Merge pull request #400 from Ensembl/release/105

Release/105

lib/Bio/EnsEMBL/DataCheck/Checks/CheckHomology.pm

@@ -44,16 +44,22 @@ sub tests {
   is_one_to_many($dbc, "homology_member", "homology_id", $desc_1);
   ### Hoping for a better idea than this query (below)
   my $hideous_sql = q/
-    SELECT hm1.gene_member_id gene_member_id1, hm2.gene_member_id gene_member_id2, COUNT(*) num, 
-      GROUP_CONCAT(h1.description order by h1.description) descs 
-        FROM homology h1 
-          CROSS JOIN homology_member hm1 
-            USING (homology_id)
-          CROSS JOIN homology_member hm2 
-            USING (homology_id)
-    WHERE hm1.gene_member_id < hm2.gene_member_id
-      GROUP BY hm1.gene_member_id, hm2.gene_member_id 
-        HAVING COUNT(*) > 1
+    SELECT
+      hm1.gene_member_id gene_member_id1,
+      hm2.gene_member_id gene_member_id2,
+      COUNT(*) num,
+      GROUP_CONCAT(h1.description
+          ORDER BY h1.description) descs
+    FROM
+      homology h1
+          CROSS JOIN
+      homology_member hm1 USING (homology_id)
+          CROSS JOIN
+      homology_member hm2 USING (homology_id)
+    WHERE
+      hm1.gene_member_id < hm2.gene_member_id
+    GROUP BY h1.gene_tree_root_id, hm1.gene_member_id, hm2.gene_member_id
+    HAVING COUNT(*) > 1
   /;
 
   my $desc_2 = "There is no redundancy in homology";

lib/Bio/EnsEMBL/DataCheck/Checks/CheckOntologyTerm.pm

@@ -39,15 +39,13 @@ use constant {
 sub tests {
   my ($self) = @_;
 
-  my $desc = 'Critical terms are present in term table';
-  my @critical_terms = (
-      "'EFO:0003900'"
-  );
-  my $len = @critical_terms;
+  my @critical_terms = qw/EFO:0003900/;
 
-  my $sql = "SELECT COUNT(*) FROM term WHERE accession IN (".join(', ', @critical_terms).")";
-
-  is_rows($self->dba, $sql, $len, $desc);
+  foreach (@critical_terms) {
+    my $desc = "Critical term $_ is present in term table";
+    my $sql = "SELECT accession FROM term WHERE accession = '$_'";
+    is_rows($self->dba, $sql, 1, $desc);
+  }
 }
 
 1;

lib/Bio/EnsEMBL/DataCheck/Checks/ChromosomesAnnotated.pm

@@ -23,6 +23,7 @@ use strict;
 
 use Moose;
 use Test::More;
+use Bio::EnsEMBL::DataCheck::Test::DataCheck;
 use Bio::EnsEMBL::DataCheck::Utils qw/sql_count/;
 
 extends 'Bio::EnsEMBL::DataCheck::DbCheck';
@@ -35,7 +36,7 @@ use constant {
   TABLES         => ['attrib_type', 'coord_system', 'seq_region', 'seq_region_attrib']
 };
 
-sub skip_tests {
+sub tests {
   my ($self) = @_;
 
   my $sa = $self->dba->get_adaptor('Slice');
@@ -45,53 +46,44 @@ sub skip_tests {
 
   my @chromosomal = ('chromosome', 'chromosome_group', 'plasmid');
 
