#!/usr/bin/perl  

#Program to convert information in EMBL format to 
#the format of the MalariaDB .ace files format.

($#ARGV>=0) || die
   "usage: embl2ace [-D] [-o <output_filename>] <filename>
    if -D is presented, the ace file created will have \"-D <Class>: id\" line
    proceeded to each object \"<Class>: id\", as the \"-D\" flag of ACeDB;
    use - for standard input;
    the default output is on the screen;
    options must be given in the order shown above\n";

if ($ARGV[0] =~ /^-D$/) 
{	$VAR_D = 1;
	shift 
}
else {  $VAR_D = 0 };

if ($ARGV[0] =~ /^-o$/)
{       shift;
        # set the filehandle for output as $ARGV[0]
        open(OUTPUT, ">$ARGV[0]");     
        select(OUTPUT);       
        shift
};

#Define EMBL_feature key names

@key_names = ("TATA_signal","allele_seq","conflict","mat_peptide",
"misc_binding","misc_signal","misc_feature","misc_recomb","modified_base",
"mutation","old_sequence","polyA_site","polyA_signal","prim_binding",
"prim_transcript","promoter","repeat_region","repeat_unit","satellite",
"sig_peptide","variation","enhancer","protein_bind","stem_loop",
"primer_bind","transit_peptide","misc_structure","precursor_RNA",
"terminator","INTRON","EXON");

#Define sub sequence key names

@RNA_keys =("CDS","mRNA","tRNA","rRNA","snRNA","scRNA","misc_RNA");

SCAN:
while (<>)
{    
	next SCAN if /^\s*$/;			# skip blank lines.
	next SCAN if /^XX/;			# skip XX lines
        next SCAN if /^KW\s+\.\s*$/;            # skip empty KW line
        next SCAN if /^OC\s+\.\s*$/;            # skip empty OC line

        if (/^\/\//)				# // lines
	{		
	    # output (last) entry details.
	    &output_entry_details if ($VAR_id);

	    next SCAN
	};

# Extract Sequence name, DNA/RNA, and Sequence length
# from: ID   $VAR_id	standard; XNA; EST; $VAR_length BP.
	if (/^ID/) 
	{ 
		# start of an entry, initialize variables.
		&variables_initialisation;

		# split;	# does not work in Perl5
		@ID_elements = split(';', $_);
		@ID_initials = split(' ', $ID_elements[0]);

		$VAR_id = $ID_initials[1];
		$VAR_id .= ' (EMBL)';    

		$VAR_cDNA = "cDNA" if ($ID_elements[1] =~ /RNA/);  

		# $1 refers to the part matching [0-9]*
		$VAR_length = $ID_elements[3] if ($_ =~ /([0-9]+) BP/); 
		$VAR_length =~ s/[^0-9]//g;
		$VAR_int_length = &strtoint($VAR_length); 

		next SCAN
	};

# Extract Accession number(s).
	if (/^AC\s+(.+)/) 
	{       
		chop;
		$_ =~s/^AC   //;
		# Accession numbers are seperated by \s.
		$VAR_temp_accessions = $_;
		while (<>){
			if (/^AC\s+(.+)/) {
				chop;
				$_ =~ s/^AC   //;
				$VAR_temp_accessions .= " ";
				$VAR_temp_accessions .= $_;
			} else { last }
		}
		$VAR_temp_accessions =~ s/;//;
		if ($VAR_temp_accessions =~ /\s/){
		    @VAR_accession = split(" ", $VAR_temp_accessions); 
		} else { $VAR_accession[0] = $VAR_temp_accessions; }
		#We now have an array, @VAR_accession, of Accession numbers.

		redo SCAN;
	};

# Extract keywords
	if (/^KW\s+(.+)/)
        {
                if ($VAR_keywords) {
                        $VAR_keywords .= " $1" }
                else {  $VAR_keywords  = $1};

                $VAR_keywords =~ s/\.\s*$//g;      # remove trailing "." if any

                next SCAN
        };



	if (/^DT   ([^\s]*)\s*/)
	{	
		$temp_temp_date = $1;
		
		if ($_ =~ /Created/i){
			$VAR_entry_date = &EMBLdate2ACEdate($temp_temp_date);
    		} else {
			$VAR_modification_date = &EMBLdate2ACEdate($temp_temp_date);
		}
	};

