From ae70e08cb8977e76a7902aee905a46596ecd18ed Mon Sep 17 00:00:00 2001 From: lopierra Date: Thu, 19 Feb 2026 13:10:22 -0800 Subject: [PATCH 01/10] change back to ParticipantDataFileManifest (no sample) and update slots per Ann's request --- src/linkml/include_schema.yaml | 16 ++++++---------- 1 file changed, 6 insertions(+), 10 deletions(-) diff --git a/src/linkml/include_schema.yaml b/src/linkml/include_schema.yaml index 830711d..ec11f62 100644 --- a/src/linkml/include_schema.yaml +++ b/src/linkml/include_schema.yaml @@ -156,26 +156,22 @@ 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 From 681adaaee2b5c8d9efd4adaaef0ea56239c21b71 Mon Sep 17 00:00:00 2001 From: lopierra Date: Thu, 26 Feb 2026 15:05:33 -0800 Subject: [PATCH 02/10] make vbrEmail multivalued --- src/linkml/include_schema.yaml | 1 + 1 file changed, 1 insertion(+) diff --git a/src/linkml/include_schema.yaml b/src/linkml/include_schema.yaml index ec11f62..0584247 100644 --- a/src/linkml/include_schema.yaml +++ b/src/linkml/include_schema.yaml @@ -393,6 +393,7 @@ 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 From 95fdfcaedabf927c170e3092b2685fb646914202 Mon Sep 17 00:00:00 2001 From: lopierra Date: Thu, 5 Mar 2026 17:22:28 -0800 Subject: [PATCH 03/10] add studyGlobalId to Study class; update studyCode description to describe it as an acronym instead of an identifier --- src/linkml/include_schema.yaml | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/src/linkml/include_schema.yaml b/src/linkml/include_schema.yaml index 0584247..3b63362 100644 --- a/src/linkml/include_schema.yaml +++ b/src/linkml/include_schema.yaml @@ -31,6 +31,7 @@ classes: description: General information about the study title: Study slots: + - studyGlobalId - studyCode - studyTitle - program @@ -334,9 +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 From b80960caf637fb4e9aa50dcfdf94e8f284bab721 Mon Sep 17 00:00:00 2001 From: lopierra Date: Thu, 5 Mar 2026 17:27:57 -0800 Subject: [PATCH 04/10] comment out accessLimitations and accessRequirements from Dataset since this info is captured in Institutional Certification forms --- src/linkml/include_schema.yaml | 14 -------------- 1 file changed, 14 deletions(-) diff --git a/src/linkml/include_schema.yaml b/src/linkml/include_schema.yaml index 3b63362..ad097f5 100644 --- a/src/linkml/include_schema.yaml +++ b/src/linkml/include_schema.yaml @@ -110,8 +110,6 @@ classes: - experimentalStrategy - experimentalPlatform - publication - - accessLimitations - - accessRequirements - dbgap - otherRepository - otherAccessAuthority @@ -640,18 +638,6 @@ slots: range: string #pattern: "^1|2\\d(3)$|nan" required: false - accessLimitations: - definition_uri: include:accessLimitations - description: Data access limitations, as defined in the GA4GH Data Use Ontology (DUO; can list more than one, pipe separated) - title: Access Limitations - range: string - required: false #make true when we have enums - accessRequirements: - definition_uri: include:accessRequirements - description: Data access requirements, as defined in the GA4GH Data Use Ontology (DUO; can list more than one, pipe separated) - title: Access Requirements - range: string - required: false #make true when we have enums otherRepository: definition_uri: include:otherRepository description: URL if dataset is already deposited in a public repository other than dbGaP (e.g. LONI, Metabolomics Workbench, etc.) From fc63089ac378e0aa1294dfc87184c71ad7d78b53 Mon Sep 17 00:00:00 2001 From: lopierra Date: Wed, 25 Mar 2026 10:47:46 -0700 Subject: [PATCH 05/10] make datasetDescription required --- src/linkml/include_schema.yaml | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/src/linkml/include_schema.yaml b/src/linkml/include_schema.yaml index ad097f5..a4cc269 100644 --- a/src/linkml/include_schema.yaml +++ b/src/linkml/include_schema.yaml @@ -110,6 +110,8 @@ classes: - experimentalStrategy - experimentalPlatform - publication +# - accessLimitations +# - accessRequirements - dbgap - otherRepository - otherAccessAuthority @@ -607,6 +609,7 @@ slots: description: Brief additional notes about the dataset (1-3 sentences) that are not already captured in the other fields title: Dataset Description range: string + required: true datasetGlobalId: definition_uri: include:datasetGlobalId description: Unique Global ID for dataset, generated by DCC @@ -638,6 +641,18 @@ slots: range: string #pattern: "^1|2\\d(3)$|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 + # 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.) From fbe288d0c2e830b3130b1128537df0b69d4a05e5 Mon Sep 17 00:00:00 2001 From: lopierra Date: Thu, 30 Apr 2026 07:56:28 -0700 Subject: [PATCH 06/10] add Hearing Disorders to enum_researchDomain --- src/linkml/include_schema.yaml | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/src/linkml/include_schema.yaml b/src/linkml/include_schema.yaml index a4cc269..8d339b4 100644 --- a/src/linkml/include_schema.yaml +++ b/src/linkml/include_schema.yaml @@ -1190,6 +1190,9 @@ 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 @@ -1293,8 +1296,10 @@ 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: From 95d23ec629696eacff13d964274a4236444cfcb4 Mon Sep 17 00:00:00 2001 From: lopierra Date: Thu, 30 Apr 2026 10:36:35 -0700 Subject: [PATCH 07/10] add Speech/Language/Hearing to enum_dataCategory --- src/linkml/include_schema.yaml | 2 ++ 1 file changed, 2 insertions(+) diff --git a/src/linkml/include_schema.yaml b/src/linkml/include_schema.yaml index 8d339b4..9796173 100644 --- a/src/linkml/include_schema.yaml +++ b/src/linkml/include_schema.yaml @@ -1328,6 +1328,8 @@ enums: title: Other sleep_study: title: Sleep + speech_language_hearing: + title: Speech/Language/Hearing enum_guidType: definition_uri: include:enum_guidType permissible_values: From 3ac0cc6a4387b0f53cc62532dcb648445b82d0ff Mon Sep 17 00:00:00 2001 From: lopierra Date: Thu, 30 Apr 2026 10:47:02 -0700 Subject: [PATCH 08/10] update schemasheet --- src/data/sheets/schemasheet.tsv | 19 +++++++++---------- 1 file changed, 9 insertions(+), 10 deletions(-) diff --git a/src/data/sheets/schemasheet.tsv b/src/data/sheets/schemasheet.tsv index 0988cca..de9b454 100644 --- a/src/data/sheets/schemasheet.tsv +++ b/src/data/sheets/schemasheet.tsv @@ -1,6 +1,7 @@ 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 + studyGlobalId Study Global ID Unique identifier for the study, assigned by DCC true + 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 @@ -8,7 +9,7 @@ class slot title description required range any_of minimum_value maximum_value m 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 +39,11 @@ 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 +135,9 @@ 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 @@ -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 From 6c6d34c8d5f4b03b037fb4fbb62b737782f535ed Mon Sep 17 00:00:00 2001 From: lopierra Date: Thu, 30 Apr 2026 11:07:24 -0700 Subject: [PATCH 09/10] remove Study Global ID for now --- src/data/sheets/schemasheet.tsv | 1 - src/linkml/include_schema.yaml | 12 ++++++------ 2 files changed, 6 insertions(+), 7 deletions(-) diff --git a/src/data/sheets/schemasheet.tsv b/src/data/sheets/schemasheet.tsv index de9b454..6c9eed9 100644 --- a/src/data/sheets/schemasheet.tsv +++ b/src/data/sheets/schemasheet.tsv @@ -1,6 +1,5 @@ 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 - studyGlobalId Study Global ID Unique identifier for the study, assigned by DCC true 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 diff --git a/src/linkml/include_schema.yaml b/src/linkml/include_schema.yaml index 9796173..68816b8 100644 --- a/src/linkml/include_schema.yaml +++ b/src/linkml/include_schema.yaml @@ -31,7 +31,7 @@ classes: description: General information about the study title: Study slots: - - studyGlobalId + # - studyGlobalId - studyCode - studyTitle - program @@ -335,11 +335,11 @@ classes: #################################################################################################### slots: - studyGlobalId: - definition_uri: include:studyGlobalId - description: Unique identifier for the study, assigned by DCC - title: Study Global ID - required: true + # 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 short acronym for the study From 8cac0ee960056c69955f676d0ac7c92fe9e1ff43 Mon Sep 17 00:00:00 2001 From: lopierra Date: Thu, 30 Apr 2026 11:17:58 -0700 Subject: [PATCH 10/10] add DS-SAH to enum_studyCode --- src/data/sheets/schemasheet.tsv | 1 + src/linkml/include_schema.yaml | 2 ++ 2 files changed, 3 insertions(+) diff --git a/src/data/sheets/schemasheet.tsv b/src/data/sheets/schemasheet.tsv index 6c9eed9..5a24f03 100644 --- a/src/data/sheets/schemasheet.tsv +++ b/src/data/sheets/schemasheet.tsv @@ -177,6 +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 diff --git a/src/linkml/include_schema.yaml b/src/linkml/include_schema.yaml index 68816b8..3003a0f 100644 --- a/src/linkml/include_schema.yaml +++ b/src/linkml/include_schema.yaml @@ -1125,6 +1125,8 @@ enums: title: DS-PALS ds_pcgc: title: DS-PCGC + ds_sah: + title: DS-SAH ds_sleep: title: DS-Sleep ds_vite: