line |
stmt |
bran |
cond |
sub |
pod |
time |
code |
1
|
|
|
|
|
|
|
package Bio::Roary::UniqueGenesPerSample; |
2
|
|
|
|
|
|
|
$Bio::Roary::UniqueGenesPerSample::VERSION = '3.10.2'; |
3
|
|
|
|
|
|
|
# ABSTRACT: Take in the clustered file and produce a sorted file with the frequency of each samples unique genes |
4
|
|
|
|
|
|
|
|
5
|
|
|
|
|
|
|
|
6
|
1
|
|
|
1
|
|
151841
|
use Moose; |
|
1
|
|
|
|
|
512461
|
|
|
1
|
|
|
|
|
7
|
|
7
|
1
|
|
|
1
|
|
8960
|
use Bio::Roary::Exceptions; |
|
1
|
|
|
|
|
3
|
|
|
1
|
|
|
|
|
543
|
|
8
|
|
|
|
|
|
|
|
9
|
|
|
|
|
|
|
has 'clustered_proteins' => ( is => 'rw', isa => 'Str', default => 'clustered_proteins' ); |
10
|
|
|
|
|
|
|
has 'output_filename' => ( is => 'rw', isa => 'Str', default => 'unique_genes_per_sample.tsv' ); |
11
|
|
|
|
|
|
|
|
12
|
|
|
|
|
|
|
has '_output_fh' => ( is => 'ro', lazy => 1, builder => '_build__output_fh' ); |
13
|
|
|
|
|
|
|
|
14
|
|
|
|
|
|
|
sub _build__output_fh { |
15
|
1
|
|
|
1
|
|
4
|
my ($self) = @_; |
16
|
1
|
50
|
|
|
|
49
|
open( my $fh, '>', $self->output_filename ) |
17
|
|
|
|
|
|
|
or Bio::Roary::Exceptions::CouldntWriteToFile->throw( error => "Couldnt write output file:" . $self->output_filename ); |
18
|
1
|
|
|
|
|
45
|
return $fh; |
19
|
|
|
|
|
|
|
} |
20
|
|
|
|
|
|
|
|
21
|
|
|
|
|
|
|
#group_17585: 14520_6#21_00645 |
22
|
|
|
|
|
|
|
sub _sample_to_gene_freq { |
23
|
2
|
|
|
2
|
|
7
|
my ($self) = @_; |
24
|
|
|
|
|
|
|
|
25
|
2
|
50
|
|
|
|
159
|
open( my $input_fh, $self->clustered_proteins ) |
26
|
|
|
|
|
|
|
or Bio::Roary::Exceptions::FileNotFound->throw( error => "Couldnt read input file:" . $self->clustered_proteins ); |
27
|
|
|
|
|
|
|
|
28
|
2
|
|
|
|
|
9
|
my %sample_to_gene_freq; |
29
|
2
|
|
|
|
|
36
|
while (<$input_fh>) { |
30
|
12
|
|
|
|
|
27
|
chomp; |
31
|
12
|
|
|
|
|
22
|
my $line = $_; |
32
|
12
|
50
|
|
|
|
30
|
next if ( length( $line ) < 6 ); |
33
|
12
|
100
|
|
|
|
71
|
if ( $line =~ /^.+: ([^\s]+)$/ ) { |
34
|
10
|
|
|
|
|
31
|
my $gene_id = $1; |
35
|
10
|
50
|
|
|
|
45
|
if ( $gene_id =~ /^(.+)_[\d]+$/ ) { |
36
|
10
|
|
|
|
|
26
|
my $sample_name = $1; |
37
|
10
|
|
|
|
|
61
|
$sample_to_gene_freq{$sample_name}++; |
38
|
|
|
|
|
|
|
} |
39
|
|
|
|
|
|
|
else { |
40
|
|
|
|
|
|
|
# gene id may not be valid so ignore |
41
|
0
|
|
|
|
|
0
|
next; |
42
|
|
|
|
|
|
|
} |
43
|
|
|
|
|
|
|
} |
44
|
|
|
|
|
|
|
else { |
45
|
|
|
|
|
|
|
# its either an invalid line or theres more than 1 gene in the cluster |
46
|
2
|
|
|
|
|
10
|
next; |
47
|
|
|
|
|
|
|
} |
48
|
|
|
|
|
|
|
} |
49
|
|
|
|
|
|
|
|
50
|
2
|
|
|
|
|
49
|
return \%sample_to_gene_freq; |
51
|
|
|
|
|
|
|
} |
52
|
|
|
|
|
|
|
|
53
|
|
|
|
|
|
|
sub write_unique_frequency { |
54
|
1
|
|
|
1
|
0
|
5
|
my ($self) = @_; |
55
|
|
|
|
|
|
|
|
56
|
1
|
|
|
|
|
3
|
my %sample_to_gene_freq = %{$self->_sample_to_gene_freq}; |
|
1
|
|
|
|
|
4
|
|
57
|
|
|
|
|
|
|
|
58
|
1
|
50
|
|
|
|
14
|
for my $sample ( sort { $sample_to_gene_freq{$b} <=> $sample_to_gene_freq{$a} || $a cmp $b } keys %sample_to_gene_freq ) { |
|
5
|
|
|
|
|
24
|
|
59
|
4
|
|
|
|
|
10
|
print { $self->_output_fh } $sample . "\t" . $sample_to_gene_freq{$sample} . "\n"; |
|
4
|
|
|
|
|
143
|
|
60
|
|
|
|
|
|
|
} |
61
|
1
|
|
|
|
|
38
|
close($self->_output_fh); |
62
|
1
|
|
|
|
|
14
|
return 1; |
63
|
|
|
|
|
|
|
} |
64
|
|
|
|
|
|
|
|
65
|
1
|
|
|
1
|
|
8
|
no Moose; |
|
1
|
|
|
|
|
2
|
|
|
1
|
|
|
|
|
7
|
|
66
|
|
|
|
|
|
|
__PACKAGE__->meta->make_immutable; |
67
|
|
|
|
|
|
|
|
68
|
|
|
|
|
|
|
1; |
69
|
|
|
|
|
|
|
|
70
|
|
|
|
|
|
|
__END__ |
71
|
|
|
|
|
|
|
|
72
|
|
|
|
|
|
|
=pod |
73
|
|
|
|
|
|
|
|
74
|
|
|
|
|
|
|
=encoding UTF-8 |
75
|
|
|
|
|
|
|
|
76
|
|
|
|
|
|
|
=head1 NAME |
77
|
|
|
|
|
|
|
|
78
|
|
|
|
|
|
|
Bio::Roary::UniqueGenesPerSample - Take in the clustered file and produce a sorted file with the frequency of each samples unique genes |
79
|
|
|
|
|
|
|
|
80
|
|
|
|
|
|
|
=head1 VERSION |
81
|
|
|
|
|
|
|
|
82
|
|
|
|
|
|
|
version 3.10.2 |
83
|
|
|
|
|
|
|
|
84
|
|
|
|
|
|
|
=head1 SYNOPSIS |
85
|
|
|
|
|
|
|
|
86
|
|
|
|
|
|
|
Take in the clustered file and produce a sorted file with the frequency of each samples unique genes |
87
|
|
|
|
|
|
|
use Bio::Roary::UniqueGenesPerSample; |
88
|
|
|
|
|
|
|
|
89
|
|
|
|
|
|
|
my $obj = Bio::Roary::SequenceLengths->new( |
90
|
|
|
|
|
|
|
clustered_proteins => 'clustered_proteins', |
91
|
|
|
|
|
|
|
output_filename => 'output_filename', |
92
|
|
|
|
|
|
|
); |
93
|
|
|
|
|
|
|
$obj->write_unique_frequency; |
94
|
|
|
|
|
|
|
|
95
|
|
|
|
|
|
|
=head1 AUTHOR |
96
|
|
|
|
|
|
|
|
97
|
|
|
|
|
|
|
Andrew J. Page <ap13@sanger.ac.uk> |
98
|
|
|
|
|
|
|
|
99
|
|
|
|
|
|
|
=head1 COPYRIGHT AND LICENSE |
100
|
|
|
|
|
|
|
|
101
|
|
|
|
|
|
|
This software is Copyright (c) 2013 by Wellcome Trust Sanger Institute. |
102
|
|
|
|
|
|
|
|
103
|
|
|
|
|
|
|
This is free software, licensed under: |
104
|
|
|
|
|
|
|
|
105
|
|
|
|
|
|
|
The GNU General Public License, Version 3, June 2007 |
106
|
|
|
|
|
|
|
|
107
|
|
|
|
|
|
|
=cut |