Change Study class name to ResearchInitiative

project.Makefile

@@ -397,8 +397,8 @@ nmdc_schema/nmdc_schema_accepting_legacy_ids.yaml: src/schema/nmdc.yaml
 	yq -i '(.classes[] | select(.name == "ReadBasedTaxonomyAnalysisActivity") | .slot_usage.id.structured_pattern.syntax) = ".*"' $@
 	yq -i '(.classes[] | select(.name == "ReadQcAnalysisActivity") | .slot_usage.id.pattern) = ".*"' $@
 	yq -i '(.classes[] | select(.name == "ReadQcAnalysisActivity") | .slot_usage.id.structured_pattern.syntax) = ".*"' $@
-	yq -i '(.classes[] | select(.name == "Study") | .slot_usage.id.pattern) = ".*"' $@
-	yq -i '(.classes[] | select(.name == "Study") | .slot_usage.id.structured_pattern.syntax) = ".*"' $@
+	yq -i '(.classes[] | select(.name == "ResearchInitiative") | .slot_usage.id.pattern) = ".*"' $@
+	yq -i '(.classes[] | select(.name == "ResearchInitiative") | .slot_usage.id.structured_pattern.syntax) = ".*"' $@
 
 	$(RUN) gen-linkml \
 		--format yaml \

src/data/valid/ResearchInitiative-credit-1.yaml

@@ -0,0 +1,11 @@
+id: 'nmdc:sty-99-WoeqAi'
+initiative_type: study
+has_credit_associations:
+  - applied_roles:
+      - Data curation
+    applies_to_person:
+      orcid: 'orcid:0000-0002-1825-00'
+  - applied_roles:
+      - Software
+    applies_to_person:
+      orcid: 'orcid:0000-0001-9076-6066'

src/data/valid/ResearchInitiative-exhaustive.yaml

@@ -0,0 +1,99 @@
+id: nmdc:sty-11-ab
+name: see also description, title, objective, various alternatives
+description: see also name, title, objective, various alternatives
+alternative_identifiers:
+  - generic:abc1
+related_identifiers: any string R1
+#emsl_proposal_identifier:
+#  - generic:abc1
+#emsl_proposal_doi: any string
+gold_study_identifiers:
+  - GOLD:Gs12345
+  - GOLD:Gs90909
+mgnify_project_identifiers:
+  - mgnify.proj:ABC123
+ecosystem: unconstrained text. should be validated against the controlled vocabulary,
+  by the sample's environmental package. would also be nice to align the CV with MIxS
+  environmental triads
+ecosystem_category: unconstrained text
+ecosystem_type: unconstrained text
+ecosystem_subtype: unconstrained text
+specific_ecosystem: unconstrained text
+principal_investigator:
+  has_raw_value: Craig Venter
+  was_generated_by: nmdc:any_string_1
+  orcid: ORCID:0000-0002-7086-765X
+  profile_image_url: https://en.wikipedia.org/wiki/Craig_Venter#/media/File:Craigventer2.jpg
+  email: jcventer@jcvi.org
+  name: J. Craig Venter
+  websites:
+    - https://www.jcvi.org/
+    - https://www.jcvi.org/about/j-craig-venter
+publication_dois:
+  - doi:10.1126/science.1058040
+title: Sample Exhaustive Biosample instance. Although all of these values should pass
+  validation, that does not mean that any Biosample of any type would necessarily
+  have this particular combination of values.
+alternative_titles:
+  - any string 1
+  - any string 2
+alternative_descriptions:
+  - any string 1
+  - any string 2
+alternative_names:
+  - any string 1
+  - any string 2
+objective: This record, an instance of class Study from the nmdc-schema was had authored,
+  so that the NMDC team would have at least one instance, using all slots, with a
+  mixture of reasonable values and minimally compliant values.
+websites:
+  - https://w3id.org/nmdc
+  - https://w3id.org/linkml
+publications:
+  - any string 1
+  - any string 2
+ess_dive_datasets:
+  - any string 1
+  - any string 2
+type: any string
+relevant_protocols:
+  - any string 1
+  - any string 2
+funding_sources:
+  - any string 1
+  - any string 2
+has_credit_associations:
+  - applies_to_person:
+      has_raw_value: Craig Venter
+      was_generated_by: nmdc:any_string_1
+      orcid: ORCID:0000-0002-7086-765X
+      profile_image_url: https://en.wikipedia.org/wiki/Craig_Venter#/media/File:Craigventer2.jpg
+      email: jcventer@jcvi.org
+      name: J. Craig Venter
+      websites:
+        - https://www.jcvi.org/
+        - https://www.jcvi.org/about/j-craig-venter
+    applied_roles:
+      - Supervision
+      - Conceptualization
+    applied_role: Funding acquisition
+    type: any string
+  - applies_to_person:
+      name: Tanja Davidsen
+    applied_roles:
+      - Investigation
+      - Supervision
+study_image:
+  - has_raw_value: https://upload.wikimedia.org/wikipedia/commons/8/86/J._Craig_Vernter_Institute_Rockville_Maryland.jpg
+    was_generated_by: nmdc:any_string_1
+    url: https://upload.wikimedia.org/wikipedia/commons/8/86/J._Craig_Vernter_Institute_Rockville_Maryland.jpg
+    description: Photo of Craig Venter Institute, Rockville, Maryland
+    display_order: '1'
+  - has_raw_value: https://today.ucsd.edu/news_uploads/140213ventor2.jpg
+    was_generated_by: nmdc:any_string_1
+    url: https://today.ucsd.edu/news_uploads/140213ventor2.jpg
+    description: Photo of Craig Venter Institute, La Jolla, California
+    display_order: '2'
+initiative_type: study
+part_of: 
+  - nmdc:sty-11-34xj1157

src/data/valid/ResearchInitiative-minimal.yaml

@@ -0,0 +1,2 @@
+id: nmdc:sty-11-ab
+initiative_type: study

src/schema/nmdc.yaml

@@ -87,7 +87,7 @@ subsets:
   sample subset:
     description:
       Subset consisting of entities linked to the processing of samples.  Currently,
-      this subset consists of study, omics process, and biosample.
+      this subset consists of research initiative, omics process, and biosample.
   data object subset:
     description:
       Subset consisting of the data objects that either inputs or outputs
@@ -229,7 +229,7 @@ classes:
     title: Field Research Site
     comments:
       - Provides grouping of biosamples at level that's more specific than belonging
-        to the same study
+        to the same research initiative.
       - be very clear that this could be part of a larger site
       - In Bioscales, one might say that rhizosphere soil and bulk soil from around
         the same plant were obtained at the same site. In this case, the site would
@@ -1083,7 +1083,7 @@ classes:
         required: true
       part_of:
         required: true
-        range: Study
+        range: ResearchInitiative
       fire:
         comments:
           - Provide the date the fire occurred. If extended burning occurred provide the date range.
@@ -1318,7 +1318,7 @@ classes:
       - NCIT:C43412
       - http://purl.obolibrary.org/obo/FBcv_0003024
 
-  Study:
+  ResearchInitiative:
     is_a: NamedThing
     in_subset:
       - sample subset
@@ -1330,9 +1330,10 @@ classes:
       - project
       - umbrella project
       - research inititative
+      - consortium
     description: >-
-      A study summarizes the overall goal of a research initiative and outlines the key objective of its underlying projects.
-    comments: The Study class can include both consortia and studies.
+      A research initiative summarizes the overall goal of a research initiative and outlines the key objective of its underlying projects.
+    comments: The research initiative class can include both consortia and studies.
     alt_descriptions:
       embl.ena:
         A study (project) groups together data submitted to the archive and
@@ -1399,42 +1400,42 @@ classes:
 
       name:
         annotations:
-          display_hint: Provide a name for the study your samples will belong with.
+          display_hint: Provide a name for the research initiative your samples will belong with.
       websites:
         annotations:
           display_hint:
             Link to the Principal Investigator's research lab webpage
-            or the study webpage associated with this collection of samples.
+            or the research initiative's webpage associated with this collection of samples.
             Multiple links can be provided.
       description:
-        description: A brief, link-free summary of a Study
+        description: A brief, link-free summary of a research initiative.
         annotations:
-          display_hint: Provide a brief description of your study.
-        comments: Include links in other Study slots, such as websites or dois.
+          display_hint: Provide a brief description of your research initiative.
+        comments: Include links in other ResearchInitiative slots, such as websites or dois.
       notes:
         annotations:
-          display_hint: Add any additional notes or comments about this study.
+          display_hint: Add any additional notes or comments about this research initiative.
       alternative_identifiers:
-        description: Unique identifier for a study submitted to additional resources. Matches that which has been submitted to NMDC
+        description: Unique identifier for a research initiative submitted to additional resources. Matches that which has been submitted to NMDC
       alternative_names:
         annotations:
           display_hint:
             Project, study, or sample set names the are also associated with this submission
-            or other names / identifiers for this study.
+            or other names / identifiers for this research initiative.
       related_identifiers:
-        description: Unique identifier for a study submitted to additional resources. Similar, but not necessarily identical to that which has been submitted to NMDC
+        description: Unique identifier for a research initiative submitted to additional resources. Similar, but not necessarily identical to that which has been submitted to NMDC
       insdc_bioproject_identifiers:
-        description: Unique identifier for a bioproject submitted to INSDC that relates to the NMDC submitted study.
+        description: Unique identifier for a bioproject submitted to INSDC that relates to the NMDC submitted research initiative.
         annotations:
           display_hint: Provide the NCBI BioProject Accession Number associated with the listed NCBI BioProject Title.
     #      emsl_project_identifier:
     #        description: The EMSL project ID that relates to the NMDC submitted study
     #      emsl_proposal_doi:
     #        description: The DOI for the EMSL awarded study that relates to the NMDC submitted study
       part_of:
-        description: Links a study or consortium to a parent study or consortium.
-        comments: Value is the id of the parent study or consortium.
-        range: Study
+        description: Links a research initiative, such as a study or consortium, to a parent research initiative.
+        comments: Value is the id of the parent research initiative.
+        range: ResearchInitiative
     exact_mappings:
       - OBI:0000066
       - SIO:000747
@@ -1446,13 +1447,12 @@ classes:
       - determine how to get data values for submitted_to_insdc, investigation_type,
         experimental_factor
       - project_name is redundant with name, so excluding it
-      - potentially change the class name from Study to ResearchInitiative to make more semantically accurate and clear; encompassing instances of studies and consortia.
 
     notes:
       - "sample GOLD link https://identifiers.org/gold:Gs0110115"
       - "sample insdc.srs link https://www.ebi.ac.uk/ena/browser/view/PRJEB45055 ?"
       - "sample mgnify link https://www.ebi.ac.uk/metagenomics/studies/MGYS00005757"
-      - "GOLD, insdc.srs and mgnify are reasonable prefixes for alternative study identifiers, but no longer for the Study.id"
+      - "GOLD, insdc.srs and mgnify are reasonable prefixes for alternative research initiative identifiers, but no longer for the ResearchInitiative.id"
 
   BiosampleProcessing:
     aliases:
@@ -1943,7 +1943,7 @@ enums:
         description: principal investigator role
         meaning: OBI:0000103
       Submitter:
-        description: the person(s) who enter study and biosample metadata into the NMDC submission portal
+        description: the person(s) who enter research initiative and biosample metadata into the NMDC submission portal
         meaning: EFO:0001741
     comments:
       - credit enums come from https://casrai.org/credit/
@@ -2222,7 +2222,7 @@ slots:
       - make this required?
       - first apply to Biosample
       - try to apply to all Biosamples in a particular nmdc-server SubmissionMetadata?
-      - applying to a Study may nto be granular enough
+      - applying to a ResearchInitiative may not be granular enough
 
   collected_from:
     description: The Site from which a Biosample was collected
@@ -2253,33 +2253,33 @@ slots:
   #- insdc_sra_ena_study_identifiers
 
   notes:
-    description: from study class
+    description: from ResearchInitiative class
 
