Merge pull request #192 from microbiomedata/2043_extraction_target_slot

Make `extraction_target` slot multivalued and implement migrator
microbiomedata · Jun 5, 2024 · ca304e4 · ca304e4
2 parents 110777a + ad39841
commit ca304e4
Show file tree

Hide file tree

Showing 13 changed files with 61 additions and 15 deletions.
diff --git a/nmdc_schema/migrators/migrator_from_X_to_PR192.py b/nmdc_schema/migrators/migrator_from_X_to_PR192.py
@@ -0,0 +1,31 @@
+from typing import List
+from nmdc_schema.migrators.migrator_base import MigratorBase
+
+
+class Migrator(MigratorBase):
+    """
+    Migrates data from X to PR192, makes the existing extraction_target slot multivalued and change its name to extraction_targets
+
+    Should be run after migrator_from_X_to_PR2_and_PR24.py.
+    """
+
+    def upgrade(self):
+        r"""Migrates the database from conforming to the original schema, to conforming to the new schema."""
+
+        self.adapter.process_each_document("extraction_set", [self.rename_extraction_target])
+
+    def rename_extraction_target(self, extraction: dict) -> dict:
+        r"""
+        Renames the `extraction_target` field to `extraction_targets` and makes it multivalued.
+
+        >>> m = Migrator()
+        >>> m.rename_extraction_target({'id': 123})  # no `extraction_target` field
+        {'id': 123}
+        >>> m.rename_extraction_target({'id': 123, 'extraction_target': 'DNA'})  # test: renames field and casts it as a list value
+        {'id': 123, 'extraction_targets': ['DNA']}
+        """
+
+        self.logger.info(f"Starting migration of {extraction['id']}")
+        if "extraction_target" in extraction:
+            extraction["extraction_targets"] = [extraction.pop("extraction_target")]
+        return extraction
diff --git a/src/data/invalid/Database-Extraction-extraction_method-slot-retired.yaml b/src/data/invalid/Database-Extraction-extraction_method-slot-retired.yaml
@@ -16,5 +16,6 @@ extraction_set:
     end_date: "2019-11-08"
     qc_status: pass
     extraction_method: phenol/chloroform extraction # not allowed anymore
-    extraction_target: DNA
+    extraction_targets: 
+      - DNA
 
diff --git a/src/data/invalid/Database-Extraction-sample_mass-now_input_mass.yaml b/src/data/invalid/Database-Extraction-sample_mass-now_input_mass.yaml
@@ -19,4 +19,5 @@ extraction_set:
       has_numeric_value: 0.25
       has_unit: gram
     qc_status: pass
-    extraction_target: DNA
+    extraction_targets: 
+      - DNA
diff --git a/src/data/invalid/Database-plannedprocess-non-string-end_datet.yaml b/src/data/invalid/Database-plannedprocess-non-string-end_datet.yaml
@@ -6,7 +6,8 @@ extraction_set:
       - bare:pool_out_1
     has_output:
       - bare:dna_extract_1
-    extraction_target: DNA
+    extraction_targets: 
+      - DNA
     end_date: 2021-01-15
 
 library_preparation_set:

diff --git a/src/data/invalid/Extraction-invalid_enum.yaml b/src/data/invalid/Extraction-invalid_enum.yaml
@@ -6,7 +6,8 @@ has_output:
 start_date: "2020-06-24T22:06Z"
 end_date: "2021-08-19"
 qc_status: "pass"
-extraction_target: "phenol/chloroform extraction"
+extraction_targets: 
+  - "phenol/chloroform extraction"
 input_mass:
   has_numeric_value: 0.25
   has_unit: "g"

diff --git a/src/data/valid/Database-extraction_set-exhaustive.yaml b/src/data/valid/Database-extraction_set-exhaustive.yaml
@@ -35,7 +35,8 @@ extraction_set:
 
