1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
|
#!/usr/bin/perl
# Katharina J. Hoff
# November 20th 2018
use strict;
use warnings;
use Getopt::Long;
my $usage = << 'ENDUSAGE';
compare_masking compare the repeat masking content of differently masked (same) assemblies
SYNOPSIS
compare_masking file1.fa file2.fa
file1.fa softmasked fasta file
file2.fa softmasked second fasta file
OPTIONS
--help output this help message
WARNING: This script keeps two assemblies in memory, i.e. it is not suitable for large genomes!
ENDUSAGE
my ($help);
GetOptions('help' => \$help);
if($help){
print $usage;
exit(1);
}
my %masking1;
my $key;
open(FILE1, "<", $ARGV[0]) or die ("Could not open file $ARGV[0]!\n");
while(<FILE1>){
chomp;
if(m/^>/){
$masking1{$_} = "";
$key = $_;
}else{
$masking1{$key} .= $_;
}
}
close(FILE1) or die ("Could not close file $ARGV[0]!\n");
my %masking2;
open(FILE2, "<", $ARGV[1]) or die ("Could not open file $ARGV[1]!\n");
while(<FILE2>){
chomp;
if(m/^>/){
$masking2{$_} = "";
$key = $_;
}else{
$masking2{$key} .= $_;
}
}
close(FILE2) or die ("Could not close file $ARGV[1]!\n");
my $only1 = 0;
my $only2 = 0;
my $both = 0;
while( my($key, $value) = each(%masking1)){
my @arr1 = split(//, $value);
my @arr2 = split(//, $masking2{$key});
my $counter = 0;
foreach(@arr1){
if( ($_ =~ m/\p{Lowercase}/) and ($arr2[$counter] =~ m/\p{Lowercase}/)){
$both++;
}elsif($_ =~ m/\p{Lowercase}/){
$only1++;
}elsif($arr2[$counter] =~ m/\p{Lowercase}/){
$only2++;
}
$counter++;
}
}
print("Masked in both files: $both\n");
print("Masked in File1, only: $only1\n");
print("Masked in File2, only: $only2\n");
|
