Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Multifastas not created when group limit (default 8000) exceeded #80

Merged
merged 3 commits into from
Nov 4, 2014
Merged

Multifastas not created when group limit (default 8000) exceeded #80

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
1d4e269
Limiting cluster number
Nov 4, 2014
d77713b
Merge branch 'master' of https://github.com/carlacummins/Bio-PanGenome
Nov 4, 2014
b4eee64
Multifastas not created when group limit (default 8000) exceeded
Nov 4, 2014
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
18 changes: 17 additions & 1 deletion lib/Bio/PanGenome/Output/GroupsMultifastasNucleotide.pm
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -28,16 +28,32 @@ has 'annotate_groups' => ( is => 'ro', isa => 'Bio::PanGenome::AnnotateGroups',

has 'output_directory' => ( is => 'ro', isa => 'Str', lazy => 1, builder => '_build_output_directory');

has '_number_of_groups' => ( is => 'rw', isa => 'Num', lazy_build => 1 );
has '_group_limit' => ( is => 'rw', isa => 'Num', default => 8000 );

sub _build_output_directory
{
my ($self) = @_;
my $output_directory = 'pan_genome_sequences';
return $output_directory;
}

sub _build__number_of_groups {
my $self = shift;

return $self->annotate_groups->_group_counter;
}

sub create_files {
my ($self) = @_;


my $num_groups = $self->_number_of_groups;
my $limit = $self->_group_limit;
if ( $num_groups > $limit ){
print STDERR "Number of clusters ($num_groups) exceeds limit ($limit). Multifastas not created.\n";
return 1;
}

make_path($self->output_directory);

for my $gff_file ( @{ $self->gff_files } )
Expand Down
20 changes: 10 additions & 10 deletions lib/Bio/PanGenome/PostAnalysis.pm
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -181,19 +181,19 @@ sub _delete_intermediate_files
my ($self) = @_;
return if($self->dont_delete_files == 1);

unlink($self->_output_mcl_filename) ;
unlink($self->_output_inflate_clusters_filename) ;
unlink($self->_output_group_labels_filename) ;
unlink($self->_output_combined_filename) ;
unlink($self->_output_mcl_filename) ;
unlink($self->_output_inflate_clusters_filename) ;
unlink($self->_output_group_labels_filename) ;
unlink($self->_output_combined_filename) ;
unlink($self->clusters_filename) ;
unlink($self->clusters_filename . '.clstr' ) ;
unlink($self->clusters_filename . '.bak.clstr' ) ;
unlink('_gff_files') ;
unlink('_fasta_files') ;
unlink('_clustered_filtered.fa') ;
unlink($self->_input_cd_hit_groups_file) ;
unlink('database_masking.asnb') ;
unlink('_clustered') ;
unlink('_gff_files') ;
unlink('_fasta_files') ;
unlink('_clustered_filtered.fa') ;
unlink($self->_input_cd_hit_groups_file) ;
unlink('database_masking.asnb') ;
unlink('_clustered') ;
}

no Moose;
Expand Down
25 changes: 22 additions & 3 deletions t/Bio/PanGenome/Output/GroupsMultifastasNucleotide.t
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,6 +9,7 @@ BEGIN { unshift( @INC, './lib' ) }

BEGIN {
use Test::Most;
use Test::Output;
use_ok('Bio::PanGenome::Output::GroupsMultifastasNucleotide');
use Bio::PanGenome::AnnotateGroups;
use Bio::PanGenome::AnalyseGroups;
Expand All @@ -18,6 +19,7 @@ BEGIN {
remove_tree('pan_genome_sequences');
my $gff_files = [ 't/data/query_1.gff', 't/data/query_2.gff','t/data/query_3.gff' ];

my $obj;

my $annotate_groups = Bio::PanGenome::AnnotateGroups->new(
gff_files => $gff_files,
Expand All @@ -26,10 +28,14 @@ my $annotate_groups = Bio::PanGenome::AnnotateGroups->new(

$annotate_groups->reannotate;

#print Dumper $annotate_groups->_genes_to_file;
#print Dumper $annotate_groups;
#print $annotate_groups->_group_counter;

ok(
my $obj = Bio::PanGenome::Output::GroupsMultifastasNucleotide->new(
group_names => [ 'group_2', 'group_5' ],
gff_files => $gff_files,
$obj = Bio::PanGenome::Output::GroupsMultifastasNucleotide->new(
group_names => [ 'group_2', 'group_5' ],
gff_files => $gff_files,
annotate_groups => $annotate_groups
),
'initialise creating multiple fastas'
Expand All @@ -44,4 +50,17 @@ is(read_file('pan_genome_sequences/group_6.fa'), read_file('t/data/pan_genome_se
is(read_file('pan_genome_sequences/yfnB.fa'), read_file('t/data/pan_genome_sequences/yfnB.fa' ), 'Check multifasta content is correct for 1-yfnB.fa ');
remove_tree('pan_genome_sequences');

# test group number limit
ok(
$obj = Bio::PanGenome::Output::GroupsMultifastasNucleotide->new(
group_names => [ 'group_2', 'group_5' ],
gff_files => $gff_files,
annotate_groups => $annotate_groups,
_group_limit => 4
),
'initialise creating multiple fastas'
);
my $exp_stderr = "Number of clusters (8) exceeds limit (4). Multifastas not created.\n";
stderr_is { $obj->create_files() } $exp_stderr, 'multifasta creation fails when group limit exceeded';

done_testing();