Reg using hash of arrays in foreach loop

[natarajmtech]

Hi all,
I have defined some array variables a
*************** *************** ***********

@L=('CTT','CTC','CTA','CTG','TTA','TTG');
 
@S=('TCT','TCC','TCA','TCG','AGT','AGC');
 
@R=('CGT','CGC','CGA','CGG','AGA','AGG');
 
@V=('GTT','GTC','GTA','GTG');
 
@A=('GCT','GCC','GCA','GCG');
 
@G=('GGT','GGC','GGA','GGG');
 
@P=('CCT','CCC','CCA','CCG');
 
@T=('ACT','ACC','ACA','ACG');
 
@I=('ATT','ATC','ATA');
 
@F=('TTT','TTC');
 
@C=('TGT','TGC');
 
@Y=('TAT','TAC');
 
@Q=('CAA','CAG');
 
@N=('AAT','AAC');
 
@H=('CAT','CAC');
 
@E=('GAA','GAG');
 
@D=('GAT','GAC');
 
@K=('AAA','AAG');
 
@M=('ATG');
 
@W=('TGG');
 

*************** *************** *************** **********
and also created a hash to store the arrays in it and finally I wanted to do a foreach loop over the desired input say for example input=VEFCDAMP and to create all possible permutation of the word taken from the definition from dictionary as defined in the array.

The following is the perl script that I conceived to do the job but I am confused here how to use the forloop here to iterate through this and make permutation,
*************** *************** *************** ***************

print "\n\n\t\#################### AA 2 PROTEIN #################### \n\n";
 
print "This script will convert your amino acid sequence to DNA Sequence\n\n";
 
print "ENTER THE FILENAME OF THE Amino acid SEQUENCE:= ";
 
$aafilename = <STDIN>;
 
chomp $aafilename;
 
unless ( open(aaFILE, $aafilename) ) {
 
print "Cannot open file \"$aafilename\"\n\n";
 
}
 
@aa = <aaFILE>;
 
close aaFILE;
 
$aa = join( '', @aa);
 
print " \nThe original AA file is:\n$aa \n";
 
$aa =~ s/\s//g;
 
@aa=$aa;
 
my $protein='';
 
my $codon;
 
@L=('CTT','CTC','CTA','CTG','TTA','TTG');
 
@S=('TCT','TCC','TCA','TCG','AGT','AGC');
 
@R=('CGT','CGC','CGA','CGG','AGA','AGG');
 
@V=('GTT','GTC','GTA','GTG');
 
@A=('GCT','GCC','GCA','GCG');
 
@G=('GGT','GGC','GGA','GGG');
 
@P=('CCT','CCC','CCA','CCG');
 
@T=('ACT','ACC','ACA','ACG');
 
@I=('ATT','ATC','ATA');
 
@F=('TTT','TTC');
 
@C=('TGT','TGC');
 
@Y=('TAT','TAC');
 
@Q=('CAA','CAG');
 
@N=('AAT','AAC');
 
@H=('CAT','CAC');
 
@E=('GAA','GAG');
 
@D=('GAT','GAC');
 
@K=('AAA','AAG');
 
@M=('ATG');
 
@W=('TGG');
 
 
 
$L=\@L;
 
$S=\@S;
 
$R=\@R;
 
$V=\@V;
 
$A=\@A;
 
$G=\@G;
 
$P=\@P;
 
$T=\@T;
 
$I=\@I;
 
$F=\@F;
 
$C=\@C;
 
$Y=\@Y;
 
$Q=\@Q;
 
$N=\@N;
 
$H=\@H;
 
$E=\@E;
 
$D=\@D;
 
$K=\@K;
 
$M=\@M;
 
$W=\@W;
 
 
 
%hash = (L=>$L,S=>$S,R=>$R,V=>$V,A=>$A,G=>$G,P=>$P,T=>$T,I=>$I,F=>$F,C=>$C,Y=>$Y,Q=>$Q,N=>$N,H=>$H,E=>$E,D=>$D,K=>$K,M=>$M,W=>$W);
 
 
 
$hash_ref=\%hash;
 
 
my @aa_split = split //, $aa;
 
 
 
foreach my $val (@{hash{@aa_split}})
 
{
print "@{$val} ";
 
}
print " \n";
 

*************** *************** *************** *************** *****

to run this program please create and save a txt file with the content of word VEFCDAMP in it.

I want my program to perform simillar task what the following program does it for
*************** *************** *************** *************** ****

use strict;
use warnings;
my @V=('GTT','GTC','GTA','GTG');
my @A=('GCT','GCC','GCA','GCG');
my @E=('GAA','GAG');
my @F=('TTT','TTC');
my @G=('GGT','GGC','GGA','GGG');
my @H=('CAT','CAC');
my $i = 1;
foreach my $v (@V) {
   foreach my $a (@A) {
      foreach my $e (@E) {
         foreach my $f (@F) {
            foreach my $g (@G) {
               foreach my $h (@H) {
                  print "$i $v$a$e$f$g$h\n";
                  $i++;
               }
            }
         }
      }
   }
}
 

*************** *************** *************** *************** **

Thanks in advance,
B.Nataraj

[KevinADC]

