view release on metacpan or  search on metacpan

lib/Bio/Tools/Run/Phylo/Phylip/ProtDist.pm  view on Meta::CPAN

  Usage       : @params = ('freq'=>('W','X','Y','Z')
                where W + X + Y + Z = 1
		Defaults to Equal (0.25,0.25,0.25,0.25)


=head1 FEEDBACK

=head2 Mailing Lists

User feedback is an integral part of the evolution of this and other
Bioperl modules. Send your comments and suggestions preferably to one
of the Bioperl mailing lists.  Your participation is much appreciated.

  bioperl-l@bioperl.org                  - General discussion
  http://bioperl.org/wiki/Mailing_lists  - About the mailing lists

=head2 Support 

Please direct usage questions or support issues to the mailing list:

I<bioperl-l@bioperl.org>

rather than to the module maintainer directly. Many experienced and 
reponsive experts will be able look at the problem and quickly 
address it. Please include a thorough description of the problem 
with code and data examples if at all possible.

=head2 Reporting Bugs

Report bugs to the Bioperl bug tracking system to help us keep track
the bugs and their resolution.  Bug reports can be submitted via the
web:

  http://redmine.open-bio.org/projects/bioperl/

=head1 AUTHOR - Shawn Hoon 

Email shawnh@fugu-sg.org 

=head1 APPENDIX

The rest of the documentation details each of the object
methods. Internal methods are usually preceded with a _

=cut

#'

	
package Bio::Tools::Run::Phylo::Phylip::ProtDist;

use vars qw($AUTOLOAD @ISA $PROGRAM $PROGRAMDIR $PROGRAMNAME
	    @PROTDIST_PARAMS @OTHER_SWITCHES
	    %OK_FIELD);
use strict;
use Bio::SimpleAlign;
use Bio::AlignIO;
use Bio::TreeIO;
use Bio::Tools::Run::Phylo::Phylip::Base;
use Bio::Tools::Run::Phylo::Phylip::PhylipConf qw(%Menu);
use Bio::Tools::Phylo::Phylip::ProtDist;
use Cwd;


# inherit from Phylip::Base which has some methods for dealing with
# Phylip specifics
@ISA = qw(Bio::Tools::Run::Phylo::Phylip::Base);

# You will need to enable the protdist program. This
# can be done in (at least) 3 ways:
#
# 1. define an environmental variable PHYLIPDIR:
# export PHYLIPDIR=/home/shawnh/PHYLIP/bin
#
# 2. include a definition of an environmental variable CLUSTALDIR in
# every script that will use Clustal.pm.
# $ENV{PHYLIPDIR} = '/home/shawnh/PHYLIP/bin';
#
# 3. You can set the path to the program through doing:
# my @params('program'=>'/usr/local/bin/protdist');
# my $protdist_factory = Bio::Tools::Run::Phylo::Phylip::ProtDist->new(@params);
# 


BEGIN {
	@PROTDIST_PARAMS = qw(MODEL GENCODE CATEGORY PROBCHANGE TRANS WEIGHTS FREQ MULTIPLE);
	@OTHER_SWITCHES = qw(QUIET);
	foreach my $attr(@PROTDIST_PARAMS,@OTHER_SWITCHES) {
		$OK_FIELD{$attr}++;
	}
}

=head2 program_name

 Title   : program_name
 Usage   : >program_name()
 Function: holds the program name
 Returns:  string
 Args    : None

=cut

sub program_name {
  return 'protdist';
}

=head2 program_dir

 Title   : program_dir
 Usage   : ->program_dir()
 Function: returns the program directory, obtained from ENV variable.
 Returns:  string
 Args    :

=cut

sub program_dir {
  return Bio::Root::IO->catfile($ENV{PHYLIPDIR}) if $ENV{PHYLIPDIR};
}

lib/Bio/Tools/Run/Phylo/Phylip/ProtDist.pm  view on Meta::CPAN

    my ($alnfilename,$tfh);

    # suffix is used to distinguish alignment files  from an align obkect
	#If $input is not a  reference it better be the name of a file with the sequence/

