nmdc-runtime 2.7.0__py3-none-any.whl → 2.9.0__py3-none-any.whl

nmdc_runtime/site/repair/database_updater.py

@@ -1,5 +1,5 @@
 from functools import lru_cache
-from typing import Any, Dict, List
+from typing import Any, Dict, List, Union
 import pandas as pd
 from nmdc_runtime.site.resources import (
     RuntimeApiUserClient,
@@ -18,6 +18,8 @@ class DatabaseUpdater:
         gold_api_client: GoldApiClient,
         study_id: str,
         gold_nmdc_instrument_map_df: pd.DataFrame = pd.DataFrame(),
+        include_field_site_info: bool = False,
+        enable_biosample_filtering: bool = True,
     ):
         """This class serves as an API for repairing connections in the database by
         adding records that are essentially missing "links"/"connections". As we identify
@@ -39,6 +41,8 @@ class DatabaseUpdater:
         self.gold_api_client = gold_api_client
         self.study_id = study_id
         self.gold_nmdc_instrument_map_df = gold_nmdc_instrument_map_df
+        self.include_field_site_info = include_field_site_info
+        self.enable_biosample_filtering = enable_biosample_filtering
 
     @lru_cache
     def _fetch_gold_biosample(self, gold_biosample_id: str) -> List[Dict[str, Any]]:
@@ -95,6 +99,8 @@ class DatabaseUpdater:
             biosamples=all_gold_biosamples,
             projects=all_gold_projects,
             gold_nmdc_instrument_map_df=self.gold_nmdc_instrument_map_df,
+            include_field_site_info=self.include_field_site_info,
+            enable_biosample_filtering=self.enable_biosample_filtering,
         )
 
         # The GoldStudyTranslator class has some pre-processing logic which filters out
@@ -214,6 +220,8 @@ class DatabaseUpdater:
             projects=gold_sequencing_projects_for_study,
             analysis_projects=gold_analysis_projects_for_study,
             gold_nmdc_instrument_map_df=self.gold_nmdc_instrument_map_df,
+            include_field_site_info=self.include_field_site_info,
+            enable_biosample_filtering=self.enable_biosample_filtering,
         )
 
         translated_biosamples = gold_study_translator.biosamples
@@ -240,3 +248,204 @@ class DatabaseUpdater:
         ]
 
         return database
+
+    def queries_run_script_to_update_insdc_identifiers(
+        self,
+    ) -> Union[Dict[str, Any], List[Dict[str, Any]]]:
+        """This method creates a `/queries:run` API endpoint compatible update script that can be run
+        using that API endpoint to update/add information on the `insdc_biosample_identifiers` field
+        of biosample_set records and the `insdc_bioproject_identifiers` field on data_generation_set records.
+
+        The information to be asserted is retrieved from the `ncbiBioSampleAccession` and
+        `ncbiBioProjectAccession` fields on the GOLD `/projects` API endpoint.
+
+        :return: A `/queries:run` update query compatible script serialized as a dictionary/JSON.
+        """
+        # Fetch all biosamples associated with the study
+        biosample_set = self.runtime_api_user_client.get_biosamples_for_study(
+            self.study_id
+        )
+
+        # Fetch all data_generation records associated with the study
+        data_generation_set = (
+            self.runtime_api_user_client.get_data_generation_records_for_study(
+                self.study_id
+            )
+        )
+
+        biosample_updates = []
+        data_generation_updates = []
+
+        # Dictionary to store gold_project_id -> ncbi_bioproject_accession mapping
+        gold_project_to_bioproject = {}
+
+        # Dictionary to store all project data we gather during biosample processing
+        all_processed_projects = {}
+
+        # Process biosamples for insdc_biosample_identifiers
+        for biosample in biosample_set:
+            # get the list (usually one) of GOLD biosample identifiers on the gold_biosample_identifiers slot
+            gold_biosample_identifiers = biosample.get("gold_biosample_identifiers", [])
+            if not gold_biosample_identifiers:
+                continue
+
+            biosample_id = biosample.get("id")
+            if not biosample_id:
+                continue
+
+            insdc_biosample_identifiers = []
+
+            for gold_biosample_id in gold_biosample_identifiers:
+                normalized_id = gold_biosample_id.replace("gold:", "")
+
+                # fetch projects associated with a GOLD biosample from the GOLD `/projects` API endpoint
+                gold_projects = self.gold_api_client.fetch_projects_by_biosample(
+                    normalized_id
+                )
+
+                for project in gold_projects:
+                    # Store each project for later use
+                    project_gold_id = project.get("projectGoldId")
+                    if project_gold_id:
+                        all_processed_projects[project_gold_id] = project
+
+                    # Collect ncbi_biosample_accession for biosample updates
+                    ncbi_biosample_accession = project.get("ncbiBioSampleAccession")
+                    if ncbi_biosample_accession and ncbi_biosample_accession.strip():
+                        insdc_biosample_identifiers.append(ncbi_biosample_accession)
+
+                    # Collect ncbi_bioproject_accession for data_generation records
+                    ncbi_bioproject_accession = project.get("ncbiBioProjectAccession")
+                    if (
+                        project_gold_id
+                        and ncbi_bioproject_accession
+                        and ncbi_bioproject_accession.strip()
+                    ):
+                        gold_project_to_bioproject[project_gold_id] = (
+                            ncbi_bioproject_accession
+                        )
+
+            if insdc_biosample_identifiers:
+                existing_insdc_biosample_identifiers = biosample.get(
+                    "insdc_biosample_identifiers", []
+                )
+                new_insdc_biosample_identifiers = list(
+                    set(insdc_biosample_identifiers)
+                    - set(existing_insdc_biosample_identifiers)
+                )
+
+                if new_insdc_biosample_identifiers:
+                    prefixed_new_biosample_identifiers = [
+                        f"biosample:{id}" for id in new_insdc_biosample_identifiers
+                    ]
+
+                    if existing_insdc_biosample_identifiers:
+                        all_biosample_identifiers = list(
+                            set(
+                                existing_insdc_biosample_identifiers
+                                + prefixed_new_biosample_identifiers
+                            )
+                        )
+                        biosample_updates.append(
+                            {
+                                "q": {"id": biosample_id},
+                                "u": {
+                                    "$set": {
+                                        "insdc_biosample_identifiers": all_biosample_identifiers
+                                    }
+                                },
+                            }
+                        )
+                    else:
+                        biosample_updates.append(
+                            {
+                                "q": {"id": biosample_id},
+                                "u": {
+                                    "$set": {
+                                        "insdc_biosample_identifiers": prefixed_new_biosample_identifiers
+                                    }
+                                },
+                            }
+                        )
+
+        # Process data_generation records for insdc_bioproject_identifiers
+        for data_generation in data_generation_set:
+            data_generation_id = data_generation.get("id")
+            if not data_generation_id:
+                continue
+
+            # Extract existing insdc_bioproject_identifiers
+            existing_insdc_bioproject_identifiers = data_generation.get(
+                "insdc_bioproject_identifiers", []
+            )
+
+            collected_insdc_bioproject_identifiers = set()
+
+            # Add any project identifiers already on the record
+            if "insdc_bioproject_identifiers" in data_generation:
+                for identifier in data_generation["insdc_bioproject_identifiers"]:
+                    collected_insdc_bioproject_identifiers.add(identifier)
+
+            # If there are gold_sequencing_project_identifiers, use our pre-collected mapping
+            gold_project_identifiers = data_generation.get(
+                "gold_sequencing_project_identifiers", []
+            )
+            for gold_project_id in gold_project_identifiers:
+                normalized_id = gold_project_id.replace("gold:", "")
+
+                # Check if we have a bioproject ID for this GOLD project ID
+                if normalized_id in gold_project_to_bioproject:
+                    ncbi_bioproject_accession = gold_project_to_bioproject[
+                        normalized_id
+                    ]
+                    collected_insdc_bioproject_identifiers.add(
+                        f"bioproject:{ncbi_bioproject_accession}"
+                    )
+                else:
+                    # Only if we don't have it in our mapping, try to fetch it
+                    # Instead of making a direct API request, check if we've already seen this project
+                    if normalized_id in all_processed_projects:
+                        project_data = all_processed_projects[normalized_id]
+                        ncbi_bioproject_accession = project_data.get(
+                            "ncbiBioProjectAccession"
+                        )
+                        if (
+                            ncbi_bioproject_accession
+                            and ncbi_bioproject_accession.strip()
+                        ):
+                            collected_insdc_bioproject_identifiers.add(
+                                f"bioproject:{ncbi_bioproject_accession}"
+                            )
+                            # Add to our mapping for future reference
+                            gold_project_to_bioproject[normalized_id] = (
+                                ncbi_bioproject_accession
+                            )
+
+            # Create a list from the set of collected identifiers
+            collected_insdc_bioproject_identifiers = list(
+                collected_insdc_bioproject_identifiers
+            )
+
+            # Only update if there are identifiers to add
+            if collected_insdc_bioproject_identifiers and set(
+                collected_insdc_bioproject_identifiers
+            ) != set(existing_insdc_bioproject_identifiers):
+                data_generation_updates.append(
+                    {
+                        "q": {"id": data_generation_id},
+                        "u": {
+                            "$set": {
+                                "insdc_bioproject_identifiers": collected_insdc_bioproject_identifiers
+                            }
+                        },
+                    }
+                )
+
+        # Return updates for both collections
+        if data_generation_updates:
+            return [
+                {"update": "biosample_set", "updates": biosample_updates},
+                {"update": "data_generation_set", "updates": data_generation_updates},
+            ]
+        else:
+            return {"update": "biosample_set", "updates": biosample_updates}

