From daf7b2aabc4dd36d12d5df497476a44f6317d3e4 Mon Sep 17 00:00:00 2001
From: Bilal <bilal@ebi.ac.uk>
Date: Mon, 24 Jun 2024 15:14:53 +0100
Subject: [PATCH 01/14] first attempt

---
 common/db.py                             |  28 +++---
 common/schemas/genome.graphql            |   2 +
 common/utils.py                          |  26 ++++++
 graphql_service/resolver/data_loaders.py |   8 ++
 graphql_service/resolver/exceptions.py   |  24 +++++
 graphql_service/resolver/gene_model.py   | 106 +++++++++++++++++++++--
 6 files changed, 177 insertions(+), 17 deletions(-)

diff --git a/common/db.py b/common/db.py
index 95b5a093..83235f26 100644
--- a/common/db.py
+++ b/common/db.py
@@ -17,6 +17,8 @@
 import grpc
 from ensembl.production.metadata.grpc import ensembl_metadata_pb2_grpc
 
+from common.utils import process_release_version
+
 logger = logging.getLogger(__name__)
 
 
@@ -33,26 +35,30 @@ def __init__(self, config):
         self.config = config
         self.mongo_client = MongoDbClient.connect_mongo(self.config)
 
-    def get_database_conn(self, grpc_model, uuid):
+    def get_database_conn(self, grpc_model, uuid, force_grpc=False):
         grpc_response = None
         chosen_db = self.config.get("mongo_default_db")
         # Try to connect to gRPC
         try:
             grpc_response = grpc_model.get_release_by_genome_uuid(uuid)
         except Exception as grpc_exp:
-            # chosen_db value will fall back to the default value, which is 'mongo_default_db' that is in the config
             # TODO: check why "except graphql.error.graphql_error.GraphQLError as grpc_exp:" didn't catch the error
             logger.debug(
                 "[get_database_conn] Couldn't connect to gRPC Host: %s", grpc_exp
             )
 
-        if grpc_response:
-            logger.debug("[get_database_conn] grpc_response: %s", grpc_response)
-            # replacing '.' with '_' to avoid
-            # "pymongo.errors.InvalidName: database names cannot contain the character '.'" error ¯\_(ツ)_/¯
-            release_version = str(grpc_response.release_version).replace(".", "_")
-            logger.debug("[get_database_conn] release_version: %s", release_version)
-            chosen_db = "release_" + release_version
+        if force_grpc:
+            chosen_db = process_release_version(grpc_response)
+        else:
+            if grpc_response and grpc_response.release_version:
+                chosen_db = process_release_version(grpc_response)
+            else:
+                # chosen_db value will fall back to the default value, which is 'mongo_default_db' that is in the config
+                # if force_grpc is not True
+                logger.warning(
+                    "[get_database_conn] Falling back to the default Mongo DB: '%s'",
+                    chosen_db,
+                )
 
         logger.debug("[get_database_conn] Connected to '%s' MongoDB", chosen_db)
         data_database_connection = self.mongo_client[chosen_db]
@@ -68,8 +74,8 @@ def connect_mongo(config):
         password = config.get("mongo_password")
 
         client = pymongo.MongoClient(
-            host,
-            port,
+            host=host,
+            port=port,
             username=user,
             password=password,
             read_preference=pymongo.ReadPreference.SECONDARY_PREFERRED,
diff --git a/common/schemas/genome.graphql b/common/schemas/genome.graphql
index db86757c..214b9189 100644
--- a/common/schemas/genome.graphql
+++ b/common/schemas/genome.graphql
@@ -36,4 +36,6 @@ type Genome {
   parlance_name: String
   genome_tag: String
   is_reference: Boolean!
+#  region: Region!
+  assembly: Assembly
 }
\ No newline at end of file
diff --git a/common/utils.py b/common/utils.py
index 0c8a81d2..b711e431 100644
--- a/common/utils.py
+++ b/common/utils.py
@@ -12,6 +12,10 @@
    limitations under the License.
 """
 
+import logging
+
+logger = logging.getLogger(__name__)
+
 
 def check_config_validity(config):
     mandatory_fields = [
@@ -30,6 +34,28 @@ def check_config_validity(config):
             )
 
 
+def process_release_version(grpc_response):
+    """
+    Processes the release version from the gRPC response and formats it for use as a database name.
+
+    This function extracts the release version from the provided gRPC response, replaces any dots ('.')
+    with underscores ('_') to avoid pymongo.errors.InvalidName errors, and returns a formatted database
+    name string.
+
+    Args:
+        grpc_response: The gRPC response object containing the release version.
+
+    Returns:
+        str: A formatted string suitable for use as a database name, prefixed with 'release_'.
+    """
+    logger.debug("[get_database_conn] grpc_response: %s", grpc_response)
+    # replacing '.' with '_' to avoid
+    # "pymongo.errors.InvalidName: database names cannot contain the character '.'" error ¯\_(ツ)_/¯
+    release_version = str(grpc_response.release_version).replace(".", "_")
+    logger.debug("[get_database_conn] release_version: %s", release_version)
+    return "release_" + release_version
+
+
 def get_ensembl_metadata_api_version():
     """
     Get the Metadata API tag from requirement.txt file
diff --git a/graphql_service/resolver/data_loaders.py b/graphql_service/resolver/data_loaders.py
index 2714ed03..f193b74c 100644
--- a/graphql_service/resolver/data_loaders.py
+++ b/graphql_service/resolver/data_loaders.py
@@ -35,6 +35,9 @@ def __init__(self, database_conn):
             batch_load_fn=self.batch_region_by_assembly_load
         )
         self.organism_loader = DataLoader(batch_load_fn=self.batch_organism_load)
+        self.assembly_by_genome_loader = DataLoader(
+            batch_load_fn=self.batch_assembly_by_genome_load
+        )
         self.assembly_by_organism_loader = DataLoader(
             batch_load_fn=self.batch_assembly_by_organism_load
         )
@@ -83,6 +86,11 @@ async def batch_organism_load(self, keys: List[str]) -> List[List]:
         data = await self.query_mongo(query=query, doc_type="organism")
         return self.collate_dataloader_output("organism_primary_key", keys, data)
 
+    async def batch_assembly_by_genome_load(self, keys: List[str]) -> List[List]:
+        query = {"type": "Assembly", "assembly_id": {"$in": keys}}
+        data = await self.query_mongo(query=query, doc_type="assembly")
+        return self.collate_dataloader_output("assembly", keys, data)
+
     async def batch_assembly_by_organism_load(self, keys: List[str]) -> List[List]:
         query = {"type": "Assembly", "organism_foreign_key": {"$in": keys}}
         data = await self.query_mongo(query=query, doc_type="assembly")
diff --git a/graphql_service/resolver/exceptions.py b/graphql_service/resolver/exceptions.py
index 4f400b05..ddbbee2b 100644
--- a/graphql_service/resolver/exceptions.py
+++ b/graphql_service/resolver/exceptions.py
@@ -13,6 +13,7 @@
 """
 from typing import Optional, Dict
 
+import grpc
 from graphql import GraphQLError
 
 
@@ -141,6 +142,15 @@ def __init__(self, organism_id):
         super().__init__("organism", {"organism_id": organism_id})
 
 
+class AssembliesFromGenomeNotFound(FieldNotFoundError):
+    """
+    Custom error to be raised if we can't find the assemblies for a genome
+    """
+
+    def __init__(self, assembly_id):
+        super().__init__("assemblies", {"assembly_id": assembly_id})
+
+
 class AssembliesFromOrganismNotFound(FieldNotFoundError):
     """
     Custom error to be raised if we can't find the assemblies for an organism
@@ -211,3 +221,17 @@ def __init__(self, message: str):
             message: The error message describing the missing argument.
         """
         super().__init__(message)
+
+
+class FailedToConnectToGrpc(grpc.RpcError):
+    """
+    Exception raised when there is gRPC connection issue.
+    """
+
+    def __init__(self, message: str):
+        """Initializes a FailedToConnectToGrpc instance.
+
+        Args:
+            message: The error message describing the issue.
+        """
+        super().__init__(message)
diff --git a/graphql_service/resolver/gene_model.py b/graphql_service/resolver/gene_model.py
index ae2ca472..346101a6 100644
--- a/graphql_service/resolver/gene_model.py
+++ b/graphql_service/resolver/gene_model.py
@@ -15,6 +15,7 @@
 import logging
 from typing import Dict, Optional, List, Any
 
+import grpc
 from ariadne import QueryType, ObjectType
 from graphql import GraphQLResolveInfo
 from pymongo.database import Database
@@ -39,6 +40,8 @@
     GenomeNotFoundError,
     MissingArgumentException,
     DatabaseNotFoundError,
+    AssembliesFromGenomeNotFound,
+    FailedToConnectToGrpc,
 )
 
 
@@ -59,6 +62,7 @@
 ORGANISM_TYPE = ObjectType("Organism")
 SPECIES_TYPE = ObjectType("Species")
 TRANSCRIPT_PAGE_TYPE = ObjectType("TranscriptsPage")
+GENOME_TYPE = ObjectType("Genome")
 
 
 @QUERY_TYPE.field("gene")
@@ -570,6 +574,56 @@ async def resolve_region_from_slice(
     return regions[0]
 
