diff --git a/src/linkml/include_assay.yaml b/src/linkml/include_assay.yaml index ddac7dd..f858471 100644 --- a/src/linkml/include_assay.yaml +++ b/src/linkml/include_assay.yaml @@ -254,7 +254,7 @@ slots: Metabolomics, Immune profiling, Transcriptomics) title: Data Category required: true - range: string + 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) diff --git a/src/linkml/include_study.yaml b/src/linkml/include_study.yaml index 68bbde4..3e0ad24 100644 --- a/src/linkml/include_study.yaml +++ b/src/linkml/include_study.yaml @@ -7,6 +7,9 @@ prefixes: linkml: prefix_prefix: linkml prefix_reference: https://w3id.org/linkml/ + mesh: + prefix_prefix: mesh + prefix_reference: http://id.nlm.nih.gov/mesh/ imports: - linkml:types - include_core @@ -17,59 +20,316 @@ classes: name: Study definition_uri: include:Study annotations: - required: + required: tag: required value: 'True' description: General information about the study title: Study is_a: Thing - slots: + slots: - studyCode - - studyName + - studyTitle - program - - dbgap + - studyDescription + - principalInvestigatorName + - studyContactName + - studyContactInstitution + - studyContactEmail - vbrEmail - vbrUrl - vbrReadme + - researchDomain + - participantLifespanStage + - selectionCriteria + - studyDesign + - clinicalDataSourceType + - expectedDataCategory + - studyWebsite + - studyDbgap + - studyPublication + - studyExpectedNumberOfParticipants + - guidType + Dataset: + name: Dataset + definition_uri: include:Dataset + annotations: + required: + tag: required + value: 'False' #may change to True later + description: Information about a specific grouping of data files + title: Dataset + is_a: Thing + slots: + - hasStudy + #add hasDataset to Assay>DataFile? + - datasetName + - datasetGlobalId + - datasetExternalId + - datasetExpectedNumberOfParticipants + - expectedNumberOfFiles +# - fileIdList #TBD - may make this into a separate manifest + - dataCollectionStartYear + - dataCollectionEndYear + - datasetDataCategory + - datasetDataType + - datasetExperimentalStrategy + - datasetExperimentalPlatform + - datasetPublication + - accessLimitations + - accessRequirements + - datasetDbgap + - otherRepository + - otherAccessAuthority + slots: studyCode: definition_uri: include:studyCode - description: Unique identifer for the study, assigned by DCC + description: Unique identifer for the study (generally a short acronym) title: Study Code range: enum_studyCode required: true - studyName: - definition_uri: include:studyName - description: Full name of the study, chosen by data contributor - title: Study Name + studyTitle: + definition_uri: include:studyTitle + description: Full title of the study + title: Study Title required: true range: string program: definition_uri: include:program - description: Funding source for the study + description: Funding source(s) for the study (pipe-separated if multiple) title: Program range: enum_program required: true - dbgap: - definition_uri: include:dbgap - description: dbGaP study accession code - title: dbGaP + multivalued: true + studyDescription: + definition_uri: include:studyDescription + description: Brief description of the study (2-4 sentences). Should match description in https://includedcc.org/studies. + title: Study Description + required: true + range: string + principalInvestigatorName: + definition_uri: include:principalInvestigatorName + description: Name(s) of Principal Investigator(s) of this study; pipe-separated if multiple + title: Principal Investigator Name + required: true range: string + multivalued: true + studyContactName: + definition_uri: include:studyContactName + description: Name of contact person for this study; pipe-separated if multiple + title: Study Contact Name + required: true + range: string + multivalued: true + studyContactInstitution: + definition_uri: include:studyContactInstitution + description: Institution of contact person for this study; pipe-separated if multiple + title: Study Contact Institution + required: true + range: string + multivalued: true + studyContactEmail: + definition_uri: include:studyContactEmail + description: Email address of contact person for this study; pipe-separated if multiple + title: Study Contact Email + required: true + range: string + multivalued: true vbrEmail: definition_uri: include:vbrEmail description: Email address for Virtual Biorepository requests/inquiries - title: Virtual Biorepository Email + title: VBR Email range: string vbrUrl: definition_uri: include:vbrUrl description: Link to Virtual Biorepository request form - title: Virtual Biorepository URL - range: string + title: VBR URL + range: uri vbrReadme: definition_uri: include:vbrReadme description: Instructions for contacting or requesting samples from Virtual Biorepository - title: Virtual Biorepository Readme + title: VBR Readme range: string + researchDomain: + definition_uri: include:researchDomain + description: Main research domain(s) of the study, other than Down syndrome; pipe-separated if multiple + title: Research Domain + range: enum_researchDomain + required: true + multivalued: true + participantLifespanStage: + definition_uri: include:participantLifespanStage + description: Focus age group(s) of the study population; pipe-separated if multiple + title: Participant Lifespan Stage + range: enum_participantLifespanStage + required: true + multivalued: true + selectionCriteria: + definition_uri: include:selectionCriteria + description: Brief description of inclusion and/or exclusion criteria for the study + title: Selection Criteria + range: string + studyDesign: + definition_uri: include:studyDesign + description: Overall design of study, including whether it is longitudinal and whether family members/unrelated controls are also enrolled + title: Study Design + range: string + required: true + clinicalDataSourceType: + definition_uri: include:clinicalDataSourceType + description: Source(s) of data collected from study participants; pipe-separated if multiple + title: Clinical Data Source Type + range: enum_clinicalDataSourceType + #TODO: replace enum_conditionDataSource with this - or consider deleting slot conditionDataSource + required: true + multivalued: true + expectedDataCategory: + definition_uri: include:expectedDataCategory + description: Categories of data expected to be collected in this study + title: Expected Data Category + range: enum_DataCategory + required: true + multivalued: true + studyWebsite: + definition_uri: include:studyWebsite + description: Website for the study + title: Study Website + range: uri + studyPublication: + definition_uri: include:studyPublication + description: URL for publication(s) describing the study's rationale and methodology (PubMed Central preferred but not required; pipe-separated if multiple) + title: Study Publication + range: uri + multivalued: true + studyExpectedNumberOfParticipants: + definition_uri: include:studyExpectedNumberOfParticipants + description: Expected number of participants in this study + title: Study Expected Number of Participants + range: integer + required: true + guidType: + definition_uri: include:guidType + description: System used to generate globally unique identifiers (GUIDs) + title: GUID Type + range: enum_guidType + required: true + studyDbgap: + definition_uri: include:studyDbgap + description: dbGaP "phs" accession code(s) associated with this Study, either for access or informational purposes (pipe-separated if multiple) + title: Study dbGaP + 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 + datasetGlobalId: + definition_uri: include:datasetGlobalId + description: Unique Global ID for dataset, generated by DCC + title: Dataset Global ID + range: string + required: false #update to true when this is figured out + datasetExternalId: + definition_uri: include:datasetExternalId + description: Unique identifier or code for dataset, if provided by contributor + title: Dataset External ID + range: string + # fileIdList: + # definition_uri: include:fileIdList + # description: Global IDs for files associated with this dataset. Should include one or more dictionary files that provide definitions for every field in every file + # title: File ID List + # range: string + # multivalued: true + # required: false #should be derived from dataFile if omics + datasetExpectedNumberOfParticipants: + definition_uri: include:datasetExpectedNumberOfParticipants + description: Expected number of participants in this dataset + title: Dataset Expected Number of Participants + range: integer + required: true + expectedNumberOfFiles: + definition_uri: include:expectedNumberOfFiles + description: Expected number of files associated with this dataset + title: Expected Number of Files + range: integer + required: false #update to true when this is figured out + # participantIdList: + # definition_uri: include:participantIdList + # description: Global IDs for Participants associated with this dataset + # title: Participant ID List + # range: string + # multivalued: true + # required: false #not sure if we need this - update to true when this is figured out + dataCollectionStartYear: + definition_uri: include:dataCollectionStartYear + description: Year that data collection started + title: Data Collection Start Year + 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" + 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 + 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) + title: Dataset Data Type + range: string #eventually share enum with dataFile + datasetExperimentalStrategy: + definition_uri: include:experimentalStrategy + description: Experimental method used to obtain data in dataset; pipe-separated if multiple (e.g. Whole genome sequencing, RNAseq, Multiplex immunoassay, Mass spec metabolomics) + title: Dataset Experimental Strategy + range: string #eventually share enum with dataFile + datasetExperimentalPlatform: + definition_uri: include:experimentalPlatform + description: Specific platform used to perform experiment; pipe-separated if multiple (e.g. SOMAscan, MSD, Luminex, Illumina) + title: Dataset Experimental Platform + range: string #eventually share enum with dataFile + datasetPublication: + definition_uri: include:datasetPublication + description: URL for publication(s) describing the dataset's rationale and methodology (PubMed Central preferred but not required; pipe-separated if multiple) + title: Dataset Publication + range: uri + multivalued: true + 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 + datasetDbgap: + definition_uri: include:datasetDbgap + description: dbGaP "phs" accession code(s) required to access the files in this Dataset, if applicable (pipe-separated if multiple) + title: Dataset dbGaP + range: string + multivalued: true + 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.) + title: Other Repository + range: uri + otherAccessAuthority: + definition_uri: include:otherAccessAuthority + description: Email or URL for dataset's Access Authority, if not dbGaP + title: Other Access Authority + range: string + enums: enum_program: name: enum_program @@ -81,12 +341,15 @@ enums: kf: text: kf title: KF + other: + text: other + title: Other enum_studyCode: name: enum_studyCode definition_uri: include:enum_studyCode permissible_values: - abcds: - text: abcds + abc_ds: + text: abc_ds title: ABC-DS ads: text: ads @@ -100,6 +363,9 @@ enums: bri_dsr: text: bri_dsr title: BRI-DSR + child_ds: + text: child_ds + title: CHILD-DS charge_ds: text: charge_ds title: CHARGE-DS @@ -144,7 +410,7 @@ enums: title: ECODS exceeds: text: exceeds - title: ExCEEDS + title: EXcEEDS htp: text: htp title: HTP @@ -160,3 +426,129 @@ enums: x01_hakonarson: text: x01_hakonarson title: X01-Hakonarson + enum_researchDomain: + name: enum_researchDomain + definition_uri: include:enum_researchDomain + permissible_values: + behavior_and_behavior_mechanisms: + text: behavior_and_behavior_mechanisms + title: Behavior and Behavior Mechanisms + meaning: mesh:D001520 + congenital_heart_defects: + text: congenital_heart_defects + title: Congenital Heart Defects + meaning: mesh:D006330 + immune_system_diseases: + text: immune_system_diseases + title: Immune System Diseases + meaning: mesh:D007154 + hematologic_diseases: + text: hematologic_diseases + title: Hematologic Diseases + meaning: mesh:D006402 + sleep_wake_disorders: + text: sleep_wake_disorders + title: Sleep Wake Disorders + meaning: mesh:D012893 + all_co_occurring_conditions: + text: all_co_occurring_conditions + title: All Co-occurring Conditions + meaning: mesh:D013568 + other: + text: other + title: Other + enum_participantLifespanStage: + name: enum_participantLifespanStage + definition_uri: include:enum_participantLifespanStage + permissible_values: + fetal: + text: fetal + title: Fetal + neonatal: + text: neonatal + title: Neonatal + description: 0-28 days old + pediatric: + text: pediatric + title: Pediatric + description: Birth-17 years old + adult: + text: adult + title: Adult + description: 18+ years old + enum_clinicalDataSourceType: + #TODO: replace enum_conditionDataSource with this - or consider deleting slot conditionDataSource + name: enum_clinicalDataSourceType + definition_uri: include:enum_clinicalDataSourceType + permissible_values: + medical_record: + text: medical_record + title: Medical Record + description: Data obtained directly from medical record + investigator_assessment: + text: investigator_assessment + title: Investigator Assessment + description: Data obtained by examination, interview, etc. with investigator + participant_or_caregiver_report: + text: participant_or_caregiver_report + title: Participant or Caregiver Report + description: Data obtained from survey, questionnaire, etc. + other: + text: other + title: Other + unknown: + text: unknown + title: Unknown + enum_DataCategory: + name: enum_DataCategory + definition_uri: include:enum_DataCategory + permissible_values: + unharmonized_demographic_clinical_data: + text: unharmonized_demographic_clinical_data + title: Unharmonized Demographic/Clinical Data + harmonized_demographic_clinical_data: + text: harmonized_demographic_clinical_data + title: Harmonized Demographic/Clinical Data + genomics: + text: genomics + title: Genomics + transcriptomics: + text: transcriptomics + title: Transcriptomics + proteomics: + text: proteomics + title: Proteomics + metabolomics: + text: metabolomics + title: Metabolomics + cognitive_behavioral: + text: cognitive_behavioral + title: Cognitive/Behavioral + immune_maps: + text: immune_maps + title: Immune Maps + imaging: + text: imaging + title: Imaging + microbiome: + text: microbiome + title: Microbiome + other: + text: other + title: Other + enum_guidType: + name: enum_guidType + definition_uri: include:enum_guidType + permissible_values: + ndar: + text: ndar + title: NDAR + description: GUID generated by NIMH Data Archive (NDA) GUID tool + other: + text: other + title: Other + description: GUID generated by other system + no_guid: + text: no_guid + title: No GUID + description: No GUIDs used in this study \ No newline at end of file