diff --git a/ark.all_attributes.csv b/ark.all_attributes.csv index 642aafd..9142db7 100644 --- a/ark.all_attributes.csv +++ b/ark.all_attributes.csv @@ -17,7 +17,7 @@ "parentBiospecimenID","The biospecimenID associated with the originating biospecimen for derived or child biospecimens.","","","FALSE","","","","string","","","","" "biospecimenType","A label indicating the biological material collected for experimentation and data collection. Where applicable, provide all types in a comma-separated list.","PBMCs, cell line, fibroblast-like synoviocyte, kidney biopsy, none, plasma, primary cell culture, saliva, salivary gland, serum, skin biopsy, skin swab, stool, suction blister cells, suction blister fluid, synovial fluid, synovial tissue, total leukocytes, urine, uvea, whole blood","","TRUE","","","#BiospecimenMetadataTemplate str^^#InVitroBiospecimenMetadataTemplate^^list like error","string_list","","","","" "primaryCellSource","A label indicating the biological source material from which a primary cell culture was derived.","PBMCs, kidney, pannus-derived dermis, pannus-derived epidermis, salivary gland, synovial tissue, total leukocytes, urine, uvea, whole blood","","TRUE","","","","string","","","","" -"metadataType","A label further classifying the content of metadata resource.","assay, biospecimen, cell coordinates, data dictionary, file manifest, medication, other, phenotype, protocol, single-cell metadata, target panel, template, tissue microarray map, tissue multiarray map, user manual","","TRUE","","","","string","","","","" +"metadataType","A label further classifying the content of metadata resource.","assay, biospecimen, cell coordinates, clinical, data dictionary, demographics, file manifest, medication, other, phenotype, protocol, single-cell metadata, target panel, template, tissue microarray map, tissue multiarray map, user manual","","TRUE","","","","string","","","","" "codingLanguage","The coding, aka programming, language(s) contained in the file marked with `resourceType = code`. Select all that apply.","C, C#, C++, Fortan, Java, Julia, Matlab, Python, R, Ruby, SAS","","TRUE","","","","string","","","","" "visitID","Ordinal ID distinguishing different patient visits.","","","TRUE","","","","string","","","","" "softwareAndVersion","Relevant software and version used to generate the data file.","BD FACSDiva 8.0.1, Cell Ranger 9.0.1, Cell Ranger ATAC v1.1.0, Cell Ranger v3.0.0, Cell Ranger v3.0.1, Cell Ranger v3.0.2, Cell Ranger v3.1.0, Cell Ranger v4.0.0, Cell Ranger v5.0.0, Cell Ranger v5.0.1, Cell Ranger v6.0.0, Cell Ranger v6.0.1, Cell Ranger v6.0.2, Cell Ranger v6.1.0, Cell Ranger v6.1.1, Cell Ranger v6.1.2, Cell Ranger v7.0.0, Cell Ranger v7.0.1, Cell Ranger v7.1.0, Cell Ranger v7.2.0, Cell Ranger v8.0.0, Cell Ranger v8.0.1, Cell Ranger v9.0.0, Space Ranger 3.0.0, Space Ranger 3.0.1, Space Ranger 3.1.0, Space Ranger 3.1.1, Space Ranger 3.1.2, Space Ranger 3.1.3, demuxlet","","FALSE","","","","string","","","","" @@ -108,3 +108,4 @@ "ImmPortAccession","Accession to corresponding information in ImmPort.","","","FALSE","","","regex search ^SDY error","string","","","","^SDY" "cellOntologyID","Cell Ontology CL identifier that best describes a biopsecimen used to generate data, e.g., CL:0000084 for T cell.","","","FALSE","","","regex search ^CL: error","string","","","","^CL:" "PMCID","Pubmed Central Identifier, formatted as a compact URI string that will automatically resolve into a URL based on the Synapse bioregistry; e.g., pmc:PMCxxxxxxxx","","","FALSE","","","regex search ^pmc:PMC[0-9]{8} error","string","","","","^pmc:PMC[0-9]{8}" +"demultiplexMethod","This attribute indicates the general method that needs to be used to demultiplex multispecimen raw data.","genotypic demux, hashtag oligos, sample barcode, slide array map","","TRUE","","","","string","","","","" diff --git a/model_contexts/biospecimen/ark.biospecimen_model.csv b/model_contexts/biospecimen/ark.biospecimen_model.csv index c5205f9..2658fd3 100644 --- a/model_contexts/biospecimen/ark.biospecimen_model.csv +++ b/model_contexts/biospecimen/ark.biospecimen_model.csv @@ -32,7 +32,7 @@ "specimenModality","Label assigned to experimental data files indicating whether the data contained corresponds to a single or multiple biospecimens","multispecimen, single specimen, unknown","","TRUE","","","","string","","","","" "parentBiospecimenID","The biospecimenID associated with the originating biospecimen for derived or child biospecimens.","","","FALSE","","","","string","","","","" "primaryCellSource","A label indicating the biological source material from which a primary cell culture was derived.","PBMCs, kidney, pannus-derived dermis, pannus-derived epidermis, salivary gland, synovial tissue, total leukocytes, urine, uvea, whole blood","","TRUE","","","","string","","","","" -"metadataType","A label further classifying the content of metadata resource.","assay, biospecimen, cell coordinates, data dictionary, file manifest, medication, other, phenotype, protocol, single-cell metadata, target panel, template, tissue microarray map, tissue multiarray map, user manual","","TRUE","","","","string","","","","" +"metadataType","A label further classifying the content of metadata resource.","assay, biospecimen, cell coordinates, clinical, data dictionary, demographics, file manifest, medication, other, phenotype, protocol, single-cell metadata, target panel, template, tissue microarray map, tissue multiarray map, user manual","","TRUE","","","","string","","","","" "codingLanguage","The coding, aka programming, language(s) contained in the file marked with `resourceType = code`. Select all that apply.","C, C#, C++, Fortan, Java, Julia, Matlab, Python, R, Ruby, SAS","","TRUE","","","","string","","","","" "visitID","Ordinal ID distinguishing different patient visits.","","","TRUE","","","","string","","","","" "softwareAndVersion","Relevant software and version used to generate the data file.","BD FACSDiva 8.0.1, Cell Ranger 9.0.1, Cell Ranger ATAC v1.1.0, Cell Ranger v3.0.0, Cell Ranger v3.0.1, Cell Ranger v3.0.2, Cell Ranger v3.1.0, Cell Ranger v4.0.0, Cell Ranger v5.0.0, Cell Ranger v5.0.1, Cell Ranger v6.0.0, Cell Ranger v6.0.1, Cell Ranger v6.0.2, Cell Ranger v6.1.0, Cell Ranger v6.1.1, Cell Ranger v6.1.2, Cell Ranger v7.0.0, Cell Ranger v7.0.1, Cell Ranger v7.1.0, Cell Ranger v7.2.0, Cell Ranger v8.0.0, Cell Ranger v8.0.1, Cell Ranger v9.0.0, Space Ranger 3.0.0, Space Ranger 3.0.1, Space Ranger 3.1.0, Space Ranger 3.1.1, Space Ranger 3.1.2, Space Ranger 3.1.3, demuxlet","","FALSE","","","","string","","","","" @@ -122,3 +122,4 @@ "ImmPortAccession","Accession to corresponding information in ImmPort.","","","FALSE","","","regex search ^SDY error","string","","","","^SDY" "cellOntologyID","Cell Ontology CL identifier that best describes a biopsecimen used to generate data, e.g., CL:0000084 for T cell.","","","FALSE","","","regex search ^CL: error","string","","","","^CL:" "PMCID","Pubmed Central Identifier, formatted as a compact URI string that will automatically resolve into a URL based on the Synapse bioregistry; e.g., pmc:PMCxxxxxxxx","","","FALSE","","","regex search ^pmc:PMC[0-9]{8} error","string","","","","^pmc:PMC[0-9]{8}" +"demultiplexMethod","This attribute indicates the general method that needs to be used to demultiplex multispecimen raw data.","genotypic demux, hashtag oligos, sample barcode, slide array map","","TRUE","","","","string","","","","" diff --git a/model_contexts/clinical/ark.clinical_model.csv b/model_contexts/clinical/ark.clinical_model.csv index 9bb7c60..579368c 100644 --- a/model_contexts/clinical/ark.clinical_model.csv +++ b/model_contexts/clinical/ark.clinical_model.csv @@ -24,7 +24,7 @@ "parentBiospecimenID","The biospecimenID associated with the originating biospecimen for derived or child biospecimens.","","","FALSE","","","","string","","","","" "biospecimenType","A label indicating the biological material collected for experimentation and data collection. Where applicable, provide all types in a comma-separated list.","PBMCs, cell line, fibroblast-like synoviocyte, kidney biopsy, none, plasma, primary cell culture, saliva, salivary gland, serum, skin biopsy, skin swab, stool, suction blister cells, suction blister fluid, synovial fluid, synovial tissue, total leukocytes, urine, uvea, whole blood","","TRUE","","","#BiospecimenMetadataTemplate str^^#InVitroBiospecimenMetadataTemplate^^list like error","string_list","","","","" "primaryCellSource","A label indicating the biological source material from which a primary cell culture was derived.","PBMCs, kidney, pannus-derived dermis, pannus-derived epidermis, salivary gland, synovial tissue, total leukocytes, urine, uvea, whole blood","","TRUE","","","","string","","","","" -"metadataType","A label further classifying the content of metadata resource.","assay, biospecimen, cell coordinates, data dictionary, file manifest, medication, other, phenotype, protocol, single-cell metadata, target panel, template, tissue microarray map, tissue multiarray map, user manual","","TRUE","","","","string","","","","" +"metadataType","A label further classifying the content of metadata resource.","assay, biospecimen, cell coordinates, clinical, data dictionary, demographics, file manifest, medication, other, phenotype, protocol, single-cell metadata, target panel, template, tissue microarray map, tissue multiarray map, user manual","","TRUE","","","","string","","","","" "codingLanguage","The coding, aka programming, language(s) contained in the file marked with `resourceType = code`. Select all that apply.","C, C#, C++, Fortan, Java, Julia, Matlab, Python, R, Ruby, SAS","","TRUE","","","","string","","","","" "visitID","Ordinal ID distinguishing different patient visits.","","","TRUE","","","","string","","","","" "softwareAndVersion","Relevant software and version used to generate the data file.","BD FACSDiva 8.0.1, Cell Ranger 9.0.1, Cell Ranger ATAC v1.1.0, Cell Ranger v3.0.0, Cell Ranger v3.0.1, Cell Ranger v3.0.2, Cell Ranger v3.1.0, Cell Ranger v4.0.0, Cell Ranger v5.0.0, Cell Ranger v5.0.1, Cell Ranger v6.0.0, Cell Ranger v6.0.1, Cell Ranger v6.0.2, Cell Ranger v6.1.0, Cell Ranger v6.1.1, Cell Ranger v6.1.2, Cell Ranger v7.0.0, Cell Ranger v7.0.1, Cell Ranger v7.1.0, Cell Ranger v7.2.0, Cell Ranger v8.0.0, Cell Ranger v8.0.1, Cell Ranger v9.0.0, Space Ranger 3.0.0, Space Ranger 3.0.1, Space Ranger 3.1.0, Space Ranger 3.1.1, Space Ranger 3.1.2, Space Ranger 3.1.3, demuxlet","","FALSE","","","","string","","","","" @@ -114,3 +114,4 @@ "ImmPortAccession","Accession to corresponding information in ImmPort.","","","FALSE","","","regex search ^SDY error","string","","","","^SDY" "cellOntologyID","Cell Ontology CL identifier that best describes a biopsecimen used to generate data, e.g., CL:0000084 for T cell.","","","FALSE","","","regex search ^CL: error","string","","","","^CL:" "PMCID","Pubmed Central Identifier, formatted as a compact URI string that will automatically resolve into a URL based on the Synapse bioregistry; e.g., pmc:PMCxxxxxxxx","","","FALSE","","","regex search ^pmc:PMC[0-9]{8} error","string","","","","^pmc:PMC[0-9]{8}" +"demultiplexMethod","This attribute indicates the general method that needs to be used to demultiplex multispecimen raw data.","genotypic demux, hashtag oligos, sample barcode, slide array map","","TRUE","","","","string","","","","" diff --git a/model_contexts/fastq/ark.fastq_model.csv b/model_contexts/fastq/ark.fastq_model.csv index 6d285dc..06374b2 100644 --- a/model_contexts/fastq/ark.fastq_model.csv +++ b/model_contexts/fastq/ark.fastq_model.csv @@ -24,7 +24,7 @@ "parentBiospecimenID","The biospecimenID associated with the originating biospecimen for derived or child biospecimens.","","","FALSE","","","","string","","","","" "biospecimenType","A label indicating the biological material collected for experimentation and data collection. Where applicable, provide all types in a comma-separated list.","PBMCs, cell line, fibroblast-like synoviocyte, kidney biopsy, none, plasma, primary cell culture, saliva, salivary gland, serum, skin biopsy, skin swab, stool, suction blister cells, suction blister fluid, synovial fluid, synovial tissue, total leukocytes, urine, uvea, whole blood","","TRUE","","","#BiospecimenMetadataTemplate str^^#InVitroBiospecimenMetadataTemplate^^list like error","string_list","","","","" "primaryCellSource","A label indicating the biological source material from which a primary cell culture was derived.","PBMCs, kidney, pannus-derived dermis, pannus-derived epidermis, salivary gland, synovial tissue, total leukocytes, urine, uvea, whole blood","","TRUE","","","","string","","","","" -"metadataType","A label further classifying the content of metadata resource.","assay, biospecimen, cell coordinates, data dictionary, file manifest, medication, other, phenotype, protocol, single-cell metadata, target panel, template, tissue microarray map, tissue multiarray map, user manual","","TRUE","","","","string","","","","" +"metadataType","A label further classifying the content of metadata resource.","assay, biospecimen, cell coordinates, clinical, data dictionary, demographics, file manifest, medication, other, phenotype, protocol, single-cell metadata, target panel, template, tissue microarray map, tissue multiarray map, user manual","","TRUE","","","","string","","","","" "codingLanguage","The coding, aka programming, language(s) contained in the file marked with `resourceType = code`. Select all that apply.","C, C#, C++, Fortan, Java, Julia, Matlab, Python, R, Ruby, SAS","","TRUE","","","","string","","","","" "visitID","Ordinal ID distinguishing different patient visits.","","","TRUE","","","","string","","","","" "softwareAndVersion","Relevant software and version used to generate the data file.","BD FACSDiva 8.0.1, Cell Ranger 9.0.1, Cell Ranger ATAC v1.1.0, Cell Ranger v3.0.0, Cell Ranger v3.0.1, Cell Ranger v3.0.2, Cell Ranger v3.1.0, Cell Ranger v4.0.0, Cell Ranger v5.0.0, Cell Ranger v5.0.1, Cell Ranger v6.0.0, Cell Ranger v6.0.1, Cell Ranger v6.0.2, Cell Ranger v6.1.0, Cell Ranger v6.1.1, Cell Ranger v6.1.2, Cell Ranger v7.0.0, Cell Ranger v7.0.1, Cell Ranger v7.1.0, Cell Ranger v7.2.0, Cell Ranger v8.0.0, Cell Ranger v8.0.1, Cell Ranger v9.0.0, Space Ranger 3.0.0, Space Ranger 3.0.1, Space Ranger 3.1.0, Space Ranger 3.1.1, Space Ranger 3.1.2, Space Ranger 3.1.3, demuxlet","","FALSE","","","","string","","","","" @@ -114,3 +114,4 @@ "ImmPortAccession","Accession to corresponding information in ImmPort.","","","FALSE","","","regex search ^SDY error","string","","","","^SDY" "cellOntologyID","Cell Ontology CL identifier that best describes a biopsecimen used to generate data, e.g., CL:0000084 for T cell.","","","FALSE","","","regex search ^CL: error","string","","","","^CL:" "PMCID","Pubmed Central Identifier, formatted as a compact URI string that will automatically resolve into a URL based on the Synapse bioregistry; e.g., pmc:PMCxxxxxxxx","","","FALSE","","","regex search ^pmc:PMC[0-9]{8} error","string","","","","^pmc:PMC[0-9]{8}" +"demultiplexMethod","This attribute indicates the general method that needs to be used to demultiplex multispecimen raw data.","genotypic demux, hashtag oligos, sample barcode, slide array map","","TRUE","","","","string","","","","" diff --git a/model_contexts/fcs/ark.fcs_model.csv b/model_contexts/fcs/ark.fcs_model.csv index 384a0bd..cd8b250 100644 --- a/model_contexts/fcs/ark.fcs_model.csv +++ b/model_contexts/fcs/ark.fcs_model.csv @@ -23,7 +23,7 @@ "parentBiospecimenID","The biospecimenID associated with the originating biospecimen for derived or child biospecimens.","","","FALSE","","","","string","","","","" "biospecimenType","A label indicating the biological material collected for experimentation and data collection. Where applicable, provide all types in a comma-separated list.","PBMCs, cell line, fibroblast-like synoviocyte, kidney biopsy, none, plasma, primary cell culture, saliva, salivary gland, serum, skin biopsy, skin swab, stool, suction blister cells, suction blister fluid, synovial fluid, synovial tissue, total leukocytes, urine, uvea, whole blood","","TRUE","","","#BiospecimenMetadataTemplate str^^#InVitroBiospecimenMetadataTemplate^^list like error","string_list","","","","" "primaryCellSource","A label indicating the biological source material from which a primary cell culture was derived.","PBMCs, kidney, pannus-derived dermis, pannus-derived epidermis, salivary gland, synovial tissue, total leukocytes, urine, uvea, whole blood","","TRUE","","","","string","","","","" -"metadataType","A label further classifying the content of metadata resource.","assay, biospecimen, cell coordinates, data dictionary, file manifest, medication, other, phenotype, protocol, single-cell metadata, target panel, template, tissue microarray map, tissue multiarray map, user manual","","TRUE","","","","string","","","","" +"metadataType","A label further classifying the content of metadata resource.","assay, biospecimen, cell coordinates, clinical, data dictionary, demographics, file manifest, medication, other, phenotype, protocol, single-cell metadata, target panel, template, tissue microarray map, tissue multiarray map, user manual","","TRUE","","","","string","","","","" "codingLanguage","The coding, aka programming, language(s) contained in the file marked with `resourceType = code`. Select all that apply.","C, C#, C++, Fortan, Java, Julia, Matlab, Python, R, Ruby, SAS","","TRUE","","","","string","","","","" "visitID","Ordinal ID distinguishing different patient visits.","","","TRUE","","","","string","","","","" "softwareAndVersion","Relevant software and version used to generate the data file.","BD FACSDiva 8.0.1, Cell Ranger 9.0.1, Cell Ranger ATAC v1.1.0, Cell Ranger v3.0.0, Cell Ranger v3.0.1, Cell Ranger v3.0.2, Cell Ranger v3.1.0, Cell Ranger v4.0.0, Cell Ranger v5.0.0, Cell Ranger v5.0.1, Cell Ranger v6.0.0, Cell Ranger v6.0.1, Cell Ranger v6.0.2, Cell Ranger v6.1.0, Cell Ranger v6.1.1, Cell Ranger v6.1.2, Cell Ranger v7.0.0, Cell Ranger v7.0.1, Cell Ranger v7.1.0, Cell Ranger v7.2.0, Cell Ranger v8.0.0, Cell Ranger v8.0.1, Cell Ranger v9.0.0, Space Ranger 3.0.0, Space Ranger 3.0.1, Space Ranger 3.1.0, Space Ranger 3.1.1, Space Ranger 3.1.2, Space Ranger 3.1.3, demuxlet","","FALSE","","","","string","","","","" @@ -113,3 +113,4 @@ "ImmPortAccession","Accession to corresponding information in ImmPort.","","","FALSE","","","regex search ^SDY error","string","","","","^SDY" "cellOntologyID","Cell Ontology CL identifier that best describes a biopsecimen used to generate data, e.g., CL:0000084 for T cell.","","","FALSE","","","regex search ^CL: error","string","","","","^CL:" "PMCID","Pubmed Central Identifier, formatted as a compact URI string that will automatically resolve into a URL based on the Synapse bioregistry; e.g., pmc:PMCxxxxxxxx","","","FALSE","","","regex search ^pmc:PMC[0-9]{8} error","string","","","","^pmc:PMC[0-9]{8}" +"demultiplexMethod","This attribute indicates the general method that needs to be used to demultiplex multispecimen raw data.","genotypic demux, hashtag oligos, sample barcode, slide array map","","TRUE","","","","string","","","","" diff --git a/model_contexts/main/ark.main_context.csv b/model_contexts/main/ark.main_context.csv index 62a82c3..70d7e37 100644 --- a/model_contexts/main/ark.main_context.csv +++ b/model_contexts/main/ark.main_context.csv @@ -10,5 +10,8 @@ snATAC-seq Assay Metadata Template,A template outlining metadata to be collected CyTOF Assay Metadata Template,A template outlining assay-related metadata for a cytometry time-of-flight (CyTOF) dataset. Each row corresponds to a biospecimen profiled in the experiment.,,"Component, assay, biospecimenID, sampleProcessingBatch, dataCollectionBatch, platform, softwareAndVersion, targetPanel, targetPanelSynID, targetPanelSize",,,,,,,,, metadata,"Any file that contains curated data describing an experiment and experimental-derived data, including metadata about study subjects, biospecimens, protocols, assay reagents, marker panels, and ID mappings. Is a valid value of Resource Type that triggers conditional dependencies for additional attributes.",,"metadataType, metadataStandards",,,,,,,,, 10x GEM-X Flex Gene Expression Human,A scRNA-seq method that analyzes gene expression using pre-designed probes. Is a valid value of `libraryPrepMethod` and when selected triggers conditional dependencies for additional metadata collection.,,10xProbeSetReference,,,,,,,,, -multispecimen,Is a valid value of `specimenModality` that triggers conditional dependencies for additional attributes.,,libraryID,,,,,,,,, -single specimen,Is a valid value of `specimenModality` that triggers conditional dependencies for additional attributes.,,biospecimenID,,,,,,,,, \ No newline at end of file +multispecimen,Is a valid value of `specimenModality` that triggers conditional dependencies for additional attributes.,,"libraryID, demultiplexMethod",,,,,,,,, +single specimen,Is a valid value of `specimenModality` that triggers conditional dependencies for additional attributes.,,biospecimenID,,,,,,,,, +metadataType,A label further classifying the content of metadata resource. If a metadata file contains multiple types please specify all that apply in a comma-delimited list,"demographics, clinical, assay, biospecimen, cell coordinates, data dictionary, file manifest, medication, other, phenotype, protocol, single-cell metadata, target panel, template, tissue microarray map, user manual",,TRUE,,,list like error,string_list,,,, +metadataStandards,Metadata standards used to generate the metadata.,"ARK data model, user-defined",,TRUE,,,,string,,,, +demultiplexMethod,This attribute indicates the general method that needs to be used to demultiplex multispecimen raw data.,"genotypic demux, hashtag oligos, sample barcode, slide array map",,TRUE,,,,string,,,, \ No newline at end of file diff --git a/model_contexts/main/ark.main_model.csv b/model_contexts/main/ark.main_model.csv index 0369058..7ac2b29 100644 --- a/model_contexts/main/ark.main_model.csv +++ b/model_contexts/main/ark.main_model.csv @@ -10,8 +10,11 @@ "CyTOF Assay Metadata Template","A template outlining assay-related metadata for a cytometry time-of-flight (CyTOF) dataset. Each row corresponds to a biospecimen profiled in the experiment.","","Component, assay, biospecimenID, sampleProcessingBatch, dataCollectionBatch, platform, softwareAndVersion, targetPanel, targetPanelSynID, targetPanelSize","","","","","","","","","" "metadata","Any file that contains curated data describing an experiment and experimental-derived data, including metadata about study subjects, biospecimens, protocols, assay reagents, marker panels, and ID mappings. Is a valid value of Resource Type that triggers conditional dependencies for additional attributes.","","metadataType, metadataStandards","","","","","","","","","" "10x GEM-X Flex Gene Expression Human","A scRNA-seq method that analyzes gene expression using pre-designed probes. Is a valid value of `libraryPrepMethod` and when selected triggers conditional dependencies for additional metadata collection.","","10xProbeSetReference","","","","","","","","","" -"multispecimen","Is a valid value of `specimenModality` that triggers conditional dependencies for additional attributes.","","libraryID","","","","","","","","","" +"multispecimen","Is a valid value of `specimenModality` that triggers conditional dependencies for additional attributes.","","libraryID, demultiplexMethod","","","","","","","","","" "single specimen","Is a valid value of `specimenModality` that triggers conditional dependencies for additional attributes.","","biospecimenID","","","","","","","","","" +"metadataType","A label further classifying the content of metadata resource. If a metadata file contains multiple types please specify all that apply in a comma-delimited list","demographics, clinical, assay, biospecimen, cell coordinates, data dictionary, file manifest, medication, other, phenotype, protocol, single-cell metadata, target panel, template, tissue microarray map, user manual","","TRUE","","","list like error","string_list","","","","" +"metadataStandards","Metadata standards used to generate the metadata.","ARK data model, user-defined","","TRUE","","","","string","","","","" +"demultiplexMethod","This attribute indicates the general method that needs to be used to demultiplex multispecimen raw data.","genotypic demux, hashtag oligos, sample barcode, slide array map","","TRUE","","","","string","","","","" "Component","A high-level attribute for grouping attributes into templates.","","","TRUE","","","","string","","","","" "fileFormat","Standard file format name or file extension","bai, bam, bed, bim, csv, czi, docx, dose, erate, fam, fastq, fcs, geojson, h5, h5ad, html, info, mcd, mtx, parquet, pdf, py, rds, rec, svs, tbi, tgz, tsv, txt, vcf, xls, xlsx, zip","","TRUE","","","","string","","","","" "program","Name of the funding program that supported the generation of data and associated files","AMP AIM, AMP RA/SLE, Community Contribution","","TRUE","","","","string","","","","" @@ -30,7 +33,6 @@ "parentBiospecimenID","The biospecimenID associated with the originating biospecimen for derived or child biospecimens.","","","FALSE","","","","string","","","","" "biospecimenType","A label indicating the biological material collected for experimentation and data collection. Where applicable, provide all types in a comma-separated list.","PBMCs, cell line, fibroblast-like synoviocyte, kidney biopsy, none, plasma, primary cell culture, saliva, salivary gland, serum, skin biopsy, skin swab, stool, suction blister cells, suction blister fluid, synovial fluid, synovial tissue, total leukocytes, urine, uvea, whole blood","","TRUE","","","#BiospecimenMetadataTemplate str^^#InVitroBiospecimenMetadataTemplate^^list like error","string_list","","","","" "primaryCellSource","A label indicating the biological source material from which a primary cell culture was derived.","PBMCs, kidney, pannus-derived dermis, pannus-derived epidermis, salivary gland, synovial tissue, total leukocytes, urine, uvea, whole blood","","TRUE","","","","string","","","","" -"metadataType","A label further classifying the content of metadata resource.","assay, biospecimen, cell coordinates, data dictionary, file manifest, medication, other, phenotype, protocol, single-cell metadata, target panel, template, tissue microarray map, tissue multiarray map, user manual","","TRUE","","","","string","","","","" "codingLanguage","The coding, aka programming, language(s) contained in the file marked with `resourceType = code`. Select all that apply.","C, C#, C++, Fortan, Java, Julia, Matlab, Python, R, Ruby, SAS","","TRUE","","","","string","","","","" "visitID","Ordinal ID distinguishing different patient visits.","","","TRUE","","","","string","","","","" "softwareAndVersion","Relevant software and version used to generate the data file.","BD FACSDiva 8.0.1, Cell Ranger 9.0.1, Cell Ranger ATAC v1.1.0, Cell Ranger v3.0.0, Cell Ranger v3.0.1, Cell Ranger v3.0.2, Cell Ranger v3.1.0, Cell Ranger v4.0.0, Cell Ranger v5.0.0, Cell Ranger v5.0.1, Cell Ranger v6.0.0, Cell Ranger v6.0.1, Cell Ranger v6.0.2, Cell Ranger v6.1.0, Cell Ranger v6.1.1, Cell Ranger v6.1.2, Cell Ranger v7.0.0, Cell Ranger v7.0.1, Cell Ranger v7.1.0, Cell Ranger v7.2.0, Cell Ranger v8.0.0, Cell Ranger v8.0.1, Cell Ranger v9.0.0, Space Ranger 3.0.0, Space Ranger 3.0.1, Space Ranger 3.1.0, Space Ranger 3.1.1, Space Ranger 3.1.2, Space Ranger 3.1.3, demuxlet","","FALSE","","","","string","","","","" @@ -90,7 +92,6 @@ "datasetStatus","A categorical label indicating the status of an ARK Portal dataset. This is applied to improve downstream management of datasets as well as various ETL workflows.","deprecated, released, test, under peer review, unreleased","","TRUE","","","","string","","","","" "sampleProcessingBatch","A label indicating batching of sample processing or preparation that occurs prior to data collection.","","","FALSE","","","","string","","","","" "dataCollectionBatch","A label indicating batching that occurs during data collection, e.g., collecting data across multiple days.","","","FALSE","","","","string","","","","" -"metadataStandards","Metadata standards used to generate the metadata","ARK data model, user-defined","","FALSE","","","","string","","","","" "skinSunExposure","For skin-based biospecimen, this attribute indicates whether the sample was collected from an anatomical site that does or does not receive routine sun exposure.","not sun exposed, sun exposed","","FALSE","","","","string","","","","" "sequencingSpikeIn","Pre-made sequencing libraries may be added to your sequencing run to improve sequencing results. If such a 'spike-in' library was used, this attribute specifies the name of the library and the percentage of the spike-in library used in the sequencing run.","","","FALSE","","","","string","","","","" "librarySpikeIn","Pre-made collections of nucleic acid fragments can be added to samples during the library construction process to improve downstream quantification and statistical analyses. If such a 'spike-in' was used, this attribute specifies the name and manufacturer of the spike-in.","","","FALSE","","","","string","","","","" diff --git a/model_contexts/olink/ark.olink_model.csv b/model_contexts/olink/ark.olink_model.csv index e3e044b..e552ca7 100644 --- a/model_contexts/olink/ark.olink_model.csv +++ b/model_contexts/olink/ark.olink_model.csv @@ -23,7 +23,7 @@ "parentBiospecimenID","The biospecimenID associated with the originating biospecimen for derived or child biospecimens.","","","FALSE","","","","string","","","","" "biospecimenType","A label indicating the biological material collected for experimentation and data collection. Where applicable, provide all types in a comma-separated list.","PBMCs, cell line, fibroblast-like synoviocyte, kidney biopsy, none, plasma, primary cell culture, saliva, salivary gland, serum, skin biopsy, skin swab, stool, suction blister cells, suction blister fluid, synovial fluid, synovial tissue, total leukocytes, urine, uvea, whole blood","","TRUE","","","#BiospecimenMetadataTemplate str^^#InVitroBiospecimenMetadataTemplate^^list like error","string_list","","","","" "primaryCellSource","A label indicating the biological source material from which a primary cell culture was derived.","PBMCs, kidney, pannus-derived dermis, pannus-derived epidermis, salivary gland, synovial tissue, total leukocytes, urine, uvea, whole blood","","TRUE","","","","string","","","","" -"metadataType","A label further classifying the content of metadata resource.","assay, biospecimen, cell coordinates, data dictionary, file manifest, medication, other, phenotype, protocol, single-cell metadata, target panel, template, tissue microarray map, tissue multiarray map, user manual","","TRUE","","","","string","","","","" +"metadataType","A label further classifying the content of metadata resource.","assay, biospecimen, cell coordinates, clinical, data dictionary, demographics, file manifest, medication, other, phenotype, protocol, single-cell metadata, target panel, template, tissue microarray map, tissue