line |
stmt |
bran |
cond |
sub |
pod |
time |
code |
1
|
|
|
|
|
|
|
package BioX::SeqUtils::Promoter::Alignment; |
2
|
|
|
|
|
|
|
#################################################################### |
3
|
|
|
|
|
|
|
# Charles Stephen Embry # |
4
|
|
|
|
|
|
|
# MidSouth Bioinformatics Center # |
5
|
|
|
|
|
|
|
# University of Arkansas Little Rock # |
6
|
|
|
|
|
|
|
#################################################################### |
7
|
1
|
|
|
1
|
|
4862
|
use base qw(BioX::SeqUtils::Promoter::Base); |
|
1
|
|
|
|
|
3
|
|
|
1
|
|
|
|
|
12896
|
|
8
|
|
|
|
|
|
|
use Class::Std; |
9
|
|
|
|
|
|
|
use Class::Std::Utils; |
10
|
|
|
|
|
|
|
use BioX::SeqUtils::Promoter::Sequences; |
11
|
|
|
|
|
|
|
use BioX::SeqUtils::Promoter::Annotations; |
12
|
|
|
|
|
|
|
use BioX::SeqUtils::Promoter::Annotations::Consensus; |
13
|
|
|
|
|
|
|
use BioX::SeqUtils::Promoter::SaveTypes; |
14
|
|
|
|
|
|
|
use warnings; |
15
|
|
|
|
|
|
|
use strict; |
16
|
|
|
|
|
|
|
use Carp; |
17
|
|
|
|
|
|
|
use Bio::Perl; |
18
|
|
|
|
|
|
|
use Bio::Seq; |
19
|
|
|
|
|
|
|
use Bio::SeqIO; |
20
|
|
|
|
|
|
|
use Bio::Tools::Run::Alignment::TCoffee; |
21
|
|
|
|
|
|
|
|
22
|
|
|
|
|
|
|
use version; our $VERSION = qv('0.1.1'); |
23
|
|
|
|
|
|
|
|
24
|
|
|
|
|
|
|
{ |
25
|
|
|
|
|
|
|
my %sequences_of :ATTR( :get :set :default<''> :init_arg ); |
26
|
|
|
|
|
|
|
|
27
|
|
|
|
|
|
|
sub BUILD { |
28
|
|
|
|
|
|
|
my ($self, $ident, $arg_ref) = @_; |
29
|
|
|
|
|
|
|
|
30
|
|
|
|
|
|
|
|
31
|
|
|
|
|
|
|
return; |
32
|
|
|
|
|
|
|
} |
33
|
|
|
|
|
|
|
|
34
|
|
|
|
|
|
|
sub START { |
35
|
|
|
|
|
|
|
my ($self, $ident, $arg_ref) = @_; |
36
|
|
|
|
|
|
|
my $sequences = BioX::SeqUtils::Promoter::Sequences->new(); |
37
|
|
|
|
|
|
|
$self->set_sequences($sequences); |
38
|
|
|
|
|
|
|
return; |
39
|
|
|
|
|
|
|
} |
40
|
|
|
|
|
|
|
|
41
|
|
|
|
|
|
|
sub annotate { |
42
|
|
|
|
|
|
|
my ($self, $arg_ref) = @_; |
43
|
|
|
|
|
|
|
my $filename = defined $arg_ref->{filename} ? $arg_ref->{filename} : ''; |
44
|
|
|
|
|
|
|
my $annotations = BioX::SeqUtils::Promoter::Annotations->new({type => 'Consensus', motifs => $self->get_default_motifs() }); |
45
|
|
|
|
|
|
|
$annotations->print_motifs(); |
46
|
|
|
|
|
|
|
|
47
|
|
|
|
|
|
|
return; |
48
|
|
|
|
|
|
|
} |
49
|
|
|
|
|
|
|
|
50
|
|
|
|
|
|
|
sub m_align { |
51
|
|
|
|
|
|
|
my ($self, $arg_ref) = @_; |
52
|
|
|
|
|
|
|
#a file of fasta sequences will be a parameter |
53
|
|
|
|
|
|
|
my $afilename = defined $arg_ref->{afilename} ? $arg_ref->{afilename} : ''; |
54
|
|
|
|
|
|
|
#matrix used multiple alignment, can be Pam, Blosum or none |
55
|
|
|
|
|
|
|
my $matrix = defined $arg_ref->{matrix} ? $arg_ref->{matrix} : ''; |
56
|
