This file is indexed.

/usr/bin/bp_genbank2gff is in bioperl 1.6.924-3.

This file is owned by root:root, with mode 0o755.

The actual contents of the file can be viewed below.

  1
  2
  3
  4
  5
  6
  7
  8
  9
 10
 11
 12
 13
 14
 15
 16
 17
 18
 19
 20
 21
 22
 23
 24
 25
 26
 27
 28
 29
 30
 31
 32
 33
 34
 35
 36
 37
 38
 39
 40
 41
 42
 43
 44
 45
 46
 47
 48
 49
 50
 51
 52
 53
 54
 55
 56
 57
 58
 59
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
#!/usr/bin/perl 

eval 'exec /usr/bin/perl  -S $0 ${1+"$@"}'
    if 0; # not running under some shell

use lib '.';

use strict;
use warnings;
use Bio::DB::GFF;
use Getopt::Long;

=head1 NAME

bp_genbank2gff.pl - Load a Bio::DB::GFF database from GENBANK files.

=head1 SYNOPSIS

  % bp_genbank2gff.pl -d genbank -f localfile.gb
  % bp_genbank2gff.pl -d genbank --accession AP003256
  % bp_genbank2gff.pl --accession AP003256 --stdout

=head1 DESCRIPTION

This script loads a Bio::DB::GFF database with the features contained
in a either a local genbank file or an accession that is fetched from
genbank.  Various command-line options allow you to control which
database to load and whether to allow an existing database to be
overwritten.

The database must already have been created and the current user must
have appropriate INSERT and UPDATE privileges.  The --create option
will initialize a new database with the appropriate schema, deleting
any tables that were already there.

=head1 COMMAND-LINE OPTIONS

Command-line options can be abbreviated to single-letter options.
e.g. -d instead of --database.

   --create                 Force creation and initialization of database
   --dsn       <dsn>        Data source (default dbi:mysql:test)
   --user      <user>       Username for mysql authentication
   --pass      <password>   Password for mysql authentication
   --proxy     <proxy>      Proxy server to use for remote access
   --stdout                 direct output to STDOUT
   --adaptor   <adaptor>    adaptor to use (eg dbi::mysql, dbi::pg, dbi::oracle)   --viral                  the genome you are loading is viral (changes tag
                                 choices)
   --source    <source>     source field for features ['genbank']
    EITHER --file           Arguments that follow are Genbank/EMBL file names
    OR --gb_folder          What follows is a folder full of gb files to process    OR --accession          Arguments that follow are genbank accession numbers
                                 (not gi!)
    OR --acc_file           Accession numbers (not gi!) in a file (one per line,                                 no punc.)
    OR --acc_pipe           Accession numbers (not gi!) from a STDIN pipe (one
                                 per line)


=head1 SEE ALSO

L<Bio::DB::GFF>, L<bulk_load_gff.pl>, L<load_gff.pl>

=head1 AUTHOR

Scott Cain, cain@cshl.org

Copyright (c) 2003 Cold Spring Harbor Laboratory

This library is free software; you can redistribute it and/or modify
it under the same terms as Perl itself.  See DISCLAIMER.txt for
disclaimers of warranty.

=cut

package Bio::DB::GFF::Adaptor::biofetch_to_stdout;
use CGI 'escape';
use Bio::DB::GFF::Util::Rearrange;
use Bio::DB::GFF::Adaptor::biofetch;
use vars '@ISA';
@ISA = 'Bio::DB::GFF::Adaptor::biofetch';

