diff --git a/scripts/download_genomic_library.sh b/scripts/download_genomic_library.sh index f713ed3..ddf2ef1 100755 --- a/scripts/download_genomic_library.sh +++ b/scripts/download_genomic_library.sh @@ -20,6 +20,7 @@ # Download specific genomic libraries for use with Kraken. # Supported choices are: # bacteria - NCBI RefSeq complete bacterial/archaeal genomes +# plasmids - NCBI RefSeq plasmid sequences # viruses - NCBI RefSeq complete viral DNA and RNA genomes # human - NCBI RefSeq GRCh38 human reference genome @@ -49,6 +50,22 @@ case "$1" in echo "Skipping download of bacterial genomes, already downloaded here." fi ;; + "plasmids") + mkdir -p $LIBRARY_DIR/Plasmids + cd $LIBRARY_DIR/Plasmids + if [ ! -e "lib.complete" ] + then + rm -f plasmids.all.fna.tar.gz + wget $FTP_SERVER/genomes/Plasmids/plasmids.all.fna.tar.gz + echo -n "Unpacking..." + tar zxf plasmids.all.fna.tar.gz + rm plasmids.all.fna.tar.gz + echo " complete." + touch "lib.complete" + else + echo "Skipping download of plasmids, already downloaded here." + fi + ;; "viruses") mkdir -p $LIBRARY_DIR/Viruses cd $LIBRARY_DIR/Viruses @@ -97,6 +114,6 @@ case "$1" in ;; *) echo "Unsupported library. Valid options are: " - echo " bacteria virus human" + echo " bacteria plasmids virus human" ;; esac diff --git a/scripts/kraken-build b/scripts/kraken-build index fbc1d41..bf36ae6 100755 --- a/scripts/kraken-build +++ b/scripts/kraken-build @@ -40,7 +40,7 @@ my $DEF_MINIMIZER_LEN = 15; my $DEF_KMER_LEN = 31; my $DEF_THREAD_CT = 1; -my @VALID_LIBRARY_TYPES = qw/bacteria viruses human/; +my @VALID_LIBRARY_TYPES = qw/bacteria plasmids viruses human/; # Option/task option variables my ( @@ -199,7 +199,8 @@ Usage: $PROG [task option] [options] Task options (exactly one must be selected): --download-taxonomy Download NCBI taxonomic information --download-library TYPE Download partial library - (TYPE = one of "bacteria", "viruses", "human") + (TYPE = one of "bacteria", "plasmids", + "viruses", "human") --add-to-library FILE Add FILE to library --build Create DB from library (requires taxonomy d/l'ed and at least one file