     #extraction_type should have range of dna_extraction_enum with possible values of 'DNA extraction', 'RNA extraction', 'protein extraction'
     #http://purl.obolibrary.org/obo/OBI_0000257
-    extraction_target: DNA
+    extraction_targets: 
+      - DNA
     #not needed at this time
     #protocol_materials:
     #  - { material_name : DNeasy 96 PowerSoil Pro Kit, material_vendor: Qiagen, catalog_number: 47017 }

diff --git a/src/data/valid/Database-interleaved.yaml b/src/data/valid/Database-interleaved.yaml
@@ -3325,7 +3325,8 @@ extraction_set:
     start_date: '2019-99-08'
     end_date: '2019-99-08'
     qc_status: pass
-    extraction_target: DNA
+    extraction_targets: 
+      - DNA
     input_mass:
       type: nmdc:QuantityValue
       has_numeric_value: 0.25
@@ -3337,7 +3338,8 @@ extraction_set:
       - nmdc:bsm-99-74d83z
     has_output:
       - nmdc:procsm-99-k4m6j
-    extraction_target: DNA
+    extraction_targets: 
+      - DNA
     input_mass:
       type: nmdc:QuantityValue
       has_numeric_value: 0.25
@@ -3349,7 +3351,8 @@ extraction_set:
       - nmdc:bsm-99-49z38t
     has_output:
       - nmdc:procsm-99-29dl
-    extraction_target: DNA
+    extraction_targets: 
+      - DNA
     volume:
       type: nmdc:QuantityValue
       has_numeric_value: 100
@@ -3361,7 +3364,8 @@ extraction_set:
       - nmdc:bsm-99-bbbbbb
     has_output:
       - nmdc:procsm-99-3z8t
-    extraction_target: DNA
+    extraction_targets: 
+      - DNA
 field_research_site_set:
   - id: nmdc:frsite-99-SPreao
     type: nmdc:FieldResearchSite

diff --git a/src/data/valid/Database-neon-story.yaml b/src/data/valid/Database-neon-story.yaml
@@ -33,7 +33,8 @@ extraction_set:
       - nmdc:procsm-99-pooled
     has_output:
       - nmdc:procsm-99-extract
-    extraction_target: DNA
+    extraction_targets: 
+      - DNA
     start_date: "2021-01-15"
     end_date: "2021-01-15"
     type: nmdc:Extraction

diff --git a/src/data/valid/Database-neon_Biosample_to_DataObject_NEON.yaml b/src/data/valid/Database-neon_Biosample_to_DataObject_NEON.yaml
@@ -28,7 +28,8 @@ extraction_set:
       - nmdc:procsm-99-xyz2
     start_date: '2021-01-15'
     end_date: '2021-01-15'
-    extraction_target: DNA
+    extraction_targets: 
+      - DNA
     type: nmdc:Extraction
 biosample_set:
   - id: nmdc:bsm-99-abcdef1

diff --git a/src/data/valid/Database-nucleic-extraction.yaml b/src/data/valid/Database-nucleic-extraction.yaml
@@ -47,7 +47,8 @@ extraction_set:
 
     #extraction_type should have range of dna_extraction_enum with possible values of 'DNA extraction', 'RNA extraction', 'protein extraction'
     #http://purl.obolibrary.org/obo/OBI_0000257
-    extraction_target: DNA
+    extraction_targets: 
+      - DNA
 
     #not needed at this time
     #protocol_materials:

diff --git a/src/data/valid/Extraction-NEON.yaml b/src/data/valid/Extraction-NEON.yaml
@@ -9,7 +9,8 @@ start_date: "2020-06-24T22:06Z"
 end_date: "2021-08-19"
 processing_institution: Battelle
 qc_status: pass
-extraction_target: DNA
+extraction_targets: 
+  - DNA
 input_mass:
   type: nmdc:QuantityValue
   has_numeric_value: 0.25

diff --git a/src/schema/basic_slots.yaml b/src/schema/basic_slots.yaml
@@ -466,9 +466,10 @@ slots:
     minimum_value: 0
     maximum_value: 2000
 
-  extraction_target:
+  extraction_targets:
     description: Provides the target biomolecule that has been separated from a sample during an extraction process.
     rank: 1000
+    multivalued: true
     range: ExtractionTargetEnum
     notes:
       - todos, remove nucl_acid_ext from OmicsProcessing (DataGeneration)
@@ -1057,6 +1058,7 @@ enums:
       RNA: { }
       metabolite: { }
       protein: { }
+      lipid: { }
 
   ProcessingInstitutionEnum:
     notes:

diff --git a/src/schema/nmdc.yaml b/src/schema/nmdc.yaml
@@ -319,7 +319,7 @@ classes:
       - OBI:0302884
     slots:
       - substances_used
-      - extraction_target
+      - extraction_targets
       - input_mass
       - volume
     slot_usage: