From a5778a6575854afa51ad975d43500a1aac523bc1 Mon Sep 17 00:00:00 2001
From: Patrick Meidl <pm2@sanger.ac.uk>
Date: Thu, 9 Mar 2006 15:54:21 +0000
Subject: [PATCH] schema and API changes for archive stable id history
---
modules/Bio/EnsEMBL/ArchiveStableId.pm | 321 +++--
.../EnsEMBL/DBSQL/ArchiveStableIdAdaptor.pm | 581 +++++---
modules/t/archiveStableId.t | 4 +-
sql/patch_37_38.sql | 9 +
sql/table.sql | 1237 +++++++++--------
5 files changed, 1258 insertions(+), 894 deletions(-)
diff --git a/modules/Bio/EnsEMBL/ArchiveStableId.pm b/modules/Bio/EnsEMBL/ArchiveStableId.pm
index 1effcb36fa..4b78f71bb1 100644
--- a/modules/Bio/EnsEMBL/ArchiveStableId.pm
+++ b/modules/Bio/EnsEMBL/ArchiveStableId.pm
@@ -1,11 +1,4 @@
-# EnsEMBL module for ArchiveStableId
-# Copyright EMBL-EBI/Sanger center 2003
-#
-#
-#
-# You may distribute this module under the same terms as perl itself
-
-# POD documentation - main docs before the code
+package Bio::EnsEMBL::ArchiveStableId;
=head1 NAME
@@ -13,81 +6,98 @@ Bio::EnsEMBL::ArchiveStableId
=head1 SYNOPSIS
-ArchiveStableId objects are the main workunit for retrieving stable id archived information from
- EnsEMBL core database.
-
=head1 DESCRIPTION
- Attributes:
+ArchiveStableId objects are the main workunit for retrieving stable id archived
+information from EnsEMBL core database.
+
+Attributes:
type: Gene, Transcript, Translation, Exon, other, undef
stable_id: eg. ENSG00000000001
+ version: e.g. 1
db_name: eg. homo_sapiens_core_12_31
- version: 1
+ release: e.g. 35
+ assembly: e.g. NCBI35
+ successors: listref of Bio::EnsEMBL::ArchiveStableIds
+ adaptor: Bio::EnsEMBL::DBSQL::ArchiveStableIdAdaptor
- Methods:
- new:
- new_fast:
- get_all_direct_predecessors:
- get_all_direct_successors:
+Status: At Risk. This module is in development.
+
+=head1 METHODS
- get_components:
-
- Status: At Risk. This module is in development.
+ new
+ new_fast
+ get_all_predecessors
+ get_all_successors
+ get_peptide
+ get_all_transcript_archive_ids
+ get_all_translation_archive_ids
+=head1 LICENCE
-=cut
+This code is distributed under an Apache style licence:
+Please see http://www.ensembl.org/code_licence.html for details
+=head1 AUTHOR
+Ensembl core API team
+Currently maintained by Patrick Meidl <meidl@ebi.ac.uk>
-package Bio::EnsEMBL::ArchiveStableId;
+=head1 CONTACT
+
+Please post comments/questions to the Ensembl development list
+<ensembl-dev@ebi.ac.uk>
+
+=cut
+
use strict;
use warnings;
no warnings qw(uninitialized);
use Bio::EnsEMBL::Root;
+our @ISA = qw(Bio::EnsEMBL::Root);
+
use Bio::EnsEMBL::Utils::Argument qw(rearrange);
use Bio::EnsEMBL::Utils::Exception qw(deprecate);
-use vars qw(@ISA);
-
-
-@ISA = qw(Bio::EnsEMBL::Root);
-
-
=head2 new
- Arg 1 : -stable_id $stable_id
- Arg [ ] : -version $version
- Arg [ ] : -db_name $db_name
- Arg [ ] : -adaptor $adaptor
- Arg [ ] : -type $type
- "Gene", "Transcript", "Translation", "Exon"
- Example : none
- Description: standard constructor with named arguments to create ArchiveStableId
- Returntype : Bio::EnsEMBL::ArchiveStableId
- Exceptions : none
- Caller : Adaptor
- Status : At Risk
- : under development
+ Arg [STABLE_ID] : String $stable_id
+ Arg [VERSION] : Int $version
+ Arg [DB_NAME] : String $db_name
+ Arg [RELEASE] : String $release
+ Arg [ASSEMBLY_NAME] : String $assembly
+ Arg [TYPE] : String $type - "Gene", "Transcript", "Translation", "Exon"
+ Arg [ADAPTOR] : Bio::EnsEMBL::DBSQL::ArchiveStableIdAdaptor $adaptor
+ Example : none
+ Description : standard constructor with named arguments to create
+ ArchiveStableId
+ Returntype : Bio::EnsEMBL::ArchiveStableId
+ Exceptions : none
+ Caller : general, Bio::EnsEMBL::DBSQL::ArchiveStableIdAdaptor
+ Status : At Risk
+ : under development
=cut
-
sub new {
my $class = shift;
$class = ref( $class ) || $class;
my $self = bless {}, $class;
- my ( $stable_id, $version, $db_name, $type, $adaptor ) =
- rearrange( [ qw( STABLE_ID VERSION DB_NAME TYPE ADAPTOR ) ], @_ );
+ my ($stable_id, $version, $db_name, $release, $assembly, $type, $adaptor) =
+ rearrange([qw( STABLE_ID VERSION DB_NAME RELEASE ASSEMBLY TYPE ADAPTOR)],
+ @_ );
$self->{'stable_id'} = $stable_id;
$self->{'version'} = $version;
$self->{'db_name'} = $db_name;
+ $self->{'release'} = $release;
+ $self->{'assembly'} = $assembly;
$self->{'type'} = $type;
$self->{'adaptor'} = $adaptor;
@@ -95,93 +105,107 @@ sub new {
}
-
=head2 new_fast
- Arg [1] : string $stable_id
- Arg [2] : int $version
- Arg [3] : string $db_name
- Arg [4] : string $type
- Arg [5] : Bio::EnsEMBL::DBSQL::ArchiveStableIdAdaptor $adaptor
- Example : none
- Description: faster version of above constructor
- Returntype : Bio::EnsEMBL::ArchiveStableId
- Exceptions : none
- Caller : general, Adaptor
- Status : At Risk
- : under development
+ Arg [1] : String $stable_id
+ Arg [2] : Int $version
+ Arg [3] : String $db_name
+ Arg [4] : String $release
+ Arg [5] : String $assembly
+ Arg [6] : String $type - "Gene", "Transcript", "Translation", "Exon"
+ Arg [7] : Bio::EnsEMBL::DBSQL::ArchiveStableIdAdaptor $adaptor
+ Example : none
+ Description : faster version of above constructor
+ Returntype : Bio::EnsEMBL::ArchiveStableId
+ Exceptions : none
+ Caller : general, Bio::EnsEMBL::DBSQL::ArchiveStableIdAdaptor
+ Status : At Risk
+ : under development
=cut
-
sub new_fast {
my $class = shift;
- $class = ref( $class ) || $class;
+ $class = ref ($class) || $class;
my $self = bless {
- 'stable_id' => $_[0],
- 'version' => $_[1],
- 'db_name' => $_[2],
- 'type' => $_[3],
- 'adaptor' => $_[4]
- }, $class;
+ 'stable_id' => $_[0],
+ 'version' => $_[1],
+ 'db_name' => $_[2],
+ 'release' => $_[3],
+ 'assembly' => $_[4],
+ 'type' => $_[5],
+ 'adaptor' => $_[6]
+ }, $class;
+
return $self;
}
=head2 get_all_predecessors
- Args : none
- Example : none
- Description: Retrieve a list of ArchiveStableIds that were mapped to this one.
- Returntype : listref Bio::EnsEMBL::ArchiveStableId
- Exceptions : none
- Caller : general
- Status : At Risk
- : under development
+ Args : none
+ Example : none
+ Description : Retrieve a list of ArchiveStableIds that were mapped to this
+ one.
+ Returntype : listref of Bio::EnsEMBL::ArchiveStableId
+ Exceptions : none
+ Caller : general
+ Status : At Risk
+ : under development
=cut
-
sub get_all_predecessors {
my $self = shift;
+
+ my $predecessors = $self->adaptor->fetch_predecessors_by_archive_id($self);
+
+ foreach my $pre (@$predecessors) {
+ $pre->successors($self);
+ }
- $self->adaptor->fetch_pre_by_arch_id( $self );
+ return $predecessors;
}
+
=head2 get_all_successors
- Args : none
- Example : none
- Description: Retrieve a list of ArchiveStableIds that this one was mapped to.
- Returntype : listref Bio::EnsEMBL::ArchiveStableId
- Exceptions : none
- Caller : general
- Status : At Risk
- : under development
+ Args : none
+ Example : none
+ Description : Retrieve a list of ArchiveStableIds that this one was mapped to.
+ Returntype : listref Bio::EnsEMBL::ArchiveStableId
+ Exceptions : none
+ Caller : general
+ Status : At Risk
+ : under development
=cut
sub get_all_successors {
my $self = shift;
- $self->adaptor->fetch_succ_by_arch_id( $self );
+ if ($self->{'successors'}) {
+ return $self->{'successors'};
+ } else {
+ my $successors = $self->adaptor->fetch_successors_by_archive_id($self);
+ return $self->successors(@$successors);
+ }
}
-
=head2 get_peptide
- Args : none
- Example : none
- Description: Retrieves the peptide string for this ArchiveStableId.
- Undef if this is not a Translation or cant be found in the database.
- Returntype : string
- Exceptions : none
- Caller : general
- Status : At Risk
- : under development
+ Args : none
+ Example : none
+ Description : Retrieves the peptide string for this ArchiveStableId.
+ Returntype : String, or undef if this is not a Translation or cant be found
+ in the database.
+ Exceptions : none
+ Caller : general
+ Status : At Risk
+ : under development
=cut
@@ -198,19 +222,18 @@ sub get_peptide {
=head2 get_all_transcript_archive_ids
- Args : none
- Example : none
- Description: If this is a genes ArchiveStableId and found in the database, this
- function gets the transcripts archiveStableIds from it. Returns undef otherwise.
- Returntype : listref Bio::EnsEMBL::ArchiveStableId
- Exceptions : empty if not a gene stable id or not in database
- Caller : general
- Status : At Risk
- : under development
+ Args : none
+ Example : none
+ Description : If this is a genes ArchiveStableId and found in the database,
+ this function gets the transcripts archiveStableIds from it.
+ Returntype : listref of Bio::EnsEMBL::ArchiveStableId
+ Exceptions : none
+ Caller : general
+ Status : At Risk
+ : under development
=cut
-
sub get_all_transcript_archive_ids {
my $self = shift;
@@ -224,22 +247,20 @@ sub get_all_transcript_archive_ids {
}
-
=head2 get_all_translation_archive_ids
- Args : none
- Example : none
- Description: Retrieves the Translation ArchiveStableId for this transcript stable id.
- If not found or this is not a transcripts id return undef
- Returntype : Bio::EnsEMBL::ArchiveStableId
- Exceptions : undef if not in db or not a Transcript
- Caller : general
- Status : At Risk
- : under development
+ Args : none
+ Example : none
+ Description : Retrieves the Translation ArchiveStableIds for this transcript
+ stable id.
+ Returntype : listref of Bio::EnsEMBL::ArchiveStableId
+ Exceptions : none
+ Caller : general
+ Status : At Risk
+ : under development
=cut
-
sub get_all_translation_archive_ids {
my $self = shift;
@@ -259,52 +280,54 @@ sub get_all_translation_archive_ids {
}
}
-sub get_translation_archive_id {
- my $self = shift;
-
- deprecate("Use get_all_translation_archive_ids() instead");
-
- return $self->get_all_translation_archive_ids;
-}
-
-
-# getter / setter attribute section
-
-sub type {
- my $self = shift;
- if( @_ ) {
- $self->{'type'} = shift;
- }
- return $self->{'type'};
-}
+# getter/setters for attributes
sub stable_id {
my $self = shift;
- if( @_ ) {
- $self->{'stable_id'} = shift;
- }
+ $self->{'stable_id'} = shift if (@_);
return $self->{'stable_id'};
}
sub db_name {
my $self = shift;
- if( @_ ) {
- $self->{'db_name'} = shift;
- }
+ $self->{'db_name'} = shift if (@_);
return $self->{'db_name'};
}
+sub release {
+ my $self = shift;
+ $self->{'release'} = shift if (@_);
+ return $self->{'release'};
+}
+
+sub assembly {
+ my $self = shift;
+ $self->{'assembly'} = shift if (@_);
+ return $self->{'assembly'};
+}
+
sub adaptor {
my $self = shift;
- if( @_ ) {
- $self->{'adaptor'} = shift;
- }
+ $self->{'adaptor'} = shift if (@_);
return $self->{'adaptor'};
}
+sub type {
+ my $self = shift;
+ $self->{'type'} = shift if (@_);
+ return $self->{'type'};
+}
+
+sub successors {
+ my $self = shift;
+ $self->{'successors'} = \@_;
+ return $self->{'successors'};
+}
+
# lazy loading
+
sub version {
my $self = shift;
if( @_ ) {
@@ -321,4 +344,16 @@ sub version {
return $self->{'version'};
}
+
+# deprecated methods (changed to more descriptive names)
+
+sub get_translation_archive_id {
+ my $self = shift;
+
+ deprecate("Use get_all_translation_archive_ids() instead");
+
+ return $self->get_all_translation_archive_ids;
+}
+
+
1;
diff --git a/modules/Bio/EnsEMBL/DBSQL/ArchiveStableIdAdaptor.pm b/modules/Bio/EnsEMBL/DBSQL/ArchiveStableIdAdaptor.pm
index 1b820bcb37..2e687a7017 100644
--- a/modules/Bio/EnsEMBL/DBSQL/ArchiveStableIdAdaptor.pm
+++ b/modules/Bio/EnsEMBL/DBSQL/ArchiveStableIdAdaptor.pm
@@ -6,6 +6,17 @@ Bio::EnsEMBL::ArchiveStableIdAdaptor
=head1 SYNOPSIS
+my $reg = "Bio::EnsEMBL::Registry";
+my $archiveStableIdAdaptor =
+ $reg->get_adaptor('human', 'core', 'ArchiveStableId');
+
+my $arch_id = $archiveStableIdAdaptor->fetch_by_stable_id("ENSG00000068990");
+my @history = @{ $archiveStableIdAdaptor->fetch_stable_id_history($arch_id) };
+
+foreach my $a (@history) {
+ print "Stable ID: ".$a->stable_id.".".$a->version."\n";
+ print "Release: ".$a->release." (".$a->assembly.", ".$a->db_name.")\n");
+}
=head1 DESCRIPTION
@@ -22,12 +33,18 @@ This whole module has a status of At Risk as it is under development.
