diff --git a/modules/Bio/EnsEMBL/IdMapping/Archiver.pm b/modules/Bio/EnsEMBL/IdMapping/Archiver.pm
index 8cdf7e46098b9eb6ec7461f733049311f0219256..0cb6cc79ddaddcf1a90fd3c3d715922621a3467a 100644
--- a/modules/Bio/EnsEMBL/IdMapping/Archiver.pm
+++ b/modules/Bio/EnsEMBL/IdMapping/Archiver.pm
@@ -2,15 +2,41 @@ package Bio::EnsEMBL::IdMapping::Archiver;
=head1 NAME
+Bio::EnsEMBL::IdMapping::Archiver - create gene_archive and peptide_archive
=head1 SYNOPSIS
+my $archiver = Bio::EnsEMBL::IdMapping::Archiver->new(
+ -LOGGER => $logger,
+ -CONF => $conf,
+ -CACHE => $cache
+);
+
+# create gene and peptide archive
+$archiver->create_archive($mapping_session_id);
+
+# dump existing archive tables to file
+my $num_entries = $archiver->dump_table_to_file('source', 'gene_archive',
+ 'gene_archive_existing.txt', 1);
=head1 DESCRIPTION
+This module creates the gene_archive and peptide_archive tables. Data is written
+to a file as tab-delimited text for loading into a MySQL database (this can be
+done manually, or using StableIdmapper->upload_file_into_table()).
+
+An archive entry for a given source gene is created if no target gene exists, or
+if any of its transcripts or their translations changed. Non-coding transcripts
+only have an entry in gene_archive (i.e. without a corresponding peptide_archive
+entry).
=head1 METHODS
+create_archive
+dump_gene
+dump_tuple
+dump_nc_row
+mapping_session_id
=head1 LICENCE
@@ -45,6 +71,22 @@ use Digest::MD5 qw(md5_hex);
my $pa_id;
+=head2 create_archive
+
+ Arg[1] : Int $mapping_session_id - the mapping_session_id for this run
+ Example : $archiver->create_archive($stable_id_mapper->mapping_session_id);
+ Description : Creates the gene_archive and peptide_archive tables and writes
+ the data to a tab-delimited file. The decision as to what to
+ archive is deferred to dump_gene(), see documentation there for
+ details.
+ Return type : none
+ Exceptions : Thrown on missing argument.
+ Caller : id_mapping.pl
+ Status : At Risk
+ : under development
+
+=cut
+
sub create_archive {
my $self = shift;
my $mapping_session_id = shift;
@@ -92,6 +134,25 @@ sub create_archive {
}
+=head2 dump_gene
+
+ Arg[1] : Bio::EnsEMBL::IdMapping::TinyGene $s_gene - source gene
+ Arg[2] : Bio::EnsEMBL::IdMapping::TinyGene $t_gene - target gene
+ Arg[3] : Filehandle $ga_fh - filehandle for writing gene_archive data
+ Arg[4] : Filehandle $pa_fh - filehandle for writing peptide_archive data
+ Example : my $target_gene = $gene_mappings{$source_gene->stable_id};
+ $archiver->dump_gene($source_gene, $target_gene, $ga_fh, $pa_fh);
+ Description : Given a source gene, it will write a gene_achive and
+ peptide_achive entry for it if no target gene exists, or if any
+ of its transcripts or their translation changed.
+ Return type : none
+ Exceptions : none
+ Caller : create_archive()
+ Status : At Risk
+ : under development
+
+=cut
+
sub dump_gene {
my ($self, $s_gene, $t_gene, $ga_fh, $pa_fh) = @_;
@@ -113,7 +174,7 @@ sub dump_gene {
if (! $t_gene) {
$self->dump_tuple($s_gene, $s_tr, $s_tl, $ga_fh, $pa_fh);
- # otherwise, only dump if translation of this transcript changed
+ # otherwise, only dump if any transcript or its translation changed
} else {
my $changed_flag = 1;
@@ -160,6 +221,23 @@ sub dump_gene {
}
+=head2 dump_tuple
+
+ Arg[1] : Bio::EnsEMBL::IdMapping::TinyGene $gene - gene to archive
+ Arg[2] : Bio::EnsEMBL::IdMapping::TinyTrancript $tr - its transcript
+ Arg[3] : Bio::EnsEMBL::IdMapping::TinyTranslation $tl - its translation
+ Arg[4] : Filehandle $ga_fh - filehandle for writing gene_archive data
+ Arg[5] : Filehandle $pa_fh - filehandle for writing peptide_archive data
+ Example : $archive->dump_tuple($s_gene, $s_tr, $s_tl, $ga_fh, $pa_fh);
+ Description : Writes entry lines for gene_archive and peptide_archive.
+ Return type : none
+ Exceptions : none
+ Caller : dump_gene()
+ Status : At Risk
+ : under development
+
+=cut
+
sub dump_tuple {
my ($self, $gene, $tr, $tl, $ga_fh, $pa_fh) = @_;
@@ -188,6 +266,22 @@ sub dump_tuple {
}
+=head2 dump_nc_row
+
+ Arg[1] : Bio::EnsEMBL::IdMapping::TinyGene $gene - gene to archive
+ Arg[2] : Bio::EnsEMBL::IdMapping::TinyTrancript $tr - its transcript
+ Arg[3] : Filehandle $ga_fh - filehandle for writing gene_archive data
+ Example : $archive->dump_nc_row($s_gene, $s_tr, $ga_fh);
+ Description : Writes an entry line for gene_archive for non-coding
+ transcripts.
+ Return type : none
+ Exceptions : none
+ Caller : dump_gene()
+ Status : At Risk
+ : under development
+
+=cut
+
sub dump_nc_row {
my ($self, $gene, $tr, $ga_fh) = @_;
@@ -208,6 +302,19 @@ sub dump_nc_row {
}
+=head2 mapping_session_id
+
+ Arg[1] : (optional) Int - mapping_session_id to set
+ Example : my $msi = $archiver->mapping_session_id;
+ Description : Getter/setter for mapping_session_id.
+ Return type : Int
+ Exceptions : none
+ Caller : create_archive()
+ Status : At Risk
+ : under development
+
+=cut
+
sub mapping_session_id {
my $self = shift;
$self->{'_mapping_session_id'} = shift if (@_);
diff --git a/modules/Bio/EnsEMBL/IdMapping/Cache.pm b/modules/Bio/EnsEMBL/IdMapping/Cache.pm
index 8d298aeff5e5e7d67f9c9df9d7086c9e72010346..ba60460e6c94d7ef2650c2f20b93fd897d708306 100644
--- a/modules/Bio/EnsEMBL/IdMapping/Cache.pm
+++ b/modules/Bio/EnsEMBL/IdMapping/Cache.pm
@@ -1173,11 +1173,7 @@ sub slice_names {
}
-#
-# getters/setters
-#
-
-=head2
+=head2 logger
Arg[1] :
Example :
@@ -1196,7 +1192,7 @@ sub logger {
}
-=head2
+=head2 conf
Arg[1] :
Example :
diff --git a/modules/Bio/EnsEMBL/IdMapping/Entry.pm b/modules/Bio/EnsEMBL/IdMapping/Entry.pm
index b56112314e39f9c6c6f031f2188288961b73f96a..a78be390f699efce13132fb065bc3080b8649a40 100644
--- a/modules/Bio/EnsEMBL/IdMapping/Entry.pm
+++ b/modules/Bio/EnsEMBL/IdMapping/Entry.pm
@@ -2,15 +2,24 @@ package Bio::EnsEMBL::IdMapping::Entry;
=head1 NAME
+Bio::EnsEMBL::IdMapping::Entry - object representing a ScoredMappingMatrix entry
=head1 SYNOPSIS
=head1 DESCRIPTION
+This object represents a ScoredMappingMatrix entry. It is defined by a pair of a
+source and target object's internal Id and a score for this mapping.
=head1 METHODS
+new
+new_fast
+source
+target
+score
+to_string
=head1 LICENCE
@@ -35,6 +44,20 @@ no warnings 'uninitialized';
use Bio::EnsEMBL::Utils::Exception qw(throw warning);
+=head2 new
+
+ Example : my $entry = Bio::EnsEMBL::IdMapping::Entry->new();
+ Description : Constructor. This is a no-argument constructor, so you need to
+ populate the object manually. Rarely used since in most cases
+ new_fast() is preferred.
+ Return type : a Bio::EnsEMBL::IdMapping::Entry object
+ Exceptions : none
+ Caller : general
+ Status : At Risk
+ : under development
+
+=cut
+
sub new {
my $caller = shift;
my $class = ref($caller) || $caller;
@@ -46,6 +69,21 @@ sub new {
}
+=head2 new_fast
+
+ Arg[1] : Arrayref $array_ref - the arrayref to bless into the Entry
+ object
+ Example : my $entry = Bio::EnsEMBL::IdMapping::Entry->new_fast([
+ $source_gene->id, $target_gene->id, 0.9]);
+ Description : Fast constructor.
+ Return type : a Bio::EnsEMBL::IdMapping::Entry object
+ Exceptions : none
+ Caller : general
+ Status : At Risk
+ : under development
+
+=cut
+
sub new_fast {
my $class = shift;
my $array_ref = shift;
@@ -53,6 +91,18 @@ sub new_fast {
}
+=head2 source
+
+ Arg[1] : (optional) Int - source object's internal Id
+ Description : Getter/setter for source object's internal Id.
+ Return type : Int
+ Exceptions : none
+ Caller : general
+ Status : At Risk
+ : under development
+
+=cut
+
sub source {
my $self = shift;
$self->[0] = shift if (@_);
@@ -60,6 +110,18 @@ sub source {
}
+=head2 target
+
+ Arg[1] : (optional) Int - target object's internal Id
+ Description : Getter/setter for target object's internal Id.
+ Return type : Int
+ Exceptions : none
+ Caller : general
+ Status : At Risk
+ : under development
+
+=cut
+
sub target {
my $self = shift;
$self->[1] = shift if (@_);
@@ -67,6 +129,19 @@ sub target {
}
+=head2 score
+
+ Arg[1] : (optional) Float - a score
+ Description : Getter/setter for score for the mapping between source and
+ target object.
+ Return type : Float
+ Exceptions : none
+ Caller : general
+ Status : At Risk
+ : under development
+
+=cut
+
sub score {
my $self = shift;
$self->[2] = shift if (@_);
@@ -74,15 +149,22 @@ sub score {
}
-sub to_string {
- my $self = shift;
- return sprintf('%-10s%-10s%-5.6f', $self->source, $self->target, $self->score);
-}
+=head2 to_string
+ Example : print LOG $entry->to_string, "\n";
+ Description : Returns a string representation of the Entry object. Useful for
+ debugging and logging.
+ Return type : String
+ Exceptions : none
+ Caller : general
+ Status : At Risk
+ : under development
-sub to_string_compat {
+=cut
+
+sub to_string {
my $self = shift;
- return join(" ", $self->source, $self->target, $self->score);
+ return sprintf('%-10s%-10s%-5.6f', $self->source, $self->target, $self->score);
}
diff --git a/modules/Bio/EnsEMBL/IdMapping/MappingList.pm b/modules/Bio/EnsEMBL/IdMapping/MappingList.pm
index 4f9d66cedb2f8bb3ef78a515b5d0a420060d43e4..300a107cd9fd22d37cc0baf18bed466096428c41 100644
--- a/modules/Bio/EnsEMBL/IdMapping/MappingList.pm
+++ b/modules/Bio/EnsEMBL/IdMapping/MappingList.pm
@@ -2,15 +2,45 @@ package Bio::EnsEMBL::IdMapping::MappingList;
=head1 NAME
+Bio::EnsEMBL::IdMapping::MappingList - object holding a list of Entries
=head1 SYNOPSIS
+# create a new MappingList
+my $mappings = Bio::EnsEMBL::IdMapping::MappingList->new(
+ -DUMP_PATH => $dump_path,
+ -CACHE_FILE => 'gene_mappings.ser',
+);
+
+# add entries
+my $mappings->add_Entry($entry1);
+my $mappings->add_all($entry2, $entry3);
+
+# serialise to file
+$mappings->write_to_file;
+
+# later, read these mappings from file
+my $mappings1 = Bio::EnsEMBL::IdMapping::MappingList->new(
+ -DUMP_PATH => $dump_path,
+ -CACHE_FILE => 'gene_mappings.ser',
+);
+$mappings1->read_from_file;
=head1 DESCRIPTION
+This object represents a list of Bio::EnsEMBL::IdMapping::Entry objects. It's
+essentially an OO wrapper for an array with some type checking and convenience
+methods.
=head1 METHODS
+new
+add_Entry
+get_all_Entries
+add_all
+get_entry_count
+log
+to_string
=head1 LICENCE
@@ -40,6 +70,22 @@ use Bio::EnsEMBL::Utils::Exception qw(throw warning);
use Bio::EnsEMBL::Utils::ScriptUtils qw(path_append);
+=head2 new
+
+ Arg[1-N] : see superclass
+ Example : my $gene_mappings = Bio::EnsEMBL::IdMapping::MappingList->new(
+ -DUMP_PATH => $dump_path,
+ -CACHE_FILE => 'gene_mappings.ser',
+ );
+ Description : Constructor.