sub load_gff_line {
  my ($self,$options) = @_;
  # synthesize GFF3-compatible line
  my @attributes;
  if (my $id = $options->{gname}) {
    my $parent = $id;
    $parent    =~ s/\..\d+$//                  if     $options->{method} =~ /^(mRNA|transcript|exon|gene)$/;
    push @attributes,"Parent=".escape($parent) if     $options->{method} =~ /^(variation|exon|CDS|transcript|mRNA|coding)$/;
    push @attributes,"ID=".escape($id)         unless $options->{method} =~ /^(exon|CDS)$/;
  }
  if (my $tstart = $options->{tstart}) {
    my $tstop    = $options->{tstop};
    my $target   = escape($options->{gname});
    push @attributes,"Target=$target+$tstart+$tstop";
  }
  my %a;
  if (my $attributes = $options->{attributes}) {
    for my $a (@$attributes) {
      my ($tag,$value) = @$a;
      push @{$a{escape($tag)}},escape($value);
    }
    for my $a (keys %a) {
       push @attributes,"$a=".join(',',@{$a{$a}});
    }
  }
  ${$options}{'score'} = "." unless ${$options}{'score'};
  ${$options}{'strand'} = "." unless ${$options}{'strand'};
  ${$options}{'phase'} = "." unless ${$options}{'phase'};
  my $last_column = join ';',@attributes;
  if ($options->{method} eq 'origin') {
     print "##sequence-region $options->{gname} $options->{start} $options->{stop}\n";
  }
  print join("\t",@{$options}{qw(ref source method start stop score strand phase)},$last_column),"\n";
}

sub load_sequence_string {
  my $self = shift;
  my ($acc,$seq)  = @_;
  return unless $seq;
  $seq =~ s/(.{1,60})/$1\n/g;
  print ">$acc\n\L$seq\U\n";
}

sub setup_load {
   my $self = shift;
   print "##gff-version 3\n";
}

sub finish_load { }

1;

package main;

my $USAGE = <<USAGE;

Usage: $0 [options] [<gff file 1> <gff file 2>] ...
Load a Bio::DB::GFF database from GFF files.

 Options:
   --create                 Force creation and initialization of database
   --dsn       <dsn>        Data source (default dbi:mysql:test)
   --user      <user>       Username for mysql authentication
   --pass      <password>   Password for mysql authentication
   --proxy     <proxy>      Proxy server to use for remote access
   --stdout                 direct output to STDOUT
   --adaptor   <adaptor>    adaptor to use (eg dbi::mysql, dbi::pg, dbi::oracle)
   --viral                  the genome you are loading is viral (changes tag
                                 choices)
   --source    <source>     source field for features ['genbank']
    EITHER --file           Arguments that follow are Genbank/EMBL file names
    OR --gb_folder          What follows is a folder full of gb files to process
    OR --accession          Arguments that follow are genbank accession numbers
                                 (not gi!)
    OR --acc_file           Accession numbers (not gi!) in a file (one per line,
                                 no punc.) 
    OR --acc_pipe           Accession numbers (not gi!) from a STDIN pipe (one
                                 per line)   


This script loads a Bio::DB::GFF database with the features contained
in a either a local genbank file or an accession that is fetched from
genbank.  Various command-line options allow you to control which
database to load and whether to allow an existing database to be
overwritten.

USAGE
;

my ($DSN,$ADAPTOR,$CREATE,$USER,$VIRAL,$PASSWORD,$gbFOLDER,
    $FASTA,$ACC,$accFILE, $accPIPE, $FILE,$PROXY,$STDOUT,$SOURCE);


GetOptions (
            'dsn:s'       => \$DSN,
            'user:s'      => \$USER,
            'password:s'  => \$PASSWORD,
            'adaptor:s'   => \$ADAPTOR,
            'accession'   => \$ACC,
            'file'        => \$FILE,
            'viral'       => \$VIRAL,
            'acc_file'    => \$accFILE,
            'acc_pipe'    => \$accPIPE,
	    'source:s'    => \$SOURCE,
            'gb_folder=s' => \$gbFOLDER,
            'proxy:s'     => \$PROXY,
            'stdout'      => \$STDOUT,
            'create'      => \$CREATE) or die $USAGE;


die $USAGE unless ($DSN || $STDOUT);  # at a minimum we need to have a place to write to!