=head1 METHODS
+ fetch_by_stable_id
fetch_by_stable_id_version
fetch_by_stable_id_dbname
- fetch_pre_by_arch_id
- fetch_succ_by_arch_id
- list_dbnames
+ fetch_all_by_gene_archive_id
+ fetch_by_transcript_archive_id
+ fetch_predecessors_by_archive_id
+ fetch_successors_by_archive_id
+ fetch_stable_id_history
+ fetch_predecessor_history
+ fetch_successor_history
get_peptide
+ list_dbnames
_lookup_version
_resolve_type
@@ -39,6 +56,7 @@ Please see http://www.ensembl.org/code_licence.html for details
=head1 AUTHOR
Ensembl core API team
+Currently maintained by Patrick Meidl <meidl@ebi.ac.uk>
=head1 CONTACT
@@ -47,27 +65,29 @@ Please post comments/questions to the Ensembl development list
=cut
+
use strict;
use warnings;
no warnings qw(uninitialized);
use Bio::EnsEMBL::DBSQL::BaseAdaptor;
-use Bio::EnsEMBL::ArchiveStableId;
-
our @ISA = qw(Bio::EnsEMBL::DBSQL::BaseAdaptor);
+use Bio::EnsEMBL::ArchiveStableId;
+use Bio::EnsEMBL::Utils::Exception qw(deprecate);
+
=head2 fetch_by_stable_id
- Arg [1] : string $stable_id
- Example : none
- Description: retrives an ArchiveStableId that is the latest incarnation of
- given stable_id. If not in database, will return undef.
- Returntype : Bio::EnsEMBL::ArchiveStableId
- Exceptions : none
- Caller : general
- Status : At Risk
- : under development
+ Arg [1] : string $stable_id
+ Example : none
+ Description : retrives an ArchiveStableId that is the latest incarnation of
+ given stable_id.
+ Returntype : Bio::EnsEMBL::ArchiveStableId or undef if not in database
+ Exceptions : none
+ Caller : general
+ Status : At Risk
+ : under development
=cut
@@ -93,16 +113,16 @@ sub fetch_by_stable_id {
=head2 fetch_by_stable_id_version
- Arg [1] : string $stable_id
- Arg [2] : int $version
- Example : none
- Description: Create an archiveStableId with given version and stableId
- No lookup is done in the database.
- Returntype : Bio::EnsEMBL::ArchiveStableId
- Exceptions : none
- Caller : general
- Status : At Risk
- : under development
+ Arg [1] : string $stable_id
+ Arg [2] : int $version
+ Example : none
+ Description : Create an archiveStableId with given version and stableId
+ No lookup is done in the database.
+ Returntype : Bio::EnsEMBL::ArchiveStableId
+ Exceptions : none
+ Caller : general
+ Status : At Risk
+ : under development
=cut
@@ -126,16 +146,15 @@ sub fetch_by_stable_id_version {
=head2 fetch_by_stable_id_dbname
- Arg [1] : string $stable_id
- Arg [2] : string $db_name
- Example : none
- Description: create an ArchiveStableId from given arguments.
- No database lookup is done.
- Returntype : Bio::EnsEMBL::ArchiveStableId
- Exceptions : none
- Caller : general
- Status : At Risk
- : under development
+ Arg [1] : string $stable_id
+ Arg [2] : string $db_name
+ Example : none
+ Description : create an ArchiveStableId from given arguments.
+ Returntype : Bio::EnsEMBL::ArchiveStableId or undef if not in database
+ Exceptions : none
+ Caller : general
+ Status : At Risk
+ : under development
=cut
@@ -163,15 +182,15 @@ sub fetch_by_stable_id_dbname {
=head2 fetch_all_by_gene_archive_id
- Arg [1] : Bio::EnsEMBL::ArchiveStableId $gene_archive_id
- Example : none
- Description: Given the ArchiveStableId of a gene retrieves ArchiveStableIds
- of Transcripts that make that gene.
- Returntype : listref Bio::EnsEMBL::ArchiveStableId
- Exceptions : empty if not a gene stable id or not in database
- Caller : ArchiveStableId->get_all_transcripts()
- Status : At Risk
- : under development
+ Arg [1] : Bio::EnsEMBL::ArchiveStableId $gene_archive_id
+ Example : none
+ Description : Given the ArchiveStableId of a gene retrieves ArchiveStableIds
+ of Transcripts that make that gene.
+ Returntype : listref Bio::EnsEMBL::ArchiveStableId
+ Exceptions : none
+ Caller : Bio::EnsEMBL::ArchiveStableId->get_all_transcript_archive_ids
+ Status : At Risk
+ : under development
=cut
@@ -181,21 +200,25 @@ sub fetch_all_by_gene_archive_id {
my @result = ();
my $sql = qq(
- SELECT ga.transcript_stable_id, ga.transcript_version,
- m.old_db_name
- FROM gene_archive ga, mapping_session m
- WHERE ga.gene_stable_id = ?
- AND ga.gene_version = ?
- AND ga.mapping_session_id = m.mapping_session_id
+ SELECT
+ ga.transcript_stable_id,
+ ga.transcript_version,
+ m.old_db_name,
+ m.old_release,
+ m.old_assembly
+ FROM gene_archive ga, mapping_session m
+ WHERE ga.gene_stable_id = ?
+ AND ga.gene_version = ?
+ AND ga.mapping_session_id = m.mapping_session_id
);
- my $sth = $self->prepare( $sql );
+ my $sth = $self->prepare($sql);
$sth->bind_param(1,$gene_archive_id->stable_id,SQL_VARCHAR);
$sth->bind_param(2,$gene_archive_id->version,SQL_SMALLINT);
$sth->execute();
- my ( $stable_id, $version, $db_name );
- $sth->bind_columns( \$stable_id, \$version, \$db_name );
+ my ($stable_id, $version, $db_name, $release, $assembly);
+ $sth->bind_columns(\$stable_id, \$version, \$db_name, \$release, \$assembly);
while( $sth->fetch() ) {
my $new_arch_id = Bio::EnsEMBL::ArchiveStableId->new
@@ -204,7 +227,9 @@ sub fetch_all_by_gene_archive_id {
-adaptor => $self,
-stable_id => $stable_id,
-type => "Transcript",
- -db_name => $db_name
+ -db_name => $db_name,
+ -release => $release,
+ -assembly => $assembly
);
push( @result, $new_arch_id );
@@ -217,15 +242,15 @@ sub fetch_all_by_gene_archive_id {
=head2 fetch_by_transcript_archive_id
- Arg [1] : Bio::EnsEMBL::ArchiveStableId
- Example : none
- Description: Given a Transcripts ArchiveStableId retrieves the
- Translations ArchiveStableId.
- Returntype : Bio::EnsEMBL::ArchiveStableId
- Exceptions : undef if not in db or not a Transcript
- Caller : Bio::EnsEMBL::ArchiveStableId->get_translation_archive_id
- Status : At Risk
- : under development
+ Arg [1] : Bio::EnsEMBL::ArchiveStableId
+ Example : none
+ Description : Given a Transcripts ArchiveStableId retrieves the
+ Translations ArchiveStableId.
+ Returntype : Bio::EnsEMBL::ArchiveStableId or undef if not in database
+ Exceptions : none
+ Caller : Bio::EnsEMBL::ArchiveStableId->get_all_translation_archive_ids
+ Status : At Risk
+ : under development
=cut
@@ -234,11 +259,15 @@ sub fetch_by_transcript_archive_id {
my $transcript_archive_id = shift;
my $sql = qq(
- SELECT ga.translation_stable_id, ga.translation_version,
- m.old_db_name
- FROM gene_archive ga, mapping_session m
- WHERE ga.transcript_stable_id = ?
- AND ga.transcript_version = ?
+ SELECT
+ ga.translation_stable_id,
+ ga.translation_version,
+ m.old_db_name,
+ m.old_release,
+ m.old_assembly
+ FROM gene_archive ga, mapping_session m
+ WHERE ga.transcript_stable_id = ?
+ AND ga.transcript_version = ?
);
my $sth = $self->prepare( $sql );
@@ -246,7 +275,7 @@ sub fetch_by_transcript_archive_id {
$sth->bind_param(2,$transcript_archive_id->version,SQL_SMALLINT);
$sth->execute();
- my ( $stable_id, $version, $db_name ) = $sth->fetchrow_array();
+ my ($stable_id, $version, $db_name, $release, $assembly) = $sth->fetchrow_array();
$sth->finish();
@@ -257,7 +286,9 @@ sub fetch_by_transcript_archive_id {
-adaptor => $self,
-stable_id => $stable_id,
-type => "Translation",
- -db_name => $db_name
+ -db_name => $db_name,
+ -release => $release,
+ -assembly => $assembly
);
return $new_arch_id;
@@ -267,21 +298,21 @@ sub fetch_by_transcript_archive_id {
}
-=head2 fetch_pre_by_arch_id
+=head2 fetch_predecessors_by_archive_id
- Arg [1] : Bio::EnsEMBL::ArchiveStableId
- Example : none
- Description: Retrieve a list of ArchiveStableIds that were mapped to the
- given one.
- Returntype : listref Bio::EnsEMBL::ArchiveStableId
- Exceptions : none
- Caller : Bio::EnsEMBL::ArchiveStableId->get_all_predecessors
- Status : At Risk
- : under development
+ Arg [1] : Bio::EnsEMBL::ArchiveStableId
+ Example : none
+ Description : Retrieve a list of ArchiveStableIds that were mapped to the
+ given one.
+ Returntype : listref Bio::EnsEMBL::ArchiveStableId
+ Exceptions : none
+ Caller : Bio::EnsEMBL::ArchiveStableId->get_all_predecessors
+ Status : At Risk
+ : under development
=cut
-sub fetch_pre_by_arch_id {
+sub fetch_predecessors_by_archive_id {
my $self = shift;
my $arch_id = shift;
my @result;
@@ -293,27 +324,35 @@ sub fetch_pre_by_arch_id {
}
my $sql = qq(
- SELECT sie.old_stable_id, sie.old_version, m.old_db_name
- FROM mapping_session m, stable_id_event sie
+ SELECT
+ sie.old_stable_id,
+ sie.old_version,
+ m.old_db_name,
+ m.old_release,
+ m.old_assembly
+ FROM mapping_session m, stable_id_event sie
WHERE sie.mapping_session_id = m.mapping_session_id
- AND sie.new_stable_id = ?
- AND m.new_db_name = ?
+ AND sie.new_stable_id = ?
+ AND m.new_db_name = ?
);
my $sth = $self->prepare( $sql );
$sth->bind_param(1,$arch_id->stable_id, SQL_VARCHAR);
$sth->bind_param(2,$arch_id->db_name,SQL_VARCHAR);
$sth->execute();
- my ( $old_stable_id, $old_version, $old_db_name );
- $sth->bind_columns( \$old_stable_id, \$old_version, \$old_db_name );
+
+ my ($old_stable_id, $old_version, $old_db_name, $old_release, $old_assembly);
+ $sth->bind_columns(\$old_stable_id, \$old_version, \$old_db_name, \$old_release, \$old_assembly);
+
while( $sth->fetch() ) {
if( defined $old_stable_id ) {
-
my $old_arch_id = Bio::EnsEMBL::ArchiveStableId->new
(
-version => $old_version,
-stable_id => $old_stable_id,
-db_name => $old_db_name,
+ -release => $old_release,
+ -assembly => $old_assembly,
-adaptor => $self
);
_resolve_type( $old_arch_id );
@@ -326,134 +365,238 @@ sub fetch_pre_by_arch_id {
}
-=head2 fetch_all_currently_related
+=head2 fetch_successors_by_archive_id
- Arg [1] : Bio::EnsEMBL::ArchiveStableId $arch_id
- The one where you want to know the currently related ones.
- Example : none
- Description: Gives back a list of archive stable ids which are successors in
- the stable_id_event tree of the given stable_id. Might well be
- empty.
- Returntype : listref Bio::EnsEMBL::ArchiveStableId
- Exceptions : none
- Caller : webcode for archive
- Status : At Risk
- : under development
+ Arg [1] : Bio::EnsEMBL::ArchiveStableId
+ Example : none
+ Description : Retrieve a list of ArchiveStableIds that the given one was
+ mapped to. This method goes forward only one level, to retrieve
+ a full successor history use fetch_successor_history().
+ Returntype : listref Bio::EnsEMBL::ArchiveStableId
+ Exceptions : none
+ Caller : Bio::EnsEMBL::ArchiveStableId->get_all_successors
+ Status : At Risk
+ : under development
=cut
-sub fetch_all_currently_related {
+sub fetch_successors_by_archive_id {
my $self = shift;
my $arch_id = shift;
+ my @result;
- my $current_db_name = $self->list_dbnames()->[0];
- my $dbname = $arch_id->db_name;
+
+ if( ! ( defined $arch_id->stable_id() &&
+ defined $arch_id->db_name() )) {
+ $self->throw( "Need db_name for successor retrieval" );
+ }
- my $old = [];
+ my $sql = qq(
+ SELECT
+ sie.new_stable_id,
+ sie.new_version,
+ m.new_db_name,
+ m.new_release,
+ m.new_assembly
+ FROM mapping_session m, stable_id_event sie
+ WHERE sie.mapping_session_id = m.mapping_session_id
+ AND sie.old_stable_id = ?
+ AND m.old_db_name = ?
+ );
+
+ my $sth = $self->prepare( $sql );
+ $sth->bind_param(1,$arch_id->stable_id,SQL_VARCHAR);
+ $sth->bind_param(2,$arch_id->db_name,SQL_VARCHAR);
+ $sth->execute();
+
+ my ($new_stable_id, $new_version, $new_db_name, $new_release, $new_assembly);
+ $sth->bind_columns(\$new_stable_id, \$new_version, \$new_db_name, \$new_release, \$new_assembly);
+
+ while( $sth->fetch() ) {
+ if( defined $new_stable_id ) {
+ my $new_arch_id = Bio::EnsEMBL::ArchiveStableId->new
+ (
+ -version => $new_version,
+ -stable_id => $new_stable_id,
+ -db_name => $new_db_name,
+ -release => $new_release,
+ -assembly => $new_assembly,
+ -adaptor => $self
+ );
+
+ _resolve_type($new_arch_id);
+ push( @result, $new_arch_id );
+ }
+ }
+ $sth->finish();
+
+ return \@result;
+}
+
+
+=head2 fetch_archive_id_history
+
+ Arg [1] : Bio::EnsEMBL::ArchiveStableId $arch_id
+ Example : none
+ Description : Gives back a list of archive stable ids which are successors or
+ predecessors in the stable_id_event tree of the given
+ stable_id. Might well be empty. This is not the complete network
+ this stable id belongs to, but rather branches out from this id
+ only.
