Support .gbk / .gbff [.gz] files

scripts/add_to_library.sh

@@ -24,24 +24,38 @@ set -e  # Stop on error
 
 LIBRARY_DIR="$KRAKEN_DB_NAME/library"
 
-if [ ! -e "$1" ]
+input_file=$1
+
+if [ ! -e "$input_file" ]
 then
-  echo "Can't add \"$1\": file does not exist"
+  echo "Can't add \"$input_file\": file does not exist"
   exit 1
 fi
-if [ ! -f "$1" ]
+if [ ! -f "$input_file" ]
 then
-  echo "Can't add \"$1\": not a regular file"
+  echo "Can't add \"$input_file\": not a regular file"
   exit 1
 fi
 
 add_dir="$LIBRARY_DIR/added"
 mkdir -p "$add_dir"
-scan_fasta_file.pl "$1" > "$add_dir/temp_map.txt"
 
-filename=$(cp_into_tempfile.pl -t "XXXXXXXXXX" -d "$add_dir" -s fna "$1")
+if [[ $input_file == *.gbff || $input_file == *.gbff.gz || $input_file == *.gbk || $input_file == *.gbk.gz ]]
+then
+    convert_gb_to_fa.pl $input_file > "$add_dir/temp.fna"
+    input_file="$add_dir/temp.fna"
+fi
+
+scan_fasta_file.pl "$input_file" > "$add_dir/temp_map.txt"
+
+filename=$(cp_into_tempfile.pl -t "XXXXXXXXXX" -d "$add_dir" -s fna "$input_file")
 
 cat "$add_dir/temp_map.txt" >> "$add_dir/prelim_map.txt"
 rm "$add_dir/temp_map.txt"
 
+if [ -e "$add_dir/temp.fna" ]
+then
+    rm "$add_dir/temp.fna"
+fi
+
 echo "Added \"$1\" to library ($KRAKEN_DB_NAME)"

scripts/convert_gb_to_fa.pl

@@ -0,0 +1,62 @@
+#!/usr/bin/env perl
+
+# Copyright 2013-2017, Derrick Wood <[email protected]>
+#
+# This file is part of the Kraken taxonomic sequence classification system.
+#
+# Kraken is free software: you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# Kraken is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with Kraken.  If not, see <http://www.gnu.org/licenses/>.
+
+# Pull sequence data with accession and taxid from Genbank file and output in fasta format  
+# Adapted from @tseemann https://github.com/MDU-PHL/mdu-tools/blob/master/bin/genbank-to-kraken_fasta.pl
+
+use strict;
+use warnings;
+
+@ARGV or die "Usage: $0 <file.gbk[.gz]> ...";
+
+my $wrote=0;
+my($seqid, $in_seq, $taxid);
+
+my $input_file = $ARGV[0];
+
+if ($input_file =~ /.gz$/) {
+  open(IN, "gunzip -c $input_file |") or die "can’t open pipe to $input_file";
+} else {
+  open(IN, $input_file) or die "can’t open $input_file";
+}
+
+while (<IN>) {
+  if (m/^VERSION\s+(\S+)/) {
+    $seqid = $1;
+  }
+  elsif (m/taxon:(\d+)/) {
+    $taxid = $1;
+  }
+  elsif (m/^ORIGIN/) {
+    $in_seq = 1;
+    print ">$seqid|kraken:taxid|$taxid\n";
+  }
+  elsif (m{^//}) {
+    $in_seq = $taxid = $seqid = undef;
+    $wrote++;
+  }
+  elsif ($in_seq) {
+    substr $_, 0, 10, '';
+    s/\s//g;
+    print uc($_), "\n";
+  }
+}
+
+close IN;
+