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

$outfile = "genetable.txt";
open (OUT, ">$outfile") or die "can't open file: $!";
# 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
	$name = $_;
	$name =~ s/(\[\sArabidopsis\sthaliana\s\])|(\[\sArabidopsis\s)|(\[)//;
	$name =~ s/^\d+:\s//;
	@array = split(/\s+/, $name);
	$locus_tag = @array[0];
	print OUT "$locus_tag\n \n";
	$name =~ s/^(AT\w+)|(\w+)//;
	$name =~ s/^\s//;
	print OUT "$name\n";
}
	next if /(^Function\sEvidence)|^(Process\sEvidence)|^(Component\sEvidence)|^(\d+:\s\w.+)/;
	
	if ($_ =~ /(KEGG\spathway:)|(\w+\d\d\d\d\d\s)/){ #removing "KEGG pathway" from the kegg description
		$kegg = $_,
		$kegg =~ s/^(KEGG\spathway:\s)//;
		$kegg =~ s/KEGG/ KEGG/g;
		$kegg =~ s/(KEGG\spathway:\s)//g;
		print OUT "$kegg";
}	
	else {print OUT $_;}
	
	
	
}