+ Returntype : listref of Bio::EnsEMBL::ArchiveStableId
+ Since every ArchiveStableId knows about it's successors, this is
+ a linked tree.
+ Exceptions : none
+ Caller : webcode for archive
+ Status : At Risk
+ : under development
+
+=cut
+
+sub fetch_archive_id_history {
+ my $self = shift;
+ my $arch_id = shift;
+
+ my @result = (
+ $arch_id,
+ @{ $self->fetch_predecessor_history($arch_id) },
+ @{ $self->fetch_successor_history($arch_id) }
+ );
+
+ # filter duplicates
+ my %unique = map { join(":", $_->stable_id, $_->version, $_->release) => $_ }
+ @result;
+ @result = values %unique;
+
+ return \@result;
+}
+
+
+=head2 fetch_successor_history
+
+ Arg [1] : Bio::EnsEMBL::ArchiveStableId $arch_id
+ Example : none
+ Description : Gives back a list of archive stable ids which are successors in
+ the stable_id_event tree of the given stable_id. Might well be
+ empty.
+ Returntype : listref Bio::EnsEMBL::ArchiveStableId
+ Since every ArchiveStableId knows about it's successors, this is
+ a linked tree.
+ Exceptions : none
+ Caller : webcode for archive
+ Status : At Risk
+ : under development
+
+=cut
+
+sub fetch_successor_history {
+ my $self = shift;
+ my $arch_id = shift;
+
+ my $current_db_name = $self->list_dbnames->[0];
+ my $dbname = $arch_id->db_name;
- if( $dbname eq $current_db_name ) {
- return [ $arch_id ];
+ if ($dbname eq $current_db_name) {
+ return [$arch_id];
}
- push( @$old, $arch_id );
+ my $old = [];
+ my @result = ();
+
+ push @$old, $arch_id;
- while( $dbname ne $current_db_name ) {
+ while ($dbname ne $current_db_name) {
my $new = [];
- while( my $asi = ( shift @$old )) {
- push( @$new, @{$asi->get_all_successors()});
+ while (my $asi = (shift @$old)) {
+ push @$new, @{ $asi->get_all_successors };
}
- if( @$new ) {
- $dbname = $new->[0]->db_name();
+ if (@$new) {
+ $dbname = $new->[0]->db_name;
} else {
last;
}
@$old = @$new;
+ push @result, @$new;
}
- my %stable_ids;
- my @result;
- while( my $arch_id = ( shift @$old )) {
- if( exists $stable_ids{ $arch_id->stable_id } ) {
- next;
- } else {
- push( @result, $arch_id );
- $stable_ids{ $arch_id->stable_id() } = 1;
- }
- }
+ # filter duplicates
+ my %unique = map { join(":", $_->stable_id, $_->version, $_->release) => $_ }
+ @result;
+ @result = values %unique;
return \@result;
}
-=head2 fetch_succ_by_arch_id
+=head2 fetch_predecessor_history
- Arg [1] : Bio::EnsEMBL::ArchiveStableId
- Example : none
- Description: Retrieve a list of ArchiveStableIds that the given one was
- mapped to.
- Returntype : listref Bio::EnsEMBL::ArchiveStableId
- Exceptions : none
- Caller : Bio::EnsEMBL::ArchiveStableId->get_all_successors
- Status : At Risk
- : under development
+ Arg [1] : Bio::EnsEMBL::ArchiveStableId $arch_id
+ Example : none
+ Description : Gives back a list of archive stable ids which are predecessors
+ in the stable_id_event tree of the given stable_id. Might well
+ be empty.
+ Returntype : listref Bio::EnsEMBL::ArchiveStableId
+ Since every ArchiveStableId knows about it's successors, this is
+ a linked tree.
+ Exceptions : none
+ Caller : webcode for archive
+ Status : At Risk
+ : under development
=cut
-sub fetch_succ_by_arch_id {
+sub fetch_predecessor_history {
my $self = shift;
my $arch_id = shift;
- my @result;
-
- if( ! ( defined $arch_id->stable_id() &&
- defined $arch_id->db_name() )) {
- $self->throw( "Need db_name for successor retrieval" );
+ my $oldest_db_name = $self->list_dbnames->[-1];
+ my $dbname = $arch_id->db_name;
+
+ if ($dbname eq $oldest_db_name) {
+ return [$arch_id];
}
- my $sql = qq(
- SELECT sie.new_stable_id, sie.new_version, m.new_db_name
- FROM mapping_session m, stable_id_event sie
- WHERE sie.mapping_session_id = m.mapping_session_id
- AND sie.old_stable_id = ?
- AND m.old_db_name = ?
- );
+ my $old = [];
+ my @result = ();
- my $sth = $self->prepare( $sql );
- $sth->bind_param(1,$arch_id->stable_id,SQL_VARCHAR);
- $sth->bind_param(2,$arch_id->db_name,SQL_VARCHAR);
- $sth->execute();
- my ( $new_stable_id, $new_version, $new_db_name );
- $sth->bind_columns( \$new_stable_id, \$new_version, \$new_db_name );
- while( $sth->fetch() ) {
- if( defined $new_stable_id ) {
- my $new_arch_id = Bio::EnsEMBL::ArchiveStableId->new
- (
- -version => $new_version,
- -stable_id => $new_stable_id,
- -db_name => $new_db_name,
- -adaptor => $self
- );
- _resolve_type( $new_arch_id );
- push( @result, $new_arch_id );
+ push @$old, $arch_id;
+
+ while ($dbname ne $oldest_db_name) {
+ my $new = [];
+ while (my $asi = (shift @$old)) {
+ push @$new, @{ $asi->get_all_predecessors };
}
+
+ if( @$new ) {
+ $dbname = $new->[0]->db_name;
+ } else {
+ last;
+ }
+ @$old = @$new;
+ push @result, @$new;
}
- $sth->finish();
+
+ # filter duplicates
+ my %unique = map { join(":", $_->stable_id, $_->version, $_->release) => $_ }
+ @result;
+ @result = values %unique;
+
return \@result;
}
=head2 list_dbnames
- Args : none
- Example : none
- Description: A list of available database names from the latest (current) to
- the oldest (ordered).
- Returntype : listref string
- Exceptions : none
- Caller : general
- Status : At Risk
- : under development
+ Args : none
+ Example : none
+ Description : A list of available database names from the latest (current) to
+ the oldest (ordered).
+ Returntype : listref string
+ Exceptions : none
+ Caller : general
+ Status : At Risk
+ : under development
=cut
@@ -463,8 +606,8 @@ sub list_dbnames {
if( ! defined $self->{'dbnames'} ) {
my $sql = qq(
SELECT old_db_name, new_db_name
- FROM mapping_session
- ORDER BY created DESC
+ FROM mapping_session
+ ORDER BY created DESC
);
my $sth = $self->prepare( $sql );
$sth->execute();
@@ -495,15 +638,15 @@ sub list_dbnames {
=head2 get_peptide
- Arg [1] :
- Example : none
- Description: Retrieves the peptide string for given ArchiveStableId. If its
- not a peptide or not in the database returns undef.
- Returntype : string
- Exceptions : none
- Caller : ArchiveStableId->get_peptide or general
- Status : At Risk
- : under development
+ Arg [1] : Bio::EnsEMBL::ArchiveStableId $arch_id
+ Example : none
+ Description : Retrieves the peptide string for given ArchiveStableId. If its
+ not a peptide or not in the database returns undef.
+ Returntype : string or undef
+ Exceptions : none
+ Caller : Bio::EnsEMBL::ArchiveStableId->get_peptide, general
+ Status : At Risk
+ : under development
=cut
@@ -556,35 +699,48 @@ sub _lookup_version {
if( ! defined $arch_id->{'db_name'} ) {
# latest version of this stable id
- my $sql_tmp = "SELECT new_db_name, new_version ";
- $sql_tmp .= "FROM stable_id_event sie, mapping_session m ";
- $sql_tmp .= "WHERE sie.mapping_session_id = m.mapping_session_id AND new_stable_id = \"@{[$arch_id->stable_id]}\" $EXTRA_SQL ";
- $sql_tmp .= "ORDER BY m.created DESC";
- $sql = $self->dbc->add_limit_clause($sql_tmp,1);
+ my $sql_tmp = qq(
+ SELECT
+ m.new_db_name,
+ m.new_release,
+ m.new_assembly,
+ sie.new_version
+ FROM stable_id_event sie, mapping_session m
+ WHERE sie.mapping_session_id = m.mapping_session_id
+ AND new_stable_id = "@{[$arch_id->stable_id]}" $EXTRA_SQL
+ ORDER BY m.created DESC
+ );
+ $sql = $self->dbc->add_limit_clause($sql_tmp, 1);
} else {
$sql = qq(
- SELECT old_db_name, old_version
- FROM stable_id_event sie, mapping_session m
- WHERE sie.mapping_session_id = m.mapping_session_id
- AND old_stable_id = "@{[$arch_id->stable_id]}"
- AND m.old_db_name = "@{[$arch_id->db_name]}"
- $EXTRA_SQL
- );
+ SELECT
+ m.old_db_name,
+ m.old_release,
+ m.old_assembly,
+ sie.old_version
+ FROM stable_id_event sie, mapping_session m
+ WHERE sie.mapping_session_id = m.mapping_session_id
+ AND sie.old_stable_id = "@{[$arch_id->stable_id]}"
+ AND m.old_db_name = "@{[$arch_id->db_name]}"
+ $EXTRA_SQL
+ );
}
my $id_type;
my $sth = $self->prepare( $sql );
$sth->execute();
- my ( $db_name, $version ) = $sth->fetchrow_array();
+ my ($db_name, $release, $assembly, $version) = $sth->fetchrow_array();
$sth->finish();
if( ! defined $db_name ) {
return 0;
} else {
- $arch_id->version( $version );
+ $arch_id->version($version);
if( ! defined $arch_id->{'db_name'} ) {
- $arch_id->db_name( $db_name );
+ $arch_id->db_name($db_name);
+ $arch_id->release($release);
+ $arch_id->assembly($assembly);
}
}
@@ -613,4 +769,35 @@ sub _resolve_type {
$arch_id->type( $id_type );
}
+
+# deprecated methods (changed to more descriptive names)
+
+sub fetch_pre_by_arch_id {
+ my $self = shift;
+ my $arch_id = shift;
+
+ deprecate("Use fetch_predecessors_by_archive_id() instead");
+
+ return $self->fetch_predecessors_by_archive_id($arch_id);
+}
+
+sub fetch_succ_by_arch_id {
+ my $self = shift;
+ my $arch_id = shift;
+
+ deprecate("Use fetch_successors_by_archive_id() instead");
+
+ return $self->fetch_successors_by_archive_id($arch_id);
+}
+
+sub fetch_all_currently_related {
+ my $self = shift;
+ my $arch_id = shift;
+
+ deprecate("Use fetch_successor_history() instead");
+
+ return $self->fetch_successor_history($arch_id);
+}
+
+
1;
diff --git a/modules/t/archiveStableId.t b/modules/t/archiveStableId.t
index 1179fcfd62..a0bc9395e1 100644
--- a/modules/t/archiveStableId.t
+++ b/modules/t/archiveStableId.t
@@ -105,11 +105,11 @@ for my $asi ( @$succ_asis ) {
ok( scalar( @$succ_asis ) == 0 );
#
-# 8 fetch_all_currently_related
+# 8 fetch_successor_history
#
$asi = $asia->fetch_by_stable_id_dbname( "G2", "release_1" );
-my $asis = $asia->fetch_all_currently_related( $asi );
+my $asis = $asia->fetch_successor_history( $asi );
debug( "\tCurrently related from G2.release_1" );
for my $asi ( @$asis ) {
diff --git a/sql/patch_37_38.sql b/sql/patch_37_38.sql
index f168171e26..15b45e775a 100644
--- a/sql/patch_37_38.sql
+++ b/sql/patch_37_38.sql
@@ -56,6 +56,15 @@ CREATE TABLE unmapped_reason (
) COLLATE=latin1_swedish_ci TYPE=MyISAM;
+# Add some more columns to mapping_session
+
+ALTER TABLE mapping_session ADD COLUMN new_assembly varchar(20) NOT NULL default '' AFTER new_db_name;
+ALTER TABLE mapping_session ADD COLUMN old_assembly varchar(20) NOT NULL default '' AFTER new_db_name;
+ALTER TABLE mapping_session ADD COLUMN new_release varchar(5) NOT NULL default '' AFTER new_db_name;
+ALTER TABLE mapping_session ADD COLUMN old_release varchar(5) NOT NULL default '' AFTER new_db_name;
+ALTER TABLE mapping_session CHANGE created created DATETIME NOT NULL;
+
+
# Add the new oligo tables, which replace the affy tables
CREATE TABLE oligo_feature (
diff --git a/sql/table.sql b/sql/table.sql
index 436dc0d7df..bfa796ed9f 100755
--- a/sql/table.sql
+++ b/sql/table.sql
@@ -12,54 +12,82 @@
# - internal ids are integers named tablename_id
# - same name is given in foreign key relations
+
+################################################################################
+#
+# Table structure for table 'oligo_feature'
+#
+
CREATE TABLE oligo_feature (
- oligo_feature_id INT NOT NULL auto_increment,
- seq_region_id INT UNSIGNED NOT NULL,
- seq_region_start INT NOT NULL,
- seq_region_end INT NOT NULL,
- seq_region_strand TINYINT NOT NULL,
-
- mismatches TINYINT,
- oligo_probe_id INT NOT NULL,
- analysis_id INT NOT NULL,
-
- PRIMARY KEY (oligo_feature_id),
- KEY seq_region_idx (seq_region_id, seq_region_start),
- KEY probe_idx (oligo_probe_id)
+
+ oligo_feature_id INT NOT NULL AUTO_INCREMENT,
+ seq_region_id INT UNSIGNED NOT NULL,
+ seq_region_start INT NOT NULL,
+ seq_region_end INT NOT NULL,
+ seq_region_strand TINYINT NOT NULL,
+ mismatches TINYINT,
+ oligo_probe_id INT NOT NULL,
+ analysis_id INT NOT NULL,
+
+ PRIMARY KEY (oligo_feature_id),
+ KEY seq_region_idx (seq_region_id, seq_region_start),
+ KEY probe_idx (oligo_probe_id)
+
) COLLATE=latin1_swedish_ci TYPE=MyISAM;
+
+################################################################################
+#
+# Table structure for table 'oligo_probe'
+#
+
CREATE TABLE oligo_probe (
- oligo_probe_id INT NOT NULL auto_increment,
- oligo_array_id INT NOT NULL,
- probeset VARCHAR(40),
- name VARCHAR(20),
- description TEXT,
- length SMALLINT NOT NULL,
-
- PRIMARY KEY (oligo_probe_id, oligo_array_id),
- KEY probeset_idx (probeset),
- KEY array_idx (oligo_array_id)
+
+ oligo_probe_id INT NOT NULL AUTO_INCREMENT,
+ oligo_array_id INT NOT NULL,
+ probeset VARCHAR(40),
+ name VARCHAR(20),
+ description TEXT,
+ length SMALLINT NOT NULL,
+
+ PRIMARY KEY (oligo_probe_id, oligo_array_id),
+ KEY probeset_idx (probeset),
+ KEY array_idx (oligo_array_id)
+
) COLLATE=latin1_swedish_ci TYPE=MyISAM;
+
+################################################################################
+#
+# Table structure for table 'oligo_array'
+#
+
CREATE TABLE oligo_array (
- oligo_array_id INT NOT NULL auto_increment,
- parent_array_id INT,
- probe_setsize TINYINT NOT NULL,
- name VARCHAR(40) NOT NULL,
- type ENUM( 'AFFY', 'OLIGO' ),
- PRIMARY KEY (oligo_array_id)
+ oligo_array_id INT NOT NULL auto_increment,
+ parent_array_id INT,
+ probe_setsize TINYINT NOT NULL,
+ name VARCHAR(40) NOT NULL,
+ type ENUM( 'AFFY', 'OLIGO' ),
+
+ PRIMARY KEY (oligo_array_id)
+
) COLLATE=latin1_swedish_ci TYPE=MyISAM;
+################################################################################
+#
+# Table structure for table 'alt_allele'
+#
+
CREATE TABLE alt_allele (
- alt_allele_id INT NOT NULL auto_increment,
- gene_id INT NOT NULL,
+ alt_allele_id INT NOT NULL AUTO_INCREMENT,
+ gene_id INT NOT NULL,
- UNIQUE gene_idx( gene_id ),
- UNIQUE allele_idx( alt_allele_id, gene_id )
-) COLLATE=latin1_swedish_ci;
-
+ UNIQUE gene_idx (gene_id),
+ UNIQUE allele_idx (alt_allele_id, gene_id)
+
+) COLLATE=latin1_swedish_ci TYPE=MyISAM;
################################################################################
@@ -67,10 +95,12 @@ CREATE TABLE alt_allele (
# Table structure for table 'analysis'
#
# semantics:
+#
# analysis_id - internal id
-# created - date to distinguish newer and older versions off the
-# same analysis. Not well maintained so far.
