Standardize GeneBank Fasta Format

StandardizeGeneBankFaFormat.pl

#!/usr/bin/perl -w

use strict;

my $f = shift; # input fasta file download from batch Entrez (http://www.ncbi.nlm.nih.gov/sites/batchentrez)
open IN,"$f" || die $!;
$/ = ">"; <IN>; $/ = "\n";
while(<IN>){
	chomp;
	my $id = $_;
	# replace "gi|634859302|gb|KJ524455.1|" > "gi_634859302|gb|KJ524455.1|"
	$id =~ s/^(gi\|)/gi_/g;
	
	# replace "gi_634859302|gb|KJ524455.1|" > "gi_634859302 KJ524455.1|"
	# you can add more things to this part
	$id =~ s/(\|gb\|)/ /g;
	$id =~ s/(\|ref\|)/ /g;
	$id =~ s/(\|dbj\|)/ /g;
	
	# replace "gi_634859302 KJ524455.1|" > "gi_634859302 KJ524455.1"
	$id =~ s/(\|) / /g;
	
	# get seq
	$/ = ">";
	my $seq = <IN>;
	chomp($seq);
	$seq =~ s/\n//g;
	$/ = "\n";
	
	# stdout
	print ">$id\n$seq\n";
}
close IN;