wip to get annotation by analysis name'

backend/src/core/annotation.py

@@ -3,8 +3,8 @@
 import logging
 import queue
 
-from backend.src.repository.analysis_collection import AnalysisCollection
-from backend.src.repository.genomic_unit_collection import GenomicUnitCollection
+from ..repository.analysis_collection import AnalysisCollection
+from ..repository.genomic_unit_collection import GenomicUnitCollection
 
 from .annotation_task import AnnotationTaskFactory, VersionAnnotationTask
 from ..models.analysis import Analysis
@@ -108,7 +108,7 @@ def process_tasks(annotation_queue: AnnotationQueue, analysis_name: str, genomic
                         missing_dependencies = annotation_unit.get_missing_dependencies()
                         for missing_dataset_name in missing_dependencies:
                             # missing_dataset_name
-                            dependency_dataset = analysis_collection.get_manifest_dataset(analysis_name, missing_dataset_name)
+                            dependency_dataset = analysis_collection.get_manifest_dataset_config(analysis_name, missing_dataset_name)
                             dependency_annotation_unit = AnnotationUnit(annotation_unit.genomic_unit, dependency_dataset)
                             annotation_value = genomic_unit_collection.find_genomic_unit_annotation_value(
                                 dependency_annotation_unit

backend/src/core/annotation_unit.py

@@ -9,7 +9,7 @@ class AnnotationUnit:
     def __init__(self, genomic_unit, dataset):
         self.genomic_unit = copy.deepcopy(genomic_unit)
         self.dataset = dataset
-        self.version = "" if not dataset['version'] else dataset['version']
+        self.version = ""
 
     def get_genomic_unit(self):
         """Returs 'unit' from genomic_unit"""

backend/src/core/dataset_manifest.py

@@ -0,0 +1,9 @@
+
+
+class DatasetManifest:
+  """a helper to streamline getting the config for a dataset"""
+
+  def __init__(self, manifest):
+    self.manifest = manifest
+
+

backend/src/repository/analysis_collection.py

@@ -6,7 +6,7 @@
 
 from pymongo import ReturnDocument
 
-from backend.src.core.annotation_unit import AnnotationUnit
+from ..core.annotation_unit import AnnotationUnit
 
 from ..models.analysis import Section
 from ..models.event import Event
@@ -148,13 +148,28 @@ def add_dataset_to_manifest(self, analysis_name: str, annotation_unit: Annotatio
 
         return updated_document['manifest']
 
-    def get_manifest_dataset(self, analysis_name: str, dataset_name: str):
+    def get_manifest_dataset_config(self, analysis_name: str, dataset_name: str):
         dataset_attribute = f"manifest.{dataset_name}"
-        return self.collection.find_one({
+        result = self.collection.find_one({
             "name": analysis_name,
             dataset_attribute : {'$exists': True }
         })
 
+        if not result:
+            return None
+
+        return {
+            "data_set": dataset_name,
+            "data_source": result[dataset_name]['data_source'],
+            "version": result[dataset_name]['version']
+        }
+
+    def get_dataset_manifest(self, analysis_name):
+        analysis = self.find_by_name(analysis_name)
+        if analysis is None:
+            return
+
+        return analysis['manifest']
 
     def create_analysis(self, analysis_data: dict):
         """Creates a new analysis if the name does not already exist"""

backend/src/routers/annotation_router.py

@@ -49,7 +49,7 @@ def annotate_analysis(
     return {"name": f"{name} annotations queued."}
 
 
-@router.get("/gene/{gene}")
+@router.get("/gene/{gene}/analysis/{analysis_name}")
 def get_annotations_by_gene(gene, repositories=Depends(database)):
     """Returns annotations data by calling method to find annotations by gene"""
 
@@ -72,8 +72,8 @@ def get_annotations_by_gene(gene, repositories=Depends(database)):
     return annotations
 
 
-@router.get("/hgvsVariant/{variant}/analysis/CPAM0002")
-def get_annotations_by_hgvs_variant(variant: str, repositories=Depends(database)):
+@router.get("/hgvsVariant/{variant}/analysis/{analysis_name}")
+def get_annotations_by_hgvs_variant(variant: str, analysis_name: str, repositories=Depends(database)):
     """Returns annotations data by calling method to find annotations for variant and relevant transcripts
     by HGVS Variant"""
 