 
+# @GENOME_TYPE.field("assembly")
+# async def resolve_assembly_from_genome_uuid(
+#     genome: Dict, info: GraphQLResolveInfo
+# ) -> Optional[Dict]:
+#     "Fetch an assembly referenced by a genome"
+#     print("&&&&&&&&& BBBOOOOOOOOOOOM !!!!!! &&&&&&&&&&")
+#     print(f"*********^^^^^^^^ genome ---> {genome}")
+#     # data_loader = get_data_loader(info)
+#     # loader = data_loader.organism_loader
+#     # assemblies = await loader.load(key=genome["assembly"])
+#     # # assemblies = await loader.load(key=genome["assembly"])
+#     # if not assemblies:
+#     #     raise AssembliesFromGenomeNotFound(genome["assembly"])
+#     # return assemblies[0]
+#
+#     return {"assembly": "yoyoyoyo assembly"}
+
+
+@GENOME_TYPE.field("assembly")
+async def fetch_assembly_data(
+    genome_uuid: str, assembly_id: str, info: GraphQLResolveInfo
+):
+    # query = {"type": "Assembly", "assembly_id": assembly_id}
+    query = {"type": "Assembly"}
+
+    # connection_db = get_db_conn(info)
+    # assembly_collection = connection_db["assembly"]
+    # connection_db = info.context["mongo_db_client"].mongo_client
+    set_db_conn_for_uuid(info, genome_uuid)
+    connection_db = get_db_conn(info)
+    assembly_collection = connection_db.mongo_db["assembly"]
+    logger.info(
+        "[fetch_assembly_data] Getting Assembly from DB: '%s'",
+        connection_db.name,
+    )
+    # assembly = assembly_collection.find_one(query)
+    try:
+        assembly = assembly_collection.find_one(query)
+    except Exception as e:
+        logging.error("Exception: %s", e)
+        raise DatabaseNotFoundError(db_name=connection_db.name)
+
+    # print(f"assembly ---> {list(assembly)}")
+    # print(f"len assembly ---> {len(list(assembly))}")
+    if not assembly:
+        raise AssemblyNotFoundError(assembly_id)
+    # return assembly
+    return {"assembly": "yoyoyoyo assembly"}
+
+
 @REGION_TYPE.field("assembly")
 async def resolve_assembly_from_region(
     region: Dict, info: GraphQLResolveInfo
@@ -708,11 +762,49 @@ def resolve_genomes(
         result = grpc_model.get_genome_by_keyword(
             by_keyword.get("keyword"), by_keyword.get("release_version")
         )
-        genomes = list(result)
-        if not genomes:
-            raise GenomeNotFoundError(by_keyword)
-        genomes = list(map(create_genome_response, genomes))
-        return genomes
+        try:
+            genomes = list(result)
+            if not genomes:
+                raise GenomeNotFoundError(by_keyword)
+            genomes = [create_genome_response(genome, info) for genome in genomes]
+            return genomes
+
+        except grpc.RpcError as e:
+            if e.code() == grpc.StatusCode.UNAVAILABLE:
+                msg = "Error: Failed to connect to the remote host. Connection refused."
+                logger.error(msg)
+                raise FailedToConnectToGrpc(msg)
+            else:
+                # Print the default error message for any other gRPC errors
+                msg = f"gRPC Error: {e.details()}"
+                logger.error(msg)
+                raise FailedToConnectToGrpc(msg)
+
+        # print(f"$$$$$$$$$$ genome ---> {genomes}")
+
+        # print("===========================")
+        # # print(f"{[genome['genome_id'] for genome in genomes]}")
+        # print(f"{genomes[0]['genome_id']}")
+        # print("===========================")
+        #
+        # for genome in genomes:
+        #     query = {"genome_id": genome["genome_id"]}
+        #     set_db_conn_for_uuid(info, genome["genome_id"])
+        #     connection_db = get_db_conn(info)
+        #     region_collection = connection_db["region"]
+        #     logger.info(
+        #         "[resolve_genomes] Getting Region from DB: '%s'", connection_db.name
+        #     )
+        #
+        #     result = region_collection.find_one(query)
+        #     print("===========================")
+        #     # print(f"{[genome['genome_id'] for genome in genomes]}")
+        #     print(f"{result}")
+        #     print("===========================")
+
+        # return genomes
+        # print((f"*********^^^^^^^^ genomes[0] ---> {genomes[0]}"))
+        # return result
 
     if by_assembly_accession_id:
         result = grpc_model.get_genome_by_assembly_acc_id(
@@ -741,7 +833,8 @@ def resolve_genome(_, info: GraphQLResolveInfo, by_genome_uuid: Dict[str, str])
     return genomes
 
 
-def create_genome_response(genome):
+def create_genome_response(genome, info):
+    print(f"*********^^^^^^^^ genome ---> {genome}")
     response = {
         "genome_id": genome.genome_uuid,
         "assembly_accession": genome.assembly.accession,
@@ -752,6 +845,7 @@ def create_genome_response(genome):
         "parlance_name": genome.organism.scientific_parlance_name,
         "genome_tag": genome.assembly.url_name if not None else genome.assembly.tol_id,
         "is_reference": genome.assembly.is_reference,
+        "assembly": fetch_assembly_data(genome.genome_uuid, genome.assembly.name, info),
     }
     return response
 

From 8d6f18cd7c140160ddc462dc5e25e964be59f89e Mon Sep 17 00:00:00 2001
From: Bilal <bilal@ebi.ac.uk>
Date: Tue, 25 Jun 2024 10:01:20 +0100
Subject: [PATCH 02/14] clean up and refactor the newely added feature's code

---
 common/schemas/genome.graphql          |   1 -
 graphql_service/resolver/exceptions.py |  11 ++
 graphql_service/resolver/gene_model.py | 144 +++++++------------------
 3 files changed, 52 insertions(+), 104 deletions(-)

diff --git a/common/schemas/genome.graphql b/common/schemas/genome.graphql
index 214b9189..61c9a883 100644
--- a/common/schemas/genome.graphql
+++ b/common/schemas/genome.graphql
@@ -36,6 +36,5 @@ type Genome {
   parlance_name: String
   genome_tag: String
   is_reference: Boolean!
-#  region: Region!
   assembly: Assembly
 }
\ No newline at end of file
diff --git a/graphql_service/resolver/exceptions.py b/graphql_service/resolver/exceptions.py
index ddbbee2b..4eacd1d6 100644
--- a/graphql_service/resolver/exceptions.py
+++ b/graphql_service/resolver/exceptions.py
@@ -28,6 +28,17 @@ def __init__(self, db_name: str):
         super().__init__(message, extensions=self.extensions)
 
 
+class CollectionNotFoundError(GraphQLError):
+    """
+    Custom error to be raised if collection is not found
+    """
+
+    def __init__(self, collection_name: str):
+        self.extensions = {"code": f"COLLECTION_NOT_FOUND"}
+        message = f"Failed to find collection: {collection_name}"
+        super().__init__(message, extensions=self.extensions)
+
+
 class FieldNotFoundError(GraphQLError):
     """
     Custom error to be raised if a field cannot be found by id
diff --git a/graphql_service/resolver/gene_model.py b/graphql_service/resolver/gene_model.py
index 346101a6..88906ced 100644
--- a/graphql_service/resolver/gene_model.py
+++ b/graphql_service/resolver/gene_model.py
@@ -13,12 +13,11 @@
 """
 import configparser
 import logging
-from typing import Dict, Optional, List, Any
+from typing import Dict, Optional, List, Any, Mapping
 
-import grpc
 from ariadne import QueryType, ObjectType
 from graphql import GraphQLResolveInfo
-from pymongo.database import Database
+from pymongo.database import Database, Collection
 
 from graphql_service.resolver.data_loaders import BatchLoaders
 
@@ -40,8 +39,7 @@
     GenomeNotFoundError,
     MissingArgumentException,
     DatabaseNotFoundError,
-    AssembliesFromGenomeNotFound,
-    FailedToConnectToGrpc,
+    CollectionNotFoundError,
 )
 
 
@@ -574,56 +572,6 @@ async def resolve_region_from_slice(
     return regions[0]
 