-# logic_name string to identify the analysis. Used mainly inside pipeline.
+# created
+# - date to distinguish newer and older versions off the same analysis. Not
+# well maintained so far.
+# logic_name - string to identify the analysis. Used mainly inside pipeline.
# db, db_version, db_file
# - db should be a database name, db version the version of that db
# db_file the file system location of that database,
@@ -79,42 +109,50 @@ CREATE TABLE alt_allele (
# - The binary used to create a feature. Similar semantic to above
# module, module_version
# - Perl module names (RunnableDBS usually) executing this analysis.
-# parameters a paramter string which is processed by the perl module
+# parameters - a paramter string which is processed by the perl module
# gff_source, gff_feature
# - how to make a gff dump from features with this analysis
CREATE TABLE analysis (
- analysis_id int(10) unsigned NOT NULL auto_increment,
+ analysis_id INT(10) UNSIGNED NOT NULL AUTO_INCREMENT,
created datetime DEFAULT '0000-00-00 00:00:00' NOT NULL,
- logic_name varchar(40) not null,
- db varchar(120),
- db_version varchar(40),
- db_file varchar(120),
- program varchar(80),
- program_version varchar(40),
- program_file varchar(80),
- parameters varchar(255),
- module varchar(80),
- module_version varchar(40),
- gff_source varchar(40),
- gff_feature varchar(40),
+ logic_name VARCHAR(40) NOT NULL,
+ db VARCHAR(120),
+ db_version VARCHAR(40),
+ db_file VARCHAR(120),
+ program VARCHAR(80),
+ program_version VARCHAR(40),
+ program_file VARCHAR(80),
+ parameters VARCHAR(255),
+ module VARCHAR(80),
+ module_version VARCHAR(40),
+ gff_source VARCHAR(40),
+ gff_feature VARCHAR(40),
PRIMARY KEY (analysis_id),
- KEY logic_name_idx( logic_name ),
- UNIQUE(logic_name)
+ KEY logic_name_idx (logic_name),
+ UNIQUE (logic_name)
+
+) COLLATE=latin1_swedish_ci TYPE=MyISAM;
-) COLLATE=latin1_swedish_ci;
+################################################################################
+#
+# Table structure for table 'analysis_description'
+#
CREATE TABLE analysis_description (
- analysis_id int(10) unsigned NOT NULL,
- description text,
- display_label varchar(255),
- KEY analysis_idx( analysis_id )
-) COLLATE=latin1_swedish_ci;
+ analysis_id INT(10) UNSIGNED NOT NULL,
+ description TEXT,
+ display_label VARCHAR(255),
+
+ KEY analysis_idx (analysis_id)
+
+) COLLATE=latin1_swedish_ci TYPE=MyISAM;
+
################################################################################
#
@@ -123,53 +161,63 @@ CREATE TABLE analysis_description (
# This table stores DNA sequence.
CREATE TABLE dna (
- seq_region_id int unsigned NOT NULL,
- sequence mediumtext NOT NULL,
+
+ seq_region_id INT UNSIGNED NOT NULL,
+ sequence MEDIUMTEXT NOT NULL,
PRIMARY KEY (seq_region_id)
-) MAX_ROWS = 750000 AVG_ROW_LENGTH = 19000;
+) COLLATE=latin1_swedish_ci TYPE=MyISAM MAX_ROWS=750000 AVG_ROW_LENGTH=19000;
+
################################################################################
#
# Table structure for table 'dnac'
#
-# Contains equivalent data to dna table, but 4 letters of DNA code are represented
-# by a single binary character, based on 2 bit encoding
-# do not need to worry about ambiguity of length, since this is stored in contig.length
-# n_line column contains start-end pairs of coordinates in the string that are really Ns
+# Contains equivalent data to dna table, but 4 letters of DNA code are
+# represented by a single binary character, based on 2 bit encoding
+#
+# do not need to worry about ambiguity of length, since this is stored in
+# contig.length
+#
+# n_line column contains start-end pairs of coordinates in the string that are
+# really Ns
CREATE TABLE dnac (
- seq_region_id int unsigned NOT NULL,
- sequence mediumblob NOT NULL,
- n_line text,
+
+ seq_region_id INT UNSIGNED NOT NULL,
+ sequence MEDIUMBLOB NOT NULL,
+ n_line TEXT,
PRIMARY KEY (seq_region_id)
-) MAX_ROWS = 750000 AVG_ROW_LENGTH = 19000;
+
+) COLLATE=latin1_swedish_ci TYPE=MyISAM MAX_ROWS=750000 AVG_ROW_LENGTH=19000;
+
################################################################################
#
# Table structure for table 'exon'
#
-# Note seq_region_start always less that seq_region_end, i.e.
-# when the exon is on the other strand the seq_region_start
-# is specifying the 3prime end of the exon.
+# Note seq_region_start always less that seq_region_end, i.e. when the exon is
+# on the other strand the seq_region_start is specifying the 3prime end of the
+# exon.
CREATE TABLE exon (
- exon_id int unsigned NOT NULL auto_increment,
- seq_region_id int(10) unsigned NOT NULL, # foreign key, seq_region:seq_region_id
- seq_region_start int(10) unsigned NOT NULL, # start of exon within seq_region
- seq_region_end int(10) unsigned NOT NULL, # end of exon within specified seq_region
- seq_region_strand tinyint(2) NOT NULL, # 1 or -1 depending on the strand of the exon
-
- phase tinyint(2) NOT NULL,
- end_phase tinyint(2) NOT NULL,
+ exon_id INT UNSIGNED NOT NULL AUTO_INCREMENT,
+ seq_region_id INT(10) UNSIGNED NOT NULL,
+ seq_region_start INT(10) UNSIGNED NOT NULL,
+ seq_region_end INT(10) UNSIGNED NOT NULL,
+ seq_region_strand TINYINT(2) NOT NULL,
+
+ phase TINYINT(2) NOT NULL,
+ end_phase TINYINT(2) NOT NULL,
PRIMARY KEY (exon_id),
- KEY seq_region_idx (seq_region_id, seq_region_start )
+ KEY seq_region_idx (seq_region_id, seq_region_start)
+
+) COLLATE=latin1_swedish_ci TYPE=MyISAM;
-) COLLATE=latin1_swedish_ci;
################################################################################
#
@@ -178,16 +226,17 @@ CREATE TABLE exon (
CREATE TABLE exon_stable_id (
- exon_id int unsigned not null, # foreign key exon:exon_id
- stable_id VARCHAR(128) not null,
- version int(10),
+ exon_id INT UNSIGNED NOT NULL,
+ stable_id VARCHAR(128) NOT NULL,
+ version INT(10),
created_date DATETIME NOT NULL,
modified_date DATETIME NOT NULL,
- PRIMARY KEY( exon_id ),
- UNIQUE( stable_id, version )
+ PRIMARY KEY (exon_id),
+ UNIQUE (stable_id, version)
+
+) COLLATE=latin1_swedish_ci TYPE=MyISAM;
-) COLLATE=latin1_swedish_ci;
################################################################################
#
@@ -199,15 +248,16 @@ CREATE TABLE exon_stable_id (
CREATE TABLE exon_transcript (
- exon_id INT unsigned NOT NULL, # foreign key exon:exon_id
- transcript_id INT unsigned NOT NULL, # foregin key transcript:transcript_id
- rank int(10) NOT NULL,
+ exon_id INT UNSIGNED NOT NULL,
+ transcript_id INT UNSIGNED NOT NULL,
+ rank INT(10) NOT NULL,
PRIMARY KEY (exon_id,transcript_id,rank),
KEY transcript (transcript_id),
- KEY exon ( exon_id )
+ KEY exon (exon_id)
+
+) COLLATE=latin1_swedish_ci TYPE=MyISAM;
-) COLLATE=latin1_swedish_ci;
################################################################################
#
@@ -216,21 +266,22 @@ CREATE TABLE exon_transcript (
CREATE TABLE simple_feature (
- simple_feature_id int unsigned not null auto_increment,
- seq_region_id int(10) unsigned NOT NULL,
- seq_region_start int(10) unsigned NOT NULL,
- seq_region_end int(10) unsigned NOT NULL,
- seq_region_strand tinyint(1) NOT NULL,
- display_label varchar(40) NOT NULL,
- analysis_id int(10) unsigned NOT NULL,
- score double,
+ simple_feature_id INT UNSIGNED NOT NULL AUTO_INCREMENT,
+ seq_region_id INT(10) UNSIGNED NOT NULL,
+ seq_region_start INT(10) UNSIGNED NOT NULL,
+ seq_region_end INT(10) UNSIGNED NOT NULL,
+ seq_region_strand TINYINT(1) NOT NULL,
+ display_label VARCHAR(40) NOT NULL,
+ analysis_id INT(10) UNSIGNED NOT NULL,
+ score DOUBLE,
- PRIMARY KEY ( simple_feature_id ),
- KEY seq_region_idx (seq_region_id, seq_region_start ),
- KEY analysis_idx( analysis_id ),
- KEY hit_idx( display_label )
+ PRIMARY KEY (simple_feature_id),
+ KEY seq_region_idx (seq_region_id, seq_region_start),
+ KEY analysis_idx (analysis_id),
+ KEY hit_idx (display_label)
+
+) COLLATE=latin1_swedish_ci TYPE=MyISAM MAX_ROWS=100000000 AVG_ROW_LENGTH=80;
-) MAX_ROWS=100000000 AVG_ROW_LENGTH=80;
################################################################################
#
@@ -239,27 +290,28 @@ CREATE TABLE simple_feature (
CREATE TABLE protein_align_feature (
- protein_align_feature_id int unsigned not null auto_increment,
- seq_region_id int(10) unsigned NOT NULL,
- seq_region_start int(10) unsigned NOT NULL,
- seq_region_end int(10) unsigned NOT NULL,
- seq_region_strand tinyint(1) DEFAULT '1' NOT NULL,
- hit_start int(10) NOT NULL,
- hit_end int(10) NOT NULL,
- hit_name varchar(40) NOT NULL,
- analysis_id int(10) unsigned NOT NULL,
- score double,
- evalue double,
- perc_ident float,
- cigar_line text,
-
- PRIMARY KEY ( protein_align_feature_id ),
- KEY seq_region_idx( seq_region_id, analysis_id, seq_region_start, score ),
- KEY seq_region_idx_2( seq_region_id, seq_region_start),
- KEY hit_idx( hit_name ),
- KEY analysis_idx( analysis_id )
-
-) MAX_ROWS=100000000 AVG_ROW_LENGTH=80;
+ protein_align_feature_id INT UNSIGNED NOT NULL AUTO_INCREMENT,
+ seq_region_id INT(10) UNSIGNED NOT NULL,
+ seq_region_start INT(10) UNSIGNED NOT NULL,
+ seq_region_end INT(10) UNSIGNED NOT NULL,
+ seq_region_strand TINYINT(1) DEFAULT '1' NOT NULL,
+ hit_start INT(10) NOT NULL,
+ hit_end INT(10) NOT NULL,
+ hit_name VARCHAR(40) NOT NULL,
+ analysis_id INT(10) UNSIGNED NOT NULL,
+ score DOUBLE,
+ evalue DOUBLE,
+ perc_ident FLOAT,
+ cigar_line TEXT,
+
+ PRIMARY KEY (protein_align_feature_id),
+ KEY seq_region_idx (seq_region_id, analysis_id, seq_region_start, score),
+ KEY seq_region_idx_2 (seq_region_id, seq_region_start),
+ KEY hit_idx (hit_name),
+ KEY analysis_idx (analysis_id)
+
+) COLLATE=latin1_swedish_ci TYPE=MyISAM MAX_ROWS=100000000 AVG_ROW_LENGTH=80;
+
################################################################################
#
@@ -268,50 +320,52 @@ CREATE TABLE protein_align_feature (
CREATE TABLE dna_align_feature (
- dna_align_feature_id int unsigned not null auto_increment,
- seq_region_id int(10) unsigned NOT NULL,
- seq_region_start int(10) unsigned NOT NULL,
- seq_region_end int(10) unsigned NOT NULL,
- seq_region_strand tinyint(1) NOT NULL,
- hit_start int NOT NULL,
- hit_end int NOT NULL,
- hit_strand tinyint(1) NOT NULL,
- hit_name varchar(40) NOT NULL,
- analysis_id int(10) unsigned NOT NULL,
- score double,
- evalue double,
- perc_ident float,
- cigar_line text,
+ dna_align_feature_id INT UNSIGNED NOT NULL AUTO_INCREMENT,
+ seq_region_id INT(10) UNSIGNED NOT NULL,
+ seq_region_start INT(10) UNSIGNED NOT NULL,
+ seq_region_end INT(10) UNSIGNED NOT NULL,
+ seq_region_strand TINYINT(1) NOT NULL,
+ hit_start INT NOT NULL,
+ hit_end INT NOT NULL,
+ hit_strand TINYINT(1) NOT NULL,
+ hit_name VARCHAR(40) NOT NULL,
+ analysis_id INT(10) UNSIGNED NOT NULL,
+ score DOUBLE,
+ evalue DOUBLE,
+ perc_ident FLOAT,
+ cigar_line TEXT,
+
+ PRIMARY KEY (dna_align_feature_id),
+ KEY seq_region_idx (seq_region_id, analysis_id, seq_region_start, score),
+ KEY seq_region_idx_2 (seq_region_id, seq_region_start),
+ KEY hit_idx (hit_name),
+ KEY analysis_idx (analysis_id)
- PRIMARY KEY ( dna_align_feature_id ),
- KEY seq_region_idx( seq_region_id, analysis_id, seq_region_start, score ),
- KEY seq_region_idx_2( seq_region_id, seq_region_start),
- KEY hit_idx( hit_name ),
- KEY analysis_idx( analysis_id )
+) COLLATE=latin1_swedish_ci TYPE=MyISAM MAX_ROWS=100000000 AVG_ROW_LENGTH=80;
-) MAX_ROWS=100000000 AVG_ROW_LENGTH=80;
################################################################################
#
# Table structure for table 'repeat_consensus'
#
+# repeat_class examples: SINE, LINE, DNA Transposon, Retroviral LTR,
+# Satellite, Tandem
CREATE TABLE repeat_consensus (
- repeat_consensus_id int unsigned NOT NULL auto_increment,
- repeat_name varchar(255) NOT NULL,
- repeat_class varchar(100) NOT NULL, # eg: SINE, LINE, DNA Transposon,
- # Retroviral LTR, Satellite,Tandem
- repeat_type varchar(40) NOT NULL,
- repeat_consensus text,
+ repeat_consensus_id INT UNSIGNED NOT NULL AUTO_INCREMENT,
+ repeat_name VARCHAR(255) NOT NULL,
+ repeat_class VARCHAR(100) NOT NULL,
+ repeat_type VARCHAR(40) NOT NULL,
+ repeat_consensus TEXT,
- PRIMARY KEY( repeat_consensus_id ),
+ PRIMARY KEY (repeat_consensus_id),
KEY name (repeat_name),
KEY class (repeat_class),
- KEY consensus(repeat_consensus(10)),
- KEY type( repeat_type )
+ KEY consensus (repeat_consensus(10)),
+ KEY type (repeat_type)
-) COLLATE=latin1_swedish_ci;
+) COLLATE=latin1_swedish_ci TYPE=MyISAM;
################################################################################
#
@@ -320,23 +374,24 @@ CREATE TABLE repeat_consensus (
CREATE TABLE repeat_feature (
- repeat_feature_id int unsigned NOT NULL auto_increment,
- seq_region_id int(10) unsigned NOT NULL,
- seq_region_start int(10) unsigned NOT NULL,
- seq_region_end int(10) unsigned NOT NULL,
- seq_region_strand tinyint(1) DEFAULT '1' NOT NULL,
- repeat_start int(10) NOT NULL,
- repeat_end int(10) NOT NULL,
- repeat_consensus_id int(10) unsigned NOT NULL,
- analysis_id int(10) unsigned NOT NULL,
- score double,
+ repeat_feature_id INT UNSIGNED NOT NULL AUTO_INCREMENT,
+ seq_region_id INT(10) UNSIGNED NOT NULL,
+ seq_region_start INT(10) UNSIGNED NOT NULL,
+ seq_region_end INT(10) UNSIGNED NOT NULL,
+ seq_region_strand TINYINT(1) DEFAULT '1' NOT NULL,
+ repeat_start INT(10) NOT NULL,
+ repeat_end INT(10) NOT NULL,
+ repeat_consensus_id INT(10) UNSIGNED NOT NULL,
+ analysis_id INT(10) UNSIGNED NOT NULL,
+ score DOUBLE,
- PRIMARY KEY ( repeat_feature_id ),
- KEY seq_region_idx( seq_region_id, seq_region_start ),
- KEY repeat_idx( repeat_consensus_id ),
- KEY analysis_idx( analysis_id )
+ PRIMARY KEY (repeat_feature_id),
+ KEY seq_region_idx (seq_region_id, seq_region_start),
+ KEY repeat_idx (repeat_consensus_id),
+ KEY analysis_idx (analysis_id)
+
+) COLLATE=latin1_swedish_ci TYPE=MyISAM MAX_ROWS=100000000 AVG_ROW_LENGTH=80;
-) MAX_ROWS=100000000 AVG_ROW_LENGTH=80;
################################################################################
#
@@ -345,41 +400,44 @@ CREATE TABLE repeat_feature (
CREATE TABLE gene (
- gene_id int unsigned NOT NULL auto_increment,
+ gene_id INT UNSIGNED NOT NULL AUTO_INCREMENT,
biotype VARCHAR(40) NOT NULL,
- analysis_id int,
- seq_region_id int(10) unsigned NOT NULL,
- seq_region_start int(10) unsigned NOT NULL,
- seq_region_end int(10) unsigned NOT NULL,
- seq_region_strand tinyint(2) NOT NULL,
- display_xref_id int unsigned,
+ analysis_id INT,
+ seq_region_id INT(10) UNSIGNED NOT NULL,
+ seq_region_start INT(10) UNSIGNED NOT NULL,
+ seq_region_end INT(10) UNSIGNED NOT NULL,
+ seq_region_strand TINYINT(2) NOT NULL,
+ display_xref_id INT UNSIGNED,
source VARCHAR(20) NOT NULL,
- status enum( 'KNOWN', 'NOVEL', 'PUTATIVE', 'PREDICTED' ),
- description text,
+ status ENUM('KNOWN', 'NOVEL', 'PUTATIVE', 'PREDICTED'),
+ description TEXT,
PRIMARY KEY (gene_id),
- KEY seq_region_idx( seq_region_id, seq_region_start ),
- KEY xref_id_index ( display_xref_id ),
- KEY analysis_idx( analysis_id )
+ KEY seq_region_idx (seq_region_id, seq_region_start),
+ KEY xref_id_index (display_xref_id),
+ KEY analysis_idx (analysis_id)
+
+) COLLATE=latin1_swedish_ci TYPE=MyISAM;
-) COLLATE=latin1_swedish_ci;
################################################################################
#
# Table structure for table 'gene_stable_id'
#
+
CREATE TABLE gene_stable_id (
- gene_id int unsigned not null, # foreign key gene:gene_id
- stable_id VARCHAR(128) not null,
- version int(10),
+ gene_id INT UNSIGNED NOT NULL,
+ stable_id VARCHAR(128) NOT NULL,
+ version INT(10),
created_date DATETIME NOT NULL,
modified_date DATETIME NOT NULL,
- PRIMARY KEY( gene_id ),
- UNIQUE( stable_id, version )
+ PRIMARY KEY (gene_id),
+ UNIQUE (stable_id, version)
+
+) COLLATE=latin1_swedish_ci TYPE=MyISAM;
-) COLLATE=latin1_swedish_ci;
################################################################################
#
@@ -388,14 +446,15 @@ CREATE TABLE gene_stable_id (
CREATE TABLE supporting_feature (
- exon_id int(11) DEFAULT '0' NOT NULL,
- feature_type enum('dna_align_feature','protein_align_feature'),
- feature_id int(11) DEFAULT '0' NOT NULL,
+ exon_id INT(11) DEFAULT '0' NOT NULL,
+ feature_type ENUM('dna_align_feature','protein_align_feature'),
+ feature_id INT(11) DEFAULT '0' NOT NULL,
UNIQUE all_idx (exon_id,feature_type,feature_id),
KEY feature_idx (feature_type,feature_id)
-) MAX_ROWS=100000000 AVG_ROW_LENGTH=80;
+) COLLATE=latin1_swedish_ci TYPE=MyISAM MAX_ROWS=100000000 AVG_ROW_LENGTH=80;
+
################################################################################
#
@@ -404,14 +463,15 @@ CREATE TABLE supporting_feature (
CREATE TABLE transcript_supporting_feature (
- transcript_id int(11) DEFAULT '0' NOT NULL,
- feature_type enum('dna_align_feature','protein_align_feature'),
- feature_id int(11) DEFAULT '0' NOT NULL,
+ transcript_id INT(11) DEFAULT '0' NOT NULL,
+ feature_type ENUM('dna_align_feature','protein_align_feature'),
+ feature_id INT(11) DEFAULT '0' NOT NULL,
UNIQUE all_idx (transcript_id,feature_type,feature_id),
KEY feature_idx (feature_type,feature_id)
-) MAX_ROWS=100000000 AVG_ROW_LENGTH=80;
+) COLLATE=latin1_swedish_ci TYPE=MyISAM MAX_ROWS=100000000 AVG_ROW_LENGTH=80;
+
################################################################################
#
@@ -420,23 +480,24 @@ CREATE TABLE transcript_supporting_feature (
CREATE TABLE transcript (
- transcript_id INT UNSIGNED NOT NULL auto_increment,
- gene_id INT UNSIGNED NOT NULL, # foreign key gene:gene_id
- seq_region_id int(10) unsigned NOT NULL,
- seq_region_start int(10) unsigned NOT NULL,
- seq_region_end int(10) unsigned NOT NULL,
- seq_region_strand tinyint(2) NOT NULL,
- display_xref_id int unsigned,
+ transcript_id INT UNSIGNED NOT NULL AUTO_INCREMENT,
+ gene_id INT UNSIGNED NOT NULL,
+ seq_region_id INT(10) UNSIGNED NOT NULL,
+ seq_region_start INT(10) UNSIGNED NOT NULL,
+ seq_region_end INT(10) UNSIGNED NOT NULL,
+ seq_region_strand TINYINT(2) NOT NULL,
+ display_xref_id INT UNSIGNED,
biotype VARCHAR(40) NOT NULL,
- status enum( 'KNOWN', 'NOVEL', 'PUTATIVE', 'PREDICTED' ),
- description text,
+ status ENUM('KNOWN', 'NOVEL', 'PUTATIVE', 'PREDICTED'),
+ description TEXT,
PRIMARY KEY (transcript_id),
- KEY seq_region_idx( seq_region_id, seq_region_start ),
+ KEY seq_region_idx (seq_region_id, seq_region_start),
KEY gene_index (gene_id),
- KEY xref_id_index ( display_xref_id )
+ KEY xref_id_index (display_xref_id)
+
+) COLLATE=latin1_swedish_ci TYPE=MyISAM;
-) COLLATE=latin1_swedish_ci;
################################################################################
#
@@ -445,16 +506,17 @@ CREATE TABLE transcript (
CREATE TABLE transcript_stable_id (
- transcript_id int unsigned not null, # foreign key transcript:transcript_id
- stable_id VARCHAR(128) not null,
- version int(10),
+ transcript_id INT UNSIGNED NOT NULL,
+ stable_id VARCHAR(128) NOT NULL,
+ version INT(10),
created_date DATETIME NOT NULL,
modified_date DATETIME NOT NULL,
- PRIMARY KEY( transcript_id ),
- UNIQUE( stable_id, version )
+ PRIMARY KEY (transcript_id),
+ UNIQUE (stable_id, version)
+
+) COLLATE=latin1_swedish_ci TYPE=MyISAM;
-) COLLATE=latin1_swedish_ci;
################################################################################
#
@@ -466,16 +528,17 @@ CREATE TABLE transcript_stable_id (
CREATE TABLE translation (
- translation_id INT UNSIGNED NOT NULL auto_increment,
+ translation_id INT UNSIGNED NOT NULL AUTO_INCREMENT,
transcript_id INT UNSIGNED NOT NULL,
seq_start INT(10) NOT NULL, # relative to exon start
- start_exon_id INT UNSIGNED NOT NULL, # foreign key exon:exon_id
+ start_exon_id INT UNSIGNED NOT NULL,
seq_end INT(10) NOT NULL, # relative to exon start
- end_exon_id INT UNSIGNED NOT NULL, # foreign key exon:exon_id
+ end_exon_id INT UNSIGNED NOT NULL,
PRIMARY KEY (translation_id),
KEY (transcript_id)
-) COLLATE=latin1_swedish_ci;
+
+) COLLATE=latin1_swedish_ci TYPE=MyISAM;
################################################################################
@@ -484,16 +547,16 @@ CREATE TABLE translation (
#
CREATE TABLE translation_stable_id (
- translation_id INT unsigned NOT NULL, # foreign key translation:translation_id
+ translation_id INT UNSIGNED NOT NULL,
stable_id VARCHAR(128) NOT NULL,
version INT(10),
created_date DATETIME NOT NULL,
modified_date DATETIME NOT NULL,
- PRIMARY KEY( translation_id ),
- UNIQUE( stable_id, version )
+ PRIMARY KEY (translation_id),
+ UNIQUE (stable_id, version)
-) COLLATE=latin1_swedish_ci;
+) COLLATE=latin1_swedish_ci TYPE=MyISAM;
################################################################################
@@ -501,32 +564,34 @@ CREATE TABLE translation_stable_id (
# Table structure for table 'assembly'
#
# This is a denormalised golden path.
-# The data in this table defines the "static golden path", i.e. the
-# best effort draft full genome sequence as determined by the UCSC or NCBI
-# (depending which assembly you are using)
-#
-# Each row represents a component, e.g. a contig, (comp_seq_region_id,
-# FK from seq_region table) at least part of which is present in the golden path.
-# The part of the component that is in the path is delimited by fields cmp_start
-# and cmp_end (start < end), and the absolute position within the golden path
-# chromosome (or other appropriate assembled structure) (asm_seq_region_id) is
-# given by asm_start and asm_end.
-#
+#
+# The data in this table defines the "static golden path", i.e. the best effort
+# draft full genome sequence as determined by the UCSC or NCBI (depending which
+# assembly you are using).
+#
+# Each row represents a component, e.g. a contig, (comp_seq_region_id, FK from
+# seq_region table) at least part of which is present in the golden path.
+#
+# The part of the component that is in the path is delimited by fields
+# cmp_start and cmp_end (start < end), and the absolute position within the
+# golden path chromosome (or other appropriate assembled structure)
+# (asm_seq_region_id) is given by asm_start and asm_end.
CREATE TABLE assembly (
- asm_seq_region_id int unsigned NOT NULL,
- cmp_seq_region_id int(10) unsigned NOT NULL,
- asm_start int(10) NOT NULL,
- asm_end int(10) NOT NULL,
- cmp_start int(10) NOT NULL,
- cmp_end int(10) NOT NULL,
- ori tinyint NOT NULL,
+ asm_seq_region_id INT UNSIGNED NOT NULL,
+ cmp_seq_region_id INT(10) UNSIGNED NOT NULL,
+ asm_start INT(10) NOT NULL,
+ asm_end INT(10) NOT NULL,
+ cmp_start INT(10) NOT NULL,
+ cmp_end INT(10) NOT NULL,
+ ori TINYINT NOT NULL,
- KEY(cmp_seq_region_id),
- KEY(asm_seq_region_id, asm_start)
+ KEY (cmp_seq_region_id),
+ KEY (asm_seq_region_id, asm_start)
+
+) COLLATE=latin1_swedish_ci TYPE=MyISAM;
-) COLLATE=latin1_swedish_ci;
################################################################################
#
@@ -535,24 +600,25 @@ CREATE TABLE assembly (
CREATE TABLE protein_feature (
- protein_feature_id int(10) unsigned NOT NULL auto_increment,
- translation_id int NOT NULL,
- seq_start int(10) NOT NULL,
- seq_end int(10) NOT NULL,
- hit_start int(10) NOT NULL,
- hit_end int(10) NOT NULL,
- hit_id varchar(40) NOT NULL,
- analysis_id int(10) unsigned NOT NULL,
- score double NOT NULL,
- evalue double,
- perc_ident float,
-
- PRIMARY KEY (protein_feature_id),
+ protein_feature_id INT(10) UNSIGNED NOT NULL AUTO_INCREMENT,
+ translation_id INT NOT NULL,
+ seq_start INT(10) NOT NULL,
+ seq_end INT(10) NOT NULL,
+ hit_start INT(10) NOT NULL,
+ hit_end INT(10) NOT NULL,
+ hit_id VARCHAR(40) NOT NULL,
+ analysis_id INT(10) UNSIGNED NOT NULL,
+ score DOUBLE NOT NULL,
+ evalue DOUBLE,
+ perc_ident FLOAT,
+
+ PRIMARY KEY (protein_feature_id),
KEY (translation_id),
- KEY hid_index ( hit_id ),
- KEY analysis_idx( analysis_id )
+ KEY hid_index (hit_id),
+ KEY analysis_idx (analysis_id)
+
+) COLLATE=latin1_swedish_ci TYPE=MyISAM;
-) COLLATE=latin1_swedish_ci;
################################################################################
#
@@ -561,13 +627,13 @@ CREATE TABLE protein_feature (
CREATE TABLE interpro (
- interpro_ac varchar(40) NOT NULL,
- id varchar(40) NOT NULL,
+ interpro_ac VARCHAR(40) NOT NULL,
+ id VARCHAR(40) NOT NULL,
UNIQUE (interpro_ac, id),
KEY (id)
-) COLLATE=latin1_swedish_ci;
+) COLLATE=latin1_swedish_ci TYPE=MyISAM;
################################################################################
@@ -576,17 +642,18 @@ CREATE TABLE interpro (
#
CREATE TABLE karyotype (
- karyotype_id int unsigned NOT NULL auto_increment,
- seq_region_id int unsigned NOT NULL,
- seq_region_start int(10) NOT NULL,
- seq_region_end int(10) NOT NULL,
- band varchar(40) NOT NULL,
- stain varchar(40) NOT NULL,
+ karyotype_id INT UNSIGNED NOT NULL AUTO_INCREMENT,
+ seq_region_id INT UNSIGNED NOT NULL,
+ seq_region_start INT(10) NOT NULL,
+ seq_region_end INT(10) NOT NULL,
+ band VARCHAR(40) NOT NULL,
+ stain VARCHAR(40) NOT NULL,
PRIMARY KEY (karyotype_id),
KEY region_band_idx (seq_region_id,band)
-) COLLATE=latin1_swedish_ci;
+) COLLATE=latin1_swedish_ci TYPE=MyISAM;
+
################################################################################
#
@@ -595,16 +662,20 @@ CREATE TABLE karyotype (
CREATE TABLE object_xref (
- object_xref_id INT not null auto_increment,
- ensembl_id int unsigned not null,
- ensembl_object_type ENUM( 'RawContig', 'Transcript', 'Gene', 'Translation', 'regulatory_factor', 'regulatory_feature' ) not null,
- xref_id INT unsigned not null,
+ object_xref_id INT NOT NULL AUTO_INCREMENT,
+ ensembl_id INT UNSIGNED NOT NULL,
+ ensembl_object_type ENUM('RawContig', 'Transcript', 'Gene',
+ 'Translation', 'regulatory_factor',
+ 'regulatory_feature')
+ NOT NULL,
+ xref_id INT UNSIGNED NOT NULL,
+
+ UNIQUE (ensembl_object_type, ensembl_id, xref_id),
+ KEY oxref_idx (object_xref_id, xref_id, ensembl_object_type, ensembl_id),
+ KEY xref_idx (xref_id, ensembl_object_type)
- UNIQUE ( ensembl_object_type, ensembl_id, xref_id ),
- KEY oxref_idx( object_xref_id, xref_id, ensembl_object_type, ensembl_id ),
- KEY xref_idx(xref_id, ensembl_object_type)
+) COLLATE=latin1_swedish_ci TYPE=MyISAM;
-) COLLATE=latin1_swedish_ci;
################################################################################
#
@@ -612,23 +683,26 @@ CREATE TABLE object_xref (
#
CREATE TABLE identity_xref(
- object_xref_id INT unsigned not null ,
- query_identity int(5),
- target_identity int(5),
-
- hit_start int,
- hit_end int,
- translation_start int,
- translation_end int,
- cigar_line text,
-
- score double,
- evalue double,
- analysis_id int,
+
+ object_xref_id INT UNSIGNED NOT NULL ,
+ query_identity INT(5),
+ target_identity INT(5),
+
+ hit_start INT,
+ hit_end INT,
+ translation_start INT,
+ translation_end INT,
+ cigar_line TEXT,
+
+ score DOUBLE,
+ evalue DOUBLE,
+ analysis_id INT,
PRIMARY KEY (object_xref_id),
- KEY analysis_idx( analysis_id )
-) COLLATE=latin1_swedish_ci;
+ KEY analysis_idx (analysis_id)
+
+) COLLATE=latin1_swedish_ci TYPE=MyISAM;
+
################################################################################
#
@@ -637,13 +711,15 @@ CREATE TABLE identity_xref(
CREATE TABLE go_xref (
- object_xref_id int(10) unsigned DEFAULT '0' NOT NULL,
- linkage_type enum('IC', 'IDA', 'IEA', 'IEP', 'IGI', 'IMP',
- 'IPI', 'ISS', 'NAS', 'ND', 'TAS', 'NR', 'RCA') NOT NULL,
+ object_xref_id INT(10) UNSIGNED DEFAULT '0' NOT NULL,
+ linkage_type ENUM('IC', 'IDA', 'IEA', 'IEP', 'IGI', 'IMP',
+ 'IPI', 'ISS', 'NAS', 'ND', 'TAS', 'NR', 'RCA')
+ NOT NULL,
KEY (object_xref_id),
- UNIQUE(object_xref_id, linkage_type)
+ UNIQUE (object_xref_id, linkage_type)
+
+) COLLATE=latin1_swedish_ci TYPE=MyISAM;
-) COLLATE=latin1_swedish_ci;
################################################################################
#
@@ -652,21 +728,22 @@ CREATE TABLE go_xref (
CREATE TABLE xref (
- xref_id INT unsigned not null auto_increment,
- external_db_id int not null,
- dbprimary_acc VARCHAR(40) not null,
- display_label VARCHAR(128) not null,
+ xref_id INT UNSIGNED NOT NULL AUTO_INCREMENT,
+ external_db_id INT NOT NULL,
+ dbprimary_acc VARCHAR(40) NOT NULL,
+ display_label VARCHAR(128) NOT NULL,
version VARCHAR(10) DEFAULT '' NOT NULL,
description VARCHAR(255),
info_type ENUM('PROJECTION', 'MISC'),
info_text VARCHAR(255),
- PRIMARY KEY( xref_id ),
- UNIQUE KEY id_index( dbprimary_acc, external_db_id ),
- KEY display_index ( display_label ),
- KEY info_type_idx ( info_type )
+ PRIMARY KEY (xref_id),
+ UNIQUE KEY id_index (dbprimary_acc, external_db_id),
+ KEY display_index (display_label),
+ KEY info_type_idx (info_type)
+
+) COLLATE=latin1_swedish_ci TYPE=MyISAM;
-) COLLATE=latin1_swedish_ci;
################################################################################
#
@@ -675,12 +752,14 @@ CREATE TABLE xref (
CREATE TABLE external_synonym (
- xref_id INT unsigned not null,
- synonym VARCHAR(40) not null,
- PRIMARY KEY( xref_id, synonym ),
- KEY name_index( synonym )
+ xref_id INT UNSIGNED NOT NULL,
+ synonym VARCHAR(40) NOT NULL,
+
+ PRIMARY KEY (xref_id, synonym),
+ KEY name_index (synonym)
+
+) COLLATE=latin1_swedish_ci TYPE=MyISAM;
-) COLLATE=latin1_swedish_ci;
################################################################################
#
@@ -689,56 +768,67 @@ CREATE TABLE external_synonym (
CREATE TABLE external_db (
- external_db_id INT not null,
+ external_db_id INT NOT NULL,
db_name VARCHAR(27) NOT NULL,
db_release VARCHAR(40) NOT NULL,
- status ENUM ('KNOWNXREF','KNOWN','XREF','PRED','ORTH', 'PSEUDO') not null,
-
+ status ENUM('KNOWNXREF','KNOWN','XREF','PRED','ORTH',
+ 'PSEUDO')
+ NOT NULL,
dbprimary_acc_linkable BOOLEAN DEFAULT 1 NOT NULL,
display_label_linkable BOOLEAN DEFAULT 0 NOT NULL,
-
priority INT NOT NULL,
-
db_display_name VARCHAR(255),
- PRIMARY KEY( external_db_id )
+ PRIMARY KEY (external_db_id)
-) COLLATE=latin1_swedish_ci;
+) COLLATE=latin1_swedish_ci TYPE=MyISAM;
+################################################################################
+#
+# Table structure for table 'prediction_exon'
+#
CREATE TABLE prediction_exon (
- prediction_exon_id int unsigned not null auto_increment,
- prediction_transcript_id int unsigned not null,
- exon_rank smallint unsigned not null,
- seq_region_id int unsigned not null,
- seq_region_start int unsigned not null,
- seq_region_end int unsigned not null,
- seq_region_strand tinyint not null,
- start_phase tinyint not null,
- score double,
- p_value double,
-
- PRIMARY KEY( prediction_exon_id ),
- KEY (prediction_transcript_id),
- KEY ( seq_region_id, seq_region_start )
-) COLLATE=latin1_swedish_ci;
+
+ prediction_exon_id INT UNSIGNED NOT NULL AUTO_INCREMENT,
+ prediction_transcript_id INT UNSIGNED NOT NULL,
+ exon_rank SMALLINT UNSIGNED NOT NULL,
+ seq_region_id INT UNSIGNED NOT NULL,
+ seq_region_start INT UNSIGNED NOT NULL,
+ seq_region_end INT UNSIGNED NOT NULL,
+ seq_region_strand TINYINT NOT NULL,
+ start_phase TINYINT NOT NULL,
+ score DOUBLE,
+ p_value DOUBLE,
+
+ PRIMARY KEY (prediction_exon_id),
+ KEY (prediction_transcript_id),
+ KEY (seq_region_id, seq_region_start)
+
+) COLLATE=latin1_swedish_ci TYPE=MyISAM;
+################################################################################
+#
+# Table structure for table 'prediction_transcript'
+#
+
CREATE TABLE prediction_transcript (
- prediction_transcript_id int unsigned not null auto_increment,
- seq_region_id int unsigned not null,
- seq_region_start int unsigned not null,
- seq_region_end int unsigned not null,
- seq_region_strand tinyint not null,
- analysis_id int,
- display_label varchar(255),
-
- PRIMARY KEY( prediction_transcript_id ),
- KEY ( seq_region_id, seq_region_start ),
- KEY analysis_idx( analysis_id )
-) COLLATE=latin1_swedish_ci;
+ prediction_transcript_id INT UNSIGNED NOT NULL AUTO_INCREMENT,
+ seq_region_id INT UNSIGNED NOT NULL,
+ seq_region_start INT UNSIGNED NOT NULL,
+ seq_region_end INT UNSIGNED NOT NULL,
+ seq_region_strand TINYINT NOT NULL,
+ analysis_id INT,
+ display_label VARCHAR(255),
+
+ PRIMARY KEY (prediction_transcript_id),
+ KEY (seq_region_id, seq_region_start),
+ KEY analysis_idx (analysis_id)
+
+) COLLATE=latin1_swedish_ci TYPE=MyISAM;
################################################################################
@@ -748,36 +838,37 @@ CREATE TABLE prediction_transcript (
CREATE TABLE meta (
- meta_id INT not null auto_increment,
- meta_key varchar( 40 ) not null,
- meta_value varchar( 255 ) not null,
+ meta_id INT NOT NULL AUTO_INCREMENT,
+ meta_key VARCHAR(40) NOT NULL,
+ meta_value VARCHAR(255) NOT NULL,
- PRIMARY KEY( meta_id ),
- KEY meta_key_index ( meta_key ),
- KEY meta_value_index ( meta_value )
+ PRIMARY KEY (meta_id),
+ KEY meta_key_index (meta_key),
+ KEY meta_value_index (meta_value)
-) COLLATE=latin1_swedish_ci;
+) COLLATE=latin1_swedish_ci TYPE=MyISAM;
-# Auto add schema version to database
+# Auto add schema version to database
INSERT INTO meta (meta_key, meta_value) VALUES ("schema_version", "38");
+
################################################################################
#
# Table structure for table 'marker_synonym'
CREATE TABLE marker_synonym (
- marker_synonym_id int unsigned not null auto_increment,
- marker_id int unsigned not null, # foreign key marker:marker_id
- source varchar(20),
- name varchar(30),
+ marker_synonym_id INT UNSIGNED NOT NULL AUTO_INCREMENT,
+ marker_id INT UNSIGNED NOT NULL,
+ source VARCHAR(20),
+ name VARCHAR(30),
PRIMARY KEY (marker_synonym_id),
KEY marker_synonym_idx (marker_synonym_id, name),
KEY marker_idx (marker_id)
-) COLLATE=latin1_swedish_ci;
+) COLLATE=latin1_swedish_ci TYPE=MyISAM;
################################################################################
@@ -786,19 +877,20 @@ CREATE TABLE marker_synonym (
CREATE TABLE marker (
- marker_id int unsigned not null auto_increment,
- display_marker_synonym_id int unsigned, #foreign key marker_synonym:marker_synonym_id
- left_primer varchar(100) not null,
- right_primer varchar(100) not null,
- min_primer_dist int(10) unsigned not null,
- max_primer_dist int(10) unsigned not null,
- priority int,
- type enum('est', 'microsatellite'),
+ marker_id INT UNSIGNED NOT NULL AUTO_INCREMENT,
+ display_marker_synonym_id INT UNSIGNED,
+ left_primer VARCHAR(100) NOT NULL,
+ right_primer VARCHAR(100) NOT NULL,
+ min_primer_dist INT(10) UNSIGNED NOT NULL,
+ max_primer_dist INT(10) UNSIGNED NOT NULL,
+ priority INT,
+ type ENUM('est', 'microsatellite'),
PRIMARY KEY (marker_id),
KEY marker_idx (marker_id, priority)
-) COLLATE=latin1_swedish_ci;
+) COLLATE=latin1_swedish_ci TYPE=MyISAM;
+
################################################################################
#
@@ -806,37 +898,39 @@ CREATE TABLE marker (
CREATE TABLE marker_feature (
- marker_feature_id int unsigned not null auto_increment,
- marker_id int unsigned not null, #foreign key marker:marker_id
- seq_region_id int(10) unsigned NOT NULL, #foreign key contig:seq_region_id
- seq_region_start int(10) unsigned NOT NULL,
- seq_region_end int(10) unsigned NOT NULL,
- analysis_id int(10) unsigned NOT NULL, #foreign key analysis:analysis_id
- map_weight int(10) unsigned,
+ marker_feature_id INT UNSIGNED NOT NULL AUTO_INCREMENT,
+ marker_id INT UNSIGNED NOT NULL,
+ seq_region_id INT(10) UNSIGNED NOT NULL,
+ seq_region_start INT(10) UNSIGNED NOT NULL,
+ seq_region_end INT(10) UNSIGNED NOT NULL,
+ analysis_id INT(10) UNSIGNED NOT NULL,
+ map_weight INT(10) UNSIGNED,
PRIMARY KEY (marker_feature_id),
- KEY seq_region_idx (seq_region_id, seq_region_start ),
- KEY analysis_idx( analysis_id )
+ KEY seq_region_idx (seq_region_id, seq_region_start),
+ KEY analysis_idx (analysis_id)
-) COLLATE=latin1_swedish_ci;
+) COLLATE=latin1_swedish_ci TYPE=MyISAM;
+
################################################################################
#
# Table structure for table 'marker_map_location'
CREATE TABLE marker_map_location (
- marker_id int unsigned not null, #foreign key marker:marker_id
- map_id int unsigned not null, #foreign key map:map_id
- chromosome_name varchar(15) not null,
- marker_synonym_id int unsigned not null, #foreign key marker_synonym:marker_synonym_id
- position varchar(15) not null,
- lod_score double,
+ marker_id INT UNSIGNED NOT NULL,
+ map_id INT UNSIGNED NOT NULL,
+ chromosome_name VARCHAR(15) NOT NULL,
+ marker_synonym_id INT UNSIGNED NOT NULL,
+ position VARCHAR(15) NOT NULL,
+ lod_score DOUBLE,
PRIMARY KEY (marker_id, map_id),
- KEY map_idx( map_id, chromosome_name, position)
+ KEY map_idx (map_id, chromosome_name, position)
+
+) COLLATE=latin1_swedish_ci TYPE=MyISAM;
-) COLLATE=latin1_swedish_ci;
################################################################################
#
@@ -844,11 +938,13 @@ CREATE TABLE marker_map_location (
CREATE TABLE map (
- map_id int unsigned not null auto_increment,
- map_name varchar(30) not null,
+ map_id INT UNSIGNED NOT NULL AUTO_INCREMENT,
+ map_name VARCHAR(30) NOT NULL,
PRIMARY KEY (map_id)
-) COLLATE=latin1_swedish_ci;
+
+) COLLATE=latin1_swedish_ci TYPE=MyISAM;
+
################################################################################
#
@@ -857,14 +953,14 @@ CREATE TABLE map (
CREATE TABLE misc_feature (
- misc_feature_id int(10) unsigned NOT NULL auto_increment,
- seq_region_id int(10) unsigned NOT NULL default '0',
- seq_region_start int(10) unsigned NOT NULL default '0',
- seq_region_end int(10) unsigned NOT NULL default '0',
- seq_region_strand tinyint(4) NOT NULL default '0',
+ misc_feature_id INT(10) UNSIGNED NOT NULL AUTO_INCREMENT,
+ seq_region_id INT(10) UNSIGNED NOT NULL default '0',
+ seq_region_start INT(10) UNSIGNED NOT NULL default '0',
+ seq_region_end INT(10) UNSIGNED NOT NULL default '0',
+ seq_region_strand TINYINT(4) NOT NULL default '0',
PRIMARY KEY (misc_feature_id),
- KEY seq_region_idx( seq_region_id, seq_region_start )
+ KEY seq_region_idx (seq_region_id, seq_region_start)
) COLLATE=latin1_swedish_ci TYPE=MyISAM;
@@ -875,26 +971,31 @@ CREATE TABLE misc_feature (
#
CREATE TABLE misc_attrib (
- misc_feature_id int(10) unsigned NOT NULL default '0',
- attrib_type_id smallint(5) unsigned NOT NULL default '0',
- value varchar(255) NOT NULL default '',
- KEY type_val_idx( attrib_type_id, value ),
- KEY misc_feature_idx( misc_feature_id )
+ misc_feature_id INT(10) UNSIGNED NOT NULL default '0',
+ attrib_type_id SMALLINT(5) UNSIGNED NOT NULL default '0',
+ value VARCHAR(255) NOT NULL default '',
+
+ KEY type_val_idx (attrib_type_id, value),
+ KEY misc_feature_idx (misc_feature_id)
+
) COLLATE=latin1_swedish_ci TYPE=MyISAM;
+
################################################################################
#
# Table structure for table 'translation_attrib'
#
CREATE TABLE translation_attrib (
- translation_id int(10) unsigned NOT NULL default '0',
- attrib_type_id smallint(5) unsigned NOT NULL default '0',
- value varchar(255) NOT NULL default '',
- KEY type_val_idx( attrib_type_id, value ),
- KEY translation_idx( translation_id )
+ translation_id INT(10) UNSIGNED NOT NULL default '0',
+ attrib_type_id SMALLINT(5) UNSIGNED NOT NULL default '0',
+ value VARCHAR(255) NOT NULL default '',
+
+ KEY type_val_idx (attrib_type_id, value),
+ KEY translation_idx (translation_id)
+
) COLLATE=latin1_swedish_ci TYPE=MyISAM;
################################################################################
@@ -903,26 +1004,31 @@ CREATE TABLE translation_attrib (
#
CREATE TABLE transcript_attrib (
- transcript_id int(10) unsigned NOT NULL default '0',
- attrib_type_id smallint(5) unsigned NOT NULL default '0',
- value varchar(255) NOT NULL default '',
- KEY type_val_idx( attrib_type_id, value ),
- KEY transcript_idx( transcript_id )
+ transcript_id INT(10) UNSIGNED NOT NULL default '0',
+ attrib_type_id SMALLINT(5) UNSIGNED NOT NULL default '0',
+ value VARCHAR(255) NOT NULL default '',
+
+ KEY type_val_idx (attrib_type_id, value),
+ KEY transcript_idx (transcript_id)
+
) COLLATE=latin1_swedish_ci TYPE=MyISAM;
+
################################################################################
#
# Table structure for table 'gene_attrib'
#
CREATE TABLE gene_attrib (
- gene_id int(10) unsigned NOT NULL default '0',
- attrib_type_id smallint(5) unsigned NOT NULL default '0',
- value varchar(255) NOT NULL default '',
- KEY type_val_idx( attrib_type_id, value ),
- KEY gene_idx( gene_id )
+ gene_id INT(10) UNSIGNED NOT NULL default '0',
+ attrib_type_id SMALLINT(5) UNSIGNED NOT NULL default '0',
+ value VARCHAR(255) NOT NULL default '',
+
+ KEY type_val_idx (attrib_type_id, value),
+ KEY gene_idx (gene_id)
+
) COLLATE=latin1_swedish_ci TYPE=MyISAM;
@@ -932,11 +1038,12 @@ CREATE TABLE gene_attrib (
#
CREATE TABLE seq_region_attrib (
- seq_region_id int(10) unsigned NOT NULL default '0',
- attrib_type_id smallint(5) unsigned NOT NULL default '0',
- value varchar(255) NOT NULL default '',
- KEY type_val_idx( attrib_type_id, value),
+ seq_region_id INT(10) UNSIGNED NOT NULL default '0',
+ attrib_type_id SMALLINT(5) UNSIGNED NOT NULL default '0',
+ value VARCHAR(255) NOT NULL default '',
+
+ KEY type_val_idx (attrib_type_id, value),
KEY seq_region_idx (seq_region_id)
) COLLATE=latin1_swedish_ci TYPE=MyISAM;
@@ -949,16 +1056,17 @@ CREATE TABLE seq_region_attrib (
CREATE TABLE attrib_type (
- attrib_type_id smallint(5) unsigned NOT NULL auto_increment,
- code varchar(15) NOT NULL default '',
- name varchar(255) NOT NULL default '',
- description text,
+ attrib_type_id SMALLINT(5) UNSIGNED NOT NULL AUTO_INCREMENT,
+ code VARCHAR(15) NOT NULL default '',
+ name VARCHAR(255) NOT NULL default '',
+ description TEXT,
- PRIMARY KEY ( attrib_type_id),
- UNIQUE KEY c(code)
+ PRIMARY KEY (attrib_type_id),
+ UNIQUE KEY c (code)
) COLLATE=latin1_swedish_ci TYPE=MyISAM;
+
################################################################################
#
# Table structure for table 'misc_set'
@@ -966,17 +1074,18 @@ CREATE TABLE attrib_type (
CREATE TABLE misc_set (
- misc_set_id smallint(5) unsigned NOT NULL auto_increment,
- code varchar(25) NOT NULL default '',
- name varchar(255) NOT NULL default '',
- description text NOT NULL,
- max_length int unsigned not null,
+ misc_set_id SMALLINT(5) UNSIGNED NOT NULL AUTO_INCREMENT,
+ code VARCHAR(25) NOT NULL default '',
+ name VARCHAR(255) NOT NULL default '',
+ description TEXT NOT NULL,
+ max_length INT UNSIGNED NOT NULL,
PRIMARY KEY (misc_set_id),
- UNIQUE KEY c(code)
+ UNIQUE KEY c (code)
) COLLATE=latin1_swedish_ci TYPE=MyISAM;
+
################################################################################
#
# Table structure for table 'misc_feature_misc_set'
@@ -984,19 +1093,14 @@ CREATE TABLE misc_set (
CREATE TABLE misc_feature_misc_set (
- misc_feature_id int(10) unsigned NOT NULL default '0',
- misc_set_id smallint(5) unsigned NOT NULL default '0',
+ misc_feature_id INT(10) UNSIGNED NOT NULL default '0',
+ misc_set_id SMALLINT(5) UNSIGNED NOT NULL default '0',
- PRIMARY KEY ( misc_feature_id, misc_set_id ),
- KEY reverse_idx( misc_set_id, misc_feature_id )
+ PRIMARY KEY (misc_feature_id, misc_set_id),
+ KEY reverse_idx (misc_set_id, misc_feature_id)
) COLLATE=latin1_swedish_ci TYPE=MyISAM;
-################################################################################
-#
-# Tables for QTLs
-#
-################################################################################
################################################################################
#
@@ -1005,17 +1109,18 @@ CREATE TABLE misc_feature_misc_set (
CREATE TABLE qtl (
- qtl_id int unsigned auto_increment not null,
- trait varchar(255) not null,
- lod_score float,
- flank_marker_id_1 int,
- flank_marker_id_2 int,
- peak_marker_id int,
+ qtl_id INT UNSIGNED AUTO_INCREMENT NOT NULL,
+ trait VARCHAR(255) NOT NULL,
+ lod_score FLOAT,
+ flank_marker_id_1 INT,
+ flank_marker_id_2 INT,
+ peak_marker_id INT,
+
+ PRIMARY KEY (qtl_id),
+ KEY trait_idx (trait)
- PRIMARY KEY ( qtl_id ),
- KEY trait_idx( trait )
+) COLLATE=latin1_swedish_ci TYPE=MyISAM;
-) COLLATE=latin1_swedish_ci;
################################################################################
#
@@ -1024,15 +1129,16 @@ CREATE TABLE qtl (
CREATE TABLE qtl_synonym (
- qtl_synonym_id int unsigned auto_increment not null,
- qtl_id int unsigned not null,
- source_database enum("rat genome database", "ratmap") not null,
- source_primary_id varchar(255) not null,
+ qtl_synonym_id INT UNSIGNED AUTO_INCREMENT NOT NULL,
+ qtl_id INT UNSIGNED NOT NULL,
+ source_database ENUM("rat genome database", "ratmap") NOT NULL,
+ source_primary_id VARCHAR(255) NOT NULL,
PRIMARY KEY (qtl_synonym_id),
- KEY qtl_idx(qtl_id)
+ KEY qtl_idx (qtl_id)
+
+) COLLATE=latin1_swedish_ci TYPE=MyISAM;
-) COLLATE=latin1_swedish_ci;
################################################################################
#
@@ -1041,22 +1147,18 @@ CREATE TABLE qtl_synonym (
CREATE TABLE qtl_feature (
- seq_region_id int not null,
- seq_region_start int not null,
- seq_region_end int not null,
- qtl_id int not null,
- analysis_id int not null,
+ seq_region_id INT NOT NULL,
+ seq_region_start INT NOT NULL,
+ seq_region_end INT NOT NULL,
+ qtl_id INT NOT NULL,
+ analysis_id INT NOT NULL,
+
+ KEY (qtl_id),
+ KEY loc_idx (seq_region_id, seq_region_start),
+ KEY analysis_idx (analysis_id)
- KEY( qtl_id ),
- KEY loc_idx( seq_region_id, seq_region_start ),
- KEY analysis_idx( analysis_id )
-) COLLATE=latin1_swedish_ci;
+) COLLATE=latin1_swedish_ci TYPE=MyISAM;
-################################################################################
-#
-# Tables for stable ID mapping tracking
-#
-################################################################################
################################################################################
#
@@ -1065,15 +1167,20 @@ CREATE TABLE qtl_feature (
CREATE TABLE mapping_session (
- mapping_session_id int(11) NOT NULL auto_increment,
- old_db_name varchar(80) NOT NULL default '',
- new_db_name varchar(80) NOT NULL default '',
- created timestamp(14) NOT NULL,
