Core alignment missing file

lib/Bio/PanGenome/CommandLine/CreatePanGenome.pm

@@ -56,6 +56,7 @@ sub BUILD {
         'h|help'                    => \$help,
     );
 
+    $self->help($help) if(defined($help));
     if ( @{ $self->args } == 0 ) {
         $self->_error_message("Error: You need to provide a GFF file");
     }

lib/Bio/PanGenome/CommandLine/ExtractProteomeFromGff.pm

@@ -34,6 +34,7 @@ sub BUILD {
         'h|help'                  => \$help,
     );
 
+    $self->help($help) if(defined($help));
     if ( @{ $self->args } == 0 ) {
         $self->_error_message("Error: You need to provide a GFF file");
     }

lib/Bio/PanGenome/CommandLine/IterativeCdhit.pm

@@ -45,6 +45,7 @@ sub BUILD {
         'h|help'                              => \$help,
     );
 
+    $self->help($help) if(defined($help));
     $self->lower_bound_percentage($lower_bound_percentage/100) if ( defined($lower_bound_percentage) );
     $self->upper_bound_percentage($upper_bound_percentage/100) if ( defined($upper_bound_percentage) );
     $self->step_size_percentage($step_size_percentage/100)     if ( defined($step_size_percentage) );

lib/Bio/PanGenome/CommandLine/MergeMultipleFastaAlignments.pm

@@ -31,6 +31,7 @@ sub BUILD {
         'h|help'              => \$help,
     );
 
+    $self->help($help) if(defined($help));
     if ( @{ $self->args } < 2 ) {
         $self->_error_message("Error: You need to provide at least 2 FASTA files");
     }

lib/Bio/PanGenome/CommandLine/PanGenomeCoreAlignment.pm

@@ -36,6 +36,8 @@ sub BUILD {
         'o|output_filename=s'           => \$output_filename,
         'h|help'                        => \$help,
     );
+
+    $self->help($help) if(defined($help));
 
     if ( defined($multifasta_base_directory) && ( -d $multifasta_base_directory ) ) {
         $self->multifasta_base_directory( abs_path($multifasta_base_directory));

lib/Bio/PanGenome/CommandLine/PanGenomePostAnalysis.pm

@@ -51,6 +51,7 @@ sub BUILD {
         'h|help'                  => \$help,
     );
 
+    $self->help($help) if(defined($help));
     $self->job_runner($job_runner)                                   if (defined($job_runner) );
     $self->fasta_files($fasta_files)                                 if (defined($fasta_files));
     $self->input_files($input_files)                                 if (defined($input_files));

lib/Bio/PanGenome/CommandLine/PanGenomeReorderSpreadsheet.pm

@@ -35,6 +35,7 @@ sub BUILD {
         'h|help'                   => \$help,
     );
 
+    $self->help($help) if(defined($help));
     $self->output_filename($output_filename)           if ( defined($output_filename) );
     $self->tree_file($tree_file)                       if ( defined($tree_file) );
     $self->tree_format($tree_format)                   if ( defined($tree_format) );

lib/Bio/PanGenome/CommandLine/ParallelAllAgainstAllBlastp.pm

@@ -44,6 +44,7 @@ sub BUILD {
         $self->_error_message("Error: You need to provide a FASTA file");
     }
 
+    $self->help($help) if(defined($help));
     $self->output_filename($output_filename)   if ( defined($output_filename) );
     $self->job_runner($job_runner)             if ( defined($job_runner) );
     $self->makeblastdb_exec($makeblastdb_exec) if ( defined($makeblastdb_exec) );

lib/Bio/PanGenome/CommandLine/ProteinMuscleAlignmentFromNucleotides.pm

@@ -14,6 +14,7 @@ use Bio::PanGenome::AnnotateGroups;
 use Bio::PanGenome::External::Muscle;
 use Bio::PanGenome::External::Revtrans;
 use Bio::PanGenome::Output::GroupsMultifastaProtein;
+use Bio::PanGenome::SortFasta;
 
 
 has 'args'        => ( is => 'ro', isa => 'ArrayRef', required => 1 );
@@ -33,6 +34,7 @@ sub BUILD {
         'h|help'              => \$help,
     );
 
+    $self->help($help) if(defined($help));
     if ( @{ $self->args } == 0 ) {
         $self->_error_message("Error: You need to provide at least 1 FASTA file");
     }
@@ -57,6 +59,12 @@ sub run {
 
     for my $fasta_file (@{$self->nucleotide_fasta_files})
     {
+
+      my $sort_fasta_before = Bio::PanGenome::SortFasta->new(
+         input_filename   => $fasta_file,
+       );
+      $sort_fasta_before->sort_fasta->replace_input_with_output_file;
+
       my $multifasta_protein_obj = Bio::PanGenome::Output::GroupsMultifastaProtein->new(
           nucleotide_fasta_file => $fasta_file,
         );
@@ -67,13 +75,24 @@ sub run {
         job_runner  => 'Local'
       );
       $seg->run();
+
+      my $sort_fasta_after_muscle = Bio::PanGenome::SortFasta->new(
+         input_filename   => $multifasta_protein_obj->output_filename. '.aln',
+       );
+      $sort_fasta_after_muscle->sort_fasta->replace_input_with_output_file;
 
       my $revtrans= Bio::PanGenome::External::Revtrans->new(
         nucleotide_filename => $fasta_file,
         protein_filename  => $multifasta_protein_obj->output_filename. '.aln',
         output_filename   => $fasta_file.'.aln'
       );
       $revtrans->run();
+
+      my $sort_fasta_after_revtrans = Bio::PanGenome::SortFasta->new(
+         input_filename   => $fasta_file.'.aln',
+       );
+      $sort_fasta_after_revtrans->sort_fasta->replace_input_with_output_file;
+
       unlink($multifasta_protein_obj->output_filename);
       unlink($multifasta_protein_obj->output_filename. '.aln');
     }

lib/Bio/PanGenome/CommandLine/QueryPanGenome.pm

@@ -50,14 +50,16 @@ sub BUILD {
         'h|help'              => \$help,
     );
 
+    $self->help($help) if(defined($help));
+
     $self->output_filename($output_filename) if ( defined($output_filename) );
     $self->action($action)                   if ( defined($action) );
     if ( defined($groups_filename) && ( -e $groups_filename ) ) {
         $self->groups_filename($groups_filename);
     }
 
-    if(! (-e $self->groups_filename($groups_filename))) {
-        $self->_error_message("Error: Cant access the groups file $groups_filename");
+    if(! (-e $self->groups_filename)) {
+        $self->_error_message("Error: Cant access the groups file: ".$self->groups_filename);
     }
 
     @group_names = split( /,/, join( ',', @group_names ) );

lib/Bio/PanGenome/CommandLine/TransferAnnotationToGroups.pm

@@ -35,6 +35,7 @@ sub BUILD {
         'h|help'              => \$help,
     );
 
+    $self->help($help) if(defined($help));
     if ( @{ $self->args } == 0 ) {
         $self->_error_message("Error: You need to provide a FASTA file");
     }

lib/Bio/PanGenome/External/ProteinMuscleAlignmentFromNucleotides.pm

@@ -29,7 +29,7 @@ has 'exec'          => ( is => 'ro', isa => 'Str',      default  => 'protein_mus
 # Overload Role
 has '_memory_required_in_mb' => ( is => 'ro', isa => 'Int', lazy     => 1, builder => '_build__memory_required_in_mb' );
 has '_queue'                 => ( is => 'rw', isa => 'Str', default  => 'normal' );
-has '_files_per_chunk'       => ( is => 'ro', isa => 'Int', default  => 20 );
+has '_files_per_chunk'       => ( is => 'ro', isa => 'Int', default  => 25 );
 
 sub _build__memory_required_in_mb {
     my ($self)          = @_;
@@ -68,7 +68,8 @@ sub run {
         dont_wait       => $self->dont_wait,
     );
     $job_runner_obj->run();
-
+
+    $job_runner_obj->submit_dependancy_job('pan_genome_core_alignment');
     1;
 }
 

lib/Bio/PanGenome/JobRunner/LSF.pm

@@ -23,7 +23,8 @@ has 'commands_to_run' => ( is => 'ro', isa => 'ArrayRef',        required => 1 )
 has 'memory_in_mb'    => ( is => 'ro', isa => 'Int',             default  => 500 );
 has 'queue'           => ( is => 'ro', isa => 'Str',             default  => 'normal' );
 has '_job_manager'    => ( is => 'ro', isa => 'LSF::JobManager', lazy     => 1, builder => '_build__job_manager' );
-has 'dont_wait'       => ( is => 'rw', isa => 'Bool', default => 0 );
+has 'dont_wait'       => ( is => 'rw', isa => 'Bool',            default  => 0 );
+has 'job_ids'         => ( is => 'ro', isa => 'ArrayRef',        default  => {[]} );
 
 sub _build__job_manager {
     my ($self) = @_;
@@ -46,11 +47,25 @@ sub _submit_job {
     );
 }
 
