view release on metacpan or  search on metacpan

lib/Bio/Roary/CommandLine/QueryRoary.pm  view on Meta::CPAN

            $prepare_input_files->lookup_fasta_files_from_unknown_input_files($self->input_set_two) 
          ],
        );
      $difference_between_sets->groups_set_one_unique();
      $difference_between_sets->groups_set_two_unique();
      $difference_between_sets->groups_in_common();
      
      for my $differences_group_filename(($difference_between_sets->groups_set_one_unique_filename,$difference_between_sets->groups_set_two_unique_filename,$difference_between_sets->groups_in_common_filename))
      {
        $self->create_spreadsheets($differences_group_filename, $prepare_input_files->fasta_files, $self->input_files);
      }

    }
    else {
        print "Nothing done\n";
    }
}

sub create_spreadsheets
{
      my ($self, $groups_file, $fasta_files, $gff_files) = @_;

      my $analyse_groups_obj = Bio::Roary::AnalyseGroups->new(
          fasta_files     => $fasta_files,
          groups_filename => $groups_file,
      );
      
      my $annotate_groups = Bio::Roary::AnnotateGroups->new(
          gff_files       => $gff_files,
          output_filename => $groups_file.'_reannotated',
          groups_filename => $groups_file,
      );
      $annotate_groups->reannotate;
    
      my $order_genes_obj = Bio::Roary::OrderGenes->new(
        analyse_groups_obj => $analyse_groups_obj,
        gff_files          => $gff_files,
		core_definition    => $self->core_definition,
		pan_graph_filename => 'set_difference_core_accessory_graph.dot',
		accessory_graph_filename  => 'set_difference_accessory_graph.dot',
      );
      
      my $group_statistics = Bio::Roary::GroupStatistics->new(
          output_filename     => $groups_file.'_statistics.csv',
          annotate_groups_obj => $annotate_groups,
          analyse_groups_obj  => $analyse_groups_obj,
          groups_to_contigs   => $order_genes_obj->groups_to_contigs
      );
      $group_statistics->create_spreadsheet;
}

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

    return <<USAGE;
Usage: query_pan_genome [options] *.gff
Perform set operations on the pan genome to see the gene differences between groups of isolates.

Options: -g STR    groups filename [clustered_proteins]
         -a STR    action (union/intersection/complement/gene_multifasta/difference) [union]
         -c FLOAT  percentage of isolates a gene must be in to be core [99]
         -o STR    output filename [pan_genome_results]
         -n STR    comma separated list of gene names for use with gene_multifasta action
         -i STR    comma separated list of filenames, comparison set one
         -t STR    comma separated list of filenames, comparison set two
         -v        verbose output to STDOUT
         -h        this help message
 
Examples: 
Union of genes found in isolates
         query_pan_genome -a union *.gff
         
Intersection of genes found in isolates (core genes)
         query_pan_genome -a intersection *.gff
         
Complement of genes found in isolates (accessory genes)
         query_pan_genome -a complement *.gff

Extract the sequence of each gene listed and create multi-FASTA files
         query_pan_genome -a gene_multifasta -n gryA,mecA,abc *.gff

Gene differences between sets of isolates
         query_pan_genome -a difference --input_set_one 1.gff,2.gff --input_set_two 3.gff,4.gff,5.gff

For further info see: http://sanger-pathogens.github.io/Roary/
USAGE
}

__PACKAGE__->meta->make_immutable;
no Moose;
1;

__END__

=pod

=encoding UTF-8

=head1 NAME

Bio::Roary::CommandLine::QueryRoary - Take in a groups file and the protein fasta files and output selected data

=head1 VERSION

version 3.13.0

=head1 SYNOPSIS

Take in a groups file and the protein fasta files and output selected data

=head1 AUTHOR

Andrew J. Page <ap13@sanger.ac.uk>

=head1 COPYRIGHT AND LICENSE

This software is Copyright (c) 2013 by Wellcome Trust Sanger Institute.

This is free software, licensed under:

  The GNU General Public License, Version 3, June 2007