 
-# @GENOME_TYPE.field("assembly")
-# async def resolve_assembly_from_genome_uuid(
-#     genome: Dict, info: GraphQLResolveInfo
-# ) -> Optional[Dict]:
-#     "Fetch an assembly referenced by a genome"
-#     print("&&&&&&&&& BBBOOOOOOOOOOOM !!!!!! &&&&&&&&&&")
-#     print(f"*********^^^^^^^^ genome ---> {genome}")
-#     # data_loader = get_data_loader(info)
-#     # loader = data_loader.organism_loader
-#     # assemblies = await loader.load(key=genome["assembly"])
-#     # # assemblies = await loader.load(key=genome["assembly"])
-#     # if not assemblies:
-#     #     raise AssembliesFromGenomeNotFound(genome["assembly"])
-#     # return assemblies[0]
-#
-#     return {"assembly": "yoyoyoyo assembly"}
-
-
-@GENOME_TYPE.field("assembly")
-async def fetch_assembly_data(
-    genome_uuid: str, assembly_id: str, info: GraphQLResolveInfo
-):
-    # query = {"type": "Assembly", "assembly_id": assembly_id}
-    query = {"type": "Assembly"}
-
-    # connection_db = get_db_conn(info)
-    # assembly_collection = connection_db["assembly"]
-    # connection_db = info.context["mongo_db_client"].mongo_client
-    set_db_conn_for_uuid(info, genome_uuid)
-    connection_db = get_db_conn(info)
-    assembly_collection = connection_db.mongo_db["assembly"]
-    logger.info(
-        "[fetch_assembly_data] Getting Assembly from DB: '%s'",
-        connection_db.name,
-    )
-    # assembly = assembly_collection.find_one(query)
-    try:
-        assembly = assembly_collection.find_one(query)
-    except Exception as e:
-        logging.error("Exception: %s", e)
-        raise DatabaseNotFoundError(db_name=connection_db.name)
-
-    # print(f"assembly ---> {list(assembly)}")
-    # print(f"len assembly ---> {len(list(assembly))}")
-    if not assembly:
-        raise AssemblyNotFoundError(assembly_id)
-    # return assembly
-    return {"assembly": "yoyoyoyo assembly"}
-
-
 @REGION_TYPE.field("assembly")
 async def resolve_assembly_from_region(
     region: Dict, info: GraphQLResolveInfo
@@ -762,49 +710,12 @@ def resolve_genomes(
         result = grpc_model.get_genome_by_keyword(
             by_keyword.get("keyword"), by_keyword.get("release_version")
         )
-        try:
-            genomes = list(result)
-            if not genomes:
-                raise GenomeNotFoundError(by_keyword)
-            genomes = [create_genome_response(genome, info) for genome in genomes]
-            return genomes
-
-        except grpc.RpcError as e:
-            if e.code() == grpc.StatusCode.UNAVAILABLE:
-                msg = "Error: Failed to connect to the remote host. Connection refused."
-                logger.error(msg)
-                raise FailedToConnectToGrpc(msg)
-            else:
-                # Print the default error message for any other gRPC errors
-                msg = f"gRPC Error: {e.details()}"
-                logger.error(msg)
-                raise FailedToConnectToGrpc(msg)
-
-        # print(f"$$$$$$$$$$ genome ---> {genomes}")
-
-        # print("===========================")
-        # # print(f"{[genome['genome_id'] for genome in genomes]}")
-        # print(f"{genomes[0]['genome_id']}")
-        # print("===========================")
-        #
-        # for genome in genomes:
-        #     query = {"genome_id": genome["genome_id"]}
-        #     set_db_conn_for_uuid(info, genome["genome_id"])
-        #     connection_db = get_db_conn(info)
-        #     region_collection = connection_db["region"]
-        #     logger.info(
-        #         "[resolve_genomes] Getting Region from DB: '%s'", connection_db.name
-        #     )
-        #
-        #     result = region_collection.find_one(query)
-        #     print("===========================")
-        #     # print(f"{[genome['genome_id'] for genome in genomes]}")
-        #     print(f"{result}")
-        #     print("===========================")
-
-        # return genomes
-        # print((f"*********^^^^^^^^ genomes[0] ---> {genomes[0]}"))
-        # return result
+        genomes = list(result)
+        if not genomes:
+            raise GenomeNotFoundError(by_keyword)
+
+        # Fetch assembly data and combine it with genome data
+        return fetch_and_combine_genome_data(info, genomes)
 
     if by_assembly_accession_id:
         result = grpc_model.get_genome_by_assembly_acc_id(
@@ -813,8 +724,9 @@ def resolve_genomes(
         genomes = list(result)
         if not genomes:
             raise GenomeNotFoundError(by_assembly_accession_id)
-        genomes = list(map(create_genome_response, genomes))
-        return genomes
+
+        # Fetch assembly data and combine it with genome data
+        return fetch_and_combine_genome_data(info, genomes)
 
     return []
 
@@ -833,8 +745,7 @@ def resolve_genome(_, info: GraphQLResolveInfo, by_genome_uuid: Dict[str, str])
     return genomes
 
 
-def create_genome_response(genome, info):
-    print(f"*********^^^^^^^^ genome ---> {genome}")
+def create_genome_response(genome, assembly_data=None):
     response = {
         "genome_id": genome.genome_uuid,
         "assembly_accession": genome.assembly.accession,
@@ -845,11 +756,38 @@ def create_genome_response(genome, info):
         "parlance_name": genome.organism.scientific_parlance_name,
         "genome_tag": genome.assembly.url_name if not None else genome.assembly.tol_id,
         "is_reference": genome.assembly.is_reference,
-        "assembly": fetch_assembly_data(genome.genome_uuid, genome.assembly.name, info),
+        "assembly": assembly_data,
     }
     return response
 
 
+def fetch_assembly_data(assembly_collection: Collection, assembly_id: str) -> Mapping:
+    query = {"assembly_id": assembly_id}
+    try:
+        assembly = assembly_collection.find_one(query)
+    except Exception as e:
+        logging.error("Exception: %s", e)
+        raise CollectionNotFoundError(collection_name=assembly_collection.name)
+
+    if not assembly:
+        raise AssemblyNotFoundError(assembly_id)
+    return assembly
+
+
+def fetch_and_combine_genome_data(info: GraphQLResolveInfo, genomes: List) -> List:
+    combined_results = []
+    for genome in genomes:
+        set_db_conn_for_uuid(info, genome.genome_uuid)
+        connection_db = get_db_conn(info)
+        # logging.debug("Collections in the database:", connection_db.list_collection_names())
+        assembly_collection = connection_db["assembly"]
+        # logging.debug("assembly_collection.name:", assembly_collection.name)
+
+        assembly_data = fetch_assembly_data(assembly_collection, genome.assembly.name)
+        combined_results.append(create_genome_response(genome, assembly_data))
+    return combined_results
+
+
 def get_version_details() -> Dict[str, str]:
     """
     Fetch version details from a 'version_config.ini' file.

From b8732ea137cb4c6a11fc276ba38bb3ed7468cf19 Mon Sep 17 00:00:00 2001
From: Bilal <bilal@ebi.ac.uk>
Date: Tue, 25 Jun 2024 13:51:15 +0100
Subject: [PATCH 03/14] optimise the script by checking if assembly related
 data is requested or not

---
 graphql_service/resolver/gene_model.py | 20 +++++++++++++++++---
 1 file changed, 17 insertions(+), 3 deletions(-)

diff --git a/graphql_service/resolver/gene_model.py b/graphql_service/resolver/gene_model.py
index 88906ced..c2ba1902 100644
--- a/graphql_service/resolver/gene_model.py
+++ b/graphql_service/resolver/gene_model.py
@@ -775,6 +775,12 @@ def fetch_assembly_data(assembly_collection: Collection, assembly_id: str) -> Ma
 
 
 def fetch_and_combine_genome_data(info: GraphQLResolveInfo, genomes: List) -> List:
+    # Check if the assembly field is requested in the query
+    requested_fields = [
+        field.name.value for field in info.field_nodes[0].selection_set.selections
+    ]
+    is_assembly_prensent = "assembly" in requested_fields
+
     combined_results = []
     for genome in genomes:
         set_db_conn_for_uuid(info, genome.genome_uuid)
@@ -782,9 +788,17 @@ def fetch_and_combine_genome_data(info: GraphQLResolveInfo, genomes: List) -> Li
         # logging.debug("Collections in the database:", connection_db.list_collection_names())
         assembly_collection = connection_db["assembly"]
         # logging.debug("assembly_collection.name:", assembly_collection.name)
-
-        assembly_data = fetch_assembly_data(assembly_collection, genome.assembly.name)
-        combined_results.append(create_genome_response(genome, assembly_data))
+        logging.debug("is_assembly_prensent:", is_assembly_prensent)
+
+        if not is_assembly_prensent:
+            # Don't bother getting the assembly data if it's not requested in the query
+            # TODO: See if this can be approved
+            combined_results.append(create_genome_response(genome, None))
+        else:
+            assembly_data = fetch_assembly_data(
+                assembly_collection, genome.assembly.name
+            )
+            combined_results.append(create_genome_response(genome, assembly_data))
     return combined_results
 
 

From 0a50ce4b736bef39623ba6f9836119e4635d4a9a Mon Sep 17 00:00:00 2001
From: Bilal <bilal@ebi.ac.uk>
Date: Tue, 25 Jun 2024 14:06:26 +0100
Subject: [PATCH 04/14] fix tests

---
 .../tests/snapshots/snap_test_gene_name_retrieval.py          | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/graphql_service/tests/snapshots/snap_test_gene_name_retrieval.py b/graphql_service/tests/snapshots/snap_test_gene_name_retrieval.py
index 87f6deb9..ca01b9be 100644
--- a/graphql_service/tests/snapshots/snap_test_gene_name_retrieval.py
+++ b/graphql_service/tests/snapshots/snap_test_gene_name_retrieval.py
@@ -27,7 +27,7 @@
             "name": {
                 "accession_id": "A0A1D5TR86",
                 "source": None,
-                "url": "https://purl.uniprot.org/uniprot/A0A1D5TR86",
+                "url": "http://purl.uniprot.org/uniprot/A0A1D5TR86",
                 "value": "Sulfotransferase [Source:UniProtKB/TrEMBL;Acc:A0A1D5TR86]",
             }
         },
@@ -67,7 +67,7 @@
                     "release": None,
                     "url": "https://www.uniprot.org/",
                 },
-                "url": "https://purl.uniprot.org/uniprot/A0A1D5TR86",
+                "url": "http://purl.uniprot.org/uniprot/A0A1D5TR86",
                 "value": None,
             }
         },

From f8d588542fd6510d024f4f8af7dffd40a064d87a Mon Sep 17 00:00:00 2001
From: Bilal <bilal@ebi.ac.uk>
Date: Tue, 25 Jun 2024 14:22:46 +0100
Subject: [PATCH 05/14] fix pylint

---
 graphql_service/resolver/exceptions.py |  4 ++--
 graphql_service/resolver/gene_model.py | 27 +++++++++++++-------------
 graphql_service/server.py              |  2 +-
 3 files changed, 17 insertions(+), 16 deletions(-)

diff --git a/graphql_service/resolver/exceptions.py b/graphql_service/resolver/exceptions.py
index 4eacd1d6..aeed2081 100644
--- a/graphql_service/resolver/exceptions.py
+++ b/graphql_service/resolver/exceptions.py
@@ -23,7 +23,7 @@ class DatabaseNotFoundError(GraphQLError):
     """
 
     def __init__(self, db_name: str):
-        self.extensions = {"code": f"DATABASE_NOT_FOUND"}
+        self.extensions = {"code": "DATABASE_NOT_FOUND"}
         message = f"Failed to find database: {db_name}"
         super().__init__(message, extensions=self.extensions)
 
@@ -34,7 +34,7 @@ class CollectionNotFoundError(GraphQLError):
     """
 
     def __init__(self, collection_name: str):
-        self.extensions = {"code": f"COLLECTION_NOT_FOUND"}
+        self.extensions = {"code": "COLLECTION_NOT_FOUND"}
         message = f"Failed to find collection: {collection_name}"
         super().__init__(message, extensions=self.extensions)
 
diff --git a/graphql_service/resolver/gene_model.py b/graphql_service/resolver/gene_model.py
index c2ba1902..d88a6f22 100644
--- a/graphql_service/resolver/gene_model.py
+++ b/graphql_service/resolver/gene_model.py
@@ -99,9 +99,9 @@ def resolve_gene(
     logger.info("[resolve_gene] Getting Gene from DB: '%s'", connection_db.name)
     try:
         result = gene_collection.find_one(query)
-    except Exception as e:
-        logging.error("Exception: %s", e)
-        raise DatabaseNotFoundError(db_name=connection_db.name)
+    except Exception as db_exp:
+        logging.error("Exception: %s", db_exp)
+        raise (DatabaseNotFoundError(db_name=connection_db.name)) from db_exp
 
     if not result:
         raise GeneNotFoundError(by_id=by_id)
@@ -126,9 +126,9 @@ def resolve_genes(_, info: GraphQLResolveInfo, by_symbol: Dict[str, str]) -> Lis
 
     try:
         result = gene_collection.find(query)
-    except Exception as e:
-        logging.error("Exception: %s", e)
-        raise DatabaseNotFoundError(db_name=connection_db.name)
+    except Exception as db_exp:
+        logging.error("Exception: %s", db_exp)
+        raise (DatabaseNotFoundError(db_name=connection_db.name)) from db_exp
 
     # unpack cursor into a list. We're guaranteed relatively small results
     result = list(result)
@@ -247,9 +247,9 @@ def resolve_transcript(
 
     try:
         transcript = transcript_collection.find_one(query)
-    except Exception as e:
-        logging.error("Exception: %s", e)
-        raise DatabaseNotFoundError(db_name=connection_db.name)
+    except Exception as db_exp:
+        logging.error("Exception: %s", db_exp)
+        raise (DatabaseNotFoundError(db_name=connection_db.name)) from db_exp
 
     if not transcript:
         raise TranscriptNotFoundError(by_symbol=by_symbol, by_id=by_id)
@@ -765,9 +765,11 @@ def fetch_assembly_data(assembly_collection: Collection, assembly_id: str) -> Ma
     query = {"assembly_id": assembly_id}
     try:
         assembly = assembly_collection.find_one(query)
-    except Exception as e:
-        logging.error("Exception: %s", e)
-        raise CollectionNotFoundError(collection_name=assembly_collection.name)
+    except Exception as coll_exp:
+        logging.error("Exception: %s", coll_exp)
+        raise (
+            CollectionNotFoundError(collection_name=assembly_collection.name)
+        ) from coll_exp
 
     if not assembly:
         raise AssemblyNotFoundError(assembly_id)
@@ -788,7 +790,6 @@ def fetch_and_combine_genome_data(info: GraphQLResolveInfo, genomes: List) -> Li
         # logging.debug("Collections in the database:", connection_db.list_collection_names())
         assembly_collection = connection_db["assembly"]
         # logging.debug("assembly_collection.name:", assembly_collection.name)
-        logging.debug("is_assembly_prensent:", is_assembly_prensent)
 
         if not is_assembly_prensent:
             # Don't bother getting the assembly data if it's not requested in the query
diff --git a/graphql_service/server.py b/graphql_service/server.py
index d02277bc..e6e6a317 100644
--- a/graphql_service/server.py
+++ b/graphql_service/server.py
@@ -25,13 +25,13 @@
 from starlette import applications, middleware
 from starlette.middleware.cors import CORSMiddleware
 
+from dotenv import load_dotenv
 from common import crossrefs, db, extensions, utils, logger
 from grpc_service import grpc_model
 from graphql_service.ariadne_app import (
     prepare_executable_schema,
     prepare_context_provider,
 )
-from dotenv import load_dotenv
 
 
 load_dotenv("connections.conf")

From 7fb9dadb3ab2c9046cda90fcce6e3eb42819db55 Mon Sep 17 00:00:00 2001
From: Bilal <bilal@ebi.ac.uk>
Date: Tue, 25 Jun 2024 14:29:36 +0100
Subject: [PATCH 06/14] remove uneccessary code

---
 graphql_service/resolver/data_loaders.py | 8 --------
 1 file changed, 8 deletions(-)

diff --git a/graphql_service/resolver/data_loaders.py b/graphql_service/resolver/data_loaders.py
index f193b74c..2714ed03 100644
--- a/graphql_service/resolver/data_loaders.py
+++ b/graphql_service/resolver/data_loaders.py
@@ -35,9 +35,6 @@ def __init__(self, database_conn):
             batch_load_fn=self.batch_region_by_assembly_load
         )
         self.organism_loader = DataLoader(batch_load_fn=self.batch_organism_load)
-        self.assembly_by_genome_loader = DataLoader(
-            batch_load_fn=self.batch_assembly_by_genome_load
-        )
         self.assembly_by_organism_loader = DataLoader(
             batch_load_fn=self.batch_assembly_by_organism_load
         )
@@ -86,11 +83,6 @@ async def batch_organism_load(self, keys: List[str]) -> List[List]:
         data = await self.query_mongo(query=query, doc_type="organism")
         return self.collate_dataloader_output("organism_primary_key", keys, data)
 
-    async def batch_assembly_by_genome_load(self, keys: List[str]) -> List[List]:
-        query = {"type": "Assembly", "assembly_id": {"$in": keys}}
-        data = await self.query_mongo(query=query, doc_type="assembly")
-        return self.collate_dataloader_output("assembly", keys, data)
-
     async def batch_assembly_by_organism_load(self, keys: List[str]) -> List[List]:
         query = {"type": "Assembly", "organism_foreign_key": {"$in": keys}}
         data = await self.query_mongo(query=query, doc_type="assembly")

From b11e627eb57235ccd952a8c9b9a4e61494f58133 Mon Sep 17 00:00:00 2001
From: Bilal <bilal@ebi.ac.uk>
Date: Mon, 8 Jul 2024 16:27:44 +0100
Subject: [PATCH 07/14] add release_date

---
 README.md                              | 11 ++++++++---
 common/schemas/genome.graphql          |  1 +
 graphql_service/resolver/gene_model.py |  3 ++-
 3 files changed, 11 insertions(+), 4 deletions(-)

diff --git a/README.md b/README.md
index 31069005..8e038a99 100644
--- a/README.md
+++ b/README.md
@@ -21,11 +21,16 @@ To install dependencies, run:
 Rename example_connections.conf to connections.conf and update the config values accordingly.
 
 This command will start the server:
+```
+uvicorn --workers 1 --host=0.0.0.0 graphql_service.server:APP
+```
 
-```uvicorn --workers 1 --host=0.0.0.0 graphql_service.server:APP```
-
+To run a Uvicorn server with automatic reload for development purposes, you can use the --reload flag. This flag will make Uvicorn watch your code for changes and automatically restart the server when it detects any changes.
+```
+uvicorn --workers 1 --host 0.0.0.0 --reload graphql_service.server:APP
+```
 
-If you're developing in PyCharm, you will probably find it useful to create a run 
+Also, if you're developing in PyCharm, you will probably find it useful to create a run 
 configuration so that you can use the debugger.  Create a run configuration that 
 looks like this:
 
diff --git a/common/schemas/genome.graphql b/common/schemas/genome.graphql
index 61c9a883..56ac5b1f 100644
--- a/common/schemas/genome.graphql
+++ b/common/schemas/genome.graphql
@@ -31,6 +31,7 @@ type Genome {
   assembly_accession: String!
   scientific_name: String!
   release_number: Float!
+  release_date: String!
   taxon_id: Int!
   tol_id: String
   parlance_name: String
diff --git a/graphql_service/resolver/gene_model.py b/graphql_service/resolver/gene_model.py
index d88a6f22..0add8705 100644
--- a/graphql_service/resolver/gene_model.py
+++ b/graphql_service/resolver/gene_model.py
@@ -751,6 +751,7 @@ def create_genome_response(genome, assembly_data=None):
         "assembly_accession": genome.assembly.accession,
         "scientific_name": genome.organism.scientific_name,
         "release_number": genome.release.release_version,
+        "release_date": genome.release.release_date,
         "taxon_id": genome.taxon.taxonomy_id,
         "tol_id": genome.assembly.tol_id,
         "parlance_name": genome.organism.scientific_parlance_name,
@@ -793,7 +794,7 @@ def fetch_and_combine_genome_data(info: GraphQLResolveInfo, genomes: List) -> Li
 
         if not is_assembly_prensent:
             # Don't bother getting the assembly data if it's not requested in the query
-            # TODO: See if this can be approved
+            # TODO: See if this can be improved
             combined_results.append(create_genome_response(genome, None))
         else:
             assembly_data = fetch_assembly_data(

