view release on metacpan or  search on metacpan

AI/Gene/Sequence.pm  view on Meta::CPAN

    }
    my $chunk1 = substr($new, $pos1, $len1, substr($new, $pos2, $len2,''));
    substr($new,$pos2 -$len1 + $len2,0) = $chunk1;
    next unless $self->valid_gene($new);
    $self->[0]= $new;
    my @chunk1 = splice(@{$self->[1]}, $pos1, $len1,
			splice(@{$self->[1]}, $pos2, $len2) );
    splice @{$self->[1]}, $pos2 + $len2 - $len1,0, @chunk1;
    $rt++;
  }
  return $rt;
}

##
# takes a sequence, removes it, then inserts it at another position
# odd things might occur if posn to replace to lies within area taken from
# 0: number to perform
# 1: posn to get from   (undef for rand)
# 2: posn to put        (undef for rand)
# 3: length of sequence (undef for 1, 0 for rand)

sub mutate_shuffle {
  my $self = shift;
  my $num = +$_[0] || 1;
  my $rt = 0;
  
  for (1..$num) {
    my $length = length $self->[0];
    my $pos1 = defined($_[1]) ? $_[1] : int rand $length;
    my $pos2 = defined($_[2]) ? $_[2] : int rand $length;
    my $len = !defined($_[3]) ? 1 : ($_[3] || int rand $length);

    my $new = $self->[0];
    if ($pos1 +$len > $length   # outside gene
	or $pos2 >= $length      # outside gene
	or ($pos2 < ($pos1 + $len) and $pos2 > $pos1)) { # overlap
      next;
    }
    if ($pos1 < $pos2) {
      substr($new, $pos2-$len,0) = substr($new, $pos1, $len, '');
    }
    else {
      substr($new, $pos2, 0) = substr($new, $pos1, $len, '');
    }
    next unless $self->valid_gene($new);
    $self->[0] = $new;
    if ($pos1 < $pos2) {
      splice (@{$self->[1]}, $pos2-$len, 0, 
	      splice(@{$self->[1]}, $pos1, $len) );
    }
    else {
      splice(@{$self->[1]}, $pos2, 0,
	     splice(@{$self->[1]}, $pos1, $len) );
    }
    $rt++;
  }
  return $rt;
}

# These are intended to be overriden, simple versions are
# provided for the sake of testing.

# Generates things to make up genes
# can be called with a token type to produce, or with none.
# if called with a token type, it will also be passed the original
# token as the second argument.
# should return a two element list of the token type followed by the token itself.

sub generate_token {
  my $self = shift;
  my $token_type = $_[0];
  my $letter = ('a'..'z')[rand 25];
  unless ($token_type) {
    return ($letter) x2;
  }
  return ($token_type) x2;
}

# takes sting of token types to be checked for validity.
# If a mutation affects only one place, then the position of the
# mutation can be passed as a second argument.
sub valid_gene {1}

## You might also want to have methods like the following,
# they will not be called by the 'sequence' methods.

# Default constructor
sub new {
  my $gene = ['',[]];
  return bless $gene, ref $_[0] || $_[0];
}

# remember that clone method may require deep copying depending on
# your specific needs

sub clone {
  my $self = shift;
  my $new = [$self->[0]];
  $new->[1] = [@{$self->[1]}];
  return bless $new, ref $self;
}

# You need some way to use the gene you've made and mutated, but
# this will let you have a look, if it starts being odd.

sub render_gene {
  my $self = shift;
  my $return =  "$self\n";
  $return .= $self->[0] . "\n";
  $return .= (join ',', @{$self->[1]}). "\n";
  return $return;
}

# used for testing

sub _test_dump {
  my $self = shift;
  my @rt = ($self->[0], join('',@{$self->[1]}));
  return @rt;
}
1;

__END__;

=pod

=head1 NAME

 AI::Gene::Sequence

=head1 SYNOPSIS

A base class for storing and mutating genetic sequences.