+ Return type : Bio::EnsEMBL::IdMapping::MappingList
+ Exceptions : none
+ Caller : general
+ Status : At Risk
+ : under development
+
+=cut
+
sub new {
my $caller = shift;
my $class = ref($caller) || $caller;
@@ -54,6 +100,19 @@ sub new {
}
+=head2 add_Entry
+
+ Arg[1] : Bio::EnsEMBL::IdMapping::Entry - Entry to add
+ Example : $mappings->add_Entry($entry);
+ Description : Adds an Entry to the MappingList.
+ Return type : none
+ Exceptions : thrown on wrong or missing argument
+ Caller : general
+ Status : At Risk
+ : under development
+
+=cut
+
sub add_Entry {
my $self = shift;
my $entry = shift;
@@ -66,12 +125,40 @@ sub add_Entry {
}
+=head2 get_all_Entries
+
+ Example : foreach my $entry (@{ $mappings->get_all_Entries }) {
+ # do something with the entry
+ }
+ Description : Gets all Entries in the MappingList.
+ Return type : Arrayref of Bio::EnsEMBL::IdMapping::Entry
+ Exceptions : none
+ Caller : general
+ Status : At Risk
+ : under development
+
+=cut
+
sub get_all_Entries {
my $self = shift;
return $self->{'cache'}->{'entries'};
}
+=head2 add_all
+
+ Arg[1] : List of Bio::EnsEMBL::IdMapping::Entry objects
+ Example : my @entries = ($entry1, $entry2);
+ $mappings->add_all(@entries);
+ Description : Adds a list of Entries to the MappingList.
+ Return type : none
+ Exceptions : thrown on wrong argument
+ Caller : general
+ Status : At Risk
+ : under development
+
+=cut
+
sub add_all {
my $self = shift;
my @mappings = @_;
@@ -87,12 +174,39 @@ sub add_all {
}
+=head2 get_entry_count
+
+ Example : my $num_entries = $mappings->get_entry_count;
+ Description : Returns the number of Entries in the MappingList.
+ Return type : Int
+ Exceptions : none
+ Caller : general
+ Status : At Risk
+ : under development
+
+=cut
+
sub get_entry_count {
my $self = shift;
return scalar(@{ $self->{'cache'}->{'entries'} });
}
+=head2 log
+
+ Arg[1] : String $type - object type (e.g. 'gene')
+ Arg[2] : String $dump_path - path for writing output
+ Example : $mappings->log('gene', $conf->param('basedir'));
+ Description : Logs all Entries in the MappingList to a file. Used for
+ debugging.
+ Return type : none
+ Exceptions : thrown on I/0 error
+ Caller : general
+ Status : At Risk
+ : under development
+
+=cut
+
sub log {
my $self = shift;
my $type = shift;
@@ -112,6 +226,21 @@ sub log {
}
+=head2 to_string
+
+ Example : print LOG $mappings->to_string, "\n";
+ Description : Returns a string representation of the MappingList. This is
+ simply a multi-line string, where each line is a stringified
+ Entry.
+ Useful for debugging and logging.
+ Return type : String
+ Exceptions : none
+ Caller : general
+ Status : At Risk
+ : under development
+
+=cut
+
sub to_string {
my $self = shift;
diff --git a/modules/Bio/EnsEMBL/IdMapping/ResultAnalyser.pm b/modules/Bio/EnsEMBL/IdMapping/ResultAnalyser.pm
index db83cf8a1793aa01518d1d00bb7ea157e22b6886..b96542d91c6a1e8966c4d66078175c560c9ba628 100644
--- a/modules/Bio/EnsEMBL/IdMapping/ResultAnalyser.pm
+++ b/modules/Bio/EnsEMBL/IdMapping/ResultAnalyser.pm
@@ -2,15 +2,55 @@ package Bio::EnsEMBL::IdMapping::ResultAnalyser;
=head1 NAME
+Bio::EnsEMBL::IdMapping::ResultAnalyser - analyse stable Id mapping results
=head1 SYNOPSIS
+# get a result analyser
+my $analyser = Bio::EnsEMBL::IdMapping::ResultAnalyser->new(
+ -LOGGER => $logger,
+ -CONF => $conf,
+ -CACHE => $cache
+);
+
+# analyse results
+$analyser->analyse($gene_mappings,
+ $stable_id_mapper->get_all_stable_id_events('similarity'));
+
+# write results to file
+$analyser->write_results_to_file;
+
+# create click lists
+$analyser->create_clicklist;
+
+# summary email
+$analyser->create_summary_email;
=head1 DESCRIPTION
+This is a utility module which analyses the stable Id mapping results by
+providing various sorts of mapping statistics. It also creates clicklists and a
+summary email.
=head1 METHODS
+analyse
+analyse_db
+classify_source_genes_by_type
+classify_genes_by_mapping_simple
+classify_genes_by_mapping
+add
+get
+get_all_by_subclass
+get_all_by_class
+get_count_by_subclass
+get_count_by_class
+get_all_classes
+class_key
+write_results_to_file
+create_clicklist
+create_summary_email
+read_from_file
=head1 LICENCE
@@ -40,6 +80,22 @@ use Bio::EnsEMBL::Utils::Exception qw(throw warning);
use Bio::EnsEMBL::Utils::ScriptUtils qw(path_append);
+=head2 analyse
+
+ Arg[1] : Bio::EnsEMBL::IdMapping::MappingList $gene_mappings - the gene
+ mappings to analyse
+ Arg[2] : Arrayref of Strings - similarity events
+ Example : $analyser->analyse($gene_mappings,
+ $stable_id_mapper->get_all_stable_id_events('similarity'));
+ Description : Analyses the results of a stable Id mapping run.
+ Return type : none
+ Exceptions : thrown on wrong or missing arguments
+ Caller : general
+ Status : At Risk
+ : under development
+
+=cut
+
sub analyse {
my $self = shift;
my $gene_mappings = shift;
@@ -62,14 +118,20 @@ sub analyse {
$self->classify_genes_by_mapping($gene_mappings, $similarity_events);
}
-#
-# Analyse stable ID data from two existing dbs.
-# This is for potential stand-alone use of this module.
-#
-# [todo]
-sub analyse_db {
-}
+=head2 classify_source_genes_by_type
+
+ Example : $analyser->classify_source_genes_by_type;
+ Description : Classifies source genes by type and adds them to the internal
+ datastructure. For the format of the classification string see
+ class_key().
+ Return type : none
+ Exceptions : none
+ Caller : internal
+ Status : At Risk
+ : under development
+
+=cut
sub classify_source_genes_by_type {
my $self = shift;
@@ -80,7 +142,21 @@ sub classify_source_genes_by_type {
}
-sub classify_target_genes_by_type {
+=head2 classify_genes_by_mapping_simple
+
+ Arg[1] : Bio::EnsEMBL::IdMapping::MapppingList $gene_mappings - gene
+ mappings to classify
+ Example : $analyser->classify_genes_by_mapping_simple;
+ Description : Classifies target genes by mapping ('mapped' or 'unmapped').
+ Return type : none
+ Exceptions : thrown on wrong or missing argument
+ Caller : This method is not in use at the momen.
+ Status : At Risk
+ : under development
+
+=cut
+
+sub classify_genes_by_mapping_simple {
my $self = shift;
my $gene_mappings = shift;
@@ -122,13 +198,25 @@ sub classify_target_genes_by_type {
}
-#
-# genes will be classified as:
-# - mapped
-# - deleted
-# - lost_similar
-# - lost_definite
-#
+=head2 classify_genes_by_mapping
+
+ Arg[1] : Bio::EnsEMBL::IdMapping::MapppingList $gene_mappings - gene
+ mappings to classify
+ Arg[2] : Arrayref of Strings - similarity events
+ Example : $analyser->classify_genes_by_mapping;
+ Description : Classifies genes by mapping. Status is
+ 'mapped' => stable Id was mapped
+ 'lost_similar' => stable Id not mapped, but there is a
+ similarity entry for the source Id
+ 'lost_definite' => not mapped and no similarity
+ Return type : none
+ Exceptions : thrown on wrong or missing argument
+ Caller : This method is not in use at the momen.
+ Status : At Risk
+ : under development
+
+=cut
+
sub classify_genes_by_mapping {
my $self = shift;
my $gene_mappings = shift;
@@ -179,13 +267,28 @@ sub classify_genes_by_mapping {
}
-#
-# Add a stable ID / property pair to a name/dbtype lookup hash.
-#
-# This datastructure is a bloat for some applications, but is general enough to
-# be used as a lookup hash and to generate statistics (counts by type) and
-# debug lists (dump by type).
-#
+=head2 add
+
+ Arg[1] : String $dbtype - db type ('source' or 'target')
+ Arg[2] : String $class - key identifying a gene type (see class_key())
+ Arg[3] : String $subclass - status identifier (e.g. 'mapped', 'lost')
+ Arg[4] : String $stable_id - gene stable Id
+ Arg[5] : String $val - value (usually 0 or 1)
+ Example : $analyser->add('source', 'KNOWN-ensembl-protein_coding',
+ 'mapped', 'ENSG00002342', 1);
+ Description : Add a stable Id / property pair to a name/dbtype lookup hash.
+
+ The datastructure is a bit of a bloat, but is general enough to
+ be used as a lookup hash and to generate statistics (counts by
+ type) and debug lists (dump by type).
+ Return type : String - the added value
+ Exceptions : none
+ Caller : internal
+ Status : At Risk
+ : under development
+
+=cut
+
sub add {
my ($self, $dbtype, $class, $subclass, $stable_id, $val) = @_;
@@ -198,6 +301,23 @@ sub add {
}
+=head2 get
+
+ Arg[1] : String $dbtype - db type ('source' or 'target')
+ Arg[2] : String $class - key identifying a gene type (see class_key())
+ Arg[3] : String $subclass - status identifier (e.g. 'mapped', 'lost')
+ Arg[4] : String $stable_id - gene stable Id
+ Example : my $mapping_status = $analyser->get('source',
+ 'KNOWN-ensembl-protein_coding', 'mapped', 'ENSG00002342');
+ Description : Gets a stable Id mapping status from the internal datastructure.
+ Return type : String
+ Exceptions : none
+ Caller : internal
+ Status : At Risk
+ : under development
+
+=cut
+
sub get {
my ($self, $dbtype, $class, $subclass, $stable_id) = @_;
@@ -207,6 +327,22 @@ sub get {
}
+=head2 get_all_by_subclass
+
+ Arg[1] : String $dbtype - db type ('source' or 'target')
+ Arg[2] : String $class - key identifying a gene type (see class_key())
+ Arg[3] : String $subclass - status identifier (e.g. 'mapped', 'lost')
+ Example : my @mapped_stable_ids = $analyser->get_all_by_subclass('source',
+ 'KNOWN-ensembl-protein_coding', 'mapped');
+ Description : Gets a list of stable Id for a given subclass.
+ Return type : Arrayref of String (stable Ids)
+ Exceptions : thrown on missing arguments
+ Caller : internal
+ Status : At Risk
+ : under development
+
+=cut
+
sub get_all_by_subclass {
my ($self, $dbtype, $class, $subclass) = @_;
@@ -219,6 +355,21 @@ sub get_all_by_subclass {
}
+=head2 get_all_by_class
+
+ Arg[1] : String $dbtype - db type ('source' or 'target')
+ Arg[2] : String $class - key identifying a gene type (see class_key())
+ Example : my @stable_ids = $analyser->get_all_by_class('source',
+ 'KNOWN-ensembl-protein_coding');
+ Description : Gets a list of stable Id for a given class.
+ Return type : Arrayref of String (stable Ids)
+ Exceptions : thrown on missing arguments
+ Caller : internal
+ Status : At Risk
+ : under development
+
+=cut
+
sub get_all_by_class {
my ($self, $dbtype, $class) = @_;
@@ -238,6 +389,22 @@ sub get_all_by_class {
}
+=head2 get_count_by_subclass
+
+ Arg[1] : String $dbtype - db type ('source' or 'target')
+ Arg[2] : String $class - key identifying a gene type (see class_key())
+ Arg[3] : String $subclass - status identifier (e.g. 'mapped', 'lost')
+ Example : my $num_mapped = $analyser->get_count_by_subclass('source',
+ 'KNOWN-ensembl-protein_coding', 'mapped');
+ Description : Gets the number of stable Ids for a given subclass.
+ Return type : Int
+ Exceptions : thrown on missing arguments
+ Caller : internal
+ Status : At Risk
+ : under development
+
+=cut
+
sub get_count_by_subclass {
my ($self, $dbtype, $class, $subclass) = @_;
@@ -250,6 +417,21 @@ sub get_count_by_subclass {
}
+=head2 get_count_by_class
+
+ Arg[1] : String $dbtype - db type ('source' or 'target')
+ Arg[2] : String $class - key identifying a gene type (see class_key())
+ Example : my $num_mapped = $analyser->get_count_by_class('source',
+ 'KNOWN-ensembl-protein_coding');
+ Description : Gets the number of stable Ids for a given class.
