Implement migrator that removes used slot from WorkflowExecution (file: migrator_from_X_to_PR31.py)

nmdc_schema/migrators/migrator_from_X_to_PR31.py

@@ -0,0 +1,81 @@
+from nmdc_schema.migrators.migrator_base import MigratorBase
+
+class Migrator(MigratorBase):
+    r"""
+    Migrates data from X to PR31, removes used slot from WorkflowExecution subclasses and checks that the 
+    value in the used slot on the WorkflowExecution classes matches the value on the DataGeneration 
+    instances in the instrument_name slot.
+    """
+
+    _from_version = "X"
+    _to_version = "PR31"
+
+    def upgrade(self):
+        r"""Migrates the database from conforming to the original schema, to conforming to the new schema."""
+
+        workflow_execution_collection_names = [
+            "metaproteomics_analysis_set",
+            "nom_analysis_set",
+            "metabolomics_analysis_set",
+            "read_based_taxonomy_analysis_set",
+            "read_qc_analysis_set",
+            "metagenome_sequencing_set",
+            "mags_set",
+            "metatranscriptome_analysis_set",
+            "metagenome_annotation_set",
+            "metagenome_assembly_set",
+            "mags_activity_set",
+            "metabolomics_analysis_activity_set",
+            "metagenome_annotation_activity_set",
+            "metagenome_sequencing_activity_set",
+            "metaproteomics_analysis_activity_set"
+        ]
+
+        self.adapter.process_each_document("omics_processing_set", [self.check_instrument_name])
+
+        for collection_name in workflow_execution_collection_names:
+            self.adapter.process_each_document(
+                collection_name=collection_name,
+                pipeline=[self.remove_used_slot],
+            )
+
+    def remove_used_slot(self, doc: dict) -> dict:
+        r"""
+        Removes the used slot from WorkflowExecution subclasses.
+
+        >>> m = Migrator()  
+        >>> m.remove_used_slot({'id': 123, 'used': 'abc'})  
+        {'id': 123}
+        """
+
+        if "used" in doc:
+            doc.pop("used")
+
+        return doc
+
+    def check_instrument_name(self, workflow_execution: dict) -> dict:
+        r"""
+        Checks that the value in the used slot on the WorkflowExecution classes matches the value
+        in the `instrument_name` field of a related `OmicsProcessing` (soon to be renamed to `DataGeneration`) instance. 
+        If it matches, then remove used from the WorkflowExecution instance.
+
+        >>> m = Migrator()
+        >>> m.check_instrument_name({'id': 123, 'used': 'abc'})
+        {'id': 123, 'used': 'abc'}
+        """
+
+        if "used" in workflow_execution:
+
+            try: 
+                data_generation_doc = self.adapter.get_document_having_value_in_field(
+                    collection_name="omics_processing_set", field_name="instrument_name", value=workflow_execution["used"]
+                    )
+
+                if workflow_execution["used"] == data_generation_doc["instrument_name"]:
+                    workflow_execution.pop("used")
+
+            except:
+                self.logger.error(f"WorkflowExecution {workflow_execution['id']} used: {workflow_execution['used']} does not match OmicsProcessing instrument_name.")
+
+        return workflow_execution
+

src/data/valid/Database-neon_Biosample_to_DataObject_NEON.yaml

@@ -116,23 +116,23 @@ data_object_set:
     data_object_type: Filtered Sequencing Reads
     url: https://data.microbiomedata.org/data/1472_51293/qa/1472_51293.filtered.fastq.gz
     type: nmdc:DataObject
-data_generation_set:
-  - id: nmdc:dgns-11-s9xj2r24
-    analyte_category: metagenome
-    name: Test NEON data
-    has_input:
-      - nmdc:procsm-99-xyz3
-    has_output:
-      - nmdc:dobj-12-jdhk9537
-      - nmdc:dobj-12-yx0tfp52
-    instrument_used:
-      - nmdc:inst-12-yx0tfp52
-    part_of:
-      - nmdc:dgns-11-34xj1150
-    processing_institution: Battelle
-    type: nmdc:NucleotideSequencing
-    associated_studies: 
-      - nmdc:sty-11-34xj1150
+# data_generation_set:
+#   - id: nmdc:dgns-11-s9xj2r24
+#     analyte_category: metagenome
+#     name: Test NEON data
+#     has_input:
+#       - nmdc:procsm-99-xyz3
+#     has_output:
+#       - nmdc:dobj-12-jdhk9537
+#       - nmdc:dobj-12-yx0tfp52
+#     instrument_used:
+#       - nmdc:inst-12-yx0tfp52
+#     part_of:
+#       - nmdc:dgns-11-34xj1150
+#     processing_institution: Battelle
+#     type: nmdc:NucleotideSequencing
+#     associated_studies: 
+#       - nmdc:sty-11-34xj1150
 workflow_chain_set:
   - id: nmdc:wfch-11-ab
     analyte_category: metagenome

src/schema/basic_classes.yaml

@@ -73,7 +73,6 @@ classes:
     slots:
       - has_input
       - has_output
-      - instrument_used
       - processing_institution
       - protocol_link
       - start_date
@@ -292,6 +291,7 @@ classes:
       - omics assay
       - sequencing project
       - experiment
+      - instrument_used
     is_a: PlannedProcess
     abstract: true
     in_subset:

src/schema/core.yaml

@@ -1183,7 +1183,8 @@ classes:
     description:
       A process that takes one or more samples as inputs and generates
       one or more samples as outputs.
-
+    slots:
+      - instrument_used
     notes:
       - This class is a replacement for BiosampleProcessing.
     slot_usage: