Updates and unpacks NCBI BLAST dbs

update_unpack_blastdbs.sh

#!/bin/bash
module use /ifs/opt/modulefiles
module load python/gcc/3.9.1
module load ncbi-blast

### About the db sources:
### - ncbi provides .tar.gz files, which need to be extracted
### - gcp and aws provide all the db files directly

logfile=/var/log/blast.log
date -u -Iseconds >> $logfile

export dbsource="ncbi"

if [[ $dbsource = "ncbi" ]]
then
    export nthreads=1
else
    export nthreads=4
fi

echo "Updating BLAST dbs from ${dbsource}; no. of threads = ${nthreads}" >> $logfile 2>&1

curl -s https://ftp.ncbi.nlm.nih.gov/blast/db/v5/README --output README
curl -s https://ftp.ncbi.nlm.nih.gov/blast/db/v5/blastdbv5.pdf --output blastdbv5.pdf
curl -s https://ftp.ncbi.nlm.nih.gov/blast/db/v5/blastdb-manifest.json --output blastdb-manifest.json

for db in $( update_blastdb.pl --showall --quiet )
do
    echo "Updating $db ..." >> $logfile 2>&1
    update_blastdb.pl --num_threads $nthreads --source $dbsource $db >> $logfile 2>&1
    retval=$?
    while [ $retval -ne 0 ]
    do
        sleep 120
        update_blastdb.pl --num_threads $nthreads --source $dbsource $db >> $logfile 2>&1
        retval=$?
    done
done

if [[ $dbsource = "ncbi" ]]
then
    for tarball in *.tar.gz
    do
        echo "Extracting ${tarball} …" >> $logfile 2>&1
        tar --no-same-owner -xvf $tarball >> $logfile 2>&1
    done
fi

chgrp urcfadm *

echo "$(date -u -Iseconds) - Done" >> $logfile