BioPerl
view release on metacpan or search on metacpan
Bio/Tools/MZEF.pm view on Meta::CPAN
return $self->next_prediction(@args);
}
=head2 next_prediction
Title : next_prediction
Usage : while($gene = $mzef->next_prediction()) {
# do something
}
Function: Returns the next gene structure prediction of the MZEF result
file. Call this method repeatedly until FALSE is returned.
Note that with the present version of MZEF there will only be one
object returned, because MZEF does not predict individual genes
but just potential internal exons.
Example :
Returns : A Bio::Tools::Prediction::Gene object.
Args :
=cut
sub next_prediction {
my ($self) = @_;
my $gene;
# if the prediction section hasn't been parsed yet, we do this now
$self->_parse_predictions() unless $self->_predictions_parsed();
# return the next gene structure (transcript)
return $self->_prediction();
}
=head2 _parse_predictions
Title : _parse_predictions()
Usage : $obj->_parse_predictions()
Function: Parses the prediction section. Automatically called by
next_prediction() if not yet done.
Example :
Returns :
=cut
sub _parse_predictions {
my ($self) = @_;
my ($method); # set but not used presently
my $exon_tag = "InternalExon";
my $gene;
# my $seqname; # name given in output is poorly formatted
my $seqlen;
my $prednr = 1;
while(defined($_ = $self->_readline())) {
if(/^\s*(\d+)\s*-\s*(\d+)\s+/) {
# exon or signal
if(! defined($gene)) {
$gene = Bio::Tools::Prediction::Gene->new(
'-primary' => "GenePrediction$prednr",
'-source' => 'MZEF');
}
# we handle start-end first because may not be space delimited
# for large numbers
my ($start,$end) = ($1,$2);
s/^\s*(\d+)\s*-\s*(\d+)\s+//;
# split the rest into fields
chomp();
# format: Coordinates P Fr1 Fr2 Fr3 Orf 3ss Cds 5ss
# index: 0 1 2 3 4 5 6 7
my @flds = split(' ', $_);
# create the feature object depending on the type of signal --
# which is always an (internal) exon for MZEF
my $predobj = Bio::Tools::Prediction::Exon->new();
# set common fields
$predobj->source_tag('MZEF');
$predobj->significance($flds[0]);
$predobj->score($flds[0]); # what shall we set as overall score?
$predobj->strand($self->{'_strand'}); # MZEF searches only one
if($predobj->strand() == 1) {
$predobj->start($start);
$predobj->end($end);
} else {
$predobj->start($seqlen-$end+1);
$predobj->end($seqlen-$start+1);
}
# set scores
$predobj->start_signal_score($flds[5]);
$predobj->end_signal_score($flds[7]);
$predobj->coding_signal_score($flds[6]);
# frame -- we simply extract the one with highest score from the
# orf field, and store the individual scores for now
my $frm = index($flds[4], "1");
$predobj->frame(($frm < 0) ? undef : $frm);
$predobj->primary_tag($exon_tag);
$predobj->is_coding(1);
# add to gene structure (should be done only when start and end
# are set, in order to allow for proper expansion of the range)
$gene->add_exon($predobj);
next;
}
if(/^\s*Internal .*(MZEF)/) {
$self->analysis_method($1);
next;
}
if(/^\s*File_Name:\s+(\S+)\s+Sequence_length:\s+(\d+)/) {
# $seqname = $1; # this is too poor currently (file name truncated
# to 10 chars) in order to be sensible enough
$seqlen = $2;
next;
}
}
# $gene->seq_id($seqname);
$self->_add_prediction($gene) if defined($gene);
$self->_predictions_parsed(1);
}
=head2 _prediction
Title : _prediction()
Usage : $gene = $obj->_prediction()
Function: internal
Example :
( run in 0.825 second using v1.01-cache-2.11-cpan-39bf76dae61 )