Add support for the mouse (GRCm38) library

docs/MANUAL.html

@@ -154,6 +154,7 @@ <h1 id="custom-databases"><a href="#custom-databases">Custom Databases</a></h1>
 <li>plasmids: RefSeq plasmid sequences</li>
 <li>viruses: RefSeq complete viral genomes</li>
 <li>human: GRCh38 human genome</li>
+<li>mouse: GRCm38 mouse genome</li>
 </ul>
 <p>To download and install any one of these, use the <code>--download-library</code> switch, e.g.:</p>
 <pre><code>kraken-build --download-library bacteria --db $DBNAME</code></pre>

docs/MANUAL.markdown

@@ -365,6 +365,7 @@ To build a custom database:
     - plasmids: RefSeq plasmid sequences
     - viruses: RefSeq complete viral genomes
     - human: GRCh38 human genome
+    - mouse: GRCm38 mouse genome
 
     To download and install any one of these, use the `--download-library`
     switch, e.g.:

scripts/download_genomic_library.sh

@@ -23,6 +23,7 @@
 #   plasmids - NCBI RefSeq plasmid sequences
 #   viruses - NCBI RefSeq complete viral DNA and RNA genomes
 #   human - NCBI RefSeq GRCh38 human reference genome
+#   mouse - NCBI RefSeq GRCm38 mouse reference genome
 
 set -u  # Protect against uninitialized vars.
 set -e  # Stop on error
@@ -101,7 +102,7 @@ case "$1" in
       do
         wget --spider --no-remove-listing $FTP_SERVER/genomes/H_sapiens/$directory/
         file=$(perl -nle '/^-/ and /\b(hs_ref_GRCh\S+\.fa\.gz)\s*$/ and print $1' .listing)
-        [ -z "$file" ] && exit 1
+        [ -z $file ] && exit 1
         rm .listing
         wget $FTP_SERVER/genomes/H_sapiens/$directory/$file
         gunzip "$file"
@@ -112,8 +113,35 @@ case "$1" in
       echo "Skipping download of human genome, already downloaded here."
     fi
     ;;
+  "mouse")
+    mkdir -p $LIBRARY_DIR/Mouse
+    cd $LIBRARY_DIR/Mouse
+    if [ ! -e "lib.complete" ]
+    then
+      # get list of CHR_* directories
+      wget --spider --no-remove-listing $FTP_SERVER/genomes/M_musculus/
+      directories=$(perl -nle '/^d/ and /(CHR_\w+)\s*$/ and print $1' .listing)
+      rm .listing
+
+      # For each CHR_* directory, get GRCh* fasta gzip file name, d/l, unzip, and add
+      for directory in $directories
+      do
+        wget --spider --no-remove-listing $FTP_SERVER/genomes/M_musculus/$directory/
+        file=$(perl -nle '/^-/ and /\b(mm_ref_GRCm\S+\.fa\.gz)\s*$/ and print $1' .listing)
+        [ -z $file ] && exit 1
+        rm .listing
+        wget $FTP_SERVER/genomes/M_musculus/$directory/$file
+        gunzip "$file"
+      done
+
+      touch "lib.complete"
+    else
+      echo "Skipping download of mouse genome, already downloaded here."
+    fi
+    ;;
   *)
     echo "Unsupported library.  Valid options are: "
-    echo "  bacteria plasmids virus human"
+    echo "  bacteria plasmids virus human mouse"
     ;;
+
 esac

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 plasmids viruses human/;
+my @VALID_LIBRARY_TYPES = qw/bacteria plasmids viruses human mouse/;
 
 # Option/task option variables
 my (
@@ -200,7 +200,7 @@ Task options (exactly one must be selected):
   --download-taxonomy        Download NCBI taxonomic information
   --download-library TYPE    Download partial library
                              (TYPE = one of "bacteria", "plasmids", 
-                             "viruses", "human")
+                             "viruses", "human","mouse")
   --add-to-library FILE      Add FILE to library
   --build                    Create DB from library
                              (requires taxonomy d/l'ed and at least one file