Created
May 13, 2014 03:17
-
-
Save Buttonwood/c27f8f92fd1d1932780c to your computer and use it in GitHub Desktop.
A short script for function annotation table statistics!
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#============================================================================= | |
# FileName: stat_func.pl | |
# Desc: | |
# Author: tanhao | |
# Email: tanhao2013@gmail.com | |
# HomePage: http://buttonwood.github.io | |
# Version: 0.0.1 | |
# LastChange: 2014-05-13 10:06:14 | |
# History: | |
#============================================================================= | |
use Data::Dumper; | |
#my (%cog, %kegg, %swiss, %nr, %go); | |
use Getopt::Long; | |
my ($c,$s,$n,$k,$g,$help); | |
GetOptions( | |
"cog:s" => \$c, | |
"kegg:s" => \$k, | |
"swiss:s" => \$s, | |
"nr:s" => \$n, | |
"go:s" => \$g, | |
"help:s" => \$help | |
); | |
if(defined($help) || (!defined($c) && !defined($k) && !defined($s) && !defined($n) && !defined($g))){ | |
die("Usage:\n\tperl $0 -cog cog.best -kegg kegg.best -swiss swiss.best ... \n"); | |
} | |
my %hash; | |
&hash_id($c, \%hash, 15, "COG") if($c); | |
&hash_id($k, \%hash, 15, "KEGG") if($k); | |
&hash_id($s, \%hash, 5, "SWISS") if($s); | |
&hash_id($n, \%hash, 15, "NR") if($n); | |
&hash_id($g, \%hash, 15, "GO") if($g); | |
#print Dumper(\%hash); | |
my @genes = map { $_->[0] } | |
sort{ $a->[1] <=> $b->[1] } | |
map { [$_, (split /\_/)[1]] } keys(%hash); | |
my @func = ("COG","KEGG","SWISS","NR","GO"); | |
foreach my $x (@genes){ | |
print $x; | |
foreach my $y (@func){ | |
if(exists $hash{$x}{$y}){ | |
print "\t",$hash{$x}{$y}; | |
}else{ | |
print "\t*"; | |
} | |
} | |
print "\n"; | |
} | |
sub hash_id{ | |
my ($file, $h_r, $clm, $tag) = @_; | |
open(IN,"<$file")or die("$file wrong! Plead check\n$!"); | |
while(<IN>){ | |
next if (/Query\_id/); | |
my @t = split; | |
if($clm == 5){ | |
my @a = split(/\|/, $t[4]); | |
$h_r->{$t[0]}->{$tag} = $a[1]; | |
}else{ | |
$h_r->{$t[0]}->{$tag} = $t[14]; | |
} | |
} | |
close IN; | |
} | |
########### Float like a butterfly! Stand like a buttonwood! ########### |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment