view release on metacpan or search on metacpan
bin/annotate-ali.pl view on Meta::CPAN
}
# optionally output annotated file
if ($ARGV_ann_file) {
my $ali = Bio::MUST::Core::Ali->load($infile);
$ali->dont_guess if $ARGV_noguessing;
my $outfile = secure_outfile($infile, $ARGV_out_suffix);
#### Writing annotated file: $outfile->stringify
prefix_ids($ali, \%ann_for)->store_fasta($outfile);
}
}
bin/annotate-ali.pl view on Meta::CPAN
infiles are preserved by being appended a .bak suffix.
=for Euclid: suffix.type: string
suffix.default: '-ann'
=item --[no]guessing
[Don't] guess whether sequences are aligned or not [default: yes].
=item --version
=item --usage
view release on metacpan or search on metacpan
bin/abbr-ids-fas.pl view on Meta::CPAN
for my $infile (@ARGV_infiles) {
### Processing: $infile
my $ali = Ali->load($infile);
$ali->dont_guess;
# determine seq_id prefix
my $prefix = $ARGV_id_prefix // q{}; # defaults to no prefix
if ($prefix_mapper) { # infile paths are ignored
my ($filename) = fileparse($infile);
view release on metacpan or search on metacpan
bin/tree-clan-splitter.pl view on Meta::CPAN
#### @main_clans
# fit ali to ali2phylip filtering
my $alifile = $stripped_intree . '.ali';
my $base_ali = Ali->load($alifile);
$base_ali->dont_guess;
my $alist = $tree->alphabetical_list;
#### $list
my $ali = $alist->filtered_ali($base_ali);
my $n_ali;
view release on metacpan or search on metacpan
lib/Bio/MaxQuant/Evidence/Statistics.pm view on Meta::CPAN
$p->{data}->{$replicate}->{$pgid}->{'Ratio H/L'}->[$i] -= $median;
}
}
}
}
# i guess we should do something better with generating this status:
return 1;
}
=head2 median
view release on metacpan or search on metacpan
lib/Bio/Maxd.pm view on Meta::CPAN
=over 4
=item B<-file>, datafile to parse.
=item B<-format>, data file format; Bio::Maxd will guess it, if not provided.
Valid values are 'AFF' (Affimetrix matrics file)
=item B<-experiment>, Experiment ID or Experiment name.
=item B<-array_type>, ArrayType ID or ArrayType name
view release on metacpan or search on metacpan
bin/phylip2nex.pl view on Meta::CPAN
=item B<-f, --format>
The format of the input file. See L<Bio::NEXUS::Import> for a list of
supported file formats. If no format is specified, then L<Bio::NEXUS::Import>
will try to guess the correct format.
=item B<-o, --outfile>
The name of the output file. Defaults to out.nex.
view release on metacpan or search on metacpan
doc/buglist.txt view on Meta::CPAN
The BigPrint code apparently leaves margins (1/2" at this point in time) all
around, so that one can print them without having things cut off. However,
when converting to PDF, this doesn't happen. Instead, the margins only apply
to the first page and don't apply to everything else. I don't know why this
happens, but I'm guessing the fault isn't totally on our side. This should
be looked into more deeply.