Heres a solution that does not use eval, but I would benchmark my code and nithinpes code when you get a chance and see if one is better than the other.

use warnings;
use strict; 
my $seq = 'VF'; 
my %hash = (  
   L => ['CTT','CTC','CTA','CTG','TTA','TTG'], 
   S => ['TCT','TCC','TCA','TCG','AGT','AGC'], 
   R => ['CGT','CGC','CGA','CGG','AGA','AGG'], 
   V => ['GTT','GTC','GTA','GTG'], 
   A => ['GCT','GCC','GCA','GCG'], 
   G => ['GGT','GGC','GGA','GGG'], 
   P => ['CCT','CCC','CCA','CCG'], 
   T => ['ACT','ACC','ACA','ACG'], 
   I => ['ATT','ATC','ATA'], 
   F => ['TTT','TTC'], 
   C => ['TGT','TGC'], 
   Y => ['TAT','TAC'], 
   Q => ['CAA','CAG'], 
   N => ['AAT','AAC'], 
   H => ['CAT','CAC'], 
   E => ['GAA','GAG'], 
   D => ['GAT','GAC'], 
   K => ['AAA','AAG'], 
   M => ['ATG'], 
   W => ['TGG'], 
); 
 
my @letters = split '', $seq; 
my $loops = 1;
foreach my $L (@letters) {
   $loops *= @{$hash{$L}};
}
my @perms;
foreach my $S (@letters) {
   my @t = @{$hash{$S}};
   for my $i (0..$loops-1) {
      my $c = shift @t;
      $perms[$i] .= $c;
      push @t, $c;
   }
}
my $i = 1;
foreach my $s (@perms) {
   print $i++, " $s\n";
}
 

I'm not sure how efficient my use of "shift" and "push" is to loop through the arrays over and over the number of times necessary.

[natarajmtech]

Heres a solution that does not use eval, but I would benchmark my code and nithinpes code when you get a chance and see if one is better than the other.

use warnings;
use strict; 
my $seq = 'VF'; 
my %hash = (  
   L => ['CTT','CTC','CTA','CTG','TTA','TTG'], 
   S => ['TCT','TCC','TCA','TCG','AGT','AGC'], 
   R => ['CGT','CGC','CGA','CGG','AGA','AGG'], 
   V => ['GTT','GTC','GTA','GTG'], 
   A => ['GCT','GCC','GCA','GCG'], 
   G => ['GGT','GGC','GGA','GGG'], 
   P => ['CCT','CCC','CCA','CCG'], 
   T => ['ACT','ACC','ACA','ACG'], 
   I => ['ATT','ATC','ATA'], 
   F => ['TTT','TTC'], 
   C => ['TGT','TGC'], 
   Y => ['TAT','TAC'], 
   Q => ['CAA','CAG'], 
   N => ['AAT','AAC'], 
   H => ['CAT','CAC'], 
   E => ['GAA','GAG'], 
   D => ['GAT','GAC'], 
   K => ['AAA','AAG'], 
   M => ['ATG'], 
   W => ['TGG'], 
); 
 
my @letters = split '', $seq; 
my $loops = 1;
foreach my $L (@letters) {
   $loops *= @{$hash{$L}};
}
my @perms;
foreach my $S (@letters) {
   my @t = @{$hash{$S}};
   for my $i (0..$loops-1) {
      my $c = shift @t;
      $perms[$i] .= $c;
      push @t, $c;
   }
}
my $i = 1;
foreach my $s (@perms) {
   print $i++, " $s\n";
}
 

I'm not sure how efficient my use of "shift" and "push" is to loop through the arrays over and over the number of times necessary.

Hi Kevin,

Thanks for your new code and pointing out possible pitfall. In fact I am half way down my real work and another half way to pass on. I am making the remaining code and hopefully that wont be so difficult logic to make it out and all about string manipulation and once entire code is ready and I will be in a position to check yours and nithin for a real time problem and I hope can give you my feedback very soon.


B.Nataraj

[natarajmtech]

Hi Kevin,

The last code you have posted, is in fact repeating the first four sequence as output but it make up to the desired 512 (for a input seqnence of VAEFGH) sequence as per rule. But the alternative code by Nithin is working just fine for creating all possible combination and there is no repetition.

I just happened to compare this bug in your code at the last stage of implementing in my entire code using your code as a starting point. I could not fix in it and possibly you can do it quickly so I am posting it to you once again.

Thanks,
B.Nataraj

[natarajmtech]

(I tried to delete this message, but I could not do it)

Hi Kevin,
Sorry I did not mention my input sequence in my previous message, here it is "VAEFGH".

Thanks,
B.Nataraj

[KevinADC]

(I tried to delete this message, but I could not do it)

Hi Kevin,
Sorry I did not mention my input sequence in my previous message, here it is "VAEFGH".

Thanks,
B.Nataraj

hmmm...guess I made a logical error in the code I wrote. I'll look at it later today and see if I can find the error.

[KevinADC]

well, I can't get it to work. I think you are will need to use nithinpes code or wait and see if someone else can help or post on www.perlmonks.c om and see if one of the members there has a suggestion.

