Features/uuids assembly organism

VERSION

@@ -1 +1 @@
-1.1.0
+1.1.1

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

@@ -9,6 +9,8 @@
 #   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 uuid
+
 from sqlalchemy import Column, Integer, String, DateTime, Index, ForeignKey
 from sqlalchemy.dialects.mysql import TINYINT
 from sqlalchemy.orm import relationship
@@ -20,6 +22,7 @@ class Assembly(Base):
     __tablename__ = 'assembly'
 
     assembly_id = Column(Integer, primary_key=True)
+    assembly_uuid = Column(String(128), unique=True, nullable=False, default=uuid.uuid4)
     ucsc_name = Column(String(16))
     accession = Column(String(16), nullable=False, unique=True)
     level = Column(String(32), nullable=False)

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

@@ -12,6 +12,7 @@
 from sqlalchemy import Column, Integer, String, Enum, text, ForeignKey, Index
 from sqlalchemy.dialects.mysql import DATETIME
 from sqlalchemy.orm import relationship
+import uuid
 
 from ensembl.production.metadata.api.models.base import Base
 
@@ -35,7 +36,7 @@ class Dataset(Base):
     __tablename__ = 'dataset'
 
     dataset_id = Column(Integer, primary_key=True)
-    dataset_uuid = Column(String(128), nullable=False, unique=True)
+    dataset_uuid = Column(String(128), nullable=False, unique=True, default=str(uuid.uuid4))
     dataset_type_id = Column(ForeignKey('dataset_type.dataset_type_id'), nullable=False, index=True)
     name = Column(String(128), nullable=False)
     version = Column(String(128))

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

@@ -9,6 +9,8 @@
 #   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 uuid
+
 from sqlalchemy import Column, Integer, String, ForeignKey
 from sqlalchemy.dialects.mysql import DATETIME, TINYINT
 from sqlalchemy.orm import relationship
@@ -17,54 +19,54 @@
 
 
 class Genome(Base):
-    __tablename__ = 'genome'
+    __tablename__ = "genome"
 
     genome_id = Column(Integer, primary_key=True)
-    genome_uuid = Column(String(128), nullable=False, unique=True)
-    assembly_id = Column(ForeignKey('assembly.assembly_id'), nullable=False, index=True)
-    organism_id = Column(ForeignKey('organism.organism_id'), nullable=False, index=True)
+    genome_uuid = Column(String(128), nullable=False, unique=True, default=str(uuid.uuid4))
+    assembly_id = Column(ForeignKey("assembly.assembly_id"), nullable=False, index=True)
+    organism_id = Column(ForeignKey("organism.organism_id"), nullable=False, index=True)
     created = Column(DATETIME(fsp=6), nullable=False)
     # One to many relationships
     # genome_id to genome_dataset and genome release
-    genome_datasets = relationship('GenomeDataset', back_populates='genome')
-    genome_releases = relationship('GenomeRelease', back_populates='genome')
+    genome_datasets = relationship("GenomeDataset", back_populates="genome")
+    genome_releases = relationship("GenomeRelease", back_populates="genome")
     # many to one relationships
     # assembly_id to assembly
-    assembly = relationship('Assembly', back_populates="genomes")
+    assembly = relationship("Assembly", back_populates="genomes")
     # organism_id to organism
-    organism = relationship('Organism', back_populates="genomes")
+    organism = relationship("Organism", back_populates="genomes")
 
 
 class GenomeDataset(Base):
-    __tablename__ = 'genome_dataset'
+    __tablename__ = "genome_dataset"
 
     genome_dataset_id = Column(Integer, primary_key=True)
-    dataset_id = Column(ForeignKey('dataset.dataset_id'), nullable=False, index=True)
-    genome_id = Column(ForeignKey('genome.genome_id'), nullable=False, index=True)
-    release_id = Column(ForeignKey('ensembl_release.release_id'), index=True)
+    dataset_id = Column(ForeignKey("dataset.dataset_id"), nullable=False, index=True)
+    genome_id = Column(ForeignKey("genome.genome_id"), nullable=False, index=True)
+    release_id = Column(ForeignKey("ensembl_release.release_id"), index=True)
     is_current = Column(TINYINT(1), nullable=False)
     # One to many relationships
     # none
     # many to one relationships
     # genome_dataset_id to genome
-    dataset = relationship('Dataset', back_populates="genome_datasets")
+    dataset = relationship("Dataset", back_populates="genome_datasets")
     # genome_id to genome
-    genome = relationship('Genome', back_populates="genome_datasets")
+    genome = relationship("Genome", back_populates="genome_datasets")
     # release_id to release
-    ensembl_release = relationship('EnsemblRelease', back_populates="genome_datasets")
+    ensembl_release = relationship("EnsemblRelease", back_populates="genome_datasets")
 
