diff --git a/ark.all_attributes.csv b/ark.all_attributes.csv index 07bd61f..6c9c246 100644 --- a/ark.all_attributes.csv +++ b/ark.all_attributes.csv @@ -1,10 +1,10 @@ "Attribute","Description","Valid Values","DependsOn","Properties","Required","Parent","DependsOn Component","Source","Validation Rules","columnType" "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, info, mcd, mtx, parquet, pdf, rds, rec, svs, tbi, tgz, tsv, txt, vcf, xls, xlsx, zip","","","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, info, mcd, mtx, parquet, pdf, py, rds, rec, svs, tbi, tgz, tsv, txt, vcf, xls, xlsx, zip","","","True","","","","","string" "publicationSynID","The synID of the corresponding Synapse entity that stores metadata about the publication. This is used to differentiate publication-specific files, often consisting of level 4 processed data and expanded subject metadata, in a publication dataset that also includes raw or minimally processed files from experimental datasets. This provides an easy way to distinguish and select for the publication-specific data from which the research findings were derived. When this attribute is used to annotate a Dataset it serves as a way to directly link the Dataset entity with the publication metadata stored in Synapse.","","","","False","","","","regex search ^syn[0-9]{8} error","string" "associatedDataset","The synID of a Dataset entity. This serves to link other Synapse entities to Dataset entities. When used to annotate a publication Dataset this attribute should include the synID for an experimental Datasets from which the publication data was derived. Multiple synID can be specified using a comma-delimited list.","","","","False","","","","list like::regex search ^syn[0-9]{8} error","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, ELLIPSS, LOCKIT, RA, SLE, STAMP, V-CoRT","","","True","","","","list like error","string" +"project","A sub-level attribute of `program` specifying a research initiative working to investigate particular hypotheses.","AIM for RA, ELLIPSS, LOCKIT, RA, SLE, STAMP, UMass V-CoRT","","","True","","","","list like error","string" "programPhase","A label noting which AMP RA/SLE program phase generated the data.","I, II","","","True","","","","list like error","string" "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" @@ -14,7 +14,7 @@ "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" "custom10xProbeSetSynID","If custom modified probe sets were used for collecting 10x Chromium Flex scRNA-seq data, then the probe reference files should be grouped as a zip or tar archive and uploaded as metadata. This attribute links the experimental data back to the probe set archive file via a synapse ID.","","","","True","","","","regex search ^syn[0-9]{8} error","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" -"specimenModality","Label assigned to experimental data files indicating whether the data contained corresponds to a single or multiple biospecimens","multispecimen, single specimen","","","True","","","","","string" +"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" "individualID","Unique identifier assigned to each study participant. For multi-specimen data files provide all IDs in a comma-separated list.","","","","True","","","","#ClinicalMetadataTemplate unique error^^#BiospecimenMetadataTemplate str^^list like error","string" "biospecimenID","A unique identifier assigned to specimens collected from study participants. For multi-specimen data files provide all IDs in a comma-separated list.","","","","True","","","","#BiospecimenMetadataTemplate unique error^^list like error","string" "parentBiospecimenID","The biospecimenID associated with the originating biospecimen for derived or child biospecimens.","","","","False","","","","","string" @@ -30,15 +30,14 @@ "nucleicAcidSource","The source of the nucleic acid used as input for sequencing library fragments. Select all that apply, though in most cases only a single label is expected.","BCR mRNA, CRISPR protospacer feature barcode, TCR mRNA, Tn5-accessible gDNA, antigen capture barcode, gDNA, globin-depleted RNA, intracellular protein feature barcode, multiplexing oligo, poly(A) RNA, rRNA-depleted RNA, surface protein feature barcode","","","True","","","","list like error","string" "biospecimenSubtype","Biospecimen status before sample is processed into a scRNA-seq library. Several scRNA-seq technologies support a variety of sample processing methods which can introduces sources of technical variation.","FFPE tissue, PFA-fixed tissue, cell or tissue lysate, cell suspension, flow-sorted cells, fresh tissue, frozen tissue, nuclei suspension, supernatant","","","False","","","","","string" "cellRangerOutput","10x Genomics Cell Ranger software output several different counts results and formats, some with different processing applied. This label distinguishes between these types and is particularly helpful when multiple files are uploaded with the sample name, e.g., barcodes.tsv.gz","Not Applicable, filtered MEX, filtered_feature_bc_matrix, filtered_peak_bc_matrix, raw MEX, raw_feature_bc_matrix, raw_peak_bc_matrix","","","True","","","","","string" -"alignmentReference","The genomic/transcriptomic reference used for performing read alignment against.","10x Cell Ranger Human GRCh38 2020-A, 10x Cell Ranger Human GRCh38 2024-A, modified GRCh38, unknown, vdj_GRCh38_alts_ensembl-4.0.0","","","True","","","","","string" -"libraryPrepMethod","Sequencing library preparation method or kit used to create the library. If no commercially available kit was used, please select 'in-house library prep'.","10x Chromium Fixed RNA Human Transcriptome, 10x Chromium GEM-X Single Cell 3' v4, 10x Chromium GEM-X Single Cell 5' v3, 10x Chromium Next GEM Single Cell 3', 10x Chromium Next GEM Single Cell 3' 3.1, 10x Chromium Next GEM Single Cell 5' v1.1, 10x Chromium Next GEM Single Cell 5' v2, 10x Chromium Next GEM Single Cell ATAC v2, 10x Chromium Single Cell Human BCR, 10x Chromium Single Cell Human TCR, 10x GEM-X Flex Gene Expression Human, 10x GEM-X Universal 5? Gene Expression v3, CEL-Seq2, Chromium Next GEM Single Cell ATAC v1.1, Fluidigm C1 HT, NEBNext Human Immune Sequencing Kit, NEBNext Ultra II Directional RNA Library, Nextera XT, Nextera XT DNA, QIAseq miRNA Library, SMART-Seq Human BCR with UMI, SMART-Seq Human TCR with UMI, SMART-Seq v4 Ultra Low Input RNA, SMARTer Stranded Total RNA v2, Takara Human BCR profiling for Illumina, Takara Human TCR profiling for Illumina, Takara Human TCRv2 profiling for Illumina, Takara Human scTCR profiling for Illumina, TruSeq Stranded mRNA, custom DASH-treatment, in-house library prep","","","True","","","","","string" +"alignmentReference","The genomic/transcriptomic reference used for performing read alignment against.","10x Cell Ranger Human GRCh38 2020-A, 10x Cell Ranger Human GRCh38 2024-A, GRCh38, modified GRCh38, unknown, vdj_GRCh38_alts_ensembl-4.0.0","","","True","","","","","string" +"libraryPrepMethod","Sequencing library preparation method or kit used to create the library. If no commercially available kit was used, please select 'in-house library prep'.","10x Chromium Fixed RNA Human Transcriptome, 10x Chromium GEM-X Single Cell 3' v4, 10x Chromium GEM-X Single Cell 5' v3, 10x Chromium Next GEM Single Cell 3', 10x Chromium Next GEM Single Cell 3' 3.1, 10x Chromium Next GEM Single Cell 5' v1.1, 10x Chromium Next GEM Single Cell 5' v2, 10x Chromium Next GEM Single Cell ATAC v2, 10x Chromium Single Cell Human BCR, 10x Chromium Single Cell Human TCR, 10x GEM-X Flex Gene Expression Human, 10x GEM-X Universal 5' Gene Expression v3, CEL-Seq2, Chromium Next GEM Single Cell ATAC v1.1, Fluidigm C1 HT, NEBNext Human Immune Sequencing Kit, NEBNext Ultra II Directional RNA Library, Nextera XT, Nextera XT DNA, QIAseq miRNA Library, SMART-Seq Human BCR with UMI, SMART-Seq Human TCR with UMI, SMART-Seq v4 Ultra Low Input RNA, SMARTer Stranded Total RNA v2, Takara Human BCR profiling for Illumina, Takara Human TCR profiling for Illumina, Takara Human TCRv2 profiling for Illumina, Takara Human scTCR profiling for Illumina, TruSeq Stranded mRNA, custom DASH-treatment, in-house library prep","","","True","","","","","string" "datasetType","High-level classification of dataset entity distinguishing between datasets compiled for a specific publication or as a general data resource.","experimental, publication","","","True","","","","","string" "acknowledgmentStatement","A Dataset-specific attribute specifying the path to the wiki subpage within the ARK Portal - backend project that contains the acknowledgement statement that must be included in publications using data from the given dataset as a stipulation of the conditions of use.","syn26710600/wiki/619685","","","True","","","","","string" "datasetDescription","A Dataset-specific attribute specifying the synID of the folder that contains a wiki write-up of the dataset description. This wiki content will be surfaced on the ARK Portal frontend site.","","","","True","","","","regex search ^syn[0-9]{8} error","string" "ARKRelease","A Dataset-specific attribute specifying the ARK Portal release in which this dataset was first made available to the public.","1.0, 2.0, 2024.06.R1, 2024.07.R1, 2024.08.R1, 2024.09.R1, 2024.10.R1, 2024.12.R1, 2025.01.R1, 2025.02.R1, 2025.03.R1, 2025.04.R1, 2025.05.R1, 2025.06.R1, 2025.07.R1, 2025.08.R1, 2025.09.R1, 2025.10.R1, 2025.11.R1, 2025.12.R1","","","True","","","","","string" "RObjectClass","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.","ROCR prediction.object, Seurat object, SummarizedExperiment, Symphony reference, data.frame, list, matrix, sparse matrix, vector","","","False","","","","","string" -"dbGapAccession","NIH policy requires large-scale human genomics studies to be registered in dbGap. This is a Dataset-specific attribute indicating the unique identifier (i.e., accession) of the corresponding study that is registered in dbGap, formatted as a compact URI, e.g., dbgap:phs003417.v2.p1","","","","False","","","","regex search ^dbgap:","string" -"diagnosis","A high-level classifier indicating the disease status of an individual.","At-Risk RA, OA, RA, SLE, Sjogren's disease, control, cutaneous lupus erythematosus, dermatomyositis, lupus nephritis, psoriasis, psoriatic arthritis, scleroderma, unknown, vitiligo","","","True","","","","list like error","string" +"diagnosis","A high-level classifier indicating the disease status of an individual.","At-Risk RA, Not Applicable, OA, RA, SLE, Sjogren's disease, control, cutaneous lupus erythematosus, dermatomyositis, discoid lupus erythematosus, lupus nephritis, psoriasis, psoriatic arthritis, scleroderma, unknown, vitiligo","","","True","","","","list like error","string" "DOID","Disease ontology identifier associated with `diagnosis`. Attribute values are applied by ARK Portal data managers.","","","","True","","","","regex search ^DOID error","string" "libraryID","A library label or name, unique within an experiment, used to distinguish sequencing libraries.","","","","True","","","","","string" "associatedCodeURL","A URL to the repository where associated code is available.","","","","False","","","","","string" @@ -55,7 +54,7 @@ "PMID","PubMed(R) Identifier","","","","True","","","","regex search ^PMID error","string" "DOI","Digital object identifier","","","","True","","","","","string" "anatomicalSite","The anatomical site, i.e., location on or within the body, from which the biospecimen was collected. This attribute is required depending on the value selected for biospecimenType.","left 2nd MCP joint, left ankle joint, left hip joint, left knee joint, left wrist joint, other site, right 1st MTP joint, right 2nd MCP joint, right 2nd MTP joint, right 3rd MCP joint, right ankle joint, right hip joint, right knee joint, right wrist joint, unknown","","","True","","","","","string" -"vitiligoType","A high-level classification of vitiligo based on the distribution and patterning of lesions across the body.","mixed, non-segmental, segmental, unclassified","","","False","","","","","string" +"vitiligoPattern","A high-level classification of vitiligo based on the distribution and patterning of lesions across the body.","mixed, non-segmental, segmental, unclassified","","","False","","","","","string" "vitiligoPhenotype","Classification of vitiligo lesions which correlate with autoimmune activity and result in specific skin and depigmentation manifestations at the lesion site. If N/A please select 'none'. Multiple selections can be provided in a comma-delimited list.","active, confetti, inflammatory, none, trichrome","","","True","","","","list like error","string" "psoriasisType","General type classification of psoriasis disease manifestation.","erythrodermic, guttate, inverse, plaque, pustular","","","False","","","","","string" "ageDiagnosis","Age at which subject was diagnosed with `diagnosis`. If providing this value be sure the unit matches that used for `age`.","","","","False","","","","num error","number" @@ -107,3 +106,5 @@ "treatmentTimepoint","Where applicable, specify the timepoint relative to treatment to distinguish different sets of samples that have undergone the same treatment but for different lengths of time. REQUIRED: please specify the unit of time, e.g., secs, mins, hrs, days, etc.","","","","False","","","","","string" "slideID","A distinct label or name, unique within an experiment, assigned to an imaging slides.","","","","True","","","","","string" "altSampleID","An alternate identifier for a sample. With some assays there can be default or alternate sample identifiers entered into the data collection software. If you will be uploading data collected with an alternate identifier please provide that here. In some cases, the ARK BDM team will use this field to capture original but out-dated identifiers for samples.","","","","False","","","","","string" +"sampleCollectionBatch","A label indicating batching of sample collection or experiment execution that occurs prior to data collection.","","","","False","","","","","string" +"associatedAccession","This is a File and Dataset annotation attribute indicating additional accessions (i.e., unique identifiers) associated with the data when the data has also been submitted to or can be found in other repositories such as GEO, SRA, dbGaP, etc.","","","","False","","","","list like error","string" diff --git a/model_contexts/biospecimen/ark.biospecimen_context.csv b/model_contexts/biospecimen/ark.biospecimen_context.csv index 918c8ca..69c2185 100644 --- a/model_contexts/biospecimen/ark.biospecimen_context.csv +++ b/model_contexts/biospecimen/ark.biospecimen_context.csv @@ -1,17 +1,17 @@ -Attribute,Description,Valid Values,DependsOn,Properties,Required,Parent,DependsOn Component,Source,Validation Rules,columnType -Biospecimen Metadata Template,A general template outlining metadata to be collected for biospecimen profiled in a dataset.,,"Component, program, project, individualID, biospecimenID, parentBiospecimenID, altSampleID, biospecimenType, biospecimenSubtype, notes",,,,,,, -In Vitro Biospecimen Metadata Template,A template outlining metadata to be collected for biospecimen used for an in vitro experiment.,,"Component, program, project, individualID, biospecimenID, parentBiospecimenID, altSampleID, biospecimenType, biospecimenSubtype, treatment, treatmentTimepoint, notes",,,,,,, -skin swab,Is a valid value of 'biospecimenType' that triggers conditional dependencies for additional attributes.,,"skinSiteStatus, anatomicalSite",,,,,,, -skin biopsy,Is a valid value of 'biospecimenType' that triggers conditional dependencies for additional attributes.,,"skinSiteStatus, anatomicalSite",,,,,,, -suction blister cells,Is a valid value of 'biospecimenType' that triggers conditional dependencies for additional attributes.,,"skinSiteStatus, anatomicalSite",,,,,,, -suction blister fluid,Is a valid value of 'biospecimenType' that triggers conditional dependencies for additional attributes.,,"skinSiteStatus, anatomicalSite",,,,,,, -saliva,Is a valid value of 'biospecimenType' that triggers conditional dependencies for additional attributes.,,salivaCollectionProcedure,,,,,,, -synovial tissue,Is a valid value of 'biospecimenType' that triggers conditional dependencies for additional attributes.,,"synovialCollectionProcedure, anatomicalSite, krennInflammatory, krennLining, krennStroma, krennSynovitisScore",,,,,,, -synovial fluid,Is a valid value of 'biospecimenType' that triggers conditional dependencies for additional attributes.,,"synovialCollectionProcedure, anatomicalSite",,,,,,, -flow-sorted cells,A valid value of 'biospecimenSubtype' that triggers conditional dependencies for additional attributes.,,"FACSPopulation, cellOntologyID, cellType, userDefinedCellType",,,,,,, -cell suspension,A valid value of 'biospecimenSubtype' that triggers conditional dependencies for additional attributes.,,"cellOntologyID, cellType, userDefinedCellType",,,,,,, -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,,,,,,, -AMP AIM,Accelerating Medicines Partnership Autoimmune and Immune-Mediated Diseases. Is a valid value for 'program' that triggers conditional dependencies for additional attributes.,,visitID,,,,,,, -primary cell culture,Is a valid value of 'biospecimenType' that triggers conditional dependencies for additional attributes.,,"cellType, cellOntologyID, primaryCellSource",,,,,,, -cell line,Is a valid value of 'biospecimenType' that triggers conditional dependencies for additional attributes.,,"cellType, cellOntologyID",,,,,,, -individualID,,,,,FALSE,,,,#BiospecimenMetadataTemplate required^^,string \ No newline at end of file +"Attribute","Description","Valid Values","DependsOn","Properties","Required","Parent","DependsOn Component","Source","Validation Rules","columnType" +"Biospecimen Metadata Template","A general template outlining metadata to be collected for biospecimen profiled in a dataset.","","Component, program, project, individualID, biospecimenID, parentBiospecimenID, altSampleID, biospecimenType, biospecimenSubtype, notes, sampleCollectionBatch","","","","","","","" +"In Vitro Biospecimen Metadata Template","A template outlining metadata to be collected for biospecimen used for an in vitro experiment.","","Component, program, project, individualID, biospecimenID, parentBiospecimenID, altSampleID, biospecimenType, biospecimenSubtype, treatment, treatmentTimepoint, notes, sampleCollectionBatch","","","","","","","" +"skin swab","Is a valid value of 'biospecimenType' that triggers conditional dependencies for additional attributes.","","skinSiteStatus, anatomicalSite","","","","","","","" +"skin biopsy","Is a valid value of 'biospecimenType' that triggers conditional dependencies for additional attributes.","","skinSiteStatus, anatomicalSite","","","","","","","" +"suction blister cells","Is a valid value of 'biospecimenType' that triggers conditional dependencies for additional attributes.","","skinSiteStatus, anatomicalSite","","","","","","","" +"suction blister fluid","Is a valid value of 'biospecimenType' that triggers conditional dependencies for additional attributes.","","skinSiteStatus, anatomicalSite","","","","","","","" +"saliva","Is a valid value of 'biospecimenType' that triggers conditional dependencies for additional attributes.","","salivaCollectionProcedure","","","","","","","" +"synovial tissue","Is a valid value of 'biospecimenType' that triggers conditional dependencies for additional attributes.","","synovialCollectionProcedure, anatomicalSite, krennInflammatory, krennLining, krennStroma, krennSynovitisScore","","","","","","","" +"synovial fluid","Is a valid value of 'biospecimenType' that triggers conditional dependencies for additional attributes.","","synovialCollectionProcedure, anatomicalSite","","","","","","","" +"flow-sorted cells","A valid value of 'biospecimenSubtype' that triggers conditional dependencies for additional attributes.","","FACSPopulation, cellOntologyID, cellType, userDefinedCellType","","","","","","","" +"cell suspension","A valid value of 'biospecimenSubtype' that triggers conditional dependencies for additional attributes.","","cellOntologyID, cellType, userDefinedCellType","","","","","","","" +"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","","","","","","","" +"AMP AIM","Accelerating Medicines Partnership Autoimmune and Immune-Mediated Diseases. Is a valid value for 'program' that triggers conditional dependencies for additional attributes.","","visitID","","","","","","","" +"primary cell culture","Is a valid value of 'biospecimenType' that triggers conditional dependencies for additional attributes.","","cellType, cellOntologyID, primaryCellSource","","","","","","","" +"cell line","Is a valid value of 'biospecimenType' that triggers conditional dependencies for additional attributes.","","cellType, cellOntologyID","","","","","","","" +"individualID","","","","","FALSE","","","","#BiospecimenMetadataTemplate required^^","string" diff --git a/model_contexts/biospecimen/ark.biospecimen_model.csv b/model_contexts/biospecimen/ark.biospecimen_model.csv index 3bd6ae0..f537a91 100644 --- a/model_contexts/biospecimen/ark.biospecimen_model.csv +++ b/model_contexts/biospecimen/ark.biospecimen_model.csv @@ -1,6 +1,6 @@ "Attribute","Description","Valid Values","DependsOn","Properties","Required","Parent","DependsOn Component","Source","Validation Rules","columnType" -"Biospecimen Metadata Template","A general template outlining metadata to be collected for biospecimen profiled in a dataset.","","Component, program, project, individualID, biospecimenID, parentBiospecimenID, altSampleID, biospecimenType, biospecimenSubtype, notes","","","","","","","" -"In Vitro Biospecimen Metadata Template","A template outlining metadata to be collected for biospecimen used for an in vitro experiment.","","Component, program, project, individualID, biospecimenID, parentBiospecimenID, altSampleID, biospecimenType, biospecimenSubtype, treatment, treatmentTimepoint, notes","","","","","","","" +"Biospecimen Metadata Template","A general template outlining metadata to be collected for biospecimen profiled in a dataset.","","Component, program, project, individualID, biospecimenID, parentBiospecimenID, altSampleID, biospecimenType, biospecimenSubtype, notes, sampleCollectionBatch","","","","","","","" +"In Vitro Biospecimen Metadata Template","A template outlining metadata to be collected for biospecimen used for an in vitro experiment.","","Component, program, project, individualID, biospecimenID, parentBiospecimenID, altSampleID, biospecimenType, biospecimenSubtype, treatment, treatmentTimepoint, notes, sampleCollectionBatch","","","","","","","" "skin swab","Is a valid value of 'biospecimenType' that triggers conditional dependencies for additional attributes.","","skinSiteStatus, anatomicalSite","","","","","","","" "skin biopsy","Is a valid value of 'biospecimenType' that triggers conditional dependencies for additional attributes.","","skinSiteStatus, anatomicalSite","","","","","","","" "suction blister cells","Is a valid value of 'biospecimenType' that triggers conditional dependencies for additional attributes.","","skinSiteStatus, anatomicalSite","","","","","","","" @@ -16,11 +16,11 @@ "cell line","Is a valid value of 'biospecimenType' that triggers conditional dependencies for additional attributes.","","cellType, cellOntologyID","","","","","","","" "individualID","Unique identifier assigned to each study participant. For multi-specimen data files provide all IDs in a comma-separated list.","","","","FALSE","","","","#BiospecimenMetadataTemplate required^^","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, info, mcd, mtx, parquet, pdf, rds, rec, svs, tbi, tgz, tsv, txt, vcf, xls, xlsx, zip","","","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, info, mcd, mtx, parquet, pdf, py, rds, rec, svs, tbi, tgz, tsv, txt, vcf, xls, xlsx, zip","","","True","","","","","string" "publicationSynID","The