#!/usr/bin/perl -w
#
# compare_sequences.pl
# A script to compare two sequences and output the position and base change at each position
#
# janet.higgins@bbsrc.ac.uk, 22/02/2011
#
# Script used to compare the cured A and C versions of the naive reference sequences
# The unigene identifier needs to be the same in both sequences
# can also be used to compare a cured sequence to the naive reference sequence
# Input the sequences to be compare as fasta files
# Outputs a list of the unigene,position within the unigene,and the base in both versions of the sequence at this position

use FileHandle;

# Hashes
my %A=();
my %C=();

# Check arguments
unless(@ARGV == 3) {
  print "Usage: compare_sequences.pl <input A_genome refseq file> <input Cgenome refseq file> <output bp change position file>\n";
  exit;
}

# Open FHs
open(A, "<$ARGV[0]") or die "Couldn't open inputA fasta file ($!)\n";
open(C, "<$ARGV[1]") or die "Couldn't open inputC fasta file ($!)\n";
open(OUT, ">$ARGV[2]") or die "Couldn't open output file ($!)\n";

#Read in genome A refseqs
print "Reading in A genome cured refseq... ";
while (<A>) {
  chomp;
  if (/^>(\S+)(.*)/) {
    ($id)= $1;
  }
  elsif (/^(\w+)$/) {
    $A{$id} .=$1;
  }
}
close A;
print "done\n";

#Read in genome C refseqs
print "Reading in C genome cured refseq... ";
while (<C>) {
  chomp;
  if (/^>(\S+)(.*)/) {
    ($id)= $1;
  }
  elsif (/^(\w+)$/) {
    $C{$id} .=$1;
  }
}
close C;
print "done\n";

foreach my $id (sort keys %A) {
  my @A = split //, $A{$id};
  my @C = split //, $C{$id};
  foreach my $pos (0 ... $#A) {
    if ( $A[$pos] ne $C[$pos]){
      print OUT "$id\t";
      print OUT "" . $pos+1 . "\t";
      print OUT "$A[$pos]\t";
      print OUT "$C[$pos]\t";
      print OUT "\n";
    }
  }
}
close OUT;