# Extract Sequence remark.
	if (/^DE\s+(.+)/)
	{
		chop;
		$_ =~s/^DE   //;
		$VAR_description = $_;
		while (<>){
			if (/^DE\s+(.+)/) {
				chop;
				$_ =~s/^DE   //;
				$VAR_description .= " " . $_;
			} else { last }
		}
		redo SCAN;
		
	};

		
        if (/^OS\s+(.+)/)
	{
		next SCAN
	};

	if (/^OC\s+(.+)/)
	{
		next SCAN
	};


# Extract database remark.
	if (/^CC\s+(.+)/)
	{
		chop;
		$_ =~ s/^CC   //;
		$VAR_db_remark = $_;
		while (<>){
			if (/^CC\s+(.+)/) {
				chop;
				$_ =~s/^CC   //;
				$VAR_db_remark .= " ";
				$VAR_db_remark .= $_;
			} else { last }
		}
		redo SCAN;
	};

# Extract EMBL features.
        if (/^FT\s{3}/ )
        {   
		# We grab the source information for organism, clone, 
		# and strain names.
		if (/^FT\s{3}source/){
		   chop;
		   $VAR_source_info[$VAR_source_index] = $_;
		   $VAR_source_info[$VAR_source_index] =~ s/^FT\s{3}source\s*//g;
		   while(<>){
			if (/^FT\s{3}\s+/){
		            chop;
			    $_ =~ s/^FT\s*//g;
			    $_ =~ s/"/'/g;
			    $VAR_source_info[$VAR_source_index] .= " ";
			    $VAR_source_info[$VAR_source_index] .= $_;
		        } else { last }
	           }
		   $VAR_source_index += 1;
		   redo SCAN;
	        }

		# Check for sub sequence
		foreach $key(@RNA_keys){
		 if (/^FT\s{3}$key/){
		   chop;
		   $_ =~ s/^FT\s{3}$key\s*//g;
		   $_ =~ s/"/'/g;
		   $VAR_RNA{$key} .= $_;
		   while(<>){
			if (/^FT\s{3}\s+/){
		            chop;
			    $_ =~ s/^FT\s*//g;
			    $_ =~ s/"/'/g;
			    $VAR_RNA{$key} .= "\"";
			    $VAR_RNA{$key} .= " ";
			    $VAR_RNA{$key} .= $_;
		        } else { last }
	           }
		   $VAR_RNA{$key} .= "\"\"";
		   # such that lines are seperated by "
		   # and subsequences are seperated by ""
		   redo SCAN;
		 }
		}

		# Check for EMBL_feature
		foreach $key(@key_names){
		  if (/^FT\s{3}$key/){
		    chop;
		    $_ =~ s/"/'/g;
		    $_ =~ s/^FT\s{3}$key\s*//g;
		    $VAR_EMBL_feature{$key} .= $_;
		    while(<>){
                        if (/^FT\s{3}\s+/){
                            chop;
			    $_ =~ s/^FT\s*//g;
			    $_ =~ s/"/'/g;
		    	    $VAR_EMBL_feature{$key} .= "\"";
			    $VAR_EMBL_feature{$key} .= " ";
			    $VAR_EMBL_feature{$key} .= $_;	
			} else { last }
                    }
		    $VAR_EMBL_feature{$key} .= "\"\"";
		    # such that lines are seperated by "
                    # and features are seperated by ""
		    redo SCAN;
		  }
		}
			
	};

# Extract the DNA sequence.
	if (/^SQ\s+Sequence\s+(.+)/)
	{
		$VAR_sequence = "";
		while (<>)
                {
			if (/^\s\s\s\s\s/){
				$_ =~ s/\s//g;
				$_ =~ s/[0-9]//g;
				$VAR_sequence .= "\n";
				$VAR_sequence .= $_;
			} else { last }
			$VAR_sequence =~ s/\*//g;
		}
		redo SCAN;
	};
				