+ Return type : Int
+ Exceptions : thrown on missing arguments
+ Caller : internal
+ Status : At Risk
+ : under development
+
+=cut
+
sub get_count_by_class {
my ($self, $dbtype, $class) = @_;
@@ -261,6 +443,21 @@ sub get_count_by_class {
}
+=head2 get_all_classes
+
+ Arg[1] : String $dbtype - db type ('source' or 'target')
+ Example : foreach my $class (@{ $analyser->get_all_classes('source') }) {
+ print "$class\n";
+ }
+ Description : Gets a list of classes in the ResultAnalyser.
+ Return type : Arrayref of String
+ Exceptions : thrown on missing argument
+ Caller : internal
+ Status : At Risk
+ : under development
+
+=cut
+
sub get_all_classes {
my ($self, $dbtype) = @_;
@@ -271,12 +468,39 @@ sub get_all_classes {
}
+=head2 class_key
+
+ Arg[1] : Bio::EnsEMBL::IdMapping::TinyGene $gene - a gene object
+ Example : my $class = $analyser->class_key($gene);
+ Description : Generates a key identifying a gene class. This identifier is
+ composed from the gene's status, logic naame, and biotye.
+ Return type : String
+ Exceptions : none
+ Caller : internal
+ Status : At Risk
+ : under development
+
+=cut
+
sub class_key {
my ($self, $gene) = @_;
return join('-', map { $gene->$_ } qw(status logic_name biotype));
}
+=head2 write_results_to_file
+
+ Example : $analyser->write_results_to_file;
+ Description : Writes the results of the result analysis to a file. This is a
+ human-readable text detailing the mapping statistics.
+ Return type : none
+ Exceptions : none
+ Caller : general
+ Status : At Risk
+ : under development
+
+=cut
+
sub write_results_to_file {
my $self = shift;
@@ -320,6 +544,20 @@ sub write_results_to_file {
}
+=head2 create_clicklist
+
+ Example : $analyser->create_clicklist;
+ Description : Writes an html file which contains a list of all lost genes,
+ with hyperlinks to the appropriate archive website. This is to
+ manually check lost genes.
+ Return type : none
+ Exceptions : none
+ Caller : general
+ Status : At Risk
+ : under development
+
+=cut
+
sub create_clicklist {
my $self = shift;
@@ -377,6 +615,21 @@ sub create_clicklist {
}
+=head2 create_summary_email
+
+ Example : $analyser->create_summary_email;
+ Description : Writes a text file containing a summary of the mapping stats.
+ This will be emailed to the genebuilder for evaluation (you will
+ have to manually send the email, using the text in
+ summary_email.txt as the template).
+ Return type : none
+ Exceptions : none
+ Caller : general
+ Status : At Risk
+ : under development
+
+=cut
+
sub create_summary_email {
my $self = shift;
@@ -496,6 +749,21 @@ sub create_summary_email {
}
+=head2 read_from_file
+
+ Arg[1] : String $filename - name of file to read
+ Arg[2] : (optional) String $append - directory name to append to basedir
+ Example : my $stats_text = $analyser->read_from_file('gene_mapping_stats',
+ 'stats');
+ Description : Reads mapping stats from a file.
+ Return type : String
+ Exceptions : none
+ Caller : internal
+ Status : At Risk
+ : under development
+
+=cut
+
sub read_from_file {
my $self = shift;
my $filename = shift;
diff --git a/modules/Bio/EnsEMBL/IdMapping/ScoreBuilder.pm b/modules/Bio/EnsEMBL/IdMapping/ScoreBuilder.pm
index e884d99c6cb4be52b646e3893c5e5840116d64d8..015db1a63051f7fbf8c584103c2f4cbfe6555749 100644
--- a/modules/Bio/EnsEMBL/IdMapping/ScoreBuilder.pm
+++ b/modules/Bio/EnsEMBL/IdMapping/ScoreBuilder.pm
@@ -2,15 +2,23 @@ package Bio::EnsEMBL::IdMapping::ScoreBuilder;
=head1 NAME
+Bio::EnsEMBL::IdMapping::ScoreBuilder - score builder base class
=head1 SYNOPSIS
+This class is not instantiated. Please see subclasses for usage examples (e.g.
+GeneScoreBuilder).
=head1 DESCRIPTION
+This is the base class for the score builders used in the stable Id mapping
+application. It contains methods which are used by more than one ScoreBuilder.
=head1 METHODS
+create_shrinked_matrix
+internal_id_rescore
+log_matrix_stats
=head1 LICENCE
@@ -41,9 +49,26 @@ use Bio::EnsEMBL::Utils::ScriptUtils qw(path_append);
use Bio::EnsEMBL::IdMapping::ScoredMappingMatrix;
-#
-# create a shrinked matrix which doesn't contain entries which were already
-# mapped
+=head2 create_shrinked_matrix
+
+ Arg[1] : Bio::EnsEMBL::Idmapping::ScoredMappingMatrix $matrix - a scoring
+ matrix
+ Arg[2] : Bio::EnsEMBL::Idmapping::MappingList $mappings - mappings
+ Arg[3] : String $cache_file - base name of a cache file (extension '.ser'
+ will be added automatically) for the returned matrix
+ Example : my $new_scores = $score_builder->create_shrinked_matrix(
+ $gene_scores, $mappings, "gene_matrix1");
+ Description : Create a shrinked scoring matrix which doesn't contain entries
+ which were already mapped. It also logs how many new mappings
+ were added in this process.
+ Return type : Bio::EnsEMBL::IdMapping::ScoredMappingMatrix
+ Exceptions : thrown on wrong or missing arguments
+ Caller : InternalIdMapper plugin
+ Status : At Risk
+ : under development
+
+=cut
+
#
sub create_shrinked_matrix {
my $self = shift;
@@ -111,6 +136,27 @@ sub create_shrinked_matrix {
}
+=head2 internal_id_rescore
+
+ Arg[1] : Bio::EnsEMBL::Idmapping::ScoredMappingMatrix $matrix - a scoring
+ matrix
+ Example : $score_builder->internal_id_rescore($gene_scores);
+ Description : Rescore ambiguous mappings based on internal Ids. This is the
+ last disambiguation step and is only useful if objects with the
+ same internal Id were used in source and target dbs (e.g. in
+ patch builds or if objects were copied from source to target).
+
+ If a source and target gene have the same internal Id and there
+ are mappings to other target genes then these *other* mappings
+ are penalised.
+ Return type : none
+ Exceptions : thrown on wrong or missing argument
+ Caller : InternalIdMapper plugins
+ Status : At Risk
+ : under development
+
+=cut
+
sub internal_id_rescore {
my $self = shift;
my $matrix = shift;
@@ -158,6 +204,21 @@ sub internal_id_rescore {
}
+=head2 log_matrix_stats
+
+ Arg[1] : Bio::EnsEMBL::Idmapping::ScoredMappingMatrix $matrix - a scoring
+ matrix
+ Example : $score_builder->log_matrix_stats;
+ Description : Logs scoring matrix statistics (number of entries, min/max/avg
+ scores).
+ Return type : none
+ Exceptions : thrown on wrong or missing argument
+ Caller : general
+ Status : At Risk
+ : under development
+
+=cut
+
sub log_matrix_stats {
my $self = shift;
my $matrix = shift;
diff --git a/modules/Bio/EnsEMBL/IdMapping/ScoredMappingMatrix.pm b/modules/Bio/EnsEMBL/IdMapping/ScoredMappingMatrix.pm
index fb85effd88191f3f13f6d94016f35c298b44b555..a9f3ba1c6cc32a7a17847f6d46026b8bdc0272d4 100644
--- a/modules/Bio/EnsEMBL/IdMapping/ScoredMappingMatrix.pm
+++ b/modules/Bio/EnsEMBL/IdMapping/ScoredMappingMatrix.pm
@@ -2,15 +2,68 @@ package Bio::EnsEMBL::IdMapping::ScoredMappingMatrix;
=head1 NAME
+Bio::EnsEMBL::IdMapping::ScoredMappingMatrix - object holding a list of scored
+Entries
=head1 SYNOPSIS
+# create a new ScoredMappingMatrix
+my $gene_scores = Bio::EnsEMBL::IdMapping::ScoredMappingMatrix->new(
+ -DUMP_PATH => $dump_path,
+ -CACHE_FILE => 'gene_scores.ser',
+);
+
+# add entries
+my $gene_scores->add_Entry($entry1);
+
+# serialise to file
+$gene_scores->write_to_file;
+
+# later, read these gene_scores from file
+my $gene_scores1 = Bio::EnsEMBL::IdMapping::ScoredMappingMatrix->new(
+ -DUMP_PATH => $dump_path,
+ -CACHE_FILE => 'gene_gene_scores.ser',
+);
+$gene_scores1->read_from_file;
=head1 DESCRIPTION
+This object represents a collection of scores between source and target objects.
+It holds a list of Bio::EnsEMBL::IdMapping::Entry objects and has methods to
+retrieve indiviual or all Entries, as well as derived data like number of unique
+sources or targets, or various counts and averages.
+
+It is the main collection for dealing with scored relationships in the stable Id
+mapping application.
=head1 METHODS
+new
+flush
+sub_matrix
+add_Entry
+update_Entry
+remove_Entry
+add_score
+set_score
+get_Entry
+get_score
+get_targets_for_source
+get_Entries_for_source
+get_sources_for_target
+get_Entries_for_target
+get_all_Entries
+get_all_sources
+get_all_targets
+get_entry_count
+size
+get_source_count
+get_target_count
+get_min_max_scores
+get_average_score
+merge
+log
+to_string
=head1 LICENCE
@@ -42,6 +95,22 @@ use Bio::EnsEMBL::Utils::ScriptUtils qw(path_append);
use Bio::EnsEMBL::IdMapping::Entry;
+=head2 new
+
+ Arg[1-N] : see superclass
+ Example : my $gene_scores = Bio::EnsEMBL::IdMapping::ScoredMappingMatrix->new(
+ -DUMP_PATH => $dump_path,
+ -CACHE_FILE => 'gene_scores.ser',
+ );
+ Description : Constructor.
+ Return type : Bio::EnsEMBL::IdMapping::ScoredMappingMatrix
+ Exceptions : none
+ Caller : general
+ Status : At Risk
+ : under development
+
+=cut
+
sub new {
my $caller = shift;
my $class = ref($caller) || $caller;
@@ -58,6 +127,18 @@ sub new {
}
+=head2 flush
+
+ Example : $gene_scores->flush;
+ Description : Flushes (empties) the scoring matrix.
+ Return type : none
+ Exceptions : none
+ Caller : general
+ Status : At Risk
+ : under development
+
+=cut
+
sub flush {
my $self = shift;
@@ -68,6 +149,24 @@ sub flush {
}
+=head2 sub_matrix
+
+ Arg[1] : Int $start - start index (inclusive)
+ Arg[2] : Int $end - end index (inclusive)
+ Example : # get the first 1000 elements in the matrix
+ my $sub_matrix = $gene_scores->sub_matrix(1, 1000);
+ Description : Returns a sub-matrix of the ScoredMappingMatrix. The arguments
+ ($start and $end) specify the position of the first and last
+ element to return (inclusive, counting starts with element 1,
+ not 0)
+ Return type : Bio::EnsEMBL::IdMapping::ScoredMappingMatrix
+ Exceptions : none
+ Caller : general
+ Status : At Risk
+ : under development
+
+=cut
+
sub sub_matrix {
my $self = shift;
my $start = shift;
@@ -97,6 +196,19 @@ sub sub_matrix {
}
+=head2 add_Entry
+
+ Arg[1] : Bio::EnsEMBL::IdMapping::Entry $entry - Entry to add
+ Example : $gene_scores->add_Entry($entry);
+ Description : Adds an Entry to the scoring matrix.
+ Return type : Float - the Entry's score
+ Exceptions : thrown on wrong or missing argument
+ Caller : general
+ Status : At Risk
+ : under development
+
+=cut
+
sub add_Entry {
my $self = shift;
my $entry = shift;
@@ -109,16 +221,50 @@ sub add_Entry {
}
+=head2 update_Entry
+
+ Arg[1] : Bio::EnsEMBL::IdMapping::Entry $entry - Entry to update
+ Example : $gene_scores->update_Entry($entry);
+ Description : Updates an Entry (or rather its score) in the scoring matrix.
+ Actually delegates to add_Entry(), only there as an intuitively
+ named wrapper.
+ Return type : Float - the Entry's score
+ Exceptions : thrown on wrong or missing argument
+ Caller : general
+ Status : At Risk
+ : under development
+
+=cut
+
sub update_Entry {
return $_[0]->add_Entry($_[1]);
}
+#
+# not needed in the current application, so not implemented
+#
sub remove_Entry {
warning('Method ScoredMappingMatrix->remove_Entry not implemented (yet).');
}
+=head2 add_score
+
+ Arg[1] : Int $source - source object's internal Id ("dbID")
+ Arg[2] : Int $target - target object's internal Id ("dbID")
+ Arg[3] : Float $score - score for source/target pair
+ Example : $gene_scores->add_score(1234, 5678, 0.997);
+ Description : Adds a score for a source/target pair to the scoring matrix.
+ This is a low-level version of add_Entry().
+ Return type : Float - the score
+ Exceptions : none
+ Caller : general
+ Status : At Risk
+ : under development
+
+=cut
+
sub add_score {
my $self = shift;
my $source = shift;
@@ -135,6 +281,24 @@ sub add_score {
}
+=head2 set_score
+
+ Arg[1] : Int $source - source object's internal Id ("dbID")
+ Arg[2] : Int $target - target object's internal Id ("dbID")
+ Arg[3] : Float $score - score for source/target pair
+ Example : $gene_scores->set_score(1234, 5678, 0.997);
+ Description : Sets the score for a source/target pair in the scoring matrix.
+ This method is similar to add_score, but assumes that the Entry
+ has been added before, so won't update the sources and target
+ lists.
+ Return type : Float - the score
+ Exceptions : none
+ Caller : general
+ Status : At Risk
+ : under development
+
+=cut
+
sub set_score {
my $self = shift;
my $source = shift;
@@ -145,6 +309,22 @@ sub set_score {
}
+=head2 get_Entry
+
+ Arg[1] : Int $source - source object's internal Id ("dbID")
+ Arg[2] : Int $target - target object's internal Id ("dbID")
+ Example : my $entry = $gene_scores->get_Entry($source_gene->id,
+ $target_gene->id);
+ Description : Gets an Entry from the scoring matrix for a given source and
+ target object.
+ Return type : Bio::EnsEMBL::IdMapping::Entry or undef
+ Exceptions : none
+ Caller : general
+ Status : At Risk
+ : under development
+
+=cut
+
sub get_Entry {
my $self = shift;
my $source = shift;
@@ -160,6 +340,22 @@ sub get_Entry {
}
+=head2 get_score
+
+ Arg[1] : Int $source - source object's internal Id ("dbID")
+ Arg[2] : Int $target - target object's internal Id ("dbID")
+ Example : my $score = $gene_scores->get_score($source_gene->id,
+ $target_gene->id);
+ Description : Gets the score from the scoring matrix for a given source and
+ target object.
+ Return type : Float or undef
+ Exceptions : none
+ Caller : general
+ Status : At Risk
+ : under development
+
+=cut
+
sub get_score {
my $self = shift;
my $source = shift;
@@ -174,6 +370,20 @@ sub get_score {
}
+=head2 get_targets_for_source
+
+ Arg[1] : Int $source - source object's internal Id ("dbID")
+ Example : my @targets = $gene_scores->get_targets_for_source(1234);
+ Description : Returns a list of all targets which have a score against a given
+ source object.
+ Return type : Arrayref of Int (target objects' internal Ids)
+ Exceptions : none
+ Caller : general
+ Status : At Risk
+ : under development
+
+=cut
+
sub get_targets_for_source {
my $self = shift;
my $source = shift;
@@ -182,6 +392,20 @@ sub get_targets_for_source {
}
+=head2 get_Entries_for_source
+
+ Arg[1] : Int $source - source object's internal Id ("dbID")
+ Example : my @entries = $gene_scores->get_Entries_for_source(1234);
+ Description : Returns a list of all Entries in the scoring matrix for a given
+ source object.
+ Return type : Arrayref of Bio::EnsEMBL::IdMapping::Entry objects
+ Exceptions : none
+ Caller : general
+ Status : At Risk
+ : under development
+
+=cut
+
sub get_Entries_for_source {
my $self = shift;
my $source = shift;
@@ -191,6 +415,20 @@ sub get_Entries_for_source {
}
+=head2 get_sources_for_target
+
+ Arg[1] : Int $target - target object's internal Id ("dbID")
+ Example : my @sources = $gene_scores->get_sources_for_target(5678);
+ Description : Returns a list of all sources which have a score against a given
+ target object.
+ Return type : Arrayref of Int (source objects' internal Ids)
+ Exceptions : none
+ Caller : general
+ Status : At Risk
+ : under development
+
+=cut
+
sub get_sources_for_target {
my $self = shift;
my $target = shift;
@@ -199,6 +437,20 @@ sub get_sources_for_target {
}
+=head2 get_Entries_for_target
+
+ Arg[1] : Int $target - target object's internal Id ("dbID")
+ Example : my @entries = $gene_scores->get_Entries_for_target(5678);
+ Description : Returns a list of all Entries in the scoring matrix for a given
+ target object.
+ Return type : Arrayref of Bio::EnsEMBL::IdMapping::Entry objects
+ Exceptions : none
+ Caller : general
+ Status : At Risk
+ : under development
+
+=cut
+
sub get_Entries_for_target {
my $self = shift;
my $target = shift;
@@ -208,6 +460,20 @@ sub get_Entries_for_target {
}
+=head2 get_all_Entries
+
+ Example : foreach my $entry (@{ $gene_scores->get_all_Entries }) {
+ # do something with the entry
+ }
+ Description : Returns a list of all Entries in the scoring matrix.
+ Return type : Arrayref of Bio::EnsEMBL::IdMapping::Entry objects
+ Exceptions : none
+ Caller : general
+ Status : At Risk
+ : under development
+
+=cut
+
sub get_all_Entries {
my $self = shift;
@@ -224,41 +490,127 @@ sub get_all_Entries {
}
+=head2 get_all_sources
+
+ Example : my @sources = @{ $gene_scores->get_all_sources };
+ Description : Returns a list of all sources in the scoring matrix.
+ Return type : Arrayref of Int (source objects' internal Ids)
+ Exceptions : none
+ Caller : general
+ Status : At Risk
+ : under development
+
+=cut
+
sub get_all_sources {
my $self = shift;
return [keys %{ $self->{'cache'}->{'source_list'} }];
}
+=head2 get_all_targets
+
+ Example : my @targets = @{ $gene_scores->get_all_targets };
+ Description : Returns a list of all targets in the scoring matrix.
+ Return type : Arrayref of Int (target objects' internal Ids)
+ Exceptions : none
+ Caller : general
+ Status : At Risk
+ : under development
+
+=cut
+
sub get_all_targets {
my $self = shift;
return [keys %{ $self->{'cache'}->{'target_list'} }];
}
+=head2 get_entry_count
+
+ Example : my $num_entries = $gene_scores->get_entry_count;
+ Description : Returns the number of Entries in the scoring matrix.
+ Return type : Int
+ Exceptions : none
+ Caller : general
+ Status : At Risk
+ : under development
+
+=cut
+
sub get_entry_count {
my $self = shift;
return scalar(keys %{ $self->{'cache'}->{'matrix'} });
}
+=head2 size
+
+ Example : my $size = $gene_scores->size;
+ Description : Returns the size of the scoring matrix. Same value as returned
+ by get_entry_count().
+ Return type : Int
+ Exceptions : none
+ Caller : general
+ Status : At Risk
+ : under development
+
+=cut
+
sub size {
return $_[0]->get_entry_count;
}
+=head2 get_source_count
+
+ Example : my $num_sources = $gene_scores->get_source_count;
+ Description : Returns the number of distinct sources in the scoring matrix.
+ Return type : Int
+ Exceptions : none
+ Caller : general
+ Status : At Risk
+ : under development
+
+=cut
+
sub get_source_count {
my $self = shift;
return scalar(keys %{ $self->{'cache'}->{'source_list'} });
}
+=head2 get_target_count
+
+ Example : my $num_targets = $gene_scores->get_target_count;
+ Description : Returns the number of distinct targets in the scoring matrix.
+ Return type : Int
+ Exceptions : none
+ Caller : general
+ Status : At Risk
+ : under development
+
+=cut
+
sub get_target_count {
my $self = shift;
return scalar(keys %{ $self->{'cache'}->{'target_list'} });
}
+=head2 get_min_max_scores
+
+ Example : my ($min_score, $max_score) =
+ @{ $gene_scores->get_min_max_scores };
+ Description : Returns the mininum and maximum score in the scoring matrix.
+ Return type : Arrayref of Float [min_score, max_score]
+ Exceptions : none
+ Caller : general
+ Status : At Risk
+ : under development
+
+=cut
+
sub get_min_max_scores {
my $self = shift;
@@ -279,6 +631,18 @@ sub get_min_max_scores {
}
+=head2 get_average_score
+
+ Example : my $avg_score = $gene_scores->get_average_score;
+ Description : Returns the average (mean) score in the matrix.
+ Return type : Float
+ Exceptions : none
+ Caller : general
+ Status : At Risk
+ : under development
+
+=cut
+
sub get_average_score {
my $self = shift;
@@ -296,6 +660,22 @@ sub get_average_score {
}
+=head2 merge
+
+ Arg[1] : Bio::EnsEMBL::IdMapping::ScoredMappingMatrix $matrix - another
+ matrix to merge with
+ Example : my $update_count = $gene_scores->merge($more_gene_scores);
+ Description : Merges two scoring matrices. If there's an Entry for a
+ source/target pair in both matrices, the higher score will be
+ retained.
+ Return type : Int - number of Entries added or updated
+ Exceptions : thrown on wrong or missing argument
+ Caller : general
+ Status : At Risk
+ : under development
+
+=cut
+
sub merge {
my $self = shift;
my $matrix = shift;
@@ -345,6 +725,21 @@ sub merge {
}
+=head2 log
+
+ Arg[1] : String $type - object type (e.g. 'gene')
+ Arg[2] : String $dump_path - path for writing output
+ Example : $gene_scores->log('gene', $conf->param('basedir'));
+ Description : Logs all Entries in the scoring matrix to a file. Used for
+ debugging.
+ Return type : none
+ Exceptions : thrown on I/0 error
+ Caller : general
+ Status : At Risk
+ : under development
+
+=cut
+
sub log {
my $self = shift;
my $type = shift;
@@ -364,6 +759,21 @@ sub log {
}
+=head2 to_string
+
+ Example : print LOG $gene_scores->to_string, "\n";
+ Description : Returns a string representation of the scoring matrix. This is
+ simply a multi-line string, where each line is a stringified
+ Entry.
+ Useful for debugging and logging.
+ Return type : String
+ Exceptions : none
+ Caller : general
+ Status : At Risk
+ : under development
+
+=cut
+
sub to_string {
my $self = shift;
diff --git a/modules/Bio/EnsEMBL/IdMapping/Serialisable.pm b/modules/Bio/EnsEMBL/IdMapping/Serialisable.pm
index 221db38ffa35c3e3c205828ec758dba5beaa8c46..f0949db626864cc9dab47f57c03d8bb162400348 100644
--- a/modules/Bio/EnsEMBL/IdMapping/Serialisable.pm
+++ b/modules/Bio/EnsEMBL/IdMapping/Serialisable.pm
@@ -2,15 +2,49 @@ package Bio::EnsEMBL::IdMapping::Serialisable;
=head1 NAME
+Bio::EnsEMBL::IdMapping::Serialisable - base class for serialisable objects
=head1 SYNOPSIS
+# instantiate an object which extends Serialisable
+my $object = YourObject->new(
+ -DUMP_PATH => '/tmp',
+ -CACHE_FILE => 'object_cache.ser',
+);
+
+# serialise object to file
+my $filesize = $object->write_to_file;
+print LOG "Serialised object to file of size $filesize.\n";
+
+# later, create another object defining the same serialisation location.
+# specifying -LOAD_AUTO will automatically load it from the serialisation file.
+my $object1 = YourObject->new(
+ -DUMP_PATH => '/tmp',
+ -CACHE_FILE => 'object_cache.ser',
+ -LOAD_AUTO => 1,
+);
+
+# alternatively, manually load the object from file
+$object1->load_from_file;
=head1 DESCRIPTION
+This is the base class for serialisable objects used by the stable Id mapping.
+It's essentially an OO wrapper for Storable, providing a method to store
+(write_to_file(()) and one to retrieve (read_from_file()) serialised objects.
+
+This class is not instantiated itself, but rather extended by implementing
+classes.
=head1 METHODS
+new
+write_to_file
+read_from_file
+dump_path
+cache_file_name
+cache_file
+loaded
=head1 LICENCE
@@ -39,6 +73,21 @@ use Bio::EnsEMBL::Utils::ScriptUtils qw(parse_bytes);
use Storable qw(nstore retrieve);
+=head2 new
+
+ Arg [DUMP_PATH] : String - path for object serialisation
+ Arg [CACHE_FILE] : String - filename of serialised object
+ Arg [AUTO_LOAD] : Boolean - determines whether object should be automatically
+ loaded on instantiation
+ Description : Constructor.
