[Bio] / FigKernelScripts / genbank2fasta.pl Repository:
ViewVC logotype

View of /FigKernelScripts/genbank2fasta.pl

Parent Directory Parent Directory | Revision Log Revision Log


Revision 1.2 - (download) (as text) (annotate)
Fri Nov 6 19:36:49 2009 UTC (10 years ago) by redwards
Branch: MAIN
CVS Tags: mgrast_dev_08112011, mgrast_dev_08022011, rast_rel_2014_0912, myrast_rel40, mgrast_dev_05262011, mgrast_dev_04082011, rast_rel_2010_0928, mgrast_version_3_2, mgrast_dev_12152011, mgrast_dev_06072011, rast_rel_2010_0526, rast_rel_2014_0729, mgrast_dev_02212011, rast_rel_2010_1206, mgrast_release_3_0, mgrast_dev_03252011, rast_rel_2010_0118, rast_rel_2011_0119, mgrast_release_3_0_4, mgrast_release_3_0_2, mgrast_release_3_0_3, mgrast_release_3_0_1, mgrast_dev_03312011, mgrast_release_3_1_2, mgrast_release_3_1_1, mgrast_release_3_1_0, mgrast_dev_04132011, mgrast_dev_04012011, rast_rel_2010_0827, myrast_33, rast_rel_2011_0928, mgrast_dev_04052011, mgrast_dev_02222011, mgrast_dev_10262011, HEAD
Changes since 1.1: +1 -1 lines
correcting ORIGIN regexp

########################################################################
#
# Copyright (c) 2003-2006 University of Chicago and Fellowship
# for Interpretations of Genomes. All Rights Reserved.
#
# This file is part of the SEED Toolkit.
# 
# The SEED Toolkit is free software. You can redistribute
# it and/or modify it under the terms of the SEED Toolkit
# Public License. 
#
# You should have received a copy of the SEED Toolkit Public License
# along with this program; if not write to the University of Chicago
# at info@ci.uchicago.edu or the Fellowship for Interpretation of
# Genomes at veronika@thefig.info or download a copy from
# http://www.theseed.org/LICENSE.TXT.
#

use strict;
use warnings;

use FIG;
use Carp;

my $genbank = shift @ARGV;
unless ($genbank and -f $genbank) {
  print "Usage: genbank2fasta genbank_file\n";
  print ">>> extract the contigs as fasta from a genbank file and print to STDOUT.\n";
}


open(IN, "<$genbank") ||
  die "Unable to read file $genbank.";

$/ = "\n//\n";
while (defined($_ = <IN>)) {
  $_ =~ s/^\s+//os;
  last unless $_;
  
  if ($_ !~ m/LOCUS\s+(\S+)/os) {
    print STDERR "No LOCUS line for record begining with:\n"
      , substr($_, 0, 160), "\n\n";
  }
  else {
    my $id = $1;
    if ($_ =~ m/\nORIGIN[^\n]*\n(.*?)(\/\/|LOCUS)/os) {
      my $seq = $1;
      $seq =~ s/\s//ogs;
      $seq =~ s/\d//og;
      &FIG::display_id_and_seq($id,\$seq,\*STDOUT);
    }
    else {
      warn "could not find contig sequence for $id\n";
      next;
    }
  }
}

close(IN);


MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3