 
 class GenomeRelease(Base):
-    __tablename__ = 'genome_release'
+    __tablename__ = "genome_release"
 
     genome_release_id = Column(Integer, primary_key=True)
-    genome_id = Column(ForeignKey('genome.genome_id'), nullable=False, index=True)
-    release_id = Column(ForeignKey('ensembl_release.release_id'), nullable=False, index=True)
+    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)
     # One to many relationships
     # none
     # many to one relationships
     # genome_release_id to genome_release
-    genome = relationship('Genome', back_populates='genome_releases')
+    genome = relationship("Genome", back_populates="genome_releases")
     # release_id to ensembl release
-    ensembl_release = relationship('EnsemblRelease', back_populates='genome_releases')
+    ensembl_release = relationship("EnsemblRelease", back_populates="genome_releases")

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

@@ -9,6 +9,8 @@
 #   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 uuid
+
 from sqlalchemy import Column, Integer, String, Index, ForeignKey
 from sqlalchemy.dialects.mysql import TINYINT
 from sqlalchemy.orm import relationship
@@ -17,9 +19,10 @@
 
 
 class Organism(Base):
-    __tablename__ = 'organism'
+    __tablename__ = "organism"
 
     organism_id = Column(Integer, primary_key=True)
+    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)
@@ -30,21 +33,21 @@ class Organism(Base):
     scientific_parlance_name = Column(String(255))
     # One to many relationships
     # Organism_id to organism_group_member and genome
-    genomes = relationship('Genome', back_populates='organism')
-    organism_group_members = relationship('OrganismGroupMember', back_populates='organism')
+    genomes = relationship("Genome", back_populates="organism")
+    organism_group_members = relationship("OrganismGroupMember", back_populates="organism")
 
     # 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}'
+        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}"
 
 
 class OrganismGroup(Base):
-    __tablename__ = 'organism_group'
+    __tablename__ = "organism_group"
     __table_args__ = (
-        Index('group_type_name_63c2f6ac_uniq', 'type', 'name', unique=True),
+        Index("group_type_name_63c2f6ac_uniq", "type", "name", unique=True),
     )
 
     organism_group_id = Column(Integer, primary_key=True)
@@ -53,34 +56,34 @@ class OrganismGroup(Base):
     code = Column(String(48), unique=True)
     # One to many relationships
     # Organism_group_id to organism_group_member
-    organism_group_members = relationship('OrganismGroupMember', back_populates='organism_group')
+    organism_group_members = relationship("OrganismGroupMember", back_populates="organism_group")
 
     # many to one relationships
     # none
     def __repr__(self):
-        return f'organism_group_id={self.organism_group_id}, type={self.type}, name={self.name}, ' \
-               f'code={self.code}'
+        return f"organism_group_id={self.organism_group_id}, type={self.type}, name={self.name}, " \
+               f"code={self.code}"
 
 
 class OrganismGroupMember(Base):
-    __tablename__ = 'organism_group_member'
+    __tablename__ = "organism_group_member"
     __table_args__ = (
-        Index('organism_group_member_organism_id_organism_gro_fe8f49ac_uniq', 'organism_id', 'organism_group_id',
+        Index("organism_group_member_organism_id_organism_gro_fe8f49ac_uniq", "organism_id", "organism_group_id",
               unique=True),
     )
 
     organism_group_member_id = Column(Integer, primary_key=True)
     is_reference = Column(TINYINT(1), nullable=False)
-    organism_id = Column(ForeignKey('organism.organism_id'), nullable=False)
-    organism_group_id = Column(ForeignKey('organism_group.organism_group_id'), nullable=False, index=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
     # none
     # many to one relationships
     # Organism_group_id to organism_group_member
     # organism_id to organism
-    organism_group = relationship('OrganismGroup', back_populates='organism_group_members')
-    organism = relationship('Organism', back_populates='organism_group_members')
+    organism_group = relationship("OrganismGroup", back_populates="organism_group_members")
+    organism = relationship("Organism", back_populates="organism_group_members")
 
     def __repr__(self):
-        return f'organism_group_member_id={self.organism_group_member_id}, is_reference={self.is_reference}, organism_id={self.organism_id}, ' \
-               f'organism_group_id={self.organism_group_id}'
+        return f"organism_group_member_id={self.organism_group_member_id}, is_reference={self.is_reference}, organism_id={self.organism_id}, " \
+               f"organism_group_id={self.organism_group_id}"