+ Return type : Bio::EnsEMBL::IdMapping::Serialisable implementing object
+ Exceptions : thrown on missing argument
+ Caller : implementing subclass
+ Status : At Risk
+ : under development
+
+=cut
+
sub new {
my $caller = shift;
my $class = ref($caller) || $caller;
@@ -67,6 +116,19 @@ sub new {
}
+=head2 write_to_file
+
+ Example : my $filesize = $object->write_to_file;
+ Description : Serialises an object to a file (determined by
+ $self->cache_file).
+ Return type : String - size of serialisation file
+ Exceptions : thrown on I/O errors
+ Caller : general
+ Status : At Risk
+ : under development
+
+=cut
+
sub write_to_file {
my $self = shift;
@@ -90,6 +152,19 @@ sub write_to_file {
}
+=head2 read_from_file
+
+ Example : $object->read_from_file;
+ Description : Reads a serialised object from file (determined by
+ $self->cache_file).
+ Return type : Bio::EnsEMBL::IdMapping::Serialisable implementing object
+ Exceptions : thrown on I/O errors
+ Caller : general
+ Status : At Risk
+ : under development
+
+=cut
+
sub read_from_file {
my $self = shift;
@@ -108,9 +183,18 @@ sub read_from_file {
}
-#
-# getter/setters
-#
+=head2 dump_path
+
+ Arg[1] : String - dump path for serialisation
+ Example : $object->dump_path('/tmp');
+ Description : Getter/setter for the dump path for serialisation.
+ Return type : String
+ Exceptions : none
+ Caller : general
+ Status : At Risk
+ : under development
+
+=cut
sub dump_path {
my $self = shift;
@@ -119,6 +203,19 @@ sub dump_path {
}
+=head2 cache_file_name
+
+ Arg[1] : String - file name for serialisation
+ Example : $object->cache_file_name('object_cache.ser');
+ Description : Getter/setter for the file name for serialisation.
+ Return type : String
+ Exceptions : none
+ Caller : general
+ Status : At Risk
+ : under development
+
+=cut
+
sub cache_file_name {
my $self = shift;
$self->{'cache_file_name'} = shift if (@_);
@@ -126,12 +223,42 @@ sub cache_file_name {
}
+=head2 cache_file
+
+ Example : my $cache_file = $object->cache_file;
+ Description : Returns the path and name of the serialised object file.
+ Return type : String
+ Exceptions : none
+ Caller : general
+ Status : At Risk
+ : under development
+
+=cut
+
sub cache_file {
my $self = shift;
return $self->dump_path.'/'.$self->cache_file_name;
}
+=head2 loaded
+
+ Arg[1] : Boolean - "loaded" status
+ Example : if ($object->loaded) {
+ # do something with the object that was loaded from a file
+ } else {
+ # the object wasn't loaded but is new, so fill it
+ }
+ Description : Indicates whether a given object was loaded from its serialised
+ state on disk.
+ Return type : Boolean - TRUE if loaded from disk, FALSE otherwise
+ Exceptions : none
+ Caller : general
+ Status : At Risk
+ : under development
+
+=cut
+
sub loaded {
my $self = shift;
$self->{'loaded'} = shift if (@_);
diff --git a/modules/Bio/EnsEMBL/IdMapping/SyntenyFramework.pm b/modules/Bio/EnsEMBL/IdMapping/SyntenyFramework.pm
index 7ed7f90777168f82ce3dc04e1144819407f67db9..df58482f0940c9910f3157b49d1ffd4f4a4eb449 100644
--- a/modules/Bio/EnsEMBL/IdMapping/SyntenyFramework.pm
+++ b/modules/Bio/EnsEMBL/IdMapping/SyntenyFramework.pm
@@ -2,15 +2,48 @@ package Bio::EnsEMBL::IdMapping::SyntenyFramework;
=head1 NAME
+Bio::EnsEMBL::IdMapping::SyntenyFramework - framework representing syntenic
+regions across the genome
=head1 SYNOPSIS
+# build the SyntenyFramework from unambiguous gene mappings
+my $sf = Bio::EnsEMBL::IdMapping::SyntenyFramework->new(
+ -DUMP_PATH => $dump_path,
+ -CACHE_FILE => 'synteny_framework.ser',
+ -LOGGER => $self->logger,
+ -CONF => $self->conf,
+ -CACHE => $self->cache,
+);
+$sf->build_synteny($gene_mappings);
+
+# use it to rescore the genes
+$gene_scores = $sf->rescore_gene_matrix_lsf($gene_scores);
=head1 DESCRIPTION
+The SyntenyFramework is a set of SyntenyRegions. These are pairs of locations
+very analoguous to the information in the assembly table (the locations dont
+have to be the same length though). They are built from genes that map uniquely
+between source and target.
+
+Once built, the SyntenyFramework is used to score source and target gene pairs
+to determine whether they are similar. This process is slow (it involves testing
+all gene pairs against all SyntenyRegions), this module therefor has built-in
+support to run the process in parallel via LSF.
=head1 METHODS
+new
+build_synteny
+_by_overlap
+add_SyntenyRegion
+get_all_SyntenyRegions
+rescore_gene_matrix_lsf
+rescore_gene_matrix
+logger
+conf
+cache
=head1 REALTED MODULES
@@ -48,6 +81,30 @@ use Bio::EnsEMBL::IdMapping::ScoredMappingMatrix;
use FindBin qw($Bin);
FindBin->again;
+
+=head2 new
+
+ Arg [LOGGER]: Bio::EnsEMBL::Utils::Logger $logger - a logger object
+ Arg [CONF] : Bio::EnsEMBL::Utils::ConfParser $conf - a configuration object
+ Arg [CACHE] : Bio::EnsEMBL::IdMapping::Cache $cache - a cache object
+ Arg [DUMP_PATH] : String - path for object serialisation
+ Arg [CACHE_FILE] : String - filename of serialised object
+ Example : my $sf = Bio::EnsEMBL::IdMapping::SyntenyFramework->new(
+ -DUMP_PATH => $dump_path,
+ -CACHE_FILE => 'synteny_framework.ser',
+ -LOGGER => $self->logger,
+ -CONF => $self->conf,
+ -CACHE => $self->cache,
+ );
+ Description : Constructor.
+ Return type : Bio::EnsEMBL::IdMapping::SyntenyFramework
+ Exceptions : thrown on wrong or missing arguments
+ Caller : InternalIdMapper plugins
+ Status : At Risk
+ : under development
+
+=cut
+
sub new {
my $caller = shift;
my $class = ref($caller) || $caller;
@@ -80,6 +137,23 @@ sub new {
}
+=head2 build_synteny
+
+ Arg[1] : Bio::EnsEMBL::IdMapping::MappingList $mappings - gene mappings
+ to build the SyntenyFramework from
+ Example : $synteny_framework->build_synteny($gene_mappings);
+ Description : Builds the SyntenyFramework from unambiguous gene mappings.
+ SyntenyRegions are allowed to overlap. At most two overlapping
+ SyntenyRegions are merged (otherwise we'd get too large
+ SyntenyRegions with little information content).
+ Return type : none
+ Exceptions : thrown on wrong or missing argument
+ Caller : InternalIdMapper plugins
+ Status : At Risk
+ : under development
+
+=cut
+
sub build_synteny {
my $self = shift;
my $mappings = shift;
@@ -169,6 +243,9 @@ sub build_synteny {
}
+#
+# sort SyntenyRegions by overlap
+#
sub _by_overlap {
# first sort by seq_region
my $retval = ($b->source_seq_region_name cmp $a->source_seq_region_name);
@@ -182,16 +259,65 @@ sub _by_overlap {
}
+=head2 add_SyntenyRegion
+
+ Arg[1] : Bio::EnsEMBL::IdMaping::SyntenyRegion - SyntenyRegion to add
+ Example : $synteny_framework->add_SyntenyRegion($synteny_region);
+ Description : Adds a SyntenyRegion to the framework. For speed reasons (and
+ since this is an internal method), no argument check is done.
+ Return type : none
+ Exceptions : none
+ Caller : internal
+ Status : At Risk
+ : under development
+
+=cut
+
sub add_SyntenyRegion {
push @{ $_[0]->{'cache'} }, $_[1];
}
+=head2 get_all_SyntenyRegions
+
+ Example : foreach my $sr (@{ $sf->get_all_SyntenyRegions }) {
+ # do something with the SyntenyRegion
+ }
+ Description : Get a list of all SyntenyRegions in the framework.
+ Return type : Arrayref of Bio::EnsEMBL::IdMapping::SyntenyRegion
+ Exceptions : none
+ Caller : general
+ Status : At Risk
+ : under development
+
+=cut
+
sub get_all_SyntenyRegions {
return $_[0]->{'cache'};
}
+=head2 rescore_gene_matrix_lsf
+
+ Arg[1] : Bio::EnsEMBL::IdMapping::ScoredmappingMatrix $matrix - gene
+ scores to rescore
+ Example : my $new_scores = $sf->rescore_gene_matrix_lsf($gene_scores);
+ Description : This method runs rescore_gene_matrix() (via the
+ synteny_resocre.pl script) in parallel with lsf, then combines
+ the results to return a single rescored scoring matrix.
+ Parallelisation is done by chunking the scoring matrix into
+ several pieces (determined by the --synteny_rescore_jobs
+ configuration option).
+ Return type : Bio::EnsEMBL::IdMapping::ScoredMappingMatrix
+ Exceptions : thrown on wrong or missing argument
+ thrown on filesystem I/O error
+ thrown on failure of one or mor lsf jobs
+ Caller : InternalIdMapper plugins
+ Status : At Risk
+ : under development
+
+=cut
+
sub rescore_gene_matrix_lsf {
my $self = shift;
my $matrix = shift;
@@ -314,8 +440,22 @@ sub rescore_gene_matrix_lsf {
#
-# retain 70% of old score and build other 30% from synteny match
#
+=head2 rescore_gene_matrix
+
+ Arg[1] : Bio::EnsEMBL::IdMapping::ScoredmappingMatrix $matrix - gene
+ scores to rescore
+ Example : my $new_scores = $sf->rescore_gene_matrix($gene_scores);
+ Description : Rescores a gene matrix. Retains 70% of old score and builds
+ other 30% from the synteny match.
+ Return type : Bio::EnsEMBL::IdMapping::ScoredMappingMatrix
+ Exceptions : thrown on wrong or missing argument
+ Caller : InternalIdMapper plugins
+ Status : At Risk
+ : under development
+
+=cut
+
sub rescore_gene_matrix {
my $self = shift;
my $matrix = shift;
diff --git a/modules/Bio/EnsEMBL/IdMapping/SyntenyRegion.pm b/modules/Bio/EnsEMBL/IdMapping/SyntenyRegion.pm
index 6adb55329267a577dd460d476b0a9230f0d1491b..59cccf4775f2e92364e4a8f6ed28c36f63391718 100644
--- a/modules/Bio/EnsEMBL/IdMapping/SyntenyRegion.pm
+++ b/modules/Bio/EnsEMBL/IdMapping/SyntenyRegion.pm
@@ -2,15 +2,51 @@ package Bio::EnsEMBL::IdMapping::SyntenyRegion;
=head1 NAME
+Bio::EnsEMBL::IdMapping::SyntenyRegion - object representing syntenic regions
=head1 SYNOPSIS
+# create a new SyntenyRegion from a source and a target gene
+my $sr = Bio::EnsEMBL::IdMapping::SyntenyRegion->new_fast([
+ $source_gene->start,
+ $source_gene->end,
+ $source_gene->strand,
+ $source_gene->seq_region_name,
+ $target_gene->start,
+ $target_gene->end,
+ $target_gene->strand,
+ $target_gene->seq_region_name,
+ $entry->score,
+]);
+
+# merge with another SyntenyRegion
+my $merged_sr = $sr->merge($sr1);
+
+# score a gene pair against this SyntenyRegion
+my $score = $sr->score_location_relationship($source_gene1, $target_gene1);
=head1 DESCRIPTION
+This object represents a synteny between a source and a target location.
+SyntenyRegions are built from mapped genes, and the their score is defined as
+the score of the gene mapping. For merged SyntenyRegions, scores are combined.
=head1 METHODS
+new_fast
+source_start
+source_end
+source_strand
+source_seq_region_name
+target_start
+target_end
+target_strand
+target_seq_region_name
+score
+merge
+stretch
+score_location_relationship
+to_string
=head1 LICENCE
@@ -36,6 +72,22 @@ no warnings 'uninitialized';
use Bio::EnsEMBL::Utils::Exception qw(throw warning);
+=head2 new_fast
+
+ Arg[1] : Arrayref $array_ref - the arrayref to bless into the
+ SyntenyRegion object
+ Example : my $sr = Bio::EnsEMBL::IdMapping::SyntenyRegion->new_fast([
+ ]);
+ Description : Constructor. On instantiation, source and target regions are
+ reverse complemented so that source is always on forward strand.
+ Return type : a Bio::EnsEMBL::IdMapping::SyntenyRegion object
+ Exceptions : none
+ Caller : Bio::EnsEMBL::IdMapping::SyntenyFramework
+ Status : At Risk
+ : under development
+
+=cut
+
sub new_fast {
my $class = shift;
my $array_ref = shift;
@@ -52,6 +104,18 @@ sub new_fast {
}
+=head2 source_start
+
+ Arg[1] : (optional) Int - source location start coordinate
+ Description : Getter/setter for source location start coordinate.
+ Return type : Int
+ Exceptions : none
+ Caller : Bio::EnsEMBL::IdMapping::SyntenyFramework
+ Status : At Risk
+ : under development
+
+=cut
+
sub source_start {
my $self = shift;
$self->[0] = shift if (@_);
@@ -59,6 +123,18 @@ sub source_start {
}
+=head2 source_end
+
+ Arg[1] : (optional) Int - source location end coordinate
+ Description : Getter/setter for source location end coordinate.
+ Return type : Int
+ Exceptions : none
+ Caller : Bio::EnsEMBL::IdMapping::SyntenyFramework
+ Status : At Risk
+ : under development
+
+=cut
+
sub source_end {
my $self = shift;
$self->[1] = shift if (@_);
@@ -66,6 +142,18 @@ sub source_end {
}
+=head2 source_strand
+
+ Arg[1] : (optional) Int - source location strand
+ Description : Getter/setter for source location strand.
+ Return type : Int
+ Exceptions : none
+ Caller : Bio::EnsEMBL::IdMapping::SyntenyFramework
+ Status : At Risk
+ : under development
+
+=cut
+
sub source_strand {
my $self = shift;
$self->[2] = shift if (@_);
@@ -73,6 +161,18 @@ sub source_strand {
}
+=head2 source_seq_region_name
+
+ Arg[1] : (optional) String - source location seq_region name
+ Description : Getter/setter for source location seq_region name.
+ Return type : String
+ Exceptions : none
+ Caller : Bio::EnsEMBL::IdMapping::SyntenyFramework
+ Status : At Risk
+ : under development
+
+=cut
+
sub source_seq_region_name {
my $self = shift;
$self->[3] = shift if (@_);
@@ -80,6 +180,18 @@ sub source_seq_region_name {
}
+=head2 target_start
+
+ Arg[1] : (optional) Int - target location start coordinate
+ Description : Getter/setter for target location start coordinate.
+ Return type : Int
+ Exceptions : none
+ Caller : Bio::EnsEMBL::IdMapping::SyntenyFramework
+ Status : At Risk
+ : under development
+
+=cut
+
sub target_start {
my $self = shift;
$self->[4] = shift if (@_);
@@ -87,6 +199,18 @@ sub target_start {
}
+=head2 target_end
+
+ Arg[1] : (optional) Int - target location end coordinate
+ Description : Getter/setter for target location end coordinate.
+ Return type : Int
+ Exceptions : none
+ Caller : Bio::EnsEMBL::IdMapping::SyntenyFramework
+ Status : At Risk
+ : under development
+
+=cut
+
sub target_end {
my $self = shift;
$self->[5] = shift if (@_);
@@ -94,6 +218,18 @@ sub target_end {
}
+=head2 target_strand
+
+ Arg[1] : (optional) Int - target location strand
+ Description : Getter/setter for target location strand.
+ Return type : Int
+ Exceptions : none
+ Caller : Bio::EnsEMBL::IdMapping::SyntenyFramework
+ Status : At Risk
+ : under development
+
+=cut
+
sub target_strand {
my $self = shift;
$self->[6] = shift if (@_);
@@ -101,6 +237,18 @@ sub target_strand {
}
+=head2 target_seq_region_name
+
+ Arg[1] : (optional) String - target location seq_region name
+ Description : Getter/setter for target location seq_region name.
+ Return type : String
+ Exceptions : none
+ Caller : Bio::EnsEMBL::IdMapping::SyntenyFramework
+ Status : At Risk
+ : under development
+
+=cut
+
sub target_seq_region_name {
my $self = shift;
$self->[7] = shift if (@_);
@@ -108,6 +256,18 @@ sub target_seq_region_name {
}
+=head2 score
+
+ Arg[1] : (optional) Float - score
+ Description : Getter/setter for the score between source and target location.
+ Return type : Int
+ Exceptions : none
+ Caller : Bio::EnsEMBL::IdMapping::SyntenyFramework
+ Status : At Risk
+ : under development
+
+=cut
+
sub score {
my $self = shift;
$self->[8] = shift if (@_);
@@ -115,6 +275,23 @@ sub score {
}
+=head2 merge
+
+ Arg[1] : Bio::EnsEMBL::IdMapping::SyntenyRegion $sr - another
+ SyntenyRegion
+ Example : $merged_sr = $sr->merge($other_sr);
+ Description : Merges two overlapping SyntenyRegions if they meet certain
+ criteria (see documentation in the code for details). Score is
+ calculated as a combined distance score. If the two
+ SyntenyRegions aren't mergeable, this method returns undef.
+ Return type : Bio::EnsEMBL::IdMapping::SyntenyRegion or undef
+ Exceptions : warns on bad scores
+ Caller : Bio::EnsEMBL::IdMapping::SyntenyFramework
+ Status : At Risk
+ : under development
+
+=cut
+
sub merge {
my ($self, $sr) = @_;
@@ -181,9 +358,20 @@ sub merge {
return $self;
}
-#
-# extend this SyntenyRegion to span a $factor * $score more area
-#
+
+=head2 stretch
+
+ Arg[1] : Float $factor - stretching factor
+ Example : $stretched_sr = $sr->stretch(2);
+ Description : Extends this SyntenyRegion to span a $factor * $score more area.
+ Return type : Bio::EnsEMBL::IdMapping::SyntenyRegion
+ Exceptions : none
+ Caller : Bio::EnsEMBL::IdMapping::SyntenyFramework
+ Status : At Risk
+ : under development
+
+=cut
+
sub stretch {
my ($self, $factor) = @_;
@@ -203,6 +391,41 @@ sub stretch {
}
+=head2 score_location_relationship
+
+ Arg[1] : Bio::EnsEMBL::IdMapping::TinyGene $source_gene - source gene
+ Arg[2] : Bio::EnsEMBL::IdMapping::TinyGene $target_gene - target gene
+ Example : my $score = $sr->score_location_relationship($source_gene,
+ $target_gene);
+ Description : This function calculates how well the given source location
+ interpolates on given target location inside this SyntenyRegion.
+
+ Scoring is done the following way: Source and target location
+ are normalized with respect to this Regions source and target.
+ Source range will then be somewhere close to 0.0-1.0 and target
+ range anything around that.
+
+ The extend of the covered area between source and target range
+ is a measurement of how well they agree (smaller extend is
+ better). The extend (actually 2*extend) is reduced by the size
+ of the regions. This will result in 0.0 if they overlap
+ perfectly and bigger values if they dont.
+
+ This is substracted from 1.0 to give the score. The score is
+ likely to be below zero, but is cut off at 0.0f.
+
+ Finally, the score is multiplied with the score of the synteny
+ itself.
+ Return type : Float
+ Exceptions : warns if score out of range
+ Caller : Bio::EnsEMBL::IdMapping::SyntenyFramework
+ Status : At Risk
+ : under development
+
+=cut
+
+
+
sub score_location_relationship {
my ($self, $source_gene, $target_gene) = @_;
@@ -269,6 +492,19 @@ sub score_location_relationship {
}
+=head2 to_string
+
+ Example : print LOG $sr->to_string, "\n";
+ Description : Returns a string representation of the SyntenyRegion object.
+ Useful for debugging and logging.
+ Return type : String
+ Exceptions : none
+ Caller : Bio::EnsEMBL::IdMapping::SyntenyFramework
+ Status : At Risk
+ : under development
+
+=cut
+
sub to_string {
my $self = shift;
return sprintf("%s:%s-%s:%s %s:%s-%s:%s %.6f",
diff --git a/modules/Bio/EnsEMBL/IdMapping/TinyExon.pm b/modules/Bio/EnsEMBL/IdMapping/TinyExon.pm
index 443867f97e5529022eecb9c9cecdb4d6e54c80bc..7fc69887267965e0b0aed3981eb84525e26927e4 100644
--- a/modules/Bio/EnsEMBL/IdMapping/TinyExon.pm
+++ b/modules/Bio/EnsEMBL/IdMapping/TinyExon.pm
@@ -2,15 +2,51 @@ package Bio::EnsEMBL::IdMapping::TinyExon;
=head1 NAME
+Bio::EnsEMBL::IdMapping::TinyExon - lightweight exon object
=head1 SYNOPSIS
+# fetch an exon from the db and create a lightweight exon object from it
+my $exon = $exon_adaptor->fetch_by_stable_id('ENSE000345437');
+my $lightweight_exon = Bio::EnsEMBL::IdMapping::TinyExon->new_fast([
+ $exon->dbID,
+ $exon->stable_id,
+ $exon->version,
+ $exon->created_date,
+ $exon->modified_date,
+ $exon->start,
+ $exon->end,
+ $exon->strand,
+ $exon->slice->seq_region_name,
+ $exon->slice->coord_system_name,
+ $exon->slice->coord_system->version,
+ $exon->slice->subseq($exon->start, $exon->end, $exon->strand),
+ $exon->phase,
+ $need_project,
+]);
=head1 DESCRIPTION
+This is a lightweight exon object for the stable Id mapping. See the
+documentation in TinyFeature for general considerations about its design.
=head1 METHODS
+start
+end
+strand
+seq_region_name
+coord_system_name
+coord_system_version
+seq
+phase
+need_project
+common_start
+common_end
+common_strand
+common_sr_name
+length
+is_known
=head1 LICENCE
@@ -31,21 +67,20 @@ Please post comments/questions to the Ensembl development list
# internal data structure (array indices):
#
-# 0 dbID
-# 1 stable_id
-# 2 start
-# 3 end
-# 4 strand
-# 5 seq_region_name
-# 6 coord_system_name
-# 7 coord_system_version
-# 8 seq
-# 9 phase
-# 10 need_project
-# 11 common_start
-# 12 common_end
-# 13 common_strand
-# 14 common_sr_name
+# 0-4 see TinyFeature
+# 5 start
+# 6 end
+# 7 strand
+# 8 seq_region_name
+# 9 coord_system_name
+# 10 coord_system_version
+# 11 seq
+# 12 phase
+# 13 need_project
+# 14 common_start
+# 15 common_end
+# 16 common_strand
+# 17 common_sr_name
use strict;
@@ -58,6 +93,18 @@ our @ISA = qw(Bio::EnsEMBL::IdMapping::TinyFeature);
use Bio::EnsEMBL::Utils::Exception qw(throw warning);
+=head2 start
+
+ Arg[1] : (optional) Int - the exon's start coordinate
+ Description : Getter/setter for the exon's start coordinate.
+ Return type : Int
+ Exceptions : none
+ Caller : general
+ Status : At Risk
+ : under development
+
+=cut
+
sub start {
my $self = shift;
$self->[5] = shift if (@_);
@@ -65,6 +112,18 @@ sub start {
}
+=head2 end
+
+ Arg[1] : (optional) Int - the exon's end coordinate
+ Description : Getter/setter for the exon's end coordinate.
+ Return type : Int
+ Exceptions : none
+ Caller : general
+ Status : At Risk
+ : under development
+
+=cut
+
sub end {
my $self = shift;
$self->[6] = shift if (@_);
@@ -72,6 +131,18 @@ sub end {
}
+=head2 strand
+
+ Arg[1] : (optional) Int - the exon's strand
+ Description : Getter/setter for the exon's strand.
+ Return type : Int
+ Exceptions : none
+ Caller : general
+ Status : At Risk
+ : under development
+
+=cut
+
sub strand {
my $self = shift;
$self->[7] = shift if (@_);
@@ -79,6 +150,19 @@ sub strand {
}
+=head2 seq_region_name
+
+ Arg[1] : (optional) String - seq_region name
+ Description : Getter/setter for the seq_region name of the slice the exon is
+ on.
+ Return type : String
+ Exceptions : none
+ Caller : general
+ Status : At Risk
+ : under development
+
+=cut
+
sub seq_region_name {
my $self = shift;
$self->[8] = shift if (@_);
@@ -86,6 +170,19 @@ sub seq_region_name {
}
+=head2 coord_system_name
+
+ Arg[1] : (optional) String - coord_system name
+ Description : Getter/setter for the coord_system name of the slice the exon is
+ on.
+ Return type : String
+ Exceptions : none
+ Caller : general
+ Status : At Risk
+ : under development
+
+=cut
+
sub coord_system_name {
my $self = shift;
$self->[9] = shift if (@_);
@@ -93,6 +190,19 @@ sub coord_system_name {
}
+=head2 coord_system_version
+
+ Arg[1] : (optional) String - coord_system version
+ Description : Getter/setter for the coord_system version of the slice the
+ exon is on.
+ Return type : String
+ Exceptions : none
+ Caller : general
+ Status : At Risk
+ : under development
+
+=cut
+
sub coord_system_version {
my $self = shift;
$self->[10] = shift if (@_);
@@ -100,6 +210,18 @@ sub coord_system_version {
}
+=head2 seq
+
+ Arg[1] : (optional) String - the exon's sequence
+ Description : Getter/setter for the exon's sequence.
+ Return type : String
+ Exceptions : none
+ Caller : general
+ Status : At Risk
+ : under development
+
+=cut
+
sub seq {
my $self = shift;
$self->[11] = shift if (@_);
@@ -107,6 +229,18 @@ sub seq {
}
+=head2 phase
+
+ Arg[1] : (optional) Int - the exon's phase
+ Description : Getter/setter for the exon's phase.
+ Return type : Int
+ Exceptions : none
+ Caller : general
+ Status : At Risk
+ : under development
+
+=cut
+
sub phase {
my $self = shift;
$self->[12] = shift if (@_);
@@ -114,6 +248,22 @@ sub phase {
}
+=head2 need_project
+
+ Arg[1] : (optional) Boolean - attribute to set
+ Description : Getter/setter for the attribute determining whether an exon
+ needs to be projected onto a common coord_system. You don't need
+ to do so if the native coord_system is common to the source and
+ target assemblies, or if no common coord_system is found (the
+ Cache object has methods to determine this).
+ Return type : Boolean
+ Exceptions : none
+ Caller : general
+ Status : At Risk
+ : under development
+
+=cut
+
sub need_project {
my $self = shift;
$self->[13] = shift if (@_);
@@ -121,6 +271,21 @@ sub need_project {
}
+=head2 common_start
+
+ Arg[1] : (optional) Int - the exon's start in common coord_system
+ coordinates
+ Description : Getter/setter for the exon's start in common coord_system
+ coordinates. Will return $self->start if no projection to a
+ common coord_system is required.
+ Return type : Int
+ Exceptions : none
+ Caller : general
+ Status : At Risk
+ : under development
+
+=cut
+
sub common_start {
my $self = shift;
@@ -143,6 +308,21 @@ sub common_start {
}
+=head2 common_end
+
+ Arg[1] : (optional) Int - the exon's end in common coord_system
+ coordinates
+ Description : Getter/setter for the exon's end in common coord_system
+ coordinates. Will return $self->end if no projection to a
+ common coord_system is required.
+ Return type : Int
+ Exceptions : none
+ Caller : general
+ Status : At Risk
+ : under development
+
+=cut
+
sub common_end {
my $self = shift;
@@ -165,6 +345,21 @@ sub common_end {
}
+=head2 common_strand
+
+ Arg[1] : (optional) Int - the exon's strand in common coord_system
+ coordinates
+ Description : Getter/setter for the exon's strand in common coord_system
+ coordinates. Will return $self->strand if no projection to a
+ common coord_system is required.
+ Return type : Int
+ Exceptions : none
+ Caller : general
+ Status : At Risk
+ : under development
+
+=cut
+
sub common_strand {
my $self = shift;
@@ -187,6 +382,22 @@ sub common_strand {
}
+=head2 common_sr_name
+
+ Arg[1] : (optional) String - seq_region name of the exon's slice on the
+ common coord_system
+ Description : Getter/setter for the seq_region name of the exon's slice on the
+ common coord_system coordinates. Will return
+ $self->seq_region_name if no projection to a common coord_system
+ is required.
+ Return type : String
+ Exceptions : none
+ Caller : general
+ Status : At Risk
+ : under development
+
+=cut
+
sub common_sr_name {
my $self = shift;
@@ -209,12 +420,35 @@ sub common_sr_name {
}
+=head2 length
+
+ Description : Returns the exon length (distance between start and end).
+ Return type : Int
+ Exceptions : none
+ Caller : general
+ Status : At Risk
+ : under development
+
+=cut
+
sub length {
my $self = shift;
return ($self->end - $self->start + 1);
}
+=head2 is_known
+
+ Description : Determine whether an exon is known. In the context of stable Id
+ mapping, this is true for all exons.
+ Return type : Boolean
+ Exceptions : none
+ Caller : general
+ Status : At Risk
+ : under development
+
+=cut
+
sub is_known {
return 1;
}
diff --git a/modules/Bio/EnsEMBL/IdMapping/TinyFeature.pm b/modules/Bio/EnsEMBL/IdMapping/TinyFeature.pm
index 8b083f43591e873dae8a8f19635fed1631fe8a2a..9811cf6656ec3f7dea79f0aefc0337cb39ce61b3 100644
--- a/modules/Bio/EnsEMBL/IdMapping/TinyFeature.pm
+++ b/modules/Bio/EnsEMBL/IdMapping/TinyFeature.pm
@@ -2,15 +2,37 @@ package Bio::EnsEMBL::IdMapping::TinyFeature;
=head1 NAME
+Bio::EnsEMBL::IdMapping::TinyFeature - lightweight feature object
=head1 SYNOPSIS
+This object isn't instantiated. See objects which inherit from it (TinyGene,
+TinyTranscript, etc.) for examples.
=head1 DESCRIPTION
+This is the base class for the lightweight feature objects used by the stable Id
+maping application. For performance reasons, these objects are instantiated
+using a new_fast() method. The internal implementation is an arrayref (rather
+than the more common hashref), which optimises memory usage.
+
+There are no adaptors to fetch TinyFeatures from the database. You rather use
+the normal feature adaptors and then create the TinyFeatures from the heavy
+objects you get. The memory saving will therefore mainly take effect when
+serialising and reloading these objects.
+
+Also note that TinyFeatures don't have a slice attached to them - all location
+information (where required) is stored on the feature object directly.
=head1 METHODS
+new_fast
+id
+stable_id
+version
+created_date
+modified_date
+to_string
=head1 LICENCE
@@ -33,6 +55,9 @@ Please post comments/questions to the Ensembl development list
#
# 0 dbID
# 1 stable_id
+# 2 version
+# 3 created_date
+# 4 modified_date
#
# other instance variables differ by subclass implementation, so look there.
@@ -44,6 +69,18 @@ no warnings 'uninitialized';
use Bio::EnsEMBL::Utils::Exception qw(throw warning);
+=head2 new_fast
+
+ Arg[1] : Arrayref $array_ref - the arrayref to bless into the new object
+ Description : Constructor.
+ Return type : Bio::EnsEMBL::IdMapping::TinyFeature implementing class
+ Exceptions : none
+ Caller : Bio::EnsEMBL::IdMapping::Cache
+ Status : At Risk
+ : under development
+
+=cut
+
sub new_fast {
my $class = shift;
my $array_ref = shift;
@@ -51,6 +88,18 @@ sub new_fast {
}
+=head2 id
+
+ Arg[1] : (optional) Int - the feature's internal Id ("dbID")
+ Description : Getter/setter for the feature's internal Id.
+ Return type : Int
+ Exceptions : none
+ Caller : Bio::EnsEMBL::IdMapping::Cache
+ Status : At Risk
+ : under development
+
+=cut
+
sub id {
my $self = shift;
$self->[0] = shift if (@_);
@@ -58,6 +107,18 @@ sub id {
}
+=head2 stable_id
+
+ Arg[1] : (optional) String - the feature's stable Id
+ Description : Getter/setter for the feature's stable Id.
+ Return type : String
+ Exceptions : none
+ Caller : Bio::EnsEMBL::IdMapping::Cache
+ Status : At Risk
+ : under development
+
+=cut
+
sub stable_id {
my $self = shift;
$self->[1] = shift if (@_);
@@ -65,6 +126,18 @@ sub stable_id {
}
+=head2 version
+
+ Arg[1] : (optional) Int - the feature's stable Id version
+ Description : Getter/setter for the feature's stable Id version.
+ Return type : Int
+ Exceptions : none
+ Caller : Bio::EnsEMBL::IdMapping::Cache
+ Status : At Risk
+ : under development
+
+=cut
+
sub version {
my $self = shift;
$self->[2] = shift if (@_);
@@ -72,6 +145,18 @@ sub version {
}
+=head2 created_date
+
+ Arg[1] : (optional) String - the feature's stable Id creation date
+ Description : Getter/setter for the feature's stable Id creation date.
+ Return type : String
+ Exceptions : none
+ Caller : Bio::EnsEMBL::IdMapping::Cache
+ Status : At Risk
+ : under development
+
+=cut
+
sub created_date {
my $self = shift;
$self->[3] = shift if (@_);
@@ -79,6 +164,18 @@ sub created_date {
}
+=head2 modified_date
+
+ Arg[1] : (optional) String - the feature's stable Id modification date
+ Description : Getter/setter for the feature's stable Id modification date.
+ Return type : String
+ Exceptions : none
+ Caller : Bio::EnsEMBL::IdMapping::Cache
+ Status : At Risk
+ : under development
+
+=cut
+
sub modified_date {
my $self = shift;
$self->[4] = shift if (@_);
@@ -86,6 +183,19 @@ sub modified_date {
}
+=head2 to_string
+
+ Example : print LOG "Created ", $f->to_string, "\n";
+ Description : Prints a string representation of the feature for debug
+ purposes.
+ Return type : String
+ Exceptions : none
+ Caller : general
+ Status : At Risk
+ : under development
+
+=cut
+
sub to_string {
my $self = shift;
return $self->id.':'.$self->stable_id.'.'.$self->version;
diff --git a/modules/Bio/EnsEMBL/IdMapping/TinyGene.pm b/modules/Bio/EnsEMBL/IdMapping/TinyGene.pm
index 8a91fea1a140011a770b6a5142660982d9e8e336..5e69ffa15925bd30c0d600ca674b69967fd94734 100644
--- a/modules/Bio/EnsEMBL/IdMapping/TinyGene.pm
+++ b/modules/Bio/EnsEMBL/IdMapping/TinyGene.pm
@@ -2,15 +2,46 @@ package Bio::EnsEMBL::IdMapping::TinyGene;
=head1 NAME
+Bio::EnsEMBL::IdMapping::TinyGene - lightweight gene object
=head1 SYNOPSIS
+# fetch a gene from the db and create a lightweight gene object from it
+my $gene = $gene_adaptor->fetch_by_stable_id('ENSG000345437');
+my $lightweight_gene = Bio::EnsEMBL::IdMapping::TinyGene->new_fast([
+ $gene->dbID,
+ $gene->stable_id,
+ $gene->version,
+ $gene->created_date,
+ $gene->modified_date,
+ $gene->start,
+ $gene->end,
+ $gene->strand,
+ $gene->slice->seq_region_name,
+ $gene->biotype,
+ $gene->status,
+ $gene->analysis->logic_name,
+ ($gene->is_known ? 1 : 0),
+]);
=head1 DESCRIPTION
+This is a lightweight gene object for the stable Id mapping. See the
+documentation in TinyFeature for general considerations about its design.
=head1 METHODS
+start
+end
+strand
+seq_region_name
+biotype
+status
+logic_name
+is_known
+add_Transcript
+get_all_Transcripts
+length
=head1 LICENCE
@@ -29,6 +60,20 @@ Please post comments/questions to the Ensembl development list
=cut
+# internal data structure (array indices):
+#
+# 0-4 see TinyFeature
+# 5 start
+# 6 end
+# 7 strand
+# 8 seq_region_name
+# 9 biotype
+# 10 status
+# 11 logic_name
+# 12 is_known
+# 13 [transcripts]
+
+
use strict;
use warnings;
no warnings 'uninitialized';
@@ -39,6 +84,18 @@ our @ISA = qw(Bio::EnsEMBL::IdMapping::TinyFeature);
use Bio::EnsEMBL::Utils::Exception qw(throw warning);
+=head2 start
+
+ Arg[1] : (optional) Int - the gene's start coordinate
+ Description : Getter/setter for the gene's start coordinate.
+ Return type : Int
+ Exceptions : none
+ Caller : general
+ Status : At Risk
+ : under development
+
+=cut
+
sub start {
my $self = shift;
$self->[5] = shift if (@_);
@@ -46,6 +103,18 @@ sub start {
}
+=head2 end
+
+ Arg[1] : (optional) Int - the gene's end coordinate
+ Description : Getter/setter for the gene's end coordinate.
+ Return type : Int
+ Exceptions : none
+ Caller : general
+ Status : At Risk
+ : under development
+
+=cut
+
sub end {
my $self = shift;
$self->[6] = shift if (@_);
@@ -53,6 +122,18 @@ sub end {
}
+=head2 strand
+
+ Arg[1] : (optional) Int - the gene's strand
+ Description : Getter/setter for the gene's strand.
+ Return type : Int
+ Exceptions : none
+ Caller : general
+ Status : At Risk
+ : under development
+
+=cut
+
sub strand {
my $self = shift;
$self->[7] = shift if (@_);
@@ -60,6 +141,19 @@ sub strand {
}
+=head2 seq_region_name
+
+ Arg[1] : (optional) String - seq_region name
+ Description : Getter/setter for the seq_region name of the slice the gene is
+ on.