@@ -82,6 +82,7 @@ def get_annotations_by_hgvs_variant(variant: str, repositories=Depends(database)
         'unit': variant,
     }
 
+    dataset_manifest = repositories["analyses"].get_dataset_manifest(analysis_name)
     queried_genomic_unit = repositories["genomic_unit"].find_genomic_unit(genomic_unit)
 
     if queried_genomic_unit is None:
@@ -90,8 +91,12 @@ def get_annotations_by_hgvs_variant(variant: str, repositories=Depends(database)
     annotations = {}
     for annotation in queried_genomic_unit['annotations']:
         for dataset in annotation:
-            if len(annotation[dataset]) > 0:
-                annotations[dataset] = annotation[dataset][0]['value']
+            dataset_config = next((config for config in dataset_manifest if dataset in config), None)
+            if dataset_config is None:
+                continue
+            "annotation[dataset][0]['value']"
+            found_dataset = next((by_version for by_version in annotation[dataset] if dataset in dataset_manifest), None)
+            annotations[dataset] = 
 
     transcript_annotation_list = []
     for transcript_annotation in queried_genomic_unit['transcripts']:

backend/tests/fixtures/analysis-CPAM0002.json

@@ -38,6 +38,11 @@
         "data_source": "Ensembl",
         "version": "rosalution-manifest-00"
       }
+    },{
+      "HGNC_ID": {
+        "data_source": "Ensembl",
+        "version": "rosalution-manifest-00"
+      }
     }
   ],
   "genomic_units": [

backend/tests/fixtures/analysis-CPAM0046.json

@@ -38,7 +38,12 @@
        "data_source": "Ensembl",
        "version": "rosalution-manifest-00"
      }
-   }],
+   },{
+      "HGNC_ID": {
+        "data_source": "Ensembl",
+        "version": "rosalution-manifest-00"
+      }
+    }],
   "genomic_units":[
      {
         "gene":"LMNA",

backend/tests/fixtures/analysis-CPAM0047.json

@@ -38,7 +38,12 @@
        "data_source": "Ensembl",
        "version": "rosalution-manifest-00"
      }
-   }],
+   },{
+      "HGNC_ID": {
+        "data_source": "Ensembl",
+        "version": "rosalution-manifest-00"
+      }
+    }],
   "genomic_units":[
      {
         "gene":"SBF1",

backend/tests/fixtures/analysis-CPAM0112.json

@@ -38,6 +38,11 @@
         "data_source": "Ensembl",
         "version": "rosalution-manifest-00"
       }
+    },{
+      "HGNC_ID": {
+        "data_source": "Ensembl",
+        "version": "rosalution-manifest-00"
+      }
     }],
   "genomic_units": [
     {

backend/tests/unit/conftest.py

@@ -115,6 +115,28 @@ def fixture_annotation_config_collection(annotation_config_collection_json):
     mock_collection.find_one = Mock(return_value=read_test_fixture("annotations-config.json"))
     return AnnotationConfigCollection(mock_collection)
 
+@pytest.fixture(name='get_dataset_manifest_config')
+def get_dataset_manifest_config(analysis_collection_json):
+    """Fixture factory method to create an dataset from the genomic unit information and name of the datset."""
+
+    def _create_dataset_manifest(analysis_name, dataset_name):
+        """Method to create the dataset manifest config"""
+
+        analysis_json = next((item for item in analysis_collection_json if item['name'] == analysis_name),
+                        None)
+        analysis = Analysis(**analysis_json)
+        dataset_manifest = next((item for item in analysis.manifest if dataset_name in item),
+                None)
+
+        dataset_config = {
+            "data_set": dataset_name,
+            "data_source": dataset_manifest[dataset_name]['data_source'],
+            "version": dataset_manifest[dataset_name]['version']
+        }
+
+        return dataset_config
+
+    return _create_dataset_manifest
 
 @pytest.fixture(name='get_annotation_unit')
 def get_standard_annotation_unit(annotation_config_collection_json):

backend/tests/unit/core/test_annotate.py

@@ -2,8 +2,10 @@
 from unittest.mock import Mock, patch
 import pytest
 
+from src.core.annotation_unit import AnnotationUnit
 from src.core.annotation import AnnotationService
 from src.enums import GenomicUnitType
+from src.repository.analysis_collection import AnalysisCollection
 from src.repository.genomic_unit_collection import GenomicUnitCollection
 
