wip

backend/src/core/annotation.py

@@ -3,6 +3,9 @@
 import logging
 import queue
 
+from backend.src.repository.analysis_collection import AnalysisCollection
+from backend.src.repository.genomic_unit_collection import GenomicUnitCollection
+
 from .annotation_task import AnnotationTaskFactory, VersionAnnotationTask
 from ..models.analysis import Analysis
 from ..repository.annotation_config_collection import AnnotationConfigCollection
@@ -83,7 +86,7 @@ def queue_annotation_tasks(self, analysis: Analysis, annotation_task_queue: Anno
  annotation_task_queue.put(annotation_unit_queued)
 
  @staticmethod
- def process_tasks(annotation_queue, genomic_unit_collection): # pylint: disable=too-many-branches
+ def process_tasks(annotation_queue: AnnotationQueue, analysis_name: str, genomic_unit_collection: GenomicUnitCollection, analysis_collection: AnalysisCollection): # pylint: disable=too-many-branches
  """Processes items that have been added to the queue"""
  logger.info("%s Processing annotation tasks queue ...", annotation_log_label())
 
@@ -104,8 +107,11 @@ def process_tasks(annotation_queue, genomic_unit_collection): # pylint: disable
  if annotation_unit.has_dependencies():
  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_annotation_unit = AnnotationUnit(annotation_unit.genomic_unit, dependency_dataset)
  annotation_value = genomic_unit_collection.find_genomic_unit_annotation_value(
- annotation_unit.genomic_unit, missing_dataset_name
+ dependency_annotation_unit
  )
  if annotation_value:
  annotation_unit.set_annotation_for_dependency(missing_dataset_name, annotation_value)
@@ -154,6 +160,7 @@ def process_tasks(annotation_queue, genomic_unit_collection): # pylint: disable
  genomic_unit_collection.annotate_genomic_unit(
  task.annotation_unit.genomic_unit, annotation
  )
+ analysis_collection.add_dataset_to_manifest(analysis_name, annotation_unit)
 
  except FileNotFoundError as error:
  logger.info(

backend/src/core/annotation_task.py

@@ -240,17 +240,17 @@ def annotate(self):
 
  def get_annotation_version_from_rest(self):
  """Gets version for rest type and returns the version data"""
- version_from_rest = "REST-VERSION-PLACEHOLDER"
+ version_from_rest = "rosalution-temp-manifest-00"
  return version_from_rest
 
  def get_annotation_version_from_rosalution(self):
  """Gets version for rosalution type and returns the version data"""
- version_from_rosalution = "ROSALUTION-VERSION-PLACEHOLDER"
+ version_from_rosalution = "rosalution-temp-manifest-00"
  return version_from_rosalution
 
  def get_annotation_version_from_date(self):
  """Gets version for date type and returns the version data"""
- version_from_date = {'date': "DATE-VERSION-PLACEHOLDER"}
+ version_from_date = "rosalution-temp-manifest-00"
  # getting version from date
  return version_from_date
 

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 = ""
+ self.version = "" if not dataset['version'] else dataset['version']
 
  def get_genomic_unit(self):
  """Returs 'unit' from genomic_unit"""

backend/src/models/analysis.py

@@ -90,6 +90,8 @@ class Analysis(BaseAnalysis):
  sections: List[Section] = []
  discussions: List = []
  supporting_evidence_files: List = []
+ manifest: List = [
+ ]
 
  def units_to_annotate(self):
  """Returns the types of genomic units within the analysis"""

backend/src/repository/analysis_collection.py

@@ -6,6 +6,8 @@
 
 from pymongo import ReturnDocument
 
+from backend.src.core.annotation_unit import AnnotationUnit
+
 from ..models.analysis import Section
 from ..models.event import Event
 from ..enums import EventType
@@ -130,6 +132,30 @@ def get_genomic_units(self, analysis_name: str):
 