# Extract the references.
       if (/^RN\s+/)
       { 
	$_ =~ s/RN   \[//;
	$_ =~ s/]\s*//;
	
	$VAR_ref_num += 1;
	$VAR_authors[$VAR_ref_num] = "";
	$VAR_title[$VAR_ref_num] = "";
	$VAR_journal[$VAR_ref_num] = "";		
	$VAR_medline[$VAR_ref_num] = "";


   REFERENCE_BLOCK:
	while(<>)
	{
		next REFERENCE_BLOCK if (/^XX\s+/);
		next REFERENCE_BLOCK if (/^RP\s+/);
		next REFERENCE_BLOCK if (/^RC\s+/);



		if (/^RX   MEDLINE;\s*([0-9]*)[^0-9]/)
			{  	
			# medline account
			$medline = $1;
			$VAR_medline[$VAR_ref_num] = $medline;
			next REFERENCE_BLOCK
		}

		if (/^RA\s+(.+)/)
			{  	
			# authors
			$_ =~ s/^RA   //;
			$_ =~ s/,\s*\n$/,/;
			$_ =~ s/;\s*\n$//;
			$_ =~ s/\s*\n$//;
			$VAR_author[$VAR_ref_num] .= " $_";
			next REFERENCE_BLOCK
		}

		if (/^RT\s+(.+)/)
		{	

			# Title
			$_ =~ s/^RT   //g;
			chop;
                       	$VAR_title[$VAR_ref_num] = $_;

  
                  	   # continue RT line ...
                       	while(<>)
                       	{   
			    if (/^RT\s+(.+)/) {
				$_ =~ s/^RT   //g;
				chop;
                       		$VAR_title[$VAR_ref_num] .= " $_";
                            } else { last  }
                       	};

		        $VAR_title[$VAR_ref_num] =~ s/\"//g;	       # remove "
			$VAR_title[$VAR_ref_num] =~ s/\s{2,}/ /g;      # single space
			$VAR_title[$VAR_ref_num] =~ s/;\s*$//g;     # remove last ";".
			$VAR_title[$VAR_ref_num] =~ s/^The //;      # remove "The" 
							 # ("WashU-Merck EST Project" = "The WashU-Merck EST Project")
                
			redo REFERENCE_BLOCK
		};

		if (/^RL\s+(.+)/)
		{
			$_ =~ s/RL   //;
			chop;
			$VAR_journal[$VAR_ref_num] = $_;
                       	while(<>)
                       	{   
			    if (/^RL\s+(.+)/) {
				$_ =~ s/^RL   //g;
				chop;
                       		$VAR_journal[$VAR_ref_num] .= " $_";
                            } else { last  }
                       	};
			
                       	redo REFERENCE_BLOCK
               	};


		last REFERENCE_BLOCK

	};   # end of REFERENCE_BLOCK

	redo SCAN 

};  # end of RN blocks.
};


#-------------------------------------------------------------------
# SUBROUTINE: VARIABLES_INITIALISATION
#
# Before processing an EMBL entry, initialise variables.
#-------------------------------------------------------------------
sub variables_initialisation
{
	$VAR_entry_date = "";  #Sequence entry date.
	$VAR_modification_date = ""; #Sequence modification date.
        $VAR_id = "";          # Sequence name.
        $VAR_cDNA = "";        # ie. RNA, not DNA.
        $VAR_length = "";      # Sequence length(char).
        $VAR_int_length = 0;   # Sequence length(int).
        $VAR_keywords = "";    # Sequence keywords.
	$VAR_ref_num = 0;      # Reference enumerator.
	$VAR_temp_accessions = ""; # Accession numbers seperated by \s.
	@VAR_author = ();      # Authors seperated by ',' /reference.
	@VAR_journal = ();     # Journal / reference.
	@VAR_title = ();       # Title of Paper / reference 
			       # (= "" if Paper unpublished).
	@VAR_medline = ();     # Medline ID / reference.
	@VAR_accession = ();   # Accession numbers / reference.	
	$VAR_description = ""; # Seqence Title.
	$VAR_db_remark = "";   # Seqence DB_remark.
	$VAR_source_index = 0; # Index for EMBL FT   source.
	@VAR_source_info = (); # Source information / source.
	$VAR_keywords = "";    # Seqence Keyword.
	$VAR_gene = "";        # Sequence Locus.