nmdc_runtime/site/repository.py

@@ -14,6 +14,7 @@ from dagster import (
     DagsterRunStatus,
     RunStatusSensorContext,
     DefaultSensorStatus,
+    in_process_executor,
 )
 from starlette import status
 from toolz import merge, get_in
@@ -44,8 +45,10 @@ from nmdc_runtime.site.graphs import (
     ingest_neon_benthic_metadata,
     ingest_neon_surface_water_metadata,
     ensure_alldocs,
+    run_ontology_load,
     nmdc_study_to_ncbi_submission_export,
     generate_data_generation_set_for_biosamples_in_nmdc_study,
+    generate_update_script_for_insdc_biosample_identifiers,
 )
 from nmdc_runtime.site.resources import (
     get_mongo,
@@ -123,6 +126,55 @@ ensure_alldocs_daily = ScheduleDefinition(
 )
 
 
+load_envo_ontology_weekly = ScheduleDefinition(
+    name="weekly_load_envo_ontology",
+    cron_schedule="0 7 * * 1",
+    execution_timezone="America/New_York",
+    job=run_ontology_load.to_job(
+        name="scheduled_envo_ontology_load",
+        config=unfreeze(
+            merge(
+                run_config_frozen__normal_env,
+                {"ops": {"load_ontology": {"config": {"source_ontology": "envo"}}}},
+            )
+        ),
+        resource_defs=resource_defs,
+    ),
+)
+
+load_uberon_ontology_weekly = ScheduleDefinition(
+    name="weekly_load_uberon_ontology",
+    cron_schedule="0 8 * * 1",
+    execution_timezone="America/New_York",
+    job=run_ontology_load.to_job(
+        name="scheduled_uberon_ontology_load",
+        config=unfreeze(
+            merge(
+                run_config_frozen__normal_env,
+                {"ops": {"load_ontology": {"config": {"source_ontology": "uberon"}}}},
+            )
+        ),
+        resource_defs=resource_defs,
+    ),
+)
+
+load_po_ontology_weekly = ScheduleDefinition(
+    name="weekly_load_po_ontology",
+    cron_schedule="0 9 * * 1",
+    execution_timezone="America/New_York",
+    job=run_ontology_load.to_job(
+        name="scheduled_po_ontology_load",
+        config=unfreeze(
+            merge(
+                run_config_frozen__normal_env,
+                {"ops": {"load_ontology": {"config": {"source_ontology": "po"}}}},
+            )
+        ),
+        resource_defs=resource_defs,
+    ),
+)
+
+
 def asset_materialization_metadata(asset_event, key):
     """Get metadata from an asset materialization event.
 