-  my $chr_count = 0;
   foreach my $cs_name (@chromosomal) {
     my $slices = $sa->fetch_all($cs_name, $cs_version);
     foreach (@$slices) {
       # seq_regions that are not genuine biological chromosomes,
       # but are instead collections of unmapped sequence,
       # have a 'chromosome' attribute - these regions do not
       # necessarily need a karyotype_rank attribute.
-      my @non_bio_chr = @{$_->get_all_Attributes('chromosome')};
-      if (! scalar(@non_bio_chr)) {
-        $chr_count++;
-      }
-    }
-  }
-
-  if ( $chr_count <= 1 ) {
-    return (1, 'Zero or one chromosomal seq_regions.');
-  }
-}
-
-sub tests {
-  my ($self) = @_;
-
-  my $sa = $self->dba->get_adaptor('Slice');
-
-  my $mca = $self->dba->get_adaptor('MetaContainer');
-  my $cs_version = $mca->single_value_by_key('assembly.default');
-
-  my @chromosomal = ('chromosome', 'chromosome_group', 'plasmid');
-
-  foreach my $cs_name (@chromosomal) {
-    my $slices = $sa->fetch_all($cs_name, $cs_version);
-    foreach (@$slices) {
       my @non_bio_chr = @{$_->get_all_Attributes('chromosome')};
       next if scalar(@non_bio_chr);
 
       my $sr_name = $_->seq_region_name;
       my $desc = "$cs_name $sr_name has 'karyotype_rank' attribute";
       ok($_->has_karyotype, $desc);
-
-      if ($sr_name =~ /^(chrM|chrMT|MT|Mito|mitochondrion_genome)$/) {
-        my $desc_mt = "$cs_name $sr_name has mitochondrial 'sequence_location' attribute";
-        my %seq_locs = map { $_->value => 1 } @{$_->get_all_Attributes('sequence_location')};
-        ok(exists $seq_locs{'mitochondrial_chromosome'}, $desc_mt);
-      }
     }
   }
+
+  $self->karyotype_rank_cardinality();
+}
+
+sub karyotype_rank_cardinality {
+  my ($self) = @_;
+
+  # This is a separate check because 'primary_assembly' regions
+  # need to be tested, as well those marked as 'chromosomes'.
+  my $desc = "Regions have only one 'karyotype_rank' attribute";
+  my $diag = "Regions with multiple 'karyotype_rank' attributes";
+  my $sql  = q/
+    SELECT seq_region_id, COUNT(*) FROM
+      seq_region_attrib sra INNER JOIN
+      attrib_type at USING (attrib_type_id)
+    WHERE
+      at.code = 'karyotype_rank'
+    GROUP BY
+      sra.seq_region_id
+    HAVING COUNT(*) > 1;
+  /;
+
+  is_rows_zero($self->dba, $sql, $desc, $diag);
 }
 
 1;

lib/Bio/EnsEMBL/DataCheck/Checks/CompareGOXref.pm

@@ -24,6 +24,7 @@ use strict;
 use Moose;
 use Test::More;
 use Bio::EnsEMBL::DataCheck::Test::DataCheck;
+use Bio::EnsEMBL::DataCheck::Utils qw(same_assembly same_geneset);
 
 extends 'Bio::EnsEMBL::DataCheck::DbCheck';
 
@@ -42,6 +43,17 @@ sub tests {
     my $old_dba = $self->get_old_dba();
 
     skip 'No old version of database', 1 unless defined $old_dba;
+
+    my $mca = $self->dba->get_adaptor('MetaContainer');
+    my $old_mca = $old_dba->get_adaptor('MetaContainer');
+
+    if (!same_assembly($mca, $old_mca)) {    
+      skip 'Current DB has different assembly', 1;
+    }
+
+    if (!same_geneset($mca, $old_mca)) {    
+      skip 'Current DB has different geneset', 1;
+    }
 
     $self->go_xref_counts($old_dba);
   }

lib/Bio/EnsEMBL/DataCheck/Checks/CompareOntologyTerm.pm

@@ -29,9 +29,9 @@ extends 'Bio::EnsEMBL::DataCheck::DbCheck';
 
 use constant {
   NAME           => 'CompareOntologyTerm',
-  DESCRIPTION    => 'Compare Term counts between current and previous ontology database',
+  DESCRIPTION    => 'Compare namespace counts between current and previous ontology database',
   GROUPS         => ['ontologies'],
-  DATACHECK_TYPE => 'critical',
+  DATACHECK_TYPE => 'advisory',
   DB_TYPES       => ['ontology'],
   TABLES         => ['ontology', 'term']
 };

