Fix RNA uploads/delivery message

cg/meta/upload/scout/uploadscoutapi.py

@@ -4,7 +4,6 @@
 from pathlib import Path
 
 from housekeeper.store.models import File, Version
-from pydantic.dataclasses import dataclass
 
 from cg.apps.housekeeper.hk import HousekeeperAPI
 from cg.apps.lims import LimsAPI
@@ -26,22 +25,13 @@
 from cg.meta.workflow.analysis import AnalysisAPI
 from cg.meta.workflow.utils.genome_build_helpers import genome_to_scout_format, get_genome_build
 from cg.models.scout.scout_load_config import ScoutLoadConfig
+from cg.store.api.data_classes import RNADNACollection
 from cg.store.models import Analysis, Case, Customer, Sample
 from cg.store.store import Store
 
 LOG = logging.getLogger(__name__)
 
 
-@dataclass
-class RNADNACollection:
-    """Contains the id for an RNA sample, the name of its connected DNA sample,
-    and a list of connected, uploaded DNA cases."""
-
-    rna_sample_internal_id: str
-    dna_sample_name: str
-    dna_case_ids: list[str]
-
-
 class UploadScoutAPI:
     """Class that handles everything that has to do with uploading to Scout."""
 
@@ -182,15 +172,6 @@ def get_rna_omics_outrider(self, case_id: str) -> File | None:
         tags: set[str] = {AnalysisTag.OUTRIDER, case_id, AnalysisTag.CLINICAL}
         return self.housekeeper.get_file_from_latest_version(bundle_name=case_id, tags=tags)
 
-    def get_unique_dna_cases_related_to_rna_case(self, case_id: str) -> set[str]:
-        """Return a set of unique DNA cases related to an RNA case."""
-        case: Case = self.status_db.get_case_by_internal_id(case_id)
-        rna_dna_collections: list[RNADNACollection] = self.create_rna_dna_collections(case)
-        unique_dna_cases_related_to_rna_case: set[str] = set()
-        for rna_dna_collection in rna_dna_collections:
-            unique_dna_cases_related_to_rna_case.update(rna_dna_collection.dna_case_ids)
-        return unique_dna_cases_related_to_rna_case
-
     def get_rna_alignment_cram(self, case_id: str, sample_id: str) -> File | None:
         """Return an RNA alignment CRAM file for a case in Housekeeper."""
         tags: set[str] = {AlignmentFileTag.CRAM, sample_id}
@@ -206,9 +187,11 @@ def get_rna_alignment_cram(self, case_id: str, sample_id: str) -> File | None:
     def upload_rna_alignment_file(self, case_id: str, dry_run: bool) -> None:
         """Upload RNA alignment file to Scout."""
         rna_case: Case = self.status_db.get_case_by_internal_id(case_id)
-        rna_dna_collections: list[RNADNACollection] = self.create_rna_dna_collections(rna_case)
+        rna_dna_collections: list[RNADNACollection] = (
+            self.status_db.get_related_dna_cases_with_samples(rna_case)
+        )
         for rna_dna_collection in rna_dna_collections:
-            rna_sample_internal_id: str = rna_dna_collection.rna_sample_internal_id
+            rna_sample_internal_id: str = rna_dna_collection.rna_sample_id
             dna_sample_name: str = rna_dna_collection.dna_sample_name
             rna_alignment_cram: File | None = self.get_rna_alignment_cram(
                 case_id=case_id, sample_id=rna_sample_internal_id
@@ -346,9 +329,11 @@ def upload_rna_coverage_bigwig_to_scout(self, case_id: str, dry_run: bool) -> No
 
