Run BLAST as an array job using SGE (on SANBI cluster)

blastplus_array.sh

#!/bin/sh

# requirement:
# working directory with:
# in/ - files named .fasta that are query sequences
# out/ - empty directory to put outputs in
# logs/ - empty directory to put logs in 
#
# qsub with:
# qsub -t 1-2 -wd ./my-work-dir blastplus_array.sh

#$ -o logs/$JOB_NAME.o$JOB_ID.$TASK_ID
#$ -e logs/$JOB_NAME.e$JOB_ID.$TASK_ID


### -----
### define input and output directories

base_dir=`pwd`
in_dir=$base_dir/in
out_dir=$base_dir/out

cd $in_dir

### -----
### get all the file names into a file

filelist=../logs/file_list.txt
ls *.fasta > $filelist

### -----
### access the fasta files by the ${SGE_TASK_ID}

fasta=`awk "NR == ${SGE_TASK_ID} {print}" $filelist` # ${file_list[$counter]}
echo $fasta

### -----
### add the blast module and run blast

. /etc/profile.d/module.sh
module add blastplus/default

blastn -query $in_dir/$fasta -db nt -out $out_dir/$fasta.txt -outfmt "6 std slen qlen qcovs qcovhsp staxids sscinames sskingdoms" -soft_masking false -max_target_seqs 3 -evalue 10