/usr/bin/bp_extract_feature_seq is in bioperl 1.6.901-3.
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 | #!/usr/bin/perl -w
eval 'exec /usr/bin/perl -w -S $0 ${1+"$@"}'
if 0; # not running under some shell
use strict;
# Author Jason Stajich <jason@bioperl.org>
=head1 NAME
extract_feature_seq - extract the corresponding sequence for a specified feature type
=head1 SYNOPSIS
extract_feature_seq.PLS -i file --format genbank --feature=CDS -o output.fa
=head1 DESCRIPTION
This script will extract the sequence for all the features you specify.
=head1 FEEDBACK
=head2 Mailing Lists
User feedback is an integral part of the evolution of this and other
Bioperl modules. Send your comments and suggestions preferably to
the Bioperl mailing list. Your participation is much appreciated.
bioperl-l@bioperl.org - General discussion
http://bioperl.org/wiki/Mailing_lists - About the mailing lists
=head2 Reporting Bugs
Report bugs to the Bioperl bug tracking system to help us keep track
of the bugs and their resolution. Bug reports can be submitted via
email or the web:
https://redmine.open-bio.org/projects/bioperl/
=head1 AUTHOR
Jason Stajich E<lt>jason-at-bioperl-dot-orgE<gt>
=cut
use Bio::SeqIO;
use Getopt::Long;
my ($input,$format,$featuretype,$output);
$featuretype ='CDS';
GetOptions(
'i|input:s' => \$input,
'format:s' => \$format,
'feature:s' => \$featuretype,
'o|output:s'=> \$output);
$input || shift if @ARGV;
my $in = new Bio::SeqIO(-file => $input,
-format => $format);
my $out;
if ($output ) {
$out = new Bio::SeqIO(-file => ">$output");
} else {
$out = new Bio::SeqIO(); # use STDOUT for output
}
my $count = 1;
while( my $seq = $in->next_seq ) {
foreach my $f ( grep { $_->primary_tag =~ /$featuretype/i }
$seq->get_SeqFeatures ) {
my $s = $f->spliced_seq;
if( $featuretype =~ /gene|CDS/ ) {
$s->display_id($f->has_tag('gene') ? join(',',sort $f->each_tag_value('gene')) :
$f->has_tag('label') ? join(',',$f->each_tag_value('label')):
$s->display_id);
} else {
$s->display_id(sprintf("%s_%s_%d",
$seq->display_id,
$f->primary_tag,
$count++));
}
$out->write_seq($s);
}
}
__END__
|