         status_db: Store = self.status_db
         rna_case = status_db.get_case_by_internal_id(case_id)
-        rna_dna_collections: list[RNADNACollection] = self.create_rna_dna_collections(rna_case)
+        rna_dna_collections: list[RNADNACollection] = (
+            self.status_db.get_related_dna_cases_with_samples(rna_case)
+        )
         for rna_dna_collection in rna_dna_collections:
-            rna_sample_internal_id: str = rna_dna_collection.rna_sample_internal_id
+            rna_sample_internal_id: str = rna_dna_collection.rna_sample_id
             dna_sample_name: str = rna_dna_collection.dna_sample_name
             rna_coverage_bigwig: File | None = self.get_rna_coverage_bigwig(
                 case_id=case_id, sample_id=rna_sample_internal_id
@@ -382,7 +367,7 @@ def upload_omics_sample_id_to_scout(
         self, dry_run: bool, rna_dna_collections: list[RNADNACollection]
     ) -> None:
         for rna_dna_collection in rna_dna_collections:
-            rna_sample_internal_id: str = rna_dna_collection.rna_sample_internal_id
+            rna_sample_internal_id: str = rna_dna_collection.rna_sample_id
             dna_sample_name: str = rna_dna_collection.dna_sample_name
             for dna_case_id in rna_dna_collection.dna_case_ids:
                 LOG.info(
@@ -406,7 +391,7 @@ def upload_rna_fraser_outrider_to_scout(
         """Upload omics fraser and outrider file for a case to Scout."""
         status_db: Store = self.status_db
         for rna_dna_collection in rna_dna_collections:
-            rna_sample_internal_id: str = rna_dna_collection.rna_sample_internal_id
+            rna_sample_internal_id: str = rna_dna_collection.rna_sample_id
             dna_sample_name: str = rna_dna_collection.dna_sample_name
             rna_fraser: File | None = self.get_rna_omics_fraser(case_id=case_id)
             rna_outrider: File | None = self.get_rna_omics_outrider(case_id=case_id)
@@ -442,7 +427,7 @@ def upload_rna_fraser_outrider_to_scout(
     def upload_rna_genome_build_to_scout(
         self,
         dry_run: bool,
-        rna_case: str,
+        rna_case: Case,
         rna_dna_collections: list[RNADNACollection],
     ) -> None:
         """Upload RNA genome built for a RNA/DNA case to Scout."""
@@ -502,9 +487,11 @@ def upload_splice_junctions_bed_to_scout(self, dry_run: bool, case_id: str) -> N
         status_db: Store = self.status_db
         rna_case: Case = status_db.get_case_by_internal_id(case_id)
 
-        rna_dna_collections: list[RNADNACollection] = self.create_rna_dna_collections(rna_case)
+        rna_dna_collections: list[RNADNACollection] = (
+            self.status_db.get_related_dna_cases_with_samples(rna_case)
+        )
         for rna_dna_collection in rna_dna_collections:
-            rna_sample_internal_id: str = rna_dna_collection.rna_sample_internal_id
+            rna_sample_internal_id: str = rna_dna_collection.rna_sample_id
             dna_sample_name: str = rna_dna_collection.dna_sample_name
             splice_junctions_bed: File | None = self.get_splice_junctions_bed(
                 case_id=case_id, sample_id=rna_sample_internal_id
@@ -615,7 +602,9 @@ def upload_rna_omics_to_scout(self, dry_run: bool, case_id: str) -> None:
         """Upload RNA omics files to Scout."""
         status_db: Store = self.status_db
         rna_case = status_db.get_case_by_internal_id(case_id)
-        rna_dna_collections: list[RNADNACollection] = self.create_rna_dna_collections(rna_case)
+        rna_dna_collections: list[RNADNACollection] = (
+            self.status_db.get_related_dna_cases_with_samples(rna_case)
+        )
         self.upload_omics_sample_id_to_scout(
             dry_run=dry_run, rna_dna_collections=rna_dna_collections
         )
@@ -675,45 +664,6 @@ def get_config_builder(self, analysis, hk_version) -> ScoutConfigBuilder:
 
         return config_builders[analysis.workflow]
 