+ Return type : String
+ Exceptions : none
+ Caller : general
+ Status : At Risk
+ : under development
+
+=cut
+
sub seq_region_name {
my $self = shift;
$self->[8] = shift if (@_);
@@ -67,6 +161,18 @@ sub seq_region_name {
}
+=head2 biotype
+
+ Arg[1] : (optional) String - the gene's biotype
+ Description : Getter/setter for the gene's biotype.
+ Return type : String
+ Exceptions : none
+ Caller : general
+ Status : At Risk
+ : under development
+
+=cut
+
sub biotype {
my $self = shift;
$self->[9] = shift if (@_);
@@ -74,6 +180,18 @@ sub biotype {
}
+=head2 strand
+
+ Arg[1] : (optional) String - the gene's status
+ Description : Getter/setter for the gene's status.
+ Return type : String
+ Exceptions : none
+ Caller : general
+ Status : At Risk
+ : under development
+
+=cut
+
sub status {
my $self = shift;
$self->[10] = shift if (@_);
@@ -81,6 +199,18 @@ sub status {
}
+=head2 logic_name
+
+ Arg[1] : (optional) String - the gene's analysis' logic_name
+ Description : Getter/setter for the gene's analysis' logic_name.
+ Return type : String
+ Exceptions : none
+ Caller : general
+ Status : At Risk
+ : under development
+
+=cut
+
sub logic_name {
my $self = shift;
$self->[11] = shift if (@_);
@@ -88,6 +218,18 @@ sub logic_name {
}
+=head2 is_known
+
+ Arg[1] : (optional) Boolean - the gene's "known" status
+ Description : Getter/setter for the gene's "known" status.
+ Return type : Boolean
+ Exceptions : none
+ Caller : general
+ Status : At Risk
+ : under development
+
+=cut
+
sub is_known {
my $self = shift;
$self->[12] = shift if (@_);
@@ -95,6 +237,20 @@ sub is_known {
}
+=head2 add_Transcript
+
+ Arg[1] : Bio::EnsEMBL::IdMapping::TinyTranscript $tr - the transcript to
+ add
+ Example : $tiny_gene->add_Transcript($tiny_transcript);
+ Description : Adds a transcript to a gene.
+ Return type : none
+ Exceptions : thrown on wrong or missing argument
+ Caller : general
+ Status : At Risk
+ : under development
+
+=cut
+
sub add_Transcript {
my $self = shift;
my $tr = shift;
@@ -107,11 +263,36 @@ sub add_Transcript {
}
+=head2 get_all_Transcripts
+
+ Example : foreach my $tr (@{ $tiny_gene->get_all_Transcripts }) {
+ # do something with transcript
+ }
+ Description : Returns all transcripts attached to that gene.
+ Return type : Arrayref of Bio::EnsEMBL::IdMapping::TinyTranscript objects
+ Exceptions : none
+ Caller : general
+ Status : At Risk
+ : under development
+
+=cut
+
sub get_all_Transcripts {
return $_[0]->[13] || [];
}
+=head2 length
+
+ Description : Returns the gene length (distance between start and end).
+ Return type : Int
+ Exceptions : none
+ Caller : general
+ Status : At Risk
+ : under development
+
+=cut
+
sub length {
my $self = shift;
return ($self->end - $self->start + 1);
diff --git a/modules/Bio/EnsEMBL/IdMapping/TinyTranscript.pm b/modules/Bio/EnsEMBL/IdMapping/TinyTranscript.pm
index f9c1870880b1d4a06ef9847035675f694ec44cbb..a62a2effe28e7918a19e706af9839606e968264b 100644
--- a/modules/Bio/EnsEMBL/IdMapping/TinyTranscript.pm
+++ b/modules/Bio/EnsEMBL/IdMapping/TinyTranscript.pm
@@ -2,15 +2,44 @@ package Bio::EnsEMBL::IdMapping::TinyTranscript;
=head1 NAME
+Bio::EnsEMBL::IdMapping::TinyTranscript - lightweight transcript object
=head1 SYNOPSIS
+# fetch a transcript from the db and create a lightweight transcript object from
+# it
+my $tr = $transcript_adaptor->fetch_by_stable_id('ENST000345437');
+my $lightweight_tr = Bio::EnsEMBL::IdMapping::TinyTranscript->new_fast([
+ $tr->dbID,
+ $tr->stable_id,
+ $tr->version,
+ $tr->created_date,
+ $tr->modified_date,
+ $tr->start,
+ $tr->end,
+ $tr->strand,
+ $tr->length,
+ md5_hex($tr->spliced_seq),
+ ($tr->is_known ? 1 : 0),
+]);
=head1 DESCRIPTION
+This is a lightweight transcript object for the stable Id mapping. See the
+documentation in TinyFeature for general considerations about its design.
=head1 METHODS
+start
+end
+strand
+length
+seq_md5_sum
+is_known
+add_Translation
+translation
+add_Exon
+get_all_Exons
=head1 LICENCE
@@ -29,6 +58,19 @@ Please post comments/questions to the Ensembl development list
=cut
+# internal data structure (array indices):
+#
+# 0-4 see TinyFeature
+# 5 start
+# 6 end
+# 7 strand
+# 8 length
+# 9 seq_md5_sum
+# 10 is_known
+# 11 translation
+# 12 [exons]
+
+
use strict;
use warnings;
no warnings 'uninitialized';
@@ -39,6 +81,18 @@ our @ISA = qw(Bio::EnsEMBL::IdMapping::TinyFeature);
use Bio::EnsEMBL::Utils::Exception qw(throw warning);
+=head2 start
+
+ Arg[1] : (optional) Int - the transcript's start coordinate
+ Description : Getter/setter for the transcript's start coordinate.
+ Return type : Int
+ Exceptions : none
+ Caller : general
+ Status : At Risk
+ : under development
+
+=cut
+
sub start {
my $self = shift;
$self->[5] = shift if (@_);
@@ -46,6 +100,18 @@ sub start {
}
+=head2 end
+
+ Arg[1] : (optional) Int - the transcript's end coordinate
+ Description : Getter/setter for the transcript's end coordinate.
+ Return type : Int
+ Exceptions : none
+ Caller : general
+ Status : At Risk
+ : under development
+
+=cut
+
sub end {
my $self = shift;
$self->[6] = shift if (@_);
@@ -53,6 +119,18 @@ sub end {
}
+=head2 strand
+
+ Arg[1] : (optional) Int - the transcript's strand
+ Description : Getter/setter for the transcript's strand.
+ Return type : Int
+ Exceptions : none
+ Caller : general
+ Status : At Risk
+ : under development
+
+=cut
+
sub strand {
my $self = shift;
$self->[7] = shift if (@_);
@@ -60,6 +138,20 @@ sub strand {
}
+=head2 length
+
+ Arg[1] : (optional) Int - the transcript's length
+ Description : Getter/setter for the transcript's length. Note that this is
+ *not* the distance between start and end, but rather the sum of
+ the lengths of all exons.
+ Return type : Int
+ Exceptions : none
+ Caller : general
+ Status : At Risk
+ : under development
+
+=cut
+
sub length {
my $self = shift;
$self->[8] = shift if (@_);
@@ -67,6 +159,21 @@ sub length {
}
+=head2 seq_md5_sum
+
+ Arg[1] : (optional) String - the md5 digest of the transcript's sequence
+ Description : Getter/setter for the md5 digest of the transcript's sequence.
+ Note that when used as a setter, you are expected to pass a
+ digest, not the raw sequence (i.e. the digest is not created for
+ you).
+ Return type : String
+ Exceptions : none
+ Caller : general
+ Status : At Risk
+ : under development
+
+=cut
+
sub seq_md5_sum {
my $self = shift;
$self->[9] = shift if (@_);
@@ -74,6 +181,18 @@ sub seq_md5_sum {
}
+=head2 is_known
+
+ Arg[1] : (optional) Boolean - the transcript's "known" status
+ Description : Getter/setter for the transcript's "known" status.
+ Return type : Boolean
+ Exceptions : none
+ Caller : general
+ Status : At Risk
+ : under development
+
+=cut
+
sub is_known {
my $self = shift;
$self->[10] = shift if (@_);
@@ -81,6 +200,20 @@ sub is_known {
}
+=head2 add_Translation
+
+ Arg[1] : Bio::EnsEMBL::IdMapping::TinyTranslation $tl - the translation
+ to add
+ Example : $tiny_transcript->add_Translation($tiny_translation);
+ Description : Adds a translation to this transcript.
+ Return type : none
+ Exceptions : thrown on wrong or missing argument
+ Caller : general
+ Status : At Risk
+ : under development
+
+=cut
+
sub add_Translation {
my $self = shift;
my $tl = shift;
@@ -93,11 +226,35 @@ sub add_Translation {
}
+=head2 translation
+
+ Description : Getter for the transcript's translation.
+ Return type : Bio::EnsEMBL::IdMapping::TinyTranslation
+ Exceptions : none
+ Caller : general
+ Status : At Risk
+ : under development
+
+=cut
+
sub translation {
return $_[0]->[11];
}
+=head2 add_Exon
+
+ Arg[1] : Bio::EnsEMBL::IdMapping::TinyExon $exon - the exon to add
+ Example : $tiny_transcript->add_Exon($tiny_exon);
+ Description : Adds an exon to this transcript.
+ Return type : none
+ Exceptions : thrown on wrong or missing argument
+ Caller : general
+ Status : At Risk
+ : under development
+
+=cut
+
sub add_Exon {
my $self = shift;
my $exon = shift;
@@ -110,6 +267,20 @@ sub add_Exon {
}
+=head2 get_all_Exons
+
+ Example : foreach my $exon (@{ $tiny_transcript->get_all_Exons }) {
+ # do something with exon
+ }
+ Description : Returns all exons attached to that transcript.
+ Return type : Arrayref of Bio::EnsEMBL::IdMapping::TinyExon objects
+ Exceptions : none
+ Caller : general
+ Status : At Risk
+ : under development
+
+=cut
+
sub get_all_Exons {
return $_[0]->[12] || [];
}
diff --git a/modules/Bio/EnsEMBL/IdMapping/TinyTranslation.pm b/modules/Bio/EnsEMBL/IdMapping/TinyTranslation.pm
index 6b47038af118c379185a366127c42a686251d561..365242a904ec31563b04620efb43df66e1ed9e80 100644
--- a/modules/Bio/EnsEMBL/IdMapping/TinyTranslation.pm
+++ b/modules/Bio/EnsEMBL/IdMapping/TinyTranslation.pm
@@ -2,15 +2,33 @@ package Bio::EnsEMBL::IdMapping::TinyTranslation;
=head1 NAME
+Bio::EnsEMBL::IdMapping::TinyTranslation - lightweight translation object
=head1 SYNOPSIS
+if (my $tl = $tr->translation) {
+ my $lightweight_tl = Bio::EnsEMBL::IdMapping::TinyTranslation->new_fast([
+ $tl->dbID,
+ $tl->stable_id,
+ $tl->version,
+ $tl->created_date,
+ $tl->modified_date,
+ $tr->dbID,
+ $tr->translate->seq,
+ ($tr->is_known ? 1 : 0),
+ ]);
+}
=head1 DESCRIPTION
+This is a lightweight translation object for the stable Id mapping. See the
+documentation in TinyFeature for general considerations about its design.
=head1 METHODS
+transcript_id
+seq
+is_known
=head1 LICENCE
@@ -29,6 +47,14 @@ Please post comments/questions to the Ensembl development list
=cut
+# internal data structure (array indices):
+#
+# 0-4 see TinyFeature
+# 5 transcript_id
+# 6 seq
+# 7 is_known
+
+
use strict;
use warnings;
no warnings 'uninitialized';
@@ -39,6 +65,19 @@ our @ISA = qw(Bio::EnsEMBL::IdMapping::TinyFeature);
use Bio::EnsEMBL::Utils::Exception qw(throw warning);
+=head2 transcript_id
+
+ Arg[1] : (optional) Int - the transcript internal Id ("dbID")
+ Description : Getter/setter for the transcript internal Id this translation is
+ attached to.
+ Return type : Int
+ Exceptions : none
+ Caller : general
+ Status : At Risk
+ : under development
+
+=cut
+
sub transcript_id {
my $self = shift;
$self->[5] = shift if (@_);
@@ -46,6 +85,18 @@ sub transcript_id {
}
+=head2 seq
+
+ Arg[1] : (optional) String - the translation's sequence
+ Description : Getter/setter for the translation's sequence.
+ Return type : String
+ Exceptions : none
+ Caller : general
+ Status : At Risk
+ : under development
+
+=cut
+
sub seq {
my $self = shift;
$self->[6] = shift if (@_);
@@ -53,6 +104,18 @@ sub seq {
}
+=head2 is_known
+
+ Arg[1] : (optional) Boolean - the translation's "known" status
+ Description : Getter/setter for the translation's "known" status.
+ Return type : Boolean
+ Exceptions : none
+ Caller : general
+ Status : At Risk
+ : under development
+
+=cut
+
sub is_known {
my $self = shift;
$self->[7] = shift if (@_);