multiarray map, user manual","","TRUE","","","","string","","","","" "codingLanguage","The coding, aka programming, language(s) contained in the file marked with `resourceType = code`. Select all that apply.","C, C#, C++, Fortan, Java, Julia, Matlab, Python, R, Ruby, SAS","","TRUE","","","","string","","","","" "visitID","Ordinal ID distinguishing different patient visits.","","","TRUE","","","","string","","","","" "softwareAndVersion","Relevant software and version used to generate the data file.","BD FACSDiva 8.0.1, Cell Ranger 9.0.1, Cell Ranger ATAC v1.1.0, Cell Ranger v3.0.0, Cell Ranger v3.0.1, Cell Ranger v3.0.2, Cell Ranger v3.1.0, Cell Ranger v4.0.0, Cell Ranger v5.0.0, Cell Ranger v5.0.1, Cell Ranger v6.0.0, Cell Ranger v6.0.1, Cell Ranger v6.0.2, Cell Ranger v6.1.0, Cell Ranger v6.1.1, Cell Ranger v6.1.2, Cell Ranger v7.0.0, Cell Ranger v7.0.1, Cell Ranger v7.1.0, Cell Ranger v7.2.0, Cell Ranger v8.0.0, Cell Ranger v8.0.1, Cell Ranger v9.0.0, Space Ranger 3.0.0, Space Ranger 3.0.1, Space Ranger 3.1.0, Space Ranger 3.1.1, Space Ranger 3.1.2, Space Ranger 3.1.3, demuxlet","","FALSE","","","","string","","","","" @@ -112,3 +112,4 @@ "ImmPortAccession","Accession to corresponding information in ImmPort.","","","FALSE","","","regex search ^SDY error","string","","","","^SDY" "cellOntologyID","Cell Ontology CL identifier that best describes a biopsecimen used to generate data, e.g., CL:0000084 for T cell.","","","FALSE","","","regex search ^CL: error","string","","","","^CL:" "PMCID","Pubmed Central Identifier, formatted as a compact URI string that will automatically resolve into a URL based on the Synapse bioregistry; e.g., pmc:PMCxxxxxxxx","","","FALSE","","","regex search ^pmc:PMC[0-9]{8} error","string","","","","^pmc:PMC[0-9]{8}" +"demultiplexMethod","This attribute indicates the general method that needs to be used to demultiplex multispecimen raw data.","genotypic demux, hashtag oligos, sample barcode, slide array map","","TRUE","","","","string","","","","" diff --git a/model_contexts/singlecell/ark.singlecell_model.csv b/model_contexts/singlecell/ark.singlecell_model.csv index b4acd1d..e654735 100644 --- a/model_contexts/singlecell/ark.singlecell_model.csv +++ b/model_contexts/singlecell/ark.singlecell_model.csv @@ -122,3 +122,4 @@ "ImmPortAccession","Accession to corresponding information in ImmPort.","","","FALSE","","","regex search ^SDY error","string","","","","^SDY" "cellOntologyID","Cell Ontology CL identifier that best describes a biopsecimen used to generate data, e.g., CL:0000084 for T cell.","","","FALSE","","","regex search ^CL: error","string","","","","^CL:" "PMCID","Pubmed Central Identifier, formatted as a compact URI string that will automatically resolve into a URL based on the Synapse bioregistry; e.g., pmc:PMCxxxxxxxx","","","FALSE","","","regex search ^pmc:PMC[0-9]{8} error","string","","","","^pmc:PMC[0-9]{8}" +"demultiplexMethod","This attribute indicates the general method that needs to be used to demultiplex multispecimen raw data.","genotypic demux, hashtag oligos, sample barcode, slide array map","","TRUE","","","","string","","","","" diff --git a/model_contexts/spatial/ark.spatial_context.csv b/model_contexts/spatial/ark.spatial_context.csv index 570f47b..70d7e37 100644 --- a/model_contexts/spatial/ark.spatial_context.csv +++ b/model_contexts/spatial/ark.spatial_context.csv @@ -1,14 +1,17 @@ -"Attribute","Description","Valid Values","DependsOn","Required","Parent","Source","Validation Rules","columnType","Format","Minimum","Maximum","Pattern" -"Spatial Imaging Assay Metadata Template","A template outlining metadata to be collected for each slide in a spatial transcriptomic or imaging based dataset.","","Component, assay, specimenModality, sampleProcessingBatch, dataCollectionBatch, targetPanel, targetPanelSynID, targetPanelSize","","","","","","","","","" -"Spatial Imaging File Annotation Template","A data contributor template outlining metadata to be collected as file annotations for imaging-based data files.","","Component, fileFormat, assay, resourceType, specimenModality","","","","","","","","","" -"BDM Spatial Imaging File Annotations","A template outlining as file annotations for imaging-based data files to be compiled by ARK BDM.","","Component, fileFormat, assay, resourceType, specimenModality, parentBiospecimenID, biospecimenType, biospecimenSubtype, dataType, dataSubtype, diagnosis, visitID, targetPanel, targetPanelSynID, targetPanelSize, program, project, species, primaryCellSource, cellType, userDefinedCellType","","","","","","","","","" -"single specimen","Is a valid value of `specimenModality` that triggers conditional dependencies for additional attributes.","","biospecimenID","","","","","","","","","" -"multispecimen","Is a valid value of `specimenModality` that triggers conditional dependencies for additional attributes.","","slideID","","","","","","","","","" -"resourceType","","experimental data, metadata","","TRUE","","","list like error","string_list","","","","" -"assay","","Xenium, CosMX, GenePS SeqFISH, imaging mass cytometry, Visium, H&E, serial IHC","","TRUE","","","","string","","","","" -"rds","Is a valid value of 'fileFormat' that triggers conditional dependencies for additional attributes.","","RObjectClass","FALSE","","","","","","","","" -"experimental data","Is a valid value of 'resourceType' that triggers conditional dependencies for additional attributes.","","processedDataType","FALSE","","","","","","","","" -"metadata","Is a valid value of Resource Type that triggers conditional dependencies for additional attributes. Any file that contains curated data describing an experiment and experimental-derived data, including metadata about study subjects, biospecimens, protocols, assay reagents, marker panels, and ID mappings","","metadataType","FALSE","","","","","","","","" -"metadataType","","single-cell metadata, cell coordinates, target panel, tissue microarray map, other","","TRUE","","","","string","","","","" -"AMP RA/SLE","Accelerating Medicines Partnership Rheumatoid Arthritis and Systemic Lupus Erythematosus. Is a valid value for 'program' that triggers conditional dependencies for additional attributes.","","visitID","FALSE","","","","","","","","" -"AMP AIM","Accelerating Medicines Partnership Autoimmune and Immune-Mediated Diseases. Is a valid value for 'program' that triggers conditional dependencies for additional attributes.","","visitID","FALSE","","","","","","","","" +Attribute,Description,Valid Values,DependsOn,Required,Parent,Source,Validation Rules,columnType,Format,Minimum,Maximum,Pattern +Dataset Annotation Template,A template outlining dataset metadata to use as annotations for a synapse dataset entity.,,"Component, program, project, datasetType, biospecimenType, biospecimenSubtype, diagnosis, acknowledgmentStatement, datasetDescription, ARKRelease, dataType, dataSubtype, assay, publicationSynID, associatedDataset, associatedCodeURL, associatedAccession, ImmPortAccession, datasetStatus, species",,,,,,,,, +Publication Metadata Template,A template outlining metadata to use as annotations for Publication ‘file’ entities.,,"Component, program, project, associatedDataset, PMID, PMCID, DOI, journal, year, title, publicationType, publicationDate",,,,,,,,, +scRNASeq Assay Metadata Template,A template outlining metadata to be collected for each library in a scRNA-seq dataset.,,"Component, assay, specimenModality, libraryPrepMethod, nucleicAcidSource, totalReads, percentCellViability, platform, sequencingSaturation, sampleProcessingBatch, dataCollectionBatch, inputCellCount, alignmentReference, softwareAndVersion",,,,,,,,, +Bulk RNA-seq Assay Metadata Template,A template outlining metadata to be collected for each library in a bulk RNA-seq dataset.,,"Component, assay, specimenModality, libraryPrepMethod, nucleicAcidSource, totalReads, platform, sampleProcessingBatch, dataCollectionBatch, alignmentReference, softwareAndVersion",,,,,,,,, +Metadata File Annotation Template,A template outlining metadata to be collected for annotating metadata files to be compiled by ARK BDM.,,"Component, program, project, fileFormat, dataType, resourceType",,,,,,,,, +snRNASeq Assay Metadata Template,A template outlining metadata to be collected for each library in a snRNA-seq dataset.,,"Component, assay, specimenModality, libraryPrepMethod, nucleicAcidSource, totalReads, percentCellViability, platform, sequencingSaturation, sampleProcessingBatch, dataCollectionBatch, inputCellCount, alignmentReference, softwareAndVersion",,,,,,,,, +Bulk ATAC-seq Assay Metadata Template,A template outlining metadata to be collected for each library in a bulk ATAC-seq dataset.,,"Component, assay, specimenModality, libraryPrepMethod, nucleicAcidSource, totalReads, platform, sampleProcessingBatch, dataCollectionBatch, alignmentReference, softwareAndVersion",,,,,,,,, +snATAC-seq Assay Metadata Template,A template outlining metadata to be collected for each library in a snATAC-seq dataset.,,"Component, assay, specimenModality, libraryPrepMethod, nucleicAcidSource, totalReads, percentCellViability, platform, sequencingSaturation, sampleProcessingBatch, dataCollectionBatch, inputCellCount, alignmentReference, softwareAndVersion",,,,,,,,, +CyTOF Assay Metadata Template,A template outlining assay-related metadata for a cytometry time-of-flight (CyTOF) dataset. Each row corresponds to a biospecimen profiled in the experiment.,,"Component, assay, biospecimenID, sampleProcessingBatch, dataCollectionBatch, platform, softwareAndVersion, targetPanel, targetPanelSynID, targetPanelSize",,,,,,,,, +metadata,"Any file that contains curated data describing an experiment and experimental-derived data, including metadata about study subjects, biospecimens, protocols, assay reagents, marker panels, and ID mappings. Is a valid value of Resource Type that triggers conditional dependencies for additional attributes.",,"metadataType, metadataStandards",,,,,,,,, +10x GEM-X Flex Gene Expression Human,A scRNA-seq method that analyzes gene expression using pre-designed probes. Is a valid value of `libraryPrepMethod` and when selected triggers conditional dependencies for additional metadata collection.,,10xProbeSetReference,,,,,,,,, +multispecimen,Is a valid value of `specimenModality` that triggers conditional dependencies for additional attributes.,,"libraryID, demultiplexMethod",,,,,,,,, +single specimen,Is a valid value