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

View of /FigKernelScripts/reformat_fasta.pl

Parent Directory Parent Directory | Revision Log Revision Log


Revision 1.2 - (download) (as text) (annotate)
Mon Dec 5 18:56:38 2005 UTC (13 years, 11 months ago) by olson
Branch: MAIN
CVS Tags: mgrast_dev_08112011, rast_rel_2009_05_18, mgrast_dev_08022011, rast_rel_2014_0912, rast_rel_2008_06_18, myrast_rel40, rast_rel_2008_06_16, mgrast_dev_05262011, rast_rel_2008_12_18, mgrast_dev_04082011, rast_rel_2008_07_21, rast_rel_2010_0928, rast_2008_0924, mgrast_version_3_2, mgrast_dev_12152011, rast_rel_2008_04_23, mgrast_dev_06072011, rast_rel_2008_09_30, rast_rel_2009_0925, rast_rel_2010_0526, rast_rel_2014_0729, mgrast_dev_02212011, rast_rel_2010_1206, caBIG-05Apr06-00, mgrast_release_3_0, mgrast_dev_03252011, rast_rel_2010_0118, mgrast_rel_2008_0924, mgrast_rel_2008_1110_v2, rast_rel_2009_02_05, rast_rel_2011_0119, mgrast_rel_2008_0625, 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, rast_rel_2008_10_09, mgrast_dev_04012011, rast_release_2008_09_29, mgrast_rel_2008_0806, mgrast_rel_2008_0923, mgrast_rel_2008_0919, rast_rel_2009_07_09, rast_rel_2010_0827, mgrast_rel_2008_1110, myrast_33, rast_rel_2011_0928, rast_rel_2008_09_29, mgrast_rel_2008_0917, rast_rel_2008_10_29, mgrast_dev_04052011, mgrast_dev_02222011, caBIG-13Feb06-00, rast_rel_2009_03_26, mgrast_dev_10262011, rast_rel_2008_11_24, rast_rel_2008_08_07, HEAD
Changes since 1.1: +17 -0 lines
Add license words.

# -*- perl -*-
#
# 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 FIG;

use Pod::Text;
# use File::Basename;   $this_tool_name = basename($0);
if ((@ARGV == 1) && ($ARGV[0] =~ m/-help/))  {
    pod2text($0);  exit(0);
}

=pod

=over 5

=item Usage:     reformat_fasta_file  < fasta_in  > fasta_out

=item Function:  Reformats a fasta file to a uniform 60 chars per line.

=back

=cut

if ($ARGV[0] =~ m/-strip/) { $strip = shift; }

if ($ARGV[0] && (-e $ARGV[0]))
{
    open(FIN, "<$ARGV[0]") or die "could not open $ARGV[0] as input";
    $fin = \*FIN;
}
else
{
    $fin = \*STDIN;
}

if ($ARGV[1])
{
    open(FOUT, ">$ARGV[1]") or die "could not open $ARGV[1] as output";
    $fout = \*FOUT;
}
else
{
    $fout = \*STDOUT;
}



while ( (! eof($fin)) && ( ($head, $seq) = &get_a_fasta_record($fin) ) )
{
    if ($strip) { $head =~ m/^(\S+)/;  $head = $1; }
    
    &display_id_and_seq( $head, \$seq, $fout );
}


sub get_a_fasta_record
{
    my ($fh) = @_;
    my ( $old_eol, $entry, @lines, $head, $id, $seq ); 

    $old_eol = $/;
    $/ = "\n>";
    
    if (! defined($fh))  { $fh = \*STDIN; }
    
    $entry = <$fh>;
    chomp $entry;
    @lines =  split( /\n/, $entry );
    
    $head  =  shift @lines;
    $head  =~ s/^>?//;
    $head  =~ m/(\S+)/;   $id = $1;
    
    $seq   =  join( "", @lines );
    $seq   =~ s/\s//g;
    $seq   =~ s/\*$//;
    
    my $tmp = $seq;
    if (($tmp =~ s/[ARNDCQEGHILKMFPSTWYUVBZX]//ig) && $tmp)
    {
	print STDERR "$id has invalid chars: $tmp\n";
	$seq  =~ s/[^ARNDCQEGHILKMFPSTWYUVBZX]/x/ig;
    }
    
    $/ = $old_eol;
    return ( $head, $seq );
}


sub display_id_and_seq {
    my( $id, $seq, $fh ) = @_;
    my ( $i, $n, $ln );
    
    if (! defined($fh) )  { $fh = \*STDOUT; }
    
    print $fh ">$id\n";
    
    $n = length($$seq);
#   confess "zero-length sequence ???" if ( (! defined($n)) || ($n == 0) );
    for ($i=0; ($i < $n); $i += 60)
    {
	if (($i + 60) <= $n)
	{
	    $ln = substr($$seq,$i,60);
	}
	else
	{
	    $ln = substr($$seq,$i,($n-$i));
	}
	print $fh "$ln\n";
    }
}

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3