[natarajmtech]

Hi Kevin,
Ok, I will use nithin's code then.

Thanks,
B.Nataraj

[natarajmtech]

Here is one way of doing it. This code dynamically generates required foreach loops and executes the command.

 my $seq = 'VF'; 
my %hash = (  
   L => ['CTT','CTC','CTA','CTG','TTA','TTG'], 
   S => ['TCT','TCC','TCA','TCG','AGT','AGC'], 
   R => ['CGT','CGC','CGA','CGG','AGA','AGG'], 
   V => ['GTT','GTC','GTA','GTG'], 
   A => ['GCT','GCC','GCA','GCG'], 
   G => ['GGT','GGC','GGA','GGG'], 
   P => ['CCT','CCC','CCA','CCG'], 
   T => ['ACT','ACC','ACA','ACG'], 
   I => ['ATT','ATC','ATA'], 
   F => ['TTT','TTC'], 
   C => ['TGT','TGC'], 
   Y => ['TAT','TAC'], 
   Q => ['CAA','CAG'], 
   N => ['AAT','AAC'], 
   H => ['CAT','CAC'], 
   E => ['GAA','GAG'], 
   D => ['GAT','GAC'], 
   K => ['AAA','AAG'], 
   M => ['ATG'], 
   W => ['TGG'], 
); 
 
my @loops = split '', $seq; 
my $cmd;
local $i=0;
my $vars;
 
foreach my $letter (@loops) {
    my ($str,$v)= createloop($letter);
    $vars.=$v;
    $cmd.=$str;
} 
$cmd=$cmd.'print'. " \"$vars\\n\";";  ## adding print statement
$cmd.= '}'x$i;       ### ending statement blocks
 
eval {eval $cmd; };   ## first eval returns statement block
 
##creating foreach loops 
sub createloop {
$i++;
my $var ='$a'.$i;
return ("foreach $var (qw(@{$hash{$_[0]}})) {",$var) ;
 
}
 

Hi Nithinpes,
I am using your code posted by you in this thread for my work. Now I had a little problem in using your code to direct the output to a file. I could not do it since I could not understand the code properly, especially the eval statement and its contribution. Kindly help me to add an extra code to direct the generated sequence to save in a text file.

Thanks,
B.Nataraj

[natarajmtech]

Hi Nithinpes,
I am using your code posted by you in this thread for my work. Now I had a little problem in using your code to direct the output to a file. I could not do it since I could not understand the code properly, especially the eval statement and its contribution. Kindly help me to add an extra code to direct the generated sequence to save in a text file.

Thanks,
B.Nataraj

Hi Nithinpes,

Yes, I done it myself by following way. Please igonre my post.

print "\n\n\t\#################### AA 2 PROTEIN #################### \n\n";
print "This script will convert your amino acid sequence to DNA Sequence\n\n";
print "ENTER THE FILENAME OF THE Amino acid SEQUENCE:= ";
$aafilename = <STDIN>;
chomp $aafilename;
 
unless ( open(aaFILE, $aafilename) ) {
    print "Cannot open file \"$aafilename\"\n\n";
}
@aa = <aaFILE>;
close aaFILE;
$aa = join( '', @aa);
 
my $seq = "$aa";  
my %hash = (   
   L => ['CTT','CTC','CTA','CTG','TTA','TTG'],  
   S => ['TCT','TCC','TCA','TCG','AGT','AGC'],  
   R => ['CGT','CGC','CGA','CGG','AGA','AGG'],  
   V => ['GTT','GTC','GTA','GTG'],  
   A => ['GCT','GCC','GCA','GCG'],  
   G => ['GGT','GGC','GGA','GGG'],  
   P => ['CCT','CCC','CCA','CCG'],  
   T => ['ACT','ACC','ACA','ACG'],  
   I => ['ATT','ATC','ATA'],  
   F => ['TTT','TTC'],  
   C => ['TGT','TGC'],  
   Y => ['TAT','TAC'],  
   Q => ['CAA','CAG'],  
   N => ['AAT','AAC'],  
   H => ['CAT','CAC'],  
   E => ['GAA','GAG'],  
   D => ['GAT','GAC'],  
   K => ['AAA','AAG'],  
   M => ['ATG'],  
   W => ['TGG'],  
);  
  open(OUT, ">>dna_outfile.txt"); 
 
my @loops = split '', $seq;  
my $cmd; 
local $i=0; 
my $vars; 
foreach my $letter (@loops) { 
    my ($str,$v)= createloop($letter); 
    $vars.=$v; 
    $cmd.=$str; 
}  
$cmd=$cmd.'print OUT'. " \"$vars\\n\";";  ## adding print statement 
#$cmd=$cmd.'print'. " \"$vars\\n\";";  ## adding print statement 
$cmd.= '}'x$i;  ;     ### ending statement blocks 
 
eval {eval $cmd; };   ## first eval returns statement block 
 
##creating foreach loops  
sub createloop { 
$i++; 
my $var ='$a'.$i; 
return ("foreach $var (qw(@{$hash{$_[0]}})) {",$var) ; 
 
} 
 
 
 
close OUT;