+sub _construct_dependancy_params
+{
+   my ($self, $ids) = @_;
+   return '' if((! defined($ids)) || @{$ids} == 0);
+
+   my @done_ids;
+   for my $id ( @{$ids})
+   {
+     push(@done_ids, 'done('.$id.')');
+   }
+   return join('&&', @done_ids);
+}
+
 
 sub run {
     my ($self) = @_;
     for my $command_to_run ( @{ $self->commands_to_run } ) {
-        $self->_submit_job($command_to_run);
+        my $job_id = $self->_submit_job($command_to_run);
+        push(@{$self->job_ids}, $job_id);    
     }
 
     if(!(defined($self->dont_wait) && $self->dont_wait == 1 ))
@@ -60,6 +75,19 @@ sub run {
     1;
 }
 
+sub submit_dependancy_job {
+    my ( $self,$command_to_run) = @_;
+    $self->_job_manager->submit(
+        -o => "out.o",
+        -e => "out.e",
+        -M => $self->memory_in_mb,
+        -R => $self->_generate_memory_parameter,
+        -w => $self->_construct_dependancy_params($self->job_ids),
+        $command_to_run
+    );
+}
+
+
 no Moose;
 __PACKAGE__->meta->make_immutable;
 

lib/Bio/PanGenome/JobRunner/Local.pm

@@ -26,6 +26,19 @@ sub run {
     }
     1;
 }
+
+
+sub _construct_dependancy_params
+{
+  my ($self) = @_;
+  return '';
+}
+
+sub submit_dependancy_job {
+    my ( $self,$command_to_run) = @_;
+    system($command_to_run );
+}
+
 no Moose;
 __PACKAGE__->meta->make_immutable;
 

lib/Bio/PanGenome/SortFasta.pm

@@ -0,0 +1,68 @@
+package Bio::PanGenome::SortFasta;
+
+# ABSTRACT: sort a fasta file by name
+
+=head1 SYNOPSIS
+
+sort a fasta file by name
+   use Bio::PanGenome::SortFasta;
+
+   my $obj = Bio::PanGenome::SortFasta->new(
+     input_filename   => 'infasta.fa',
+   );
+   $obj->sort_fasta->replace_input_with_output_file;
+
+=cut
+
+use Moose;
+use File::Copy;
+use Bio::SeqIO;
+
+has 'input_filename'  => ( is => 'ro', isa => 'Str', required => 1 );
+has 'output_filename' => ( is => 'ro', isa => 'Str', lazy => 1, builder => '_build_output_filename' );
+
+has '_input_seqio'  => ( is => 'ro', isa => 'Bio::SeqIO', lazy => 1, builder => '_build__input_seqio' );
+has '_output_seqio' => ( is => 'ro', isa => 'Bio::SeqIO', lazy => 1, builder => '_build__output_seqio' );
+
+sub _build_output_filename
+{
+  my ($self) = @_;
+  return $self->input_filename.".sorted.fa";
+}
+
+sub _build__input_seqio {
+    my ($self) = @_;
+    return Bio::SeqIO->new( -file => $self->input_filename, -format => 'Fasta' );
+}
+
+sub _build__output_seqio {
+    my ( $self) = @_;
+    return Bio::SeqIO->new( -file => ">".$self->output_filename, -format => 'Fasta' );
+}
+
+sub sort_fasta {
+    my ($self) = @_;
+
+    my %input_sequences;
+    while ( my $input_seq = $self->_input_seqio->next_seq() ) {
+       $input_sequences{$input_seq->display_id} = $input_seq;
+    }
+
+    for my $sequence_name(sort  keys %input_sequences)
+    {
+      $self->_output_seqio->write_seq($input_sequences{$sequence_name});
+    }
+    return $self;
+}
+
+sub replace_input_with_output_file
+{
+  my ($self) = @_;
+  move($self->output_filename, $self->input_filename);
+  return $self;
+}
+
+no Moose;
+__PACKAGE__->meta->make_immutable;
+
+1;

