计算蛋白质一致率

#!/usr/bin/perl

use strict;
use warnings;

my $input = $ARGV[0];my $name = $ARGV[1];my $start = $ARGV[2];my $cut_start=$ARGV[3];my $cut_end=$ARGV[4]; 

my $all_start=$ARGV[5];my $all_end =$ARGV[6];

my $cut = &store ($input);my %cut = %$cut;

my ($list,$average) = &count(%cut);

print "$name\t$list\t$average\t$cut_start\t$cut_end\t$all_start\t$all_end\n";

#####sub########

sub count{
    
    my %cut = @_;
    
    my @arr;my @all;
    
    foreach my $key(keys %cut)
    {
        my $long = $cut{$key};my @split = split //,$long;
        
        push @arr,[@split];
    }
    
    my $i=0;my $j=0;

    for($j=0;$j<10;$j++)
    {
        my %list;        
        
        for($i=0;$i<$#arr+1;$i++)
        {
            $list{$arr[$i][$j]}++; 
        }
        
        my $key = (sort {$list{$b} <=> $list{$a}} keys%list)[0];
        
        my $max = $key eq '-'?0:$list{$key};
        
        my $rate = $max/($#arr+1);
        
        $all[$j]=sprintf "%.2f",$rate;
    }
    
    my $list = join("|",@all);

    my $sum =0;
    
    foreach(@all)
    {
        $sum += $_;
    }
    
    my $average = $sum/10;  
    
    return $list,$average;
}

sub store{
    
    open FA,$input;

    my @arr;

    my $id;

    my %cut;

    while(my $line = <FA>)
    {
        chomp $line;

        if($line =~ />(\w*)/)
        {
            $id = $1;
        }
        else
        {
            $cut{$id} = substr ($line,$start-1 ,10);
        }
    }
    return \%cut;
}