of `specimenModality` that triggers conditional dependencies for additional attributes.,,biospecimenID,,,,,,,,, +metadataType,A label further classifying the content of metadata resource. If a metadata file contains multiple types please specify all that apply in a comma-delimited list,"demographics, clinical, assay, biospecimen, cell coordinates, data dictionary, file manifest, medication, other, phenotype, protocol, single-cell metadata, target panel, template, tissue microarray map, user manual",,TRUE,,,list like error,string_list,,,, +metadataStandards,Metadata standards used to generate the metadata.,"ARK data model, user-defined",,TRUE,,,,string,,,, +demultiplexMethod,This attribute indicates the general method that needs to be used to demultiplex multispecimen raw data.,"genotypic demux, hashtag oligos, sample barcode, slide array map",,TRUE,,,,string,,,, \ No newline at end of file diff --git a/model_contexts/spatial/ark.spatial_model.csv b/model_contexts/spatial/ark.spatial_model.csv index 0855a54..7ac2b29 100644 --- a/model_contexts/spatial/ark.spatial_model.csv +++ b/model_contexts/spatial/ark.spatial_model.csv @@ -1,25 +1,30 @@ "Attribute","Description","Valid Values","DependsOn","Required","Parent","Source","Validation Rules","columnType","Format","Minimum","Maximum","Pattern" -"Spatial Imaging Assay Metadata Template","A template outlining metadata to be collected for each slide in a spatial transcriptomic or imaging based dataset.","","Component, assay, specimenModality, sampleProcessingBatch, dataCollectionBatch, targetPanel, targetPanelSynID, targetPanelSize","","","","","","","","","" -"Spatial Imaging File Annotation Template","A data contributor template outlining metadata to be collected as file annotations for imaging-based data files.","","Component, fileFormat, assay, resourceType, specimenModality","","","","","","","","","" -"BDM Spatial Imaging File Annotations","A template outlining as file annotations for imaging-based data files to be compiled by ARK BDM.","","Component, fileFormat, assay, resourceType, specimenModality, parentBiospecimenID, biospecimenType, biospecimenSubtype, dataType, dataSubtype, diagnosis, visitID, targetPanel, targetPanelSynID, targetPanelSize, program, project, species, primaryCellSource, cellType, userDefinedCellType","","","","","","","","","" +"Dataset Annotation Template","A template outlining dataset metadata to use as annotations for a synapse dataset entity.","","Component, program, project, datasetType, biospecimenType, biospecimenSubtype, diagnosis, acknowledgmentStatement, datasetDescription, ARKRelease, dataType, dataSubtype, assay, publicationSynID, associatedDataset, associatedCodeURL, associatedAccession, ImmPortAccession, datasetStatus, species","","","","","","","","","" +"Publication Metadata Template","A template outlining metadata to use as annotations for Publication ‘file’ entities.","","Component, program, project, associatedDataset, PMID, PMCID, DOI, journal, year, title, publicationType, publicationDate","","","","","","","","","" +"scRNASeq Assay Metadata Template","A template outlining metadata to be collected for each library in a scRNA-seq dataset.","","Component, assay, specimenModality, libraryPrepMethod, nucleicAcidSource, totalReads, percentCellViability, platform, sequencingSaturation, sampleProcessingBatch, dataCollectionBatch, inputCellCount, alignmentReference, softwareAndVersion","","","","","","","","","" +"Bulk RNA-seq Assay Metadata Template","A template outlining metadata to be collected for each library in a bulk RNA-seq dataset.","","Component, assay, specimenModality, libraryPrepMethod, nucleicAcidSource, totalReads, platform, sampleProcessingBatch, dataCollectionBatch, alignmentReference, softwareAndVersion","","","","","","","","","" +"Metadata File Annotation Template","A template outlining metadata to be collected for annotating metadata files to be compiled by ARK BDM.","","Component, program, project, fileFormat, dataType, resourceType","","","","","","","","","" +"snRNASeq Assay Metadata Template","A template outlining metadata to be collected for each library in a snRNA-seq dataset.","","Component, assay, specimenModality, libraryPrepMethod, nucleicAcidSource, totalReads, percentCellViability, platform, sequencingSaturation, sampleProcessingBatch, dataCollectionBatch, inputCellCount, alignmentReference, softwareAndVersion","","","","","","","","","" +"Bulk ATAC-seq Assay Metadata Template","A template outlining metadata to be collected for each library in a bulk ATAC-seq dataset.","","Component, assay, specimenModality, libraryPrepMethod, nucleicAcidSource, totalReads, platform, sampleProcessingBatch, dataCollectionBatch, alignmentReference, softwareAndVersion","","","","","","","","","" +"snATAC-seq Assay Metadata Template","A template outlining metadata to be collected for each library in a snATAC-seq dataset.","","Component, assay, specimenModality, libraryPrepMethod, nucleicAcidSource, totalReads, percentCellViability, platform, sequencingSaturation, sampleProcessingBatch, dataCollectionBatch, inputCellCount, alignmentReference, softwareAndVersion","","","","","","","","","" +"CyTOF Assay Metadata Template","A template outlining assay-related metadata for a cytometry time-of-flight (CyTOF) dataset. Each row corresponds to a biospecimen profiled in the experiment.","","Component, assay, biospecimenID, sampleProcessingBatch, dataCollectionBatch, platform, softwareAndVersion, targetPanel, targetPanelSynID, targetPanelSize","","","","","","","","","" +"metadata","Any file that contains curated data describing an experiment and experimental-derived data, including metadata about study subjects, biospecimens, protocols, assay reagents, marker panels, and ID mappings. Is a valid value of Resource Type that triggers conditional dependencies for additional attributes.","","metadataType, metadataStandards","","","","","","","","","" +"10x GEM-X Flex Gene Expression Human","A scRNA-seq method that analyzes gene expression using pre-designed probes. Is a valid value of `libraryPrepMethod` and when selected triggers conditional dependencies for additional metadata collection.","","10xProbeSetReference","","","","","","","","","" +"multispecimen","Is a valid value of `specimenModality` that triggers conditional dependencies for additional attributes.","","libraryID, demultiplexMethod","","","","","","","","","" "single specimen","Is a valid value of `specimenModality` that triggers conditional dependencies for additional attributes.","","biospecimenID","","","","","","","","","" -"multispecimen","Is a valid value of `specimenModality` that triggers conditional dependencies for additional attributes.","","slideID","","","","","","","","","" -"resourceType","High-level classification of the file content","experimental data, metadata","","TRUE","","","list like error","string_list","","","","" -"assay","The technology used to generate the data in this file. For multimodal datasets with concomitant profiling of biospecimen select all assays that apply. e.g., the GEX files from a CITE-seq experiment should be labeled with both 'scRNASeq' and 'CITESeq'.","Xenium, CosMX, GenePS SeqFISH, imaging mass cytometry, Visium, H&E, serial IHC","","TRUE","","","","string","","","","" -"rds","Is a valid value of 'fileFormat' that triggers conditional dependencies for additional attributes.","","RObjectClass","FALSE","","","","","","","","" -"experimental data","Is a valid value of 'resourceType' that triggers conditional dependencies for additional attributes.","","processedDataType","FALSE","","","","","","","","" -"metadata","Is a valid value of Resource Type that triggers conditional dependencies for additional attributes. Any file that contains curated data describing an experiment and experimental-derived data, including metadata about study subjects, biospecimens, protocols, assay reagents, marker panels, and ID mappings","","metadataType","FALSE","","","","","","","","" -"metadataType","A label further classifying the content of metadata resource.","single-cell metadata, cell coordinates, target panel, tissue microarray map, other","","TRUE","","","","string","","","","" -"AMP RA/SLE","Accelerating Medicines Partnership Rheumatoid Arthritis and Systemic Lupus Erythematosus. Is a valid value for 'program' that triggers conditional dependencies for additional attributes.","","visitID","FALSE","","","","","","","","" -"AMP AIM","Accelerating Medicines Partnership Autoimmune and Immune-Mediated Diseases. Is a valid value for 'program' that triggers conditional dependencies for additional attributes.","","visitID","FALSE","","","","","","","","" +"metadataType","A label further classifying the content of metadata resource. If a metadata file contains multiple types please specify all that apply in a comma-delimited list","demographics, clinical, assay, biospecimen, cell coordinates, data dictionary, file manifest, medication, other, phenotype, protocol, single-cell metadata, target panel, template, tissue microarray map, user manual","","TRUE","","","list like error","string_list","","","","" +"metadataStandards","Metadata standards used to generate the metadata.","ARK data model, user-defined","","TRUE","","","","string","","","","" +"demultiplexMethod","This attribute indicates the general method that needs to be used to demultiplex multispecimen raw data.","genotypic demux, hashtag oligos, sample barcode, slide array map","","TRUE","","","","string","","","","" "Component","A high-level attribute for grouping attributes into templates.","","","TRUE","","","","string","","","","" "fileFormat","Standard file format name or file extension","bai, bam, bed, bim, csv, czi, docx, dose, erate, fam, fastq, fcs, geojson, h5, h5ad, html, info, mcd, mtx, parquet, pdf, py, rds, rec, svs, tbi, tgz, tsv, txt, vcf, xls, xlsx, zip","","TRUE","","","","string","","","","" "program","Name of the funding program that supported the generation of data and associated files","AMP AIM, AMP RA/SLE, Community Contribution","","TRUE","","","","string","","","","" "project","A sub-level attribute of `program` specifying a research initiative working to investigate particular hypotheses.","AIM for RA, EDP1, EDP2, ELLIPSS, LOCKIT, METRO, RA, SLE, STAMP, UMass V-CoRT","","TRUE","","","list like error","string_list","","","","" "programPhase","A label noting which AMP RA/SLE program phase generated the data.","I, II","","TRUE","","","list like error","string_list","","","","" +"resourceType","High-level classification of the file content","code, experimental data, figure, metadata","","TRUE","","","","string","","","","" "dataType","High-level classification of the type of data contained in the file, loosely related to the experimental method or biological entity that is being profiled. Select all that apply using a comma-delimited list, though in most cases only a single label is expected. For multimodal datasets with concomitant profiling of biospecimen include 'multimodal'.","cytometry, epigenomics, genomics, histology, immune repertoire profiling, immunostaining, lipidomics, metabolomics, microbiome, multimodal, proteomics, transcriptomics","","TRUE","","","list like error","string_list","","","","" "dataSubtype","General classification to differentiate between omics profiling modalities. If N/A please select 'none'. Multiple selections can be provided in a comma-delimited list, however this is largely only expected in the context of Datasets and files that contain integrated experimental data spanning multiple types.","bulk, none, pseudobulk, single-cell, single-nucleus, spatial","","TRUE","","","list like error","string_list","","","","" "dataLevel","Level of data processing applied to file. Levels refer to pre-defined standards of processing for the given assay.","1, 2, 3, 4, 5","","TRUE","","","","string","","","","" +"assay","The technology used to generate the data in this file. For multimodal datasets with concomitant profiling of biospecimen select all assays that apply. e.g., the GEX files from a CITE-seq experiment should be labeled with both 'scRNASeq' and 'CITESeq'.","ASAPSeq, CE-MS, CITESeq, CosMX, CyTOF, GenePS SeqFISH, H&E, LC-MS/MS, NULISA, Olink Explore HT, Olink Flex, Olink Focus, Olink Reveal, Olink Target 48, Olink Target 96, RNASeq, SNP array, SomaScan, VDJSeq, Visium, WES, WGS, Xenium, feature barcode sequencing, flow cytometry, imaging mass cytometry, imaging mass spectrometry, kiloplex, multiplexed ELISA, scRNASeq, scVDJSeq, serial IHC, snATACSeq, snRNASeq","","TRUE","","","list like error","string_list","","","","" "10xProbeSetReference","Name of probe set used in 10x Chromium Flex, Xenium, or Visium data. If custom modified probe set was used the probe reference should be included as metadata accompanying the experimental data files.","Flex Human Transcriptome Probe Set v1.0.1, Flex Human Transcriptome Probe Set v1.1.0, Visium Human Transcriptome v1, Visium Human Transcriptome v2, custom probe set","","TRUE","","","","string","","","","" "platform","The specific version (manufacturer, model, etc.) of a technology that is used to carry out a laboratory or computational experiment. Specify where applicable for experimental data files, else enter 'none'. In most cases only a single label is expected, however multiple selections can be provided in comma-delimited list where applicable e.g., for 10x Genomics fastq files please specify both the 10x instrument and the sequencing platform.","BD FACSAria Fusion cell sorter, BD FACSAria III, BD FACSCanto, BD FACSCanto II, BD FACSDiscover A8, BD FACSDiscover S8, BD FACSLyric Clinical, BD FACSMelody, BD FACSymphony S6, BD LSRFortessa, Chromium Controller, Chromium GEM-X Single Cell 3' Chip v4, Chromium Next GEM Chip G, Chromium Next GEM Chip H, Chromium Next GEM Chip K, Chromium Next GEM Chip M, Chromium Next GEM Chip Q, Chromium X, Chromium Xo, Chromium iX, CyTOF XT, Cytek Aurora, Cytek Aurora Evo, Fluidigm BioMark, GEM-X Flex Gene Expression Chip, GEM-X OCM 5' Chip, Helios Mass Cytometer, Hyperion, Illumina HiSeq 2500, Illumina HiSeq X Ten, Illumina NextSeq 500, Illumina NovaSeq 6000, Illumina NovaSeq X, Not Applicable, Olink Signature Q100, Sony MA900, Thermo Fisher Attune CytPix, Thermo Fisher Attune NxT, Thermo Fisher Attune Xenith, Visium CytAssist, Xenium, none, unknown","","TRUE","","","list like error","string_list","","","","" "specimenModality","Label assigned to experimental data files indicating whether the data contained corresponds to a single or multiple biospecimens","multispecimen, single specimen, unknown","","TRUE","","","","string","","","","" @@ -87,11 +92,11 @@ "datasetStatus","A categorical label indicating the status of an ARK Portal dataset. This is applied to improve downstream management of datasets as well as various ETL workflows.","deprecated, released, test, under peer review, unreleased","","TRUE","","","","string","","","","" "sampleProcessingBatch","A label indicating batching of sample processing or preparation that occurs prior to data collection.","","","FALSE","","","","string","","","","" "dataCollectionBatch","A label indicating batching that occurs during data collection, e.g., collecting data across multiple days.","","","FALSE","","","","string","","","","" -"metadataStandards","Metadata standards used to generate the metadata","ARK data model, user-defined","","FALSE","","","","string","","","","" "skinSunExposure","For skin-based biospecimen, this attribute indicates whether the sample was collected from an anatomical site that does or does not receive routine sun exposure.","not sun exposed, sun exposed","","FALSE","","","","string","","","","" "sequencingSpikeIn","Pre-made sequencing libraries may be added to your sequencing run to improve sequencing results. If such a 'spike-in' library was used, this attribute specifies the name of the library and the percentage of the spike-in library used in the sequencing run.","","","FALSE","","","","string","","","","" "librarySpikeIn","Pre-made collections of nucleic acid fragments can be added to samples during the library construction process to improve downstream quantification and statistical analyses. If such a 'spike-in' was used, this attribute specifies the name and manufacturer of the spike-in.","","","FALSE","","","","string","","","","" "readLength","The number of base pairs (bp) sequenced for reads in a fastq file.","","","FALSE","","","int error","integer","","","","" +"AMP RA/SLE","Accelerating Medicines Partnership Rheumatoid Arthritis and Systemic Lupus Erythematosus. Is a valid value for 'program' that triggers conditional dependencies for additional attributes.","","programPhase","FALSE","","","","","","","","" "plateID","An identifier assigned to a multi-well plate. Certain data types and assays profile samples using multi-well plates. Knowing which samples were profiled on each plate is important for establishing sample provenance, finding the right data files for a specific set of samples, as well as downstream exploratory data analysis and QC work particularly regarding identification and correction of batch effects.","","","FALSE","","","","string","","","","" "processedDataType","A label used for file annotations to provide a brief description of the processed data file.","barcode counts, differential expression results, epigenomic peaks, gene counts","","FALSE","","","list like error","string_list","","","","" "eventCount","The total number of events detected and captured in the corresponding FCS file. In cytometry, an event corresponds to particles detected and measured by the instrument. This number corresponds to the number of rows in the FCS file and is expected to be a whole integer number.","","","FALSE","","","int error","integer","","","","" diff --git a/model_contexts/spatial/ark.spatial_templates.txt b/model_contexts/spatial/ark.spatial_templates.txt index e8deaef..30b4fa6 100644 --- a/model_contexts/spatial/ark.spatial_templates.txt +++ b/model_contexts/spatial/ark.spatial_templates.txt @@ -1,3 +1,9 @@ -BDMSpatialImagingFileAnnotations spatial -SpatialImagingAssayMetadataTemplate spatial -SpatialImagingFileAnnotationTemplate spatial +BulkATAC-seqAssayMetadataTemplate spatial +BulkRNA-seqAssayMetadataTemplate spatial +CyTOFAssayMetadataTemplate spatial +DatasetAnnotationTemplate spatial +MetadataFileAnnotationTemplate spatial +PublicationMetadataTemplate spatial +ScRNASeqAssayMetadataTemplate spatial +SnATAC-seqAssayMetadataTemplate spatial +SnRNASeqAssayMetadataTemplate spatial diff --git a/model_json_schema/ark.BulkATAC-seqAssayMetadataTemplate.schema.json b/model_json_schema/ark.BulkATAC-seqAssayMetadataTemplate.schema.json index 7ff2d3f..d44d2ff 100644 --- a/model_json_schema/ark.BulkATAC-seqAssayMetadataTemplate.schema.json +++ b/model_json_schema/ark.BulkATAC-seqAssayMetadataTemplate.schema.json @@ -43,6 +43,11 @@ }, "then": { "properties": { + "demultiplexMethod": { + "not": { + "type": "null" + } + }, "libraryID": { "not": { "type": "null" @@ -50,6 +55,7 @@ } }, "required": [ + "demultiplexMethod", "libraryID" ] } @@ -168,6 +174,16 @@ "title": "dataCollectionBatch", "type": "string" }, + "demultiplexMethod": { + "description": "This attribute indicates the general method that needs to be used to demultiplex multispecimen raw data.", + "enum": [ + "genotypic demux", + "hashtag oligos", + "sample barcode", + "slide array map" + ], + "title": "demultiplexMethod" + }, "libraryID": { "description": "A library label or name, unique within an experiment, used to distinguish sequencing libraries.", "title": "libraryID", diff --git a/model_json_schema/ark.BulkRNA-seqAssayMetadataTemplate.schema.json b/model_json_schema/ark.BulkRNA-seqAssayMetadataTemplate.schema.json index c1aec30..35b136b 100644 --- a/model_json_schema/ark.BulkRNA-seqAssayMetadataTemplate.schema.json +++ b/model_json_schema/ark.BulkRNA-seqAssayMetadataTemplate.schema.json @@ -43,6 +43,11 @@ }, "then": { "properties": { + "demultiplexMethod": { + "not": { + "type": "null" + } + }, "libraryID": { "not": { "type": "null" @@ -50,6 +55,7 @@ } }, "required": [ + "demultiplexMethod", "libraryID" ] } @@ -168,6 +174,16 @@ "title": "dataCollectionBatch", "type": "string" }, + "demultiplexMethod": { + "description": "This attribute indicates the general method that needs to be used to demultiplex multispecimen raw data.", + "enum": [ + "genotypic demux", + "hashtag oligos", + "sample barcode", + "slide array map" + ], + "title": "demultiplexMethod" + }, "libraryID": { "description": "A library label or name, unique within an experiment, used to distinguish sequencing libraries.", "title": "libraryID", diff --git a/model_json_schema/ark.MetadataFileAnnotationTemplate.schema.json b/model_json_schema/ark.MetadataFileAnnotationTemplate.schema.json index 5231aea..9d15c25 100644 --- a/model_json_schema/ark.MetadataFileAnnotationTemplate.schema.json +++ b/model_json_schema/ark.MetadataFileAnnotationTemplate.schema.json @@ -174,7 +174,7 @@ "title": "fileFormat" }, "metadataStandards": { - "description": "Metadata standards used to generate the metadata", + "description": "Metadata standards used to generate the metadata.", "enum": [ "ARK data model", "user-defined" @@ -182,25 +182,30 @@ "title": "metadataStandards" }, "metadataType": { - "description": "A label further classifying the content of metadata resource.", - "enum": [ - "assay", - "biospecimen", - "cell coordinates", - "data dictionary", - "file manifest", - "medication", - "other", - "phenotype", - "protocol", - "single-cell metadata", - "target panel", - "template", - "tissue microarray map", - "tissue multiarray map", - "user manual" - ], - "title": "metadataType" + "description": "A label further classifying the content of metadata resource. If a metadata file contains multiple types please specify all that apply in a comma-delimited list", + "items": { + "enum": [ + "assay", + "biospecimen", + "cell coordinates", + "clinical", + "data dictionary", + "demographics", + "file manifest", + "medication", + "other", + "phenotype", + "protocol", + "single-cell metadata", + "target panel", + "template", + "tissue microarray map", + "user manual" + ], + "type": "string" + }, + "title": "metadataType", + "type": "array" }, "program": { "description": "Name of the funding program that supported the generation of data and associated files", diff --git a/model_json_schema/ark.ScRNASeqAssayMetadataTemplate.schema.json b/model_json_schema/ark.ScRNASeqAssayMetadataTemplate.schema.json index 4d06a5e..aa6291c 100644 --- a/model_json_schema/ark.ScRNASeqAssayMetadataTemplate.schema.json +++ b/model_json_schema/ark.ScRNASeqAssayMetadataTemplate.schema.json @@ -43,6 +43,11 @@ }, "then": { "properties": { + "demultiplexMethod": { + "not": { + "type": "null" + } + }, "libraryID": { "not": { "type": "null" @@ -50,6 +55,7 @@ } }, "required": [ + "demultiplexMethod", "libraryID" ] } @@ -168,6 +174,16 @@ "title": "dataCollectionBatch", "type": "string" }, + "demultiplexMethod": { + "description": "This attribute indicates the general method that needs to be used to demultiplex multispecimen raw data.", + "enum": [ + "genotypic demux", + "hashtag oligos", + "sample barcode", + "slide array map" + ], + "title": "demultiplexMethod" + }, "inputCellCount": { "description": "An estimate of the number of cells expected to be sequenced in a library. Software that process single-cell sequencing data often include options for users to specify this value to improve processing results.", "title": "inputCellCount", diff --git a/model_json_schema/ark.SnATAC-seqAssayMetadataTemplate.schema.json b/model_json_schema/ark.SnATAC-seqAssayMetadataTemplate.schema.json index 367da45..ffea929 100644 --- a/model_json_schema/ark.SnATAC-seqAssayMetadataTemplate.schema.json +++ b/model_json_schema/ark.SnATAC-seqAssayMetadataTemplate.schema.json @@ -43,6 +43,11 @@ }, "then": { "properties": { + "demultiplexMethod": { + "not": { + "type": "null" + } + }, "libraryID": { "not": { "type": "null" @@ -50,6 +55,7 @@ } }, "required": [ + "demultiplexMethod", "libraryID" ] } @@ -168,6 +174,16 @@ "title": "dataCollectionBatch", "type": "string" }, + "demultiplexMethod": { + "description": "This attribute indicates the general method that needs to be used to demultiplex multispecimen raw data.", + "enum": [ + "genotypic demux", + "hashtag oligos", + "sample barcode", + "slide array map" + ], + "title": "demultiplexMethod" + }, "inputCellCount": { "description": "An estimate of the number of cells expected to be sequenced in a library. Software that process single-cell sequencing data often include options for users to specify this value to improve processing results.", "title": "inputCellCount", diff --git a/model_json_schema/ark.SnRNASeqAssayMetadataTemplate.schema.json b/model_json_schema/ark.SnRNASeqAssayMetadataTemplate.schema.json index cb850a3..c9a7805 100644 --- a/model_json_schema/ark.SnRNASeqAssayMetadataTemplate.schema.json +++ b/model_json_schema/ark.SnRNASeqAssayMetadataTemplate.schema.json @@ -43,6 +43,11 @@ }, "then": { "properties": { + "demultiplexMethod": { + "not": { + "type": "null" + } + }, "libraryID": { "not": { "type": "null" @@ -50,6 +55,7 @@ } }, "required": [ + "demultiplexMethod", "libraryID" ] } @@ -168,6 +174,16 @@ "title": "dataCollectionBatch", "type": "string" }, + "demultiplexMethod": { + "description": "This attribute indicates the general method that needs to be used to demultiplex multispecimen raw data.", + "enum": [ + "genotypic demux", + "hashtag oligos", + "sample barcode", + "slide array map" + ], + "title": "demultiplexMethod" + }, "inputCellCount": { "description": "An estimate of the number of cells expected to be sequenced in a library. Software that process single-cell sequencing data often include options for users to specify this value to improve processing results.", "title": "inputCellCount", diff --git a/model_json_schema/ark.SpatialImagingAssayMetadataTemplate.schema.json b/model_json_schema/ark.SpatialImagingAssayMetadataTemplate.schema.json deleted file mode 100644 index e2c5464..0000000 --- a/model_json_schema/ark.SpatialImagingAssayMetadataTemplate.schema.json +++ /dev/null @@ -1,136 +0,0 @@ -{ - "$id": "http://example.com/SpatialImagingAssayMetadataTemplate", - "$schema": "http://json-schema.org/draft-07/schema#", - "allOf": [ - { - "if": { - "properties": { - "specimenModality": { - "enum": [ - "multispecimen" - ] - } - }, - "required": [ - "specimenModality" - ] - }, - "then": { - "properties": { - "slideID": { - "not": { - "type": "null" - } - } - }, - "required": [ - "slideID" - ] - } - }, - { - "if": { - "properties": { - "specimenModality": { - "enum": [ - "single specimen" - ] - } - }, - "required": [ - "specimenModality" - ] - }, - "then": { - "properties": { - "biospecimenID": { - "not": { - "type": "null" - } - } - }, - "required": [ - "biospecimenID" - ] - } - } - ], - "description": "A template outlining metadata to be collected for each slide in a spatial transcriptomic or imaging based dataset.", - "properties": { - "Component": { - "description": "A high-level attribute for grouping attributes into templates.", - "title": "Component", - "type": "string" - }, - "assay": { - "description": "The technology used to generate the data in this file. For multimodal datasets with concomitant profiling of biospecimen select all assays that apply. e.g., the GEX files from a CITE-seq experiment should be labeled with both 'scRNASeq' and 'CITESeq'.", - "enum": [ - "CosMX", - "GenePS SeqFISH", - "H&E", - "Visium", - "Xenium", - "imaging mass cytometry", - "serial IHC" - ], - "title": "assay" - }, - "biospecimenID": { - "description": "A unique identifier assigned to specimens collected from study participants. For multi-specimen data files provide all IDs in a comma-separated list.", - "items": { - "type": "string" - }, - "title": "biospecimenID", - "type": "array" - }, - "dataCollectionBatch": { - "description": "A label indicating batching that occurs during data collection, e.g., collecting data across multiple days.", - "title": "dataCollectionBatch", - "type": "string" - }, - "sampleProcessingBatch": { - "description": "A label indicating batching of sample processing or preparation that occurs prior to data collection.", - "title": "sampleProcessingBatch", - "type": "string" - }, - "slideID": { - "description": "A distinct label or name, unique within an experiment, assigned to an imaging slides.", - "title": "slideID", - "type": "string" - }, - "specimenModality": { - "description": "Label assigned to experimental data files indicating whether the data contained corresponds to a single or multiple biospecimens", - "enum": [ - "multispecimen", - "single specimen", - "unknown" - ], - "title": "specimenModality" - }, - "targetPanel": { - "description": "A unique or established human-readable name assigned to the panel of targets profiled in the experiment. For example, the panel of antibodies and corresponding fluorophores used in a flow cytometry experiment or panel used in a Xenium spatial transcriptomics experiment.", - "title": "targetPanel", - "type": "string" - }, - "targetPanelSize": { - "description": "The number of gene, transcript, protein, etc., targets profiled in the assay for assays that use a pre-defined set of probes, antibodies, etc., to measure biological components in samples. The input value is expected to be a whole integer that matches the number of targets described in the accompanying target panel metadata (i.e., targetPanelSynID).", - "title": "targetPanelSize", - "type": "integer" - }, - "targetPanelSynID": { - "description": "In most cases an accompanying metadata file should be provided that details information about the targets profiled in the experiment. This attribute links experimental data files to the target panel metadata via the synapse ID of that file.", - "pattern": "^syn[0-9]{8}", - "title": "targetPanelSynID", - "type": "string" - } - }, - "required": [ - "assay", - "Component", - "specimenModality", - "targetPanel", - "targetPanelSynID" - ], - "title": "SpatialImagingAssayMetadataTemplate", - "type": "object" -} \ No newline at end of file diff --git a/model_json_schema/ark.SpatialImagingFileAnnotationTemplate.schema.json b/model_json_schema/ark.SpatialImagingFileAnnotationTemplate.schema.json deleted file mode 100644 index 39fc7d3..0000000 --- a/model_json_schema/ark.SpatialImagingFileAnnotationTemplate.schema.json +++ /dev/null @@ -1,279 +0,0 @@ -{ - "$id": "http://example.com/SpatialImagingFileAnnotationTemplate", - "$schema": "http://json-schema.org/draft-07/schema#", - "allOf": [ - { - "if": { - "properties": { - "fileFormat": { - "enum": [ - "rds" - ] - } - }, - "required": [ - "fileFormat" - ] - }, - "then": { - "properties": { - "RObjectClass": { - "not": { - "type": "null" - } - } - }, - "required": [ - "RObjectClass" - ] - } - }, - { - "if": { - "properties": { - "resourceType": { - "enum": [ - "experimental data" - ] - } - }, - "required": [ - "resourceType" - ] - }, - "then": { - "properties": { - "processedDataType": { - "not": { - "type": "null" - } - } - }, - "required": [ - "processedDataType" - ] - } - }, - { - "if": { - "properties": { - "resourceType": { - "enum": [ - "metadata" - ] - } - }, - "required": [ - "resourceType" - ] - }, - "then": { - "properties": { - "metadataType": { - "not": { - "type": "null" - } - } - }, - "required": [ - "metadataType" - ] - } - }, - { - "if": { - "properties": { - "specimenModality": { - "enum": [ - "multispecimen" - ] - } - }, - "required": [ - "specimenModality" - ] - }, - "then": { - "properties": { - "slideID": { - "not": { - "type": "null" - } - } - }, - "required": [ - "slideID" - ] - } - }, - { - "if": { - "properties": { - "specimenModality": { - "enum": [ - "single specimen" - ] - } - }, - "required": [ - "specimenModality" - ] - }, - "then": { - "properties": { - "biospecimenID": { - "not": { - "type": "null" - } - } - }, - "required": [ - "biospecimenID" - ] - } - } - ], - "description": "A data contributor template outlining metadata to be collected as file annotations for imaging-based data files.", - "properties": { - "Component": { - "description": "A high-level attribute for grouping attributes into templates.", - "title": "Component", - "type": "string" - }, - "RObjectClass": { - "description": "Rds files store R objects, one per file. This label details the class of the R object saved to the Rds file or other similar file types.", - "enum": [ - "ROCR prediction.object", - "Seurat object", - "SummarizedExperiment", - "Symphony reference", - "data.frame", - "list", - "matrix", - "sparse matrix", - "vector" - ], - "title": "RObjectClass" - }, - "assay": { - "description": "The technology used to generate the data in this file. For multimodal datasets with concomitant profiling of biospecimen select all assays that apply. e.g., the GEX files from a CITE-seq experiment should be labeled with both 'scRNASeq' and 'CITESeq'.", - "enum": [ - "CosMX", - "GenePS SeqFISH", - "H&E", - "Visium", - "Xenium", - "imaging mass cytometry", - "serial IHC" - ], - "title": "assay" - }, - "biospecimenID": { - "description": "A unique identifier assigned to specimens collected from study participants. For multi-specimen data files provide all IDs in a comma-separated list.", - "items": { - "type": "string" - }, - "title": "biospecimenID", - "type": "array" - }, - "fileFormat": { - "description": "Standard file format name or file extension", - "enum": [ - "bai", - "bam", - "bed", - "bim", - "csv", - "czi", - "docx", - "dose", - "erate", - "fam", - "fastq", - "fcs", - "geojson", - "h5", - "h5ad", - "html", - "info", - "mcd", - "mtx", - "parquet", - "pdf", - "py", - "rds", - "rec", - "svs", - "tbi", - "tgz", - "tsv", - "txt", - "vcf", - "xls", - "xlsx", - "zip" - ], - "title": "fileFormat" - }, - "metadataType": { - "description": "A label further classifying the content of metadata resource.", - "enum": [ - "cell coordinates", - "other", - "single-cell metadata", - "target panel", - "tissue microarray map" - ], - "title": "metadataType" - }, - "processedDataType": { - "description": "A label used for file annotations to provide a brief description of the processed data file.", - "items": { - "enum": [ - "barcode counts", - "differential expression results", - "epigenomic peaks", - "gene counts" - ], - "type": "string" - }, - "title": "processedDataType", - "type": "array" - }, - "resourceType": { - "description": "High-level classification of the file content", - "items": { - "enum": [ - "experimental data", - "metadata" - ], - "type": "string" - }, - "title": "resourceType", - "type": "array" - }, - "slideID": { - "description": "A distinct label or name, unique within an experiment, assigned to an imaging slides.", - "title": "slideID", - "type": "string" - }, - "specimenModality": { - "description": "Label assigned to experimental data files indicating whether the data contained corresponds to a single or multiple biospecimens", - "enum": [ - "multispecimen", - "single specimen", - "unknown" - ], - "title": "specimenModality" - } - }, - "required": [ - "assay", - "Component", - "fileFormat", - "resourceType", - "specimenModality" - ], - "title": "SpatialImagingFileAnnotationTemplate", - "type": "object" -} \ No newline at end of file diff --git a/model_templates/ark.BDMSpatialImagingFileAnnotations.csv b/model_templates/ark.BDMSpatialImagingFileAnnotations.csv deleted file mode 100644 index 1dd5cce..0000000 --- a/model_templates/ark.BDMSpatialImagingFileAnnotations.csv +++ /dev/null @@ -1 +0,0 @@ -Component,RObjectClass,assay,biospecimenID,biospecimenSubtype,biospecimenType,cellType,dataSubtype,dataType,diagnosis,fileFormat,metadataType,parentBiospecimenID,primaryCellSource,processedDataType,program,project,resourceType,slideID,species,specimenModality,targetPanel,targetPanelSize,targetPanelSynID,userDefinedCellType,visitID diff --git a/model_templates/ark.BulkATAC-seqAssayMetadataTemplate.csv b/model_templates/ark.BulkATAC-seqAssayMetadataTemplate.csv index ed27887..b678198 100644 --- a/model_templates/ark.BulkATAC-seqAssayMetadataTemplate.csv +++ b/model_templates/ark.BulkATAC-seqAssayMetadataTemplate.csv @@ -1 +1 @@ -10xProbeSetReference,Component,alignmentReference,assay,biospecimenID,dataCollectionBatch,libraryID,libraryPrepMethod,nucleicAcidSource,platform,sampleProcessingBatch,softwareAndVersion,specimenModality,totalReads +10xProbeSetReference,Component,alignmentReference,assay,biospecimenID,dataCollectionBatch,demultiplexMethod,libraryID,libraryPrepMethod,nucleicAcidSource,platform,sampleProcessingBatch,softwareAndVersion,specimenModality,totalReads diff --git a/model_templates/ark.BulkRNA-seqAssayMetadataTemplate.csv b/model_templates/ark.BulkRNA-seqAssayMetadataTemplate.csv index ed27887..b678198 100644 --- a/model_templates/ark.BulkRNA-seqAssayMetadataTemplate.csv +++ b/model_templates/ark.BulkRNA-seqAssayMetadataTemplate.csv @@ -1 +1 @@ -10xProbeSetReference,Component,alignmentReference,assay,biospecimenID,dataCollectionBatch,libraryID,libraryPrepMethod,nucleicAcidSource,platform,sampleProcessingBatch,softwareAndVersion,specimenModality,totalReads +10xProbeSetReference,Component,alignmentReference,assay,biospecimenID,dataCollectionBatch,demultiplexMethod,libraryID,libraryPrepMethod,nucleicAcidSource,platform,sampleProcessingBatch,softwareAndVersion,specimenModality,totalReads diff --git a/model_templates/ark.ScRNASeqAssayMetadataTemplate.csv b/model_templates/ark.ScRNASeqAssayMetadataTemplate.csv index 64ab910..e1095f4 100644 --- a/model_templates/ark.ScRNASeqAssayMetadataTemplate.csv +++ b/model_templates/ark.ScRNASeqAssayMetadataTemplate.csv @@ -1 +1 @@ -10xProbeSetReference,Component,alignmentReference,assay,biospecimenID,dataCollectionBatch,inputCellCount,libraryID,libraryPrepMethod,nucleicAcidSource,percentCellViability,platform,sampleProcessingBatch,sequencingSaturation,softwareAndVersion,specimenModality,totalReads +10xProbeSetReference,Component,alignmentReference,assay,biospecimenID,dataCollectionBatch,demultiplexMethod,inputCellCount,libraryID,libraryPrepMethod,nucleicAcidSource,percentCellViability,platform,sampleProcessingBatch,sequencingSaturation,softwareAndVersion,specimenModality,totalReads diff --git a/model_templates/ark.SnATAC-seqAssayMetadataTemplate.csv b/model_templates/ark.SnATAC-seqAssayMetadataTemplate.csv index 64ab910..e1095f4 100644 --- a/model_templates/ark.SnATAC-seqAssayMetadataTemplate.csv +++ b/model_templates/ark.SnATAC-seqAssayMetadataTemplate.csv @@ -1 +1 @@ -10xProbeSetReference,Component,alignmentReference,assay,biospecimenID,dataCollectionBatch,inputCellCount,libraryID,libraryPrepMethod,nucleicAcidSource,percentCellViability,platform,sampleProcessingBatch,sequencingSaturation,softwareAndVersion,specimenModality,totalReads +10xProbeSetReference,Component,alignmentReference,assay,biospecimenID,dataCollectionBatch,demultiplexMethod,inputCellCount,libraryID,libraryPrepMethod,nucleicAcidSource,percentCellViability,platform,sampleProcessingBatch,sequencingSaturation,softwareAndVersion,specimenModality,totalReads diff --git a/model_templates/ark.SnRNASeqAssayMetadataTemplate.csv b/model_templates/ark.SnRNASeqAssayMetadataTemplate.csv index 64ab910..e1095f4 100644 --- a/model_templates/ark.SnRNASeqAssayMetadataTemplate.csv +++ b/model_templates/ark.SnRNASeqAssayMetadataTemplate.csv @@ -1 +1 @@ -10xProbeSetReference,Component,alignmentReference,assay,biospecimenID,dataCollectionBatch,inputCellCount,libraryID,libraryPrepMethod,nucleicAcidSource,percentCellViability,platform,sampleProcessingBatch,sequencingSaturation,softwareAndVersion,specimenModality,totalReads +10xProbeSetReference,Component,alignmentReference,assay,biospecimenID,dataCollectionBatch,demultiplexMethod,inputCellCount,libraryID,libraryPrepMethod,nucleicAcidSource,percentCellViability,platform,sampleProcessingBatch,sequencingSaturation,softwareAndVersion,specimenModality,totalReads diff --git a/model_templates/ark.SpatialImagingAssayMetadataTemplate.csv b/model_templates/ark.SpatialImagingAssayMetadataTemplate.csv deleted file mode 100644 index 5993b79..0000000 --- a/model_templates/ark.SpatialImagingAssayMetadataTemplate.csv +++ /dev/null @@ -1 +0,0 @@ -Component,assay,biospecimenID,dataCollectionBatch,sampleProcessingBatch,slideID,specimenModality,targetPanel,targetPanelSize,targetPanelSynID diff --git a/model_templates/ark.SpatialImagingFileAnnotationTemplate.csv b/model_templates/ark.SpatialImagingFileAnnotationTemplate.csv deleted file mode 100644 index e33eec5..0000000 --- a/model_templates/ark.SpatialImagingFileAnnotationTemplate.csv +++ /dev/null @@ -1 +0,0 @@ -Component,RObjectClass,assay,biospecimenID,fileFormat,metadataType,processedDataType,resourceType,slideID,specimenModality diff --git a/templates_by_context.txt b/templates_by_context.txt index 12ee895..197d22e 100644 --- a/templates_by_context.txt +++ b/templates_by_context.txt @@ -20,9 +20,15 @@ ScRNASeqProcessedDataAnnotationTemplate singlecell ScVDJSeqProcessedDataAnnotationTemplate singlecell SnATACSeqProcessedDataAnnotationTemplate singlecell SnRNASeqProcessedDataAnnotationTemplate singlecell -BDMSpatialImagingFileAnnotations spatial -SpatialImagingAssayMetadataTemplate spatial -SpatialImagingFileAnnotationTemplate spatial +BulkATAC-seqAssayMetadataTemplate spatial +BulkRNA-seqAssayMetadataTemplate spatial +CyTOFAssayMetadataTemplate spatial +DatasetAnnotationTemplate spatial +MetadataFileAnnotationTemplate spatial +PublicationMetadataTemplate spatial +ScRNASeqAssayMetadataTemplate spatial +SnATAC-seqAssayMetadataTemplate spatial +SnRNASeqAssayMetadataTemplate spatial BDMFastqFileAnnotations fastq FastqFileAnnotationTemplate fastq BDMOlinkFileAnnotations olink