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

View of /FigKernelScripts/match_dna_to_aligned_prots.pl

Parent Directory Parent Directory | Revision Log Revision Log


Revision 1.4 - (download) (as text) (annotate)
Mon Dec 5 18:56:37 2005 UTC (14 years 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 1.3: +17 -0 lines
Add license words.

#
# 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.
#


$usage = "match_dna_to_aligned_prots dna_filename aligned_prot_filename";

(($dna_filename = shift @ARGV) && ($aligned_prot_filename = shift @ARGV)) ||
    die $usage;

open(DNA,"<$dna_filename") or die "failed to open dna";
open(PROT,"<$aligned_prot_filename") or die "failed to open prot";
while (defined($line = <DNA>))
{
    $line =~ />(\S+)/;
    $id = $1;
    $seq = <DNA>;
    chomp $seq;
    $dnaseqs{$id} = $seq;
}

while (defined($line = <PROT>))
{
    $line =~ />(\S+)/;
    $id = $1;
    $seq = <PROT>;
    chomp $seq;
    $protseqs{$id} = $seq;
}

# for $id (keys(%protseqs)) { print "$id $protseqs{$id}\n"; }
# for $id (keys(%protseqs)) { print "$id $protseqs{$id}\n"  if ($id =~ /1048/); }
## for $id (keys(%protseqs))
## { 
    ## $protseqs{$id} =~ /(\-+)/;
    ## $subseq=$1;
    ## # print "$id NUM ", length($subseq), $subseq, "\n"  if ($id =~ /155920.*1503/);
    ## print "$id NUM=", length($subseq), "\n";
## }

for $id (keys(%protseqs))
{
    $protseq = $protseqs{$id};
    @protseq = split('',$protseq);
    $newprotseq = '';
    for ($i=0; $i < @protseq; $i++)
    {
        $newprotseq .= "$protseq[$i]  ";
    }
    @newprotseq = split('',$newprotseq);
    $protseqs{$id} = $newprotseq;
    # print "$id $newprotseq\n"  if ($id =~ /1048/);
    $dnaseq = $dnaseqs{$id};
    $dnaidx = 0;
    $newdnaseq = '';
    for ($i=0; $i < @protseq; $i++)
    {
        $c = $protseq[$i];
        if ($c =~ /[A-Z]/)
        {
            $newdnaseq .= substr($dnaseq,$dnaidx,3);
            $dnaidx += 3;
        }
        elsif ($c eq '-')
        {
            $newdnaseq .= "---";
        }
        else
        {
            print STDERR "unrecognized char $c\n";
        }
    }
    $dnaseqs{$id} = $newdnaseq;
    # print "$id $newdnaseq\n"  if ($id =~ /1048/);
    # sanity check
    if (length($newdnaseq) != length($newprotseq))
    {
        print STDERR  "BAD LEN $id ", length($newdnaseq), " ", length($newprotseq), "\n";
    }
    $dnaid = "DNA_" . $id;
    $proid = "PRO_" . $id;
    print ">$dnaid\n$newdnaseq\n";
    print ">$proid\n$newprotseq\n";
}

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3