Perl script for Needleman Wunch Algorithm

kmalhotra7 — Tue, 08 Dec 2009 17:20:36 +0000

I wrote the following perl script to run Needleman wunch algorithm on 2 protein sequences.

############## PARAMETER EXTRACTION #####################

my $blos_file=”blosum50.txt”;

open(FH,$blos_file) || die “blosum file could not be found”;

my @prot = ();

my $i=0;

my $j=0;

my %blosum;

while(my $line=){

chomp $line;

if($line=~/^\w.*/){

@prot=split(‘\s’,$line);

}

if($line=~/^\W\d.*/){

chomp $line;

my @temp_arr;

if($line=~/^\s(\d\s.*\d.*)/){

@temp_arr=split(‘\s+’,$1);

}

else{

@temp_arr=split(‘\s+’,$line);

}

#print scalar(@temp_arr),”\n”;

foreach my $line(@temp_arr){

$blosum{$prot[$i]}{$prot[$j]}=$temp_arr[$j];

$j++;

}

$i++;

$j=0;

next;

}

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

@arr_seq1 = ();

@arr_seq2 = ();

$Gap = ‘-8′;

$file_prot=”protein1.FAA”;

open(FH,$file_prot) || die “input is not found\n”;

$newprot1 = ”;

while($line = ){

if ($line =~ /^\>.*/){

}

else {

$newprot1.= $line;

}

@arr_seq1 = split(”,$newprot1);

$file_prot=”protein2.FAA”;

open(FH,$file_prot) || die “input is not found\n”;

while($line = ){

if($line =~ /^\>.*/){

}

else {

@arr_seq2 = split(”, $line);

}

$len_Seq1 = scalar @arr_seq1;

$len_Seq2 = scalar @arr_seq2;

@arr_Nos = ();

@arr_Symb = ();

$arr_Nos[0][0] = ’0′; #” Initializing the array

########## FILLING THE FIRST ROW AND COL ##################

for ($i = 1 ; $i <= $len_Seq1 ; $i++){ #””””filling the first row

$arr_Nos[0][$i] = $arr_Nos[0][$i-1] + $Gap ;

#print $arr_Nos[0][$i] , “\t”;

$arr_Symb[0][$i] = ‘-’;

#print $arr_Symb[0][$i];

}

for($i = 1 ; $i <= $len_Seq2 ; $i++){ #””’ filling the first column

$arr_Nos[$i][0] = $arr_Nos[$i-1][0] + $Gap;

$arr_Symb[$i][0] = ‘|’;

#print $arr_Nos[$i][0] , “\n”;

#print $arr_Symb[$i][0] , “\n”;

}

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

########### sub routine for maximum value #################

sub max

{

my (@numbers);

@numbers = @_;

my ($max);

$max = $numbers[0];

foreach my $i (@numbers)

{

if ($i > $max)

{

$max = $i;

}

return ($max);

}

print “The scores matrix ” , “\n\n”;

###################### For Filling the rest of the matrix ######################

$i = 1;

$j = 1;

@arr_pass = ();

while ($i <= $len_Seq2 ){

$j =1;

while ($j <= $len_Seq1){

$A = $arr_seq1[$j-1];

$B = $arr_seq2[$i-1];

$arr_pass[0] = $arr_Nos[$i-1][$j-1] + $blosum{$A}{$B};

$arr_pass[1] = $arr_Nos[$i-1][$j] + $Gap;

$arr_pass[2] = $arr_Nos[$i][$j-1] + $Gap;

$arr_Nos[$i][$j] = max(@arr_pass);

print $arr_Nos[$i][$j] , “\t”;

$j++;

}

$i++;

print “\n”;

}

print “\n\n\n\n\n”;

########################### FOR FILLING THE DIRECTIONS ########################

print “The Direction Matrix”, “\n\n”;

$i = 1;

$j = 1;

@arr_pass = ();

