Features/schema changes

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

@@ -10,7 +10,6 @@
 #   See the License for the specific language governing permissions and
 #   limitations under the License.
 import sqlalchemy as db
-from sqlalchemy.engine import make_url
 
 from ensembl.database import DBConnection
 from ensembl.ncbi_taxonomy.models import NCBITaxaName
@@ -28,42 +27,36 @@ def __init__(self, metadata_uri, taxonomy_uri=None):
         super().__init__(metadata_uri)
         self.taxonomy_db = DBConnection(taxonomy_uri)
 
-    def fetch_taxonomy_names(self, taxonomy_ids):
+    def fetch_taxonomy_names(self, taxonomy_ids, synonyms=[]):
 
         taxonomy_ids = check_parameter(taxonomy_ids)
+        synonyms = [
+            "common name",
+            "equivalent name",
+            "genbank synonym",
+            "synonym",
+        ] if len(check_parameter(synonyms)) == 0 else synonyms
+        required_class_name = ["genbank common name", "scientific name"]
         taxons = {}
-        for tid in taxonomy_ids:
-            names = {"scientific_name": None, "synonym": []}
-            taxons[tid] = names
-        for taxon in taxons:
-            sci_name_select = db.select(
-                NCBITaxaName.name
-            ).filter(
-                NCBITaxaName.taxon_id == taxon,
-                NCBITaxaName.name_class == "scientific name",
-            )
-            synonym_class = [
-                "common name",
-                "equivalent name",
-                "genbank common name",
-                "genbank synonym",
-                "synonym",
-            ]
-
-            synonyms_select = db.select(
-                NCBITaxaName.name
-            ).filter(
-                NCBITaxaName.taxon_id == taxon,
-                NCBITaxaName.name_class.in_(synonym_class),
-            )
+        with self.taxonomy_db.session_scope() as session:
+            for tid in taxonomy_ids:
+                taxons[tid] = {"scientific_name": None, "genbank_common_name": None, "synonym": []}
+
+                taxonomyname_query = db.select(
+                    NCBITaxaName.name,
+                    NCBITaxaName.name_class,
+                ).filter(
+                    NCBITaxaName.taxon_id == tid,
+                    NCBITaxaName.name_class.in_(required_class_name + synonyms),
+                )
 
-            with self.taxonomy_db.session_scope() as session:
-                sci_name = session.execute(sci_name_select).one()
-                taxons[taxon]["scientific_name"] = sci_name[0]
-                synonyms = session.execute(synonyms_select).all()
-                for synonym in synonyms:
-                    taxons[taxon]["synonym"].append(synonym[0])
-        return taxons
+                for taxon_name in session.execute(taxonomyname_query).all():
+                    if taxon_name[1] in synonyms:
+                        taxons[tid]['synonym'].append(taxon_name[0])
+                    if taxon_name[1] in required_class_name:
+                        taxon_format_name = "_".join(taxon_name[1].split(' '))
+                        taxons[tid][taxon_format_name] = taxon_name[0]
+            return taxons
 
     def fetch_taxonomy_ids(self, taxonomy_names):
         taxids = []
@@ -284,8 +277,8 @@ def fetch_genome_datasets(self, genome_id=None, genome_uuid=None, unreleased_dat
                 genome_select = genome_select.filter(Dataset.dataset_uuid.in_(dataset_uuid))
 
             if unreleased_datasets:
-                genome_select = genome_select.filter(GenomeDataset.release_id.is_(None)) \
-                    .filter(GenomeDataset.is_current == 0)
+                genome_select = genome_select.filter(GenomeDataset.release_id.is_(None))
+
             if dataset_name is not None:
                 genome_select = genome_select.filter(DatasetType.name.in_(dataset_name))
 

src/ensembl/production/metadata/api/models/assembly.py

@@ -28,11 +28,13 @@ class Assembly(Base):
     level = Column(String(32), nullable=False)
     name = Column(String(128), nullable=False)
     accession_body = Column(String(32))
-    assembly_default = Column(String(32))
+    assembly_default = Column(String(128))
     tol_id = Column(String(32), unique=True)
     created = Column(DateTime)
     ensembl_name = Column(String(255), unique=True)
     alt_accession = Column(String(16), nullable=True)
+    is_reference = Column(TINYINT(1), nullable=False)
+    url_name = Column(String(128), nullable=False)
     # One to many relationships
     # assembly_id within assembly_sequence
     assembly_sequences = relationship("AssemblySequence", back_populates="assembly", cascade="all, delete, delete-orphan")
@@ -51,10 +53,11 @@ class AssemblySequence(Base):
     assembly_id = Column(ForeignKey('assembly.assembly_id'), nullable=False, index=True)
     accession = Column(String(128), nullable=False)
     chromosomal = Column(TINYINT(1), nullable=False)
+    chromosome_rank = Column(Integer)
     length = Column(Integer, nullable=False)
     sequence_location = Column(String(10))
-    sequence_checksum = Column(String(32))
-    ga4gh_identifier = Column(String(32))
+    md5 = Column(String(32))
+    sha512t4u = Column(String(128))
     # One to many relationships
     # none
     # many to one relationships

