#!/usr/bin/perl -w
#  
use strict;
use warnings;

# useful hashes for converting one letter code to mass
#

my %s2m = (A =>  71.0371, C => 103.0092, D => 115.0269, E => 129.0426,
        F => 147.0684, G =>  57.0215, H => 137.0589, I => 113.0841,
        K => 128.0950, L => 113.0841, M => 131.0405, N => 114.0429,
        P =>  97.0528, Q => 128.0586, R => 156.1011, S =>  87.0320,
        T => 101.0477, V =>  99.0684, W => 186.0793, Y => 163.0633,
        '\s' => 0.0, "*" => 0.0
       );
my %s2a = (A =>  71.08, C => 103.14, D => 115.09, E => 129.12,
        F => 147.18, G =>  57.05, H => 137.14, I => 113.16,
        K => 128.17, L => 113.16, M => 131.19, N => 114.10,
        P =>  97.12, Q => 128.13, R => 156.19, S =>  87.08,
        T => 101.10, V =>  99.13, W => 186.21, Y => 163.18,
        '\s' => 0.0, "*" => 0.0
       );

my $file = "P1GroupCExercise2_trypsin.txt";
my $header = "";
my %sequences = ();


printf ">Mass(A):18.0153|Charge:1|";
# # open file #
open(FILE,$file) or die "error: unable to open file $file\n"; 
while ( <FILE> )
 {
 # # read in sequences in fasta format
 # 
   next if /^\s*$/; # ignore blank lines 
     if ( /^>((\S+)$)/ )  {
  $header = $1; 
    } else {      # assume its sequences  
     chomp;
      $sequences{$header} .= $_ . ";"; 
     } 
}
 close(FILE);  
 
 while ((my $key, my $value) = each %sequences) {
	my @e = split(/;/, $value);
	# loop
	my @headers= split(/:/, $key);
	foreach $value (@e) {
	my @elements= split(/\|/, $value);
	$key = $headers[1];
	# peptide = first element of @elements
	# missed = 2nd element of @elements
	# sequence = 5th element of @elements
	my @peptides= split (/:/, $elements[1]);#56
	my $peptide = $peptides[1];
	my @missedc = split (/:/, $elements[2]);#58
	my $missed = $missedc[1];
	my @typec=split (/:/, $elements[3]);#60
	my $type=$typec[1];
	my @enzymes=split (/:/, $elements[4]);#62
	my $enzyme=$enzymes[1];
	my @s= split(/:/, $elements[5]);#64
	my $sequence= $s[1];
	@peptides = split (//, $sequence);#66
	my $total = 0.0;
	foreach my $peptide (@peptides) {
		$total += $s2m{$peptide} if defined $s2m{$peptide};
	}
		 my $output = ">Protein: $headers[1]\n|Peptide:$peptide|Mass(A):$total|Charge:1|Missed:$missed|Terminal:$type|Enzyme:$enzyme|sequence:$sequence\n";#71
         print  $output;
	} }

<DATA(the format of the input file is something as displayed below)>
>Protein:HEMINF_F3_Complement_N182_S1226717_L118
|Peptide:13|Missed:0|Type:I|Enzyme:trypsin|Seq:R|
>Protein:HEMINF_F3_Complement_N182_S1226717_L118
|Peptide:14|Missed:0|Type:I|Enzyme:trypsin|Seq:SK|
>Protein:HEMINF_F3_Complement_N182_S1226717_L118
|Peptide:15|Missed:0|Type:I|Enzyme:trypsin|Seq:NWALR|
>Protein:HEMINF_F3_Complement_N182_S1226717_L118
|Peptide:16|Missed:0|Type:I|Enzyme:trypsin|Seq:R|
>Protein:HEMINF_F3_Complement_N182_S1226717_L118
|Peptide:17|Missed:0|Type:I|Enzyme:trypsin|Seq:ER|
>Protein:HEMINF_F3_Complement_N182_S1226717_L118
|Peptide:18|Missed:0|Type:I|Enzyme:trypsin|Seq:VSIFFWLLSAAAIPTMIINR|
>Protein:HEMINF_F3_Complement_N182_S1226717_L118
|Peptide:19|Missed:0|Type:I|Enzyme:trypsin|Seq:GTSGAVIIK|
>Protein:HEMINF_F3_Complement_N182_S1226717_L118
|Peptide:20|Missed:0|Type:I|Enzyme:trypsin|Seq:IKPAAQFK|
>Protein:HEMINF_F3_Complement_N182_S1226717_L118
|Peptide:21|Missed:0|Type:I|Enzyme:trypsin|Seq:GNTAMK|
>Protein:HEMINF_F3_Complement_N182_S1226717_L118
|Peptide:22|Missed:0|Type:I|Enzyme:trypsin|Seq:ITTGTMAER|
>Protein:HEMINF_F3_Complement_N182_S1226717_L118
|Peptide:23|Missed:0|Type:C|Enzyme:trypsin|Seq:LC|