From 1404283031edfd71552835a7a26ecb7880d200ec Mon Sep 17 00:00:00 2001
From: Bilal <bilal@ebi.ac.uk>
Date: Mon, 15 Jul 2024 18:19:40 +0100
Subject: [PATCH 08/14] Alter by_keyword arguments to be more specific

---
 .gitignore                             |   1 +
 common/schemas/query.graphql           |  17 +++-
 graphql_service/resolver/gene_model.py | 133 +++++++++++++------------
 grpc_service/grpc_model.py             |  51 ++++++----
 4 files changed, 119 insertions(+), 83 deletions(-)

diff --git a/.gitignore b/.gitignore
index 4486dc0a..a9c4459b 100644
--- a/.gitignore
+++ b/.gitignore
@@ -64,6 +64,7 @@ venv/
 ENV/
 env.bak/
 venv.bak/
+node_modules/
 
 # editor cruft
 .vscode
diff --git a/common/schemas/query.graphql b/common/schemas/query.graphql
index c02aa987..cf58bfcf 100644
--- a/common/schemas/query.graphql
+++ b/common/schemas/query.graphql
@@ -18,8 +18,8 @@ type Query {
                  by_slice: SliceInput): Locus
   region(by_name: RegionNameInput!): Region
 
-  genomes(by_keyword: GenomeByKeywordInput,
-          by_assembly_accession_id: AssemblyAccessionIDInput): [Genome]
+
+  genomes(by_keyword: GenomeBySpecificKeywordInput): [Genome]
 
   genome(by_genome_uuid: GenomeUUIDInput!): Genome
 
@@ -58,9 +58,16 @@ input GenomeUUIDInput {
   release_version: Float
 }
 
-input GenomeByKeywordInput {
-  keyword: String!
-  release_version: Float
+input GenomeBySpecificKeywordInput{
+    tolid: String
+    assembly_accession_id: String
+    assembly_name: String
+    ensembl_name: String
+    common_name: String
+    scientific_name: String
+    scientific_parlance_name: String
+    species_taxonomy_id: String
+    release_version: Float
 }
 
 input AssemblyAccessionIDInput {
diff --git a/graphql_service/resolver/gene_model.py b/graphql_service/resolver/gene_model.py
index 0add8705..80dd2bef 100644
--- a/graphql_service/resolver/gene_model.py
+++ b/graphql_service/resolver/gene_model.py
@@ -16,7 +16,7 @@
 from typing import Dict, Optional, List, Any, Mapping
 
 from ariadne import QueryType, ObjectType
-from graphql import GraphQLResolveInfo
+from graphql import GraphQLResolveInfo, GraphQLError
 from pymongo.database import Database, Collection
 
 from graphql_service.resolver.data_loaders import BatchLoaders
@@ -686,47 +686,85 @@ async def resolve_region(_, info: GraphQLResolveInfo, by_name: Dict[str, str]) -
     return result
 
 
+def fetch_genome_and_combine(info, grpc_model, by_keyword, key):
+    """
+    Fetches genomes by a specific keyword and combines genome data with assembly data if requested.
+
+    Args:
+        info (GraphQLResolveInfo): The GraphQL resolver information containing the field nodes and other query details.
+        grpc_model: The gRPC model to fetch genome data.
+        by_keyword (dict): Dictionary containing the keyword to search genomes by.
+        key (str): The specific key to use for fetching genomes.
+
+    Returns:
+        List: A list of combined genome and assembly data objects. If assembly data is not requested, only genome data is included.
+
+    Raises:
+        GenomeNotFoundError: If no genomes are found for the given keyword.
+    """
+    result = grpc_model.get_genome_by_specific_keyword(
+        **{key: by_keyword.get(key)},
+        release_version=by_keyword.get("release_version"),
+    )
+    genomes = list(result)
+    if not genomes:
+        raise GenomeNotFoundError(by_keyword)
+
+    # Check if the assembly field is requested in the query
+    requested_fields = [
+        field.name.value for field in info.field_nodes[0].selection_set.selections
+    ]
+    is_assembly_prensent = "assembly" in requested_fields
+
+    combined_results = []
+    for genome in genomes:
+        set_db_conn_for_uuid(info, genome.genome_uuid)
+        connection_db = get_db_conn(info)
+        # logging.debug("Collections in the database:", connection_db.list_collection_names())
+        assembly_collection = connection_db["assembly"]
+        # logging.debug("assembly_collection.name:", assembly_collection.name)
+
+        if not is_assembly_prensent:
+            # Don't bother getting the assembly data if it's not requested in the query
+            # TODO: See if this can be improved
+            combined_results.append(create_genome_response(genome, None))
+        else:
+            assembly_data = fetch_assembly_data(
+                assembly_collection, genome.assembly.name
+            )
+            combined_results.append(create_genome_response(genome, assembly_data))
+    return combined_results
+
+
 @QUERY_TYPE.field("genomes")
 def resolve_genomes(
-    _,
-    info: GraphQLResolveInfo,
-    by_keyword: Optional[Dict[str, str]] = None,
-    by_assembly_accession_id: Optional[Dict[str, str]] = None,
+    _, info: GraphQLResolveInfo, by_keyword: Optional[Dict[str, str]] = None
 ) -> List:
 
-    # in case the user provides both arguments or none
-    if sum(map(bool, [by_keyword, by_assembly_accession_id])) != 1:
-        # ask them to provide at least one argument
-        if not by_keyword and not by_assembly_accession_id:
-            raise MissingArgumentException(
-                "You must provide either 'by_keyword' or 'by_assembly_accession_id' argument."
-            )
-        # or in case they provided both, ask them to provide one only
-        raise InputFieldArgumentNumberError(1)
+    # ask them to provide at least one argument
+    if not by_keyword:
+        raise MissingArgumentException("You must provide 'by_keyword' argument.")
+
+    # Check if exactly one field is provided
+    provided_count = sum(1 for value in by_keyword.values() if value)
+    if provided_count != 1:
+        raise GraphQLError("Exactly one of the fields must be provided")
 
     grpc_model = info.context["grpc_model"]
 
     if by_keyword:
-        result = grpc_model.get_genome_by_keyword(
-            by_keyword.get("keyword"), by_keyword.get("release_version")
-        )
-        genomes = list(result)
-        if not genomes:
-            raise GenomeNotFoundError(by_keyword)
-
-        # Fetch assembly data and combine it with genome data
-        return fetch_and_combine_genome_data(info, genomes)
-
-    if by_assembly_accession_id:
-        result = grpc_model.get_genome_by_assembly_acc_id(
-            by_assembly_accession_id.get("assembly_accession_id")
-        )
-        genomes = list(result)
-        if not genomes:
-            raise GenomeNotFoundError(by_assembly_accession_id)
-
-        # Fetch assembly data and combine it with genome data
-        return fetch_and_combine_genome_data(info, genomes)
+        for key in [
+            "tolid",
+            "assembly_accession_id",
+            "assembly_name",
+            "ensembl_name",
+            "common_name",
+            "scientific_name",
+            "scientific_parlance_name",
+            "species_taxonomy_id",
+        ]:
+            if by_keyword.get(key):
+                return fetch_genome_and_combine(info, grpc_model, by_keyword, key)
 
     return []
 
@@ -777,33 +815,6 @@ def fetch_assembly_data(assembly_collection: Collection, assembly_id: str) -> Ma
     return assembly
 
 
-def fetch_and_combine_genome_data(info: GraphQLResolveInfo, genomes: List) -> List:
-    # Check if the assembly field is requested in the query
-    requested_fields = [
-        field.name.value for field in info.field_nodes[0].selection_set.selections
-    ]
-    is_assembly_prensent = "assembly" in requested_fields
-
-    combined_results = []
-    for genome in genomes:
-        set_db_conn_for_uuid(info, genome.genome_uuid)
-        connection_db = get_db_conn(info)
-        # logging.debug("Collections in the database:", connection_db.list_collection_names())
-        assembly_collection = connection_db["assembly"]
-        # logging.debug("assembly_collection.name:", assembly_collection.name)
-
-        if not is_assembly_prensent:
-            # Don't bother getting the assembly data if it's not requested in the query
-            # TODO: See if this can be improved
-            combined_results.append(create_genome_response(genome, None))
-        else:
-            assembly_data = fetch_assembly_data(
-                assembly_collection, genome.assembly.name
-            )
-            combined_results.append(create_genome_response(genome, assembly_data))
-    return combined_results
-
-
 def get_version_details() -> Dict[str, str]:
     """
     Fetch version details from a 'version_config.ini' file.
diff --git a/grpc_service/grpc_model.py b/grpc_service/grpc_model.py
index ff2f59a9..9ff3a887 100644
--- a/grpc_service/grpc_model.py
+++ b/grpc_service/grpc_model.py
@@ -21,27 +21,44 @@ def get_genome_by_genome_uuid(self, genome_uuid, release_version=None):
         response = self.grpc_stub.GetGenomeByUUID(request)
         return response
 