@@ -411,11 +463,6 @@ def claim_and_run_apply_changesheet_jobs(_context):
         yield SkipReason("; ".join(skip_notes))
 
 
-# TODO ensure data_object_type values from file_type_enum
-#    see /metadata-translation/notebooks/202106_curation_updates.ipynb
-#    for details ("Create file_type_enum collection" section).
-
-
 @sensor(job=create_objects_from_site_object_puts.to_job(**preset_normal))
 def done_object_put_ops(_context):
     client = get_runtime_api_site_client(run_config_frozen__normal_env)
@@ -462,7 +509,13 @@ def repo():
         export_study_biosamples_metadata.to_job(**preset_normal),
         ensure_alldocs.to_job(**preset_normal),
     ]
-    schedules = [housekeeping_weekly, ensure_alldocs_daily]
+    schedules = [
+        housekeeping_weekly,
+        ensure_alldocs_daily,
+        load_envo_ontology_weekly,
+        load_uberon_ontology_weekly,
+        load_po_ontology_weekly,
+    ]
     sensors = [
         done_object_put_ops,
         ensure_gold_translation_job,
@@ -516,6 +569,7 @@ def biosample_submission_ingest():
                             "study_type": "research_study",
                             "gold_nmdc_instrument_mapping_file_url": "https://raw.githubusercontent.com/microbiomedata/berkeley-schema-fy24/main/assets/misc/gold_seqMethod_to_nmdc_instrument_set.tsv",
                             "include_field_site_info": False,
+                            "enable_biosample_filtering": True,
                         },
                     },
                     "export_json_to_drs": {"config": {"username": ""}},
@@ -960,6 +1014,8 @@ def database_records_stitching():
                         "config": {
                             "nmdc_study_id": "",
                             "gold_nmdc_instrument_mapping_file_url": "https://raw.githubusercontent.com/microbiomedata/nmdc-schema/refs/heads/main/assets/misc/gold_seqMethod_to_nmdc_instrument_set.tsv",
+                            "include_field_site_info": False,
+                            "enable_biosample_filtering": True,
                         }
                     },
                     "export_json_to_drs": {"config": {"username": ""}},
@@ -1002,12 +1058,57 @@ def database_records_stitching():
                         "config": {
                             "nmdc_study_id": "",
                             "gold_nmdc_instrument_mapping_file_url": "https://raw.githubusercontent.com/microbiomedata/nmdc-schema/refs/heads/main/assets/misc/gold_seqMethod_to_nmdc_instrument_set.tsv",
+                            "include_field_site_info": False,
+                            "enable_biosample_filtering": True,
                         }
                     },
                     "export_json_to_drs": {"config": {"username": ""}},
                 },
             },
         ),
+        generate_update_script_for_insdc_biosample_identifiers.to_job(
+            description="This job generates a MongoDB update script to add INSDC biosample identifiers to biosamples based on GOLD data.",
+            resource_defs=resource_defs,
+            config={
+                "resources": merge(
+                    unfreeze(normal_resources),
+                    {
+                        "runtime_api_user_client": {
+                            "config": {
+                                "base_url": {"env": "API_HOST"},
+                                "username": {"env": "API_ADMIN_USER"},
+                                "password": {"env": "API_ADMIN_PASS"},
+                            },
+                        },
+                        "runtime_api_site_client": {
+                            "config": {
+                                "base_url": {"env": "API_HOST"},
+                                "client_id": {"env": "API_SITE_CLIENT_ID"},
+                                "client_secret": {"env": "API_SITE_CLIENT_SECRET"},
+                                "site_id": {"env": "API_SITE_ID"},
+                            },
+                        },
+                        "gold_api_client": {
+                            "config": {
+                                "base_url": {"env": "GOLD_API_BASE_URL"},
+                                "username": {"env": "GOLD_API_USERNAME"},
+                                "password": {"env": "GOLD_API_PASSWORD"},
+                            },
+                        },
+                    },
+                ),
+                "ops": {
+                    "get_database_updater_inputs": {
+                        "config": {
+                            "nmdc_study_id": "",
+                            "gold_nmdc_instrument_mapping_file_url": "https://raw.githubusercontent.com/microbiomedata/nmdc-schema/refs/heads/main/assets/misc/gold_seqMethod_to_nmdc_instrument_set.tsv",
+                            "include_field_site_info": False,
+                            "enable_biosample_filtering": True,
+                        }
+                    },
+                },
+            },
+        ),
     ]
 