# some local defaults
$DSN     ||= 'dbi:mysql:test';
$ADAPTOR ||= $STDOUT ? 'memory' : 'dbi::mysql';

# Ensure that biofetch inherits from the "right" adaptor.
# This is a horrible hack and should be fixed.
eval "use Bio::DB::GFF::Adaptor::${ADAPTOR}";
local @Bio::DB::GFF::Adaptor::biofetch::ISA = "Bio::DB::GFF::Adaptor::${ADAPTOR}";

my $biofetch = $STDOUT ? 'biofetch_to_stdout' : 'biofetch';
my @dsn      = $STDOUT ? () : (-dsn => $DSN);

my @auth;
push @auth,(-user=>$USER)     if defined $USER;
push @auth,(-pass=>$PASSWORD) if defined $PASSWORD;
push @auth,(-proxy=>$PROXY)   if defined $PROXY;

my %preferred_tags = (
		      strain        => 10,
		      organism      => 20,
		      protein_id    => 40,
		      locus_tag     => 50,
		      locus         => 60,
		      gene          => 70,
		      standard_name => 80,
                     );
$preferred_tags{'product'} = 90 if $VIRAL; # added this to the default list for viral genomes
       # since most functions come from post-translational processing, so the default labels are c**p!

my $db = Bio::DB::GFF->new(-adaptor=>$biofetch,
			   @dsn,
			   @auth,
			   -preferred_tags => \%preferred_tags,
			   -source=> $SOURCE || 'Genbank')
  or die "Can't open database: ",Bio::DB::GFF->error,"\n";

if ($CREATE) {
  $db->initialize(1);
}

die "you must specify either an accession to retrieve from\nembl or a local file containing data in embl format\n" if (($FILE || $ACC) && !scalar(@ARGV));

if ($ACC) {
  while ($_ = shift) {
    status(loading => $_);
    my $result = $db->load_from_embl(/^NC_/?'refseq':'embl' => $_);
    status(done    => $result);
  }
  exit 1;
}

elsif ($FILE) {
  while ($_ = shift) {
    status('loading' => $_);
    my $result = $db->load_from_file($_);
    status (done => $result);
  }
  exit 1;
}

elsif ($accFILE){
    my $filename = shift;
    die "you must supply a filename after the --accFILE command line flag\n" unless $filename;
    die "file $filename does not exist\n" unless (-e $filename && !(-d $filename));
    open my $IN, '<', $filename or die "Could not read file '$filename' for reading accession numbers: $!\n";
    while (my $line = <$IN>){
        chomp $line;
	status(loading => $line);
        my $result = $db->load_from_embl(/^NC_/?'refseq':'embl' => $line);
	status(done => $result);
    }
    close $IN;
    exit 1;
}

elsif ($gbFOLDER){
    my $dir = $gbFOLDER;
    die "folder $dir does not exist\n" unless (-e $dir && -d $dir);
    opendir DIR, "$dir" || die "can't open directory $dir for reading: $!\n";
    my @files = readdir DIR;
    foreach my $file(@files){
        if (!(-e "$gbFOLDER/$file") || (-d "$gbFOLDER/$file")){
            print STDERR " $gbFOLDER/$file is not a filename!  Skipping...\n";
            next
        }
        my $result = $db->load_from_file("$gbFOLDER/$file");
        print STDERR $result ? "ok\n" : "failed\n";        
    }
} elsif ($accPIPE){
    my @accessions = <STDIN>;
    chomp @accessions;
    foreach (@accessions){
      status(loading => $_);
      my $result = $db->load_from_embl(/^NC_/?'refseq':'embl' => $_);
      status(done => $result);
    }
    exit 1;
}

else {
  my $done;
  while ($_ = shift) {
    $done = 1;
    status(loading => $_);
    my $result = $db->load_from_file($_);
    status(done => $result);
  }

  $done || die "\n\nno source of data provided\n\n";
  exit 1;
}

sub status {
  my ($state,$msg) = @_;
  return if $STDOUT;
  if ($state eq 'loading') {
    print STDERR "Loading $msg...";
  } elsif ($state eq 'done') {
    print STDERR $msg ? "ok\n" : "failed\n";
  }
}