lib/Bio/EnsEMBL/DataCheck/Checks/CompareOntologyTotal.pm

@@ -0,0 +1,58 @@
+=head1 LICENSE
+
+Copyright [2018-2021] EMBL-European Bioinformatics Institute
+
+Licensed under the Apache License, Version 2.0 (the 'License');
+you may not use this file except in compliance with the License.
+You may obtain a copy of the License at
+
+    http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software
+distributed under the License is distributed on an 'AS IS' BASIS,
+WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+See the License for the specific language governing permissions and
+limitations under the License.
+
+=cut
+
+package Bio::EnsEMBL::DataCheck::Checks::CompareOntologyTotal;
+
+use warnings;
+use strict;
+
+use Moose;
+use Test::More;
+use Bio::EnsEMBL::DataCheck::Test::DataCheck;
+
+extends 'Bio::EnsEMBL::DataCheck::DbCheck';
+
+use constant {
+  NAME           => 'CompareOntologyTotal',
+  DESCRIPTION    => 'Compare total counts between current and previous ontology database',
+  GROUPS         => ['ontologies'],
+  DATACHECK_TYPE => 'critical',
+  DB_TYPES       => ['ontology'],
+  TABLES         => ['ontology', 'term']
+};
+
+sub tests {
+  my ($self) = @_;
+
+  # Inherited code from DbCheck will always fail if the previous
+  # release's database cannot be found - so don't need to test
+  # for that here.
+  my $old_dba = $self->get_old_dba();
+
+  my $desc = 'Ontology term totals have not decreased in '.
+             $self->dba->dbc->dbname.' compared to '.$old_dba->dbc->dbname;
+  my $sql  = q/
+    SELECT ontology.name, COUNT(*) FROM
+      term INNER JOIN
+      ontology USING (ontology_id)
+    GROUP BY ontology.name
+  /;
+  row_subtotals($self->dba, $old_dba, $sql, undef, 1.00, $desc);
+}
+
+1;

lib/Bio/EnsEMBL/DataCheck/Checks/CompareProjectedGOXrefs.pm

@@ -24,6 +24,7 @@ use strict;
 use Moose;
 use Test::More;
 use Bio::EnsEMBL::DataCheck::Test::DataCheck;
+use Bio::EnsEMBL::DataCheck::Utils qw(same_assembly same_geneset);
 
 extends 'Bio::EnsEMBL::DataCheck::DbCheck';
 
@@ -44,6 +45,17 @@ sub tests {
 
     skip 'No old version of database', 1 unless defined $old_dba;
 
+    my $mca = $self->dba->get_adaptor('MetaContainer');
+    my $old_mca = $old_dba->get_adaptor('MetaContainer');
+
+    if (!same_assembly($mca, $old_mca)) {    
+      skip 'Current DB has different assembly', 1;
+    }
+
+    if (!same_geneset($mca, $old_mca)) {    
+      skip 'Current DB has different geneset', 1;
+    }
+
     $self->go_xref_counts($old_dba);
   }
 }

lib/Bio/EnsEMBL/DataCheck/Checks/CompareProjectedGeneNames.pm

@@ -24,6 +24,7 @@ use strict;
 use Moose;
 use Test::More;
 use Bio::EnsEMBL::DataCheck::Test::DataCheck;
+use Bio::EnsEMBL::DataCheck::Utils qw(same_assembly same_geneset);
 
 extends 'Bio::EnsEMBL::DataCheck::DbCheck';
 
@@ -44,6 +45,17 @@ sub tests {
 
     skip 'No old version of database', 1 unless defined $old_dba;
 