 

nmdc_runtime/site/resources.py

@@ -109,7 +109,7 @@ class RuntimeApiUserClient(RuntimeApiClient):
             },
         )
         response.raise_for_status()
-        return response.json()["cursor"]["firstBatch"]
+        return response.json()["cursor"]["batch"]
 
     def get_omics_processing_records_by_gold_project_id(self, gold_project_id: str):
         gold_project_id = normalize_gold_id(gold_project_id)
@@ -126,7 +126,7 @@ class RuntimeApiUserClient(RuntimeApiClient):
             },
         )
         response.raise_for_status()
-        return response.json()["cursor"]["firstBatch"]
+        return response.json()["cursor"]["batch"]
 
     def get_biosamples_for_study(self, study_id: str):
         # TODO: 10000 is an arbitrarily large number that has been chosen for the max_page_size param.
@@ -147,6 +147,19 @@ class RuntimeApiUserClient(RuntimeApiClient):
         response.raise_for_status()
         return response.json()["resources"]
 
+    def get_data_generation_records_for_study(self, study_id: str):
+        # TODO: same as above, we are using a large max_page_size to avoid pagination.
+        response = self.request(
+            "GET",
+            f"/nmdcschema/data_generation_set",
+            {
+                "filter": json.dumps({"associated_studies": study_id}),
+                "max_page_size": 10000,
+            },
+        )
+        response.raise_for_status()
+        return response.json()["resources"]
+
     def get_omics_processing_by_name(self, name: str):
         response = self.request(
             "POST",
@@ -157,7 +170,7 @@ class RuntimeApiUserClient(RuntimeApiClient):
             },
         )
         response.raise_for_status()
-        return response.json()["cursor"]["firstBatch"]
+        return response.json()["cursor"]["batch"]
 
     def get_study(self, study_id: str):
         response = self.request(
@@ -169,7 +182,7 @@ class RuntimeApiUserClient(RuntimeApiClient):
             },
         )
         response.raise_for_status()
-        return response.json()["cursor"]["firstBatch"]
+        return response.json()["cursor"]["batch"]
 
 
 class RuntimeApiSiteClient(RuntimeApiClient):

nmdc_runtime/site/translation/gold_translator.py

@@ -45,6 +45,7 @@ class GoldStudyTranslator(Translator):
         analysis_projects: List[JSON_OBJECT] = [],
         gold_nmdc_instrument_map_df: pd.DataFrame = pd.DataFrame(),
         include_field_site_info: bool = False,
+        enable_biosample_filtering: bool = True,
         *args,
         **kwargs,
     ) -> None:
@@ -53,15 +54,20 @@ class GoldStudyTranslator(Translator):
         self.study = study
         self.study_type = nmdc.StudyCategoryEnum(study_type)
         self.include_field_site_info = include_field_site_info
+        self.enable_biosample_filtering = enable_biosample_filtering
         # Filter biosamples to only those with `sequencingStrategy` of
-        # "Metagenome" or "Metatranscriptome"
-        self.biosamples = [
-            biosample
-            for biosample in biosamples
-            if any(
-                _is_valid_project(project) for project in biosample.get("projects", [])
-            )
-        ]
+        # "Metagenome" or "Metatranscriptome" if filtering is enabled
+        if enable_biosample_filtering:
+            self.biosamples = [
+                biosample
+                for biosample in biosamples
+                if any(
+                    _is_valid_project(project)
+                    for project in biosample.get("projects", [])
+                )
+            ]
+        else:
+            self.biosamples = biosamples
         # Fetch the valid projectGoldIds that are associated with filtered
         # biosamples on their `projects` field
         valid_project_ids = {
@@ -116,6 +122,9 @@ class GoldStudyTranslator(Translator):
         :param gold_entity: GOLD entity object
         :return: PersonValue corresponding to the first PI in the `contacts` field
         """
+        if "contacts" not in gold_entity:
+            return None
+
         pi_dict = next(
             (
                 contact
@@ -169,7 +178,7 @@ class GoldStudyTranslator(Translator):
                 project["ncbiBioSampleAccession"], default_prefix="biosample"
             )
             for project in biosample_projects
-            if project["ncbiBioSampleAccession"]
+            if project.get("ncbiBioSampleAccession")
         ]
 
     def _get_samp_taxon_id(

nmdc_runtime/site/translation/neon_benthic_translator.py

@@ -349,6 +349,7 @@ class NeonBenthicDataTranslator(Translator):
             description=f"sequencing results for {basename}",
             type="nmdc:DataObject",
             data_object_type=do_type,
+            data_category=nmdc.DataCategoryEnum.instrument_data.text,
             in_manifest=manifest_id,
         )
 