    #  a phy formatted alignment file 
  	unless (ref $input) {
        # check that file exists or throw
        $alnfilename= $input;
        unless (-e $input) {return 0;}
		return $alnfilename;
    }
    my @input = ref $input eq 'ARRAY' ? @{$input} : ($input);

    #  $input may be a SimpleAlign Object
   ($tfh,$alnfilename) = $self->io->tempfile(-dir=>$self->tempdir);
    my $alnIO = Bio::AlignIO->new(-fh => $tfh, 
				  -format=>'phylip',
				  -idlength=>$self->idlength());
    my $input_count = 0;
    foreach my $input(@input){
	if ($input->isa("Bio::SimpleAlign")){
	    #  Open temporary file for both reading & writing of BioSeq array
	    $alnIO->write_aln($input);
	}
	$input_count++;
    }
    $alnIO->close();
    close($tfh);
    $tfh = undef;
    $self->_input_nbr($input_count); 
    return $alnfilename;		
}

sub _input_nbr {
    my ($self,$val) = @_;
    if($val){
        $self->{'_input_nbr'} = $val;
    }
    return $self->{'_input_nbr'};
}

=head2  _setparams()

 Title   :  _setparams
 Usage   :  Internal function, not to be called directly	
 Function:   Create parameter inputs for protdist program
 Example :
 Returns : parameter string to be passed to protdist
 Args    : name of calling object

=cut

sub _setparams {
    my ($attr, $value, $self);

    #do nothing for now
    $self = shift;
    my $param_string = "";
    my $cat = 0;
    my %menu = %{$Menu{$self->version}->{'PROTDIST'}};

    foreach  my $attr ( @PROTDIST_PARAMS) {
    	$value = $self->$attr();
    	next unless (defined $value);
    	if ($attr =~/MODEL/i){
	    if ($value=~/CAT/i){
		$cat = 1;
	    }
	    $param_string .= $menu{'MODEL'}{$value};
	}
	if($attr=~/MULTIPLE/i){
	    $param_string.=$menu{'MULTIPLE'}."$value\n";
	}
  	if ($cat == 1){
	    if($attr =~ /GENCODE/i){		
		my $allowed = $menu{'GENCODE'}{'ALLOWED'};
    		$self->throw("Unallowed value for genetic code") unless ($value =~ /[$allowed]/);
		$param_string .= $menu{'GENCODE'}{'OPTION'}."$value\n";
	    }
	    if ($attr =~/CATEGORY/i){
		my $allowed = $menu{'CATEGORY'}{'ALLOWED'};
    		$self->throw("Unallowed value for categorization of amino acids") unless ($value =~/[$allowed]/);
	    	$param_string .= $menu{'CATEGORY'}{'OPTION'}."$value\n";
	    }
	    if ($attr =~/PROBCHANGE/i){
    		if (($value =~ /\d+/)&&($value >= 0) && ($value < 1)){
		    $param_string .= $menu{'PROBCHANGE'}."$value\n";
		}
    		else {
	  	    $self->throw("Unallowed value for probability change category");  
		}
	    }
	    if ($attr =~/TRANS/i){
    		if (($value=~/\d+/) && ($value >=0)){
	  	    $param_string .=$menu{'TRANS'}."$value\n";
	    	}
	    }
	    if ($attr =~ /FREQ/i){
    		my @freq = split(",",$value);	
    		if ($freq[0] !~ /\d+/){	#a letter provided (sets frequencies equally to 0.25)
		    $param_string .=$menu{'FREQ'}.$freq[0]."\n";
	    	}
    		elsif ($#freq ==  3) {#must have 4 digits for each base
					  $param_string .=$menu{'FREQ'};
					  foreach my $f (@freq){
					      $param_string.="$f\n";
					  }
				      }
		else {
		    $self->throw("Unallowed value for base frequencies");
		}
	    }
	}
    } 
    #set multiple option is not set and there are more than one sequence
    if (($param_string !~ $menu{'MULTIPLE'}) && (defined ($self->_input_nbr) &&($self->_input_nbr > 1))){
	$param_string.=$menu{'MULTIPLE'}.$self->_input_nbr."\n";
    }
    $param_string .=$menu{'SUBMIT'};