-    def create_rna_dna_collections(self, rna_case: Case) -> list[RNADNACollection]:
-        return [self.create_rna_dna_collection(link.sample) for link in rna_case.links]
-
-    def create_rna_dna_collection(self, rna_sample: Sample) -> RNADNACollection:
-        """Creates a collection containing the given RNA sample id, its related DNA sample name, and
-        a list of ids for the DNA cases connected to the DNA sample."""
-        if not rna_sample.subject_id:
-            raise CgDataError(
-                f"Failed to link RNA sample {rna_sample.internal_id} to DNA samples - subject_id field is empty."
-            )
-
-        collaborators: set[Customer] = rna_sample.customer.collaborators
-        subject_id_samples: list[Sample] = (
-            self.status_db.get_samples_by_customer_ids_and_subject_id_and_is_tumour(
-                customer_ids=[customer.id for customer in collaborators],
-                subject_id=rna_sample.subject_id,
-                is_tumour=rna_sample.is_tumour,
-            )
-        )
-
-        subject_id_dna_samples: list[Sample] = self._get_application_prep_category(
-            subject_id_samples
-        )
-
-        if len(subject_id_dna_samples) != 1:
-            raise CgDataError(
-                f"Failed to upload files for RNA case: unexpected number of DNA sample matches for subject_id: "
-                f"{rna_sample.subject_id}. Number of matches: {len(subject_id_dna_samples)} "
-            )
-        dna_sample: Sample = subject_id_dna_samples[0]
-        dna_cases: list[str] = self._dna_cases_related_to_dna_sample(
-            dna_sample=dna_sample, collaborators=collaborators
-        )
-        return RNADNACollection(
-            rna_sample_internal_id=rna_sample.internal_id,
-            dna_sample_name=dna_sample.name,
-            dna_case_ids=dna_cases,
-        )
-
     def _dna_cases_related_to_dna_sample(
         self, dna_sample: Sample, collaborators: set[Customer]
     ) -> list[str]:
@@ -768,11 +718,6 @@ def _get_application_prep_category(
 
     def get_related_uploaded_dna_cases(self, rna_case_id: str) -> set[str]:
         """Returns all uploaded DNA cases related to the specified RNA case."""
-        unique_dna_case_ids: set[str] = self.get_unique_dna_cases_related_to_rna_case(rna_case_id)
-        uploaded_dna_cases: set[str] = set()
-        for dna_case_id in unique_dna_case_ids:
-            if self.status_db.get_case_by_internal_id(dna_case_id).is_uploaded:
-                uploaded_dna_cases.add(dna_case_id)
-            else:
-                LOG.warning(f"Related DNA case {dna_case_id} has not been completed.")
-        return uploaded_dna_cases
+        rna_case: Case = self.status_db.get_case_by_internal_id(rna_case_id)
+        dna_cases: list[Case] = self.status_db.get_uploaded_related_dna_cases(rna_case)
+        return {dna_case.internal_id for dna_case in dna_cases}

cg/store/api/data_classes.py

@@ -0,0 +1,11 @@
+from pydantic.dataclasses import dataclass
+
+
+@dataclass
+class RNADNACollection:
+    """Contains the id for an RNA sample, the name of its connected DNA sample,
+    and a list of connected, uploaded DNA cases."""
+
+    rna_sample_id: str
+    dna_sample_name: str
+    dna_case_ids: list[str]

cg/store/crud/read.py

@@ -15,11 +15,12 @@
     SampleType,
 )
 from cg.constants.sequencing import DNA_PREP_CATEGORIES, SeqLibraryPrepCategory
-from cg.exc import CaseNotFoundError, CgError, OrderNotFoundError, SampleNotFoundError
+from cg.exc import CaseNotFoundError, CgDataError, CgError, OrderNotFoundError, SampleNotFoundError
 from cg.models.orders.constants import OrderType
 from cg.models.orders.sample_base import SexEnum
 from cg.server.dto.samples.collaborator_samples_request import CollaboratorSamplesRequest
 from cg.services.orders.order_service.models import OrderQueryParams
+from cg.store.api.data_classes import RNADNACollection
 from cg.store.base import BaseHandler
 from cg.store.exc import EntryNotFoundError
 from cg.store.filters.status_analysis_filters import AnalysisFilter, apply_analysis_filter
@@ -1657,48 +1658,86 @@ def _get_related_samples_query(
                 SampleFilter.BY_CUSTOMER_ENTRY_IDS,
             ],
         )
+        if samples.count() != 1:
+            samples: list[Sample] = samples.all()
+            raise CgDataError(
+                f"No unique DNA sample could be found: found {len(samples)} samples: {[sample.internal_id for sample in samples]}"
+            )
         return samples
 
     def get_uploaded_related_dna_cases(self, rna_case: Case) -> list[Case]:
         """Returns all uploaded DNA cases ids related to the given RNA case."""
 
