unzip, and indexing complete."