=back
=for comment ------------------------------- B U G -----------------------------
view release on metacpan or search on metacpan
lib/Bio/Nexml/Factory.pm view on Meta::CPAN
$aln->unmatch;
$aln->map_chars('\.','-');
my @seqs = $aln->each_seq;
my ( $type, $missing, $gap, $matchchar );
if ( $seqs[0] ) {
$type = $seqs[0]->alphabet || $seqs[0]->_guess_alphabet || 'dna';
}
else {
$type = 'dna';
}
lib/Bio/Nexml/Factory.pm view on Meta::CPAN
=cut
sub create_bphylo_seq {
my ($self, $seq, $taxa, @args) = @_;
my $type = $seq->alphabet || $seq->_guess_alphabet || 'dna';
$type = uc($type);
my $dat = create_bphylo_datum($seq, $taxa, '-type' => $type);
# copy seq string
lib/Bio/Nexml/Factory.pm view on Meta::CPAN
$feats = shift @args;
unless (ref($feats) eq 'ARRAY') {
Bio::Root::Root->throw("Third argument must be array of SeqFeatures");
}
}
my $type = $seq->alphabet || $seq->_guess_alphabet || 'dna';
my $self = $class->new( '-type' => $type, @args );
# copy seq string
my $seqstring = $seq->seq;
if ( $seqstring and $seqstring =~ /\S/ ) {
eval { $self->set_char( $seqstring ) };
view release on metacpan or search on metacpan
beagle_wrap.c view on Meta::CPAN
#ifndef IVSIZE
# ifdef LONGSIZE
# define IVSIZE LONGSIZE
# else
# define IVSIZE 4 /* A bold guess, but the best we can make. */
# endif
#endif
#ifndef INT2PTR
# if (IVSIZE == PTRSIZE) && (UVSIZE == PTRSIZE)
view release on metacpan or search on metacpan
lib/Bio/Phylo/Matrices/DatumRole.pm view on Meta::CPAN
sub new_from_bioperl {
my ( $class, $seq, @args ) = @_;
# want $seq type-check here? Allowable: is-a Bio::PrimarySeq,
# Bio::LocatableSeq /maj
my $type = $seq->alphabet || $seq->_guess_alphabet || 'dna';
my $self = $class->new( '-type' => $type, @args );
# copy seq string
my $seqstring = $seq->seq;
if ( $seqstring and $seqstring =~ /\S/ ) {
view release on metacpan or search on metacpan
lib/Bio/PhyloTastic/DateLife.pm view on Meta::CPAN
=back
=cut
# url for the datelife.org RESTful service
my $BASE_URL = 'http://datelife.org/cgi-bin/R/result?taxa=%s,%s&format=bestguess&partial=liberal&useembargoed=yes';
# URI for datelife.org terms
my $DL_NS_URI = 'http://datelife.org/terms.owl#';
# instantiate user agent to fetch ages
view release on metacpan or search on metacpan
lib/FaSlice.pm view on Meta::CPAN
$self->throw(@msg);
}
return (@out);
}
# Read the first file of the fasta file and make a guess: Are all chromosomes
# names as 'chr1','chr2',etc or just '1','2',...?
# Future TODO: more robust chromosome name mapping?
sub chromosome_naming
{
my ($self,$fa_file) = @_;
view release on metacpan or search on metacpan
lib/Bio/Polloc/LocusIO/gff3.pm view on Meta::CPAN
for my $g (@$genomes){
$genome = $g if $g->name eq $genome_name;
last if defined $genome;
}
}
# Search the genome by sequence name (prone to errors, but it's a guess):
unless(defined $genome){
for my $g (@$genomes){
$genome = $g if defined $g->search_sequence($seqid);
last if defined $genome;
}
view release on metacpan or search on metacpan
examples/bioperl.pl view on Meta::CPAN
^,
waitenter
# we can also fetch _all_ seqs from
# a file; for this example we will
# use t/data/swiss.dat, which is in
# swiss format. usually bioperl can guess
# the file format from the file extension
# but this isn't possible here, so we
# must help by setting the input format:
^+format swiss
# now lets get all the sequences, like this:
view release on metacpan or search on metacpan
scripts/RNAalisplit.pl view on Meta::CPAN
###############
sub alisplit {
my ($alnfile,$odirn) = @_;
my ($what,$alifold,$rscape);
my $format = Bio::AlignIO->_guess_format($alnfile);
print STDERR "Guess input format $format\n";
my $AlignSplitObject = Bio::RNA::RNAaliSplit->new(ifile => $alnfile,
format => $format,
odir => $odirn);