	foreach $key(@RNA_keys){
		$VAR_RNA{$key} = "";  # Sequence Subsequences.
	}
	
	foreach $key(@key_names){
		$VAR_EMBL_feature{$key} = "";  # Sequence EMBL_features.
	}



};

#-------------------------------------------------------------------
# SUBROUTINE: OUTPUT_ENTRY_DETAILS
# Note: Output detail information on current sequence entry.
#       Variables referred are global variables.
#-------------------------------------------------------------------
sub output_entry_details {
	local($i, $j);



	# First, print out main sequence object
	$VAR_id_num = $VAR_id;
	$VAR_id_num =~ s/ \(EMBL\)$//;
	print "\n-D Sequence : \"$VAR_id\"\n\n" if ($VAR_D);
	print "Sequence : \"$VAR_id\"\n";
	print "DNA \"$VAR_id\" $VAR_length\n";
	print "Title \"$VAR_description\"\n";
	print "Entry_date $VAR_entry_date\n";
	print "Modification_date $VAR_modification_date\n";
	print "Database \"EMBL\" \"$VAR_id\" \"$VAR_accession[0]\"\n";
	print "DB_remark \"$VAR_db_remark\"\n";
	# Extract clone, strain, and/or organism name from Feature source.
	foreach $source_trait (@VAR_source_info){
		if ($source_trait =~ /\/clone='([^']*)'/i){
			$VAR_clone = $1;
			print "Clone \"$VAR_clone\"\n";
		}
		if ($source_trait =~ /\/strain='([^']*)'/i){
			$VAR_strain = $1;
			print "Strain \"$VAR_strain\"\n";
		}
		if ($source_trait =~ /\/organism='([^']*)'/i){
			$VAR_organism = $1;
			print "Organism \"$VAR_organism\"\n";
		}
	}
	if ($VAR_keywords)
        {   $VAR_keywords =~ s/\"/'/g;
            @VAR_keyword = split(/;\s*/, $VAR_keywords);
            for ($i = 0; $i <= $#VAR_keyword; $i++)
            { print "Keyword \"$VAR_keyword[$i]\"\n" };
        }
	# Establish reference to Subsequence.
	foreach $key(@RNA_keys){
		@ARR_RNA = split('""', $VAR_RNA{$key});
		# Giving us an array of subsequences of a particulr type.
		$i = 1;
		foreach $temp_ARR_RNA (@ARR_RNA){
			# For each subsequence find and print
			# subsequence name, from-base, and to-base.
	        	@Inner_ARR_RNA = split('"', $temp_ARR_RNA);
			$subseq = $Inner_ARR_RNA[0];
			$subseq =~ s/[^0-9]/ /g;
			if ($subseq =~ /^\s*([0-9]+)\s+([0-9]*|\s*)\s+([0-9]+)\s*$/){
				$first_val = $1;
 				$second_val = $3;
			}
			print "Subsequence  \"$VAR_id_num:$key.$i (EMBL)\" $first_val $second_val\n";
			$i++;
		}
	} 	
	# Extract EMBL features.
	foreach $key(@key_names){
		$temp_VAR_EMBL_feature = $VAR_EMBL_feature{$key};
		@VAR_EMBL_unit = split('""', $temp_VAR_EMBL_feature);
		# Giving us an array of features of a particulr type.
		foreach $VAR_EMBL_text(@VAR_EMBL_unit){
			@VAR_EMBL_info = split('"', $VAR_EMBL_text);
			# Establish reference to sequence bases.
			$VAR_EMBL_val = $VAR_EMBL_info[0];
			$VAR_EMBL_val =~ s/[^0-9]/ /g;	
			if ($VAR_EMBL_info[0] !~ /REPLACE/){
			   if ($VAR_EMBL_val =~ /^\s*([0-9]+)\s+([0-9]*\s+)*([0-9]+)\s*$/){
				$VAR_EMBL_one = $1;
				$VAR_EMBL_two = $3;
				print "$key $VAR_EMBL_one $VAR_EMBL_two ";
				$VAR_EMBL_tag = "$key $VAR_EMBL_one $VAR_EMBL_two ";
			    } else {
				print "$key 1 $VAR_length "; 	
				$VAR_EMBL_tag = "$key 1 $VAR_length ";
			    }
			} else {
				print "$key 1 $VAR_length ";
				$VAR_EMBL_tag = "$key 1 $VAR_length ";
			}	
			$location = $VAR_EMBL_info[0];
			$note = "";
			$product = "";
			$text = "";
			$i = 1;
			# Find Sequence EMBL_feature #EMBL_info. 
			while ($i <= $#VAR_EMBL_info){
			    if ($VAR_EMBL_info[$i] =~ /^\s*\/gene='([^']*)'/i){
	  			$VAR_gene = $1;
			        $i++;
			    } elsif ($VAR_EMBL_info[$i] =~ /^\s*\/note/i){
	  			$note = $VAR_EMBL_info[$i];
				if ($VAR_EMBL_info[$i] !~ /[^']*'[^']*'[^']*/){
	  			     while ($VAR_EMBL_info[++$i] !~ /[^']*'[^']*/){
					$note .= $VAR_EMBL_info[$i];
				     }
				     $note .= $VAR_EMBL_info[$i];
				}
			        $i++;
			    } else {
				if ($VAR_EMBL_info[$i] =~ /^\s*\/product/i){
				   $product = $VAR_EMBL_info[$i];
                                   if ($VAR_EMBL_info[$i] !~ /[^']*'[^']*'[^']*/){ 
                                     while ($VAR_EMBL_info[++$i] !~ /[^']*'[^']*/){
					$product .= $VAR_EMBL_info[$i];
				     }
				     $product .= $VAR_EMBL_info[$i];
				   }
				   $i++;
				} else {
			           $text .= $VAR_EMBL_info[$i];
				   $i++;
				}
			    }
			} 
			$text =~ s/'//g;
			$text =~ s/^\s//g;
			print " \"$text\" Location \"$location\"\n"; 
			if ($note ne ""){ 
			        $note =~ s/'//g;	
			        $note =~ s/^\s\/note=//i;	
				print "$VAR_EMBL_tag \"$text\" Note \"$note\"\n"; 
			}
			if ($product ne ""){ 
				$product =~ s/'//g;
				$product =~ s/^\s\/product=//i;
				print "$VAR_EMBL_tag \"$text\" Product \"$product\"\n"; 
			}		  
			if ($VAR_gene ne ""){
				print "Locus \"$VAR_gene\"\n";
				$VAR_gene = "";
			}
					 
