Merge pull request #181 from include-dcc/2024-04-02

Last updates before major release
include-dcc · May 13, 2024 · d37a446 · d37a446
2 parents e5ebe2f + 486e87a
commit d37a446
Show file tree

Hide file tree

Showing 3 changed files with 69 additions and 66 deletions.
diff --git a/src/linkml/include_assay.yaml b/src/linkml/include_assay.yaml
@@ -45,8 +45,9 @@ classes:
     name: Biospecimen
     title: Biospecimen
     slots:
-    - hasStudy
-    - hasParticipant    
+    - studyCode
+    - participantGlobalId
+    - participantExternalId    
     - sampleGlobalId
     - sampleExternalId
     - sampleType
@@ -67,9 +68,7 @@ classes:
     - biospecimenStorage
     - sampleAvailability
     - containerAvailability
-    # - hasDataFile
 
-    # - hasAliquot
   DataFile:
     annotations:
       required:
@@ -84,9 +83,11 @@ classes:
     name: DataFile
     title: Data File
     slots:
-    - hasStudy
-    - hasParticipant    
-    - hasBiospecimen    
+    - studyCode
+    - participantGlobalId
+    - participantExternalId    
+    - sampleGlobalId
+    - sampleExternalId
     - fileGlobalId
     - fileExternalId
     - fileName
@@ -215,11 +216,6 @@ slots:
       the Virtual Biorepository
     title: Container Availability
     range: enum_containerAvailability
-  hasParticipant:
-    definition_uri: include:hasParticipant
-    description: Link to a Participant 
-    title: Has Participant
-    range: Participant # this should link to Participant External ID for now, then INCLUDE ID when we have them
   fileGlobalId:
     definition_uri: include:fileGlobalId
     description: INCLUDE global file identifier, assigned by DCC
@@ -254,7 +250,7 @@ slots:
       Metabolomics, Immune profiling, Transcriptomics)
     title: Data Category
     required: true
-    range: enum_DataCategory
+    range: enum_dataCategory
   dataType:
     definition_uri: include:dataType
     description: Specific type of data contained in file (e.g. Preprocessed metabolite relative abundance, Absolute protein concentration, Aligned reads, Simple nucleotide variations, GVCF, Gene expression quantifications, Gene fusions, Somatic copy number variations, Somatic structural variations)
@@ -276,11 +272,6 @@ slots:
     title: File Format
     required: true
     range: string
-  # has_aliquot:
-  #   definition_uri: include:has_aliquot
-  #   description: An aliquot of a sample
-  #   title: Has Aliquot
-  #   range: Aliquot
   fileSize:
     definition_uri: include:fileSize
     description: Size of file, if known (mainly important if large)
@@ -301,26 +292,6 @@ slots:
     description: DOI of publication associated with this file, if published
     title: Publication DOI
     range: string # is there a doi range?
-  hasBiospecimen:
-    definition_uri: include:hasBiospecimen
-    description: Link to a Biospecimen
-    title: Has Biospecimen
-    range: Biospecimen
-  # hasDataFile:
-  #   definition_uri: include:hasDataFile
-  #   description: Link to a Data File
-  #   title: Has Data File
-  #   range: DataFile
-  # has_output:
-  #   definition_uri: include:has_output
-  #   description: The DataFile Output of an Assay
-  #   title: Has Output
-  #   range: DataFile
-  # uses_biospecimen:
-  #   definition_uri: include:uses_biospecimen
-  #   description: The Biospecimen an Assay is performed on
-  #   title: Uses Biospecimen
-  #   range: Biospecimen
 enums:
   enum_dataAccess:
     definition_uri: include:enum_dataAccess

diff --git a/src/linkml/include_participant.yaml b/src/linkml/include_participant.yaml
@@ -35,7 +35,7 @@ classes:
     title: Participant
     is_a: Thing
     slots:
-    - hasStudy     
+    - studyCode     
     - participantGlobalId 
     - participantExternalId
     - familyId
@@ -53,7 +53,6 @@ classes:
     - firstPatientEngagementEvent
     - outcomesVitalStatus
     - ageAtLastVitalStatus
-#    - hasCondition
   # FamilyGroup:
   #   name: FamilyGroup
   #   definition_uri: include:FamilyGroup
@@ -80,8 +79,9 @@ classes:
     is_a: Thing
     description: Co-occurring conditions and other observations for the participant
     slots:
-    - hasStudy     
-    - hasParticipant
+    - studyCode     
+    - participantGlobalId 
+    - participantExternalId
     - eventId
     - eventType
     - conditionMeasureSourceText # will include DS Genetic Diagnosis
@@ -178,12 +178,15 @@ slots:
     description: Age in days of Participant at first recorded study event (enrollment, visit, observation, sample collection, survey completion, etc.). Age at enrollment is preferred, if available.
     title: Age at First Patient Engagement
     range: integer
+    minimum_value: 0
+    maximum_value: 33000
     required: true
   firstPatientEngagementEvent:
     definition_uri: include:firstPatientEngagementEvent
     description: Event for which Age at First Patient Engagement is given (e.g. enrollment, visit, observation, sample collection, survey completion, etc.). Age at enrollment is preferred, if available.
     title: First Patient Engagement Event
     required: true
+    range: string
   outcomesVitalStatus:
     definition_uri: include:outcomesVitalStatus
     description: Whether participant is alive or dead
@@ -194,33 +197,30 @@ slots:
     description: Age in days when participant's vital status was last recorded
     title: Age at Last Vital Status
     range: integer
-#  hasCondition:
-#    definition_uri: include:hasCondition
-#    description: Link to a Condition
-#    title: Has Condition
-#    range: Condition
-  hasStudy:
-    definition_uri: include:hasStudy
-    description: Link to a Study
-    title: Has Study
-    range: Study
+    minimum_value: 0
+    maximum_value: 33000
   eventId:
     definition_uri: include:eventId
     description: Identifier for event (Visit, Survey completion, Sample collection, etc.) to which the Condition data are linked, if applicable. There may be multiple events linked to a Participant.
     title: Event ID
+    range: string
   eventType:
     definition_uri: include:eventType
     description: Type of event for which Event ID is given (Visit, Survey completion, Sample collection, etc.)
     title: Event Type
+    range: string
   conditionMeasureSourceText:
     definition_uri: include:conditionMeasureSourceText
     description: Co-occurring Condition (phenotype or diagnosis) or Measure (observation with numeric value), as described by data contributor. The Down Syndrome Genetic Diagnosis will be rolled into this field.
     title: Condition or Measure Source Text
+    range: string
   ageAtConditionMeasureObservation:
     definition_uri: include:ageAtConditionMeasureObservation
     description: Age in days at which Condition or Measure was observed, recorded, or diagnosed
     title: Age At Condition or Measure Observation
     range: integer
+    minimum_value: 0
+    maximum_value: 33000
   conditionInterpretation:
     definition_uri: include:conditionInterpretation
     description: Whether Condition was observed or not
@@ -299,7 +299,7 @@ enums:
         text: not_observed
         title: Not Observed
         description: Participant was specifically examined or medical record queried for condition and found to be negative
-  enum_conditionDataSource:
+  enum_conditionDataSource: #replace with enum_clinicalDataSourceType & re-harmonize data
     name: enum_conditionDataSource
     permissible_values:
       clinical:
@@ -416,7 +416,7 @@ enums:
         description: Proband + two parents
       trio_plus:
         text: trio_plus
-        title: Trio+
+        title: Trio Plus #need to reharmonize data
         description: Proband + two parents + other relatives
   enum_race:
     name: enum_race

diff --git a/src/linkml/include_study.yaml b/src/linkml/include_study.yaml
@@ -49,6 +49,8 @@ classes:
     - studyPublication
     - studyExpectedNumberOfParticipants
     - guidType
+    - acknowledgments
+    - citationStatement
   Dataset:
     name: Dataset
     definition_uri: include:Dataset
@@ -60,9 +62,10 @@ classes:
     title: Dataset
     is_a: Thing
     slots: 
-    - hasStudy
+    - studyCode
     #add hasDataset to Assay>DataFile?
     - datasetName
+    - datasetDescription
     - datasetGlobalId
     - datasetExternalId
     - datasetExpectedNumberOfParticipants
@@ -103,7 +106,7 @@ slots:
     multivalued: true
   studyDescription:
     definition_uri: include:studyDescription
-    description: Brief description of the study (2-4 sentences). Should match description in https://includedcc.org/studies.
+    description: Brief description of the study (2-4 sentences)
     title: Study Description
     required: true
     range: string
@@ -187,7 +190,7 @@ slots:
     definition_uri: include:expectedDataCategory
     description: Categories of data expected to be collected in this study
     title: Expected Data Category
-    range: enum_DataCategory 
+    range: enum_dataCategory 
     required: true
     multivalued: true
   studyWebsite:
@@ -203,7 +206,7 @@ slots:
     multivalued: true
   studyExpectedNumberOfParticipants: 
     definition_uri: include:studyExpectedNumberOfParticipants
-    description: Expected number of participants in this study
+    description: Expected number of participants in this study. If additional explanation is needed, please add to Study Description field.
     title: Study Expected Number of Participants
     range: integer 
     required: true
@@ -219,12 +222,29 @@ slots:
     title: Study dbGaP
     range: string
     multivalued: true
+  acknowledgments: 
+    definition_uri: include:acknowledgments
+    description: Funding statement and acknowledgments for this study
+    title: Acknowledgments
+    range: string
+    multivalued: true
+  citationStatement: 
+    definition_uri: include:citationStatement
+    description: Statement that secondary data users should use to acknowledge use of this dataset. E.g., "The results analyzed and <published or shown> here are based in whole or in part upon data generated by the INCLUDE (INvestigation of Co-occurring conditions across the Lifespan to Understand Down syndromE) Project <insert accession number(s) and/or study DOI(s)>, and were accessed from the INCLUDE Data Hub and <insert other database(s)>."
+    title: Citation Statement
+    range: string
+    multivalued: true
   datasetName: 
     definition_uri: include:datasetName
     description: Full name of the dataset, provided by contributor
     title: Dataset Name
     range: string 
     required: true
+  datasetDescription: 
+    definition_uri: include:datasetDescription
+    description: Brief additional notes about the dataset (1-3 sentences) that are not already captured in the other fields
+    title: Dataset Description
+    range: string
   datasetGlobalId: 
     definition_uri: include:datasetGlobalId
     description: Unique Global ID for dataset, generated by DCC
@@ -245,13 +265,13 @@ slots:
   #   required: false #should be derived from dataFile if omics
   datasetExpectedNumberOfParticipants: 
     definition_uri: include:datasetExpectedNumberOfParticipants
-    description: Expected number of participants in this dataset
+    description: Expected number of participants in this dataset. If additional explanation is needed, please add to Dataset Description field.
     title: Dataset Expected Number of Participants
     range: integer 
     required: true
   expectedNumberOfFiles: 
     definition_uri: include:expectedNumberOfFiles
-    description: Expected number of files associated with this dataset
+    description: Expected number of files associated with this dataset, including dictionaries. If additional explanation is needed, please add to Dataset Description field.
     title: Expected Number of Files
     range: integer 
     required: false #update to true when this is figured out
@@ -266,20 +286,22 @@ slots:
     definition_uri: include:dataCollectionStartYear
     description: Year that data collection started
     title: Data Collection Start Year
-    pattern: "^1|2\\d(3)$|nan"
+    range: string 
+    #pattern: "^1|2\\d(3)$|nan"
     required: false #change to true when we have for all studies
   dataCollectionEndYear: 
     definition_uri: include:dataCollectionEndYear
     description: Year that data collection ended
     title: Data Collection End Year
-    pattern: "^1|2\\d(3)$|nan"
+    range: string 
+    #pattern: "^1|2\\d(3)$|nan"
     required: false
   datasetDataCategory:
     definition_uri: include:dataCategory
     description: General category of data in dataset; pipe-separated if multiple
     title: Dataset Data Category
     required: true
-    range: enum_DataCategory
+    range: enum_dataCategory
   datasetDataType: 
     definition_uri: include:dataType
     description: Specific type of data contained in dataset; pipe-separated if multiple (e.g. Preprocessed metabolite relative abundance, Absolute protein concentration, Aligned reads, Simple nucleotide variations, GVCF, Gene expression quantifications, Gene fusions, Somatic copy number variations, Somatic structural variations)
@@ -454,6 +476,10 @@ enums:
         text: all_co_occurring_conditions
         title: All Co-occurring Conditions
         meaning: mesh:D013568
+      physical_fitness:
+        text: physical_fitness
+        title: Physical Fitness
+        meaning: mesh:D010809
       other:
         text: other
         title: Other
@@ -499,9 +525,9 @@ enums:
       unknown: 
         text: unknown
         title: Unknown
-  enum_DataCategory: 
-    name: enum_DataCategory
-    definition_uri: include:enum_DataCategory
+  enum_dataCategory: 
+    name: enum_dataCategory
+    definition_uri: include:enum_dataCategory
     permissible_values:
       unharmonized_demographic_clinical_data:
         text: unharmonized_demographic_clinical_data
@@ -533,6 +559,12 @@ enums:
       microbiome:
         text: microbiome
         title: Microbiome
+      fitness:
+        text: fitness
+        title: Fitness
+      physical_activity:
+        text: physical_activity
+        title: Physical Activity
       other:
         text: other
         title: Other