         related_dna_cases: list[Case] = []
+        collaborators: set[Customer] = rna_case.customer.collaborators
         for rna_sample in rna_case.samples:
-
-            collaborators: set[Customer] = rna_sample.customer.collaborators
+            if not rna_sample.subject_id:
+                raise CgDataError(
+                    f"Failed to link RNA sample {rna_sample.internal_id} to DNA samples - subject_id field is empty."
+                )
 
             related_dna_samples_query: Query = self._get_related_samples_query(
                 sample=rna_sample,
                 prep_categories=DNA_PREP_CATEGORIES,
                 collaborators=collaborators,
             )
-
-            dna_samples_cases_analysis_query: Query = (
-                related_dna_samples_query.join(Sample.links).join(CaseSample.case).join(Analysis)
+            customer_ids: list[int] = [customer.id for customer in collaborators]
+            uploaded_dna_cases: list[Case] = self._get_uploaded_dna_cases(
+                sample_query=related_dna_samples_query, customer_ids=customer_ids
             )
-
-            dna_samples_cases_analysis_query: Query = apply_case_filter(
-                cases=dna_samples_cases_analysis_query,
-                workflows=DNA_WORKFLOWS_WITH_SCOUT_UPLOAD,
-                customer_entry_ids=[customer.id for customer in collaborators],
-                filter_functions=[
-                    CaseFilter.BY_WORKFLOWS,
-                    CaseFilter.BY_CUSTOMER_ENTRY_IDS,
-                ],
+            related_dna_cases.extend(uploaded_dna_cases)
+        if not related_dna_cases:
+            raise CgDataError(
+                f"No matching uploaded DNA cases for case {rna_case.internal_id} ({rna_case.name})."
             )
+        return related_dna_cases
 
-            uploaded_dna_cases: list[Case] = (
-                apply_analysis_filter(
-                    analyses=dna_samples_cases_analysis_query,
-                    filter_functions=[AnalysisFilter.IS_UPLOADED],
+    def _get_uploaded_dna_cases(self, sample_query: Query, customer_ids: list[int]) -> list[Case]:
+        dna_samples_cases_analysis_query: Query = (
+            sample_query.join(Sample.links).join(CaseSample.case).join(Analysis)
+        )
+        dna_samples_cases_analysis_query: Query = apply_case_filter(
+            cases=dna_samples_cases_analysis_query,
+            workflows=DNA_WORKFLOWS_WITH_SCOUT_UPLOAD,
+            customer_entry_ids=customer_ids,
+            filter_functions=[
+                CaseFilter.BY_WORKFLOWS,
+                CaseFilter.BY_CUSTOMER_ENTRY_IDS,
+            ],
+        )
+        uploaded_dna_cases: list[Case] = (
+            apply_analysis_filter(
+                analyses=dna_samples_cases_analysis_query,
+                filter_functions=[AnalysisFilter.IS_UPLOADED],
+            )
+            .with_entities(Case)
+            .all()
+        )
+        return uploaded_dna_cases
+
+    def get_related_dna_cases_with_samples(self, rna_case: Case) -> list[RNADNACollection]:
+        collaborators = rna_case.customer.collaborators
+        collaborator_ids: list[int] = [collaborator.id for collaborator in collaborators]
+        rna_dna_collections: list[RNADNACollection] = []
+        for sample in rna_case.samples:
+            related_dna_samples: Query = self._get_related_samples_query(
+                sample=sample, prep_categories=DNA_PREP_CATEGORIES, collaborators=collaborators
+            )
+            nr_of_related_samples: int = related_dna_samples.count()
+            if nr_of_related_samples != 1:
+                raise CgDataError(
+                    f"Failed to upload files for RNA case: unexpected number of DNA sample matches for subject_id: "
+                    f"{sample.subject_id}. Number of matches: {nr_of_related_samples} "
                 )
-                .with_entities(Case)
-                .all()
+            dna_sample_name: str = related_dna_samples.first().name
+            dna_cases: list[Case] = self._get_uploaded_dna_cases(
+                sample_query=related_dna_samples, customer_ids=collaborator_ids
             )
-
-            related_dna_cases.extend([case for case in uploaded_dna_cases])
-        if not related_dna_cases:
-            raise CaseNotFoundError(
-                f"No matching uploaded DNA cases for case {rna_case.internal_id} ({rna_case.name})."
+            dna_case_ids: list[str] = [case.internal_id for case in dna_cases]
+            collection = RNADNACollection(
+                rna_sample_id=sample.internal_id,
+                dna_sample_name=dna_sample_name,
+                dna_case_ids=dna_case_ids,
             )
-        return related_dna_cases
+            rna_dna_collections.append(collection)
+        return rna_dna_collections