#!/usr/bin/perl

# This script reads genes from a file (one per line) and translates them
# to amino acid sequences

#~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
# YOU CAN IGNORE THIS CODE UNTIL THE NEXT LINE OF SQUIGLY LINES
# Takes in a genetic code and a nucleotide string and returns the aa string
$gcode = 1;
open(GCODES,"<gc.prt") || die ("Couldnt open gc.prt");

# going to use a hash where $nt_to_aa{$codon} gets a single let aa
$get = 0;
while (<GCODES>){
    if (/id $gcode/){ $get = 1;}
    if (($get == 1) && (/ncbieaa\s+\"(.+)\",/)){
        $aa_str = $1;
    }
    if (($get == 1) && (/sncbieaa\s+\"(.+)\"/)){
        $start_codons = $1;
    }
    if (($get == 1) && (/Base1\s+(.+)/)){
        $base_1 = $1;
    }
    if (($get == 1) && (/Base2\s+(.+)/)){
        $base_2 = $1;
    }
    if (($get == 1) && (/Base3\s+(.+)/)){
        $base_3 = $1;
        last;
    }
}

    my @aa = $aa_str =~ /[\w\*]/g;
    my @starts = $start_codons =~ /[\w-]/g;
    my @base1 = $base_1 =~ /\w/g;
    my @base2 = $base_2 =~ /\w/g;
    my @base3 = $base_3 =~ /\w/g;

    for $i (0..$#aa) {
        $codon = $base1[$i].$base2[$i].$base3[$i];
        $nt_to_aa{$codon} = $aa[$i];
    }

#~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

while (<>){
    $nt_string = $_;
    $aa_string = "";
    $place = 0;  # place holder in the nucleotide sequence (where we start
		 # translating from) $codon will hold one codon
    $codon = substr($nt_string,$place,3);
    while (length($codon) == 3){
        $aa_string .= $nt_to_aa{$codon};
        $place += 3;
        $codon = substr($nt_string,$place,3);
    }
    print $nt_string,"\n";
    $aa_string =~ s/([\w|\*])/\1  /g;
    print "$aa_string\n";
    print "============================================\n";
}