   canary:
     description: a slot that can be added and removed as evidence that schema changes have propagated to other systems
   ess_dive_datasets:
     multivalued: true
     description: List of ESS-DIVE dataset DOIs
   has_credit_associations:
-    domain: Study
+    domain: ResearchInitiative
     range: CreditAssociation
     multivalued: true
     notes:
       - 'had just been "inlined: true"'
     inlined_as_list: true
     description:
-      "This slot links a study to a credit association.  The credit association
+      "This slot links a research initiative to a credit association.  The credit association
       will be linked to a person value and to a CRediT Contributor Roles term. Overall
       semantics: person should get credit X for their participation in the study"
     slot_uri: prov:qualifiedAssociation
     annotations:
-      display_hint: Other researchers associated with this study.
+      display_hint: Other researchers associated with this research initiative.
   study_image:
-    domain: Study
+    domain: ResearchInitiative
     range: ImageValue
     multivalued: true
     inlined: true
-    description: Links a study to one or more images.
+    description: Links a research initiative to one or more images.
   relevant_protocols:
     multivalued: true
     range: string
@@ -2349,10 +2349,10 @@ slots:
   study_set:
     mixins: object_set
     domain: Database
-    range: Study
+    range: ResearchInitiative
     multivalued: true
     description:
-      This property links a database object to the set of studies within
+      This property links a database object to the set of research initiatives within
       it.
   field_research_site_set:
     inlined_as_list: true
@@ -2626,7 +2626,7 @@ slots:
   award_dois:
     is_a: dois
     description: >-
-      One or more DOIs that links a study, or similar entiry, to information about the funding authority.
+      One or more DOIs that links a research initiative, or similar entity, to information about the funding authority.
     examples:
       - value: doi:10.46936/10.25585/60000880
         description:
@@ -2636,7 +2636,7 @@ slots:
   dataset_dois:
     is_a: dois
     description: >-
-      One or more DOIs that links a study, or similar entity, to the generated data.
+      One or more DOIs that links research initiative, or similar entity, to the generated data.
     #    annotations:
     #      display_hint: DOI associated with the data in this study. This is required when data is already generated.
     examples:
@@ -2647,7 +2647,7 @@ slots:
 
   publication_dois:
     is_a: dois
-    description: One or more DOIs that links a study, or similar entity, to a publication.
+    description: One or more DOIs that links a research initiative, or similar entity, to a publication.
     examples:
       - value: doi:10.1126/science.1058040
         description:

tests/test_credit_associations.py

@@ -3,7 +3,7 @@
 
 from linkml.validators.jsonschemavalidator import JsonSchemaDataValidator
 
-from nmdc_schema.nmdc import PersonValue, CreditAssociation, Study
+from nmdc_schema.nmdc import PersonValue, CreditAssociation, ResearchInitiative
 
 ROOT = os.path.join(os.path.dirname(__file__), '..')
 SCHEMA_DIR = os.path.join(ROOT, "src", "schema")
@@ -21,17 +21,17 @@ def test_sum(self):
         ca1 = CreditAssociation(applies_to_person=pv1, applied_roles=["Supervision", "Validation"])
         ca2 = CreditAssociation(applies_to_person=pv2, applied_roles=["Investigation"])
 
-        s = Study(id="nmdc:sty-e3e05c16-8c9a-421e-ade5-cde4e5a435fa", initiative_type="study")
+        s = ResearchInitiative(id="nmdc:sty-e3e05c16-8c9a-421e-ade5-cde4e5a435fa", initiative_type="study")
 
         # # why is schema loaded each time?
         validator.validate_object(ca1, target_class=CreditAssociation)
         validator.validate_object(ca2, target_class=CreditAssociation)
 
         s.has_credit_associations.append(ca1)
         s.has_credit_associations.append(ca2)
-        validator.validate_object(s, target_class=Study)
+        validator.validate_object(s, target_class=ResearchInitiative)
 
-        self.assertEqual(type(s), Study)
+        self.assertEqual(type(s), ResearchInitiative)
 
 
 if __name__ == '__main__':

tests/test_getters.py

@@ -20,7 +20,7 @@ def test_schema_slots_getter(self):
         self.assertIsNotNone(schema_slots)
 
     def test_get_slots_from_class(self):
-        class_name = "Study"
+        class_name = "ResearchInitiative"
         class_slot_getter = ClassSlotsGetter()
         class_slots = class_slot_getter.get_class_slots(class_name)
         self.assertIsNotNone(class_slots)