lib/SGN/Genefamily.pm

   1
   2 =head1 NAME
   3
   4 SGN::Genefamily - a class to deal with (currently disk-based) genefamilies for tomato annotation purposes
   5
   6 =head1 DESCRIPTION
   7
   8 The genefamilies are defined by alignment files in a subdirectory. Thus it is easy to update the family definitions, which will happen frequently over the next two months. Then the gene families will be moved to the database. So this code is only very temporary.
   9
  10 =head1 AUTHOR
  11
  12 Lukas Mueller <lam87@cornell.edu>
  13
  14 =head1 METHODS
  15
  16 Methods in this class include:
  17
  18 =cut
  19
  20 package SGN::Genefamily;
  21
  22 use Moose;
  23 use namespace::autoclean;
  24 use File::Slurp qw/slurp/;
  25 use File::Spec::Functions;
  26 use File::Basename qw/basename/;
  27
  28 =head2 accessors name()
  29
  30  Usage:        $gf->name()
  31  Property:     the name of the gene family
  32  Side Effects: will be used to map to the corresponding file name
  33  Example:
  34
  35 =cut
  36
  37 has 'name' => (
  38     is       => 'rw',
  39 #    required => 1,
  40    );
  41
  42 =head2 members
  43
  44  Usage:        my @members = $gf->members()
  45  Desc:         retrieves the members of a genefamily. Read only.
  46  Property:     the members of the gene family
  47  Side Effects:
  48  Example:
  49
  50 =cut
  51
  52 has 'members' => ( is => 'ro', isa => 'ArrayRef', default => sub { [] } );
  53
  54 =head2 files_dir
  55
  56  Usage:        my $dir = $gf->files_dir()
  57  Desc:         sets the directory where the genefamilies are located.
  58  Property:     a path
  59  Side Effects: used for retrieving gene family information
  60  Example:
  61
  62 =cut
  63
  64 has 'files_dir' => (
  65     is       => 'rw',
  66     required => 1,
  67    );
  68
  69 =head2 dataset
  70
  71  Usage:        my $d = $gf->dataset()
  72  Desc:         under the genefamily dir (files_dir), a number of sub-dirs
  73                should be present, each of which represents a separate
  74                gene family clustering (for example, based on different
  75                species or different clustering parameters).
  76  Property:     the dataset name [string]
  77  Side Effects:
  78  Example:
  79
  80 =cut
  81
  82 has 'dataset' => (
  83     is       => 'rw',
  84     required => 1,
  85    );
  86
  87 =head2 get_alignment
  88
  89  Usage:        my $alignment = $gf->get_alignment()
  90  Desc:         returns the alignment as a string
  91  Args:         none
  92  Side Effects: dies if the alignment has not yet been calculated.
  93  Example:
  94
  95 =cut
  96
  97 sub get_alignment {
  98     my $self = shift;
  99     my $file =
 100       catfile( $self->get_path(), "alignments", $self->name() . ".fa.align" );
 101
 102     if ( !-e $file ) {
 103         die "No alignment file available for family " . $self->name();
 104     }
 105
 106     return slurp($file);
 107 }
 108
 109 =head2 get_fasta
 110
 111  Usage:        my $fasta = $gf->get_fasta()
 112  Desc:         returns the sequences of a gene family as a string
 113                formatted in fasta.
 114  Ret:          fasta
 115  Args:         none
 116  Side Effects: dies if the fasta is not available.
 117  Example:
 118
 119 =cut
 120
 121 sub get_fasta {
 122     my $self = shift;
 123     my $file = catfile( $self->get_path(), "fasta", $self->name() . ".fa" );
 124     unless( -f $file ) {
 125         die "The fasta information for family "
 126           . $self->name()
 127           . " cannot be found";
 128     }
 129     return slurp($file);
 130 }
 131
 132 =head2 get_seqs
 133
 134  Usage:        my $fasta = $gf->get_seqs()
 135  Desc:         returns the sequences of a gene family as a list of
 136                Bio::Seq objects
 137  Ret:
 138  Args:         none
 139  Side Effects: dies if the fasta information is not available.
 140  Example:
 141
 142 =cut
 143
 144 sub get_seqs {
 145     my $self = shift;
 146     my $file = catfile( $self->get_path(), "fasta", $self->name() . ".fa" );
 147     if ( !-e $file ) {
 148         die "The fasta information for family "
 149           . $self->name()
 150           . " cannot be found";
 151     }
 152     my @seqs = ();
 153     my $io = Bio::SeqIO->new( -format => 'fasta', -file => $file );
 154     while ( my $seq = $io->next_seq() ) {
 155         push @seqs, $seq;
 156     }
 157     return @seqs;
 158 }
 159
 160 =head2 get_tree
 161
 162  Usage:
 163  Desc:
 164  Ret:
 165  Args:
 166  Side Effects:
 167  Example:
 168
 169 =cut
 170
 171 sub get_tree {
 172     my $self = shift;
 173     my $file =
 174       catfile( $self->get_path(), "/trees/" . $self->name() . ".tree" );
 175     if ( !-e $file ) {
 176         die "The tree information for family "
 177           . $self->name()
 178           . " cannot be found";
 179     }
 180     return slurp($file);
 181 }
 182
 183 sub get_member_ids {
 184     my $self = shift;
 185
 186 }
 187
 188 =head2 get_available_datasets
 189
 190  Usage:        my @ds = SGN::Genefamily->get_available_datasets($DIR)
 191  Desc:         a class function that returns the available datasets
 192  Ret:          a list of dataset names
 193  Args:         the $DIR where the datasets are located.
 194  Side Effects:
 195  Example:
 196
 197 =cut
 198
 199 sub get_available_datasets {
 200     my $class = shift;
 201     my $path  = shift;
 202     my @dirs  = map { basename($_) } grep -d, glob "$path/*";
 203     return @dirs;
 204 }
 205
 206 sub get_path {
 207     my $self = shift;
 208     return catfile( $self->files_dir(), $self->dataset() );
 209 }
 210
 211 1;