PeakSnake/scripts/bam2pseudo.sh

#!/bin/bash

# Check for proper number of command line args.
if [ $# -ne 3 ]; then
    echo "Usage: $0 <input.bam> <out_prefix> <out_dir>"
    exit 1
fi

# Assign command line arguments to variables
input_bam=$1
out_prefix=$2
out_dir=$3

# Create output directory if it doesn't exist
mkdir -p "${out_dir}"

# Extract header and exclude @PG lines
samtools view -H "${input_bam}" | grep -v "^@PG" > "${out_dir}/${out_prefix}.header"

# Shuffle the reads in the BAM file to randomize
samtools view "${input_bam}" | shuf - > "${out_dir}/${out_prefix}.shuf.sam"

# Split the randomized SAM into two parts
split -n l/2 -d --additional-suffix=.sam "${out_dir}/${out_prefix}.shuf.sam" "${out_dir}/${out_prefix}_pseudo_rep"

# Add the header back to the split SAM files and convert back to BAM
for i in 00 01; do
    cat "${out_dir}/${out_prefix}.header" "${out_dir}/${out_prefix}_pseudo_rep${i}.sam" | \
    samtools view -bS - > "${out_dir}/${out_prefix}_pseudo_rep${i}.bam"
done

# Clean up intermediate files
mv ${out_dir}/${out_prefix}_pseudo_rep00.bam ${out_dir}/${out_prefix}_pseudo_rep1.bam
mv ${out_dir}/${out_prefix}_pseudo_rep01.bam ${out_dir}/${out_prefix}_pseudo_rep2.bam
rm "${out_dir}/${out_prefix}.header" "${out_dir}/${out_prefix}.shuf.sam"
rm ${out_dir}/${out_prefix}_pseudo_rep00.sam ${out_dir}/${out_prefix}_pseudo_rep01.sam

echo "Pseudo-replicate BAM files have been created: ${out_dir}/${out_prefix}_pseudo_rep1.bam and ${out_dir}/${out_prefix}_pseudo_rep2.bam"