Skip to content

Commit

Permalink
SRR_first
Browse files Browse the repository at this point in the history
  • Loading branch information
uqsdemon committed Aug 28, 2024
0 parents commit 11ed909
Show file tree
Hide file tree
Showing 12 changed files with 6,093 additions and 0 deletions.
1,585 changes: 1,585 additions & 0 deletions SRR.error

Large diffs are not rendered by default.

1,611 changes: 1,611 additions & 0 deletions SRR.out

Large diffs are not rendered by default.

759 changes: 759 additions & 0 deletions SRRIDS/bam_ids.txt

Large diffs are not rendered by default.

1,611 changes: 1,611 additions & 0 deletions SRRIDS/fastq_ids.txt

Large diffs are not rendered by default.

69 changes: 69 additions & 0 deletions convert.sh
Original file line number Diff line number Diff line change
@@ -0,0 +1,69 @@
#!/usr/bin/bash

# load modules
module load sra-tools
module load samtools

help(){
echo "Usage: use this script to convert SRA files to fastq or bam"
echo
echo "Options :"
echo " -b : convert to bam file. "
echo " -q : convert to fastq file. "
echo " -h : show this help message and exit"
echo
echo " dont forget to change the output directory inside the script"
echo "if not the output will be ./"
exit 1
}

# change your own path here
destination="./"

conversion_type=""

while getopts "bq:h" op; do
case $op in
q)
conversion_type="fastq"
;;
b)
conversion_type="bam"
;;
h)
help
;;
\?)
echo "wrong operator: -$OPTARG" >&2
help
;;
esac
done

if [ -z "$conversion_type" ]; then
echo " you need to specify a conversion option: -q or -b"
help
fi

find . -name "*.sra" -exec mv {} $destination \;

for sra_file in $destination*.sra; do
echo "running $sra_file..."

base_name=$(basename "$sra_file" .sra)

case $conversion_type in
fastq)
echo "conversion of $sra_file in fastq...."
fastq-dump.3 --ngc a.ngc "$sra_file"
;;
bam)
echo "conversion of $sra_file in bam....."
sam_dump.3 --ngc a.ngc $sra_file | samtools view -bS - > "${base_name}.bam"
;;
esac

done

echo "treatment's over"

62 changes: 62 additions & 0 deletions fastqfetch.sh
Original file line number Diff line number Diff line change
@@ -0,0 +1,62 @@
#!/usr/bin/bash
help(){
echo "this script is going to download the SRA files from a sra list provided after sorting the id from a sra table"
echo "and place them inside of a new folder"
echo "no argument is needed"
echo
echo " this script is functioning if the table file has a header"
echo " if not, just change the done by the one behind a #"
exit 1
}
# Add sratoolkit to PATH
export PATH="/scratch/user/uqsdemon/ApplicationGNN/gnnenvo/bin/sratoolkit.3.1.1-ubuntu64/bin:$PATH"

# Charger les modules nécessaires (if still required)
module load sra-tools
module load samtools

# Chemin du fichier contenant les identifiants SRR
fastq_ids_file="/scratch/user/uqsdemon/rnewbashscriptvf/SRRIDS/fastq_ids.txt"
# Liste des identifiants à exclure
exclude_ids_file="/scratch/user/uqsdemon/rnewbashscriptvf/filedone.txt"
outputpath="/QRISdata/Q7361/SRRIDS/fastqfilesncbi"
keypath="/scratch/user/uqsdemon/rnewbashscriptvf/prj_33410_D38764.ngc"

# Vérifiez que sra-tools est chargé correctement
if ! command -v fasterq-dump &> /dev/null; then
echo "fasterq-dump could not be found. Please check your sratoolkit installation and PATH."
help
fi

if [ ! -f "$fastq_ids_file" ]; then
echo "Error: the file with sra ids does not exist."
help
fi

if [ ! -f "$keypath" ]; then
echo "Erreur : le fichier NGC n'existe pas au chemin spécifié."
help
fi

# Charger les identifiants à exclure dans un tableau
mapfile -t exclude_ids < "$exclude_ids_file"

temp_path="/QRISdata/Q7361/temp"

# Assurez-vous que le répertoire temporaire existe
mkdir -p "$temp_path"

# Lire chaque ligne du fichier fastq_ids.txt
while read -r srr_id; do
# Vérifier si l'identifiant est dans la liste des exclusions
if printf '%s\n' "${exclude_ids[@]}" | grep -qx "$srr_id"; then
echo "Skipping excluded ID: $srr_id"
continue
fi
echo "Téléchargement et conversion de $srr_id en format fastq depuis NCBI..."
# Télécharger et convertir le fichier SRA en fichiers fastq
mkdir -p "$outputpath/$srr_id"
fasterq-dump --ngc "$keypath" --split-files "$srr_id" -O "$outputpath/$srr_id" --temp "$temp_path"
done < "$fastq_ids_file"

echo "download over"
Loading

0 comments on commit 11ed909

Please sign in to comment.