diff --git a/exercises/Pangenome_analysis/panaroo.sh b/exercises/Pangenome_analysis/panaroo.sh index d73272fd10bbed779fc57f686e15bd21a0a6f769..ae6f9efe8c84e0ab3ba20bac15a2dbeb2e27f0fc 100644 --- a/exercises/Pangenome_analysis/panaroo.sh +++ b/exercises/Pangenome_analysis/panaroo.sh @@ -1,10 +1,12 @@ + + #!/usr/bin/env bash #SBATCH --time=02:00:00 -#SBATCH --mem-per-cpu=20G -#SBATCH --cpus-per-task=2 +#SBATCH --mem-per-cpu=64G +#SBATCH --cpus-per-task=4 #SBATCH --job-name=panaroo -#SBATCH --output=panaroo_%j.out -#SBATCH --error=panaroo_%j.err +#SBATCH --output=slurm_panaroo_%j.out +#SBATCH --error=slurm_panaroo_%j.err # Load singularity module module load singularityce @@ -12,7 +14,7 @@ module load singularityce # Declare variables # input data folder datadir= -# results folder +# results folder (03_output_mrsa) wd= # Path to singularity images folder singpath=/shares/amr.imm.uzh/bioinfo/singularity/ @@ -25,15 +27,17 @@ cd $wd mkdir -p panaroo/annotation_files mkdir -p panaroo/panaroo_output + # generate soft links to the .gff files while looping through the sample names for sample_id in "${array[@]}" do - echo $sample_id ln -s $wd/$sample_id/prokka_annotation/$sample_id.gff $wd/panaroo/annotation_files/ done # Runs singularity on the annotations and send the output to the output folder echo Starting panaroo $(date +"%T") -cd panaroo -$singpath/panaroo_1.3.0--pyhdfd78af_0.sif panaroo -i $wd/panaroo/annotation_files/*.gff -o ./panaroo_output/ --clean-mode strict --remove-invalid-genes --core_threshold +cd $wd/panaroo +$singpath/panaroo_1.3.0--pyhdfd78af_0.sif \ +panaroo -i ./annotation_files/*.gff -o ./panaroo_output/ \ +--clean-mode strict --remove-invalid-genes --core_threshold 0.95 -t $SLURM_CPUS_PER_TASK echo Done $(date +"%T") \ No newline at end of file