 
@@ -81,7 +83,7 @@ def fixture_cpam0046_hgvs_variant(cpam0046_analysis):
 
 
 @pytest.fixture(name="process_cpam0002_tasks")
-def fixture_extract_and_annotate_cpam0002(cpam0002_annotation_queue):
+def fixture_extract_and_annotate_cpam0002(cpam0002_annotation_queue, get_dataset_manifest_config):
     """
     Emulates processing the annotations for the configured genomic unit's datasets within the CPAM0002 analysis.
     """
@@ -101,12 +103,14 @@ def fixture_extract_and_annotate_cpam0002(cpam0002_annotation_queue):
     ):
         skip_depends = SkipDepedencies()
         mock_genomic_unit_collection = Mock(spec=GenomicUnitCollection)
+        mock_analysis_collection = Mock(spec=AnalysisCollection)
         mock_genomic_unit_collection.find_genomic_unit_annotation_value.side_effect = (
             skip_depends.skip_hgncid_get_value_first_time_mock
         )
+        mock_analysis_collection.get_manifest_dataset_config.return_value = get_dataset_manifest_config("CPAM0002",'HGNC_ID')
         mock_genomic_unit_collection.annotation_exist.return_value = False
 
-        AnnotationService.process_tasks(cpam0002_annotation_queue, mock_genomic_unit_collection)
+        AnnotationService.process_tasks(cpam0002_annotation_queue, "CPAM0002", mock_genomic_unit_collection,mock_analysis_collection)
         yield {
             'extract': extract_task_annotate, 'version': version_task_annotate, 'http': http_task_annotate,
             'none': none_task_annotate, 'forge': forge_task_annotate,
@@ -126,14 +130,15 @@ def __init__(self, dependencies_to_skip=None):
 
     def skip_hgncid_get_value_first_time_mock(self, *args):
         """ Mock method that tracks if the provided dependencies are one of the ones indicated to skip"""
-        unit, name = args
-
+        annotation_unit = args[0]
+        name = annotation_unit.get_dataset_name()
+        genomic_unit = annotation_unit.get_genomic_unit()
         should_skip = (name in self.to_skip and name not in self.skip_tracker)
-        return self.skip_tracker.setdefault(name, None) if should_skip else f"{unit['unit']}-{name}-value"
+        return self.skip_tracker.setdefault(name, None) if should_skip else f"{genomic_unit}-{name}-value"
 
 
 @pytest.fixture(name="process_cpam0046_tasks")
-def fixture_extract_and_annotate_cpam0046(cpam0046_annotation_queue):
+def fixture_extract_and_annotate_cpam0046(cpam0046_annotation_queue, get_dataset_manifest_config):
     """
     Emulates processing the annotations for the configured genomic unit's datasets within the CPAM0046 analysis.
     """
@@ -153,12 +158,15 @@ def fixture_extract_and_annotate_cpam0046(cpam0046_annotation_queue):
     ):
         skip_depends = SkipDepedencies()
         mock_genomic_unit_collection = Mock(spec=GenomicUnitCollection)
+        mock_analysis_collection = Mock(spec=AnalysisCollection)
         mock_genomic_unit_collection.find_genomic_unit_annotation_value.side_effect = (
             skip_depends.skip_hgncid_get_value_first_time_mock
         )
+        dependency_dataset =  get_dataset_manifest_config("CPAM0046", 'HGNC_ID')
+        mock_analysis_collection.get_manifest_dataset_config.return_value = dependency_dataset
         mock_genomic_unit_collection.annotation_exist.return_value = False
 
-        AnnotationService.process_tasks(cpam0046_annotation_queue, mock_genomic_unit_collection)
+        AnnotationService.process_tasks(cpam0046_annotation_queue, "CPAM0046", mock_genomic_unit_collection, mock_analysis_collection)
         yield {
             'extract': extract_task_annotate, 'version': version_task_annotate, 'http': http_task_annotate,
             'none': none_task_annotate, 'forge': forge_task_annotate,