#!/bin/bash
#PBS -e /mnt/lustre/users/USERNAME/blastjobs/blast.stderr.out
#PBS -o /mnt/lustre/users/USERNAME/blastjobs/blast.stderr.out
#PBS -P PROGRAMMESHORTNAME
#PBS -M youremail@address
#PBS -l select=4:ncpus=24:nodetype=haswell_reg
#PBS -l walltime=00:60:00
#PBS -q normal
#PBS -m be

cd ${PBS_O_WORKDIR}

module add chpc/BIOMODULES
module add blast
module add gnu-parallel


#The module sets the env variable below
# and provides the path to the databases
#BLASTDB="/mnt/lustre/bsp/DB/BLAST"
# To blast against eg, simply use -db nt
# To see all databases, "ls $BLASTDB/*.?al"

BLASTCMD=$(which blastn)
BLASTARGS="-evalue 0.005 -num_alignments 20 -outfmt 5 -num_threads 24 -db nt"
INPUTDIRS="DATE/*"

ls ${INPUTDIRS}/*.fasta | parallel -M --sshdelay 0.2 -j 1 -u --sshloginfile ${PBS_NODEFILE} "cd ${PBS_O_WORKDIR}; ${BLASTCMD} -query {} ${BLASTARGS} -out {}.xml && gzip --best {} {}.xml"