@arr_Symb = ();

while ($i <= $len_Seq2 ){

$j =1;

while ($j <= $len_Seq1){

$A = $arr_seq1[$j-1];

$B = $arr_seq2[$i-1];

$arr_pass[0] = $arr_Nos[$i-1][$j-1] + $blosum{$A}{$B};

$arr_pass[1] = $arr_Nos[$i-1][$j] + $Gap;

$arr_pass[2] = $arr_Nos[$i][$j-1] + $Gap;

$arr_Nos[$i][$j] = max(@arr_pass);

if ($arr_Nos[$i][$j] == $arr_pass[0]){

$arr_Symb[$i][$j] = ‘\\’; ####### to get a backslash here

}

else {

if ($arr_Nos[$i][$j] == $arr_pass[1]){

$arr_Symb[$i][$j] = ‘|’;

}

if ($arr_Nos[$i][$j] == $arr_pass[2]){

$arr_Symb[$i][$j] = ‘-’;

}

print $arr_Symb[$i][$j] , “\t”;

$j++;

}

$i++;

print “\n”;

}

#################### BACKTRACK ALIGNMENT ################################

print “\n\n\n BackTrack \n\n\n”;

$i = $len_Seq2;

$j = $len_Seq1;

@align1 = ();

@align2 = ();

while ($i > 0){

while ($j > 0){

if ($arr_Symb[$i][$j] eq ‘\\’){

$align1[$i] = $arr_seq1[-1];

$align2[$i] = $arr_seq2[-1];

pop(@arr_seq1);

pop(@arr_seq2);

print $align1[$i], “\t”;

print $align2[$i] , “\n”;

$i–;

$j–;

}

if($arr_Symb[$i][$j] eq ‘|’){

$align1[$i] = ‘-’;

$align2[$i] = $arr_seq2[-1];

pop(@arr_seq2);

print $align1[$i], “\t”;

print $align2[$i] , “\n”;

$i–;

}

if($arr_Symb[$i][$j] eq ‘-’){

$align1[$i] = $arr_seq1[-1];

$align2[$i] = ‘-’;

pop(@arr_seq1);

print $align1[$i], “\t”;

print $align2[$i] , “\n”;

$j–;

}

############## PARAMETER EXTRACTION #####################my $blos_file=”blosum50.txt”;open(FH,$blos_file) || die “blosum file could not be found”;

my @prot = ();my $i=0;my $j=0;my %blosum;while(my $line=){ chomp $line; if($line=~/^\w.*/){ @prot=split(‘\s’,$line); } if($line=~/^\W\d.*/){ chomp $line; my @temp_arr; if($line=~/^\s(\d\s.*\d.*)/){ @temp_arr=split(‘\s+’,$1); } else{ @temp_arr=split(‘\s+’,$line); } #print scalar(@temp_arr),”\n”; foreach my $line(@temp_arr){ $blosum{$prot[$i]}{$prot[$j]}=$temp_arr[$j]; $j++; } $i++; $j=0; next; }}

####################### @arr_seq1 = ();@arr_seq2 = ();
$Gap = ‘-8′;
$file_prot=”protein1.FAA”;open(FH,$file_prot) || die “input is not found\n”;
$newprot1 = ”;
while($line = ){ if ($line =~ /^\>.*/){ } else { $newprot1.= $line; } }
@arr_seq1 = split(”,$newprot1);
$file_prot=”protein2.FAA”;open(FH,$file_prot) || die “input is not found\n”;
while($line = ){ if($line =~ /^\>.*/){ } else { @arr_seq2 = split(”, $line); }}
$len_Seq1 = scalar @arr_seq1;$len_Seq2 = scalar @arr_seq2;
@arr_Nos = ();@arr_Symb = ();
$arr_Nos[0][0] = ’0′; #” Initializing the array
########## FILLING THE FIRST ROW AND COL ##################
for ($i = 1 ; $i <= $len_Seq1 ; $i++){ #””””filling the first row $arr_Nos[0][$i] = $arr_Nos[0][$i-1] + $Gap ; #print $arr_Nos[0][$i] , “\t”; $arr_Symb[0][$i] = ‘-’; #print $arr_Symb[0][$i]; }

