MJさむらいの実験室

最もクラスター数の多い順にＣＬＵＴＥＲ＿ＩＤナンバーをつけて吐き出します。


#!/usr/bin/perl -w
use strict;
use warnings;
use POSIX;


#################################################
my ($fastafile) = @ARGV;
open FASTA, "<$fastafile";
my %hash=(); # initializes a hash

while (<FASTA>)
{
 if ($_ =~ /^>/)
 {

        my $header = $_;
        $header =~ s/\s//g;
        my $read_id = $_;
      
        $hash{$header}{name}=$read_id;
        my $line = <FASTA>; 
        $hash{$header}{sequence}= $line;
 }
}
close FASTA;
#################################################


my $counter = 0;

my $name = <STDIN>;

open (FASTANAME, $name);

while (my $name_cluster = <FASTANAME>)

{

$counter = $counter + 1;

if ($counter < 10)
{print "\nCLUSTER_ID_0000$counter\n"
}elsif ($counter < 100)
{print "\nCLUSTER_ID_000$counter\n"
}elsif ($counter < 1000)
{print "\nCLUSTER_ID_00$counter\n"
}elsif ($counter < 10000)
{print "\nCLUSTER_ID_0$counter\n"
}

my @filename = split (" ", $name_cluster);

my @count = @filename;
if (@count <= 1)
{
 exit;
}



my $header1 = ">$filename[0]";
  $header1 =~ s/\s//g;

if (exists $hash{"$header1"})
  {
            print "$hash{$header1}{name}";
        print "$hash{$header1}{sequence}";
 
 
}

}
close (FASTANAME);