+    my $mca = $self->dba->get_adaptor('MetaContainer');
+    my $old_mca = $old_dba->get_adaptor('MetaContainer');
+
+    if (!same_assembly($mca, $old_mca)) {    
+      skip 'Current DB has different assembly', 1;
+    }
+
+    if (!same_geneset($mca, $old_mca)) {    
+      skip 'Current DB has different geneset', 1;
+    }
+
     $self->projected_gene_name_counts($old_dba);
   }
 }

lib/Bio/EnsEMBL/DataCheck/Checks/ControlledTablesCompara.pm

@@ -197,7 +197,7 @@ sub taxonomy_tables {
   my ($self, $helper, $tables) = @_;
 
   my $desc_1 = "Taxonomy database found";
-  my $taxonomy_dba = ($self->registry->alias_exists('multi')) ? $self->get_dba('multi', 'taxonomy') : $self->get_dba('ncbi_taxonomy', 'taxonomy');
+  my $taxonomy_dba = $self->get_dba('multi', 'taxonomy') ? $self->get_dba('multi', 'taxonomy') : $self->get_dba('ncbi_taxonomy', 'taxonomy');
 
   if (ok(defined $taxonomy_dba, $desc_1)) {
     my $taxonomy_helper = $taxonomy_dba->dbc->sql_helper;

lib/Bio/EnsEMBL/DataCheck/Checks/DisplayNameFormat.pm

@@ -0,0 +1,50 @@
+=head1 LICENSE
+
+Copyright [2018-2021] EMBL-European Bioinformatics Institute
+
+Licensed under the Apache License, Version 2.0 (the 'License');
+you may not use this file except in compliance with the License.
+You may obtain a copy of the License at
+
+    http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software
+distributed under the License is distributed on an 'AS IS' BASIS,
+WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+See the License for the specific language governing permissions and
+limitations under the License.
+
+=cut
+
+package Bio::EnsEMBL::DataCheck::Checks::DisplayNameFormat;
+
+use warnings;
+use strict;
+
+use Moose;
+use Test::More;
+
+extends 'Bio::EnsEMBL::DataCheck::DbCheck';
+
+use constant {
+  NAME        => 'DisplayNameFormat',
+  DESCRIPTION => 'For Rapid Release, the display name must be a specific format',
+  GROUPS      => ['rapid_release'],
+  DB_TYPES    => ['core'],
+  TABLES      => ['meta']
+};
+
+sub tests {
+  my ($self) = @_;
+
+  my $mca = $self->dba->get_adaptor("MetaContainer");
+
+  # Check that the format of the display name conforms to expectations.
+  my $format = '[A-Za-z0-9 ]+ \([A-Za-z0-9 ]+\) \- GCA_\d+\.\d+';
+
+  my $desc = "Display name has correct format";
+  my $display_name = $mca->single_value_by_key('species.display_name');
+  like($display_name, qr/^$format$/, $desc);
+}
+
+1;

lib/Bio/EnsEMBL/DataCheck/Checks/GeneBounds.pm

@@ -73,7 +73,8 @@ sub bounds_check {
         t.seq_region_start = 0 OR
         t.seq_region_end > sr.length
       ) AND
-      cs.species_id = $species_id
+      cs.species_id = $species_id AND
+      at.code IS NULL
   /;
   is_rows_zero($self->dba, $sql, $desc, $diag);
 }

lib/Bio/EnsEMBL/DataCheck/Checks/Karyotype.pm

@@ -57,15 +57,17 @@ sub tests {
 
   my $sa = $self->dba->get_adaptor('Slice');
 
-  my $cs_name = 'chromosome';
-
-  my $slices = $sa->fetch_all($cs_name, undef, undef, 1);
+  my $slices = $sa->fetch_all('toplevel', undef, undef, 1);
   foreach my $slice (@$slices) {
+    next unless $slice->karyotype_rank;
+
     my $sr_name = $slice->seq_region_name;
     next if $sr_name eq 'MT';
 
     my $bands = $slice->get_all_KaryotypeBands;
 
+    my $cs_name = $slice->coord_system_name;
+
     my $desc_1 = "$cs_name $sr_name has karyotype bands";
     ok(scalar(@$bands), $desc_1);