#!/usr/bin/perl
use 5.010;
use strict;
use warnings;
use diagnostics;
open GENES,'genes.txt' or print "cant open genes\t";
open LOG,'log.txt' or print "cant open log\t";
open START,'start.txt' or print "cant open start\t";
open STOP,'stop.txt' or print "cant open stop\t";
open DIST,'diff.txt' or print "cant open diff";
open O,'>logratio_g0_revised_withnp.txt';
my @genes=<GENES>;
my @start=<START>;
my @stop=<STOP>;
my @log=<LOG>;
my @dist=<DIST>;
chomp @genes;
chomp @start;
chomp @stop;
chomp @log;
chomp @dist;
my $index=0;
my $index1=1;
my $ind=0;
my $in=0;
my $count=1;
do
{
	$ind=0;
	$ind1=1;
	$hit=0;
	undef @hold;
	undef @aminoacid;
	if($proteome[$index]=~m/^>/)
	{
		$val++;
		$proteome[$index] =~ /\|(.+)\|(.+)$/;
		$id=$1;
		$name=$2;
		$index++;
		print O "$name\t$id\t";
		push @hold,$proteome[$index];
		$index++;
		do
		{
			push @hold,$proteome[$index];
			$index++;
		}
		until($proteome[$index]=~m/^>/);
		$peptide= join ('', @hold);
		undef @hold;
		@aminoacid=split(//,$peptide);	
	}
		if(@aminoacid>0)
		{
		do
		{
			if($aminoacid[$ind]=~/^X$/)
			{
				$ind++;
				$ind1++;
			}
			else
			{
			if($aminoacid[$ind] eq $aminoacid[$ind1])
			{
				
				do
				{
					$hit++;
					$ind++;
					$ind1++;
					
				}
				until($aminoacid[$ind] ne $aminoacid[$ind1] or $ind==@aminoacid);
				$hit++;
				if($hit>9)
				{
					print O "$aminoacid[$ind]\t$hit\t";	
				}
				else
				{
					$hit=0;
				}
				$ind++;
				$ind1++;
				$hit=0;
			}
			else
			{
				$ind++;
				$ind1++;
			}
			}
			
			
		}
		until($ind==@aminoacid);
		undef @aminoacid;
		print O "\n";
	}		
}
until($index==@proteome);
say $val;