merge_fastqs.sub

#!/bin/bash -x
#SBATCH --job-name="merge_fastas"
#SBATCH --account=kgidiotis
#SBATCH --cpus-per-task=5
#SBATCH --mem=100G
#SBATCH --partition=fatnodes
#SBATCH --output=/scratch/125-emmer/kostas/errors/merge_fastas_%j.out
#SBATCH --error=/scratch/125-emmer/kostas/errors/merge_fastas_%j.err
##################################################################

#Author: Konstantinos Gidiotis 
#Description: 
#	This script takes two fastq files and converts them to fasta files 
#	then they merges them using cat 

# Load Conda module (if available)
module load conda/2-4.3.21

# Initialize Conda (replace 'bash' with your shell if different)
conda init bash

#  Create and activate Conda environment
#  conda create --name my_env
source activate my_env

# fastq files from Sothern Levant of Wild Emmer wheat
FASTQ_PATH=/projects/125-emmer/free_threshing/long_read_south/TTD140/01.Data_result/ 

# Create an empty merged.fasta file
> "${FASTQ_PATH}/south_merged_fastq.fasta"

# loop through the folders 
for file in ${FASTQ_PATH}/*fastq.gz; do
    # extract basename 
    file_basename=$(basename "$file")
    
    echo "Zcat the file and seqtk"
    # unzip and convert to fasta 
    zcat "$file" | seqtk seq -A > "$file_basename".fasta
    
    echo "Merge the files"
    # Append the content to the merged.fasta
    cat "$file_basename".fasta >> "${FASTQ_PATH}/south_merged_fastq.fasta"

done 


# deactivate conda 
conda deactivate