t/Bio/PanGenome/CommandLine/CreatePanGenome.t

@@ -12,28 +12,42 @@ with 'TestHelper';
 BEGIN {
     use Test::Most;
     use_ok('Bio::PanGenome::CommandLine::CreatePanGenome');
+    use Bio::PanGenome::SequenceLengths;
 }
 my $script_name = 'Bio::PanGenome::CommandLine::CreatePanGenome';
 my $cwd = getcwd();
 
 local $ENV{PATH} = "$ENV{PATH}:./bin";
 my %scripts_and_expected_files;
+system('touch empty_file');
+
 %scripts_and_expected_files = (
        ' -j Local  --dont_create_rplots t/data/query_1.gff t/data/query_2.gff t/data/query_6.gff ' =>
        [ 'clustered_proteins', 't/data/clustered_proteins_pan_genome' ],
       ' -j Local --dont_create_rplots  t/data/query_1.gff t/data/query_2.gff t/data/query_6.gff    ' =>
           [ 'group_statisics.csv', 't/data/overall_group_statisics.csv' ],              
+          '-h' =>
+            [ 'empty_file', 't/data/empty_file' ],
 );
 mock_execute_script_and_check_output( $script_name, \%scripts_and_expected_files, [6,7,8,9] );
 cleanup_files();
 
 
 %scripts_and_expected_files = (
-  ' -j Local --dont_create_rplots --output_multifasta_files t/data/query_1.gff t/data/query_2.gff t/data/query_6.gff  ' =>
-    [ 'pan_genome_sequences/speH.fa.aln', 't/data/speH.fa.aln' ],
+  ' -j Local --dont_create_rplots --output_multifasta_files t/data/real_data_1.gff t/data/real_data_2.gff' =>
+    [ 'pan_genome_sequences/sopB.fa.aln', 't/data/sopB.fa.aln' ],
 );
 mock_execute_script_and_check_output( $script_name, \%scripts_and_expected_files );
 
+
+ok(my $seq_len = Bio::PanGenome::SequenceLengths->new(
+  fasta_file   => 'core_gene_alignment.aln',
+), 'Check size of the core_gene_alignment.aln init');
+
+is($seq_len->sequence_lengths->{'11111_1#11'}, 58389, 'length of first sequence');
+
+
+
 ok(-e 'accessory.tab');
 ok(-e 'core_accessory.tab');
 ok(-e 'number_of_conserved_genes.Rtab');
@@ -69,5 +83,11 @@ sub cleanup_files
   unlink('number_of_new_genes.Rtab');
   unlink('number_of_unique_genes.Rtab');
   unlink('query_6.gff.proteome.faa');
+  unlink('core_gene_alignment.aln');  
+  unlink('blast_identity_frequency.Rtab');
+  unlink('real_data_1.gff.proteome.faa');
+  unlink('real_data_2.gff.proteome.faa');
+  unlink('accessory.header.embl');
+  unlink('core_accessory.header.embl');
 
 }

t/Bio/PanGenome/CommandLine/ExtractProteomeFromGff.t

@@ -14,10 +14,12 @@ BEGIN {
 }
 my $script_name = 'Bio::PanGenome::CommandLine::ExtractProteomeFromGff';
 my $cwd         = getcwd();
-
+system('touch empty_file');
 my %scripts_and_expected_files = (
     't/data/example_annotation.gff' =>
       ['example_annotation.gff.proteome.faa','t/data/example_annotation.gff.proteome.faa.expected' ],
+      '-h' =>
+        [ 'empty_file', 't/data/empty_file' ],
 );
 
 mock_execute_script_and_check_output( $script_name, \%scripts_and_expected_files );

t/Bio/PanGenome/CommandLine/MergeMultipleFastaAlignments.t

@@ -13,12 +13,14 @@ BEGIN {
     use_ok('Bio::PanGenome::CommandLine::MergeMultipleFastaAlignments');
 }
 my $script_name = 'Bio::PanGenome::CommandLine::MergeMultipleFastaAlignments';
-
+system('touch empty_file');
 my %scripts_and_expected_files = (
     't/data/multfasta1.aln t/data/multfasta2.aln t/data/multfasta3.aln' =>
       [ 'merged_alignments.aln', 't/data/expected_output_merged.aln' ],
     '-o different_output_file.aln t/data/multfasta1.aln t/data/multfasta2.aln t/data/multfasta3.aln' =>
       [ 'different_output_file.aln', 't/data/expected_output_merged.aln' ],
+      '-h' =>
+        [ 'empty_file', 't/data/empty_file' ],
 );
 
 mock_execute_script_and_check_output( $script_name, \%scripts_and_expected_files );