#!/opt/local/bin/perl

#    Copyright 2015 Geo Velikkakam James (geovjames@gmail.com)

#    This script was used in Simon et al. 2015.

#    This script is free software; you can redistribute it and/or modify
#    it under the terms of the GNU General Public License as published by
#    the Free Software Foundation; either version 3 of the License, or
#    (at your option) any later version.

#    This script is distributed in the hope that it will be useful,
#    but WITHOUT ANY WARRANTY; without even the implied warranty of
#    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
#    GNU General Public License for more details.

#    For a copy of the GNU General Public License see <http://www.gnu.org/licenses/>.



use Getopt::Std;

my $opt_string = 'i:m:f:';

getopt("$opt_string",\%options) or usage();
if(defined $options{i} && defined $options{m}){
	$dnafilename=$options{i};
	$motiffile=$options{m};
}else{
print "error in input \n\nUsage: perl motif.pl -i fasta_file -m motif_file\n\n Options:\nIn motif file motifs are given in each line\n-f: file format of input sequence, default is \"FASTA\". \"genebank\" is another option\n\n";
exit;
}

if(defined $options{f}){
	$format = $options{f}
}else{
	$format = "fasta";
}

unless ( open(dnafilename, $dnafilename) ) {
	print "Cannot open file \"$dnafilename\"\n\n";
	exit;
}

unless ( open(motiffile, $motiffile) ) {
        print "Cannot open file \"$motiffile\"\n\n";
        exit;
}
while (<motiffile>){
	chomp;
#	uc;
	push (@motif, uc($_)) unless (/^$/);
#	$motif_hash{$_}=0;
}
close (motiffile);
if($format =~ /fasta/i) {
	$/ = "\n>";
	@protein = <dnafilename>;
	$/= "\n";
}elsif($format =~ /genbank/i){
	@genbank = <dnafilename>;
	@protein = genbank2seq(@genbank);
#	print "\n\n the first seq: $protein[0] \n";
}



#print "@protein \n";

close (dnafilename);

my %iub2character_class = (
    
        A => 'A',
        C => 'C',
        G => 'G',
        T => 'T',
        R => '[GA]',
        Y => '[CT]',
        M => '[AC]',
        K => '[GT]',
        S => '[GC]',
        W => '[AT]',
        B => '[CGT]',
        D => '[AGT]',
        H => '[ACT]',
        V => '[ACG]',
        N => '[ACGT]',
    );



IUB_to_regexp(\@motif);


foreach $protein1 (@protein){
	
	$protein1 =~ s/>?(\w*).*\n//;
	$seq_name = $1;
	$protein1 =~ s/\n//g if($format =~/fasta/i);
	
	foreach $motif(@motif){
		$count=0;
		@position=();
		@seq=();
	    while( $protein1 =~ /$motif/ig ) {
#		push (@seq, $`);
		push(@position,length($`)+1);
		$count++;
	#exit;
 	   }
 
 	print "$seq_name\t$motif\t$count\t@position\n";
	
}
}

##########################################################################################################

sub match_positions {
    my($regexp, $sequence) = @_;
    my @positions = (  );
    while ( $sequence =~ /$regexp/ig ) {
        push ( @positions, pos($sequence) - length($&) + 1);
    }
    return @positions;
}


sub IUB_to_regexp {

    my($motif_ref) = @_;
    my $regular_expression = '';


for(my $j=0; $j<@$motif_ref; ++$j){

    for ( my $i = 0 ; $i < length(@$motif_ref[$j]) ; ++$i ) {
        $regular_expression
          .= $iub2character_class{substr(@$motif_ref[$j], $i, 1)};
    }
    @$motif_ref[$j] = $regular_expression;	
    $regular_expression = '';
}
 
}

sub genbank2seq {
	my @GenBankFile = @_ ;
	my @sequence = ();
	my $dna ="";
	my $locus ="";
foreach my $line (@GenBankFile) {
 
	if($line =~ /^LOCUS\s*(\w*)/){
		$locus = ">".$1."\n";
#		print "the locus is : ".">".$1."\n";	
		
	}     
	elsif( $line =~ /^\/\/\n/ ) { # If $line is end-of-record line //\n,
           
	    #last; #break out of the foreach loop.
	    push(@sequence, $dna);
	    $in_sequence = 0;
	    $dna = "";
	    $locus = "";
        } elsif( $in_sequence) { # If we know we're in a sequence,
	    $line =~ s/[\s0-9]//g;
            $dna .= $line; # add the current line to $$dna.
        } elsif ( $line =~ /^ORIGIN/ ) { # If $line begins a sequence,
	    if($locus) {
		$dna .= $locus;
		$in_sequence = 1; # set the $in_sequence flag.
	    }else {
		print "their is no locus name for the entry, Please check the genbank format";
		exit();
	    }
            
        } 

    }
#    print "the seq is @sequence \n";    
    return @sequence;

    # remove whitespace and line numbers from DNA sequence
    
}