-    def get_genome_by_keyword(self, keyword, release_version=None):
+    def get_genome_by_specific_keyword(
+        self,
+        tolid=None,
+        assembly_accession_id=None,
+        assembly_name=None,
+        ensembl_name=None,
+        common_name=None,
+        scientific_name=None,
+        scientific_parlance_name=None,
+        species_taxonomy_id=None,
+        release_version=None,
+    ):
         logger.debug(
-            "Received RPC for GetGenomesByKeyword with keyword: '%s', release: %s",
-            keyword,
-            release_version,
-        )
-        request = ensembl_metadata_pb2.GenomeByKeywordRequest(
-            keyword=keyword, release_version=release_version
-        )
-        response = self.grpc_stub.GetGenomesByKeyword(request)
-        return response
-
-    def get_genome_by_assembly_acc_id(self, assembly_accession_id):
-        logger.debug(
-            "Received RPC for GetGenomesByAssemblyAccessionID with assembly_accession_id: '%s'",
+            "Received RPC for GetGenomesBySpecificKeyword with tolid: '%s', assembly_accession_id: '%s', "
+            "assembly_name: '%s', ensembl_name: '%s', common_name: '%s', scientific_name: '%s', "
+            "scientific_parlance_name: '%s', species_taxonomy_id: '%s', release: %s",
+            tolid,
             assembly_accession_id,
+            assembly_name,
+            ensembl_name,
+            common_name,
+            scientific_name,
+            scientific_parlance_name,
+            species_taxonomy_id,
+            release_version,
         )
-        request = ensembl_metadata_pb2.AssemblyAccessionIDRequest(
-            assembly_accession=assembly_accession_id
+        request = ensembl_metadata_pb2.GenomeBySpecificKeywordRequest(
+            tolid=tolid,
+            assembly_accession_id=assembly_accession_id,
+            assembly_name=assembly_name,
+            ensembl_name=ensembl_name,
+            common_name=common_name,
+            scientific_name=scientific_name,
+            scientific_parlance_name=scientific_parlance_name,
+            species_taxonomy_id=species_taxonomy_id,
+            release_version=release_version,
         )
-        response = self.grpc_stub.GetGenomesByAssemblyAccessionID(request)
+        response = self.grpc_stub.GetGenomesBySpecificKeyword(request)
         return response
 
     def get_release_by_genome_uuid(self, genome_uuid):

From 2b7d980cb0d825e5d2070eb2059305cfade515f7 Mon Sep 17 00:00:00 2001
From: Bilal <bilal@ebi.ac.uk>
Date: Wed, 17 Jul 2024 11:52:24 +0100
Subject: [PATCH 09/14] include dataset info in 'genomes' and 'genome' queries

---
 common/schemas/dataset.graphql         | 11 +++++
 common/schemas/genome.graphql          |  1 +
 graphql_service/resolver/gene_model.py | 65 +++++++++++++++++++++-----
 grpc_service/grpc_model.py             | 12 +++++
 4 files changed, 77 insertions(+), 12 deletions(-)
 create mode 100644 common/schemas/dataset.graphql

diff --git a/common/schemas/dataset.graphql b/common/schemas/dataset.graphql
new file mode 100644
index 00000000..cfe7de66
--- /dev/null
+++ b/common/schemas/dataset.graphql
@@ -0,0 +1,11 @@
+type Dataset {
+  dataset_id: String!
+  name: String!
+  release: Float!
+  type: String!
+  source: String!
+  dataset_type: String!
+  version: String
+  release_date: String!
+  release_type: String!
+}
\ No newline at end of file
diff --git a/common/schemas/genome.graphql b/common/schemas/genome.graphql
index 56ac5b1f..27df17f9 100644
--- a/common/schemas/genome.graphql
+++ b/common/schemas/genome.graphql
@@ -38,4 +38,5 @@ type Genome {
   genome_tag: String
   is_reference: Boolean!
   assembly: Assembly
+  dataset: [Dataset]
 }
\ No newline at end of file
diff --git a/graphql_service/resolver/gene_model.py b/graphql_service/resolver/gene_model.py
index 80dd2bef..ad272ff9 100644
--- a/graphql_service/resolver/gene_model.py
+++ b/graphql_service/resolver/gene_model.py
@@ -16,6 +16,7 @@
 from typing import Dict, Optional, List, Any, Mapping
 
 from ariadne import QueryType, ObjectType
+from ensembl.production.metadata.api.models import Genome
 from graphql import GraphQLResolveInfo, GraphQLError
 from pymongo.database import Database, Collection
 
@@ -41,7 +42,7 @@
     DatabaseNotFoundError,
     CollectionNotFoundError,
 )
-
+from grpc_service.grpc_model import GRPC_MODEL
 
 logger = logging.getLogger(__name__)
 
@@ -686,7 +687,9 @@ async def resolve_region(_, info: GraphQLResolveInfo, by_name: Dict[str, str]) -
     return result
 
 
-def fetch_genome_and_combine(info, grpc_model, by_keyword, key):
+def fetch_genome_and_combine(
+    info: GraphQLResolveInfo, grpc_model: GRPC_MODEL, by_keyword: Dict, key: str
+) -> List:
     """
     Fetches genomes by a specific keyword and combines genome data with assembly data if requested.
 
@@ -702,6 +705,7 @@ def fetch_genome_and_combine(info, grpc_model, by_keyword, key):
     Raises:
         GenomeNotFoundError: If no genomes are found for the given keyword.
     """
+    # Fetch genomes data from metadata using gRPC
     result = grpc_model.get_genome_by_specific_keyword(
         **{key: by_keyword.get(key)},
         release_version=by_keyword.get("release_version"),
@@ -710,11 +714,12 @@ def fetch_genome_and_combine(info, grpc_model, by_keyword, key):
     if not genomes:
         raise GenomeNotFoundError(by_keyword)
 
-    # Check if the assembly field is requested in the query
     requested_fields = [
         field.name.value for field in info.field_nodes[0].selection_set.selections
     ]
-    is_assembly_prensent = "assembly" in requested_fields
+    # Check if the assembly and/or dataset fields are requested in the query
+    is_assembly_present = "assembly" in requested_fields
+    is_dataset_present = "dataset" in requested_fields
 
     combined_results = []
     for genome in genomes:
@@ -724,15 +729,17 @@ def fetch_genome_and_combine(info, grpc_model, by_keyword, key):
         assembly_collection = connection_db["assembly"]
         # logging.debug("assembly_collection.name:", assembly_collection.name)
 
-        if not is_assembly_prensent:
-            # Don't bother getting the assembly data if it's not requested in the query
-            # TODO: See if this can be improved
-            combined_results.append(create_genome_response(genome, None))
-        else:
+        assembly_data = None
+        dataset_data = None
+        if is_assembly_present:
             assembly_data = fetch_assembly_data(
                 assembly_collection, genome.assembly.name
             )
-            combined_results.append(create_genome_response(genome, assembly_data))
+        if is_dataset_present:
+            dataset_data = fetch_dataset_data(grpc_model, genome.genome_uuid)
+        combined_results.append(
+            create_genome_response(genome, assembly_data, dataset_data)
+        )
     return combined_results
 
 
@@ -779,11 +786,38 @@ def resolve_genome(_, info: GraphQLResolveInfo, by_genome_uuid: Dict[str, str])
     )
     if not genome.genome_uuid:
         raise GenomeNotFoundError(by_genome_uuid)
-    genomes = create_genome_response(genome)
+
+    # fetch dataset info
+    dataset_data = fetch_dataset_data(grpc_model, genome.genome_uuid)
+    genomes = create_genome_response(
+        genome=genome, assembly_data=None, dataset_data=dataset_data
+    )
     return genomes
 
 
-def create_genome_response(genome, assembly_data=None):
+def create_genome_response(
+    genome: Genome,
+    assembly_data: Optional[Dict[str, Any]] = None,
+    dataset_data: Optional[List] = None,
+) -> Dict:
+
+    datasets_response = []
+    if dataset_data:
+        for dataset in dataset_data:
+            datasets_response.append(
+                {
+                    "dataset_id": dataset.dataset_uuid,
+                    "name": dataset.dataset_label,
+                    "version": dataset.dataset_version,
+                    "release": dataset.release_version,
+                    "type": dataset.dataset_type_topic,
+                    "source": dataset.dataset_source_type,
+                    "dataset_type": dataset.dataset_type_name,
+                    "release_date": dataset.release_date,
+                    "release_type": dataset.release_type,
+                }
+            )
+
     response = {
         "genome_id": genome.genome_uuid,
         "assembly_accession": genome.assembly.accession,
@@ -796,6 +830,7 @@ def create_genome_response(genome, assembly_data=None):
         "genome_tag": genome.assembly.url_name if not None else genome.assembly.tol_id,
         "is_reference": genome.assembly.is_reference,
         "assembly": assembly_data,
+        "dataset": datasets_response,
     }
     return response
 
@@ -815,6 +850,12 @@ def fetch_assembly_data(assembly_collection: Collection, assembly_id: str) -> Ma
     return assembly
 
 
+def fetch_dataset_data(grpc_model: GRPC_MODEL, genome_uuid: str) -> List:
+    result = grpc_model.get_datasets_list_by_uuid(genome_uuid)
+    datasets = list(result.datasets)
+    return datasets
+
+
 def get_version_details() -> Dict[str, str]:
     """
     Fetch version details from a 'version_config.ini' file.
diff --git a/grpc_service/grpc_model.py b/grpc_service/grpc_model.py
index 9ff3a887..85c56d7e 100644
--- a/grpc_service/grpc_model.py
+++ b/grpc_service/grpc_model.py
@@ -61,6 +61,18 @@ def get_genome_by_specific_keyword(
         response = self.grpc_stub.GetGenomesBySpecificKeyword(request)
         return response
 