+ mapping_session_id INT(11) NOT NULL AUTO_INCREMENT,
+ old_db_name VARCHAR(80) NOT NULL default '',
+ new_db_name VARCHAR(80) NOT NULL default '',
+ old_release VARCHAR(5) NOT NULL default '',
+ new_release VARCHAR(5) NOT NULL default '',
+ old_assembly VARCHAR(20) NOT NULL default '',
+ new_assembly VARCHAR(20) NOT NULL default '',
+ created_date DATETIME NOT NULL,
- PRIMARY KEY (mapping_session_id)
+ PRIMARY KEY (mapping_session_id)
) COLLATE=latin1_swedish_ci TYPE=MyISAM;
+
################################################################################
#
# Table structure for table 'stable_id_event'
@@ -1081,20 +1188,22 @@ CREATE TABLE mapping_session (
CREATE TABLE stable_id_event (
- old_stable_id varchar(128),
- old_version smallint,
- new_stable_id varchar(128),
- new_version smallint,
- mapping_session_id int(11) NOT NULL default '0',
- type ENUM('gene', 'transcript', 'translation') NOT NULL,
+ old_stable_id VARCHAR(128),
+ old_version SMALLINT,
+ new_stable_id VARCHAR(128),
+ new_version SMALLINT,
+ mapping_session_id INT(11) NOT NULL default '0',
+ type ENUM('gene', 'transcript', 'translation') NOT NULL,
- UNIQUE KEY uni_idx (mapping_session_id, old_stable_id, old_version, new_stable_id, new_version, type),
+ UNIQUE KEY uni_idx (mapping_session_id, old_stable_id, old_version,
+ new_stable_id, new_version, type),
KEY new_idx (new_stable_id),
KEY old_idx (old_stable_id)
) COLLATE=latin1_swedish_ci TYPE=MyISAM;
+
################################################################################
#
# Table structure for table 'gene_archive'
@@ -1103,20 +1212,21 @@ CREATE TABLE stable_id_event (
CREATE TABLE gene_archive (
gene_stable_id VARCHAR(128) NOT NULL,
- gene_version smallint NOT NULL,
+ gene_version SMALLINT NOT NULL,
transcript_stable_id VARCHAR(128) NOT NULL,
- transcript_version smallint NOT NULL,
+ transcript_version SMALLINT NOT NULL,
translation_stable_id VARCHAR(128) NOT NULL,
- translation_version smallint NOT NULL,
- peptide_archive_id int NOT NULL,
- mapping_session_id int NOT NULL,
+ translation_version SMALLINT NOT NULL,
+ peptide_archive_id INT NOT NULL,
+ mapping_session_id INT NOT NULL,
- KEY gene_idx( gene_stable_id, gene_version ),
- KEY transcript_idx( transcript_stable_id, transcript_version ),
- KEY translation_idx( translation_stable_id, translation_version )
+ KEY gene_idx (gene_stable_id, gene_version),
+ KEY transcript_idx (transcript_stable_id, transcript_version),
+ KEY translation_idx (translation_stable_id, translation_version)
) COLLATE=latin1_swedish_ci TYPE=MyISAM;
+
################################################################################
#
# Table structure for table 'peptide_archive'
@@ -1126,13 +1236,14 @@ CREATE TABLE peptide_archive (
peptide_archive_id INT NOT NULL AUTO_INCREMENT,
md5_checksum char(32),
- peptide_seq mediumtext NOT NULL,
+ peptide_seq MEDIUMTEXT NOT NULL,
- PRIMARY KEY( peptide_archive_id ),
- KEY checksum( md5_checksum )
+ PRIMARY KEY (peptide_archive_id),
+ KEY checksum (md5_checksum)
) COLLATE=latin1_swedish_ci TYPE=MyISAM;
+
################################################################################
#
# Table structure for table 'seq_region'
@@ -1145,9 +1256,9 @@ CREATE TABLE seq_region (
coord_system_id INT(10) NOT NULL,
length INT(10) NOT NULL,
- UNIQUE(coord_system_id, name),
+ UNIQUE (coord_system_id, name),
PRIMARY KEY (seq_region_id),
- KEY name_idx(name)
+ KEY name_idx (name)
) COLLATE=latin1_swedish_ci TYPE=MyISAM;
@@ -1170,12 +1281,12 @@ CREATE TABLE assembly_exception (
ori INT NOT NULL,
PRIMARY KEY (assembly_exception_id),
-
KEY sr_idx (seq_region_id, seq_region_start),
KEY ex_idx (exc_seq_region_id, exc_seq_region_start)
) COLLATE=latin1_swedish_ci TYPE=MyISAM;
+
################################################################################
#
# Table structure for table 'coord_system'
@@ -1183,18 +1294,19 @@ CREATE TABLE assembly_exception (
CREATE TABLE coord_system (
- coord_system_id INT NOT NULL auto_increment,
+ coord_system_id INT NOT NULL AUTO_INCREMENT,
name VARCHAR(40) NOT NULL,
version VARCHAR(40),
rank INT NOT NULL,
- attrib SET ('default_version', 'sequence_level'),
+ attrib SET('default_version', 'sequence_level'),
- UNIQUE(name, version),
- UNIQUE(rank),
+ UNIQUE (name, version),
+ UNIQUE (rank),
PRIMARY KEY (coord_system_id)
) COLLATE=latin1_swedish_ci TYPE=MyISAM;
+
################################################################################
#
# Table structure for table 'meta_coord'
@@ -1211,34 +1323,46 @@ CREATE TABLE meta_coord (
) COLLATE=latin1_swedish_ci TYPE=MyISAM;
+################################################################################
+#
+# Table structure for table 'density_feature'
+#
CREATE TABLE density_feature (
- density_feature_id INT NOT NULL auto_increment,
- density_type_id INT NOT NULL, #FK refs density_type
- seq_region_id INT NOT NULL, #FK refs seq_region
+
+ density_feature_id INT NOT NULL AUTO_INCREMENT,
+ density_type_id INT NOT NULL,
+ seq_region_id INT NOT NULL,
seq_region_start INT NOT NULL,
seq_region_end INT NOT NULL,
density_value FLOAT NOT NULL,
- PRIMARY KEY(density_feature_id),
+ PRIMARY KEY (density_feature_id),
KEY seq_region_idx (density_type_id, seq_region_id, seq_region_start),
KEY seq_region_id_idx (seq_region_id)
) COLLATE=latin1_swedish_ci TYPE=MyISAM;
+################################################################################
+#
+# Table structure for table 'density_type'
+#
CREATE TABLE density_type (
- density_type_id INT NOT NULL auto_increment,
- analysis_id INT NOT NULL, #FK refs analysis
+
+ density_type_id INT NOT NULL AUTO_INCREMENT,
+ analysis_id INT NOT NULL,
block_size INT NOT NULL,
region_features INT NOT NULL,
value_type ENUM('sum','ratio') NOT NULL,
- PRIMARY KEY(density_type_id),
- UNIQUE(analysis_id, block_size, region_features)
+
+ PRIMARY KEY (density_type_id),
+ UNIQUE (analysis_id, block_size, region_features)
) COLLATE=latin1_swedish_ci TYPE=MyISAM;
+
################################################################################
#
# Table structure for table 'regulatory_feature'
@@ -1247,22 +1371,22 @@ CREATE TABLE density_type (
CREATE TABLE regulatory_feature (
- regulatory_feature_id INT NOT NULL auto_increment,
- name VARCHAR(255) NOT NULL,
- seq_region_id INT NOT NULL, # FK refs seq_region
- seq_region_start INT NOT NULL,
- seq_region_end INT NOT NULL,
- seq_region_strand TINYINT NOT NULL,
- analysis_id INT NOT NULL, # FK refs analysis
- regulatory_factor_id INT, # FK refs regulatory_factor
-
+ regulatory_feature_id INT NOT NULL AUTO_INCREMENT,
+ name VARCHAR(255) NOT NULL,
+ seq_region_id INT NOT NULL,
+ seq_region_start INT NOT NULL,
+ seq_region_end INT NOT NULL,
+ seq_region_strand TINYINT NOT NULL,
+ analysis_id INT NOT NULL,
+ regulatory_factor_id INT,
- PRIMARY KEY(regulatory_feature_id),
- KEY seq_region_idx(seq_region_id, analysis_id, seq_region_start),
- KEY seq_region_idx_2(seq_region_id, seq_region_start)
+ PRIMARY KEY (regulatory_feature_id),
+ KEY seq_region_idx (seq_region_id, analysis_id, seq_region_start),
+ KEY seq_region_idx_2 (seq_region_id, seq_region_start)
) COLLATE=latin1_swedish_ci TYPE=MyISAM;
+
################################################################################
#
# Table structure for table 'regulatory_factor'
@@ -1270,14 +1394,16 @@ CREATE TABLE regulatory_feature (
CREATE TABLE regulatory_factor (
- regulatory_factor_id INT NOT NULL auto_increment,
+ regulatory_factor_id INT NOT NULL AUTO_INCREMENT,
name VARCHAR(255) NOT NULL,
- type ENUM('miRNA_target', 'transcription_factor', 'transcription_factor_complex'),
+ type ENUM('miRNA_target', 'transcription_factor',
+ 'transcription_factor_complex'),
- PRIMARY KEY(regulatory_factor_id)
+ PRIMARY KEY (regulatory_factor_id)
) COLLATE=latin1_swedish_ci TYPE=MyISAM;
+
################################################################################
#
# Table structure for table 'regulatory_feature_object'
@@ -1286,11 +1412,11 @@ CREATE TABLE regulatory_factor (
CREATE TABLE regulatory_feature_object (
- regulatory_feature_id INT NOT NULL, # FK to regulatory_feature
- ensembl_object_type ENUM( 'Transcript', 'Translation', 'Gene') NOT NULL,
- ensembl_object_id INT NOT NULL, # FK to transcript,gene etc
- influence ENUM('positive', 'negative', 'mixed', 'unknown'),
- evidence VARCHAR(255),
+ regulatory_feature_id INT NOT NULL,
+ ensembl_object_type ENUM('Transcript', 'Translation', 'Gene') NOT NULL,
+ ensembl_object_id INT NOT NULL, # FK to transcript,gene etc
+ influence ENUM('positive', 'negative', 'mixed', 'unknown'),
+ evidence VARCHAR(255),
KEY regulatory_feature_idx (regulatory_feature_id),
KEY ensembl_object_idx (ensembl_object_type, ensembl_object_id)
@@ -1306,9 +1432,9 @@ CREATE TABLE regulatory_feature_object (
CREATE TABLE regulatory_factor_coding (
- regulatory_factor_id INT NOT NULL, # FK to regulatory_factor
- transcript_id INT, # FK to transcript
- gene_id INT, # FK to gene
+ regulatory_factor_id INT NOT NULL,
+ transcript_id INT,
+ gene_id INT,
KEY transcript_idx (transcript_id),
KEY gene_idx (gene_id),
@@ -1316,6 +1442,7 @@ CREATE TABLE regulatory_factor_coding (
) COLLATE=latin1_swedish_ci TYPE=MyISAM;
+
################################################################################
#
# Table structure for table 'regulatory_search_region'
@@ -1324,24 +1451,26 @@ CREATE TABLE regulatory_factor_coding (
CREATE TABLE regulatory_search_region (
- regulatory_search_region_id INT NOT NULL auto_increment,
- name VARCHAR(255) NOT NULL,
- seq_region_id INT NOT NULL, # FK refs seq_region
- seq_region_start INT NOT NULL,
- seq_region_end INT NOT NULL,
- seq_region_strand TINYINT NOT NULL,
- ensembl_object_type ENUM( 'Transcript', 'Translation', 'Gene') NOT NULL,
- ensembl_object_id INT, # FK to gene/transcript/translation
- analysis_id INT NOT NULL, # FK to analysis
+ regulatory_search_region_id INT NOT NULL AUTO_INCREMENT,
+ name VARCHAR(255) NOT NULL,
+ seq_region_id INT NOT NULL,
+ seq_region_start INT NOT NULL,
+ seq_region_end INT NOT NULL,
+ seq_region_strand TINYINT NOT NULL,
+ ensembl_object_type ENUM('Transcript', 'Translation', 'Gene')
+ NOT NULL,
+ ensembl_object_id INT, # FK to gene/transcript/translation
+ analysis_id INT NOT NULL,
PRIMARY KEY (regulatory_search_region_id),
KEY rsr_idx (regulatory_search_region_id),
KEY ensembl_object_idx (ensembl_object_type, ensembl_object_id),
- KEY seq_region_idx(seq_region_id, seq_region_start),
- KEY seq_region_idx_2(seq_region_id, seq_region_start)
+ KEY seq_region_idx (seq_region_id, seq_region_start),
+ KEY seq_region_idx_2 (seq_region_id, seq_region_start)
) COLLATE=latin1_swedish_ci TYPE=MyISAM;
+
################################################################################
#
# Table structure for table 'unmapped_object'
@@ -1358,15 +1487,18 @@ CREATE TABLE unmapped_object (
unmapped_reason_id SMALLINT(5) UNSIGNED NOT NULL,
query_score DOUBLE,
target_score DOUBLE,
- ensembl_id INT(10) unsigned default '0',
- ensembl_object_type ENUM('RawContig','Transcript','Gene','Translation') collate latin1_bin default 'RawContig',
- PRIMARY KEY ( unmapped_object_id ),
- KEY id_idx( identifier ),
- KEY anal_idx( analysis_id ),
- KEY anal_exdb_idx( analysis_id, external_db_id)
+ ensembl_id INT(10) UNSIGNED default '0',
+ ensembl_object_type ENUM('RawContig','Transcript','Gene','Translation')
+ default 'RawContig',
+
+ PRIMARY KEY (unmapped_object_id),
+ KEY id_idx (identifier),
+ KEY anal_idx (analysis_id),
+ KEY anal_exdb_idx (analysis_id, external_db_id)
) COLLATE=latin1_swedish_ci TYPE=MyISAM;
+
################################################################################
#
# Table structure for table 'unmapped_reason'
@@ -1379,6 +1511,7 @@ CREATE TABLE unmapped_reason (
summary_description VARCHAR(255),
full_description VARCHAR(255),
- PRIMARY KEY ( unmapped_reason_id )
+ PRIMARY KEY (unmapped_reason_id)
) COLLATE=latin1_swedish_ci TYPE=MyISAM;
+
--
GitLab