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

@@ -63,6 +63,7 @@ class GenomeRelease(Base):
     genome_id = Column(ForeignKey("genome.genome_id"), nullable=False, index=True)
     release_id = Column(ForeignKey("ensembl_release.release_id"), nullable=False, index=True)
     is_current = Column(TINYINT(1), nullable=False)
+    is_best = Column(TINYINT(1), nullable=False)
     # One to many relationships
     # none
     # many to one relationships

src/ensembl/production/metadata/api/models/organism.py

@@ -25,23 +25,22 @@ class Organism(Base):
     organism_uuid = Column(String(128), unique=True, nullable=False, default=uuid.uuid4)
     taxonomy_id = Column(Integer, nullable=False)
     species_taxonomy_id = Column(Integer)
-    display_name = Column(String(128), nullable=False)
+    common_name = Column(String(128), nullable=False)
     strain = Column(String(128))
     scientific_name = Column(String(128))
-    url_name = Column(String(128), nullable=False)
     ensembl_name = Column(String(128), nullable=False, unique=True)
     scientific_parlance_name = Column(String(255))
     # One to many relationships
     # Organism_id to organism_group_member and genome
     genomes = relationship("Genome", back_populates="organism", cascade="all, delete, delete-orphan")
     organism_group_members = relationship("OrganismGroupMember", back_populates="organism")
-
+    strain_type = Column(String(128), nullable=True, unique=False)
     # many to one relationships
     # organim_id and taxonomy_id to taxonomy_node #DIFFERENT DATABASE
     def __repr__(self):
         return f"organism_id={self.organism_id}, taxonomy_id={self.taxonomy_id}, species_taxonomy_id={self.species_taxonomy_id}, " \
-               f"display_name={self.display_name}, strain={self.strain}, scientific_name={self.scientific_name}, " \
-               f"url_name={self.url_name}, ensembl_name={self.ensembl_name}, scientific_parlance_name={self.scientific_parlance_name}"
+               f"common_name={self.common_name}, strain={self.strain}, scientific_name={self.scientific_name}, " \
+               f"ensembl_name={self.ensembl_name}, scientific_parlance_name={self.scientific_parlance_name}"
 
 
 class OrganismGroup(Base):
@@ -74,6 +73,7 @@ class OrganismGroupMember(Base):
 
     organism_group_member_id = Column(Integer, primary_key=True)
     is_reference = Column(TINYINT(1), nullable=False)
+    order = Column(Integer, nullable=True)
     organism_id = Column(ForeignKey("organism.organism_id"), nullable=False)
     organism_group_id = Column(ForeignKey("organism_group.organism_group_id"), nullable=False, index=True)
     # One to many relationships

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

@@ -1,7 +1,7 @@
-1	eeaaa2bf-151c-4848-8b85-a05a9993101e	hg38	GCA_000001405.28	chromosome	GRCh38.p13	\N	GRCh38	\N	2023-05-12 13:30:58	GRCh38.p13	\N
-2	633034c3-2268-40a2-866a-9f492cac84bf	hg19	GCA_000001405.14	chromosome	GRCh37.p13	\N	GRCh37	\N	2023-05-12 13:32:06	GRCh37.p13	\N
-3	f78618ef-1075-47ee-a496-be26cad47912	\N	GCA_000005845.2	chromosome	ASM584v2	\N	ASM584v2	\N	2023-05-12 13:32:14	ASM584v2	\N
-4	224d836f-36a7-4c4e-b917-ecff740e404f	\N	GCA_000002765.2	chromosome	ASM276v2	\N	ASM276v2	\N	2023-05-12 13:32:25	ASM276v2	\N
-5	ec1c4b53-c2ef-431c-ad0e-b2aef19b44f1	\N	GCA_900519105.1	chromosome	IWGSC	\N	IWGSC	\N	2023-05-12 13:32:36	IWGSC	\N
-6	7e8ed3a8-d724-4cba-92e1-e968719b7a18	\N	GCA_000146045.2	chromosome	R64-1-1	\N	R64-1-1	\N	2023-05-12 13:32:46	R64-1-1	\N
-7	f7de35c9-e0e8-4e81-b186-2962098d6361	\N	GCA_000002985.3	chromosome	WBcel235	\N	WBcel235	\N	2023-05-12 13:32:52	WBcel235	\N
+1	eeaaa2bf-151c-4848-8b85-a05a9993101e	hg38	GCA_000001405.28	chromosome	1	GRCh38.p13	\N	GRCh38	\N	2023-05-12 13:30:58	GRCh38.p13	\N	1	\N
+2	633034c3-2268-40a2-866a-9f492cac84bf	hg19	GCA_000001405.14	chromosome	2	GRCh37.p13	\N	GRCh37	\N	2023-05-12 13:32:06	GRCh37.p13	\N	0	\N
+3	f78618ef-1075-47ee-a496-be26cad47912	\N	GCA_000005845.2	chromosome	\N	ASM584v2	\N	ASM584v2	\N	2023-05-12 13:32:14	ASM584v2	\N	0	\N
+4	224d836f-36a7-4c4e-b917-ecff740e404f	\N	GCA_000002765.2	chromosome	\N	ASM276v2	\N	ASM276v2	\N	2023-05-12 13:32:25	ASM276v2	\N	0	\N
+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