+    def get_datasets_list_by_uuid(self, genome_uuid, release_version=None):
+        logger.debug(
+            "Received RPC for GetDatasetsListByUUID with genome_uuid: '%s', release: %s",
+            genome_uuid,
+            release_version,
+        )
+        request = ensembl_metadata_pb2.DatasetsRequest(
+            genome_uuid=genome_uuid, release_version=release_version
+        )
+        response = self.grpc_stub.GetDatasetsListByUUID(request)
+        return response
+
     def get_release_by_genome_uuid(self, genome_uuid):
         request = ensembl_metadata_pb2.ReleaseVersionRequest(genome_uuid=genome_uuid)
         response = self.grpc_stub.GetReleaseVersionByUUID(request)

From 97c15329d375c36ec915aa0199a7316b2365680c Mon Sep 17 00:00:00 2001
From: Bilal <bilal@ebi.ac.uk>
Date: Wed, 17 Jul 2024 13:46:44 +0100
Subject: [PATCH 10/14] Improve the code logic

---
 common/utils.py                        |  24 ++++
 graphql_service/resolver/gene_model.py | 161 ++++++++++++++++---------
 2 files changed, 126 insertions(+), 59 deletions(-)

diff --git a/common/utils.py b/common/utils.py
index b711e431..f3f93e8c 100644
--- a/common/utils.py
+++ b/common/utils.py
@@ -13,6 +13,9 @@
 """
 
 import logging
+from typing import List
+
+from graphql import GraphQLResolveInfo
 
 logger = logging.getLogger(__name__)
 
@@ -69,3 +72,24 @@ def get_ensembl_metadata_api_version():
                 version = line.strip().split("@")[-1]
                 break
     return version
+
+
+def check_requested_fields(info: GraphQLResolveInfo, fields: List[str]) -> List[bool]:
+    """
+    Check if specific fields are requested in the GraphQL query.
+
+    Args:
+        info (ResolveInfo): The GraphQL resolve information containing query details.
+        fields (List[str]): A list of field names to check for in the query.
+
+    Returns:
+        List[bool]: A list of booleans indicating whether each field is present in the query.
+
+    Usage example:
+        fields_to_check = ["assembly", "dataset"]
+        is_assembly_present, is_dataset_present = check_requested_fields(info, fields_to_check)
+    """
+    requested_fields = [
+        field.name.value for field in info.field_nodes[0].selection_set.selections
+    ]
+    return [field in requested_fields for field in fields]
diff --git a/graphql_service/resolver/gene_model.py b/graphql_service/resolver/gene_model.py
index ad272ff9..f4cb5a68 100644
--- a/graphql_service/resolver/gene_model.py
+++ b/graphql_service/resolver/gene_model.py
@@ -20,6 +20,7 @@
 from graphql import GraphQLResolveInfo, GraphQLError
 from pymongo.database import Database, Collection
 
+from common import utils
 from graphql_service.resolver.data_loaders import BatchLoaders
 
 from graphql_service.resolver.exceptions import (
@@ -687,68 +688,30 @@ async def resolve_region(_, info: GraphQLResolveInfo, by_name: Dict[str, str]) -
     return result
 
 
-def fetch_genome_and_combine(
-    info: GraphQLResolveInfo, grpc_model: GRPC_MODEL, by_keyword: Dict, key: str
+@QUERY_TYPE.field("genomes")
+def resolve_genomes(
+    _, info: GraphQLResolveInfo, by_keyword: Dict[str, str] = None
 ) -> List:
     """
-    Fetches genomes by a specific keyword and combines genome data with assembly data if requested.
+    Resolve the genomes based on provided keyword arguments.
+    Under the hood, this resolver might execute and combine 3 different queries based on the requested data:
+    - The default `get_genome_by_specific_keyword()` gRPC call (Metadata DB)
+    - If `assembly` is requested, `fetch_assembly_data()` is triggered fetching data from Mongo DB
+    - If `dataset` is requested, `fetch_dataset_data()` is triggered which triggers `get_datasets_list_by_uuid()`
+        gRPC call to fetch dataset info (Metadata DB)
 
     Args:
-        info (GraphQLResolveInfo): The GraphQL resolver information containing the field nodes and other query details.
-        grpc_model: The gRPC model to fetch genome data.
-        by_keyword (dict): Dictionary containing the keyword to search genomes by.
-        key (str): The specific key to use for fetching genomes.
+        info (GraphQLResolveInfo): GraphQL resolve information containing query details.
+        by_keyword (Dict[str, str]): Dictionary containing keyword arguments for fetching genomes.
 
     Returns:
-        List: A list of combined genome and assembly data objects. If assembly data is not requested, only genome data is included.
+        List: A list of genomes matching the provided keyword.
 
     Raises:
-        GenomeNotFoundError: If no genomes are found for the given keyword.
+        MissingArgumentException: If 'by_keyword' argument is not provided.
+        GraphQLError: If not exactly one field in 'by_keyword' is provided.
+        GenomeNotFoundError: If no genomes are found matching the provided keyword.
     """
-    # Fetch genomes data from metadata using gRPC
-    result = grpc_model.get_genome_by_specific_keyword(
-        **{key: by_keyword.get(key)},
-        release_version=by_keyword.get("release_version"),
-    )
-    genomes = list(result)
-    if not genomes:
-        raise GenomeNotFoundError(by_keyword)
-
-    requested_fields = [
-        field.name.value for field in info.field_nodes[0].selection_set.selections
-    ]
-    # Check if the assembly and/or dataset fields are requested in the query
-    is_assembly_present = "assembly" in requested_fields
-    is_dataset_present = "dataset" in requested_fields
-
-    combined_results = []
-    for genome in genomes:
-        set_db_conn_for_uuid(info, genome.genome_uuid)
-        connection_db = get_db_conn(info)
-        # logging.debug("Collections in the database:", connection_db.list_collection_names())
-        assembly_collection = connection_db["assembly"]
-        # logging.debug("assembly_collection.name:", assembly_collection.name)
-
-        assembly_data = None
-        dataset_data = None
-        if is_assembly_present:
-            assembly_data = fetch_assembly_data(
-                assembly_collection, genome.assembly.name
-            )
-        if is_dataset_present:
-            dataset_data = fetch_dataset_data(grpc_model, genome.genome_uuid)
-        combined_results.append(
-            create_genome_response(genome, assembly_data, dataset_data)
-        )
-    return combined_results
-
-
-@QUERY_TYPE.field("genomes")
-def resolve_genomes(
-    _, info: GraphQLResolveInfo, by_keyword: Optional[Dict[str, str]] = None
-) -> List:
-
-    # ask them to provide at least one argument
     if not by_keyword:
         raise MissingArgumentException("You must provide 'by_keyword' argument.")
 
@@ -770,8 +733,48 @@ def resolve_genomes(
             "scientific_parlance_name",
             "species_taxonomy_id",
         ]:
+            # if one of the keys is provided
             if by_keyword.get(key):
-                return fetch_genome_and_combine(info, grpc_model, by_keyword, key)
+                # Fetch genomes data from metadata using gRPC
+                result = grpc_model.get_genome_by_specific_keyword(
+                    **{key: by_keyword.get(key)},
+                    release_version=by_keyword.get("release_version"),
+                )
+                genomes = list(result)
+
+                if not genomes:
+                    raise GenomeNotFoundError(by_keyword)
+
+                # Check if the assembly and dataset fields are requested in the query
+                fields_to_check = ["assembly", "dataset"]
+                is_assembly_present, is_dataset_present = utils.check_requested_fields(
+                    info, fields_to_check
+                )
+
+                combined_results = []
+                for genome in genomes:
+                    set_db_conn_for_uuid(info, genome.genome_uuid)
+                    connection_db = get_db_conn(info)
+                    # logging.debug("Collections in the database:", connection_db.list_collection_names())
+                    assembly_collection = connection_db["assembly"]
+                    # logging.debug("assembly_collection.name:", assembly_collection.name)
+
+                    assembly_data = (
+                        fetch_assembly_data(assembly_collection, genome.assembly.name)
+                        if is_assembly_present
+                        else None
+                    )
+                    dataset_data = (
+                        fetch_dataset_data(grpc_model, genome.genome_uuid)
+                        if is_dataset_present
+                        else None
+                    )
+
+                    combined_results.append(
+                        create_genome_response(genome, dataset_data, assembly_data)
+                    )
+
+                return combined_results
 
     return []
 
@@ -787,20 +790,36 @@ def resolve_genome(_, info: GraphQLResolveInfo, by_genome_uuid: Dict[str, str])
     if not genome.genome_uuid:
         raise GenomeNotFoundError(by_genome_uuid)
 
-    # fetch dataset info
-    dataset_data = fetch_dataset_data(grpc_model, genome.genome_uuid)
-    genomes = create_genome_response(
-        genome=genome, assembly_data=None, dataset_data=dataset_data
+    # Check if the dataset fields is requested in the query
+    fields_to_check = ["dataset"]
+    is_dataset_present = utils.check_requested_fields(info, fields_to_check)
+
+    dataset_data = (
+        fetch_dataset_data(grpc_model, genome.genome_uuid)
+        if is_dataset_present
+        else None
     )
+
+    genomes = create_genome_response(genome=genome, dataset_data=dataset_data)
     return genomes
 
 
 def create_genome_response(
     genome: Genome,
-    assembly_data: Optional[Dict[str, Any]] = None,
     dataset_data: Optional[List] = None,
+    assembly_data: Optional[Dict[str, Any]] = None,
 ) -> Dict:
+    """
+    Create a response dictionary for a genome with optional assembly and dataset data.
+
+    Args:
+        genome (Genome): The genome object containing genome-related information.
+        assembly_data (Optional[Dict[str, Any]]): Optional dictionary containing assembly data.
+        dataset_data (Optional[List]): Optional list of dataset objects containing dataset information.
 