#print Dumper($AlignSplitObject);
view release on metacpan or search on metacpan
CHANGELOG.md view on Meta::CPAN
- query\_pan\_genome 'Cant access file' error \(Non-Working-Directory inputs\) [\#421](https://github.com/sanger-pathogens/Roary/issues/421)
- How many .gff files does Roary need? [\#419](https://github.com/sanger-pathogens/Roary/issues/419)
- Installation through Bioconda not working [\#418](https://github.com/sanger-pathogens/Roary/issues/418)
- Is it possible to run roary without prokka output files? [\#417](https://github.com/sanger-pathogens/Roary/issues/417)
- Exiting early because number of clusters is too high [\#415](https://github.com/sanger-pathogens/Roary/issues/415)
- MSG: Got a sequence without letters. Could not guess alphabet? [\#414](https://github.com/sanger-pathogens/Roary/issues/414)
- Which is the advantage to pre-use prokka to perform analysis using genbank \(.gbk and gbff\) files? [\#412](https://github.com/sanger-pathogens/Roary/issues/412)
- issues with running and empty files [\#411](https://github.com/sanger-pathogens/Roary/issues/411)
- MSG: Got a sequence without letters. Could not guess alphabet [\#410](https://github.com/sanger-pathogens/Roary/issues/410)
- moose.pm issue [\#407](https://github.com/sanger-pathogens/Roary/issues/407)
- Tutorial data: extract\_proteome\_from\_gff [\#406](https://github.com/sanger-pathogens/Roary/issues/406)
- Tutorial data: extract\_proteome\_from\_gff [\#403](https://github.com/sanger-pathogens/Roary/issues/403)
- gene\_presence\_absence.csv incomplete [\#402](https://github.com/sanger-pathogens/Roary/issues/402)
- Roary including non-protein coding features? [\#398](https://github.com/sanger-pathogens/Roary/issues/398)
CHANGELOG.md view on Meta::CPAN
## [v3.6.0](https://github.com/sanger-pathogens/Roary/tree/v3.6.0) (2016-02-23)
[Full Changelog](https://github.com/sanger-pathogens/Roary/compare/v3.5.9...v3.6.0)
**Fixed bugs:**
- MSG: Got a sequence without letters. Could not guess alphabet [\#229](https://github.com/sanger-pathogens/Roary/issues/229)
**Closed issues:**
- Roary 3.5.8 works with -i 80 switch, but not with -i 90 or higher with large datasets? [\#234](https://github.com/sanger-pathogens/Roary/issues/234)
- How to use multiple switches in commandline? [\#232](https://github.com/sanger-pathogens/Roary/issues/232)
CHANGELOG.md view on Meta::CPAN
[Full Changelog](https://github.com/sanger-pathogens/Roary/compare/v2.3.1...v2.3.2)
**Fixed bugs:**
- GFF files derived from Prokka genbank raise errors [\#130](https://github.com/sanger-pathogens/Roary/issues/130)
- MSG: Got a sequence without letters. Could not guess alphabet [\#127](https://github.com/sanger-pathogens/Roary/issues/127)
**Merged pull requests:**
- TravisCI only wants the major and minor version of perl [\#141](https://github.com/sanger-pathogens/Roary/pull/141) ([bewt85](https://github.com/bewt85))
- Add TravisCI support [\#140](https://github.com/sanger-pathogens/Roary/pull/140) ([bewt85](https://github.com/bewt85))
view release on metacpan or search on metacpan
lib/Bio/SearchIO/hmmer.pm view on Meta::CPAN
my $class = ref($caller) || $caller;
my $self = $class->SUPER::new(@args);
$self->_initialize(@args);
# Try to guess the hmmer format version if it's not specified.
my $version;
my %param = @args;
@param{ map { lc $_ } keys %param } = values %param; # lowercase keys
view release on metacpan or search on metacpan
lib/Bio/ToolBox/db_helper/big.pm view on Meta::CPAN
our $VERSION = '2.00';
# Initialize CURL buffers
BEGIN {
# not clear if this should be done only once or if it's harmless to re-init
# for every new file, so I guess best to just do it here at the very beginning
# initialization is only for remote files
Bio::DB::Big->init();
