#!/usr/bin/perl -w
use strict;
use warnings;
 
#   --------------------------------------------------------------
# This script uses the residue.txt file generated by
# resTabmakerBatch.pl and creates a new file called
# SecStructList.txt
# each protein is described by secondary structures with a
# pdbID, 2ry structureID (char or \N'), startResidue, endResidue
# Input: residue.txt (this file is the output of resTabmakerBatch.pl)
# Output: secStructList.txt
# usage: secStructList.txt to populate the SecStructure entity
#   --------------------------------------------------------------
 
#Read arguments, print error message if insufficient
if ($#ARGV<0)
{
 die("\n\nUsage:  sstruct.pl [residue_table_file.txt]\n\n");
}
 
my $filename = $ARGV[0];
 
#if either file not found return error message
if (! -e "$filename")
{
 die("\n\nresidue file $filename does not exist!\n\n");
}
 
 # Read residue.txt file, extracting the data of interest - only
 # pdb id, resNum, resID, secondaryStructID
 
#First read file, storing each line in an array 'dssplines' splitting the
data
open (MYFILE,"$filename") or die ("\nERROR: Can't open $filename\n");
 my @dssplines= split(/\r/, <MYFILE>);
 my $arraySize=@dssplines;
close(MYFILE);
#read one line from the originally loaded array dssplines at a time and loop
#over it splitting the values using the tabs
 my @dsspdata;
 my $dsspdataSize=@dssplines;
 
 my $n=0;
 for (my $i=0; $i < $arraySize; $i++)
 {
  #each line from the array goes into a new dsspline variable
  my $dsspline = $dssplines[$i];
  for (my $j = 0; $j <=4; $j++)
  {
   #each time values inside are separated using the tabs
   my ($pdbID, $resNo, $resID, $phi, $psi, $chi1, $chi2, $secStruct,
$activesite) = split(/\t/, $dsspline);
   # now each value of interest is stored into a new array @dsspdata
   $dsspdata[$n][0] = $pdbID;
   $dsspdata[$n][1] = $resNo;
   $dsspdata[$n][2] = $resID;
   $dsspdata[$n][3] = $secStruct;
  }
  $n++;
 }
 
#my @dsspdata array is now perfect to reformat into a hash analyzing the
value correlation
 
 #initialize the hash and counter
 my %dane;
 my $k=0;
 #loop around the dsspdata array
 for (my $i=0; $i < $dsspdataSize; $i++)
 {
  #split each cell in a row into variables for the hash
  for (my $k = 0; $k <=4; $k++)
  {
   my $pdb = $dsspdata[$i][0];
   my $residueNum = $dsspdata[$i][1];
   my $secStructure = $dsspdata[$i][3];
   push @{ $dane{$pdb}->{$secStructure} }, $residueNum;
  }
  $k++;
 }
 
 #now for each pdbID using the hash keys
 foreach my $pdbID ( keys %dane )
 {
  #check the secondary structure id with pdbID as a key (only if the pdbID
is the same will the values be stored)
  foreach my $secID ( keys %{ $dane{$pdbID} } )
  {
   #finally create an array of residue numbers
   my @resnums = ( $dane{$pdbID}->{$secID}->[0],
$dane{$pdbID}->{$secID}->[-1] );
   #create a new file with the secondary structures list
   open (SStruc, ">>secStructList.txt") || die "Can't open file: $!";
   #append each line to the new file with tab separated data
   print SStruc ("$pdbID \t @resnums \t $secID\n");
  }
 }
close(SStruc);

#!/usr/bin/perl -w
use strict;
use warnings;
if ($#ARGV<0)
{ die("\n\nUsage:  sstruct.pl [residue_table_file.txt]\n\n"); }
my $filename = $ARGV[0];
if (! -e "$filename")    
{ die("\n\nresidue file $filename does not exist!\n\n"); }
open (MYFILE,"$filename") or die ("\nERROR: Can't open $filename\n");
    my @dssplines= split(/\r/, <MYFILE>);
    my $arraySize=@dssplines;
close(MYFILE);
 
my @dsspdata;
my $dsspdataSize=@dssplines;
    for (my $i=0; $i < $arraySize; $i++)
    {
      my $dsspline = $dssplines[$i];
      my ($pdbID, $resNo, $resID, $phi, $psi, $chi1, $chi2, $secStruct, $activesite) = split(/\t/, $dsspline);
      push( @dsspdata, [$pdbID,$resNo,$resID,$secStruct] );
    }
 
my %dane;
my $k=0;
for (my $i=0; $i < $dsspdataSize; $i++)
{
    for (my $k = 0; $k <=4; $k++)
    {
        my $pdb = $dsspdata[$i][0];
        my $residueNum = $dsspdata[$i][1];
        my $secStructure = $dsspdata[$i][3];
        push @{ $dane{$pdb}->{$secStructure} }, $residueNum;
    }
    $k++;
}
 
foreach my $pdbID ( keys %dane )
{
    foreach my $secID ( keys %{ $dane{$pdbID} } )
    {
        my @resnums = ( $dane{$pdbID}->{$secID}->[0], $dane{$pdbID}->{$secID}->[-1] );
        open (SStruc, ">>secStructList.txt") || die "Can't open file: $!";
        print SStruc ("$pdbID \t @resnums \t $secID\n");
    }
}
close(SStruc);

my ( $x, $y, undef, $z ) = split ' ', <DATA>;
my ($last_x,$last_z,$min,$max)=($x,$z,$y,$y);
 
while (<DATA>) {
    my ( $x, $y, undef, $z ) = split;
    if ($x ne $last_x or $z ne $last_z) {
       print "$last_x $min $max $last_z\n";
       ($last_x,$last_z,$min,$max)=($x,$z,$y,$y);
    };
    $max=$y;
}
print "$last_x $min $max $last_z\n";