Bio::AlignIO
clustalw
Summary
Bio::AlignIO::clustalw - clustalw sequence input/output stream
Package variables
No package variables defined.
Included modules
Inherit
Synopsis
Do not use this module directly. Use it via the Bio::AlignIO class.
Description
This object can transform Bio::Align::AlignI objects to and from clustalw flat
file databases.
Methods
Methods description
Title : next_aln
Usage : $aln = $stream->next_aln()
Function: returns the next alignment in the stream
Returns : Bio::Align::AlignI object
Args : NONE
See Bio::Align::AlignI for details |
Title : write_aln
Usage : $stream->write_aln(@aln)
Function: writes the clustalw-format object (.aln) into the stream
Returns : 1 for success and 0 for error
Args : Bio::Align::AlignI object |
Title : percentages
Usage : $obj->percentages($newval)
Function: Set the percentages flag - whether or not to show percentages in
each output line
Returns : value of percentages
Args : newvalue (optional) |
Title : line_length
Usage : $obj->line_length($newval)
Function: Set the alignment output line length
Returns : value of line_length
Args : newvalue (optional) |
Methods code
sub _initialize
{ my ($self, @args) = @_;
$self->SUPER::_initialize(@args);
my ($percentages,
$ll) = $self->_rearrange([qw(PERCENTAGES LINELENGTH)], @args);
defined $percentages && $self->percentages($percentages);
$self->line_length($ll || $LINELENGTH);} |
sub next_aln
{ my ($self) = @_;
my $first_line;
if( defined ($first_line = $self->_readline )
&& $first_line !~ /CLUSTAL/ ) {
$self->warn("trying to parse a file which does not start with a CLUSTAL header");
}
my %alignments;
my $aln = Bio::SimpleAlign->new(-source => 'clustalw',
-verbose => $self->verbose);
my $order = 0;
my %order;
$self->{_lastline} = '';
while( defined ($_ = $self->_readline) ) {
next if ( /^\s+$/ );
my ($seqname, $aln_line) = ('', '');
if( /^\s*(\S+)\s*\/\s*(\d+)-(\d+)\s+(\S+)\s*$/ ) {
($seqname,$aln_line) = ("$1:$2-$3",$4);
} elsif( /^(\S+)\s+([A-Z\-]+)\s*$/ ) {
($seqname,$aln_line) = ($1,$2);
} else { $self->{_lastline} = $_; next }
if( !exists $order{$seqname} ) {
$order{$seqname} = $order++;
}
$alignments{$seqname} .= $aln_line;
}
my ($sname,$start,$end);
foreach my $name ( sort { $order{$a} <=> $order{$b} } keys %alignments ) {
if( $name =~ /(\S+):(\d+)-(\d+)/ ) {
($sname,$start,$end) = ($1,$2,$3);
} else {
($sname, $start) = ($name,1);
my $str = $alignments{$name};
$str =~ s/[^A-Za-z]//g;
$end = length($str);
}
my $seq = new Bio::LocatableSeq('-seq' => $alignments{$name},
'-id' => $sname,
'-start' => $start,
'-end' => $end);
$aln->add_seq($seq);
}
undef $aln if( !defined $end || $end <= 0);
return $aln;} |
sub write_aln
{ my ($self,@aln) = @_;
my ($count,$length,$seq,@seq,$tempcount,$line_len);
$line_len = $self->line_length || $LINELENGTH;
foreach my $aln (@aln) {
if( ! $aln || ! $aln->isa('Bio::Align::AlignI') ) {
$self->warn("Must provide a Bio::Align::AlignI object when calling write_aln");
next;
}
my $matchline = $aln->match_line;
$self->_print (sprintf("CLUSTAL W(1.81) multiple sequence alignment\n\n\n")) or return;
$length = $aln->length();
$count = $tempcount = 0;
@seq = $aln->each_seq();
my $max = 22;
foreach $seq ( @seq ) {
$max = length ($aln->displayname($seq->get_nse()))
if( length ($aln->displayname($seq->get_nse())) > $max );
}
while( $count < $length ) {
foreach $seq ( @seq ) {
my ($substring);
my $seqchars = $seq->seq();
SWITCH: {
if (length($seqchars) >= ($count + $line_len)) {
$substring = substr($seqchars,$count,$line_len);
last SWITCH;
} elsif (length($seqchars) >= $count) {
$substring = substr($seqchars,$count);
last SWITCH;
}
$substring = "";
}
$self->_print (sprintf("%-".$max."s %s\n",
$aln->displayname($seq->get_nse()),
$substring)) or return;
}
my $linesubstr = substr($matchline, $count,$line_len);
my $percentages = '';
if( $self->percentages ) {
my ($strcpy) = ($linesubstr);
my $count = ($strcpy =~ tr/\*//);
$percentages = sprintf("\t%d%%", 100 * ($count / length($linesubstr))); }
$self->_print (sprintf("%-".$max."s %s%s\n", '', $linesubstr,
$percentages));
$self->_print (sprintf("\n\n")) or return;
$count += $line_len;
}
}
$self->flush if $self->_flush_on_write && defined $self->_fh;
return 1;} |
sub percentages
{ my ($self,$value) = @_;
if( defined $value) {
$self->{'_percentages'} = $value;
}
return $self->{'_percentages'};} |
sub line_length
{ my ($self,$value) = @_;
if( defined $value) {
$self->{'_line_length'} = $value;
}
return $self->{'_line_length'};} |
General documentation
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://bio.perl.org/MailList.html - About the mailing lists
Report bugs to the Bioperl bug tracking system to help us keep track
the bugs and their resolution. Bug reports can be submitted via email
or the web:
bioperl-bugs@bio.perl.org
http://bugzilla.bioperl.org/
| AUTHORS - Peter Schattner | Top |
The rest of the documentation details each of the object
methods. Internal methods are usually preceded with a _
Title : new
Usage : $alignio = new Bio::AlignIO(-format => 'clustalw',
-file => 'filename');
Function: returns a new Bio::AlignIO object to handle clustalw files
Returns : Bio::AlignIO::clustalw object
Args : -verbose => verbosity setting (-1,0,1,2)
-file => name of file to read in or with ">" - writeout
-fh => alternative to -file param - provide a filehandle
to read from/write to
-format => type of Alignment Format to process or produce
-percentages => (clustalw only) display a percentage of identity
in each line of the alignment.
-linelength=> Set the alignment output line length (default 60)