}
# Exported names
lib/Bio/ToolBox/db_helper/big.pm view on Meta::CPAN
sub sum_total_bigbed_features {
# there is no easy way to do this with this adapter, except to literally
# walk through the entire file.
# well, we do this with bam files, I guess we could do the same here
# honestly, who uses this????? it's legacy. skip for now until someone complains
return undef;
}
#### BigWigSet Subroutines
view release on metacpan or search on metacpan
lib/Bio/Tools/Phylo/PAML/Codeml.pm view on Meta::CPAN
# hashref of estimates for "dN", "dS", "omega" (dN/dS ratio), "t",
# "S" and "N". If a ML matrix, "lnL" will also be defined. Any
# additional ML parameters estimated by the model will be in an
# array ref under "params"; it's up to the user to know which
# position corresponds to which parameter (since PAML doesn't label
# them, and we can't guess very well yet (a TODO I guess).
printf "The omega ratio for sequences %s vs %s was: %g\n",
$otus[0]->id, $otus[1]->id, $MLmatrix->[0]->[1]->{omega};
# with a little work, these matrices could also be passed to
view release on metacpan or search on metacpan
lib/Bio/Tools/Run/Alignment/Clustalw.pm view on Meta::CPAN
=head2 TYPE
Title : TYPE
Description : (optional) sequence type: protein or DNA. This allows
you to explicitly overide the programs attempt at
guessing the type of the sequence. It is only useful
if you are using sequences with a VERY strange
composition.
=head2 OUTPUT
view release on metacpan or search on metacpan
lib/Bio/Tools/Run/Alignment/TCoffee.pm view on Meta::CPAN
my $type = '';
if (! ref $input) {
# check that file exists or throw
$infilename = $input;
unless (-e $input) {return 0;}
# let's peek and guess
open(my $IN,$infilename) || $self->throw("Cannot open $infilename");
my $header = <$IN>;
if( $header =~ /^\s+\d+\s+\d+/ ||
$header =~ /Pileup/i ||
$header =~ /clustal/i ) { # phylip
lib/Bio/Tools/Run/Alignment/TCoffee.pm view on Meta::CPAN
=head2 TYPE
Title : TYPE
Args : [string] DNA, PROTEIN
Description : (optional) set the sequence type, guessed automatically
so should not use this directly
=head2 PARAMETERS
Title : PARAMETERS
view release on metacpan or search on metacpan
lib/Bio/Variation/IO.pm view on Meta::CPAN
my ($class, %param) = @_;
my ($format);
@param{ map { lc $_ } keys %param } = values %param; # lowercase keys
$format = $param{'-format'}
|| $class->_guess_format( $param{-file} || $ARGV[0] )
|| 'flat';
$format = "\L$format"; # normalize capitalization to lower case
return unless $class->_load_format_module($format);
return "Bio::Variation::IO::$format"->new(%param);
lib/Bio/Variation/IO.pm view on Meta::CPAN
my ($self, $seq) = @_;
$self->warn("These are not sequence objects. Use method 'write' instead of 'write_seq'.");
$self->write($seq);
}
=head2 _guess_format
Title : _guess_format
Usage : $obj->_guess_format($filename)
Function:
Example :
Returns : guessed format of filename (lower case)
Args :
=cut
sub _guess_format {
my $class = shift;
return unless $_ = shift;
return 'flat' if /\.dat$/i;
return 'xml' if /\.xml$/i;
}
view release on metacpan or search on metacpan
lib/Bio/VertRes/Config/Pipelines/Assembly.pm view on Meta::CPAN
$output_hash->{vrtrack_processed_flags} = { stored => 1, assembled => 0, rna_seq_expression => 0 };
$output_hash->{limits} = $self->_escaped_limits;
$output_hash->{data}{tmp_directory} = $self->_tmp_directory;
# rough guess at the maximum you expect to get
$output_hash->{data}{genome_size} = $self->_genome_size;
$output_hash->{data}{seq_pipeline_root} = $self->root;
$output_hash->{data}{assembler} = $self->_assembler;
$output_hash->{data}{assembler_exec} = $self->_assembler_exec;
$output_hash->{data}{optimiser_exec} = $self->_optimiser_exec;
view release on metacpan or search on metacpan
inc/Module/AutoInstall.pm view on Meta::CPAN
else {
print
"*** Dependencies will be installed the next time you type '$make'.\n";