for($i = 1 ; $i <= $len_Seq2 ; $i++){ #””’ filling the first column $arr_Nos[$i][0] = $arr_Nos[$i-1][0] + $Gap; $arr_Symb[$i][0] = ‘|’; #print $arr_Nos[$i][0] , “\n”; #print $arr_Symb[$i][0] , “\n”; }
#################################################################################
########### sub routine for maximum value #################
sub max{   my (@numbers);
@numbers = @_;
my ($max);
$max = $numbers[0];
foreach my $i (@numbers)   {   if ($i > $max)   {   $max = $i;   }       }
return ($max);}
print “The scores matrix ” , “\n\n”;###################### For Filling the rest of the matrix ######################$i = 1;$j = 1;@arr_pass = ();
while ($i <= $len_Seq2 ){ $j =1; while ($j <= $len_Seq1){ $A = $arr_seq1[$j-1]; $B = $arr_seq2[$i-1];     $arr_pass[0] = $arr_Nos[$i-1][$j-1] + $blosum{$A}{$B}; $arr_pass[1] = $arr_Nos[$i-1][$j] + $Gap; $arr_pass[2] = $arr_Nos[$i][$j-1] + $Gap; $arr_Nos[$i][$j] = max(@arr_pass); print $arr_Nos[$i][$j] , “\t”; $j++; } $i++;print “\n”; }

print “\n\n\n\n\n”;
########################### FOR FILLING THE DIRECTIONS ########################
print “The Direction Matrix”, “\n\n”;
$i = 1;$j = 1;@arr_pass = ();@arr_Symb = ();
while ($i <= $len_Seq2 ){ $j =1; while ($j <= $len_Seq1){ $A = $arr_seq1[$j-1]; $B = $arr_seq2[$i-1]; $arr_pass[0] = $arr_Nos[$i-1][$j-1] + $blosum{$A}{$B}; $arr_pass[1] = $arr_Nos[$i-1][$j] + $Gap; $arr_pass[2] = $arr_Nos[$i][$j-1] + $Gap; $arr_Nos[$i][$j] = max(@arr_pass); if ($arr_Nos[$i][$j] == $arr_pass[0]){ $arr_Symb[$i][$j] = ‘\\’; ####### to get a backslash here } else { if ($arr_Nos[$i][$j] == $arr_pass[1]){ $arr_Symb[$i][$j] = ‘|’; } if ($arr_Nos[$i][$j] == $arr_pass[2]){ $arr_Symb[$i][$j] = ‘-’; } } print $arr_Symb[$i][$j] , “\t”; $j++; } $i++;print “\n”; }

#################### BACKTRACK ALIGNMENT ################################
print “\n\n\n BackTrack \n\n\n”;

$i = $len_Seq2;$j = $len_Seq1;
@align1 = ();@align2 = ();

while ($i > 0){ while ($j > 0){ if ($arr_Symb[$i][$j] eq ‘\\’){ $align1[$i] = $arr_seq1[-1]; $align2[$i] = $arr_seq2[-1]; pop(@arr_seq1); pop(@arr_seq2); print $align1[$i], “\t”; print $align2[$i] , “\n”; $i–; $j–; } if($arr_Symb[$i][$j] eq ‘|’){ $align1[$i] = ‘-’; $align2[$i] = $arr_seq2[-1]; pop(@arr_seq2); print $align1[$i], “\t”; print $align2[$i] , “\n”; $i–; } if($arr_Symb[$i][$j] eq ‘-’){ $align1[$i] = $arr_seq1[-1]; $align2[$i] = ‘-’; pop(@arr_seq1); print $align1[$i], “\t”; print $align2[$i] , “\n”; $j–; } } }