view release on metacpan or search on metacpan
t/data/knownGene_out_of_order.dumped_result view on Meta::CPAN
'attributes' => {
'ID' => [
'AB000114'
],
'Note' => [
'guess what this thing has another location'
]
},
'start' => '11234'
}
],
view release on metacpan or search on metacpan
inc/Module/AutoInstall.pm view on Meta::CPAN
if ( @Missing and not( $CheckOnly or $UnderCPAN ) ) {
require Config;
print
"*** Dependencies will be installed the next time you type '$Config::Config{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/Gonzales/Seq.pm view on Meta::CPAN
return Bio::PrimarySeq->new(
-seq => $self->seq,
-id => $self->id,
-desc => $self->desc,
-alphabet => $self->guess_alphabet,
-direct => 1,
);
}
sub guess_alphabet {
my ($self) = @_;
my $str = $self->seq();
$str =~ s/[-.?*]//gi;
lib/Bio/Gonzales/Seq.pm view on Meta::CPAN
$alphabet = 'protein';
} else {
# Alphabet is unsure, could still be DNA, RNA or protein.
# DNA and RNA contain mostly A, T, U, G, C and N, but the other letters
# they use are also among the 15 valid letters that a protein sequence
# can contain at this stage. Make our best guess based on sequence
# composition. If it contains over 70% of ACGTUN, it is likely nucleic.
if ( ( $str =~ tr/ATUGCNatugcn// ) / $total > 0.7 ) {
if ( $str =~ m/U/i ) {
$alphabet = 'rna';
} else {
lib/Bio/Gonzales/Seq.pm view on Meta::CPAN
}
sub revcom {
my ($self) = @_;
$self->seq( _revcom_from_string( $self->seq, $self->guess_alphabet ) );
return $self;
}
sub subseq {
lib/Bio/Gonzales/Seq.pm view on Meta::CPAN
} else {
confess "cannot create reverse complement, sequence contains non-AGCTN characters"
if ( $seq =~ /[^AGCTN]/i );
}
$seq = _revcom_from_string($seq, $self->_guess_alphabet);
}
return wantarray ? ( $seq, [ $b, $e, $strand, @rest ] ) : $seq;
}
view release on metacpan or search on metacpan
lib/Bio/Graphics/Feature.pm view on Meta::CPAN
This is not called <type> because this would cause
upgrade problems from the 0.5 and earlier Seq objects.
Returns : a string either 'dna','rna','protein'. NB - the object must
make a call of the type - if there is no type specified it
has to guess.
Args : none
Status : Virtual
=head2 desc
view release on metacpan or search on metacpan
lib/Bio/Grep/Backend/BackendI.pm view on Meta::CPAN
close $NFOFILE;
}
return;
}
sub _guess_alphabet_of_file {
my ( $self, $filename ) = @_;
my $in = Bio::SeqIO->new( -file => $filename );
return $in->next_seq->alphabet;
}
view release on metacpan or search on metacpan
config_examples/blast_all-vs-all.conf view on Meta::CPAN
blast_evalue 100
# Filter query sequence (DUST with blastn, SEG with others)
blast_lowcomp F
# Perform gapped alignment (not available with tblastx)
blast_gaps T
# -a Number of processors to use and not nodes (i guess)
# -m 9 Tabular output format
blast_other -m 9 -a 1
blast_db_dir ~/blast/db
tmp_dir ~/blast/tmp
view release on metacpan or search on metacpan
}
else {
say "LD_LIBRARY_PATH is not set";
}
#could be in any of these places i guess
push @search_path, qw( /usr/local /usr /usr/share );
for my $folder ( @search_path ) {
my ( $include_dir, $lib_dir );
view release on metacpan or search on metacpan
inc/Module/AutoInstall.pm view on Meta::CPAN
else {
print
"*** Dependencies will be installed the next time you type '$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 $cwd = File::Spec->canonpath( Cwd::cwd() );
view release on metacpan or search on metacpan
t/Output/MultipleFastas.t view on Meta::CPAN
spreadsheet_basename => 'mlst_results',
parallel_processes => 3,
report_lowest_st => 1
)),'Pass in 3 assemblies, 2 perfect and where 1 has partial matches.');
ok(($multiple_fastas->create_result_files),'Create all the results files for three assemblies.');
compare_files( $tmpdirectory.'/mlst_results.genomic.csv', 't/data/expected_three_mlst_results.genomic.csv', 'Create a spreadsheet with the 3 sets of assemblies combined and the sequences, and give one best guess ST.' );
compare_files( $tmpdirectory.'/mlst_results.allele.csv', 't/data/expected_three_mlst_results.allele.csv', 'Create a spreadsheet with the 3 sets of assemblies combined and the allele numbers, and give one best guess ST.' );
compare_files( $tmpdirectory.'/concatenated_alleles.fa', 't/data/expected_three_concatenated_alleles.fa', 'Create a multi-FASTA file containing the concatenated sequences.');
###
compare_phylip_files( $tmpdirectory.'/concatenated_alleles.phylip', 't/data/expected_three_concatenated_alleles.phylip', 'Output the alignment of the concatenated gene sequences in phylip format, which is used as input to some tree building applicati...
compare_files( $tmpdirectory.'/contigs_one_unknown.unknown_allele.adk-2~.fa', 't/data/expected_three_contigs_one_unknown.unknown_allele.adk-2~.fa', 'Create FASTA files for alleles which are not in the database, so that they can be added later.' );
compare_files( $tmpdirectory.'/contigs_one_unknown.unknown_allele.recA-1~.fa', 't/data/expected_three_contigs_one_unknown.unknown_allele.recA-1~.fa', 'Create FASTA files for alleles which are not in the database, so that they can be added later.' );
view release on metacpan or search on metacpan
bin/prune-outliers.pl view on Meta::CPAN
;
### threshold: $t . ' - ' . scalar @ids . ' seqs kept out of ' . scalar keys %count_for
my $ali = Ali->load($infile);
$ali->dont_guess if $ARGV_noguessing;
my $list = IdList->new( ids => \@ids );
my $new_ali = $list->filtered_ali($ali);
# create output dirs named after input dir and identity threshold
bin/prune-outliers.pl view on Meta::CPAN
sequence to be retained in the output file [default: n.default].
=for Euclid: n.type: num
n.default: 10
=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/two-scalp.pl view on Meta::CPAN
### Check if seqs are aligned from part: $fam
# TODO: fix this as it is very dangerous to have my depending on if
# https://metacpan.org/pod/Perl::Critic::Policy::Variables::ProhibitConditionalDeclarations
## no critic (ProhibitConditionalDeclarations)
my $ali = Ali->new( seqs => $seqs_for{$fam}, guessing => 1 )
if $seqs_for{$fam};
## use critic
unless ($ali) {
carp "Warning: no sequence found for family: $fam";
bin/two-scalp.pl view on Meta::CPAN
# TODO: check how to simplify complex alternatives here
if ($aligned_seqs) {
my $aligned = Ali->new(
seqs => $aligned_seqs,
guessing => 1,
);
if ($unaligned_seqs) {
my $unaligned = Ali->new(
seqs => $unaligned_seqs,
guessing => 1,
);
### Align non aligned seqs on aligned seqs from the same family
$p2 = align_on_profile($aligned, $unaligned);
}
$p2 = $aligned unless $p2;
bin/two-scalp.pl view on Meta::CPAN
elsif ($unaligned_seqs && $master_profile) {
### There are only unaligned seqs in this family
my $unaligned = Ali->new(
seqs => $unaligned_seqs,
guessing => 1,
);
$p2 = $unaligned;
}
if ($master_profile) {
bin/two-scalp.pl view on Meta::CPAN
sub align_from_scratch {
my $seqs = shift;
my $toalign = Ali->new(
seqs => $seqs,
guessing => 1,
);
$toalign->degap_seqs;
unless ($toalign->has_uniq_ids) {
### non uniq seq id
bin/two-scalp.pl view on Meta::CPAN
my @uniq_ids = uniq @ids;
my @seq_uniq_ids = map { $ali->get_seq_with_id($_) } @uniq_ids;
my $ali2 = Ali->new(
seqs => \@seq_uniq_ids,
guessing => 1,
);
return $ali2;
}
view release on metacpan or search on metacpan
bin/ali2fasta.pl view on Meta::CPAN
for my $infile (@ARGV_infiles) {
### Processing: $infile
my $ali = Ali->load($infile);
$ali->dont_guess if $ARGV_noguessing;
$ali->degap_seqs if $ARGV_degap;
my $outfile = change_suffix($infile, '.fasta');
my $chunk = $ARGV_nowrap ? -1 : undef;
$ali->store_fasta($outfile, $chunk);
bin/ali2fasta.pl view on Meta::CPAN
=item --[no]wrap
[Don't] wrap sequences [default: yes].
=item --[no]guessing
[Don't] guess whether sequences are aligned or not [default: yes].
=item --version
=item --usage
view release on metacpan or search on metacpan
bin/annotate-ali.pl view on Meta::CPAN
}
# optionally output annotated file
if ($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 = '2.02';
# 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