}
# make an educated guess of whether we'll need root permission.
print " (You may need to do that as the 'root' user.)\n"
if eval '$>';
}
print "*** $class configuration finished.\n";
inc/Module/AutoInstall.pm view on Meta::CPAN
or _load('CPANPLUS::Shell::Default')
)
);
}
# make guesses on whether we're under the CPAN installation directory
sub _under_cpan {
require Cwd;
require File::Spec;
my $cwd = File::Spec->canonpath( Cwd::cwd() );
view release on metacpan or search on metacpan
lib/Bio/DB/BioSQL/BasePersistenceAdaptor.pm view on Meta::CPAN
Almost all of the following methods MUST be overridden by a
derived class. For some methods there is an implementation here
that assumes "no action" is the right thing, but for many adaptors
this won't be right. There is no way this base implementation can
make any meaningful guesses at the correct values for those.
=cut
=head2 get_persistent_slots
view release on metacpan or search on metacpan
t/lib/Test/Builder.pm view on Meta::CPAN
details). Returns the reason (ie. the value of $TODO) if running as
todo tests, false otherwise.
todo() is about finding the right package to look for $TODO in. It
uses the exported_to() package to find it. If that's not set, it's
pretty good at guessing the right package to look at based on $Level.
Sometimes there is some confusion about where todo() should be looking
for the $TODO variable. If you want to be sure, tell it explicitly
what $pack to use.
view release on metacpan or search on metacpan
lib/Bio/Tools/Run/Alignment/Amap.pm view on Meta::CPAN
my ($infilename, $seq, $temp, $tfh);
if (! ref $input) {
# check that file exists or throw
$infilename = $input;
unless (-e $input) {return 0;}
# let's peek and guess
open(IN,$infilename) || $self->throw("Cannot open $infilename");
my $header;
while( defined ($header = <IN>) ) {
last if $header !~ /^\s+$/;
}
view release on metacpan or search on metacpan
Bio/Align/AlignI.pm view on Meta::CPAN
and RNA. The output is in upper case except when gaps in
a column force output to be in lower case.
Note that if your alignment sequences contain a lot of
IUPAC ambiquity codes you often have to manually set
alphabet. Bio::PrimarySeq::_guess_type thinks they
indicate a protein sequence.
Returns : consensus string
Argument : none
Throws : on protein sequences
view release on metacpan or search on metacpan
lib/BioX/Seq/Stream.pm view on Meta::CPAN
# handle files coming from different platforms
#my @layers = PerlIO::get_layers($self->{fh});
#binmode($self->{fh},':unix:stdio:crlf');
$self->_guess_format;
$self->_init;
return $self;
lib/BioX/Seq/Stream.pm view on Meta::CPAN
my ($self, $bool) = @_;
$self->{fast} = $bool // 1;
}
sub _guess_format {
my ($self) = @_;
# Filetype guessing must be based on first two bytes (or less)
# which are stored in an object buffer
my $r = (read $self->{fh}, $self->{buffer}, 2);
die "failed to read initial bytes" if ($r != 2);
my $search_path = abs_path(__FILE__);
lib/BioX/Seq/Stream.pm view on Meta::CPAN
if ($classname->_check_type($self)) {
push @matched, $classname;
}
}
die "Failed to guess filetype\n" if (scalar(@matched) < 1);
# uncoverable branch true
die "Multiple filetypes matched\n" if (scalar(@matched) > 1);
eval "require $matched[0]";
bless $self => $matched[0];