Programming

#!/usr/bin/env python
import sys

try :
   filename = sys.argv[1]
except :
   print 'Specify filename'
   sys.exit()
fd = open(filename)
lines = fd.xreadlines()
compare = {}
for line in lines :
    split_line = line.strip().split('\t')
        if compare.has_key(split_line[0]) :
            for i in range(1,3) :
                try :
                    compare[split_line[0]].index(split_line[i])
                except :
                    compare[split_line[0]].append(split_line[i])
        else :
            compare[split_line[0]] = []
            for i in range(1,3) :
                try :
                    compare[split_line[0]].index(split_line[i])
                except :
                     compare[split_line[0]].append(split_line[i])
fd.close()
for i in compare.keys() :
   print '%s\t%s' %(i,compare[i])

(1) Read a line, split it by Tabs and then determine if the first token exists as a hash key.
(2) If it does not, then assign a "template" array that has "N,N"s at all the right places.
    The template array is this: ("data1", "N,N", "data2", "N,N", "data3", "N,N").
(3) From the 2nd token, determine the index of the template array that you want to update.
    So, for example, if the 2nd token is "data1", you extract 1 from it and you know that the "N,N" after "data1" is to be updated.
(4) Update the template array at the relevant index.

- Read "data1" -> extract 1 -> update index 2*1 - 1 = 1 of array ("data1", "N,N", "data2", "N,N", "data3", "N,N")
- Read "data2" -> extract 2 -> update index 2*2 - 1 = 3 of array ("data1", "N,N", "data2", "N,N", "data3", "N,N")
- Read "data3" -> extract 3 -> update index 2*3 - 1 = 5 of array ("data1", "N,N", "data2", "N,N", "data3", "N,N")

$
$ # check the data file
$ cat -n test.txt
     1  SN1     data1   A,A
     2  SN1     data2   A,B
     3  SN1     data3   A,C
     4  AC2     data1   A,B
     5  AC2     data2   A,C
     6  TP3     data3   C,C
     7  TP3     data1   C,A
$
$ # check the program file
$ cat -n process_test.pl
     1  #!/usr/bin/perl
     2  use strict;
     3  use warnings;
     4
     5  die "Specify filename\n" if not defined $ARGV[0];       # Ask for filename
     6  my %compare;                                            # Declare the hash to store all information
     7  my $file = $ARGV[0];                                    # Assign the filename to a variable
     8  open (FH, "<", $file) or die "Can't open $file: $!";    # Open the file handle; balk on error
     9  while (<FH>) {                                          # Loop through the file, line by line
    10    chomp;                                                # Remove the End-of-Line character
    11    my @tokens = split/\t+/;                              # Split line on Tab and assign to array "tokens"
    12    if (not defined $compare{$tokens[0]}) {               # If 1st element of "tokens" is not a key, then
    13      $compare{$tokens[0]} = [ "data1", "N,N",            # Create the key in the "compare" hash and
    14                               "data2", "N,N",            # assign a template value with default "N,N"s
    15                               "data3", "N,N"             # The [] returns a reference to the array, since
    16                             ];                           # the hash value must be a scalar in Perl.
    17    }
    18    (my $index = $tokens[1]) =~ s/\D+//;                  # Determine the array index to be updated
    19    $compare{$tokens[0]}->[2*$index-1] = $tokens[2];      # And then update the array
    20  }                                                       # Done reading the file
    21  close (FH) or die "Can't close $file: $!";              # So close it; balk on error
    22  while (my ($k, $v) = each %compare) {                   # Loop through the hash
    23    printf ("%s %s\n", $k, join (" ", @{$compare{$k}}));  # and print out the keys and values
    24  }
$
$ # A dry run
$ perl process_test.pl
Specify filename
$
$ # A successful run
$ perl process_test.pl test.txt
AC2 data1 A,B data2 A,C data3 N,N
TP3 data1 C,A data2 N,N data3 C,C
SN1 data1 A,A data2 A,B data3 A,C
$
$