diff --git a/exercises/Pangenome_analysis/panaroo.sh b/exercises/Pangenome_analysis/panaroo.sh new file mode 100644 index 0000000000000000000000000000000000000000..109fc6b1c76e305db81b92d07de1fd0d57ceb96a --- /dev/null +++ b/exercises/Pangenome_analysis/panaroo.sh @@ -0,0 +1,30 @@ +#!/usr/bin/env bash +#SBATCH --time=02:00:00 +#SBATCH --mem-per-cpu=20G +#SBATCH --cpus-per-task=2 +#SBATCH --job-name=panaroo +#SBATCH --output=panaroo_%j.out +#SBATCH --error=panaroo_%j.err + +module load singularityce + +datadir= +wd= +singpath=/shares/amr.imm.uzh/bioinfo/singularity + +array=($(ls $datadir | cut -f 1 -d '_' | uniq)) + +cd $wd +mkdir -p panaroo/annotation_files +mkdir -p panaroo/panaroo_output + +# gff file soft links +for sample_id in "${array[@]}" +do + ln -s $wd/$sample_id/prokka_annotation/$sample_id.gff $wd/panaroo/annotation_files/ +done + +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 +echo Done $(date +"%T") \ No newline at end of file