	
		}
	}
	print "$VAR_cDNA\n" if ($VAR_cDNA); # Sequence cDNA if RNA.
	# if no title for reference, reference is placed in
	# Sequence Origin tag.
	# Otherwise, we reference to a published article. 
	for ($i = 1; $i <= $VAR_ref_num ; $i++){
		if ($VAR_title[$i] =~ /^\s*$/){
		     $VAR_author[$i] =~ s/^\s*//;
	    	     @VAR_author_array = split(", ", $VAR_author[$i]);
	    	     foreach $VAR_auth(@VAR_author_array) { 
			print "From_Author \"$VAR_auth\"\n";	
	             }
		     if ($VAR_journal[$i] !~ /^UNPUBLISHED/i){
		     	$VAR_lab = $VAR_journal[$i];
	    	     	$VAR_lab =~ s/^[^,]*, //;
	    	     	print "From_Laboratory \"$VAR_lab\"\n";
		     	$VAR_ref_date = $VAR_journal[$i];
		     	$VAR_ref_date =~ s/^SUBMITTED \(//;
		     	$VAR_ref_date =~ s/\).*//;
#		     	print "Date $VAR_ref_date\n";
		     }
       		} else {
			if ($VAR_journal[$i] !~ /^UNPUBLISHED/i){
				$VAR_reference = $VAR_journal[$i];
				$VAR_reference =~ s/\s/_/g;
	        		print "Reference \"$VAR_reference\"\n" 
			}
		}
	};
	print "\n\n\n\n";



	# Print out DNA sequence of main sequence
	print "DNA : \"$VAR_id\"";
	print $VAR_sequence , "\n\n\n\n";


	# Print out sub sequence object.
	foreach $key(@RNA_keys){
		@ARR_RNA = split('""', $VAR_RNA{$key});
		$i = 1;
		foreach $temp_ARR_RNA (@ARR_RNA){
	        	@Inner_ARR_RNA = split('"', $temp_ARR_RNA);
			$subseq = $Inner_ARR_RNA[0];
			$subseq =~ s/[^0-9]/ /g;
			print "Sequence : \"$VAR_id_num:$key.$i (EMBL)\"\n";
			foreach $source_trait (@VAR_source_info){
				if ($source_trait =~ /\/strain='([^']*)'/i){
					$VAR_strain = $1;
					print "Strain \"$VAR_strain\"\n";
				}
				if ($source_trait =~ /\/organism='([^']*)'/i){
					$VAR_organism = $1;
					print "Organism \"$VAR_organism\"\n";
				}
			}
			print "Source \"$VAR_id\"\n";
			if ($subseq =~ /^\s*([0-9]*)\s+([0-9]*)/){
				$first_val = $1;
 				$second_val = $2;
 				$first_int = &strtoint($first_val);
 				$second_int = &strtoint($second_val);
 			}
 			$final_int = $second_int - $first_int + 1;
 			print "Source_Exons 1 " , $final_int , "\n";
			print "$key\n";
			###  if ($key eq "CDS"){
			print "Remark \"";
			$Inner_ARR_RNA[0] =~ s/^\s*//g;
			print $Inner_ARR_RNA[0];
			$j = 1;
			while ($j <= $#Inner_ARR_RNA){
			    if ($Inner_ARR_RNA[$j] =~ /\/gene='([^']*)'/i){
				$VAR_gene = $1;
				$j++;
			    } elsif (($Inner_ARR_RNA[$j] =~ /\/product='/i) && ($key eq "CDS")){
				$VAR_protein = $Inner_ARR_RNA[$j];
				$VAR_protein =~ s/\s*\/product='//i;
				$VAR_protein =~ s/'\s*$//;
				$j++;
			    } elsif ($Inner_ARR_RNA[$j] =~ /\/translation='/){
				$exp_patt = "\"$VAR_id_num:$key.$i (EMBL)\"";
				$Inner_ARR_RNA[$j] =~ s/^\s*//g;
				$pattern = $Inner_ARR_RNA[$j] . "\n";
				$pattern =~ s/\/translation='//;
				$pattern =~ s/\n/ \\\n/;
				if ($Inner_ARR_RNA[$j] !~ /'\s*\n/){
				   $j++;
				   while (($Inner_ARR_RNA[$j] !~ /'\s*$/) && ($j <= $#Inner_ARR_RNA)){
				        $Inner_ARR_RNA[$j] =~ s/^\s*//g;
					$pattern .= $Inner_ARR_RNA[$j];
					$pattern .= " \\\n";               
					$j++;
				   }
				   $Inner_ARR_RNA[$j] =~ s/^\s*//g;
				   $Inner_ARR_RNA[$j] =~ s/'//;
				   $pattern .= $Inner_ARR_RNA[$j]; 
				   $j++;
				}
			     } else {	
				$Inner_ARR_RNA[$j] =~ s/^\s*//g;
			 	print " \\\n" , $Inner_ARR_RNA[$j];
				$j++;
			     }
			}
			print "\"\n";
			if ($VAR_gene ne ""){
				print "Locus \"$VAR_gene\"\n";
				$VAR_gene = "";
			}
			if ($VAR_protein ne ""){
				print "Corresponding_protein \"$VAR_protein\"\n";
			}
			if ($exp_patt ne ""){
				print "Expr_pattern $exp_patt\n";
			}
			print "\n\n\n";	

			if ($exp_patt ne ""){
				print "Expr_pattern : $exp_patt\n";
				print "Sequence $exp_patt\n";
				if ($VAR_protein ne ""){
				    print "Protein \"$VAR_protein\"\n";
				}
				print "Pattern \"$pattern\"\n";
				print "\n\n\n";
			}

			if ($VAR_protein ne ""){
				print "Protein : \"$VAR_protein\"\n";
				print "Corresponding_DNA $exp_patt\n";
				print "Expr_pattern  $exp_patt\n";
				print "\n\n\n";
			}
			$VAR_protein = "";
			$exp_patt = "";
			$pattern = "";
			$i++;
				
