First version of get_popular_organism (list + counts)

src/ensembl/production/metadata/api/genome.py

@@ -9,15 +9,15 @@
 #   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.
-import sqlalchemy as db
+import logging
 
+import sqlalchemy as db
+from sqlalchemy.orm import aliased
 from ensembl.database import DBConnection
 from ensembl.ncbi_taxonomy.models import NCBITaxaName
-
 from ensembl.production.metadata.api.base import BaseAdaptor, check_parameter
 from ensembl.production.metadata.api.models import Genome, Organism, Assembly, OrganismGroup, OrganismGroupMember, \
     GenomeRelease, EnsemblRelease, EnsemblSite, AssemblySequence, GenomeDataset, Dataset, DatasetType, DatasetSource
-import logging
 
 logger = logging.getLogger(__name__)
 
@@ -340,3 +340,41 @@ def fetch_genomes_info(
                 yield [{'genome': genome, 'datasets': dataset}]
         except Exception as e:
             raise ValueError(str(e))
+
+    def fetch_organisms_group_counts(self, release_version=None, group_code='popular'):
+        o_species = aliased(Organism)
+        o = aliased(Organism)
+        if not release_version:
+            # Get latest released organisms
+            query = db.select(
+                o_species.species_taxonomy_id,
+                o_species.ensembl_name,
+                o_species.common_name,
+                o_species.scientific_name,
+                OrganismGroupMember.order.label('order'),
+                db.func.count().label('count')
+            )
+
+            query = query.join(o, o_species.species_taxonomy_id == o.species_taxonomy_id)
+            query = query.join(Genome, o.organism_id == Genome.organism_id)
+            query = query.join(Assembly, Genome.assembly_id == Assembly.assembly_id)
+            query = query.join(OrganismGroupMember, o_species.organism_id == OrganismGroupMember.organism_id)
+            query = query.join(OrganismGroup,
+                               OrganismGroupMember.organism_group_id == OrganismGroup.organism_group_id)
+            query = query.filter(OrganismGroup.code == group_code)
+            query = query.group_by(
+                o_species.species_taxonomy_id,
+                o_species.ensembl_name,
+                o_species.common_name,
+                o_species.scientific_name,
+                OrganismGroupMember.order
+            )
+            query = query.order_by(OrganismGroupMember.order)
+        else:
+            # change group to release_version_state and related genomes
+            raise NotImplementedError('Not implemented yet')
+            pass
+
+        with self.metadata_db.session_scope() as session:
+            # TODO check if we should return a dictionary instead
+            return session.execute(query).all()

src/ensembl/production/metadata/api/sample/ensembl_metadata/assembly.txt

@@ -5,3 +5,4 @@
 5	ec1c4b53-c2ef-431c-ad0e-b2aef19b44f1	\N	GCA_900519105.1	chromosome	\N	IWGSC	\N	IWGSC	\N	2023-05-12 13:32:36	IWGSC	\N	0	\N
 6	7e8ed3a8-d724-4cba-92e1-e968719b7a18	\N	GCA_000146045.2	chromosome	\N	R64-1-1	\N	R64-1-1	\N	2023-05-12 13:32:46	R64-1-1	\N	0	\N
 7	f7de35c9-e0e8-4e81-b186-2962098d6361	\N	GCA_000002985.3	chromosome	\N	WBcel235	\N	WBcel235	\N	2023-05-12 13:32:52	WBcel235	\N	0	\N
+8	eeaaa233-151c-4848-8b85-a05a9993101e	\N	GCA_000001499.28	chromosome	1	GRCh38 t2t	\N	GRCh38 t2t	\N	2023-09-07 14:30:58	GRCh38_t2t	\N	1	\N

src/ensembl/production/metadata/api/sample/ensembl_metadata/genome.txt

@@ -5,3 +5,5 @@
 5	a73357ab-93e7-11ec-a39d-005056b38ce3	5	4	2023-05-12 13:32:36
 6	a733574a-93e7-11ec-a39d-005056b38ce3	6	5	2023-05-12 13:32:46
 7	a733550b-93e7-11ec-a39d-005056b38ce3	7	6	2023-05-12 13:32:52
+8	a7335667-93e7-11ec-a39d-00aasab38ce3	8	1	2023-09-07 16:30:58
+

src/ensembl/production/metadata/api/sample/ensembl_metadata/organism.txt

@@ -4,3 +4,4 @@
 4	d64c34ca-b37a-476b-83b5-f21d07a3ae67	4565	4565	Triticum aestivum	reference (Chinese spring)	Triticum aestivum	Triticum_aestivum	triticum_aestivum	\N
 5	0dc46f87-0b61-403a-8cd3-86b7e0cce8f0	559292	4932	Saccharomyces cerevisiae	S288C	Saccharomyces cerevisiae S288c	Saccharomyces_cerevisiae	saccharomyces_cerevisiae	\N
 6	0f4aad7b-db15-4a72-af1e-82bbae54226	6239	6239	Caenorhabditis elegans (PRJNA13758)	N2	Caenorhabditis elegans	Caenorhabditis_elegans	caenorhabditis_elegans	\N
+7	dbbsaf09-2db8-429b-a407-c15a4ca2876d	9606	9606	Human T2T	\N	Homo sapiens	Homo_sapiens	homo_sapiens_t2t	\N

src/ensembl/production/metadata/api/sample/ensembl_metadata/organism_group.txt

@@ -3,4 +3,5 @@
 3	Division	EnsemblProtists	protists
 4	Division	EnsemblPlants	plants
 5	Division	EnsemblFungi	fungi
-6	Division	EnsemblMetazoa	metazoa
+6	Division	EnsemblMetazoa	metazoa
+7	Internal	Popular Species	popular

src/ensembl/production/metadata/api/sample/ensembl_metadata/organism_group_member.txt

@@ -3,4 +3,10 @@
 3	0	\N	3	3
 4	0	\N	4	4
 5	0	\N	5	5
-6	0	\N	6	6
+6	0	\N	6	6
+7	0	1	7	1
+8	0	2	7	2
+9	0	3	7	3
+10	0	4	7	4
+11	0	5	7	5
+12	0	6	7	6

src/tests/test_api.py

@@ -162,3 +162,15 @@ def test_fetch_genome_info(self, multi_dbs):
     #     test = conn.fetch_genomes_info(genome_uuid=uuid)
     #     assert test['genome'][0].genome_uuid == uuid
     #     assert test['datasets'][0][0].genome_uuid == uuid
+
+    def test_popular_species(self, multi_dbs):
+        conn = GenomeAdaptor(metadata_uri=multi_dbs['ensembl_metadata'].dbc.url,
+                             taxonomy_uri=multi_dbs['ncbi_taxonomy'].dbc.url)
+        test = conn.fetch_organisms_group_counts()
+        # First result should be Human
+        assert test[0][2] == 'Human'
+        # We should have three assemblies associated with Human (Two for grch37.38 organism + one t2t)
+        assert test[0][5] == 3
+        for data in test[1:]:
+            # All others have only one genome in test DB
+            assert data[5] == 1