|
|
|
|
|
|
#the pentaly for opening a gap in the alignment |
57
|
|
|
|
|
|
|
my $gap_open = defined $arg_ref->{gap_open} ? $arg_ref->{gap_open} : ''; |
58
|
|
|
|
|
|
|
#the pentaly for exiting a gap |
59
|
|
|
|
|
|
|
my $gap_ext = defined $arg_ref->{gap_ext} ? $arg_ref->{gap_ext} : ''; |
60
|
|
|
|
|
|
|
#name and location of output file |
61
|
|
|
|
|
|
|
my $outfile = '/home/stephen/BioCapstone/BioX-SeqUtils-Promoter/data/tnrab1000'; |
62
|
|
|
|
|
|
|
# Build a tcoffee alignment factory |
63
|
|
|
|
|
|
|
#my @params = ('ktuple' => 2, 'matrix' => 'BLOSUM', 'OUTFILE' => tnrab1000.aln ); |
64
|
|
|
|
|
|
|
my @params = ('ktuple' => 2, 'matrix' => $matrix, 'GAPOPEN' => $gap_open, 'GAPEXT' => $gap_ext, 'OUTFILE' => $outfile); |
65
|
|
|
|
|
|
|
#my @params = ('ktuple' => 2, 'matrix' => 'Pam', 'GAPOPEN' => 10, 'GAPEXT' => 2, 'OUTFILE' => p_GO10GE2_hexr ); |
66
|
|
|
|
|
|
|
#my @params = ('ktuple' => 2, 'matrix' => 'BLOSUM', 'OUTFILE' => $outfile); |
67
|
|
|
|
|
|
|
# feed a list of parameters to Tcoffee |
68
|
|
|
|
|
|
|
my $factory = Bio::Tools::Run::Alignment::TCoffee->new(@params); |
69
|
|
|
|
|
|
|
# Pass the factory a list of sequences to be aligned. |
70
|
|
|
|
|
|
|
# $aln is a SimpleAlign object. |
71
|
|
|
|
|
|
|
my $aln = $factory->align($afilename); |
72
|
|
|
|
|
|
|
|
73
|
|
|
|
|
|
|
return; |
74
|
|
|
|
|
|
|
} |
75
|
|
|
|
|
|
|
|
76
|
|
|
|
|
|
|
sub load_alignmentfile { |
77
|
|
|
|
|
|
|
my ($self, $arg_ref) = @_; |
78
|
|
|
|
|
|
|
#load a output file from a multiple sequence alignment |
79
|
|
|
|
|
|
|
my $filename = defined $arg_ref->{filename} ? $arg_ref->{filename} : ''; |
80
|
|
|
|
|
|
|
my $text; |
81
|
|
|
|
|
|
|
#my $line; |
82
|
|
|
|
|
|
|
my $sequences = $self->get_sequences(); |
83
|
|
|
|
|
|
|
|
84
|
|
|
|
|
|
|
open(IN,"<$filename"); |
85
|
|
|
|
|
|
|
|
86
|
|
|
|
|
|
|
# takes each gene name and uses it as a key for a hash and the data for teh values |
87
|
|
|
|
|
|
|
; |
88
|
|
|
|
|
|
|
while($text = ){ |
89
|
|
|
|
|
|
|
if($text) { |
90
|
|
|
|
|
|
|
#if($text =~/^$|^\s/){print "blank line\n"; next;} |
91
|
|
|
|
|
|
|
if($text =~/^$|^\s/){next;} |
92
|
|
|
|
|
|
|
my ($key, $value) = split /\s+/, $text; |
93
|
|
|
|
|
|
|
$sequences->add_segment({label => $key, sequence => $value}); |
94
|
|
|
|
|
|
|
} |
95
|
|
|
|
|
|
|
} |
96
|
|
|
|
|
|
|
my $seqs = $sequences->get_sequences(); |
97
|
|
|
|
|
|
|
foreach my $key (keys %$seqs ){ print $seqs->{$key}->get_sequence(),"\n"; } |
98
|
|
|
|
|
|
|
|
99
|
|
|
|
|
|
|
return; |
100
|
|
|
|
|
|
|
} |
101
|
|
|
|
|
|
|
|
102
|
|
|
|
|
|
|
} |
103
|
|
|
|
|
|
|
|
104
|
|
|
|
|
|
|
1; # Magic true value required at end of module |
105
|
|
|
|
|
|
|
__END__ |