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

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

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

@@ -1,4 +1,4 @@
-1	108.0	2023-05-15	Beta Release 1	0	1	integrated
+1	108.0	2023-05-15	Beta Release 1	1	1	integrated
 2	108.1	2023-09-15	Scaling Phase 1	0	1	partial
 3	108.2	2023-11-15	Scaling Phase 2	0	1	partial
-4	109.0	2023-12-15	MVP Release 1	1	integrated
+4	110.0	2023-12-15	MVP Release 1	0	1	integrated

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

@@ -1,5 +1,5 @@
 1	1	1	1
-2	2	1	1
+2	2	1	0
 3	3	1	1
 4	4	1	1
 5	5	1	1

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

@@ -1,6 +1,6 @@
-1	9606	9606	Human	\N	Homo sapiens	Homo_sapiens	homo_sapiens
-2	511145	562	Escherichia coli str. K-12 substr. MG1655 str. K12 (GCA_000005845)	\N	Escherichia coli str. K-12 substr. MG1655 str. K12 (GCA_000005845)	Escherichia_coli_str_k_12_substr_mg1655_gca_000005845	escherichia_coli_str_k_12_substr_mg1655_gca_000005845
-3	36329	5833	Plasmodium falciparum 3D7	\N	Plasmodium falciparum 3D7	Plasmodium_falciparum	plasmodium_falciparum
-4	4565	4565	Triticum aestivum	reference (Chinese spring)	Triticum aestivum	Triticum_aestivum	triticum_aestivum	
-5	559292	4932	Saccharomyces cerevisiae	S288C	Saccharomyces cerevisiae S288c	Saccharomyces_cerevisiae	saccharomyces_cerevisiae	
-6	6239	6239	Caenorhabditis elegans (PRJNA13758)	N2	Caenorhabditis elegans	Caenorhabditis_elegans	caenorhabditis_elegans	
+1	db2a5f09-2db8-429b-a407-c15a4ca2876d	9606	9606	Human	\N	Homo sapiens	Homo_sapiens	homo_sapiens
+2	21279e3e-e651-43e1-a6fc-79e390b9e8a8	511145	562	Escherichia coli str. K-12 substr. MG1655 str. K12 (GCA_000005845)	\N	Escherichia coli str. K-12 substr. MG1655 str. K12 (GCA_000005845)	Escherichia_coli_str_k_12_substr_mg1655_gca_000005845	escherichia_coli_str_k_12_substr_mg1655_gca_000005845
+3	e61faf49-0964-4d0e-8f3a-b2ffa3514698	36329	5833	Plasmodium falciparum 3D7	\N	Plasmodium falciparum 3D7	Plasmodium_falciparum	plasmodium_falciparum
+4	d64c34ca-b37a-476b-83b5-f21d07a3ae67	4565	4565	Triticum aestivum	reference (Chinese spring)	Triticum aestivum	Triticum_aestivum	triticum_aestivum
+5	0dc46f87-0b61-403a-8cd3-86b7e0cce8f0	559292	4932	Saccharomyces cerevisiae	S288C	Saccharomyces cerevisiae S288c	Saccharomyces_cerevisiae	saccharomyces_cerevisiae
+6	0f4aad7b-db15-4a72-af1e-82bbae54226	6239	6239	Caenorhabditis elegans (PRJNA13758)	N2	Caenorhabditis elegans	Caenorhabditis_elegans	caenorhabditis_elegans

src/ensembl/production/metadata/api/sample/ensembl_metadata/table.sql

@@ -1,7 +1,7 @@
 CREATE TABLE assembly
 (
-    assembly_id      int auto_increment
-        primary key,
+    assembly_id      int auto_increment primary key,
+    assembly_uuid     varchar(128) not null,
     ucsc_name        varchar(16)  null,
     accession        varchar(16)  not null,
     level            varchar(32)  not null,
@@ -11,6 +11,8 @@ CREATE TABLE assembly
     tol_id           varchar(32)  null,
     created          datetime     null,
     ensembl_name     varchar(255) null,
+    constraint assembly_uuid
+        unique (assembly_uuid),
     constraint accession
         unique (accession),
     constraint assembly_ensembl_name_uindex
@@ -147,6 +149,7 @@ CREATE TABLE organism
 (
     organism_id              int auto_increment
         primary key,
+    organism_uuid            varchar(128) not null,
     taxonomy_id              int          not null,
     species_taxonomy_id      int          null,
     display_name             varchar(128) not null,
@@ -155,6 +158,8 @@ CREATE TABLE organism
     url_name                 varchar(128) not null,
     ensembl_name             varchar(128) not null,
     scientific_parlance_name varchar(255) null,
+    constraint organism_uuid
+        unique (organism_uuid),
     constraint ensembl_name
         unique (ensembl_name)
 );