nmdc_runtime/site/translation/neon_soil_translator.py

@@ -264,6 +264,7 @@ class NeonSoilDataTranslator(Translator):
             description=f"sequencing results for {basename}",
             type="nmdc:DataObject",
             md5_checksum=checksum,
+            data_category=nmdc.DataCategoryEnum.instrument_data.text,
             data_object_type=do_type,
         )
 

nmdc_runtime/site/translation/neon_surface_water_translator.py

@@ -397,6 +397,7 @@ class NeonSurfaceWaterDataTranslator(Translator):
             description=f"sequencing results for {basename}",
             type="nmdc:DataObject",
             data_object_type=do_type,
+            data_category=nmdc.DataCategoryEnum.instrument_data.text,
             in_manifest=manifest_id,
         )
 

nmdc_runtime/site/translation/submission_portal_translator.py

@@ -47,6 +47,12 @@ DATA_URL_SET_AND_ANALYTE_TO_DATA_OBJECT_TYPE: dict[tuple[DataUrlSet, str], str]
     (INTERLEAVED, str(METATRANSCRIPTOME)): "Metatranscriptome Raw Reads",
 }
 
+UNIT_OVERRIDES: dict[str, dict[str, str]] = {
+    "Biosample": {
+        "depth": "m",
+    }
+}
+
 
 class EnvironmentPackage(Enum):
     r"""
@@ -475,6 +481,50 @@ class SubmissionPortalTranslator(Translator):
 
         return value
 
+    def _get_study_dois(self, metadata_submission) -> Union[List[nmdc.Doi], None]:
+        """Collect and format DOIs from submission portal schema in nmdc format DOIs
+
+        If there were no DOIs, None is returned.
+
+        :param metadata_submission: submission portal entry
+        :return: list of nmdc.DOI objects
+        """
+        data_dois = self._get_from(metadata_submission, ["studyForm", "dataDois"])
+        award_dois = self._get_from(
+            metadata_submission, ["multiOmicsForm", "awardDois"]
+        )
+        if data_dois and len(data_dois) > 0:
+            updated_data_dois = [
+                nmdc.Doi(
+                    doi_category="dataset_doi",
+                    doi_provider=doi["provider"],
+                    doi_value=self._ensure_curie(doi["value"], default_prefix="doi"),
+                    type="nmdc:Doi",
+                )
+                for doi in data_dois
+            ]
+        else:
+            updated_data_dois = []
+
+        if award_dois and len(award_dois) > 0:
+            updated_award_dois = [
+                nmdc.Doi(
+                    doi_category="award_doi",
+                    doi_provider=doi["provider"],
+                    doi_value=self._ensure_curie(doi["value"], default_prefix="doi"),
+                    type="nmdc:Doi",
+                )
+                for doi in award_dois
+            ]
+        else:
+            updated_award_dois = []
+
+        return_val = updated_data_dois + updated_award_dois
+        if len(return_val) == 0:
+            return_val = None
+
+        return return_val
+
     def _get_data_objects_from_fields(
         self,
         sample_data: JSON_OBJECT,
@@ -591,6 +641,7 @@ class SubmissionPortalTranslator(Translator):
             websites=self._get_from(
                 metadata_submission, ["studyForm", "linkOutWebpage"]
             ),
+            associated_dois=self._get_study_dois(metadata_submission),
         )
 
     def _transform_value_for_slot(
@@ -660,6 +711,17 @@ class SubmissionPortalTranslator(Translator):
                 logging.warning(f"No slot '{slot_name}' on class '{class_name}'")
                 continue
 
+            # This step handles cases where the submission portal/schema instructs a user to
+            # provide a value in a specific unit. The unit cannot be parsed out of the raw value
+            # in these cases, so we have to manually set it via UNIT_OVERRIDES. This part can
+            # go away once units are encoded in the schema itself.
+            # See: https://github.com/microbiomedata/nmdc-schema/issues/2517
+            if class_name in UNIT_OVERRIDES:
+                # If the class has unit overrides, check if the slot is in the overrides
+                unit_overrides = UNIT_OVERRIDES[class_name]
+                if slot_name in unit_overrides:
+                    unit = unit_overrides[slot_name]
+
             slot_definition = self.schema_view.induced_slot(slot_name, class_name)
             if slot_definition.multivalued:
                 value_list = value