Merge pull request #292 from include-dcc/2026-02-19-PL

2026 02 19 pl

Author: lopierra

src/data/sheets/schemasheet.tsv

@@ -1,14 +1,14 @@
 class	slot	title	description	required	range	any_of	minimum_value	maximum_value	multivalued	enum	permissible_value	meaning
 >class	slot	title	description	required	range	any_of	minimum_value	maximum_value	multivalued	enum	permissible_value	meaning
-	studyCode	Study Code	Unique identifier for the study (generally a short acronym)	true	enum_studyCode							
+	studyCode	Study Code	Unique short acronym for the study	true	enum_studyCode							
 	studyTitle	Study Title	Full title of the study	true	string							
 	program	Program	Funding source(s) for the study (pipe-separated if multiple)	true	enum_program				true			
 	studyDescription	Study Description	Brief description of the study (2-4 sentences)	true	string							
 	principalInvestigatorName	Principal Investigator Name	Name(s) of Principal Investigator(s) of this study; pipe-separated if multiple	true	string				true			
 	studyContactName	Study Contact Name	Name of contact person for this study; pipe-separated if multiple	true	string				true			
 	studyContactInstitution	Study Contact Institution	Institution of contact person for this study; pipe-separated if multiple	true	string				true			
 	studyContactEmail	Study Contact Email	Email address of contact person for this study; pipe-separated if multiple	true	string				true			
-	vbrEmail	VBR Email	Email address for Virtual Biorepository requests/inquiries, if participating		string							
+	vbrEmail	VBR Email	Email address for Virtual Biorepository requests/inquiries, if participating		string				true			
 	vbrUrl	VBR URL	Link to Virtual Biorepository request form, if participating		uri							
 	vbrReadme	VBR Readme	Instructions for contacting or requesting samples from Virtual Biorepository, if participating		string							
 	researchDomain	Research Domain	Main research domain(s) of the study, other than Down syndrome; pipe-separated if multiple	true	enum_researchDomain				true			
@@ -38,13 +38,11 @@ class	slot	title	description	required	range	any_of	minimum_value	maximum_value	m
 	secondaryOutcomeMeasure	Secondary Outcome Measure	A description of each secondary outcome measure (title, description, and time point/duration of assessment). Multiple values should be pipe-separated.		string				true			
 	otherOutcomeMeasure	Other Outcome Measure	A description of other outcome measures (title, description, and time point/duration of assessment). Multiple values should be pipe-separated.		string				true			
 	datasetName	Dataset Name	Full name of the dataset, provided by contributor	true	string							
-	datasetDescription	Dataset Description	Brief additional notes about the dataset (1-3 sentences) that are not already captured in the other fields		string							
+	datasetDescription	Dataset Description	Brief additional notes about the dataset (1-3 sentences) that are not already captured in the other fields	true	string							
 	datasetGlobalId	Dataset Global ID	Unique Global ID for dataset, generated by DCC	false	string							
 	datasetExternalId	Dataset External ID	Unique identifier or code for dataset, if provided by contributor		string							
 	dataCollectionStartYear	Data Collection Start Year	Year that data collection started	false	string							
 	dataCollectionEndYear	Data Collection End Year	Year that data collection ended	false	string							
-	accessLimitations	Access Limitations	Data access limitations, as defined in the GA4GH Data Use Ontology (DUO; can list more than one, pipe separated)	false	string							
-	accessRequirements	Access Requirements	Data access requirements, as defined in the GA4GH Data Use Ontology (DUO; can list more than one, pipe separated)	false	string							
 	otherRepository	Other Repository	URL if dataset is already deposited in a public repository other than dbGaP (e.g. LONI, Metabolomics Workbench, etc.)		uri				true			
 	otherAccessAuthority	Other Access Authority	Email or URL for dataset's Access Authority, if not dbGaP		string							
 	isHarmonized	Is Harmonized	All of the elements in this Dataset are harmonized and available in the INCLUDE Data Hub		boolean							
@@ -136,11 +134,9 @@ DatasetManifest		Dataset Manifest	Mapping information for files in Dataset
 DatasetManifest	studyCode				Study							
 DatasetManifest	fileGlobalId				DataFile							
 DatasetManifest	datasetGlobalId				Dataset							
-ParticipantSampleDataFileManifest		Participant-Sample-DataFile Manifest	List of Participants and/or Samples in DataFiles with multiple Participants and/or Samples									
-ParticipantSampleDataFileManifest	studyCode				Study							
-ParticipantSampleDataFileManifest	fileName				DataFile							
-ParticipantSampleDataFileManifest	participantExternalId				Participant							
-ParticipantSampleDataFileManifest	sampleExternalId				Biospecimen							
+ParticipantDataFileManifest		Participant-DataFile Manifest	List of Participants in DataFiles with multiple Participants									
+ParticipantDataFileManifest	fileName				DataFile							
+ParticipantDataFileManifest	participantExternalId				Participant							
 Participant		Participant	Demographic and clinical information about the participant									
 Condition		Condition	Co-occurring conditions and other observations for the participant									
 Condition	studyCode				Study							
@@ -181,6 +177,7 @@ DataFile	sampleGlobalId				Biospecimen
 		DS-Nexus								enum_studyCode	ds_nexus	
 		DS-PALS								enum_studyCode	ds_pals	
 		DS-PCGC								enum_studyCode	ds_pcgc	
+		DS-SAH								enum_studyCode	ds_sah	
 		DS-Sleep								enum_studyCode	ds_sleep	
 		DS-VitE								enum_studyCode	ds_vite	
 		DS360-CHD								enum_studyCode	ds360_chd	
@@ -210,6 +207,7 @@ DataFile	sampleGlobalId				Biospecimen
 		Behavior and Behavior Mechanisms								enum_researchDomain	behavior_and_behavior_mechanisms	mesh:D001520
 		Congenital Heart Defects								enum_researchDomain	congenital_heart_defects	mesh:D006330
 		Embryonic and Fetal Development								enum_researchDomain	embryonic_and_fetal_development	mesh:D005314
+		Hearing Disorders								enum_researchDomain	hearing_disorders	D006311
 		Immune System Diseases								enum_researchDomain	immune_system_diseases	mesh:D007154
 		Hematologic Diseases								enum_researchDomain	hematologic_diseases	mesh:D006402
 		Neurodevelopment								enum_researchDomain	neurodevelopment	mesh:D065886
@@ -265,6 +263,7 @@ DataFile	sampleGlobalId				Biospecimen
 		Physical Activity								enum_dataCategory	physical_activity	
 		Other								enum_dataCategory	other	
 		Sleep								enum_dataCategory	sleep_study	
+		Speech/Language/Hearing								enum_dataCategory	speech_language_hearing	
 										enum_guidType		
 		NDAR	GUID generated by NIMH Data Archive (NDA) GUID tool							enum_guidType	ndar	
 		Other	GUID generated by other system							enum_guidType	other	

src/linkml/include_schema.yaml

@@ -31,6 +31,7 @@ classes:
     description: General information about the study
     title: Study
     slots:
+    # - studyGlobalId
     - studyCode
     - studyTitle
     - program
@@ -109,8 +110,8 @@ classes:
     - experimentalStrategy
     - experimentalPlatform
     - publication
-    - accessLimitations
-    - accessRequirements
+#    - accessLimitations
+#    - accessRequirements
     - dbgap
     - otherRepository
     - otherAccessAuthority
@@ -156,26 +157,22 @@ classes:
         range: DataFile
       datasetGlobalId:
         range: Dataset
-  ParticipantSampleDataFileManifest:
-    definition_uri: include:ParticipantSampleDataFileManifest
-    description: List of Participants and/or Samples in DataFiles with multiple Participants and/or Samples
-    title: Participant-Sample-DataFile Manifest
+  ParticipantDataFileManifest:
+    definition_uri: include:ParticipantDataFileManifest
+    description: List of Participants in DataFiles with multiple Participants
+    title: Participant-DataFile Manifest
     slots:
-    - studyCode
     - participantExternalId
-    - sampleExternalId
+    - participantGlobalId
     - fileName
+    - fileGlobalId
     #TODO: add Dictonary File Name & Global ID
     slot_usage:
       # Reference Slots
-      studyCode:
-        range: Study
       fileName:
         range: DataFile
       participantExternalId:
         range: Participant
-      sampleExternalId:
-        range: Biospecimen
   Participant:
     definition_uri: include:Participant
     description: Demographic and clinical information about the participant
@@ -338,9 +335,14 @@ classes:
 ####################################################################################################
 
 slots:
+  # studyGlobalId:
+  #   definition_uri: include:studyGlobalId
+  #   description: Unique identifier for the study, assigned by DCC
+  #   title: Study Global ID
+  #   required: true
   studyCode:
     definition_uri: include:studyCode
-    description: Unique identifier for the study (generally a short acronym)
+    description: Unique short acronym for the study
     title: Study Code
     range: enum_studyCode
     required: true
@@ -397,6 +399,7 @@ slots:
     description: Email address for Virtual Biorepository requests/inquiries, if participating
     title: VBR Email
     range: string
+    multivalued: true
   vbrUrl:
     definition_uri: include:vbrUrl
     description: Link to Virtual Biorepository request form, if participating
@@ -606,6 +609,7 @@ slots:
     description: Brief additional notes about the dataset (1-3 sentences) that are not already captured in the other fields
     title: Dataset Description
     range: string
+    required: true
   datasetGlobalId:
     definition_uri: include:datasetGlobalId
     description: Unique Global ID for dataset, generated by DCC
@@ -637,18 +641,18 @@ slots:
     range: string
     #pattern: "^1|2\\d(3)$|nan"
     required: false
-  accessLimitations:
-    definition_uri: include:accessLimitations
-    description: Data access limitations, as defined in the GA4GH Data Use Ontology (DUO; can list more than one, pipe separated)
-    title: Access Limitations
-    range: string
-    required: false #make true when we have enums
-  accessRequirements:
-    definition_uri: include:accessRequirements
-    description: Data access requirements, as defined in the GA4GH Data Use Ontology (DUO; can list more than one, pipe separated)
-    title: Access Requirements
-    range: string
-    required: false #make true when we have enums
+  # accessLimitations:
+  #   definition_uri: include:accessLimitations
+  #   description: Data access limitations, as defined in the GA4GH Data Use Ontology (DUO; can list more than one, pipe separated)
+  #   title: Access Limitations
+  #   range: string
+  #   required: false
+  # accessRequirements:
+  #   definition_uri: include:accessRequirements
+  #   description: Data access requirements, as defined in the GA4GH Data Use Ontology (DUO; can list more than one, pipe separated)
+  #   title: Access Requirements
+  #   range: string
+  #   required: false
   otherRepository:
     definition_uri: include:otherRepository
     description: URL if dataset is already deposited in a public repository other than dbGaP (e.g. LONI, Metabolomics Workbench, etc.)
@@ -1121,6 +1125,8 @@ enums:
         title: DS-PALS
       ds_pcgc:
         title: DS-PCGC
+      ds_sah:
+        title: DS-SAH
       ds_sleep:
         title: DS-Sleep
       ds_vite:
@@ -1186,6 +1192,9 @@ enums:
       embryonic_and_fetal_development:
         title: Embryonic and Fetal Development
         meaning: mesh:D005314
+      hearing_disorders:
+        title: Hearing Disorders
+        meaning: D006311
       immune_system_diseases:
         title: Immune System Diseases
         meaning: mesh:D007154
@@ -1289,8 +1298,10 @@ enums:
     permissible_values:
       demographic_clinical_data:
         title: Demographic/Clinical Data
+        #use for Study Expected Data Category
       unharmonized_demographic_clinical_data:
         title: Unharmonized Demographic/Clinical Data
+        #use for Dataset Data Category
       genomics:
         title: Genomics
       transcriptomics:
@@ -1319,6 +1330,8 @@ enums:
         title: Other
       sleep_study:
         title: Sleep
+      speech_language_hearing:
+        title: Speech/Language/Hearing
   enum_guidType:
     definition_uri: include:enum_guidType
     permissible_values: