#!/usr/bin/perl

use strict;
use warnings;

# to modify cleangene
# an infile (to be read in)and an outfile (to write to)
# and both should be open
my $infile = "clean.txt"; #output of batch entrez gene cleaned
open (IN, $infile) or die "can't open file: $!";

my $outfile = "genetable.txt";
open (OUT, ">$outfile") or die "can't open file: $!";

my $kegg_found = 0;
# reading one line at a time using the FILE handle
while (<IN>) {
	if (/^\d+:\s\w.+/) { # disecting the first line into locus tag and name
	    my $name = $_;
	    $name =~ s/\[\sArabidopsis\sthaliana\s\]|\[\sArabidopsis\s|\[//;
	    $name =~ s/^\d+:\s//;
	    my @array = split /\s+/, $name;
	    my $locus_tag = $array[0];
	    print OUT "$locus_tag\n \n";
	    $name =~ s/^AT\w+|\w+//;
	    $name =~ s/^\s//;
	    print OUT "$name\n";
    }

    if (/^Function\sEvidence/) {
    	print OUT "Unknown\n\n" unless $kegg_found;
        $kegg_found = 0;
        
    }
	next if /^Function\sEvidence|^Process\sEvidence|^Component\sEvidence|^\d+:\s\w.+/;
	
	if (/KEGG\spathway:|\w+\d{5}\s/){ #removing "KEGG pathway" from the kegg description
		my $kegg = $_;
		$kegg =~ s/^KEGG\spathway:\s//;
		$kegg =~ s/KEGG/ KEGG/g;
		$kegg =~ s/KEGG\spathway:\s//g;
		print OUT "$kegg";
        $kegg_found = 1;
    }	
	else {
        print OUT $_;
    }
}		
close OUT;
close IN;

##</code><code>##

use strict;
use warnings;

##</code><code>##

Scalar value @array[0] better written as $array[0]