+    Returns:
+        Dict: A dictionary containing the genome response data.
+    """
     datasets_response = []
     if dataset_data:
         for dataset in dataset_data:
@@ -836,6 +855,20 @@ def create_genome_response(
 
 
 def fetch_assembly_data(assembly_collection: Collection, assembly_id: str) -> Mapping:
+    """
+    Fetch assembly data from a collection using the assembly ID.
+
+    Args:
+        assembly_collection (Collection): The collection to search for the assembly data.
+        assembly_id (str): The ID of the assembly to fetch.
+
+    Returns:
+        Mapping: The assembly data if found.
+
+    Raises:
+        CollectionNotFoundError: If there is an issue accessing the collection.
+        AssemblyNotFoundError: If the assembly with the given ID is not found.
+    """
     query = {"assembly_id": assembly_id}
     try:
         assembly = assembly_collection.find_one(query)
@@ -851,6 +884,16 @@ def fetch_assembly_data(assembly_collection: Collection, assembly_id: str) -> Ma
 
 
 def fetch_dataset_data(grpc_model: GRPC_MODEL, genome_uuid: str) -> List:
+    """
+    Fetch dataset data using a gRPC model based on the genome UUID.
+
+    Args:
+        grpc_model (GRPC_MODEL): The gRPC model to use for fetching the dataset data.
+        genome_uuid (str): The UUID of the genome for which to fetch dataset data.
+
+    Returns:
+        List: A list of datasets associated with the given genome UUID.
+    """
     result = grpc_model.get_datasets_list_by_uuid(genome_uuid)
     datasets = list(result.datasets)
     return datasets

From b9425726fa77e9880199c4bc6744f2371de84a96 Mon Sep 17 00:00:00 2001
From: Bilal <bilal@ebi.ac.uk>
Date: Thu, 18 Jul 2024 09:34:15 +0100
Subject: [PATCH 11/14] Made symbol param optional in genes and transcript
 resolvers (EA-1228)

---
 common/schemas/query.graphql           |  2 +-
 graphql_service/resolver/gene_model.py | 10 +++++++---
 2 files changed, 8 insertions(+), 4 deletions(-)

diff --git a/common/schemas/query.graphql b/common/schemas/query.graphql
index cf58bfcf..dcefe71c 100644
--- a/common/schemas/query.graphql
+++ b/common/schemas/query.graphql
@@ -26,7 +26,7 @@ type Query {
 }
 
 input SymbolInput {
-  symbol: String!
+  symbol: String
   genome_id: String!
 }
 
diff --git a/graphql_service/resolver/gene_model.py b/graphql_service/resolver/gene_model.py
index f4cb5a68..ad7cf025 100644
--- a/graphql_service/resolver/gene_model.py
+++ b/graphql_service/resolver/gene_model.py
@@ -113,12 +113,16 @@ def resolve_gene(
 
 @QUERY_TYPE.field("genes")
 def resolve_genes(_, info: GraphQLResolveInfo, by_symbol: Dict[str, str]) -> List:
-    "Load Genes via potentially ambiguous symbol"
+    """
+    Load Genes via potentially ambiguous symbol
+    Or
+    If no Symbol is specified, get all related genes (this feature might be removed later)
+    """
 
     query = {
         "genome_id": by_symbol["genome_id"],
         "type": "Gene",
-        "symbol": by_symbol["symbol"],
+        "symbol": by_symbol.get("symbol"),  # this makes symbol optional
     }
 
     set_db_conn_for_uuid(info, by_symbol["genome_id"])
@@ -227,7 +231,7 @@ def resolve_transcript(
     query: Dict[str, Any] = {"type": "Transcript"}
     genome_id = None
     if by_symbol:
-        query["symbol"] = by_symbol["symbol"]
+        query["symbol"] = by_symbol.get("symbol")  # this makes symbol optional
         query["genome_id"] = by_symbol["genome_id"]
         genome_id = by_symbol["genome_id"]
     if by_id:

From bc49c44b1947ca85ca0192f7a01806cbb3908d86 Mon Sep 17 00:00:00 2001
From: Bilal <bilal@ebi.ac.uk>
Date: Fri, 19 Jul 2024 15:53:16 +0100
Subject: [PATCH 12/14] fix mypy errors

---
 common/utils.py                        | 15 ++++++++++-----
 graphql_service/resolver/gene_model.py |  4 ++--
 2 files changed, 12 insertions(+), 7 deletions(-)

diff --git a/common/utils.py b/common/utils.py
index f3f93e8c..70b28603 100644
--- a/common/utils.py
+++ b/common/utils.py
@@ -15,7 +15,7 @@
 import logging
 from typing import List
 
-from graphql import GraphQLResolveInfo
+from graphql import GraphQLResolveInfo, FieldNode
 
 logger = logging.getLogger(__name__)
 
@@ -79,7 +79,7 @@ def check_requested_fields(info: GraphQLResolveInfo, fields: List[str]) -> List[
     Check if specific fields are requested in the GraphQL query.
 
     Args:
-        info (ResolveInfo): The GraphQL resolve information containing query details.
+        info (GraphQLResolveInfo): The GraphQL resolve information containing query details.
         fields (List[str]): A list of field names to check for in the query.
 
     Returns:
@@ -89,7 +89,12 @@ def check_requested_fields(info: GraphQLResolveInfo, fields: List[str]) -> List[
         fields_to_check = ["assembly", "dataset"]
         is_assembly_present, is_dataset_present = check_requested_fields(info, fields_to_check)
     """
-    requested_fields = [
-        field.name.value for field in info.field_nodes[0].selection_set.selections
-    ]
+    requested_fields = []
+    if info.field_nodes:
+        selection_set = info.field_nodes[0].selection_set
+        if selection_set and selection_set.selections:
+            for field in selection_set.selections:
+                if isinstance(field, FieldNode) and field.name and field.name.value:
+                    requested_fields.append(field.name.value)
+
     return [field in requested_fields for field in fields]
diff --git a/graphql_service/resolver/gene_model.py b/graphql_service/resolver/gene_model.py
index 496c846b..829793fd 100644
--- a/graphql_service/resolver/gene_model.py
+++ b/graphql_service/resolver/gene_model.py
@@ -538,7 +538,7 @@ def resolve_product_by_id(
 
 
 @PRODUCT_TYPE.field("product_generating_context")
-def resolve_pgc_for_product(product: Dict, info: GraphQLResolveInfo) -> Dict:
+def resolve_pgc_for_product(product: Dict, info: GraphQLResolveInfo) -> Optional[Dict]:
     pipeline = [
         {
             "$match": {
@@ -856,7 +856,7 @@ def resolve_genome(_, info: GraphQLResolveInfo, by_genome_uuid: Dict[str, str])
 def create_genome_response(
     genome: Genome,
     dataset_data: Optional[List] = None,
-    assembly_data: Optional[Dict[str, Any]] = None,
+    assembly_data: Optional[Mapping[Any, Any]] = None,
 ) -> Dict:
     """
     Create a response dictionary for a genome with optional assembly and dataset data.

From 04760e4a7a453cca3a8e3d5fba0b59cef5ed81fe Mon Sep 17 00:00:00 2001
From: Bilal <bilal@ebi.ac.uk>
Date: Fri, 19 Jul 2024 15:54:22 +0100
Subject: [PATCH 13/14] add mypy to github actions

---
 .github/workflows/tests.yml | 11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

diff --git a/.github/workflows/tests.yml b/.github/workflows/tests.yml
index f21e7573..375e8e84 100644
--- a/.github/workflows/tests.yml
+++ b/.github/workflows/tests.yml
@@ -1,5 +1,5 @@
 # Workflow name
-name: PyTest, Black and Pylint
+name: PyTest, Black, Pylint and Mypy
 
 # Controls when the workflow will run
 on:
@@ -17,7 +17,7 @@ jobs:
   # This workflow contains a single job called "tests"
   tests:
     # The type of runner that the job will run on and timeout in minutes
-    name: Run Python Tests, Black formatter and Pylint
+    name: Run Python Tests, Black formatter, Pylint and Mypy
     runs-on: ubuntu-latest
     timeout-minutes: 10
 
@@ -32,7 +32,7 @@ jobs:
       - name: Check out repository code
         uses: actions/checkout@v3
 
-    # Set up Python version from the matrix
+      # Set up Python version from the matrix
       - name: Set up Python ${{ matrix.python-version }}
         uses: actions/setup-python@v4
         with:
@@ -59,3 +59,8 @@ jobs:
       - name: Run Pylint
         run: |
           pylint $(git ls-files '*.py') --fail-under=9.5
+
+      # Run Mypy
+      - name: Run Mypy type checker
+        run: |
+          mypy graphql_service

From 1274e8cac8368001e4b7f3592fb5c7f3808322dd Mon Sep 17 00:00:00 2001
From: Bilal <bilal@ebi.ac.uk>
Date: Mon, 22 Jul 2024 09:30:38 +0100
Subject: [PATCH 14/14] update metadata-api tag

---
 requirements.txt | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/requirements.txt b/requirements.txt
index e940b295..30c06c5c 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -5,6 +5,6 @@ aiodataloader==0.2.1
 ariadne==0.19.1
 python-dotenv==0.19.2
 uvicorn==0.18.1
-ensembl-metadata-api@git+https://github.com/Ensembl/ensembl-metadata-api.git@2.1.0a3
+ensembl-metadata-api@git+https://github.com/Ensembl/ensembl-metadata-api.git@2.2.0a1
 grpcio==1.62.0
 grpcio-tools==1.62.0