view release on metacpan or  search on metacpan

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

        translation_table   => $self->translation_table,
        core_definition     => $self->core_definition,
        cpus                => $self->cpus,
		verbose             => $self->verbose,
		mafft               => $self->mafft,
		allow_paralogs      => $self->allow_paralogs,
        dont_delete_files   => $self->dont_delete_files,
        num_input_files     => $#{$input_files},
      );
      $seg->run();
    }
}

sub _is_lsf_job_runner_available
{
    my ($self) = @_;
    my $rc = eval "require Bio::Roary::JobRunner::LSF; 1;";
    if(defined($rc) && $rc == 1)
    {
        return 1;
    }
    else
    {
        return 0;
    }
}

sub _find_input_files
{
   my ($self) = @_;
   my @files = File::Find::Rule->file()
                               ->name( '*.fa' )
                               ->in('pan_genome_sequences' );
   return \@files;
}

sub _read_file_into_array
{
  my ($self, $filename) = @_;
  open(my $in_fh, $filename);
  
  my @filenames;
  while(<$in_fh>){
    chomp;
    my $line = $_;
    push(@filenames, $line);
  }
  return \@filenames;
}

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

    return <<USAGE;
Usage: pan_genome_post_analysis [options]
Perform the post analysis on the pan genome. This script is usally only called by another script.

Options: -a        dont delete intermediate files
         -b        dont create R plots
         -c STR    clusters filename [_clustered.clstr]
         -cd FLOAT percentage of isolates a gene must be in to be core [0.99]
         -d        dont split groups
         -e        add inference values to gene presence and absence spreadsheet
         -f STR    file of protein filenames [_fasta_files]
         -g INT    maximum number of clusters [50000]
         -i STR    file of GFF filenames [_gff_files]
         -m        core gene alignement with PRANK
         -n        fast core gene alignement with MAFFT instead of PRANK
         -o STR    clusters output filename [clustered_proteins]
         -p STR    output pan genome filename [pan_genome.fa]
         -q        allow paralogs in core alignment
         -s STR    output gene presence and absence filename [gene_presence_absence.csv]
         -t INT    translation table [11]
         -z INT    number of threads [1]
         -v        verbose output to STDOUT
         -h        this help message
         
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::RoaryPostAnalysis - Perform the post analysis on the pan genome

=head1 VERSION

version 3.13.0

=head1 SYNOPSIS

Perform the post analysis on the pan genome

=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

=cut