		}
	} 	



	# Print out instance of Paper
	for ($i = 1; $i <= $VAR_ref_num ; $i++){
		if (($VAR_title[$i] !~ /^\s*$/) && ($VAR_journal[$i] !~ /^UNPUBLISHED/)){
			$VAR_journ_name = "";
			$VAR_volume = "";
			$VAR_page = "";
			$VAR_year = "";

			$VAR_reference = $VAR_journal[$i];
			$VAR_reference =~ s/\s/_/g;
			print "Paper : \"$VAR_reference\"\n";
		        print "Title \"$VAR_title[$i]\"\n";
			print "Medline_ID $VAR_medline\n";
			if ($VAR_journal[$i] =~ /([^0-9]*)([0-9]*|[0-9]*\s*\([0-9]*\)\s*),([^\(]*)\(([0-9]*)\)/){	
				$temp_journ_name = $1;
				$temp_volume= $2;
				$temp_page = $3;
				$temp_year = $4;
				$temp_journ_name =~ s/\s*$//;
				$VAR_journ_name = "Journal \"$temp_journ_name\"\n";
				$temp_volume =~ s/\s//g;
				$VAR_volume = "Volume $temp_volume\n";
				$temp_page =~ s/\s//g;
				$VAR_page = "Page $temp_page\n";
				$VAR_year = "Year $temp_year\n";
			} else {
				if ($VAR_journal[$i] =~ /([^\(]*)\(([0-9]*)\)\s*IN PRESS\s*$/){
				$temp_journ_name = $1;
				$temp_year = $2;
				$temp_journ_name =~ s/\s*$//;
				$VAR_journ_name = "Journal \"$temp_journ_name\"\n";
				$VAR_year = "Year $temp_year\n";       
				} else {
				$VAR_journ_name = "Journal \"$VAR_journal[$i]\"\n";	
				}
			}
			print $VAR_journ_name , $VAR_volume , $VAR_page , $VAR_year;
			$VAR_author[$i] =~ s/^\s*//;
	    	        @VAR_author_array = split(", ", $VAR_author[$i]);
	    	        foreach $VAR_auth(@VAR_author_array) { 
			   print "Author \"$VAR_auth\"\n";	
	                }
			print "\n\n\n\n";
		}
	}


};




#-------------------------------------------------------------------
# SUBROUTINE: EMBL DATE FORMAT TO ACE DATETYPE FORMAT
#
# Used to convert dates                                          
#-------------------------------------------------------------------

sub EMBLdate2ACEdate{
	local(@temp_date, @VAR_date);
	@temp_date = ();
	@VAR_date = ();
	
	@temp_date = split ("-", $_);
	$VAR_date[0] = $temp_date[2];
        $VAR_date[2] = $temp_date[0];
        if ($temp_date[1] eq "JAN") { $VAR_date[1] = "01"; }
        if ($temp_date[1] eq "FEB") { $VAR_date[1] = "02"; }
        if ($temp_date[1] eq "MAR") { $VAR_date[1] = "03"; }
        if ($temp_date[1] eq "APR") { $VAR_date[1] = "04"; }
        if ($temp_date[1] eq "MAY") { $VAR_date[1] = "05"; }
        if ($temp_date[1] eq "JUN") { $VAR_date[1] = "06"; }
        if ($temp_date[1] eq "JUL") { $VAR_date[1] = "07"; }
        if ($temp_date[1] eq "AUG") { $VAR_date[1] = "08"; }
        if ($temp_date[1] eq "SEP") { $VAR_date[1] = "09"; }
        if ($temp_date[1] eq "OCT") { $VAR_date[1] = "10"; }
        if ($temp_date[1] eq "NOV") { $VAR_date[1] = "11"; }
        if ($temp_date[1] eq "DEC") { $VAR_date[1] = "12"; }
	$temp_date = join("-", @VAR_date);
	return $temp_date;
}


#-------------------------------------------------------------------
# SUBROUTINE: STRING TO INTEGER             
#
# An auxillary function                                          
#-------------------------------------------------------------------

sub strtoint{
        local($num, $i);
        @digits = split("" , $_[0]);
        $num = 0;
        for ($i = 0; $i <= $#digits; $i++){
                $num += (10**($#digits - $i)) * (ord($digits[$i]) - 48);
        }
        return $num;
}