1 | #!/usr/bin/perl |
---|
2 | |
---|
3 | @quant=( |
---|
4 | 0, 1, 1, 2, 2, 3, 3, 4, 4, 4, 5, 5, 5, 5, 6, 6, 6, |
---|
5 | 6, 7, 7, 7, 7, 7, 8, 8, 8, 8, 8, 8, 9, 9, 9, 9, 9, 9, |
---|
6 | 9, 10, 10, 10, 10, 10, 10, 10, 10, 10, 11, 11, 11, 11, 11, 11, 11, 11, |
---|
7 | 11, 11, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, |
---|
8 | 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12 |
---|
9 | ); |
---|
10 | |
---|
11 | |
---|
12 | use POSIX; |
---|
13 | my($groupn)=@ARGV; |
---|
14 | my%hash; |
---|
15 | my$count=0; |
---|
16 | my$lines=0; |
---|
17 | |
---|
18 | if(!defined($groupn)){ |
---|
19 | print "Usage: residue_entropy <groupsize> \n"; |
---|
20 | exit(1); |
---|
21 | } |
---|
22 | $|=1; |
---|
23 | |
---|
24 | while (<STDIN>) { |
---|
25 | chop; |
---|
26 | my@nums = (); |
---|
27 | @nums = split(/,/); |
---|
28 | $lines++; |
---|
29 | |
---|
30 | my$step=$#nums/$groupn; |
---|
31 | for(my$i=0;$i<$step;$i++){ |
---|
32 | my$key=""; |
---|
33 | for(my$j=$i;$j<$#nums;$j+=$step){ |
---|
34 | if($nums[$j]<0){ |
---|
35 | $num=-$quant[int(-$nums[$j]*2)]; |
---|
36 | }else{ |
---|
37 | $num=$quant[int($nums[$j]*2)]; |
---|
38 | } |
---|
39 | $key.=":$num"; |
---|
40 | } |
---|
41 | |
---|
42 | if(!defined($hash{$key})){ |
---|
43 | $count++; |
---|
44 | $hash{$key}=1; |
---|
45 | } |
---|
46 | } |
---|
47 | |
---|
48 | if(($lines % 1000)==0){ |
---|
49 | print "\rworking... $lines lines, found $count values so far"; |
---|
50 | } |
---|
51 | } |
---|
52 | |
---|
53 | foreach $key (keys %hash){ |
---|
54 | print "\t$key\n"; |
---|
55 | } |
---|
56 | |
---|
57 | print "\r$count values total \n"; |
---|
58 | print "Done.\n\n"; |
---|