continue method to create kegg annotations

.gitignore

@@ -7,3 +7,4 @@
 # Python
 __pycache__
 *.egg-info/
+notebooks/
\ No newline at end of file

backend/app/app/core/use_cases/db_creation/annotation.py

@@ -5,14 +5,13 @@ import inject
 
 import pandas as pd
 
-# from app.core.models.annotations import KeggOrthologyAnnotation
 from app.core.repositories.annotations import KeggOrthologyAnnotationsRepo
 from app.core.repositories.experiment import ExperimentsRepo
 from app.core.repositories.gene import GenesRepo
 from app.core.repositories.kegg import KeggOrthologysRepo
 
-# from app.core.schemas.entities.annotations import KeggOrthologyAnnotationCreate
 from app.core.schemas.tasks.db import DbOperation
+from app.core.schemas.entities.annotations import KeggOrthologyAnnotationCreate
 
 logger = logging.getLogger()
 
@@ -21,7 +20,8 @@ class CreateGeneAnnotationsUseCase:
     BASE_OPERATION_NAME = "create_gene_annotations"
     ID_COL = "entry_id"
 
-    @inject.autoparams("repo")
+    @inject.autoparams("genes_repo")
+    @inject.autoparams("experiments_repo")
     def __init__(
         self,
         annotations_df: pd.DataFrame,
@@ -39,27 +39,52 @@ class CreateGeneAnnotationsUseCase:
         self.df = annotations_df
         self.experiment_id = experiment_id
         self._experiments_repo = experiments_repo
+        self._genes_repo = genes_repo
         self.batch_size = batch_size
         self.db_operations: List[DbOperation] = []
         self.to_create = []
 
-    def _create_unkown_annotations(self, col: str):
-        message = f"{col} is not a valid column name for annotations. Skipped."
+    def _create_unknown_annotations(self, **kwargs):
+        message = (
+            f"{self.df.columns[1]} is not a valid column name for annotations. Skipped."
+        )
         logger.warning(message)
-        self.db_operations.append(DbOperation(name="creation_skipped", extra=message))
+        self.db_operations.append(
+            DbOperation(name="creation_skipped", extra={"message": message})
+        )
 
+    @inject.autoparams("kegg_orthology_annotations_repo")
+    @inject.autoparams("kegg_orthologys_repo")
     def _create_kegg_annotations(
         self,
         kegg_orthology_annotations_repo: KeggOrthologyAnnotationsRepo,
         kegg_orthologys_repo: KeggOrthologysRepo,
+        **kwargs,
     ):
         # Perform KEGG annotations creation
         db_operation = DbOperation(name="create-kegg-annotations")
-        return db_operation
+        # Retrieve all gene db ids
+        gene_db_dict = self._genes_repo.get_gene_db_ids(
+            list(set(self.df.iloc[:, 0])), **kwargs
+        )
+        # Retrieve all kegg db ids
+        keggs = kegg_orthologys_repo.get_entries(list(set(self.df["kegg"])), **kwargs)
+        kegg_db_dict = {kegg.kegg_id: kegg.id for kegg in keggs}
+        # Create annotations
+        # - Create format for creation from df
+        for kegg_id, subdf in self.df.groupby("kegg"):
+            annotation = KeggOrthologyAnnotationCreate(
+                experiment_id=self.experiment_id,
+                kegg_id=kegg_db_dict[kegg_id],
+                genes=[gene_db_dict[gene_id] for gene_id in subdf.iloc[:, 0]],
+            )
+            kegg_orthology_annotations_repo.create(annotation, **kwargs)
+            db_operation.created += 1
+        self.db_operations.append(db_operation)
 
-    def create_annotations(self):
+    def create_annotations(self, **kwargs):
         col = self.df.columns[1]
-        getattr(
-            self, f"_create_{col}_annotations", self._create_unkown_annotations(col)
-        )()
+        getattr(self, f"_create_{col}_annotations", self._create_unknown_annotations)(
+            **kwargs
+        )
         return self.db_operations

backend/app/pyproject.toml

@@ -31,6 +31,8 @@ flake8 = "^4.0.1"
 invoke = "^1.6.0"
 pytest-cov = "^3.0.0"
 snakeviz = "^2.1.1"
+jupyter = "^1.0.0"
+importlib-resources = "^5.4.0"
 
 [tool.poetry.scripts]
 create_test_db = "app.cli.db.create_test_db:run"

data_test/genes/kegg.csv

 gene,kegg
 gene1,K00035
 gene2,K00022
+gene2,K00029
 gene3,K00029
 gene4,K02229
\ No newline at end of file