 package Somegene;
 use AI::Gene::Sequence;
 our @ISA = qw(AI::Gene::Sequence);

 my %things = ( a => [qw(a1 a2 a3 a4 a5)],
	       b => [qw(b1 b2 b3 b4 b5)],);

 sub generate_token {
  my $self = shift;
  my ($type, $prev) = @_;
  if ($type) {
    $prev = ${ $things{$type} }[rand @{ $things{$type} }];
  } 
  else {
    $type = ('a','b')[rand 2];
    $prev = ${$things{$type}}[rand @{$things{$type}}];
  }
  return ($type, $prev); 
 }

 sub valid_gene {
   my $self = shift;
   return 0 if $_[0] =~ /(.)\1/;
   return 1;
 }

 sub seed {
   my $self = shift;
   $self->[0] = 'ababab';
   @{$self->[1]} = qw(A1 B1 A2 B2 A3 B3);
 }

 sub render {
   my $self = shift;
   return join(' ', @{$self->[1]});
 } 

 # elsewhere
 package main;

 my $gene = Somegene->new;
 $gene->seed;
 print $gene->render, "\n";
 $gene->mutate(5);
 print $gene->render, "\n";
 $gene->mutate(5);
 print $gene->render, "\n";

=head1 DESCRIPTION

This is a class which provides generic methods for the
creation and mutation of genetic sequences.  Various mutations
are provided as is a way to ensure that genes created by
mutations remain useful (for instance, if a gene gives rise to
code, it can be tested for correct syntax).

If you do not need to keep check on what sort of thing is
currently occupying a slot in the gene, you would be better
off using the AI::Gene::Simple class instead as this
will be somewhat faster.  The interface to the mutations is
the same though, so if you need to change in future, then
it will not be too painful.

This module should not be confused with the I<bioperl> modules
which are used to analyse DNA sequences.

It is intended that the methods in this code are inherited
by other modules.

=head2 Anatomy of a gene

A gene is a sequence of tokens, each a member of some group
of simillar tokens (they can of course all be members of a
single group).  This module encodes genes as a string
representing token types, and an array containing the
tokens themselves, this allows for arbitary data to be
stored as a token in a gene.

For instance, a regular expression could be encoded as:

 $self = ['ccartm',['a', 'b', '|', '[A-Z]', '\W', '*?'] ]

Using a string to indicate the sort of thing held at the
corresponding part of the gene allows for a simple test
of the validity of a proposed gene by using a regular
expression.

=head2 Using the module

To use the genetic sequences, you must write your own
implementations of the following methods:

=over 4

=item generate_token

=item valid_gene

=back

You may also want to override the following methods:

=over 4

=item new

=item clone

=item render_gene

=back

=head2 Mutation methods

Mutation methods are all named C<mutate_*>.  In general, the
first argument will be the number of mutations required, followed
by the positions in the genes which should be affected, followed
by the lengths of sequences within the gene which should be affected.
If positions are not defined, then random ones are chosen.  If
lengths are not defined, a length of 1 is assumed (ie. working on
single tokens only), if a length of 0 is requested, then a random
length is chosen.

Also, if a mutation is suggested but would result in an invalid
sequence, then the mutation will not be carried out.
If a mutation is attempted which could corrupt your gene (copying
from a region beyond the end of the gene for instance) then it
will be silently skipped.  Mutation methods all return the number
of mutations carried out (not the number of tokens affected).

These methods all expect to be passed positive integers, undef or zero,
other values could (and likely will) do something unpredictable.

=over 4

=item C<mutate([num, ref to hash of probs & methods])>

This will call at random one of the other mutation methods.
It will repeat itself I<num> times.  If passed a reference
to a hash as its second argument, it will use that to
decide which mutation to attempt.

This hash should contain keys which fit $1 in C<mutate_(.*)>
and values indicating the weight to be given to that method.