BioPerl

 view release on metacpan or  search on metacpan

Bio/DB/SeqFeature/Store/FeatureFileLoader.pm  view on Meta::CPAN

delimited text. Embedded whitespace must be escaped using shell
escaping rules (quoting the column or backslashing whitespace).

  Column 1: The feature type. You may use type:subtype as a convention
            for method:source.

  Column 2: The feature name/ID.

  Column 3: The position of this feature in base pair
            coordinates. Ranges can be given as either 
            start-end or start..end. A chromosome position
            can be specified using the format "reference:start..end".
            A discontinuous feature can be specified by giving
            multiple ranges separated by commas. Minus-strand features
            are indicated by specifying a start > end.

  Column 4: Comment/attribute field. A single Note can be given, or
            a series of attribute=value pairs, separated by
            spaces or semicolons, as in "score=23;type=transmembrane"

=head2 Specifying Positions and Ranges

Bio/LiveSeq/IO/Loader.pm  view on Meta::CPAN

	push (@ttables,$entryfeature->{'qualifiers'}->{'transl_table'}); # undef if not specified
	
	# create labels array
	for $exon (@range) {
	  push(@labels,$exon->[0],$exon->[1]); # start and end of every exon of the CDS
	}
	push (@transcripts,$entryfeature->{'range'});
      } else {
	# "simplifying" the joinedlocation features. I.e. changing them from
	# multijoined ones to simple plain start-end features, taking only
	# the start of the first "exon" and the end of the last "exon" as
	# start and end of the entire feature
	if ($entryfeature->{'locationtype'} && $entryfeature->{'locationtype'} eq "joined") { # joined location
	  @range=($range[0]->[0],$range[-1]->[1]);
	}
	push(@labels,$range[0],$range[1]); # start and end of every feature
	if ($name eq "exon") {
	  $desc=$entryfeature->{'qualifiers'}->{'number'};
	  if ($entryfeature->{'qualifiers'}->{'note'}) {
	    if ($desc) {

Bio/SearchIO/exonerate.pm  view on Meta::CPAN

	   my ($nm,$desc) = ($1,$2);
	   chomp($desc) if defined $desc;
	   $self->start_element({'Name' => 'Hit'});
	   $self->element({'Name' => 'Hit_id',
			   'Data' => $nm});
	   $self->element({'Name' => 'Hit_desc',
			   'Data' => $desc});
	   $self->{'_seencigar'} = 0;
	   $self->{'_vulgar'}    = 0;
       } elsif(  s/^vulgar:\s+(\S+)\s+         # query sequence id
		 (\d+)\s+(\d+)\s+([\-\+\.])\s+ # query start-end-strand
		 (\S+)\s+                      # target sequence id
		 (\d+)\s+(\d+)\s+([\-\+])\s+   # target start-end-strand
		 (-?\d+)\s+                    # score
		 //ox ) {
	   next if( $self->cigar || $self->{'_seencigar'});
	   $self->{'_vulgar'}++;
	   #
	   # Note from Ewan. This is ugly - copy and paste from
	   # cigar line parsing. Should unify somehow...
	   #
	   if( ! $self->within_element('result') ) {
	       $self->start_element({'Name' => 'ExonerateOutput'});

Bio/Tools/MZEF.pm  view on Meta::CPAN

    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

Bio/Tools/Sim4/Results.pm  view on Meta::CPAN

	       $seq2props{'seqname'} = $1; # redundant, since already set above
	       $seq2props{'description'} = $2 if $2;
	   }
	   next;
       }
       /^\(complement\)/ && do {
	   $hit_direction = -1;
	   next;
       };
       # this matches
       # start-end (start-end) pctid%
       if(/(\d+)-(\d+)\s+\((\d+)-(\d+)\)\s+(\d+)%/) {
 	   $seq1props{'start'} = $1;
 	   $seq1props{'end'} = $2;
 	   $seq2props{'start'} = $3;
 	   $seq2props{'end'} = $4;
	   my $pctid   = $5;
	   
	   if(! defined($estseq)) {
	       # for the first time here: need to set the references referring
	       # to seq1 and seq2 

scripts/utilities/bp_sreformat.pl  view on Meta::CPAN

                        (to pass in data on STDIN use minus sign as filename)
-o/--output             Specify the output file name
                        (to pass data out on STDOUT use minus sign as filename)
--msa                   Specify this is multiple sequence alignment data
--special=specialparams Specify special params supported by some formats
                        Comma or space separated please.
                        These include:
                        nointerleaved   -- for phylip,non-interleaved format
                        idlinebreak     -- for phylip, makes it molphy format
                        percentages     -- for clustalw, show % id per line
                        flat            -- don't show start-end in seqid
                        linelength      -- line length for clustalw
                        mrbayes         -- for MrBayes proper NEXUS output
";


my ($input,$output,$informat,$outformat,$msa,$special);

GetOptions(
	   'h|help'          => sub { print STDERR ($USAGE); exit(0) },
	   'i|input:s'         => \$input,

 view all matches for this distribution
 view release on metacpan -  search on metacpan