  return genomic_units_return
 
+ def add_dataset_to_manifest(self, analysis_name: str, annotation_unit: AnnotationUnit):
+ """Adds this dataset and its version to this Analysis."""
+
+ dataset = {
+ annotation_unit.get_dataset_name(): {
+ annotation_unit.get_dataset_source(),
+ annotation_unit.get_version()
+ }
+ }
+
+ updated_document = self.collection.find_one_and_update({"name": analysis_name},
+ {"$push": {"manifest": dataset}},
+ return_document=ReturnDocument.AFTER)
+
+ return updated_document['manifest']
+
+ def get_manifest_dataset(self, analysis_name: str, dataset_name: str):
+ dataset_attribute = f"manifest.{dataset_name}"
+ return self.collection.find_one({
+ "name": analysis_name,
+ dataset_attribute : {'$exists': True }
+ })
+
+
  def create_analysis(self, analysis_data: dict):
  """Creates a new analysis if the name does not already exist"""
  if self.collection.find_one({"name": analysis_data["name"]}) is not None:

backend/src/repository/genomic_unit_collection.py

@@ -38,10 +38,7 @@ def __find_genomic_unit_query__(self, annotation_unit: AnnotationUnit):
  """
  # find_query = {
  # 'gene': 'VMA21',
- # 'annotations.CADD': {'$exists': True },
- # 'annotations.CADD.data_source': 'Ensembl',
- # 'annotations.CADD.version': 'HARD_CODED_VERSION'
- #}}
+ #}
  """
  genomic_unit_type_string = annotation_unit.get_genomic_unit_type_string()
  genomic_unit_name = annotation_unit.get_genomic_unit()
@@ -54,7 +51,7 @@ def __find_annotation_query__(self, annotation_unit: AnnotationUnit):
  'annotations.CADD': {'$exists': True },
  'annotations.CADD.data_source': 'Ensembl',
  'annotations.CADD.version': 'HARD_CODED_VERSION'
- }}
+ }
  """
  find_query = self.__find_genomic_unit_query__(annotation_unit)
  data_set_name = annotation_unit.get_dataset_name()
@@ -78,7 +75,7 @@ def annotation_exist(self, annotation_unit: AnnotationUnit):
  data_set_name = annotation_unit.get_dataset_name()
  dataset_version = annotation_unit.get_version()
  dataset_source = annotation_unit.get_dataset_source()
-
+ 
  find_query = self.__find_genomic_unit_query__(annotation_unit)
 
  if annotation_unit.is_transcript_dataset():
@@ -103,11 +100,22 @@ def find_genomic_unit_annotation_value(self, annotation_unit: AnnotationUnit):
 
  dataset_name = annotation_unit.get_dataset_name()
  find_query = self.__find_annotation_query__(annotation_unit)
+
+ if dataset_name == "HPO_NCBI_GENE_ID" and annotation_unit.get_genomic_unit() == "DLG4":
+ logger.info("\n\n\n")
+ logger.info(f"{find_query}")
+ logger.fino("\n\n\n")
+
  projection = {f"annotations.{dataset_name}.value.$": 1, "_id": 0}
  result = self.collection.find_one(find_query, projection)
 
  if result is None:
  return None
+
+ if dataset_name == "HPO_NCBI_GENE_ID" and annotation_unit.get_genomic_unit() == "DLG4":
+ logger.info("\n\n\n")
+ logger.info(f"{result}")
+ logger.fino("\n\n\n")
 
  return next((
  annotation[dataset_name][0].get('value')
@@ -247,6 +255,7 @@ def create_genomic_unit(self, genomic_unit):
  # Make sure the genomic unit doesn't already exist
  if self.collection.find_one(genomic_unit):
  logging.info("Genomic unit already exists, skipping creation")
+ return
 
  self.collection.insert_one(genomic_unit)
  return

backend/tests/fixtures/analysis-CPAM0002.json

@@ -2,12 +2,42 @@
  "name": "CPAM0002",
  "description": "Vacuolar myopathy with autophagy, X-linked vacuolar myopathy with autophagy",
  "nominated_by": "Dr. Person One",
- "dataset_configuration": [
+ "manifest": [
  {
  "Polyphen Prediction": {
  "data_source": "Ensembl",
  "version": "112"
  }
+ }, {
+ "Entrez Gene Id": {
+ "data_source": "Ensembl",
+ "version": "rosalution-manifest-00"
+ }
+ },{
+ "HPO_NCBI_GENE_ID": {
+ "data_source": "Ensembl",
+ "version": "2024-09-06"
+ }
+ },{
+ "Ensembl Gene Id": {
+ "data_source": "Ensembl",
+ "version": "112"
+ }
+ },{
+ "ClinGen_gene_url": {
+ "data_source": "Ensembl",
+ "version": "rosalution-manifest-00"
+ }
+ },{
+ "OMIM": {
+ "data_source": "Ensembl",
+ "version": "2024-09-06"
+ }
+ },{
+ "ClinVar_Variantion_Id": {
+ "data_source": "Ensembl",
+ "version": "rosalution-manifest-00"
+ }
  }
  ],
  "genomic_units": [

backend/tests/fixtures/analysis-CPAM0046.json

@@ -2,13 +2,43 @@
  "name":"CPAM0046",
  "description":": LMNA-related congenital muscular dystropy",
  "nominated_by":"Dr. Person Two",
- "dataset_configuration": [
+ "manifest": [
  {
  "Polyphen Prediction": {
  "data_source": "Ensembl",
- "version": "120"}
- }
- ],
+ "version": "112"
+ }
+ }, {
+ "Entrez Gene Id": {
+ "data_source": "Ensembl",
+ "version": "rosalution-manifest-00"
+ }
+ },{
+ "HPO_NCBI_GENE_ID": {
+ "data_source": "Ensembl",
+ "version": "2024-09-06"
+ }
+ },{
+ "Ensembl Gene Id": {
+ "data_source": "Ensembl",
+ "version": "112"
+ }
+ },{
+ "ClinGen_gene_url": {
+ "data_source": "Ensembl",
+ "version": "rosalution-manifest-00"
+ }
+ },{
+ "OMIM": {
+ "data_source": "Ensembl",
+ "version": "2024-09-06"
+ }
+ },{
+ "ClinVar_Variantion_Id": {
+ "data_source": "Ensembl",
+ "version": "rosalution-manifest-00"
+ }
+ }],
  "genomic_units":[
  {
  "gene":"LMNA",

backend/tests/fixtures/analysis-CPAM0047.json

@@ -2,6 +2,43 @@
  "name":"CPAM0047",
  "description":"Congenital variant of Rett syndrome",
  "nominated_by":"CMT4B3 Foundation",
+ "manifest": [
+ {
+ "Polyphen Prediction": {
+ "data_source": "Ensembl",
+ "version": "112"
+ }
+ }, {
+ "Entrez Gene Id": {
+ "data_source": "Ensembl",
+ "version": "rosalution-manifest-00"
+ }
+ },{
+ "HPO_NCBI_GENE_ID": {
+ "data_source": "Ensembl",
+ "version": "2024-09-06"
+ }
+ },{
+ "Ensembl Gene Id": {
+ "data_source": "Ensembl",
+ "version": "112"
+ }
+ },{
+ "ClinGen_gene_url": {
+ "data_source": "Ensembl",
+ "version": "rosalution-manifest-00"
+ }
+ },{
+ "OMIM": {
+ "data_source": "Ensembl",
+ "version": "2024-09-06"
+ }
+ },{
+ "ClinVar_Variantion_Id": {
+ "data_source": "Ensembl",
+ "version": "rosalution-manifest-00"
+ }
+ }],
  "genomic_units":[
  {
  "gene":"SBF1",

backend/tests/fixtures/analysis-CPAM0112.json

@@ -2,6 +2,43 @@
  "name": "CPAM0112",
  "description": "",
  "nominated_by": "",
+ "manifest": [
+ {
+ "Polyphen Prediction": {
+ "data_source": "Ensembl",
+ "version": "112"
+ }
+ }, {
+ "Entrez Gene Id": {
+ "data_source": "Ensembl",
+ "version": "rosalution-manifest-00"
+ }
+ },{
+ "HPO_NCBI_GENE_ID": {
+ "data_source": "Ensembl",
+ "version": "2024-09-06"
+ }
+ },{
+ "Ensembl Gene Id": {
+ "data_source": "Ensembl",
+ "version": "112"
+ }
+ },{
+ "ClinGen_gene_url": {
+ "data_source": "Ensembl",
+ "version": "rosalution-manifest-00"
+ }
+ },{
+ "OMIM": {
+ "data_source": "Ensembl",
+ "version": "2024-09-06"
+ }
+ },{
+ "ClinVar_Variantion_Id": {
+ "data_source": "Ensembl",
+ "version": "rosalution-manifest-00"
+ }
+ }],
  "genomic_units": [
  {
  "gene": "VMA21",