synID of the corresponding Synapse entity that stores metadata about the publication. This is used to differentiate publication-specific files, often consisting of level 4 processed data and expanded subject metadata, in a publication dataset that also includes raw or minimally processed files from experimental datasets. This provides an easy way to distinguish and select for the publication-specific data from which the research findings were derived. When this attribute is used to annotate a Dataset it serves as a way to directly link the Dataset entity with the publication metadata stored in Synapse.","","","","False","","","","regex search ^syn[0-9]{8} error","string" "associatedDataset","The synID of a Dataset entity. This serves to link other Synapse entities to Dataset entities. When used to annotate a publication Dataset this attribute should include the synID for an experimental Datasets from which the publication data was derived. Multiple synID can be specified using a comma-delimited list.","","","","False","","","","list like::regex search ^syn[0-9]{8} error","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, ELLIPSS, LOCKIT, RA, SLE, STAMP, V-CoRT","","","True","","","","list like error","string" +"project","A sub-level attribute of `program` specifying a research initiative working to investigate particular hypotheses.","AIM for RA, ELLIPSS, LOCKIT, RA, SLE, STAMP, UMass V-CoRT","","","True","","","","list like error","string" "programPhase","A label noting which AMP RA/SLE program phase generated the data.","I, II","","","True","","","","list like error","string" "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" @@ -30,7 +30,7 @@ "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" "custom10xProbeSetSynID","If custom modified probe sets were used for collecting 10x Chromium Flex scRNA-seq data, then the probe reference files should be grouped as a zip or tar archive and uploaded as metadata. This attribute links the experimental data back to the probe set archive file via a synapse ID.","","","","True","","","","regex search ^syn[0-9]{8} error","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" -"specimenModality","Label assigned to experimental data files indicating whether the data contained corresponds to a single or multiple biospecimens","multispecimen, single specimen","","","True","","","","","string" +"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" "biospecimenID","A unique identifier assigned to specimens collected from study participants. For multi-specimen data files provide all IDs in a comma-separated list.","","","","True","","","","#BiospecimenMetadataTemplate unique error^^list like error","string" "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" @@ -45,15 +45,14 @@ "nucleicAcidSource","The source of the nucleic acid used as input for sequencing library fragments. Select all that apply, though in most cases only a single label is expected.","BCR mRNA, CRISPR protospacer feature barcode, TCR mRNA, Tn5-accessible gDNA, antigen capture barcode, gDNA, globin-depleted RNA, intracellular protein feature barcode, multiplexing oligo, poly(A) RNA, rRNA-depleted RNA, surface protein feature barcode","","","True","","","","list like error","string" "biospecimenSubtype","Biospecimen status before sample is processed into a scRNA-seq library. Several scRNA-seq technologies support a variety of sample processing methods which can introduces sources of technical variation.","FFPE tissue, PFA-fixed tissue, cell or tissue lysate, cell suspension, flow-sorted cells, fresh tissue, frozen tissue, nuclei suspension, supernatant","","","False","","","","","string" "cellRangerOutput","10x Genomics Cell Ranger software output several different counts results and formats, some with different processing applied. This label distinguishes between these types and is particularly helpful when multiple files are uploaded with the sample name, e.g., barcodes.tsv.gz","Not Applicable, filtered MEX, filtered_feature_bc_matrix, filtered_peak_bc_matrix, raw MEX, raw_feature_bc_matrix, raw_peak_bc_matrix","","","True","","","","","string" -"alignmentReference","The genomic/transcriptomic reference used for performing read alignment against.","10x Cell Ranger Human GRCh38 2020-A, 10x Cell Ranger Human GRCh38 2024-A, modified GRCh38, unknown, vdj_GRCh38_alts_ensembl-4.0.0","","","True","","","","","string" -"libraryPrepMethod","Sequencing library preparation method or kit used to create the library. If no commercially available kit was used, please select 'in-house library prep'.","10x Chromium Fixed RNA Human Transcriptome, 10x Chromium GEM-X Single Cell 3' v4, 10x Chromium GEM-X Single Cell 5' v3, 10x Chromium Next GEM Single Cell 3', 10x Chromium Next GEM Single Cell 3' 3.1, 10x Chromium Next GEM Single Cell 5' v1.1, 10x Chromium Next GEM Single Cell 5' v2, 10x Chromium Next GEM Single Cell ATAC v2, 10x Chromium Single Cell Human BCR, 10x Chromium Single Cell Human TCR, 10x GEM-X Flex Gene Expression Human, 10x GEM-X Universal 5? Gene Expression v3, CEL-Seq2, Chromium Next GEM Single Cell ATAC v1.1, Fluidigm C1 HT, NEBNext Human Immune Sequencing Kit, NEBNext Ultra II Directional RNA Library, Nextera XT, Nextera XT DNA, QIAseq miRNA Library, SMART-Seq Human BCR with UMI, SMART-Seq Human TCR with UMI, SMART-Seq v4 Ultra Low Input RNA, SMARTer Stranded Total RNA v2, Takara Human BCR profiling for Illumina, Takara Human TCR profiling for Illumina, Takara Human TCRv2 profiling for Illumina, Takara Human scTCR profiling for Illumina, TruSeq Stranded mRNA, custom DASH-treatment, in-house library prep","","","True","","","","","string" +"alignmentReference","The genomic/transcriptomic reference used for performing read alignment against.","10x Cell Ranger Human GRCh38 2020-A, 10x Cell Ranger Human GRCh38 2024-A, GRCh38, modified GRCh38, unknown, vdj_GRCh38_alts_ensembl-4.0.0","","","True","","","","","string" +"libraryPrepMethod","Sequencing library preparation method or kit used to create the library. If no commercially available kit was used, please select 'in-house library prep'.","10x Chromium Fixed RNA Human Transcriptome, 10x Chromium GEM-X Single Cell 3' v4, 10x Chromium GEM-X Single Cell 5' v3, 10x Chromium Next GEM Single Cell 3', 10x Chromium Next GEM Single Cell 3' 3.1, 10x Chromium Next GEM Single Cell 5' v1.1, 10x Chromium Next GEM Single Cell 5' v2, 10x Chromium Next GEM Single Cell ATAC v2, 10x Chromium Single Cell Human BCR, 10x Chromium Single Cell Human TCR, 10x GEM-X Flex Gene Expression Human, 10x GEM-X Universal 5' Gene Expression v3, CEL-Seq2, Chromium Next GEM Single Cell ATAC v1.1, Fluidigm C1 HT, NEBNext Human Immune Sequencing Kit, NEBNext Ultra II Directional RNA Library, Nextera XT, Nextera XT DNA, QIAseq miRNA Library, SMART-Seq Human BCR with UMI, SMART-Seq Human TCR with UMI, SMART-Seq v4 Ultra Low Input RNA, SMARTer Stranded Total RNA v2, Takara Human BCR profiling for Illumina, Takara Human TCR profiling for Illumina, Takara Human TCRv2 profiling for Illumina, Takara Human scTCR profiling for Illumina, TruSeq Stranded mRNA, custom DASH-treatment, in-house library prep","","","True","","","","","string" "datasetType","High-level classification of dataset entity distinguishing between datasets compiled for a specific publication or as a general data resource.","experimental, publication","","","True","","","","","string" "acknowledgmentStatement","A Dataset-specific attribute specifying the path to the wiki subpage within the ARK Portal - backend project that contains the acknowledgement statement that must be included in publications using data from the given dataset as a stipulation of the conditions of use.","syn26710600/wiki/619685","","","True","","","","","string" "datasetDescription","A Dataset-specific attribute specifying the synID of the folder that contains a wiki write-up of the dataset description. This wiki content will be surfaced on the ARK Portal frontend site.","","","","True","","","","regex search ^syn[0-9]{8} error","string" "ARKRelease","A Dataset-specific attribute specifying the ARK Portal release in which this dataset was first made available to the public.","1.0, 2.0, 2024.06.R1, 2024.07.R1, 2024.08.R1, 2024.09.R1, 2024.10.R1, 2024.12.R1, 2025.01.R1, 2025.02.R1, 2025.03.R1, 2025.04.R1, 2025.05.R1, 2025.06.R1, 2025.07.R1, 2025.08.R1, 2025.09.R1, 2025.10.R1, 2025.11.R1, 2025.12.R1","","","True","","","","","string" "RObjectClass","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.","ROCR prediction.object, Seurat object, SummarizedExperiment, Symphony reference, data.frame, list, matrix, sparse matrix, vector","","","False","","","","","string" -"dbGapAccession","NIH policy requires large-scale human genomics studies to be registered in dbGap. This is a Dataset-specific attribute indicating the unique identifier (i.e., accession) of the corresponding study that is registered in dbGap, formatted as a compact URI, e.g., dbgap:phs003417.v2.p1","","","","False","","","","regex search ^dbgap:","string" -"diagnosis","A high-level classifier indicating the disease status of an individual.","At-Risk RA, OA, RA, SLE, Sjogren's disease, control, cutaneous lupus erythematosus, dermatomyositis, lupus nephritis, psoriasis, psoriatic arthritis, scleroderma, unknown, vitiligo","","","True","","","","list like error","string" +"diagnosis","A high-level classifier indicating the disease status of an individual.","At-Risk RA, Not Applicable, OA, RA, SLE, Sjogren's disease, control, cutaneous lupus erythematosus, dermatomyositis, discoid lupus erythematosus, lupus nephritis, psoriasis, psoriatic arthritis, scleroderma, unknown, vitiligo","","","True","","","","list like error","string" "DOID","Disease ontology identifier associated with `diagnosis`. Attribute values are applied by ARK Portal data managers.","","","","True","","","","regex search ^DOID error","string" "libraryID","A library label or name, unique within an experiment, used to distinguish sequencing libraries.","","","","True","","","","","string" "associatedCodeURL","A URL to the repository where associated code is available.","","","","False","","","","","string" @@ -70,7 +69,7 @@ "PMID","PubMed(R) Identifier","","","","True","","","","regex search ^PMID error","string" "DOI","Digital object identifier","","","","True","","","","","string" "anatomicalSite","The anatomical site, i.e., location on or within the body, from which the biospecimen was collected. This attribute is required depending on the value selected for biospecimenType.","left 2nd MCP joint, left ankle joint, left hip joint, left knee joint, left wrist joint, other site, right 1st MTP joint, right 2nd MCP joint, right 2nd MTP joint, right 3rd MCP joint, right ankle joint, right hip joint, right knee joint, right wrist joint, unknown","","","True","","","","","string" -"vitiligoType","A high-level classification of vitiligo based on the distribution and patterning of lesions across the body.","mixed, non-segmental, segmental, unclassified","","","False","","","","","string" +"vitiligoPattern","A high-level classification of vitiligo based on the distribution and patterning of lesions across the body.","mixed, non-segmental, segmental, unclassified","","","False","","","","","string" "vitiligoPhenotype","Classification of vitiligo lesions which correlate with autoimmune activity and result in specific skin and depigmentation manifestations at the lesion site. If N/A please select 'none'. Multiple selections can be provided in a comma-delimited list.","active, confetti, inflammatory, none, trichrome","","","True","","","","list like error","string" "psoriasisType","General type classification of psoriasis disease manifestation.","erythrodermic, guttate, inverse, plaque, pustular","","","False","","","","","string" "ageDiagnosis","Age at which subject was diagnosed with `diagnosis`. If providing this value be sure the unit matches that used for `age`.","","","","False","","","","num error","number" @@ -121,3 +120,5 @@ "treatmentTimepoint","Where applicable, specify the timepoint relative to treatment to distinguish different sets of samples that have undergone the same treatment but for different lengths of time. REQUIRED: please specify the unit of time, e.g., secs, mins, hrs, days, etc.","","","","False","","","","","string" "slideID","A distinct label or name, unique within an experiment, assigned to an imaging slides.","","","","True","","","","","string" "altSampleID","An alternate identifier for a sample. With some assays there can be default or alternate sample identifiers entered into the data collection software. If you will be uploading data collected with an alternate identifier please provide that here. In some cases, the ARK BDM team will use this field to capture original but out-dated identifiers for samples.","","","","False","","","","","string" +"sampleCollectionBatch","A label indicating batching of sample collection or experiment execution that occurs prior to data collection.","","","","False","","","","","string" +"associatedAccession","This is a File and Dataset annotation attribute indicating additional accessions (i.e., unique identifiers) associated with the data when the data has also been submitted to or can be found in other repositories such as GEO, SRA, dbGaP, etc.","","","","False","","","","list like error","string" diff --git a/model_contexts/biospecimen/ark.biospecimen_model.jsonld b/model_contexts/biospecimen/ark.biospecimen_model.jsonld index 8717f4c..0aa3222 100644 --- a/model_contexts/biospecimen/ark.biospecimen_model.jsonld +++ b/model_contexts/biospecimen/ark.biospecimen_model.jsonld @@ -52,6 +52,9 @@ }, { "@id": "bts:Notes" + }, + { + "@id": "bts:SampleCollectionBatch" } ], "sms:validationRules": [] @@ -134,7 +137,7 @@ "@id": "bts:STAMP" }, { - "@id": "bts:V-CoRT" + "@id": "bts:UMassV-CoRT" } ], "sms:displayName": "project", @@ -365,6 +368,23 @@ "sms:required": "sms:false", "sms:validationRules": [] }, + { + "@id": "bts:SampleCollectionBatch", + "@type": "rdfs:Class", + "rdfs:comment": "A label indicating batching of sample collection or experiment execution that occurs prior to data collection.", + "rdfs:label": "SampleCollectionBatch", + "rdfs:subClassOf": [ + { + "@id": "bts:Thing" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "sampleCollectionBatch", + "sms:required": "sms:false", + "sms:validationRules": [] + }, { "@id": "bts:InVitroBiospecimenMetadataTemplate", "@type": "rdfs:Class", @@ -416,6 +436,9 @@ }, { "@id": "bts:Notes" + }, + { + "@id": "bts:SampleCollectionBatch" } ], "sms:validationRules": [] @@ -1234,6 +1257,9 @@ { "@id": "bts:Pdf" }, + { + "@id": "bts:Py" + }, { "@id": "bts:Rds" }, @@ -1612,6 +1638,23 @@ "sms:required": "sms:false", "sms:validationRules": [] }, + { + "@id": "bts:Py", + "@type": "rdfs:Class", + "rdfs:comment": "TBD", + "rdfs:label": "Py", + "rdfs:subClassOf": [ + { + "@id": "bts:FileFormat" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "py", + "sms:required": "sms:false", + "sms:validationRules": [] + }, { "@id": "bts:Rds", "@type": "rdfs:Class", @@ -1913,10 +1956,10 @@ "rdfs:label": "RA", "rdfs:subClassOf": [ { - "@id": "bts:Diagnosis" + "@id": "bts:Project" }, { - "@id": "bts:Project" + "@id": "bts:Diagnosis" } ], "schema:isPartOf": { @@ -1933,10 +1976,10 @@ "rdfs:label": "SLE", "rdfs:subClassOf": [ { - "@id": "bts:Diagnosis" + "@id": "bts:Project" }, { - "@id": "bts:Project" + "@id": "bts:Diagnosis" } ], "schema:isPartOf": { @@ -1964,10 +2007,10 @@ "sms:validationRules": [] }, { - "@id": "bts:V-CoRT", + "@id": "bts:UMassV-CoRT", "@type": "rdfs:Class", "rdfs:comment": "TBD", - "rdfs:label": "V-CoRT", + "rdfs:label": "UMassV-CoRT", "rdfs:subClassOf": [ { "@id": "bts:Project" @@ -1976,7 +2019,7 @@ "schema:isPartOf": { "@id": "http://schema.biothings.io" }, - "sms:displayName": "V-CoRT", + "sms:displayName": "UMass V-CoRT", "sms:required": "sms:false", "sms:validationRules": [] }, @@ -4232,6 +4275,9 @@ { "@id": "bts:CellRangerOutput" }, + { + "@id": "bts:Diagnosis" + }, { "@id": "bts:Platform" } @@ -4352,10 +4398,10 @@ "rdfs:label": "Unknown", "rdfs:subClassOf": [ { - "@id": "bts:Ethnicity" + "@id": "bts:SpecimenModality" }, { - "@id": "bts:AlignmentReference" + "@id": "bts:Ethnicity" }, { "@id": "bts:SynovialCollectionProcedure" @@ -4366,6 +4412,9 @@ { "@id": "bts:DiabetesType" }, + { + "@id": "bts:AlignmentReference" + }, { "@id": "bts:Race" }, @@ -4405,6 +4454,9 @@ }, { "@id": "bts:Singlespecimen" + }, + { + "@id": "bts:Unknown" } ], "sms:displayName": "specimenModality", @@ -6464,6 +6516,9 @@ { "@id": "bts:10xCellRangerHumanGRCh382024-A" }, + { + "@id": "bts:GRCh38" + }, { "@id": "bts:ModifiedGRCh38" }, @@ -6512,6 +6567,23 @@ "sms:required": "sms:false", "sms:validationRules": [] }, + { + "@id": "bts:GRCh38", + "@type": "rdfs:Class", + "rdfs:comment": "TBD", + "rdfs:label": "GRCh38", + "rdfs:subClassOf": [ + { + "@id": "bts:AlignmentReference" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "GRCh38", + "sms:required": "sms:false", + "sms:validationRules": [] + }, { "@id": "bts:ModifiedGRCh38", "@type": "rdfs:Class", @@ -6594,7 +6666,7 @@ "@id": "bts:10xGEM-XFlexGeneExpressionHuman" }, { - "@id": "bts:10xGEM-XUniversal5?GeneExpressionv3" + "@id": "bts:10xGEM-XUniversal5'GeneExpressionv3" }, { "@id": "bts:CEL-Seq2" @@ -6846,10 +6918,10 @@ "sms:validationRules": [] }, { - "@id": "bts:10xGEM-XUniversal5?GeneExpressionv3", + "@id": "bts:10xGEM-XUniversal5'GeneExpressionv3", "@type": "rdfs:Class", "rdfs:comment": "TBD", - "rdfs:label": "10xGEM-XUniversal5?GeneExpressionv3", + "rdfs:label": "10xGEM-XUniversal5'GeneExpressionv3", "rdfs:subClassOf": [ { "@id": "bts:LibraryPrepMethod" @@ -6858,7 +6930,7 @@ "schema:isPartOf": { "@id": "http://schema.biothings.io" }, - "sms:displayName": "10x GEM-X Universal 5? Gene Expression v3", + "sms:displayName": "10x GEM-X Universal 5' Gene Expression v3", "sms:required": "sms:false", "sms:validationRules": [] }, @@ -7920,25 +7992,6 @@ "sms:required": "sms:false", "sms:validationRules": [] }, - { - "@id": "bts:DbGapAccession", - "@type": "rdfs:Class", - "rdfs:comment": "NIH policy requires large-scale human genomics studies to be registered in dbGap. This is a Dataset-specific attribute indicating the unique identifier (i.e., accession) of the corresponding study that is registered in dbGap, formatted as a compact URI, e.g., dbgap:phs003417.v2.p1", - "rdfs:label": "DbGapAccession", - "rdfs:subClassOf": [ - { - "@id": "bts:Thing" - } - ], - "schema:isPartOf": { - "@id": "http://schema.biothings.io" - }, - "sms:displayName": "dbGapAccession", - "sms:required": "sms:false", - "sms:validationRules": [ - "regex search ^dbgap:" - ] - }, { "@id": "bts:Diagnosis", "@type": "rdfs:Class", @@ -7956,6 +8009,9 @@ { "@id": "bts:At-RiskRA" }, + { + "@id": "bts:NotApplicable" + }, { "@id": "bts:OA" }, @@ -7977,6 +8033,9 @@ { "@id": "bts:Dermatomyositis" }, + { + "@id": "bts:Discoidlupuserythematosus" + }, { "@id": "bts:Lupusnephritis" }, @@ -8104,6 +8163,23 @@ "sms:required": "sms:false", "sms:validationRules": [] }, + { + "@id": "bts:Discoidlupuserythematosus", + "@type": "rdfs:Class", + "rdfs:comment": "TBD", + "rdfs:label": "Discoidlupuserythematosus", + "rdfs:subClassOf": [ + { + "@id": "bts:Diagnosis" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "discoid lupus erythematosus", + "sms:required": "sms:false", + "sms:validationRules": [] + }, { "@id": "bts:Lupusnephritis", "@type": "rdfs:Class", @@ -8863,10 +8939,10 @@ "sms:validationRules": [] }, { - "@id": "bts:VitiligoType", + "@id": "bts:VitiligoPattern", "@type": "rdfs:Class", "rdfs:comment": "A high-level classification of vitiligo based on the distribution and patterning of lesions across the body.", - "rdfs:label": "VitiligoType", + "rdfs:label": "VitiligoPattern", "rdfs:subClassOf": [ { "@id": "bts:Thing" @@ -8889,7 +8965,7 @@ "@id": "bts:Unclassified" } ], - "sms:displayName": "vitiligoType", + "sms:displayName": "vitiligoPattern", "sms:required": "sms:false", "sms:validationRules": [] }, @@ -8900,7 +8976,7 @@ "rdfs:label": "Mixed", "rdfs:subClassOf": [ { - "@id": "bts:VitiligoType" + "@id": "bts:VitiligoPattern" } ], "schema:isPartOf": { @@ -8917,7 +8993,7 @@ "rdfs:label": "Non-segmental", "rdfs:subClassOf": [ { - "@id": "bts:VitiligoType" + "@id": "bts:VitiligoPattern" } ], "schema:isPartOf": { @@ -8934,7 +9010,7 @@ "rdfs:label": "Segmental", "rdfs:subClassOf": [ { - "@id": "bts:VitiligoType" + "@id": "bts:VitiligoPattern" } ], "schema:isPartOf": { @@ -8951,7 +9027,7 @@ "rdfs:label": "Unclassified", "rdfs:subClassOf": [ { - "@id": "bts:VitiligoType" + "@id": "bts:VitiligoPattern" } ], "schema:isPartOf": { @@ -10835,6 +10911,25 @@ "sms:displayName": "slideID", "sms:required": "sms:true", "sms:validationRules": [] + }, + { + "@id": "bts:AssociatedAccession", + "@type": "rdfs:Class", + "rdfs:comment": "This is a File and Dataset annotation attribute indicating additional accessions (i.e., unique identifiers) associated with the data when the data has also been submitted to or can be found in other repositories such as GEO, SRA, dbGaP, etc.", + "rdfs:label": "AssociatedAccession", + "rdfs:subClassOf": [ + { + "@id": "bts:Thing" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "associatedAccession", + "sms:required": "sms:false", + "sms:validationRules": [ + "list like error" + ] } ], "@id": "http://schema.biothings.io/#0.1" diff --git a/model_contexts/clinical/ark.clinical_context.csv b/model_contexts/clinical/ark.clinical_context.csv index f996594..7d1d8e7 100644 --- a/model_contexts/clinical/ark.clinical_context.csv +++ b/model_contexts/clinical/ark.clinical_context.csv @@ -1,8 +1,8 @@ -Attribute,Description,Valid Values,DependsOn,Properties,Required,Parent,DependsOn Component,Source,Validation Rules,columnType -Clinical Metadata Template,A template outlining clinical metadata to collect for study subjects.,,"Component, program, project, species, individualID, diagnosis, age, ageUnits, sex, race, ethnicity, height, heightUnits, weight, weightUnits, comorbidities",,,,,,, -vitiligo,A valid value of `diagnosis` that triggers conditional dependencies for additional attributes.,,"vitiligoType, VIDA, VASI, VETI",,,,,,, -diabetes,A valid value of `comorbidities` that triggers conditional dependencies for additional attributes.,,diabetesType,,,,,,, -psoriasis,A valid value of `diagnosis` that triggers conditional dependencies for additional attributes.,,PASI,,,,,,, -dermatomyositis,A valid value of `diagnosis` that triggers conditional dependencies for additional attributes.,,CDASI,,,,,,, -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,,,,,,, -AMP AIM,Accelerating Medicines Partnership Autoimmune and Immune-Mediated Diseases. Is a valid value for 'program' that triggers conditional dependencies for additional attributes.,,visitID,,,,,,, \ No newline at end of file +"Attribute","Description","Valid Values","DependsOn","Properties","Required","Parent","DependsOn Component","Source","Validation Rules","columnType" +"Clinical Metadata Template","A template outlining clinical metadata to collect for study subjects.","","Component, program, project, species, individualID, diagnosis, age, ageUnits, sex, race, ethnicity, height, heightUnits, weight, weightUnits, comorbidities","","","","","","","" +"vitiligo","A valid value of `diagnosis` that triggers conditional dependencies for additional attributes.","","vitiligoPattern, VIDA, VASI, VETI","","","","","","","" +"diabetes","A valid value of `comorbidities` that triggers conditional dependencies for additional attributes.","","diabetesType","","","","","","","" +"psoriasis","A valid value of `diagnosis` that triggers conditional dependencies for additional attributes.","","PASI","","","","","","","" +"dermatomyositis","A valid value of `diagnosis` that triggers conditional dependencies for additional attributes.","","CDASI","","","","","","","" +"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","","","","","","","" +"AMP AIM","Accelerating Medicines Partnership Autoimmune and Immune-Mediated Diseases. Is a valid value for 'program' that triggers conditional dependencies for additional attributes.","","visitID","","","","","","","" diff --git a/model_contexts/clinical/ark.clinical_model.csv b/model_contexts/clinical/ark.clinical_model.csv index d6498c3..fa6e4dd 100644 --- a/model_contexts/clinical/ark.clinical_model.csv +++ b/model_contexts/clinical/ark.clinical_model.csv @@ -1,17 +1,17 @@ "Attribute","Description","Valid Values","DependsOn","Properties","Required","Parent","DependsOn Component","Source","Validation Rules","columnType" "Clinical Metadata Template","A template outlining clinical metadata to collect for study subjects.","","Component, program, project, species, individualID, diagnosis, age, ageUnits, sex, race, ethnicity, height, heightUnits, weight, weightUnits, comorbidities","","","","","","","" -"vitiligo","A valid value of `diagnosis` that triggers conditional dependencies for additional attributes.","","vitiligoType, VIDA, VASI, VETI","","","","","","","" +"vitiligo","A valid value of `diagnosis` that triggers conditional dependencies for additional attributes.","","vitiligoPattern, VIDA, VASI, VETI","","","","","","","" "diabetes","A valid value of `comorbidities` that triggers conditional dependencies for additional attributes.","","diabetesType","","","","","","","" "psoriasis","A valid value of `diagnosis` that triggers conditional dependencies for additional attributes.","","PASI","","","","","","","" "dermatomyositis","A valid value of `diagnosis` that triggers conditional dependencies for additional attributes.","","CDASI","","","","","","","" "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","","","","","","","" "AMP AIM","Accelerating Medicines Partnership Autoimmune and Immune-Mediated Diseases. Is a valid value for 'program' that triggers conditional dependencies for additional attributes.","","visitID","","","","","","","" "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, info, mcd, mtx, parquet, pdf, rds, rec, svs, tbi, tgz, tsv, txt, vcf, xls, xlsx, zip","","","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, info, mcd, mtx, parquet, pdf, py, rds, rec, svs, tbi, tgz, tsv, txt, vcf, xls, xlsx, zip","","","True","","","","","string" "publicationSynID","The synID of the corresponding Synapse entity that stores metadata about the publication. This is used to differentiate publication-specific files, often consisting of level 4 processed data and expanded subject metadata, in a publication dataset that also includes raw or minimally processed files from experimental datasets. This provides an easy way to distinguish and select for the publication-specific data from which the research findings were derived. When this attribute is used to annotate a Dataset it serves as a way to directly link the Dataset entity with the publication metadata stored in Synapse.","","","","False","","","","regex search ^syn[0-9]{8} error","string" "associatedDataset","The synID of a Dataset entity. This serves to link other Synapse entities to Dataset entities. When used to annotate a publication Dataset this attribute should include the synID for an experimental Datasets from which the publication data was derived. Multiple synID can be specified using a comma-delimited list.","","","","False","","","","list like::regex search ^syn[0-9]{8} error","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, ELLIPSS, LOCKIT, RA, SLE, STAMP, V-CoRT","","","True","","","","list like error","string" +"project","A sub-level attribute of `program` specifying a research initiative working to investigate particular hypotheses.","AIM for RA, ELLIPSS, LOCKIT, RA, SLE, STAMP, UMass V-CoRT","","","True","","","","list like error","string" "programPhase","A label noting which AMP RA/SLE program phase generated the data.","I, II","","","True","","","","list like error","string" "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" @@ -21,7 +21,7 @@ "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" "custom10xProbeSetSynID","If custom modified probe sets were used for collecting 10x Chromium Flex scRNA-seq data, then the probe reference files should be grouped as a zip or tar archive and uploaded as metadata. This attribute links the experimental data back to the probe set archive file via a synapse ID.","","","","True","","","","regex search ^syn[0-9]{8} error","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" -"specimenModality","Label assigned to experimental data files indicating whether the data contained corresponds to a single or multiple biospecimens","multispecimen, single specimen","","","True","","","","","string" +"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" "individualID","Unique identifier assigned to each study participant. For multi-specimen data files provide all IDs in a comma-separated list.","","","","True","","","","#ClinicalMetadataTemplate unique error^^#BiospecimenMetadataTemplate str^^list like error","string" "biospecimenID","A unique identifier assigned to specimens collected from study participants. For multi-specimen data files provide all IDs in a comma-separated list.","","","","True","","","","#BiospecimenMetadataTemplate unique error^^list like error","string" "parentBiospecimenID","The biospecimenID associated with the originating biospecimen for derived or child biospecimens.","","","","False","","","","","string" @@ -37,15 +37,14 @@ "nucleicAcidSource","The source of the nucleic acid used as input for sequencing library fragments. Select all that apply, though in most cases only a single label is expected.","BCR mRNA, CRISPR protospacer feature barcode, TCR mRNA, Tn5-accessible gDNA, antigen capture barcode, gDNA, globin-depleted RNA, intracellular protein feature barcode, multiplexing oligo, poly(A) RNA, rRNA-depleted RNA, surface protein feature barcode","","","True","","","","list like error","string" "biospecimenSubtype","Biospecimen status before sample is processed into a scRNA-seq library. Several scRNA-seq technologies support a variety of sample processing methods which can introduces sources of technical variation.","FFPE tissue, PFA-fixed tissue, cell or tissue lysate, cell suspension, flow-sorted cells, fresh tissue, frozen tissue, nuclei suspension, supernatant","","","False","","","","","string" "cellRangerOutput","10x Genomics Cell Ranger software output several different counts results and formats, some with different processing applied. This label distinguishes between these types and is particularly helpful when multiple files are uploaded with the sample name, e.g., barcodes.tsv.gz","Not Applicable, filtered MEX, filtered_feature_bc_matrix, filtered_peak_bc_matrix, raw MEX, raw_feature_bc_matrix, raw_peak_bc_matrix","","","True","","","","","string" -"alignmentReference","The genomic/transcriptomic reference used for performing read alignment against.","10x Cell Ranger Human GRCh38 2020-A, 10x Cell Ranger Human GRCh38 2024-A, modified GRCh38, unknown, vdj_GRCh38_alts_ensembl-4.0.0","","","True","","","","","string" -"libraryPrepMethod","Sequencing library preparation method or kit used to create the library. If no commercially available kit was used, please select 'in-house library prep'.","10x Chromium Fixed RNA Human Transcriptome, 10x Chromium GEM-X Single Cell 3' v4, 10x Chromium GEM-X Single Cell 5' v3, 10x Chromium Next GEM Single Cell 3', 10x Chromium Next GEM Single Cell 3' 3.1, 10x Chromium Next GEM Single Cell 5' v1.1, 10x Chromium Next GEM Single Cell 5' v2, 10x Chromium Next GEM Single Cell ATAC v2, 10x Chromium Single Cell Human BCR, 10x Chromium Single Cell Human TCR, 10x GEM-X Flex Gene Expression Human, 10x GEM-X Universal 5? Gene Expression v3, CEL-Seq2, Chromium Next GEM Single Cell ATAC v1.1, Fluidigm C1 HT, NEBNext Human Immune Sequencing Kit, NEBNext Ultra II Directional RNA Library, Nextera XT, Nextera XT DNA, QIAseq miRNA Library, SMART-Seq Human BCR with UMI, SMART-Seq Human TCR with UMI, SMART-Seq v4 Ultra Low Input RNA, SMARTer Stranded Total RNA v2, Takara Human BCR profiling for Illumina, Takara Human TCR profiling for Illumina, Takara Human TCRv2 profiling for Illumina, Takara Human scTCR profiling for Illumina, TruSeq Stranded mRNA, custom DASH-treatment, in-house library prep","","","True","","","","","string" +"alignmentReference","The genomic/transcriptomic reference used for performing read alignment against.","10x Cell Ranger Human GRCh38 2020-A, 10x Cell Ranger Human GRCh38 2024-A, GRCh38, modified GRCh38, unknown, vdj_GRCh38_alts_ensembl-4.0.0","","","True","","","","","string" +"libraryPrepMethod","Sequencing library preparation method or kit used to create the library. If no commercially available kit was used, please select 'in-house library prep'.","10x Chromium Fixed RNA Human Transcriptome, 10x Chromium GEM-X Single Cell 3' v4, 10x Chromium GEM-X Single Cell 5' v3, 10x Chromium Next GEM Single Cell 3', 10x Chromium Next GEM Single Cell 3' 3.1, 10x Chromium Next GEM Single Cell 5' v1.1, 10x Chromium Next GEM Single Cell 5' v2, 10x Chromium Next GEM Single Cell ATAC v2, 10x Chromium Single Cell Human BCR, 10x Chromium Single Cell Human TCR, 10x GEM-X Flex Gene Expression Human, 10x GEM-X Universal 5' Gene Expression v3, CEL-Seq2, Chromium Next GEM Single Cell ATAC v1.1, Fluidigm C1 HT, NEBNext Human Immune Sequencing Kit, NEBNext Ultra II Directional RNA Library, Nextera XT, Nextera XT DNA, QIAseq miRNA Library, SMART-Seq Human BCR with UMI, SMART-Seq Human TCR with UMI, SMART-Seq v4 Ultra Low Input RNA, SMARTer Stranded Total RNA v2, Takara Human BCR profiling for Illumina, Takara Human TCR profiling for Illumina, Takara Human TCRv2 profiling for Illumina, Takara Human scTCR profiling for Illumina, TruSeq Stranded mRNA, custom DASH-treatment, in-house library prep","","","True","","","","","string" "datasetType","High-level classification of dataset entity distinguishing between datasets compiled for a specific publication or as a general data resource.","experimental, publication","","","True","","","","","string" "acknowledgmentStatement","A Dataset-specific attribute specifying the path to the wiki subpage within the ARK Portal - backend project that contains the acknowledgement statement that must be included in publications using data from the given dataset as a stipulation of the conditions of use.","syn26710600/wiki/619685","","","True","","","","","string" "datasetDescription","A Dataset-specific attribute specifying the synID of the folder that contains a wiki write-up of the dataset description. This wiki content will be surfaced on the ARK Portal frontend site.","","","","True","","","","regex search ^syn[0-9]{8} error","string" "ARKRelease","A Dataset-specific attribute specifying the ARK Portal release in which this dataset was first made available to the public.","1.0, 2.0, 2024.06.R1, 2024.07.R1, 2024.08.R1, 2024.09.R1, 2024.10.R1, 2024.12.R1, 2025.01.R1, 2025.02.R1, 2025.03.R1, 2025.04.R1, 2025.05.R1, 2025.06.R1, 2025.07.R1, 2025.08.R1, 2025.09.R1, 2025.10.R1, 2025.11.R1, 2025.12.R1","","","True","","","","","string" "RObjectClass","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.","ROCR prediction.object, Seurat object, SummarizedExperiment, Symphony reference, data.frame, list, matrix, sparse matrix, vector","","","False","","","","","string" -"dbGapAccession","NIH policy requires large-scale human genomics studies to be registered in dbGap. This is a Dataset-specific attribute indicating the unique identifier (i.e., accession) of the corresponding study that is registered in dbGap, formatted as a compact URI, e.g., dbgap:phs003417.v2.p1","","","","False","","","","regex search ^dbgap:","string" -"diagnosis","A high-level classifier indicating the disease status of an individual.","At-Risk RA, OA, RA, SLE, Sjogren's disease, control, cutaneous lupus erythematosus, dermatomyositis, lupus nephritis, psoriasis, psoriatic arthritis, scleroderma, unknown, vitiligo","","","True","","","","list like error","string" +"diagnosis","A high-level classifier indicating the disease status of an individual.","At-Risk RA, Not Applicable, OA, RA, SLE, Sjogren's disease, control, cutaneous lupus erythematosus, dermatomyositis, discoid lupus erythematosus, lupus nephritis, psoriasis, psoriatic arthritis, scleroderma, unknown, vitiligo","","","True","","","","list like error","string" "DOID","Disease ontology identifier associated with `diagnosis`. Attribute values are applied by ARK Portal data managers.","","","","True","","","","regex search ^DOID error","string" "libraryID","A library label or name, unique within an experiment, used to distinguish sequencing libraries.","","","","True","","","","","string" "associatedCodeURL","A URL to the repository where associated code is available.","","","","False","","","","","string" @@ -62,7 +61,7 @@ "PMID","PubMed(R) Identifier","","","","True","","","","regex search ^PMID error","string" "DOI","Digital object identifier","","","","True","","","","","string" "anatomicalSite","The anatomical site, i.e., location on or within the body, from which the biospecimen was collected. This attribute is required depending on the value selected for biospecimenType.","left 2nd MCP joint, left ankle joint, left hip joint, left knee joint, left wrist joint, other site, right 1st MTP joint, right 2nd MCP joint, right 2nd MTP joint, right 3rd MCP joint, right ankle joint, right hip joint, right knee joint, right wrist joint, unknown","","","True","","","","","string" -"vitiligoType","A high-level classification of vitiligo based on the distribution and patterning of lesions across the body.","mixed, non-segmental, segmental, unclassified","","","False","","","","","string" +"vitiligoPattern","A high-level classification of vitiligo based on the distribution and patterning of lesions across the body.","mixed, non-segmental, segmental, unclassified","","","False","","","","","string" "vitiligoPhenotype","Classification of vitiligo lesions which correlate with autoimmune activity and result in specific skin and depigmentation manifestations at the lesion site. If N/A please select 'none'. Multiple selections can be provided in a comma-delimited list.","active, confetti, inflammatory, none, trichrome","","","True","","","","list like error","string" "psoriasisType","General type classification of psoriasis disease manifestation.","erythrodermic, guttate, inverse, plaque, pustular","","","False","","","","","string" "ageDiagnosis","Age at which subject was diagnosed with `diagnosis`. If providing this value be sure the unit matches that used for `age`.","","","","False","","","","num error","number" @@ -113,3 +112,5 @@ "treatmentTimepoint","Where applicable, specify the timepoint relative to treatment to distinguish different sets of samples that have undergone the same treatment but for different lengths of time. REQUIRED: please specify the unit of time, e.g., secs, mins, hrs, days, etc.","","","","False","","","","","string" "slideID","A distinct label or name, unique within an experiment, assigned to an imaging slides.","","","","True","","","","","string" "altSampleID","An alternate identifier for a sample. With some assays there can be default or alternate sample identifiers entered into the data collection software. If you will be uploading data collected with an alternate identifier please provide that here. In some cases, the ARK BDM team will use this field to capture original but out-dated identifiers for samples.","","","","False","","","","","string" +"sampleCollectionBatch","A label indicating batching of sample collection or experiment execution that occurs prior to data collection.","","","","False","","","","","string" +"associatedAccession","This is a File and Dataset annotation attribute indicating additional accessions (i.e., unique identifiers) associated with the data when the data has also been submitted to or can be found in other repositories such as GEO, SRA, dbGaP, etc.","","","","False","","","","list like error","string" diff --git a/model_contexts/clinical/ark.clinical_model.jsonld b/model_contexts/clinical/ark.clinical_model.jsonld index 88b517c..a04d22b 100644 --- a/model_contexts/clinical/ark.clinical_model.jsonld +++ b/model_contexts/clinical/ark.clinical_model.jsonld @@ -152,7 +152,7 @@ "@id": "bts:STAMP" }, { - "@id": "bts:V-CoRT" + "@id": "bts:UMassV-CoRT" } ], "sms:displayName": "project", @@ -221,6 +221,9 @@ { "@id": "bts:At-RiskRA" }, + { + "@id": "bts:NotApplicable" + }, { "@id": "bts:OA" }, @@ -242,6 +245,9 @@ { "@id": "bts:Dermatomyositis" }, + { + "@id": "bts:Discoidlupuserythematosus" + }, { "@id": "bts:Lupusnephritis" }, @@ -590,7 +596,7 @@ "sms:required": "sms:false", "sms:requiresDependency": [ { - "@id": "bts:VitiligoType" + "@id": "bts:VitiligoPattern" }, { "@id": "bts:VIDA" @@ -605,10 +611,10 @@ "sms:validationRules": [] }, { - "@id": "bts:VitiligoType", + "@id": "bts:VitiligoPattern", "@type": "rdfs:Class", "rdfs:comment": "A high-level classification of vitiligo based on the distribution and patterning of lesions across the body.", - "rdfs:label": "VitiligoType", + "rdfs:label": "VitiligoPattern", "rdfs:subClassOf": [ { "@id": "bts:Thing" @@ -631,7 +637,7 @@ "@id": "bts:Unclassified" } ], - "sms:displayName": "vitiligoType", + "sms:displayName": "vitiligoPattern", "sms:required": "sms:false", "sms:validationRules": [] }, @@ -957,6 +963,9 @@ { "@id": "bts:Pdf" }, + { + "@id": "bts:Py" + }, { "@id": "bts:Rds" }, @@ -1335,6 +1344,23 @@ "sms:required": "sms:false", "sms:validationRules": [] }, + { + "@id": "bts:Py", + "@type": "rdfs:Class", + "rdfs:comment": "TBD", + "rdfs:label": "Py", + "rdfs:subClassOf": [ + { + "@id": "bts:FileFormat" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "py", + "sms:required": "sms:false", + "sms:validationRules": [] + }, { "@id": "bts:Rds", "@type": "rdfs:Class", @@ -1636,10 +1662,10 @@ "rdfs:label": "RA", "rdfs:subClassOf": [ { - "@id": "bts:Diagnosis" + "@id": "bts:Project" }, { - "@id": "bts:Project" + "@id": "bts:Diagnosis" } ], "schema:isPartOf": { @@ -1656,10 +1682,10 @@ "rdfs:label": "SLE", "rdfs:subClassOf": [ { - "@id": "bts:Diagnosis" + "@id": "bts:Project" }, { - "@id": "bts:Project" + "@id": "bts:Diagnosis" } ], "schema:isPartOf": { @@ -1687,10 +1713,10 @@ "sms:validationRules": [] }, { - "@id": "bts:V-CoRT", + "@id": "bts:UMassV-CoRT", "@type": "rdfs:Class", "rdfs:comment": "TBD", - "rdfs:label": "V-CoRT", + "rdfs:label": "UMassV-CoRT", "rdfs:subClassOf": [ { "@id": "bts:Project" @@ -1699,7 +1725,7 @@ "schema:isPartOf": { "@id": "http://schema.biothings.io" }, - "sms:displayName": "V-CoRT", + "sms:displayName": "UMass V-CoRT", "sms:required": "sms:false", "sms:validationRules": [] }, @@ -3955,6 +3981,9 @@ { "@id": "bts:CellRangerOutput" }, + { + "@id": "bts:Diagnosis" + }, { "@id": "bts:Platform" } @@ -4075,10 +4104,10 @@ "rdfs:label": "Unknown", "rdfs:subClassOf": [ { - "@id": "bts:Ethnicity" + "@id": "bts:SpecimenModality" }, { - "@id": "bts:AlignmentReference" + "@id": "bts:Ethnicity" }, { "@id": "bts:SynovialCollectionProcedure" @@ -4089,6 +4118,9 @@ { "@id": "bts:DiabetesType" }, + { + "@id": "bts:AlignmentReference" + }, { "@id": "bts:Race" }, @@ -4128,6 +4160,9 @@ }, { "@id": "bts:Singlespecimen" + }, + { + "@id": "bts:Unknown" } ], "sms:displayName": "specimenModality", @@ -6595,6 +6630,9 @@ { "@id": "bts:10xCellRangerHumanGRCh382024-A" }, + { + "@id": "bts:GRCh38" + }, { "@id": "bts:ModifiedGRCh38" }, @@ -6643,6 +6681,23 @@ "sms:required": "sms:false", "sms:validationRules": [] }, + { + "@id": "bts:GRCh38", + "@type": "rdfs:Class", + "rdfs:comment": "TBD", + "rdfs:label": "GRCh38", + "rdfs:subClassOf": [ + { + "@id": "bts:AlignmentReference" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "GRCh38", + "sms:required": "sms:false", + "sms:validationRules": [] + }, { "@id": "bts:ModifiedGRCh38", "@type": "rdfs:Class", @@ -6725,7 +6780,7 @@ "@id": "bts:10xGEM-XFlexGeneExpressionHuman" }, { - "@id": "bts:10xGEM-XUniversal5?GeneExpressionv3" + "@id": "bts:10xGEM-XUniversal5'GeneExpressionv3" }, { "@id": "bts:CEL-Seq2" @@ -6977,10 +7032,10 @@ "sms:validationRules": [] }, { - "@id": "bts:10xGEM-XUniversal5?GeneExpressionv3", + "@id": "bts:10xGEM-XUniversal5'GeneExpressionv3", "@type": "rdfs:Class", "rdfs:comment": "TBD", - "rdfs:label": "10xGEM-XUniversal5?GeneExpressionv3", + "rdfs:label": "10xGEM-XUniversal5'GeneExpressionv3", "rdfs:subClassOf": [ { "@id": "bts:LibraryPrepMethod" @@ -6989,7 +7044,7 @@ "schema:isPartOf": { "@id": "http://schema.biothings.io" }, - "sms:displayName": "10x GEM-X Universal 5? Gene Expression v3", + "sms:displayName": "10x GEM-X Universal 5' Gene Expression v3", "sms:required": "sms:false", "sms:validationRules": [] }, @@ -8051,25 +8106,6 @@ "sms:required": "sms:false", "sms:validationRules": [] }, - { - "@id": "bts:DbGapAccession", - "@type": "rdfs:Class", - "rdfs:comment": "NIH policy requires large-scale human genomics studies to be registered in dbGap. This is a Dataset-specific attribute indicating the unique identifier (i.e., accession) of the corresponding study that is registered in dbGap, formatted as a compact URI, e.g., dbgap:phs003417.v2.p1", - "rdfs:label": "DbGapAccession", - "rdfs:subClassOf": [ - { - "@id": "bts:Thing" - } - ], - "schema:isPartOf": { - "@id": "http://schema.biothings.io" - }, - "sms:displayName": "dbGapAccession", - "sms:required": "sms:false", - "sms:validationRules": [ - "regex search ^dbgap:" - ] - }, { "@id": "bts:At-RiskRA", "@type": "rdfs:Class", @@ -8155,6 +8191,23 @@ "sms:required": "sms:false", "sms:validationRules": [] }, + { + "@id": "bts:Discoidlupuserythematosus", + "@type": "rdfs:Class", + "rdfs:comment": "TBD", + "rdfs:label": "Discoidlupuserythematosus", + "rdfs:subClassOf": [ + { + "@id": "bts:Diagnosis" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "discoid lupus erythematosus", + "sms:required": "sms:false", + "sms:validationRules": [] + }, { "@id": "bts:Lupusnephritis", "@type": "rdfs:Class", @@ -9034,7 +9087,7 @@ "rdfs:label": "Mixed", "rdfs:subClassOf": [ { - "@id": "bts:VitiligoType" + "@id": "bts:VitiligoPattern" } ], "schema:isPartOf": { @@ -9051,7 +9104,7 @@ "rdfs:label": "Non-segmental", "rdfs:subClassOf": [ { - "@id": "bts:VitiligoType" + "@id": "bts:VitiligoPattern" } ], "schema:isPartOf": { @@ -9068,7 +9121,7 @@ "rdfs:label": "Segmental", "rdfs:subClassOf": [ { - "@id": "bts:VitiligoType" + "@id": "bts:VitiligoPattern" } ], "schema:isPartOf": { @@ -9085,7 +9138,7 @@ "rdfs:label": "Unclassified", "rdfs:subClassOf": [ { - "@id": "bts:VitiligoType" + "@id": "bts:VitiligoPattern" } ], "schema:isPartOf": { @@ -10720,6 +10773,42 @@ "sms:displayName": "altSampleID", "sms:required": "sms:false", "sms:validationRules": [] + }, + { + "@id": "bts:SampleCollectionBatch", + "@type": "rdfs:Class", + "rdfs:comment": "A label indicating batching of sample collection or experiment execution that occurs prior to data collection.", + "rdfs:label": "SampleCollectionBatch", + "rdfs:subClassOf": [ + { + "@id": "bts:Thing" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "sampleCollectionBatch", + "sms:required": "sms:false", + "sms:validationRules": [] + }, + { + "@id": "bts:AssociatedAccession", + "@type": "rdfs:Class", + "rdfs:comment": "This is a File and Dataset annotation attribute indicating additional accessions (i.e., unique identifiers) associated with the data when the data has also been submitted to or can be found in other repositories such as GEO, SRA, dbGaP, etc.", + "rdfs:label": "AssociatedAccession", + "rdfs:subClassOf": [ + { + "@id": "bts:Thing" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "associatedAccession", + "sms:required": "sms:false", + "sms:validationRules": [ + "list like error" + ] } ], "@id": "http://schema.biothings.io/#0.1" diff --git a/model_contexts/fastq/ark.fastq_context.csv b/model_contexts/fastq/ark.fastq_context.csv index d6839ea..a73ac3d 100644 --- a/model_contexts/fastq/ark.fastq_context.csv +++ b/model_contexts/fastq/ark.fastq_context.csv @@ -1,13 +1,13 @@ -Attribute,Description,Valid Values,DependsOn,Properties,Required,Parent,DependsOn Component,Source,Validation Rules,columnType -Fastq File Annotation Template,A template outlining metadata to be collected and applied to fastq file entities as annotations in Synapse.,,"Component, fileFormat, specimenModality, readLength, assay",,,,,,, -BDM Fastq File Annotations,,,"Component, fileFormat, resourceType, assay, specimenModality, readLength, parentBiospecimenID, biospecimenType, biospecimenSubtype, dataType, dataSubtype, diagnosis, libraryPrepMethod, nucleicAcidSource, platform, program, project, species",,,,,,, -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, individualID",,,,,,, -resourceType,,experimental data,,,TRUE,,,,,string -fileFormat,,fastq,,,TRUE,,,,,string -dataLevel,,1,,,TRUE,,,,,string -feature barcode sequencing,Is a valid value of `assay` that triggers conditional dependencies for additional attributes.,,"targetPanel, targetPanelSynID, targetPanelSize",,,,,,, -assay,"The technology used to generate the data in this file. Select all assays that apply. e.g., the GEX fastq files from a CITE-seq experiment should be labeled with both 'scRNASeq' and 'CITESeq'.","scRNASeq, CITESeq, snRNASeq, snATACSeq, RNASeq, ASAPSeq, VDJSeq, scVDJSeq, feature barcode sequencing, WES, WGS",,,TRUE,,,,list like error,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.","Illumina NovaSeq 6000, Illumina HiSeq X Ten, Illumina NextSeq 500, Illumina NovaSeq X, Illumina HiSeq 2500, Chromium X, Chromium Next GEM Chip M, GEM-X Flex Gene Expression Chip, GEM-X OCM 5' Chip, Chromium Next GEM Chip G, Chromium GEM-X Single Cell 3' Chip v4, Chromium Xo, Chromium Next GEM Chip H, Chromium Controller, Chromium Next GEM Chip K, Chromium Next GEM Chip Q, Chromium iX, unknown",,,TRUE,,,,list like error,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,,,,,,, -AMP AIM,Accelerating Medicines Partnership Autoimmune and Immune-Mediated Diseases. Is a valid value for 'program' that triggers conditional dependencies for additional attributes.,,visitID,,,,,,, \ No newline at end of file +"Attribute","Description","Valid Values","DependsOn","Properties","Required","Parent","DependsOn Component","Source","Validation Rules","columnType" +"Fastq File Annotation Template","A template outlining metadata to be collected and applied to fastq file entities as annotations in Synapse.","","Component, fileFormat, specimenModality, readLength, assay","","","","","","","" +"BDM Fastq File Annotations","A template outlining metadata to be collected and applied to fastq file entities as annotations in Synapse by BDM team as part of data release process.","","Component, fileFormat, resourceType, assay, specimenModality, readLength, parentBiospecimenID, biospecimenType, biospecimenSubtype, dataType, dataSubtype, diagnosis, libraryPrepMethod, nucleicAcidSource, platform, program, project, species, primaryCellSource, cellType, userDefinedCellType","","","","","","","" +"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, individualID","","","","","","","" +"resourceType","","experimental data","","","TRUE","","","","","string" +"fileFormat","","fastq","","","TRUE","","","","","string" +"dataLevel","","1","","","TRUE","","","","","string" +"feature barcode sequencing","Is a valid value of `assay` that triggers conditional dependencies for additional attributes.","","targetPanel, targetPanelSynID, targetPanelSize","","","","","","","" +"assay","The technology used to generate the data in this file. Select all assays that apply. e.g., the GEX fastq files from a CITE-seq experiment should be labeled with both 'scRNASeq' and 'CITESeq'.","scRNASeq, CITESeq, snRNASeq, snATACSeq, RNASeq, ASAPSeq, VDJSeq, scVDJSeq, feature barcode sequencing, WES, WGS","","","TRUE","","","","list like error","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.","Illumina NovaSeq 6000, Illumina HiSeq X Ten, Illumina NextSeq 500, Illumina NovaSeq X, Illumina HiSeq 2500, Chromium X, Chromium Next GEM Chip M, GEM-X Flex Gene Expression Chip, GEM-X OCM 5' Chip, Chromium Next GEM Chip G, Chromium GEM-X Single Cell 3' Chip v4, Chromium Xo, Chromium Next GEM Chip H, Chromium Controller, Chromium Next GEM Chip K, Chromium Next GEM Chip Q, Chromium iX, unknown","","","TRUE","","","","list like error","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","","","","","","","" +"AMP AIM","Accelerating Medicines Partnership Autoimmune and Immune-Mediated Diseases. Is a valid value for 'program' that triggers conditional dependencies for additional attributes.","","visitID","","","","","","","" diff --git a/model_contexts/fastq/ark.fastq_model.csv b/model_contexts/fastq/ark.fastq_model.csv index acf53d7..e3b6937 100644 --- a/model_contexts/fastq/ark.fastq_model.csv +++ b/model_contexts/fastq/ark.fastq_model.csv @@ -1,6 +1,6 @@ "Attribute","Description","Valid Values","DependsOn","Properties","Required","Parent","DependsOn Component","Source","Validation Rules","columnType" "Fastq File Annotation Template","A template outlining metadata to be collected and applied to fastq file entities as annotations in Synapse.","","Component, fileFormat, specimenModality, readLength, assay","","","","","","","" -"BDM Fastq File Annotations","","","Component, fileFormat, resourceType, assay, specimenModality, readLength, parentBiospecimenID, biospecimenType, biospecimenSubtype, dataType, dataSubtype, diagnosis, libraryPrepMethod, nucleicAcidSource, platform, program, project, species","","","","","","","" +"BDM Fastq File Annotations","A template outlining metadata to be collected and applied to fastq file entities as annotations in Synapse by BDM team as part of data release process.","","Component, fileFormat, resourceType, assay, specimenModality, readLength, parentBiospecimenID, biospecimenType, biospecimenSubtype, dataType, dataSubtype, diagnosis, libraryPrepMethod, nucleicAcidSource, platform, program, project, species, primaryCellSource, cellType, userDefinedCellType","","","","","","","" "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, individualID","","","","","","","" "resourceType","High-level classification of the file content","experimental data","","","TRUE","","","","","string" @@ -15,13 +15,13 @@ "publicationSynID","The synID of the corresponding Synapse entity that stores metadata about the publication. This is used to differentiate publication-specific files, often consisting of level 4 processed data and expanded subject metadata, in a publication dataset that also includes raw or minimally processed files from experimental datasets. This provides an easy way to distinguish and select for the publication-specific data from which the research findings were derived. When this attribute is used to annotate a Dataset it serves as a way to directly link the Dataset entity with the publication metadata stored in Synapse.","","","","False","","","","regex search ^syn[0-9]{8} error","string" "associatedDataset","The synID of a Dataset entity. This serves to link other Synapse entities to Dataset entities. When used to annotate a publication Dataset this attribute should include the synID for an experimental Datasets from which the publication data was derived. Multiple synID can be specified using a comma-delimited list.","","","","False","","","","list like::regex search ^syn[0-9]{8} error","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, ELLIPSS, LOCKIT, RA, SLE, STAMP, V-CoRT","","","True","","","","list like error","string" +"project","A sub-level attribute of `program` specifying a research initiative working to investigate particular hypotheses.","AIM for RA, ELLIPSS, LOCKIT, RA, SLE, STAMP, UMass V-CoRT","","","True","","","","list like error","string" "programPhase","A label noting which AMP RA/SLE program phase generated the data.","I, II","","","True","","","","list like error","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" "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" "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" "custom10xProbeSetSynID","If custom modified probe sets were used for collecting 10x Chromium Flex scRNA-seq data, then the probe reference files should be grouped as a zip or tar archive and uploaded as metadata. This attribute links the experimental data back to the probe set archive file via a synapse ID.","","","","True","","","","regex search ^syn[0-9]{8} error","string" -"specimenModality","Label assigned to experimental data files indicating whether the data contained corresponds to a single or multiple biospecimens","multispecimen, single specimen","","","True","","","","","string" +"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" "individualID","Unique identifier assigned to each study participant. For multi-specimen data files provide all IDs in a comma-separated list.","","","","True","","","","#ClinicalMetadataTemplate unique error^^#BiospecimenMetadataTemplate str^^list like error","string" "biospecimenID","A unique identifier assigned to specimens collected from study participants. For multi-specimen data files provide all IDs in a comma-separated list.","","","","True","","","","#BiospecimenMetadataTemplate unique error^^list like error","string" "parentBiospecimenID","The biospecimenID associated with the originating biospecimen for derived or child biospecimens.","","","","False","","","","","string" @@ -37,15 +37,14 @@ "nucleicAcidSource","The source of the nucleic acid used as input for sequencing library fragments. Select all that apply, though in most cases only a single label is expected.","BCR mRNA, CRISPR protospacer feature barcode, TCR mRNA, Tn5-accessible gDNA, antigen capture barcode, gDNA, globin-depleted RNA, intracellular protein feature barcode, multiplexing oligo, poly(A) RNA, rRNA-depleted RNA, surface protein feature barcode","","","True","","","","list like error","string" "biospecimenSubtype","Biospecimen status before sample is processed into a scRNA-seq library. Several scRNA-seq technologies support a variety of sample processing methods which can introduces sources of technical variation.","FFPE tissue, PFA-fixed tissue, cell or tissue lysate, cell suspension, flow-sorted cells, fresh tissue, frozen tissue, nuclei suspension, supernatant","","","False","","","","","string" "cellRangerOutput","10x Genomics Cell Ranger software output several different counts results and formats, some with different processing applied. This label distinguishes between these types and is particularly helpful when multiple files are uploaded with the sample name, e.g., barcodes.tsv.gz","Not Applicable, filtered MEX, filtered_feature_bc_matrix, filtered_peak_bc_matrix, raw MEX, raw_feature_bc_matrix, raw_peak_bc_matrix","","","True","","","","","string" -"alignmentReference","The genomic/transcriptomic reference used for performing read alignment against.","10x Cell Ranger Human GRCh38 2020-A, 10x Cell Ranger Human GRCh38 2024-A, modified GRCh38, unknown, vdj_GRCh38_alts_ensembl-4.0.0","","","True","","","","","string" -"libraryPrepMethod","Sequencing library preparation method or kit used to create the library. If no commercially available kit was used, please select 'in-house library prep'.","10x Chromium Fixed RNA Human Transcriptome, 10x Chromium GEM-X Single Cell 3' v4, 10x Chromium GEM-X Single Cell 5' v3, 10x Chromium Next GEM Single Cell 3', 10x Chromium Next GEM Single Cell 3' 3.1, 10x Chromium Next GEM Single Cell 5' v1.1, 10x Chromium Next GEM Single Cell 5' v2, 10x Chromium Next GEM Single Cell ATAC v2, 10x Chromium Single Cell Human BCR, 10x Chromium Single Cell Human TCR, 10x GEM-X Flex Gene Expression Human, 10x GEM-X Universal 5? Gene Expression v3, CEL-Seq2, Chromium Next GEM Single Cell ATAC v1.1, Fluidigm C1 HT, NEBNext Human Immune Sequencing Kit, NEBNext Ultra II Directional RNA Library, Nextera XT, Nextera XT DNA, QIAseq miRNA Library, SMART-Seq Human BCR with UMI, SMART-Seq Human TCR with UMI, SMART-Seq v4 Ultra Low Input RNA, SMARTer Stranded Total RNA v2, Takara Human BCR profiling for Illumina, Takara Human TCR profiling for Illumina, Takara Human TCRv2 profiling for Illumina, Takara Human scTCR profiling for Illumina, TruSeq Stranded mRNA, custom DASH-treatment, in-house library prep","","","True","","","","","string" +"alignmentReference","The genomic/transcriptomic reference used for performing read alignment against.","10x Cell Ranger Human GRCh38 2020-A, 10x Cell Ranger Human GRCh38 2024-A, GRCh38, modified GRCh38, unknown, vdj_GRCh38_alts_ensembl-4.0.0","","","True","","","","","string" +"libraryPrepMethod","Sequencing library preparation method or kit used to create the library. If no commercially available kit was used, please select 'in-house library prep'.","10x Chromium Fixed RNA Human Transcriptome, 10x Chromium GEM-X Single Cell 3' v4, 10x Chromium GEM-X Single Cell 5' v3, 10x Chromium Next GEM Single Cell 3', 10x Chromium Next GEM Single Cell 3' 3.1, 10x Chromium Next GEM Single Cell 5' v1.1, 10x Chromium Next GEM Single Cell 5' v2, 10x Chromium Next GEM Single Cell ATAC v2, 10x Chromium Single Cell Human BCR, 10x Chromium Single Cell Human TCR, 10x GEM-X Flex Gene Expression Human, 10x GEM-X Universal 5' Gene Expression v3, CEL-Seq2, Chromium Next GEM Single Cell ATAC v1.1, Fluidigm C1 HT, NEBNext Human Immune Sequencing Kit, NEBNext Ultra II Directional RNA Library, Nextera XT, Nextera XT DNA, QIAseq miRNA Library, SMART-Seq Human BCR with UMI, SMART-Seq Human TCR with UMI, SMART-Seq v4 Ultra Low Input RNA, SMARTer Stranded Total RNA v2, Takara Human BCR profiling for Illumina, Takara Human TCR profiling for Illumina, Takara Human TCRv2 profiling for Illumina, Takara Human scTCR profiling for Illumina, TruSeq Stranded mRNA, custom DASH-treatment, in-house library prep","","","True","","","","","string" "datasetType","High-level classification of dataset entity distinguishing between datasets compiled for a specific publication or as a general data resource.","experimental, publication","","","True","","","","","string" "acknowledgmentStatement","A Dataset-specific attribute specifying the path to the wiki subpage within the ARK Portal - backend project that contains the acknowledgement statement that must be included in publications using data from the given dataset as a stipulation of the conditions of use.","syn26710600/wiki/619685","","","True","","","","","string" "datasetDescription","A Dataset-specific attribute specifying the synID of the folder that contains a wiki write-up of the dataset description. This wiki content will be surfaced on the ARK Portal frontend site.","","","","True","","","","regex search ^syn[0-9]{8} error","string" "ARKRelease","A Dataset-specific attribute specifying the ARK Portal release in which this dataset was first made available to the public.","1.0, 2.0, 2024.06.R1, 2024.07.R1, 2024.08.R1, 2024.09.R1, 2024.10.R1, 2024.12.R1, 2025.01.R1, 2025.02.R1, 2025.03.R1, 2025.04.R1, 2025.05.R1, 2025.06.R1, 2025.07.R1, 2025.08.R1, 2025.09.R1, 2025.10.R1, 2025.11.R1, 2025.12.R1","","","True","","","","","string" "RObjectClass","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.","ROCR prediction.object, Seurat object, SummarizedExperiment, Symphony reference, data.frame, list, matrix, sparse matrix, vector","","","False","","","","","string" -"dbGapAccession","NIH policy requires large-scale human genomics studies to be registered in dbGap. This is a Dataset-specific attribute indicating the unique identifier (i.e., accession) of the corresponding study that is registered in dbGap, formatted as a compact URI, e.g., dbgap:phs003417.v2.p1","","","","False","","","","regex search ^dbgap:","string" -"diagnosis","A high-level classifier indicating the disease status of an individual.","At-Risk RA, OA, RA, SLE, Sjogren's disease, control, cutaneous lupus erythematosus, dermatomyositis, lupus nephritis, psoriasis, psoriatic arthritis, scleroderma, unknown, vitiligo","","","True","","","","list like error","string" +"diagnosis","A high-level classifier indicating the disease status of an individual.","At-Risk RA, Not Applicable, OA, RA, SLE, Sjogren's disease, control, cutaneous lupus erythematosus, dermatomyositis, discoid lupus erythematosus, lupus nephritis, psoriasis, psoriatic arthritis, scleroderma, unknown, vitiligo","","","True","","","","list like error","string" "DOID","Disease ontology identifier associated with `diagnosis`. Attribute values are applied by ARK Portal data managers.","","","","True","","","","regex search ^DOID error","string" "libraryID","A library label or name, unique within an experiment, used to distinguish sequencing libraries.","","","","True","","","","","string" "associatedCodeURL","A URL to the repository where associated code is available.","","","","False","","","","","string" @@ -62,7 +61,7 @@ "PMID","PubMed(R) Identifier","","","","True","","","","regex search ^PMID error","string" "DOI","Digital object identifier","","","","True","","","","","string" "anatomicalSite","The anatomical site, i.e., location on or within the body, from which the biospecimen was collected. This attribute is required depending on the value selected for biospecimenType.","left 2nd MCP joint, left ankle joint, left hip joint, left knee joint, left wrist joint, other site, right 1st MTP joint, right 2nd MCP joint, right 2nd MTP joint, right 3rd MCP joint, right ankle joint, right hip joint, right knee joint, right wrist joint, unknown","","","True","","","","","string" -"vitiligoType","A high-level classification of vitiligo based on the distribution and patterning of lesions across the body.","mixed, non-segmental, segmental, unclassified","","","False","","","","","string" +"vitiligoPattern","A high-level classification of vitiligo based on the distribution and patterning of lesions across the body.","mixed, non-segmental, segmental, unclassified","","","False","","","","","string" "vitiligoPhenotype","Classification of vitiligo lesions which correlate with autoimmune activity and result in specific skin and depigmentation manifestations at the lesion site. If N/A please select 'none'. Multiple selections can be provided in a comma-delimited list.","active, confetti, inflammatory, none, trichrome","","","True","","","","list like error","string" "psoriasisType","General type classification of psoriasis disease manifestation.","erythrodermic, guttate, inverse, plaque, pustular","","","False","","","","","string" "ageDiagnosis","Age at which subject was diagnosed with `diagnosis`. If providing this value be sure the unit matches that used for `age`.","","","","False","","","","num error","number" @@ -113,3 +112,5 @@ "treatmentTimepoint","Where applicable, specify the timepoint relative to treatment to distinguish different sets of samples that have undergone the same treatment but for different lengths of time. REQUIRED: please specify the unit of time, e.g., secs, mins, hrs, days, etc.","","","","False","","","","","string" "slideID","A distinct label or name, unique within an experiment, assigned to an imaging slides.","","","","True","","","","","string" "altSampleID","An alternate identifier for a sample. With some assays there can be default or alternate sample identifiers entered into the data collection software. If you will be uploading data collected with an alternate identifier please provide that here. In some cases, the ARK BDM team will use this field to capture original but out-dated identifiers for samples.","","","","False","","","","","string" +"sampleCollectionBatch","A label indicating batching of sample collection or experiment execution that occurs prior to data collection.","","","","False","","","","","string" +"associatedAccession","This is a File and Dataset annotation attribute indicating additional accessions (i.e., unique identifiers) associated with the data when the data has also been submitted to or can be found in other repositories such as GEO, SRA, dbGaP, etc.","","","","False","","","","list like error","string" diff --git a/model_contexts/fastq/ark.fastq_model.jsonld b/model_contexts/fastq/ark.fastq_model.jsonld index 87c2230..443ef91 100644 --- a/model_contexts/fastq/ark.fastq_model.jsonld +++ b/model_contexts/fastq/ark.fastq_model.jsonld @@ -99,6 +99,9 @@ }, { "@id": "bts:Singlespecimen" + }, + { + "@id": "bts:Unknown" } ], "sms:displayName": "specimenModality", @@ -181,7 +184,7 @@ { "@id": "bts:BDMFastqFileAnnotations", "@type": "rdfs:Class", - "rdfs:comment": "TBD", + "rdfs:comment": "A template outlining metadata to be collected and applied to fastq file entities as annotations in Synapse by BDM team as part of data release process.", "rdfs:label": "BDMFastqFileAnnotations", "rdfs:subClassOf": [ { @@ -247,6 +250,15 @@ }, { "@id": "bts:Species" + }, + { + "@id": "bts:PrimaryCellSource" + }, + { + "@id": "bts:CellType" + }, + { + "@id": "bts:UserDefinedCellType" } ], "sms:validationRules": [] @@ -535,6 +547,9 @@ { "@id": "bts:At-RiskRA" }, + { + "@id": "bts:NotApplicable" + }, { "@id": "bts:OA" }, @@ -556,6 +571,9 @@ { "@id": "bts:Dermatomyositis" }, + { + "@id": "bts:Discoidlupuserythematosus" + }, { "@id": "bts:Lupusnephritis" }, @@ -629,7 +647,7 @@ "@id": "bts:10xGEM-XFlexGeneExpressionHuman" }, { - "@id": "bts:10xGEM-XUniversal5?GeneExpressionv3" + "@id": "bts:10xGEM-XUniversal5'GeneExpressionv3" }, { "@id": "bts:CEL-Seq2" @@ -886,7 +904,7 @@ "@id": "bts:STAMP" }, { - "@id": "bts:V-CoRT" + "@id": "bts:UMassV-CoRT" } ], "sms:displayName": "project", @@ -917,6 +935,89 @@ "sms:required": "sms:true", "sms:validationRules": [] }, + { + "@id": "bts:PrimaryCellSource", + "@type": "rdfs:Class", + "rdfs:comment": "A label indicating the biological source material from which a primary cell culture was derived.", + "rdfs:label": "PrimaryCellSource", + "rdfs:subClassOf": [ + { + "@id": "bts:Thing" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "schema:rangeIncludes": [ + { + "@id": "bts:PBMCs" + }, + { + "@id": "bts:Kidney" + }, + { + "@id": "bts:Pannus-deriveddermis" + }, + { + "@id": "bts:Pannus-derivedepidermis" + }, + { + "@id": "bts:Salivarygland" + }, + { + "@id": "bts:Synovialtissue" + }, + { + "@id": "bts:Totalleukocytes" + }, + { + "@id": "bts:Urine" + }, + { + "@id": "bts:Uvea" + }, + { + "@id": "bts:Wholeblood" + } + ], + "sms:displayName": "primaryCellSource", + "sms:required": "sms:true", + "sms:validationRules": [] + }, + { + "@id": "bts:CellType", + "@type": "rdfs:Class", + "rdfs:comment": "The cell type name from Cell Ontology for the corresponding CL identifier.", + "rdfs:label": "CellType", + "rdfs:subClassOf": [ + { + "@id": "bts:Thing" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "cellType", + "sms:required": "sms:false", + "sms:validationRules": [] + }, + { + "@id": "bts:UserDefinedCellType", + "@type": "rdfs:Class", + "rdfs:comment": "User-defined label of a cell type. Contributors are provided this option to use preferred or custom cell type labels that may vary from options and standards set by Cell Ontology.", + "rdfs:label": "UserDefinedCellType", + "rdfs:subClassOf": [ + { + "@id": "bts:Thing" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "userDefinedCellType", + "sms:required": "sms:false", + "sms:validationRules": [] + }, { "@id": "bts:Multispecimen", "@type": "rdfs:Class", @@ -1644,10 +1745,10 @@ "rdfs:label": "Unknown", "rdfs:subClassOf": [ { - "@id": "bts:Ethnicity" + "@id": "bts:SpecimenModality" }, { - "@id": "bts:AlignmentReference" + "@id": "bts:Ethnicity" }, { "@id": "bts:SynovialCollectionProcedure" @@ -1658,6 +1759,9 @@ { "@id": "bts:DiabetesType" }, + { + "@id": "bts:AlignmentReference" + }, { "@id": "bts:Race" }, @@ -1853,10 +1957,10 @@ "rdfs:label": "RA", "rdfs:subClassOf": [ { - "@id": "bts:Diagnosis" + "@id": "bts:Project" }, { - "@id": "bts:Project" + "@id": "bts:Diagnosis" } ], "schema:isPartOf": { @@ -1873,10 +1977,10 @@ "rdfs:label": "SLE", "rdfs:subClassOf": [ { - "@id": "bts:Diagnosis" + "@id": "bts:Project" }, { - "@id": "bts:Project" + "@id": "bts:Diagnosis" } ], "schema:isPartOf": { @@ -1904,10 +2008,10 @@ "sms:validationRules": [] }, { - "@id": "bts:V-CoRT", + "@id": "bts:UMassV-CoRT", "@type": "rdfs:Class", "rdfs:comment": "TBD", - "rdfs:label": "V-CoRT", + "rdfs:label": "UMassV-CoRT", "rdfs:subClassOf": [ { "@id": "bts:Project" @@ -1916,7 +2020,7 @@ "schema:isPartOf": { "@id": "http://schema.biothings.io" }, - "sms:displayName": "V-CoRT", + "sms:displayName": "UMass V-CoRT", "sms:required": "sms:false", "sms:validationRules": [] }, @@ -2792,55 +2896,6 @@ "sms:required": "sms:false", "sms:validationRules": [] }, - { - "@id": "bts:PrimaryCellSource", - "@type": "rdfs:Class", - "rdfs:comment": "A label indicating the biological source material from which a primary cell culture was derived.", - "rdfs:label": "PrimaryCellSource", - "rdfs:subClassOf": [ - { - "@id": "bts:Thing" - } - ], - "schema:isPartOf": { - "@id": "http://schema.biothings.io" - }, - "schema:rangeIncludes": [ - { - "@id": "bts:PBMCs" - }, - { - "@id": "bts:Kidney" - }, - { - "@id": "bts:Pannus-deriveddermis" - }, - { - "@id": "bts:Pannus-derivedepidermis" - }, - { - "@id": "bts:Salivarygland" - }, - { - "@id": "bts:Synovialtissue" - }, - { - "@id": "bts:Totalleukocytes" - }, - { - "@id": "bts:Urine" - }, - { - "@id": "bts:Uvea" - }, - { - "@id": "bts:Wholeblood" - } - ], - "sms:displayName": "primaryCellSource", - "sms:required": "sms:true", - "sms:validationRules": [] - }, { "@id": "bts:Kidney", "@type": "rdfs:Class", @@ -4463,6 +4518,9 @@ "rdfs:subClassOf": [ { "@id": "bts:CellRangerOutput" + }, + { + "@id": "bts:Diagnosis" } ], "schema:isPartOf": { @@ -4594,6 +4652,9 @@ { "@id": "bts:10xCellRangerHumanGRCh382024-A" }, + { + "@id": "bts:GRCh38" + }, { "@id": "bts:ModifiedGRCh38" }, @@ -4642,6 +4703,23 @@ "sms:required": "sms:false", "sms:validationRules": [] }, + { + "@id": "bts:GRCh38", + "@type": "rdfs:Class", + "rdfs:comment": "TBD", + "rdfs:label": "GRCh38", + "rdfs:subClassOf": [ + { + "@id": "bts:AlignmentReference" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "GRCh38", + "sms:required": "sms:false", + "sms:validationRules": [] + }, { "@id": "bts:ModifiedGRCh38", "@type": "rdfs:Class", @@ -4864,10 +4942,10 @@ "sms:validationRules": [] }, { - "@id": "bts:10xGEM-XUniversal5?GeneExpressionv3", + "@id": "bts:10xGEM-XUniversal5'GeneExpressionv3", "@type": "rdfs:Class", "rdfs:comment": "TBD", - "rdfs:label": "10xGEM-XUniversal5?GeneExpressionv3", + "rdfs:label": "10xGEM-XUniversal5'GeneExpressionv3", "rdfs:subClassOf": [ { "@id": "bts:LibraryPrepMethod" @@ -4876,7 +4954,7 @@ "schema:isPartOf": { "@id": "http://schema.biothings.io" }, - "sms:displayName": "10x GEM-X Universal 5? Gene Expression v3", + "sms:displayName": "10x GEM-X Universal 5' Gene Expression v3", "sms:required": "sms:false", "sms:validationRules": [] }, @@ -5938,25 +6016,6 @@ "sms:required": "sms:false", "sms:validationRules": [] }, - { - "@id": "bts:DbGapAccession", - "@type": "rdfs:Class", - "rdfs:comment": "NIH policy requires large-scale human genomics studies to be registered in dbGap. This is a Dataset-specific attribute indicating the unique identifier (i.e., accession) of the corresponding study that is registered in dbGap, formatted as a compact URI, e.g., dbgap:phs003417.v2.p1", - "rdfs:label": "DbGapAccession", - "rdfs:subClassOf": [ - { - "@id": "bts:Thing" - } - ], - "schema:isPartOf": { - "@id": "http://schema.biothings.io" - }, - "sms:displayName": "dbGapAccession", - "sms:required": "sms:false", - "sms:validationRules": [ - "regex search ^dbgap:" - ] - }, { "@id": "bts:At-RiskRA", "@type": "rdfs:Class", @@ -6059,6 +6118,23 @@ "sms:required": "sms:false", "sms:validationRules": [] }, + { + "@id": "bts:Discoidlupuserythematosus", + "@type": "rdfs:Class", + "rdfs:comment": "TBD", + "rdfs:label": "Discoidlupuserythematosus", + "rdfs:subClassOf": [ + { + "@id": "bts:Diagnosis" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "discoid lupus erythematosus", + "sms:required": "sms:false", + "sms:validationRules": [] + }, { "@id": "bts:Lupusnephritis", "@type": "rdfs:Class", @@ -6952,10 +7028,10 @@ "sms:validationRules": [] }, { - "@id": "bts:VitiligoType", + "@id": "bts:VitiligoPattern", "@type": "rdfs:Class", "rdfs:comment": "A high-level classification of vitiligo based on the distribution and patterning of lesions across the body.", - "rdfs:label": "VitiligoType", + "rdfs:label": "VitiligoPattern", "rdfs:subClassOf": [ { "@id": "bts:Thing" @@ -6978,7 +7054,7 @@ "@id": "bts:Unclassified" } ], - "sms:displayName": "vitiligoType", + "sms:displayName": "vitiligoPattern", "sms:required": "sms:false", "sms:validationRules": [] }, @@ -6989,7 +7065,7 @@ "rdfs:label": "Mixed", "rdfs:subClassOf": [ { - "@id": "bts:VitiligoType" + "@id": "bts:VitiligoPattern" } ], "schema:isPartOf": { @@ -7006,7 +7082,7 @@ "rdfs:label": "Non-segmental", "rdfs:subClassOf": [ { - "@id": "bts:VitiligoType" + "@id": "bts:VitiligoPattern" } ], "schema:isPartOf": { @@ -7023,7 +7099,7 @@ "rdfs:label": "Segmental", "rdfs:subClassOf": [ { - "@id": "bts:VitiligoType" + "@id": "bts:VitiligoPattern" } ], "schema:isPartOf": { @@ -7040,7 +7116,7 @@ "rdfs:label": "Unclassified", "rdfs:subClassOf": [ { - "@id": "bts:VitiligoType" + "@id": "bts:VitiligoPattern" } ], "schema:isPartOf": { @@ -8425,40 +8501,6 @@ "regex search ^CL: error" ] }, - { - "@id": "bts:CellType", - "@type": "rdfs:Class", - "rdfs:comment": "The cell type name from Cell Ontology for the corresponding CL identifier.", - "rdfs:label": "CellType", - "rdfs:subClassOf": [ - { - "@id": "bts:Thing" - } - ], - "schema:isPartOf": { - "@id": "http://schema.biothings.io" - }, - "sms:displayName": "cellType", - "sms:required": "sms:false", - "sms:validationRules": [] - }, - { - "@id": "bts:UserDefinedCellType", - "@type": "rdfs:Class", - "rdfs:comment": "User-defined label of a cell type. Contributors are provided this option to use preferred or custom cell type labels that may vary from options and standards set by Cell Ontology.", - "rdfs:label": "UserDefinedCellType", - "rdfs:subClassOf": [ - { - "@id": "bts:Thing" - } - ], - "schema:isPartOf": { - "@id": "http://schema.biothings.io" - }, - "sms:displayName": "userDefinedCellType", - "sms:required": "sms:false", - "sms:validationRules": [] - }, { "@id": "bts:KrennInflammatory", "@type": "rdfs:Class", @@ -9097,6 +9139,42 @@ "sms:displayName": "altSampleID", "sms:required": "sms:false", "sms:validationRules": [] + }, + { + "@id": "bts:SampleCollectionBatch", + "@type": "rdfs:Class", + "rdfs:comment": "A label indicating batching of sample collection or experiment execution that occurs prior to data collection.", + "rdfs:label": "SampleCollectionBatch", + "rdfs:subClassOf": [ + { + "@id": "bts:Thing" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "sampleCollectionBatch", + "sms:required": "sms:false", + "sms:validationRules": [] + }, + { + "@id": "bts:AssociatedAccession", + "@type": "rdfs:Class", + "rdfs:comment": "This is a File and Dataset annotation attribute indicating additional accessions (i.e., unique identifiers) associated with the data when the data has also been submitted to or can be found in other repositories such as GEO, SRA, dbGaP, etc.", + "rdfs:label": "AssociatedAccession", + "rdfs:subClassOf": [ + { + "@id": "bts:Thing" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "associatedAccession", + "sms:required": "sms:false", + "sms:validationRules": [ + "list like error" + ] } ], "@id": "http://schema.biothings.io/#0.1" diff --git a/model_contexts/fcs/ark.fcs_context.csv b/model_contexts/fcs/ark.fcs_context.csv index fb84d6f..4071342 100644 --- a/model_contexts/fcs/ark.fcs_context.csv +++ b/model_contexts/fcs/ark.fcs_context.csv @@ -1,11 +1,11 @@ -Attribute,Description,Valid Values,DependsOn,Properties,Required,Parent,DependsOn Component,Source,Validation Rules,columnType -FCS File Annotation Template,A template outlining metadata to be collected and applied to FCS file entities as annotations in Synapse.,,"Component, fileFormat, specimenModality, assay, eventCount",,,,,,, -BDM FCS File Annotations,A template outlining metadata to be collected and applied to FCS file entities as annotations in Synapse by BDM team as part of data release process.,,"Component, fileFormat, resourceType, assay, specimenModality, eventCount, parentBiospecimenID, biospecimenType, biospecimenSubtype, dataType, dataSubtype, diagnosis, platform, sampleProcessingBatch, dataCollectionBatch, program, project, species",,,,,,, -multispecimen,Is a valid value of `specimenModality` that triggers conditional dependencies for additional attributes.,,"sampleProcessingBatch, dataCollectionBatch",,,,,,, -single specimen,Is a valid value of `specimenModality` that triggers conditional dependencies for additional attributes.,,"biospecimenID, individualID",,,,,,, -resourceType,,experimental data,,,TRUE,,,,,string -fileFormat,,fcs,,,,,,,,string -assay,The technology used to generate the data in this file.,"CyTOF, flow cytometry",,,TRUE,,,,,string -platform,"The specific version (manufacturer, model, etc.) of a technology that is used to carry out a laboratory or computational experiment.","Cytek Aurora, Cytek Aurora Evo, BD FACSDiscover S8, BD FACSymphony S6, BD FACSMelody, BD FACSAria III, BD FACSCanto, BD FACSLyric Clinical, BD FACSCanto II, BD FACSDiscover A8, Thermo Fisher Attune Xenith, Thermo Fisher Attune CytPix, Thermo Fisher Attune NxT, Sony MA900, BD LSRFortessa, unknown",,,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,,,,,,, -AMP AIM,Accelerating Medicines Partnership Autoimmune and Immune-Mediated Diseases. Is a valid value for 'program' that triggers conditional dependencies for additional attributes.,,visitID,,,,,,, \ No newline at end of file +"Attribute","Description","Valid Values","DependsOn","Properties","Required","Parent","DependsOn Component","Source","Validation Rules","columnType" +"FCS File Annotation Template","A template outlining metadata to be collected and applied to FCS file entities as annotations in Synapse.","","Component, fileFormat, specimenModality, assay, eventCount","","","","","","","" +"BDM FCS File Annotations","A template outlining metadata to be collected and applied to FCS file entities as annotations in Synapse by BDM team as part of data release process.","","Component, fileFormat, resourceType, assay, specimenModality, eventCount, parentBiospecimenID, biospecimenType, biospecimenSubtype, dataType, dataSubtype, diagnosis, platform, sampleProcessingBatch, dataCollectionBatch, program, project, species, primaryCellSource, cellType, userDefinedCellType","","","","","","","" +"multispecimen","Is a valid value of `specimenModality` that triggers conditional dependencies for additional attributes.","","sampleProcessingBatch, dataCollectionBatch","","","","","","","" +"single specimen","Is a valid value of `specimenModality` that triggers conditional dependencies for additional attributes.","","biospecimenID, individualID","","","","","","","" +"resourceType","","experimental data","","","TRUE","","","","","string" +"fileFormat","","fcs","","","","","","","","string" +"assay","The technology used to generate the data in this file.","CyTOF, flow cytometry","","","TRUE","","","","","string" +"platform","The specific version (manufacturer, model, etc.) of a technology that is used to carry out a laboratory or computational experiment.","Cytek Aurora, Cytek Aurora Evo, BD FACSDiscover S8, BD FACSymphony S6, BD FACSMelody, BD FACSAria III, BD FACSCanto, BD FACSLyric Clinical, BD FACSCanto II, BD FACSDiscover A8, Thermo Fisher Attune Xenith, Thermo Fisher Attune CytPix, Thermo Fisher Attune NxT, Sony MA900, BD LSRFortessa, unknown","","","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","","","","","","","" +"AMP AIM","Accelerating Medicines Partnership Autoimmune and Immune-Mediated Diseases. Is a valid value for 'program' that triggers conditional dependencies for additional attributes.","","visitID","","","","","","","" diff --git a/model_contexts/fcs/ark.fcs_model.csv b/model_contexts/fcs/ark.fcs_model.csv index 9887e20..f8e008d 100644 --- a/model_contexts/fcs/ark.fcs_model.csv +++ b/model_contexts/fcs/ark.fcs_model.csv @@ -1,6 +1,6 @@ "Attribute","Description","Valid Values","DependsOn","Properties","Required","Parent","DependsOn Component","Source","Validation Rules","columnType" "FCS File Annotation Template","A template outlining metadata to be collected and applied to FCS file entities as annotations in Synapse.","","Component, fileFormat, specimenModality, assay, eventCount","","","","","","","" -"BDM FCS File Annotations","A template outlining metadata to be collected and applied to FCS file entities as annotations in Synapse by BDM team as part of data release process.","","Component, fileFormat, resourceType, assay, specimenModality, eventCount, parentBiospecimenID, biospecimenType, biospecimenSubtype, dataType, dataSubtype, diagnosis, platform, sampleProcessingBatch, dataCollectionBatch, program, project, species","","","","","","","" +"BDM FCS File Annotations","A template outlining metadata to be collected and applied to FCS file entities as annotations in Synapse by BDM team as part of data release process.","","Component, fileFormat, resourceType, assay, specimenModality, eventCount, parentBiospecimenID, biospecimenType, biospecimenSubtype, dataType, dataSubtype, diagnosis, platform, sampleProcessingBatch, dataCollectionBatch, program, project, species, primaryCellSource, cellType, userDefinedCellType","","","","","","","" "multispecimen","Is a valid value of `specimenModality` that triggers conditional dependencies for additional attributes.","","sampleProcessingBatch, dataCollectionBatch","","","","","","","" "single specimen","Is a valid value of `specimenModality` that triggers conditional dependencies for additional attributes.","","biospecimenID, individualID","","","","","","","" "resourceType","High-level classification of the file content","experimental data","","","TRUE","","","","","string" @@ -13,14 +13,14 @@ "publicationSynID","The synID of the corresponding Synapse entity that stores metadata about the publication. This is used to differentiate publication-specific files, often consisting of level 4 processed data and expanded subject metadata, in a publication dataset that also includes raw or minimally processed files from experimental datasets. This provides an easy way to distinguish and select for the publication-specific data from which the research findings were derived. When this attribute is used to annotate a Dataset it serves as a way to directly link the Dataset entity with the publication metadata stored in Synapse.","","","","False","","","","regex search ^syn[0-9]{8} error","string" "associatedDataset","The synID of a Dataset entity. This serves to link other Synapse entities to Dataset entities. When used to annotate a publication Dataset this attribute should include the synID for an experimental Datasets from which the publication data was derived. Multiple synID can be specified using a comma-delimited list.","","","","False","","","","list like::regex search ^syn[0-9]{8} error","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, ELLIPSS, LOCKIT, RA, SLE, STAMP, V-CoRT","","","True","","","","list like error","string" +"project","A sub-level attribute of `program` specifying a research initiative working to investigate particular hypotheses.","AIM for RA, ELLIPSS, LOCKIT, RA, SLE, STAMP, UMass V-CoRT","","","True","","","","list like error","string" "programPhase","A label noting which AMP RA/SLE program phase generated the data.","I, II","","","True","","","","list like error","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" "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" "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" "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" "custom10xProbeSetSynID","If custom modified probe sets were used for collecting 10x Chromium Flex scRNA-seq data, then the probe reference files should be grouped as a zip or tar archive and uploaded as metadata. This attribute links the experimental data back to the probe set archive file via a synapse ID.","","","","True","","","","regex search ^syn[0-9]{8} error","string" -"specimenModality","Label assigned to experimental data files indicating whether the data contained corresponds to a single or multiple biospecimens","multispecimen, single specimen","","","True","","","","","string" +"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" "individualID","Unique identifier assigned to each study participant. For multi-specimen data files provide all IDs in a comma-separated list.","","","","True","","","","#ClinicalMetadataTemplate unique error^^#BiospecimenMetadataTemplate str^^list like error","string" "biospecimenID","A unique identifier assigned to specimens collected from study participants. For multi-specimen data files provide all IDs in a comma-separated list.","","","","True","","","","#BiospecimenMetadataTemplate unique error^^list like error","string" "parentBiospecimenID","The biospecimenID associated with the originating biospecimen for derived or child biospecimens.","","","","False","","","","","string" @@ -36,15 +36,14 @@ "nucleicAcidSource","The source of the nucleic acid used as input for sequencing library fragments. Select all that apply, though in most cases only a single label is expected.","BCR mRNA, CRISPR protospacer feature barcode, TCR mRNA, Tn5-accessible gDNA, antigen capture barcode, gDNA, globin-depleted RNA, intracellular protein feature barcode, multiplexing oligo, poly(A) RNA, rRNA-depleted RNA, surface protein feature barcode","","","True","","","","list like error","string" "biospecimenSubtype","Biospecimen status before sample is processed into a scRNA-seq library. Several scRNA-seq technologies support a variety of sample processing methods which can introduces sources of technical variation.","FFPE tissue, PFA-fixed tissue, cell or tissue lysate, cell suspension, flow-sorted cells, fresh tissue, frozen tissue, nuclei suspension, supernatant","","","False","","","","","string" "cellRangerOutput","10x Genomics Cell Ranger software output several different counts results and formats, some with different processing applied. This label distinguishes between these types and is particularly helpful when multiple files are uploaded with the sample name, e.g., barcodes.tsv.gz","Not Applicable, filtered MEX, filtered_feature_bc_matrix, filtered_peak_bc_matrix, raw MEX, raw_feature_bc_matrix, raw_peak_bc_matrix","","","True","","","","","string" -"alignmentReference","The genomic/transcriptomic reference used for performing read alignment against.","10x Cell Ranger Human GRCh38 2020-A, 10x Cell Ranger Human GRCh38 2024-A, modified GRCh38, unknown, vdj_GRCh38_alts_ensembl-4.0.0","","","True","","","","","string" -"libraryPrepMethod","Sequencing library preparation method or kit used to create the library. If no commercially available kit was used, please select 'in-house library prep'.","10x Chromium Fixed RNA Human Transcriptome, 10x Chromium GEM-X Single Cell 3' v4, 10x Chromium GEM-X Single Cell 5' v3, 10x Chromium Next GEM Single Cell 3', 10x Chromium Next GEM Single Cell 3' 3.1, 10x Chromium Next GEM Single Cell 5' v1.1, 10x Chromium Next GEM Single Cell 5' v2, 10x Chromium Next GEM Single Cell ATAC v2, 10x Chromium Single Cell Human BCR, 10x Chromium Single Cell Human TCR, 10x GEM-X Flex Gene Expression Human, 10x GEM-X Universal 5? Gene Expression v3, CEL-Seq2, Chromium Next GEM Single Cell ATAC v1.1, Fluidigm C1 HT, NEBNext Human Immune Sequencing Kit, NEBNext Ultra II Directional RNA Library, Nextera XT, Nextera XT DNA, QIAseq miRNA Library, SMART-Seq Human BCR with UMI, SMART-Seq Human TCR with UMI, SMART-Seq v4 Ultra Low Input RNA, SMARTer Stranded Total RNA v2, Takara Human BCR profiling for Illumina, Takara Human TCR profiling for Illumina, Takara Human TCRv2 profiling for Illumina, Takara Human scTCR profiling for Illumina, TruSeq Stranded mRNA, custom DASH-treatment, in-house library prep","","","True","","","","","string" +"alignmentReference","The genomic/transcriptomic reference used for performing read alignment against.","10x Cell Ranger Human GRCh38 2020-A, 10x Cell Ranger Human GRCh38 2024-A, GRCh38, modified GRCh38, unknown, vdj_GRCh38_alts_ensembl-4.0.0","","","True","","","","","string" +"libraryPrepMethod","Sequencing library preparation method or kit used to create the library. If no commercially available kit was used, please select 'in-house library prep'.","10x Chromium Fixed RNA Human Transcriptome, 10x Chromium GEM-X Single Cell 3' v4, 10x Chromium GEM-X Single Cell 5' v3, 10x Chromium Next GEM Single Cell 3', 10x Chromium Next GEM Single Cell 3' 3.1, 10x Chromium Next GEM Single Cell 5' v1.1, 10x Chromium Next GEM Single Cell 5' v2, 10x Chromium Next GEM Single Cell ATAC v2, 10x Chromium Single Cell Human BCR, 10x Chromium Single Cell Human TCR, 10x GEM-X Flex Gene Expression Human, 10x GEM-X Universal 5' Gene Expression v3, CEL-Seq2, Chromium Next GEM Single Cell ATAC v1.1, Fluidigm C1 HT, NEBNext Human Immune Sequencing Kit, NEBNext Ultra II Directional RNA Library, Nextera XT, Nextera XT DNA, QIAseq miRNA Library, SMART-Seq Human BCR with UMI, SMART-Seq Human TCR with UMI, SMART-Seq v4 Ultra Low Input RNA, SMARTer Stranded Total RNA v2, Takara Human BCR profiling for Illumina, Takara Human TCR profiling for Illumina, Takara Human TCRv2 profiling for Illumina, Takara Human scTCR profiling for Illumina, TruSeq Stranded mRNA, custom DASH-treatment, in-house library prep","","","True","","","","","string" "datasetType","High-level classification of dataset entity distinguishing between datasets compiled for a specific publication or as a general data resource.","experimental, publication","","","True","","","","","string" "acknowledgmentStatement","A Dataset-specific attribute specifying the path to the wiki subpage within the ARK Portal - backend project that contains the acknowledgement statement that must be included in publications using data from the given dataset as a stipulation of the conditions of use.","syn26710600/wiki/619685","","","True","","","","","string" "datasetDescription","A Dataset-specific attribute specifying the synID of the folder that contains a wiki write-up of the dataset description. This wiki content will be surfaced on the ARK Portal frontend site.","","","","True","","","","regex search ^syn[0-9]{8} error","string" "ARKRelease","A Dataset-specific attribute specifying the ARK Portal release in which this dataset was first made available to the public.","1.0, 2.0, 2024.06.R1, 2024.07.R1, 2024.08.R1, 2024.09.R1, 2024.10.R1, 2024.12.R1, 2025.01.R1, 2025.02.R1, 2025.03.R1, 2025.04.R1, 2025.05.R1, 2025.06.R1, 2025.07.R1, 2025.08.R1, 2025.09.R1, 2025.10.R1, 2025.11.R1, 2025.12.R1","","","True","","","","","string" "RObjectClass","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.","ROCR prediction.object, Seurat object, SummarizedExperiment, Symphony reference, data.frame, list, matrix, sparse matrix, vector","","","False","","","","","string" -"dbGapAccession","NIH policy requires large-scale human genomics studies to be registered in dbGap. This is a Dataset-specific attribute indicating the unique identifier (i.e., accession) of the corresponding study that is registered in dbGap, formatted as a compact URI, e.g., dbgap:phs003417.v2.p1","","","","False","","","","regex search ^dbgap:","string" -"diagnosis","A high-level classifier indicating the disease status of an individual.","At-Risk RA, OA, RA, SLE, Sjogren's disease, control, cutaneous lupus erythematosus, dermatomyositis, lupus nephritis, psoriasis, psoriatic arthritis, scleroderma, unknown, vitiligo","","","True","","","","list like error","string" +"diagnosis","A high-level classifier indicating the disease status of an individual.","At-Risk RA, Not Applicable, OA, RA, SLE, Sjogren's disease, control, cutaneous lupus erythematosus, dermatomyositis, discoid lupus erythematosus, lupus nephritis, psoriasis, psoriatic arthritis, scleroderma, unknown, vitiligo","","","True","","","","list like error","string" "DOID","Disease ontology identifier associated with `diagnosis`. Attribute values are applied by ARK Portal data managers.","","","","True","","","","regex search ^DOID error","string" "libraryID","A library label or name, unique within an experiment, used to distinguish sequencing libraries.","","","","True","","","","","string" "associatedCodeURL","A URL to the repository where associated code is available.","","","","False","","","","","string" @@ -61,7 +60,7 @@ "PMID","PubMed(R) Identifier","","","","True","","","","regex search ^PMID error","string" "DOI","Digital object identifier","","","","True","","","","","string" "anatomicalSite","The anatomical site, i.e., location on or within the body, from which the biospecimen was collected. This attribute is required depending on the value selected for biospecimenType.","left 2nd MCP joint, left ankle joint, left hip joint, left knee joint, left wrist joint, other site, right 1st MTP joint, right 2nd MCP joint, right 2nd MTP joint, right 3rd MCP joint, right ankle joint, right hip joint, right knee joint, right wrist joint, unknown","","","True","","","","","string" -"vitiligoType","A high-level classification of vitiligo based on the distribution and patterning of lesions across the body.","mixed, non-segmental, segmental, unclassified","","","False","","","","","string" +"vitiligoPattern","A high-level classification of vitiligo based on the distribution and patterning of lesions across the body.","mixed, non-segmental, segmental, unclassified","","","False","","","","","string" "vitiligoPhenotype","Classification of vitiligo lesions which correlate with autoimmune activity and result in specific skin and depigmentation manifestations at the lesion site. If N/A please select 'none'. Multiple selections can be provided in a comma-delimited list.","active, confetti, inflammatory, none, trichrome","","","True","","","","list like error","string" "psoriasisType","General type classification of psoriasis disease manifestation.","erythrodermic, guttate, inverse, plaque, pustular","","","False","","","","","string" "ageDiagnosis","Age at which subject was diagnosed with `diagnosis`. If providing this value be sure the unit matches that used for `age`.","","","","False","","","","num error","number" @@ -112,3 +111,5 @@ "treatmentTimepoint","Where applicable, specify the timepoint relative to treatment to distinguish different sets of samples that have undergone the same treatment but for different lengths of time. REQUIRED: please specify the unit of time, e.g., secs, mins, hrs, days, etc.","","","","False","","","","","string" "slideID","A distinct label or name, unique within an experiment, assigned to an imaging slides.","","","","True","","","","","string" "altSampleID","An alternate identifier for a sample. With some assays there can be default or alternate sample identifiers entered into the data collection software. If you will be uploading data collected with an alternate identifier please provide that here. In some cases, the ARK BDM team will use this field to capture original but out-dated identifiers for samples.","","","","False","","","","","string" +"sampleCollectionBatch","A label indicating batching of sample collection or experiment execution that occurs prior to data collection.","","","","False","","","","","string" +"associatedAccession","This is a File and Dataset annotation attribute indicating additional accessions (i.e., unique identifiers) associated with the data when the data has also been submitted to or can be found in other repositories such as GEO, SRA, dbGaP, etc.","","","","False","","","","list like error","string" diff --git a/model_contexts/fcs/ark.fcs_model.jsonld b/model_contexts/fcs/ark.fcs_model.jsonld index 85cc1f5..2c7aace 100644 --- a/model_contexts/fcs/ark.fcs_model.jsonld +++ b/model_contexts/fcs/ark.fcs_model.jsonld @@ -99,6 +99,9 @@ }, { "@id": "bts:Singlespecimen" + }, + { + "@id": "bts:Unknown" } ], "sms:displayName": "specimenModality", @@ -218,6 +221,15 @@ }, { "@id": "bts:Species" + }, + { + "@id": "bts:PrimaryCellSource" + }, + { + "@id": "bts:CellType" + }, + { + "@id": "bts:UserDefinedCellType" } ], "sms:validationRules": [] @@ -506,6 +518,9 @@ { "@id": "bts:At-RiskRA" }, + { + "@id": "bts:NotApplicable" + }, { "@id": "bts:OA" }, @@ -527,6 +542,9 @@ { "@id": "bts:Dermatomyositis" }, + { + "@id": "bts:Discoidlupuserythematosus" + }, { "@id": "bts:Lupusnephritis" }, @@ -714,7 +732,7 @@ "@id": "bts:STAMP" }, { - "@id": "bts:V-CoRT" + "@id": "bts:UMassV-CoRT" } ], "sms:displayName": "project", @@ -745,6 +763,89 @@ "sms:required": "sms:true", "sms:validationRules": [] }, + { + "@id": "bts:PrimaryCellSource", + "@type": "rdfs:Class", + "rdfs:comment": "A label indicating the biological source material from which a primary cell culture was derived.", + "rdfs:label": "PrimaryCellSource", + "rdfs:subClassOf": [ + { + "@id": "bts:Thing" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "schema:rangeIncludes": [ + { + "@id": "bts:PBMCs" + }, + { + "@id": "bts:Kidney" + }, + { + "@id": "bts:Pannus-deriveddermis" + }, + { + "@id": "bts:Pannus-derivedepidermis" + }, + { + "@id": "bts:Salivarygland" + }, + { + "@id": "bts:Synovialtissue" + }, + { + "@id": "bts:Totalleukocytes" + }, + { + "@id": "bts:Urine" + }, + { + "@id": "bts:Uvea" + }, + { + "@id": "bts:Wholeblood" + } + ], + "sms:displayName": "primaryCellSource", + "sms:required": "sms:true", + "sms:validationRules": [] + }, + { + "@id": "bts:CellType", + "@type": "rdfs:Class", + "rdfs:comment": "The cell type name from Cell Ontology for the corresponding CL identifier.", + "rdfs:label": "CellType", + "rdfs:subClassOf": [ + { + "@id": "bts:Thing" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "cellType", + "sms:required": "sms:false", + "sms:validationRules": [] + }, + { + "@id": "bts:UserDefinedCellType", + "@type": "rdfs:Class", + "rdfs:comment": "User-defined label of a cell type. Contributors are provided this option to use preferred or custom cell type labels that may vary from options and standards set by Cell Ontology.", + "rdfs:label": "UserDefinedCellType", + "rdfs:subClassOf": [ + { + "@id": "bts:Thing" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "userDefinedCellType", + "sms:required": "sms:false", + "sms:validationRules": [] + }, { "@id": "bts:Multispecimen", "@type": "rdfs:Class", @@ -1166,10 +1267,10 @@ "rdfs:label": "Unknown", "rdfs:subClassOf": [ { - "@id": "bts:Ethnicity" + "@id": "bts:SpecimenModality" }, { - "@id": "bts:AlignmentReference" + "@id": "bts:Ethnicity" }, { "@id": "bts:SynovialCollectionProcedure" @@ -1180,6 +1281,9 @@ { "@id": "bts:DiabetesType" }, + { + "@id": "bts:AlignmentReference" + }, { "@id": "bts:Race" }, @@ -1375,10 +1479,10 @@ "rdfs:label": "RA", "rdfs:subClassOf": [ { - "@id": "bts:Diagnosis" + "@id": "bts:Project" }, { - "@id": "bts:Project" + "@id": "bts:Diagnosis" } ], "schema:isPartOf": { @@ -1395,10 +1499,10 @@ "rdfs:label": "SLE", "rdfs:subClassOf": [ { - "@id": "bts:Diagnosis" + "@id": "bts:Project" }, { - "@id": "bts:Project" + "@id": "bts:Diagnosis" } ], "schema:isPartOf": { @@ -1426,10 +1530,10 @@ "sms:validationRules": [] }, { - "@id": "bts:V-CoRT", + "@id": "bts:UMassV-CoRT", "@type": "rdfs:Class", "rdfs:comment": "TBD", - "rdfs:label": "V-CoRT", + "rdfs:label": "UMassV-CoRT", "rdfs:subClassOf": [ { "@id": "bts:Project" @@ -1438,7 +1542,7 @@ "schema:isPartOf": { "@id": "http://schema.biothings.io" }, - "sms:displayName": "V-CoRT", + "sms:displayName": "UMass V-CoRT", "sms:required": "sms:false", "sms:validationRules": [] }, @@ -2433,55 +2537,6 @@ "sms:required": "sms:false", "sms:validationRules": [] }, - { - "@id": "bts:PrimaryCellSource", - "@type": "rdfs:Class", - "rdfs:comment": "A label indicating the biological source material from which a primary cell culture was derived.", - "rdfs:label": "PrimaryCellSource", - "rdfs:subClassOf": [ - { - "@id": "bts:Thing" - } - ], - "schema:isPartOf": { - "@id": "http://schema.biothings.io" - }, - "schema:rangeIncludes": [ - { - "@id": "bts:PBMCs" - }, - { - "@id": "bts:Kidney" - }, - { - "@id": "bts:Pannus-deriveddermis" - }, - { - "@id": "bts:Pannus-derivedepidermis" - }, - { - "@id": "bts:Salivarygland" - }, - { - "@id": "bts:Synovialtissue" - }, - { - "@id": "bts:Totalleukocytes" - }, - { - "@id": "bts:Urine" - }, - { - "@id": "bts:Uvea" - }, - { - "@id": "bts:Wholeblood" - } - ], - "sms:displayName": "primaryCellSource", - "sms:required": "sms:true", - "sms:validationRules": [] - }, { "@id": "bts:Kidney", "@type": "rdfs:Class", @@ -4216,6 +4271,9 @@ "rdfs:subClassOf": [ { "@id": "bts:CellRangerOutput" + }, + { + "@id": "bts:Diagnosis" } ], "schema:isPartOf": { @@ -4347,6 +4405,9 @@ { "@id": "bts:10xCellRangerHumanGRCh382024-A" }, + { + "@id": "bts:GRCh38" + }, { "@id": "bts:ModifiedGRCh38" }, @@ -4395,6 +4456,23 @@ "sms:required": "sms:false", "sms:validationRules": [] }, + { + "@id": "bts:GRCh38", + "@type": "rdfs:Class", + "rdfs:comment": "TBD", + "rdfs:label": "GRCh38", + "rdfs:subClassOf": [ + { + "@id": "bts:AlignmentReference" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "GRCh38", + "sms:required": "sms:false", + "sms:validationRules": [] + }, { "@id": "bts:ModifiedGRCh38", "@type": "rdfs:Class", @@ -4477,7 +4555,7 @@ "@id": "bts:10xGEM-XFlexGeneExpressionHuman" }, { - "@id": "bts:10xGEM-XUniversal5?GeneExpressionv3" + "@id": "bts:10xGEM-XUniversal5'GeneExpressionv3" }, { "@id": "bts:CEL-Seq2" @@ -4729,10 +4807,10 @@ "sms:validationRules": [] }, { - "@id": "bts:10xGEM-XUniversal5?GeneExpressionv3", + "@id": "bts:10xGEM-XUniversal5'GeneExpressionv3", "@type": "rdfs:Class", "rdfs:comment": "TBD", - "rdfs:label": "10xGEM-XUniversal5?GeneExpressionv3", + "rdfs:label": "10xGEM-XUniversal5'GeneExpressionv3", "rdfs:subClassOf": [ { "@id": "bts:LibraryPrepMethod" @@ -4741,7 +4819,7 @@ "schema:isPartOf": { "@id": "http://schema.biothings.io" }, - "sms:displayName": "10x GEM-X Universal 5? Gene Expression v3", + "sms:displayName": "10x GEM-X Universal 5' Gene Expression v3", "sms:required": "sms:false", "sms:validationRules": [] }, @@ -5803,25 +5881,6 @@ "sms:required": "sms:false", "sms:validationRules": [] }, - { - "@id": "bts:DbGapAccession", - "@type": "rdfs:Class", - "rdfs:comment": "NIH policy requires large-scale human genomics studies to be registered in dbGap. This is a Dataset-specific attribute indicating the unique identifier (i.e., accession) of the corresponding study that is registered in dbGap, formatted as a compact URI, e.g., dbgap:phs003417.v2.p1", - "rdfs:label": "DbGapAccession", - "rdfs:subClassOf": [ - { - "@id": "bts:Thing" - } - ], - "schema:isPartOf": { - "@id": "http://schema.biothings.io" - }, - "sms:displayName": "dbGapAccession", - "sms:required": "sms:false", - "sms:validationRules": [ - "regex search ^dbgap:" - ] - }, { "@id": "bts:At-RiskRA", "@type": "rdfs:Class", @@ -5924,6 +5983,23 @@ "sms:required": "sms:false", "sms:validationRules": [] }, + { + "@id": "bts:Discoidlupuserythematosus", + "@type": "rdfs:Class", + "rdfs:comment": "TBD", + "rdfs:label": "Discoidlupuserythematosus", + "rdfs:subClassOf": [ + { + "@id": "bts:Diagnosis" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "discoid lupus erythematosus", + "sms:required": "sms:false", + "sms:validationRules": [] + }, { "@id": "bts:Lupusnephritis", "@type": "rdfs:Class", @@ -6834,10 +6910,10 @@ "sms:validationRules": [] }, { - "@id": "bts:VitiligoType", + "@id": "bts:VitiligoPattern", "@type": "rdfs:Class", "rdfs:comment": "A high-level classification of vitiligo based on the distribution and patterning of lesions across the body.", - "rdfs:label": "VitiligoType", + "rdfs:label": "VitiligoPattern", "rdfs:subClassOf": [ { "@id": "bts:Thing" @@ -6860,7 +6936,7 @@ "@id": "bts:Unclassified" } ], - "sms:displayName": "vitiligoType", + "sms:displayName": "vitiligoPattern", "sms:required": "sms:false", "sms:validationRules": [] }, @@ -6871,7 +6947,7 @@ "rdfs:label": "Mixed", "rdfs:subClassOf": [ { - "@id": "bts:VitiligoType" + "@id": "bts:VitiligoPattern" } ], "schema:isPartOf": { @@ -6888,7 +6964,7 @@ "rdfs:label": "Non-segmental", "rdfs:subClassOf": [ { - "@id": "bts:VitiligoType" + "@id": "bts:VitiligoPattern" } ], "schema:isPartOf": { @@ -6905,7 +6981,7 @@ "rdfs:label": "Segmental", "rdfs:subClassOf": [ { - "@id": "bts:VitiligoType" + "@id": "bts:VitiligoPattern" } ], "schema:isPartOf": { @@ -6922,7 +6998,7 @@ "rdfs:label": "Unclassified", "rdfs:subClassOf": [ { - "@id": "bts:VitiligoType" + "@id": "bts:VitiligoPattern" } ], "schema:isPartOf": { @@ -8307,40 +8383,6 @@ "regex search ^CL: error" ] }, - { - "@id": "bts:CellType", - "@type": "rdfs:Class", - "rdfs:comment": "The cell type name from Cell Ontology for the corresponding CL identifier.", - "rdfs:label": "CellType", - "rdfs:subClassOf": [ - { - "@id": "bts:Thing" - } - ], - "schema:isPartOf": { - "@id": "http://schema.biothings.io" - }, - "sms:displayName": "cellType", - "sms:required": "sms:false", - "sms:validationRules": [] - }, - { - "@id": "bts:UserDefinedCellType", - "@type": "rdfs:Class", - "rdfs:comment": "User-defined label of a cell type. Contributors are provided this option to use preferred or custom cell type labels that may vary from options and standards set by Cell Ontology.", - "rdfs:label": "UserDefinedCellType", - "rdfs:subClassOf": [ - { - "@id": "bts:Thing" - } - ], - "schema:isPartOf": { - "@id": "http://schema.biothings.io" - }, - "sms:displayName": "userDefinedCellType", - "sms:required": "sms:false", - "sms:validationRules": [] - }, { "@id": "bts:KrennInflammatory", "@type": "rdfs:Class", @@ -8945,6 +8987,42 @@ "sms:displayName": "altSampleID", "sms:required": "sms:false", "sms:validationRules": [] + }, + { + "@id": "bts:SampleCollectionBatch", + "@type": "rdfs:Class", + "rdfs:comment": "A label indicating batching of sample collection or experiment execution that occurs prior to data collection.", + "rdfs:label": "SampleCollectionBatch", + "rdfs:subClassOf": [ + { + "@id": "bts:Thing" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "sampleCollectionBatch", + "sms:required": "sms:false", + "sms:validationRules": [] + }, + { + "@id": "bts:AssociatedAccession", + "@type": "rdfs:Class", + "rdfs:comment": "This is a File and Dataset annotation attribute indicating additional accessions (i.e., unique identifiers) associated with the data when the data has also been submitted to or can be found in other repositories such as GEO, SRA, dbGaP, etc.", + "rdfs:label": "AssociatedAccession", + "rdfs:subClassOf": [ + { + "@id": "bts:Thing" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "associatedAccession", + "sms:required": "sms:false", + "sms:validationRules": [ + "list like error" + ] } ], "@id": "http://schema.biothings.io/#0.1" diff --git a/model_contexts/main/ark.main_context.csv b/model_contexts/main/ark.main_context.csv index 8a362d4..f29776d 100644 --- a/model_contexts/main/ark.main_context.csv +++ b/model_contexts/main/ark.main_context.csv @@ -1,14 +1,14 @@ -Attribute,Description,Valid Values,DependsOn,Properties,Required,Parent,DependsOn Component,Source,Validation Rules,columnType -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, dbGapAccession, 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",,,,,,, -BDM Metadata File Annotations,A template outlining metadata to be collected for annotating metadata files to be compiled by ARK BDM.,,"Component, fileFormat, dataType, resourceType, program, project, species",,,,,,, -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,,,,,,, -single specimen,Is a valid value of `specimenModality` that triggers conditional dependencies for additional attributes.,,biospecimenID,,,,,,, \ No newline at end of file +"Attribute","Description","Valid Values","DependsOn","Properties","Required","Parent","DependsOn Component","Source","Validation Rules","columnType" +"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","","","","","","","" +"BDM Metadata File Annotations","A template outlining metadata to be collected for annotating metadata files to be compiled by ARK BDM.","","Component, fileFormat, dataType, resourceType, program, project, species, primaryCellSource, cellType, userDefinedCellType","","","","","","","" +"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","","","","","","","" +"single specimen","Is a valid value of `specimenModality` that triggers conditional dependencies for additional attributes.","","biospecimenID","","","","","","","" diff --git a/model_contexts/main/ark.main_model.csv b/model_contexts/main/ark.main_model.csv index d2ddf07..59428da 100644 --- a/model_contexts/main/ark.main_model.csv +++ b/model_contexts/main/ark.main_model.csv @@ -1,9 +1,9 @@ "Attribute","Description","Valid Values","DependsOn","Properties","Required","Parent","DependsOn Component","Source","Validation Rules","columnType" -"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, dbGapAccession, ImmPortAccession, datasetStatus, species","","","","","","","" +"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","","","","","","","" -"BDM Metadata File Annotations","A template outlining metadata to be collected for annotating metadata files to be compiled by ARK BDM.","","Component, fileFormat, dataType, resourceType, program, project, species","","","","","","","" +"BDM Metadata File Annotations","A template outlining metadata to be collected for annotating metadata files to be compiled by ARK BDM.","","Component, fileFormat, dataType, resourceType, program, project, species, primaryCellSource, cellType, userDefinedCellType","","","","","","","" "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","","","","","","","" @@ -13,11 +13,11 @@ "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","","","","","","","" "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, info, mcd, mtx, parquet, pdf, rds, rec, svs, tbi, tgz, tsv, txt, vcf, xls, xlsx, zip","","","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, info, mcd, mtx, parquet, pdf, py, rds, rec, svs, tbi, tgz, tsv, txt, vcf, xls, xlsx, zip","","","True","","","","","string" "publicationSynID","The synID of the corresponding Synapse entity that stores metadata about the publication. This is used to differentiate publication-specific files, often consisting of level 4 processed data and expanded subject metadata, in a publication dataset that also includes raw or minimally processed files from experimental datasets. This provides an easy way to distinguish and select for the publication-specific data from which the research findings were derived. When this attribute is used to annotate a Dataset it serves as a way to directly link the Dataset entity with the publication metadata stored in Synapse.","","","","False","","","","regex search ^syn[0-9]{8} error","string" "associatedDataset","The synID of a Dataset entity. This serves to link other Synapse entities to Dataset entities. When used to annotate a publication Dataset this attribute should include the synID for an experimental Datasets from which the publication data was derived. Multiple synID can be specified using a comma-delimited list.","","","","False","","","","list like::regex search ^syn[0-9]{8} error","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, ELLIPSS, LOCKIT, RA, SLE, STAMP, V-CoRT","","","True","","","","list like error","string" +"project","A sub-level attribute of `program` specifying a research initiative working to investigate particular hypotheses.","AIM for RA, ELLIPSS, LOCKIT, RA, SLE, STAMP, UMass V-CoRT","","","True","","","","list like error","string" "programPhase","A label noting which AMP RA/SLE program phase generated the data.","I, II","","","True","","","","list like error","string" "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" @@ -27,7 +27,7 @@ "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" "custom10xProbeSetSynID","If custom modified probe sets were used for collecting 10x Chromium Flex scRNA-seq data, then the probe reference files should be grouped as a zip or tar archive and uploaded as metadata. This attribute links the experimental data back to the probe set archive file via a synapse ID.","","","","True","","","","regex search ^syn[0-9]{8} error","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" -"specimenModality","Label assigned to experimental data files indicating whether the data contained corresponds to a single or multiple biospecimens","multispecimen, single specimen","","","True","","","","","string" +"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" "individualID","Unique identifier assigned to each study participant. For multi-specimen data files provide all IDs in a comma-separated list.","","","","True","","","","#ClinicalMetadataTemplate unique error^^#BiospecimenMetadataTemplate str^^list like error","string" "biospecimenID","A unique identifier assigned to specimens collected from study participants. For multi-specimen data files provide all IDs in a comma-separated list.","","","","True","","","","#BiospecimenMetadataTemplate unique error^^list like error","string" "parentBiospecimenID","The biospecimenID associated with the originating biospecimen for derived or child biospecimens.","","","","False","","","","","string" @@ -43,15 +43,14 @@ "nucleicAcidSource","The source of the nucleic acid used as input for sequencing library fragments. Select all that apply, though in most cases only a single label is expected.","BCR mRNA, CRISPR protospacer feature barcode, TCR mRNA, Tn5-accessible gDNA, antigen capture barcode, gDNA, globin-depleted RNA, intracellular protein feature barcode, multiplexing oligo, poly(A) RNA, rRNA-depleted RNA, surface protein feature barcode","","","True","","","","list like error","string" "biospecimenSubtype","Biospecimen status before sample is processed into a scRNA-seq library. Several scRNA-seq technologies support a variety of sample processing methods which can introduces sources of technical variation.","FFPE tissue, PFA-fixed tissue, cell or tissue lysate, cell suspension, flow-sorted cells, fresh tissue, frozen tissue, nuclei suspension, supernatant","","","False","","","","","string" "cellRangerOutput","10x Genomics Cell Ranger software output several different counts results and formats, some with different processing applied. This label distinguishes between these types and is particularly helpful when multiple files are uploaded with the sample name, e.g., barcodes.tsv.gz","Not Applicable, filtered MEX, filtered_feature_bc_matrix, filtered_peak_bc_matrix, raw MEX, raw_feature_bc_matrix, raw_peak_bc_matrix","","","True","","","","","string" -"alignmentReference","The genomic/transcriptomic reference used for performing read alignment against.","10x Cell Ranger Human GRCh38 2020-A, 10x Cell Ranger Human GRCh38 2024-A, modified GRCh38, unknown, vdj_GRCh38_alts_ensembl-4.0.0","","","True","","","","","string" -"libraryPrepMethod","Sequencing library preparation method or kit used to create the library. If no commercially available kit was used, please select 'in-house library prep'.","10x Chromium Fixed RNA Human Transcriptome, 10x Chromium GEM-X Single Cell 3' v4, 10x Chromium GEM-X Single Cell 5' v3, 10x Chromium Next GEM Single Cell 3', 10x Chromium Next GEM Single Cell 3' 3.1, 10x Chromium Next GEM Single Cell 5' v1.1, 10x Chromium Next GEM Single Cell 5' v2, 10x Chromium Next GEM Single Cell ATAC v2, 10x Chromium Single Cell Human BCR, 10x Chromium Single Cell Human TCR, 10x GEM-X Flex Gene Expression Human, 10x GEM-X Universal 5? Gene Expression v3, CEL-Seq2, Chromium Next GEM Single Cell ATAC v1.1, Fluidigm C1 HT, NEBNext Human Immune Sequencing Kit, NEBNext Ultra II Directional RNA Library, Nextera XT, Nextera XT DNA, QIAseq miRNA Library, SMART-Seq Human BCR with UMI, SMART-Seq Human TCR with UMI, SMART-Seq v4 Ultra Low Input RNA, SMARTer Stranded Total RNA v2, Takara Human BCR profiling for Illumina, Takara Human TCR profiling for Illumina, Takara Human TCRv2 profiling for Illumina, Takara Human scTCR profiling for Illumina, TruSeq Stranded mRNA, custom DASH-treatment, in-house library prep","","","True","","","","","string" +"alignmentReference","The genomic/transcriptomic reference used for performing read alignment against.","10x Cell Ranger Human GRCh38 2020-A, 10x Cell Ranger Human GRCh38 2024-A, GRCh38, modified GRCh38, unknown, vdj_GRCh38_alts_ensembl-4.0.0","","","True","","","","","string" +"libraryPrepMethod","Sequencing library preparation method or kit used to create the library. If no commercially available kit was used, please select 'in-house library prep'.","10x Chromium Fixed RNA Human Transcriptome, 10x Chromium GEM-X Single Cell 3' v4, 10x Chromium GEM-X Single Cell 5' v3, 10x Chromium Next GEM Single Cell 3', 10x Chromium Next GEM Single Cell 3' 3.1, 10x Chromium Next GEM Single Cell 5' v1.1, 10x Chromium Next GEM Single Cell 5' v2, 10x Chromium Next GEM Single Cell ATAC v2, 10x Chromium Single Cell Human BCR, 10x Chromium Single Cell Human TCR, 10x GEM-X Flex Gene Expression Human, 10x GEM-X Universal 5' Gene Expression v3, CEL-Seq2, Chromium Next GEM Single Cell ATAC v1.1, Fluidigm C1 HT, NEBNext Human Immune Sequencing Kit, NEBNext Ultra II Directional RNA Library, Nextera XT, Nextera XT DNA, QIAseq miRNA Library, SMART-Seq Human BCR with UMI, SMART-Seq Human TCR with UMI, SMART-Seq v4 Ultra Low Input RNA, SMARTer Stranded Total RNA v2, Takara Human BCR profiling for Illumina, Takara Human TCR profiling for Illumina, Takara Human TCRv2 profiling for Illumina, Takara Human scTCR profiling for Illumina, TruSeq Stranded mRNA, custom DASH-treatment, in-house library prep","","","True","","","","","string" "datasetType","High-level classification of dataset entity distinguishing between datasets compiled for a specific publication or as a general data resource.","experimental, publication","","","True","","","","","string" "acknowledgmentStatement","A Dataset-specific attribute specifying the path to the wiki subpage within the ARK Portal - backend project that contains the acknowledgement statement that must be included in publications using data from the given dataset as a stipulation of the conditions of use.","syn26710600/wiki/619685","","","True","","","","","string" "datasetDescription","A Dataset-specific attribute specifying the synID of the folder that contains a wiki write-up of the dataset description. This wiki content will be surfaced on the ARK Portal frontend site.","","","","True","","","","regex search ^syn[0-9]{8} error","string" "ARKRelease","A Dataset-specific attribute specifying the ARK Portal release in which this dataset was first made available to the public.","1.0, 2.0, 2024.06.R1, 2024.07.R1, 2024.08.R1, 2024.09.R1, 2024.10.R1, 2024.12.R1, 2025.01.R1, 2025.02.R1, 2025.03.R1, 2025.04.R1, 2025.05.R1, 2025.06.R1, 2025.07.R1, 2025.08.R1, 2025.09.R1, 2025.10.R1, 2025.11.R1, 2025.12.R1","","","True","","","","","string" "RObjectClass","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.","ROCR prediction.object, Seurat object, SummarizedExperiment, Symphony reference, data.frame, list, matrix, sparse matrix, vector","","","False","","","","","string" -"dbGapAccession","NIH policy requires large-scale human genomics studies to be registered in dbGap. This is a Dataset-specific attribute indicating the unique identifier (i.e., accession) of the corresponding study that is registered in dbGap, formatted as a compact URI, e.g., dbgap:phs003417.v2.p1","","","","False","","","","regex search ^dbgap:","string" -"diagnosis","A high-level classifier indicating the disease status of an individual.","At-Risk RA, OA, RA, SLE, Sjogren's disease, control, cutaneous lupus erythematosus, dermatomyositis, lupus nephritis, psoriasis, psoriatic arthritis, scleroderma, unknown, vitiligo","","","True","","","","list like error","string" +"diagnosis","A high-level classifier indicating the disease status of an individual.","At-Risk RA, Not Applicable, OA, RA, SLE, Sjogren's disease, control, cutaneous lupus erythematosus, dermatomyositis, discoid lupus erythematosus, lupus nephritis, psoriasis, psoriatic arthritis, scleroderma, unknown, vitiligo","","","True","","","","list like error","string" "DOID","Disease ontology identifier associated with `diagnosis`. Attribute values are applied by ARK Portal data managers.","","","","True","","","","regex search ^DOID error","string" "libraryID","A library label or name, unique within an experiment, used to distinguish sequencing libraries.","","","","True","","","","","string" "associatedCodeURL","A URL to the repository where associated code is available.","","","","False","","","","","string" @@ -68,7 +67,7 @@ "PMID","PubMed(R) Identifier","","","","True","","","","regex search ^PMID error","string" "DOI","Digital object identifier","","","","True","","","","","string" "anatomicalSite","The anatomical site, i.e., location on or within the body, from which the biospecimen was collected. This attribute is required depending on the value selected for biospecimenType.","left 2nd MCP joint, left ankle joint, left hip joint, left knee joint, left wrist joint, other site, right 1st MTP joint, right 2nd MCP joint, right 2nd MTP joint, right 3rd MCP joint, right ankle joint, right hip joint, right knee joint, right wrist joint, unknown","","","True","","","","","string" -"vitiligoType","A high-level classification of vitiligo based on the distribution and patterning of lesions across the body.","mixed, non-segmental, segmental, unclassified","","","False","","","","","string" +"vitiligoPattern","A high-level classification of vitiligo based on the distribution and patterning of lesions across the body.","mixed, non-segmental, segmental, unclassified","","","False","","","","","string" "vitiligoPhenotype","Classification of vitiligo lesions which correlate with autoimmune activity and result in specific skin and depigmentation manifestations at the lesion site. If N/A please select 'none'. Multiple selections can be provided in a comma-delimited list.","active, confetti, inflammatory, none, trichrome","","","True","","","","list like error","string" "psoriasisType","General type classification of psoriasis disease manifestation.","erythrodermic, guttate, inverse, plaque, pustular","","","False","","","","","string" "ageDiagnosis","Age at which subject was diagnosed with `diagnosis`. If providing this value be sure the unit matches that used for `age`.","","","","False","","","","num error","number" @@ -120,3 +119,5 @@ "treatmentTimepoint","Where applicable, specify the timepoint relative to treatment to distinguish different sets of samples that have undergone the same treatment but for different lengths of time. REQUIRED: please specify the unit of time, e.g., secs, mins, hrs, days, etc.","","","","False","","","","","string" "slideID","A distinct label or name, unique within an experiment, assigned to an imaging slides.","","","","True","","","","","string" "altSampleID","An alternate identifier for a sample. With some assays there can be default or alternate sample identifiers entered into the data collection software. If you will be uploading data collected with an alternate identifier please provide that here. In some cases, the ARK BDM team will use this field to capture original but out-dated identifiers for samples.","","","","False","","","","","string" +"sampleCollectionBatch","A label indicating batching of sample collection or experiment execution that occurs prior to data collection.","","","","False","","","","","string" +"associatedAccession","This is a File and Dataset annotation attribute indicating additional accessions (i.e., unique identifiers) associated with the data when the data has also been submitted to or can be found in other repositories such as GEO, SRA, dbGaP, etc.","","","","False","","","","list like error","string" diff --git a/model_contexts/main/ark.main_model.jsonld b/model_contexts/main/ark.main_model.jsonld index 2ded422..8f94316 100644 --- a/model_contexts/main/ark.main_model.jsonld +++ b/model_contexts/main/ark.main_model.jsonld @@ -72,7 +72,7 @@ "@id": "bts:AssociatedCodeURL" }, { - "@id": "bts:DbGapAccession" + "@id": "bts:AssociatedAccession" }, { "@id": "bts:ImmPortAccession" @@ -164,7 +164,7 @@ "@id": "bts:STAMP" }, { - "@id": "bts:V-CoRT" + "@id": "bts:UMassV-CoRT" } ], "sms:displayName": "project", @@ -347,6 +347,9 @@ { "@id": "bts:At-RiskRA" }, + { + "@id": "bts:NotApplicable" + }, { "@id": "bts:OA" }, @@ -368,6 +371,9 @@ { "@id": "bts:Dermatomyositis" }, + { + "@id": "bts:Discoidlupuserythematosus" + }, { "@id": "bts:Lupusnephritis" }, @@ -789,10 +795,10 @@ "sms:validationRules": [] }, { - "@id": "bts:DbGapAccession", + "@id": "bts:AssociatedAccession", "@type": "rdfs:Class", - "rdfs:comment": "NIH policy requires large-scale human genomics studies to be registered in dbGap. This is a Dataset-specific attribute indicating the unique identifier (i.e., accession) of the corresponding study that is registered in dbGap, formatted as a compact URI, e.g., dbgap:phs003417.v2.p1", - "rdfs:label": "DbGapAccession", + "rdfs:comment": "This is a File and Dataset annotation attribute indicating additional accessions (i.e., unique identifiers) associated with the data when the data has also been submitted to or can be found in other repositories such as GEO, SRA, dbGaP, etc.", + "rdfs:label": "AssociatedAccession", "rdfs:subClassOf": [ { "@id": "bts:Thing" @@ -801,10 +807,10 @@ "schema:isPartOf": { "@id": "http://schema.biothings.io" }, - "sms:displayName": "dbGapAccession", + "sms:displayName": "associatedAccession", "sms:required": "sms:false", "sms:validationRules": [ - "regex search ^dbgap:" + "list like error" ] }, { @@ -1170,6 +1176,9 @@ }, { "@id": "bts:Singlespecimen" + }, + { + "@id": "bts:Unknown" } ], "sms:displayName": "specimenModality", @@ -1224,7 +1233,7 @@ "@id": "bts:10xGEM-XFlexGeneExpressionHuman" }, { - "@id": "bts:10xGEM-XUniversal5?GeneExpressionv3" + "@id": "bts:10xGEM-XUniversal5'GeneExpressionv3" }, { "@id": "bts:CEL-Seq2" @@ -1625,6 +1634,9 @@ { "@id": "bts:10xCellRangerHumanGRCh382024-A" }, + { + "@id": "bts:GRCh38" + }, { "@id": "bts:ModifiedGRCh38" }, @@ -1836,6 +1848,15 @@ }, { "@id": "bts:Species" + }, + { + "@id": "bts:PrimaryCellSource" + }, + { + "@id": "bts:CellType" + }, + { + "@id": "bts:UserDefinedCellType" } ], "sms:validationRules": [] @@ -1914,6 +1935,9 @@ { "@id": "bts:Pdf" }, + { + "@id": "bts:Py" + }, { "@id": "bts:Rds" }, @@ -1983,6 +2007,89 @@ "sms:required": "sms:true", "sms:validationRules": [] }, + { + "@id": "bts:PrimaryCellSource", + "@type": "rdfs:Class", + "rdfs:comment": "A label indicating the biological source material from which a primary cell culture was derived.", + "rdfs:label": "PrimaryCellSource", + "rdfs:subClassOf": [ + { + "@id": "bts:Thing" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "schema:rangeIncludes": [ + { + "@id": "bts:PBMCs" + }, + { + "@id": "bts:Kidney" + }, + { + "@id": "bts:Pannus-deriveddermis" + }, + { + "@id": "bts:Pannus-derivedepidermis" + }, + { + "@id": "bts:Salivarygland" + }, + { + "@id": "bts:Synovialtissue" + }, + { + "@id": "bts:Totalleukocytes" + }, + { + "@id": "bts:Urine" + }, + { + "@id": "bts:Uvea" + }, + { + "@id": "bts:Wholeblood" + } + ], + "sms:displayName": "primaryCellSource", + "sms:required": "sms:true", + "sms:validationRules": [] + }, + { + "@id": "bts:CellType", + "@type": "rdfs:Class", + "rdfs:comment": "The cell type name from Cell Ontology for the corresponding CL identifier.", + "rdfs:label": "CellType", + "rdfs:subClassOf": [ + { + "@id": "bts:Thing" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "cellType", + "sms:required": "sms:false", + "sms:validationRules": [] + }, + { + "@id": "bts:UserDefinedCellType", + "@type": "rdfs:Class", + "rdfs:comment": "User-defined label of a cell type. Contributors are provided this option to use preferred or custom cell type labels that may vary from options and standards set by Cell Ontology.", + "rdfs:label": "UserDefinedCellType", + "rdfs:subClassOf": [ + { + "@id": "bts:Thing" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "userDefinedCellType", + "sms:required": "sms:false", + "sms:validationRules": [] + }, { "@id": "bts:SnRNASeqAssayMetadataTemplate", "@type": "rdfs:Class", @@ -2852,6 +2959,23 @@ "sms:required": "sms:false", "sms:validationRules": [] }, + { + "@id": "bts:Py", + "@type": "rdfs:Class", + "rdfs:comment": "TBD", + "rdfs:label": "Py", + "rdfs:subClassOf": [ + { + "@id": "bts:FileFormat" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "py", + "sms:required": "sms:false", + "sms:validationRules": [] + }, { "@id": "bts:Rds", "@type": "rdfs:Class", @@ -3153,10 +3277,10 @@ "rdfs:label": "RA", "rdfs:subClassOf": [ { - "@id": "bts:Diagnosis" + "@id": "bts:Project" }, { - "@id": "bts:Project" + "@id": "bts:Diagnosis" } ], "schema:isPartOf": { @@ -3173,10 +3297,10 @@ "rdfs:label": "SLE", "rdfs:subClassOf": [ { - "@id": "bts:Diagnosis" + "@id": "bts:Project" }, { - "@id": "bts:Project" + "@id": "bts:Diagnosis" } ], "schema:isPartOf": { @@ -3204,10 +3328,10 @@ "sms:validationRules": [] }, { - "@id": "bts:V-CoRT", + "@id": "bts:UMassV-CoRT", "@type": "rdfs:Class", "rdfs:comment": "TBD", - "rdfs:label": "V-CoRT", + "rdfs:label": "UMassV-CoRT", "rdfs:subClassOf": [ { "@id": "bts:Project" @@ -3216,7 +3340,7 @@ "schema:isPartOf": { "@id": "http://schema.biothings.io" }, - "sms:displayName": "V-CoRT", + "sms:displayName": "UMass V-CoRT", "sms:required": "sms:false", "sms:validationRules": [] }, @@ -5021,6 +5145,9 @@ { "@id": "bts:CellRangerOutput" }, + { + "@id": "bts:Diagnosis" + }, { "@id": "bts:Platform" } @@ -5141,10 +5268,10 @@ "rdfs:label": "Unknown", "rdfs:subClassOf": [ { - "@id": "bts:Ethnicity" + "@id": "bts:SpecimenModality" }, { - "@id": "bts:AlignmentReference" + "@id": "bts:Ethnicity" }, { "@id": "bts:SynovialCollectionProcedure" @@ -5155,6 +5282,9 @@ { "@id": "bts:DiabetesType" }, + { + "@id": "bts:AlignmentReference" + }, { "@id": "bts:Race" }, @@ -5574,55 +5704,6 @@ "sms:required": "sms:false", "sms:validationRules": [] }, - { - "@id": "bts:PrimaryCellSource", - "@type": "rdfs:Class", - "rdfs:comment": "A label indicating the biological source material from which a primary cell culture was derived.", - "rdfs:label": "PrimaryCellSource", - "rdfs:subClassOf": [ - { - "@id": "bts:Thing" - } - ], - "schema:isPartOf": { - "@id": "http://schema.biothings.io" - }, - "schema:rangeIncludes": [ - { - "@id": "bts:PBMCs" - }, - { - "@id": "bts:Kidney" - }, - { - "@id": "bts:Pannus-deriveddermis" - }, - { - "@id": "bts:Pannus-derivedepidermis" - }, - { - "@id": "bts:Salivarygland" - }, - { - "@id": "bts:Synovialtissue" - }, - { - "@id": "bts:Totalleukocytes" - }, - { - "@id": "bts:Urine" - }, - { - "@id": "bts:Uvea" - }, - { - "@id": "bts:Wholeblood" - } - ], - "sms:displayName": "primaryCellSource", - "sms:required": "sms:true", - "sms:validationRules": [] - }, { "@id": "bts:Kidney", "@type": "rdfs:Class", @@ -7217,6 +7298,23 @@ "sms:required": "sms:false", "sms:validationRules": [] }, + { + "@id": "bts:GRCh38", + "@type": "rdfs:Class", + "rdfs:comment": "TBD", + "rdfs:label": "GRCh38", + "rdfs:subClassOf": [ + { + "@id": "bts:AlignmentReference" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "GRCh38", + "sms:required": "sms:false", + "sms:validationRules": [] + }, { "@id": "bts:ModifiedGRCh38", "@type": "rdfs:Class", @@ -7422,10 +7520,10 @@ "sms:validationRules": [] }, { - "@id": "bts:10xGEM-XUniversal5?GeneExpressionv3", + "@id": "bts:10xGEM-XUniversal5'GeneExpressionv3", "@type": "rdfs:Class", "rdfs:comment": "TBD", - "rdfs:label": "10xGEM-XUniversal5?GeneExpressionv3", + "rdfs:label": "10xGEM-XUniversal5'GeneExpressionv3", "rdfs:subClassOf": [ { "@id": "bts:LibraryPrepMethod" @@ -7434,7 +7532,7 @@ "schema:isPartOf": { "@id": "http://schema.biothings.io" }, - "sms:displayName": "10x GEM-X Universal 5? Gene Expression v3", + "sms:displayName": "10x GEM-X Universal 5' Gene Expression v3", "sms:required": "sms:false", "sms:validationRules": [] }, @@ -8453,6 +8551,23 @@ "sms:required": "sms:false", "sms:validationRules": [] }, + { + "@id": "bts:Discoidlupuserythematosus", + "@type": "rdfs:Class", + "rdfs:comment": "TBD", + "rdfs:label": "Discoidlupuserythematosus", + "rdfs:subClassOf": [ + { + "@id": "bts:Diagnosis" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "discoid lupus erythematosus", + "sms:required": "sms:false", + "sms:validationRules": [] + }, { "@id": "bts:Lupusnephritis", "@type": "rdfs:Class", @@ -9195,10 +9310,10 @@ "sms:validationRules": [] }, { - "@id": "bts:VitiligoType", + "@id": "bts:VitiligoPattern", "@type": "rdfs:Class", "rdfs:comment": "A high-level classification of vitiligo based on the distribution and patterning of lesions across the body.", - "rdfs:label": "VitiligoType", + "rdfs:label": "VitiligoPattern", "rdfs:subClassOf": [ { "@id": "bts:Thing" @@ -9221,7 +9336,7 @@ "@id": "bts:Unclassified" } ], - "sms:displayName": "vitiligoType", + "sms:displayName": "vitiligoPattern", "sms:required": "sms:false", "sms:validationRules": [] }, @@ -9232,7 +9347,7 @@ "rdfs:label": "Mixed", "rdfs:subClassOf": [ { - "@id": "bts:VitiligoType" + "@id": "bts:VitiligoPattern" } ], "schema:isPartOf": { @@ -9249,7 +9364,7 @@ "rdfs:label": "Non-segmental", "rdfs:subClassOf": [ { - "@id": "bts:VitiligoType" + "@id": "bts:VitiligoPattern" } ], "schema:isPartOf": { @@ -9266,7 +9381,7 @@ "rdfs:label": "Segmental", "rdfs:subClassOf": [ { - "@id": "bts:VitiligoType" + "@id": "bts:VitiligoPattern" } ], "schema:isPartOf": { @@ -9283,7 +9398,7 @@ "rdfs:label": "Unclassified", "rdfs:subClassOf": [ { - "@id": "bts:VitiligoType" + "@id": "bts:VitiligoPattern" } ], "schema:isPartOf": { @@ -10573,40 +10688,6 @@ "regex search ^CL: error" ] }, - { - "@id": "bts:CellType", - "@type": "rdfs:Class", - "rdfs:comment": "The cell type name from Cell Ontology for the corresponding CL identifier.", - "rdfs:label": "CellType", - "rdfs:subClassOf": [ - { - "@id": "bts:Thing" - } - ], - "schema:isPartOf": { - "@id": "http://schema.biothings.io" - }, - "sms:displayName": "cellType", - "sms:required": "sms:false", - "sms:validationRules": [] - }, - { - "@id": "bts:UserDefinedCellType", - "@type": "rdfs:Class", - "rdfs:comment": "User-defined label of a cell type. Contributors are provided this option to use preferred or custom cell type labels that may vary from options and standards set by Cell Ontology.", - "rdfs:label": "UserDefinedCellType", - "rdfs:subClassOf": [ - { - "@id": "bts:Thing" - } - ], - "schema:isPartOf": { - "@id": "http://schema.biothings.io" - }, - "sms:displayName": "userDefinedCellType", - "sms:required": "sms:false", - "sms:validationRules": [] - }, { "@id": "bts:KrennInflammatory", "@type": "rdfs:Class", @@ -11152,6 +11233,23 @@ "sms:displayName": "altSampleID", "sms:required": "sms:false", "sms:validationRules": [] + }, + { + "@id": "bts:SampleCollectionBatch", + "@type": "rdfs:Class", + "rdfs:comment": "A label indicating batching of sample collection or experiment execution that occurs prior to data collection.", + "rdfs:label": "SampleCollectionBatch", + "rdfs:subClassOf": [ + { + "@id": "bts:Thing" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "sampleCollectionBatch", + "sms:required": "sms:false", + "sms:validationRules": [] } ], "@id": "http://schema.biothings.io/#0.1" diff --git a/model_contexts/olink/ark.olink_context.csv b/model_contexts/olink/ark.olink_context.csv index aa94de0..0565502 100644 --- a/model_contexts/olink/ark.olink_context.csv +++ b/model_contexts/olink/ark.olink_context.csv @@ -1,9 +1,9 @@ -Attribute,Description,Valid Values,DependsOn,Properties,Required,Parent,DependsOn Component,Source,Validation Rules,columnType -Olink Assay Metadata Template,A template outlining assay metadata to be collected for each plate in an Olink dataset.,,"Component, assay, plateID, platform, targetPanel, targetPanelSynID, targetPanelSize",,,,,,, -Olink File Annotation Template,A template outlining metadata to be provided by contributors that is applied as a preliminary set of annotations to Olink dataset files.,,"Component, fileFormat, resourceType, plateID, specimenModality",,,,,,, -BDM Olink File Annotations,A template outlining the complete set of metadata to be applied as annotations to Olink dataset files by ARK Portal BDM.,,"Component, fileFormat, resourceType, plateID, platform, targetPanel, targetPanelSynID, targetPanelSize, diagnosis, specimenModality, dataType, dataSubtype, visitID, program, project, biospecimenType, species",,,,,,, -assay,The technology used to generate the data in this file.,"Olink Explore HT, Olink Reveal, Olink Flex, Olink Focus, Olink Target 48, Olink Target 96",,,TRUE,,,,,string -platform,"The specific instrument (manufacturer, model, etc.) that was used to carry out a laboratory or computational experiment.","Olink Signature Q100, Fluidigm BioMark, Illumina NextSeq 500, Illumina NovaSeq 6000, unknown",,,FALSE,,,,list like error,string -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.",,,,TRUE,,,,^^#OlinkAssayMetadataTemplate unique error^^list like error,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, programPhase",,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,,,,,,, \ No newline at end of file +"Attribute","Description","Valid Values","DependsOn","Properties","Required","Parent","DependsOn Component","Source","Validation Rules","columnType" +"Olink Assay Metadata Template","A template outlining assay metadata to be collected for each plate in an Olink dataset.","","Component, assay, plateID, platform, targetPanel, targetPanelSynID, targetPanelSize","","","","","","","" +"Olink File Annotation Template","A template outlining metadata to be provided by contributors that is applied as a preliminary set of annotations to Olink dataset files.","","Component, fileFormat, resourceType, plateID, specimenModality","","","","","","","" +"BDM Olink File Annotations","A template outlining the complete set of metadata to be applied as annotations to Olink dataset files by ARK Portal BDM.","","Component, fileFormat, resourceType, plateID, platform, targetPanel, targetPanelSynID, targetPanelSize, diagnosis, specimenModality, dataType, dataSubtype, visitID, program, project, biospecimenType, species, primaryCellSource, cellType, userDefinedCellType","","","","","","","" +"assay","The technology used to generate the data in this file.","Olink Explore HT, Olink Reveal, Olink Flex, Olink Focus, Olink Target 48, Olink Target 96","","","TRUE","","","","","string" +"platform","The specific instrument (manufacturer, model, etc.) that was used to carry out a laboratory or computational experiment.","Olink Signature Q100, Fluidigm BioMark, Illumina NextSeq 500, Illumina NovaSeq 6000, unknown","","","FALSE","","","","list like error","string" +"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.","","","","TRUE","","","","^^#OlinkAssayMetadataTemplate unique error^^list like error","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, programPhase","","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","","","","","","","" diff --git a/model_contexts/olink/ark.olink_model.csv b/model_contexts/olink/ark.olink_model.csv index ee7cba1..f30a631 100644 --- a/model_contexts/olink/ark.olink_model.csv +++ b/model_contexts/olink/ark.olink_model.csv @@ -1,18 +1,18 @@ "Attribute","Description","Valid Values","DependsOn","Properties","Required","Parent","DependsOn Component","Source","Validation Rules","columnType" "Olink Assay Metadata Template","A template outlining assay metadata to be collected for each plate in an Olink dataset.","","Component, assay, plateID, platform, targetPanel, targetPanelSynID, targetPanelSize","","","","","","","" "Olink File Annotation Template","A template outlining metadata to be provided by contributors that is applied as a preliminary set of annotations to Olink dataset files.","","Component, fileFormat, resourceType, plateID, specimenModality","","","","","","","" -"BDM Olink File Annotations","A template outlining the complete set of metadata to be applied as annotations to Olink dataset files by ARK Portal BDM.","","Component, fileFormat, resourceType, plateID, platform, targetPanel, targetPanelSynID, targetPanelSize, diagnosis, specimenModality, dataType, dataSubtype, visitID, program, project, biospecimenType, species","","","","","","","" +"BDM Olink File Annotations","A template outlining the complete set of metadata to be applied as annotations to Olink dataset files by ARK Portal BDM.","","Component, fileFormat, resourceType, plateID, platform, targetPanel, targetPanelSynID, targetPanelSize, diagnosis, specimenModality, dataType, dataSubtype, visitID, program, project, biospecimenType, species, primaryCellSource, cellType, userDefinedCellType","","","","","","","" "assay","The technology used to generate the data in this file.","Olink Explore HT, Olink Reveal, Olink Flex, Olink Focus, Olink Target 48, Olink Target 96","","","TRUE","","","","","string" "platform","The specific instrument (manufacturer, model, etc.) that was used to carry out a laboratory or computational experiment.","Olink Signature Q100, Fluidigm BioMark, Illumina NextSeq 500, Illumina NovaSeq 6000, unknown","","","FALSE","","","","list like error","string" "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.","","","","TRUE","","","","^^#OlinkAssayMetadataTemplate unique error^^list like error","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, programPhase","","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","","","","","","","" "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, info, mcd, mtx, parquet, pdf, rds, rec, svs, tbi, tgz, tsv, txt, vcf, xls, xlsx, zip","","","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, info, mcd, mtx, parquet, pdf, py, rds, rec, svs, tbi, tgz, tsv, txt, vcf, xls, xlsx, zip","","","True","","","","","string" "publicationSynID","The synID of the corresponding Synapse entity that stores metadata about the publication. This is used to differentiate publication-specific files, often consisting of level 4 processed data and expanded subject metadata, in a publication dataset that also includes raw or minimally processed files from experimental datasets. This provides an easy way to distinguish and select for the publication-specific data from which the research findings were derived. When this attribute is used to annotate a Dataset it serves as a way to directly link the Dataset entity with the publication metadata stored in Synapse.","","","","False","","","","regex search ^syn[0-9]{8} error","string" "associatedDataset","The synID of a Dataset entity. This serves to link other Synapse entities to Dataset entities. When used to annotate a publication Dataset this attribute should include the synID for an experimental Datasets from which the publication data was derived. Multiple synID can be specified using a comma-delimited list.","","","","False","","","","list like::regex search ^syn[0-9]{8} error","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, ELLIPSS, LOCKIT, RA, SLE, STAMP, V-CoRT","","","True","","","","list like error","string" +"project","A sub-level attribute of `program` specifying a research initiative working to investigate particular hypotheses.","AIM for RA, ELLIPSS, LOCKIT, RA, SLE, STAMP, UMass V-CoRT","","","True","","","","list like error","string" "programPhase","A label noting which AMP RA/SLE program phase generated the data.","I, II","","","True","","","","list like error","string" "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" @@ -20,7 +20,7 @@ "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" "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" "custom10xProbeSetSynID","If custom modified probe sets were used for collecting 10x Chromium Flex scRNA-seq data, then the probe reference files should be grouped as a zip or tar archive and uploaded as metadata. This attribute links the experimental data back to the probe set archive file via a synapse ID.","","","","True","","","","regex search ^syn[0-9]{8} error","string" -"specimenModality","Label assigned to experimental data files indicating whether the data contained corresponds to a single or multiple biospecimens","multispecimen, single specimen","","","True","","","","","string" +"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" "individualID","Unique identifier assigned to each study participant. For multi-specimen data files provide all IDs in a comma-separated list.","","","","True","","","","#ClinicalMetadataTemplate unique error^^#BiospecimenMetadataTemplate str^^list like error","string" "biospecimenID","A unique identifier assigned to specimens collected from study participants. For multi-specimen data files provide all IDs in a comma-separated list.","","","","True","","","","#BiospecimenMetadataTemplate unique error^^list like error","string" "parentBiospecimenID","The biospecimenID associated with the originating biospecimen for derived or child biospecimens.","","","","False","","","","","string" @@ -36,15 +36,14 @@ "nucleicAcidSource","The source of the nucleic acid used as input for sequencing library fragments. Select all that apply, though in most cases only a single label is expected.","BCR mRNA, CRISPR protospacer feature barcode, TCR mRNA, Tn5-accessible gDNA, antigen capture barcode, gDNA, globin-depleted RNA, intracellular protein feature barcode, multiplexing oligo, poly(A) RNA, rRNA-depleted RNA, surface protein feature barcode","","","True","","","","list like error","string" "biospecimenSubtype","Biospecimen status before sample is processed into a scRNA-seq library. Several scRNA-seq technologies support a variety of sample processing methods which can introduces sources of technical variation.","FFPE tissue, PFA-fixed tissue, cell or tissue lysate, cell suspension, flow-sorted cells, fresh tissue, frozen tissue, nuclei suspension, supernatant","","","False","","","","","string" "cellRangerOutput","10x Genomics Cell Ranger software output several different counts results and formats, some with different processing applied. This label distinguishes between these types and is particularly helpful when multiple files are uploaded with the sample name, e.g., barcodes.tsv.gz","Not Applicable, filtered MEX, filtered_feature_bc_matrix, filtered_peak_bc_matrix, raw MEX, raw_feature_bc_matrix, raw_peak_bc_matrix","","","True","","","","","string" -"alignmentReference","The genomic/transcriptomic reference used for performing read alignment against.","10x Cell Ranger Human GRCh38 2020-A, 10x Cell Ranger Human GRCh38 2024-A, modified GRCh38, unknown, vdj_GRCh38_alts_ensembl-4.0.0","","","True","","","","","string" -"libraryPrepMethod","Sequencing library preparation method or kit used to create the library. If no commercially available kit was used, please select 'in-house library prep'.","10x Chromium Fixed RNA Human Transcriptome, 10x Chromium GEM-X Single Cell 3' v4, 10x Chromium GEM-X Single Cell 5' v3, 10x Chromium Next GEM Single Cell 3', 10x Chromium Next GEM Single Cell 3' 3.1, 10x Chromium Next GEM Single Cell 5' v1.1, 10x Chromium Next GEM Single Cell 5' v2, 10x Chromium Next GEM Single Cell ATAC v2, 10x Chromium Single Cell Human BCR, 10x Chromium Single Cell Human TCR, 10x GEM-X Flex Gene Expression Human, 10x GEM-X Universal 5? Gene Expression v3, CEL-Seq2, Chromium Next GEM Single Cell ATAC v1.1, Fluidigm C1 HT, NEBNext Human Immune Sequencing Kit, NEBNext Ultra II Directional RNA Library, Nextera XT, Nextera XT DNA, QIAseq miRNA Library, SMART-Seq Human BCR with UMI, SMART-Seq Human TCR with UMI, SMART-Seq v4 Ultra Low Input RNA, SMARTer Stranded Total RNA v2, Takara Human BCR profiling for Illumina, Takara Human TCR profiling for Illumina, Takara Human TCRv2 profiling for Illumina, Takara Human scTCR profiling for Illumina, TruSeq Stranded mRNA, custom DASH-treatment, in-house library prep","","","True","","","","","string" +"alignmentReference","The genomic/transcriptomic reference used for performing read alignment against.","10x Cell Ranger Human GRCh38 2020-A, 10x Cell Ranger Human GRCh38 2024-A, GRCh38, modified GRCh38, unknown, vdj_GRCh38_alts_ensembl-4.0.0","","","True","","","","","string" +"libraryPrepMethod","Sequencing library preparation method or kit used to create the library. If no commercially available kit was used, please select 'in-house library prep'.","10x Chromium Fixed RNA Human Transcriptome, 10x Chromium GEM-X Single Cell 3' v4, 10x Chromium GEM-X Single Cell 5' v3, 10x Chromium Next GEM Single Cell 3', 10x Chromium Next GEM Single Cell 3' 3.1, 10x Chromium Next GEM Single Cell 5' v1.1, 10x Chromium Next GEM Single Cell 5' v2, 10x Chromium Next GEM Single Cell ATAC v2, 10x Chromium Single Cell Human BCR, 10x Chromium Single Cell Human TCR, 10x GEM-X Flex Gene Expression Human, 10x GEM-X Universal 5' Gene Expression v3, CEL-Seq2, Chromium Next GEM Single Cell ATAC v1.1, Fluidigm C1 HT, NEBNext Human Immune Sequencing Kit, NEBNext Ultra II Directional RNA Library, Nextera XT, Nextera XT DNA, QIAseq miRNA Library, SMART-Seq Human BCR with UMI, SMART-Seq Human TCR with UMI, SMART-Seq v4 Ultra Low Input RNA, SMARTer Stranded Total RNA v2, Takara Human BCR profiling for Illumina, Takara Human TCR profiling for Illumina, Takara Human TCRv2 profiling for Illumina, Takara Human scTCR profiling for Illumina, TruSeq Stranded mRNA, custom DASH-treatment, in-house library prep","","","True","","","","","string" "datasetType","High-level classification of dataset entity distinguishing between datasets compiled for a specific publication or as a general data resource.","experimental, publication","","","True","","","","","string" "acknowledgmentStatement","A Dataset-specific attribute specifying the path to the wiki subpage within the ARK Portal - backend project that contains the acknowledgement statement that must be included in publications using data from the given dataset as a stipulation of the conditions of use.","syn26710600/wiki/619685","","","True","","","","","string" "datasetDescription","A Dataset-specific attribute specifying the synID of the folder that contains a wiki write-up of the dataset description. This wiki content will be surfaced on the ARK Portal frontend site.","","","","True","","","","regex search ^syn[0-9]{8} error","string" "ARKRelease","A Dataset-specific attribute specifying the ARK Portal release in which this dataset was first made available to the public.","1.0, 2.0, 2024.06.R1, 2024.07.R1, 2024.08.R1, 2024.09.R1, 2024.10.R1, 2024.12.R1, 2025.01.R1, 2025.02.R1, 2025.03.R1, 2025.04.R1, 2025.05.R1, 2025.06.R1, 2025.07.R1, 2025.08.R1, 2025.09.R1, 2025.10.R1, 2025.11.R1, 2025.12.R1","","","True","","","","","string" "RObjectClass","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.","ROCR prediction.object, Seurat object, SummarizedExperiment, Symphony reference, data.frame, list, matrix, sparse matrix, vector","","","False","","","","","string" -"dbGapAccession","NIH policy requires large-scale human genomics studies to be registered in dbGap. This is a Dataset-specific attribute indicating the unique identifier (i.e., accession) of the corresponding study that is registered in dbGap, formatted as a compact URI, e.g., dbgap:phs003417.v2.p1","","","","False","","","","regex search ^dbgap:","string" -"diagnosis","A high-level classifier indicating the disease status of an individual.","At-Risk RA, OA, RA, SLE, Sjogren's disease, control, cutaneous lupus erythematosus, dermatomyositis, lupus nephritis, psoriasis, psoriatic arthritis, scleroderma, unknown, vitiligo","","","True","","","","list like error","string" +"diagnosis","A high-level classifier indicating the disease status of an individual.","At-Risk RA, Not Applicable, OA, RA, SLE, Sjogren's disease, control, cutaneous lupus erythematosus, dermatomyositis, discoid lupus erythematosus, lupus nephritis, psoriasis, psoriatic arthritis, scleroderma, unknown, vitiligo","","","True","","","","list like error","string" "DOID","Disease ontology identifier associated with `diagnosis`. Attribute values are applied by ARK Portal data managers.","","","","True","","","","regex search ^DOID error","string" "libraryID","A library label or name, unique within an experiment, used to distinguish sequencing libraries.","","","","True","","","","","string" "associatedCodeURL","A URL to the repository where associated code is available.","","","","False","","","","","string" @@ -61,7 +60,7 @@ "PMID","PubMed(R) Identifier","","","","True","","","","regex search ^PMID error","string" "DOI","Digital object identifier","","","","True","","","","","string" "anatomicalSite","The anatomical site, i.e., location on or within the body, from which the biospecimen was collected. This attribute is required depending on the value selected for biospecimenType.","left 2nd MCP joint, left ankle joint, left hip joint, left knee joint, left wrist joint, other site, right 1st MTP joint, right 2nd MCP joint, right 2nd MTP joint, right 3rd MCP joint, right ankle joint, right hip joint, right knee joint, right wrist joint, unknown","","","True","","","","","string" -"vitiligoType","A high-level classification of vitiligo based on the distribution and patterning of lesions across the body.","mixed, non-segmental, segmental, unclassified","","","False","","","","","string" +"vitiligoPattern","A high-level classification of vitiligo based on the distribution and patterning of lesions across the body.","mixed, non-segmental, segmental, unclassified","","","False","","","","","string" "vitiligoPhenotype","Classification of vitiligo lesions which correlate with autoimmune activity and result in specific skin and depigmentation manifestations at the lesion site. If N/A please select 'none'. Multiple selections can be provided in a comma-delimited list.","active, confetti, inflammatory, none, trichrome","","","True","","","","list like error","string" "psoriasisType","General type classification of psoriasis disease manifestation.","erythrodermic, guttate, inverse, plaque, pustular","","","False","","","","","string" "ageDiagnosis","Age at which subject was diagnosed with `diagnosis`. If providing this value be sure the unit matches that used for `age`.","","","","False","","","","num error","number" @@ -111,3 +110,5 @@ "treatmentTimepoint","Where applicable, specify the timepoint relative to treatment to distinguish different sets of samples that have undergone the same treatment but for different lengths of time. REQUIRED: please specify the unit of time, e.g., secs, mins, hrs, days, etc.","","","","False","","","","","string" "slideID","A distinct label or name, unique within an experiment, assigned to an imaging slides.","","","","True","","","","","string" "altSampleID","An alternate identifier for a sample. With some assays there can be default or alternate sample identifiers entered into the data collection software. If you will be uploading data collected with an alternate identifier please provide that here. In some cases, the ARK BDM team will use this field to capture original but out-dated identifiers for samples.","","","","False","","","","","string" +"sampleCollectionBatch","A label indicating batching of sample collection or experiment execution that occurs prior to data collection.","","","","False","","","","","string" +"associatedAccession","This is a File and Dataset annotation attribute indicating additional accessions (i.e., unique identifiers) associated with the data when the data has also been submitted to or can be found in other repositories such as GEO, SRA, dbGaP, etc.","","","","False","","","","list like error","string" diff --git a/model_contexts/olink/ark.olink_model.jsonld b/model_contexts/olink/ark.olink_model.jsonld index 9b1f748..00f562c 100644 --- a/model_contexts/olink/ark.olink_model.jsonld +++ b/model_contexts/olink/ark.olink_model.jsonld @@ -320,6 +320,9 @@ { "@id": "bts:Pdf" }, + { + "@id": "bts:Py" + }, { "@id": "bts:Rds" }, @@ -408,6 +411,9 @@ }, { "@id": "bts:Singlespecimen" + }, + { + "@id": "bts:Unknown" } ], "sms:displayName": "specimenModality", @@ -480,6 +486,15 @@ }, { "@id": "bts:Species" + }, + { + "@id": "bts:PrimaryCellSource" + }, + { + "@id": "bts:CellType" + }, + { + "@id": "bts:UserDefinedCellType" } ], "sms:validationRules": [] @@ -501,6 +516,9 @@ { "@id": "bts:At-RiskRA" }, + { + "@id": "bts:NotApplicable" + }, { "@id": "bts:OA" }, @@ -522,6 +540,9 @@ { "@id": "bts:Dermatomyositis" }, + { + "@id": "bts:Discoidlupuserythematosus" + }, { "@id": "bts:Lupusnephritis" }, @@ -721,7 +742,7 @@ "@id": "bts:STAMP" }, { - "@id": "bts:V-CoRT" + "@id": "bts:UMassV-CoRT" } ], "sms:displayName": "project", @@ -838,6 +859,89 @@ "sms:required": "sms:true", "sms:validationRules": [] }, + { + "@id": "bts:PrimaryCellSource", + "@type": "rdfs:Class", + "rdfs:comment": "A label indicating the biological source material from which a primary cell culture was derived.", + "rdfs:label": "PrimaryCellSource", + "rdfs:subClassOf": [ + { + "@id": "bts:Thing" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "schema:rangeIncludes": [ + { + "@id": "bts:PBMCs" + }, + { + "@id": "bts:Kidney" + }, + { + "@id": "bts:Pannus-deriveddermis" + }, + { + "@id": "bts:Pannus-derivedepidermis" + }, + { + "@id": "bts:Salivarygland" + }, + { + "@id": "bts:Synovialtissue" + }, + { + "@id": "bts:Totalleukocytes" + }, + { + "@id": "bts:Urine" + }, + { + "@id": "bts:Uvea" + }, + { + "@id": "bts:Wholeblood" + } + ], + "sms:displayName": "primaryCellSource", + "sms:required": "sms:true", + "sms:validationRules": [] + }, + { + "@id": "bts:CellType", + "@type": "rdfs:Class", + "rdfs:comment": "The cell type name from Cell Ontology for the corresponding CL identifier.", + "rdfs:label": "CellType", + "rdfs:subClassOf": [ + { + "@id": "bts:Thing" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "cellType", + "sms:required": "sms:false", + "sms:validationRules": [] + }, + { + "@id": "bts:UserDefinedCellType", + "@type": "rdfs:Class", + "rdfs:comment": "User-defined label of a cell type. Contributors are provided this option to use preferred or custom cell type labels that may vary from options and standards set by Cell Ontology.", + "rdfs:label": "UserDefinedCellType", + "rdfs:subClassOf": [ + { + "@id": "bts:Thing" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "userDefinedCellType", + "sms:required": "sms:false", + "sms:validationRules": [] + }, { "@id": "bts:OlinkExploreHT", "@type": "rdfs:Class", @@ -1015,10 +1119,10 @@ "rdfs:label": "Unknown", "rdfs:subClassOf": [ { - "@id": "bts:Ethnicity" + "@id": "bts:SpecimenModality" }, { - "@id": "bts:AlignmentReference" + "@id": "bts:Ethnicity" }, { "@id": "bts:SynovialCollectionProcedure" @@ -1032,6 +1136,9 @@ { "@id": "bts:Platform" }, + { + "@id": "bts:AlignmentReference" + }, { "@id": "bts:Race" }, @@ -1463,6 +1570,23 @@ "sms:required": "sms:false", "sms:validationRules": [] }, + { + "@id": "bts:Py", + "@type": "rdfs:Class", + "rdfs:comment": "TBD", + "rdfs:label": "Py", + "rdfs:subClassOf": [ + { + "@id": "bts:FileFormat" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "py", + "sms:required": "sms:false", + "sms:validationRules": [] + }, { "@id": "bts:Rds", "@type": "rdfs:Class", @@ -1764,10 +1888,10 @@ "rdfs:label": "RA", "rdfs:subClassOf": [ { - "@id": "bts:Diagnosis" + "@id": "bts:Project" }, { - "@id": "bts:Project" + "@id": "bts:Diagnosis" } ], "schema:isPartOf": { @@ -1784,10 +1908,10 @@ "rdfs:label": "SLE", "rdfs:subClassOf": [ { - "@id": "bts:Diagnosis" + "@id": "bts:Project" }, { - "@id": "bts:Project" + "@id": "bts:Diagnosis" } ], "schema:isPartOf": { @@ -1815,10 +1939,10 @@ "sms:validationRules": [] }, { - "@id": "bts:V-CoRT", + "@id": "bts:UMassV-CoRT", "@type": "rdfs:Class", "rdfs:comment": "TBD", - "rdfs:label": "V-CoRT", + "rdfs:label": "UMassV-CoRT", "rdfs:subClassOf": [ { "@id": "bts:Project" @@ -1827,7 +1951,7 @@ "schema:isPartOf": { "@id": "http://schema.biothings.io" }, - "sms:displayName": "V-CoRT", + "sms:displayName": "UMass V-CoRT", "sms:required": "sms:false", "sms:validationRules": [] }, @@ -2955,55 +3079,6 @@ "sms:required": "sms:false", "sms:validationRules": [] }, - { - "@id": "bts:PrimaryCellSource", - "@type": "rdfs:Class", - "rdfs:comment": "A label indicating the biological source material from which a primary cell culture was derived.", - "rdfs:label": "PrimaryCellSource", - "rdfs:subClassOf": [ - { - "@id": "bts:Thing" - } - ], - "schema:isPartOf": { - "@id": "http://schema.biothings.io" - }, - "schema:rangeIncludes": [ - { - "@id": "bts:PBMCs" - }, - { - "@id": "bts:Kidney" - }, - { - "@id": "bts:Pannus-deriveddermis" - }, - { - "@id": "bts:Pannus-derivedepidermis" - }, - { - "@id": "bts:Salivarygland" - }, - { - "@id": "bts:Synovialtissue" - }, - { - "@id": "bts:Totalleukocytes" - }, - { - "@id": "bts:Urine" - }, - { - "@id": "bts:Uvea" - }, - { - "@id": "bts:Wholeblood" - } - ], - "sms:displayName": "primaryCellSource", - "sms:required": "sms:true", - "sms:validationRules": [] - }, { "@id": "bts:Kidney", "@type": "rdfs:Class", @@ -4729,6 +4804,9 @@ "rdfs:subClassOf": [ { "@id": "bts:CellRangerOutput" + }, + { + "@id": "bts:Diagnosis" } ], "schema:isPartOf": { @@ -4860,6 +4938,9 @@ { "@id": "bts:10xCellRangerHumanGRCh382024-A" }, + { + "@id": "bts:GRCh38" + }, { "@id": "bts:ModifiedGRCh38" }, @@ -4908,6 +4989,23 @@ "sms:required": "sms:false", "sms:validationRules": [] }, + { + "@id": "bts:GRCh38", + "@type": "rdfs:Class", + "rdfs:comment": "TBD", + "rdfs:label": "GRCh38", + "rdfs:subClassOf": [ + { + "@id": "bts:AlignmentReference" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "GRCh38", + "sms:required": "sms:false", + "sms:validationRules": [] + }, { "@id": "bts:ModifiedGRCh38", "@type": "rdfs:Class", @@ -4990,7 +5088,7 @@ "@id": "bts:10xGEM-XFlexGeneExpressionHuman" }, { - "@id": "bts:10xGEM-XUniversal5?GeneExpressionv3" + "@id": "bts:10xGEM-XUniversal5'GeneExpressionv3" }, { "@id": "bts:CEL-Seq2" @@ -5242,10 +5340,10 @@ "sms:validationRules": [] }, { - "@id": "bts:10xGEM-XUniversal5?GeneExpressionv3", + "@id": "bts:10xGEM-XUniversal5'GeneExpressionv3", "@type": "rdfs:Class", "rdfs:comment": "TBD", - "rdfs:label": "10xGEM-XUniversal5?GeneExpressionv3", + "rdfs:label": "10xGEM-XUniversal5'GeneExpressionv3", "rdfs:subClassOf": [ { "@id": "bts:LibraryPrepMethod" @@ -5254,7 +5352,7 @@ "schema:isPartOf": { "@id": "http://schema.biothings.io" }, - "sms:displayName": "10x GEM-X Universal 5? Gene Expression v3", + "sms:displayName": "10x GEM-X Universal 5' Gene Expression v3", "sms:required": "sms:false", "sms:validationRules": [] }, @@ -6316,25 +6414,6 @@ "sms:required": "sms:false", "sms:validationRules": [] }, - { - "@id": "bts:DbGapAccession", - "@type": "rdfs:Class", - "rdfs:comment": "NIH policy requires large-scale human genomics studies to be registered in dbGap. This is a Dataset-specific attribute indicating the unique identifier (i.e., accession) of the corresponding study that is registered in dbGap, formatted as a compact URI, e.g., dbgap:phs003417.v2.p1", - "rdfs:label": "DbGapAccession", - "rdfs:subClassOf": [ - { - "@id": "bts:Thing" - } - ], - "schema:isPartOf": { - "@id": "http://schema.biothings.io" - }, - "sms:displayName": "dbGapAccession", - "sms:required": "sms:false", - "sms:validationRules": [ - "regex search ^dbgap:" - ] - }, { "@id": "bts:At-RiskRA", "@type": "rdfs:Class", @@ -6437,6 +6516,23 @@ "sms:required": "sms:false", "sms:validationRules": [] }, + { + "@id": "bts:Discoidlupuserythematosus", + "@type": "rdfs:Class", + "rdfs:comment": "TBD", + "rdfs:label": "Discoidlupuserythematosus", + "rdfs:subClassOf": [ + { + "@id": "bts:Diagnosis" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "discoid lupus erythematosus", + "sms:required": "sms:false", + "sms:validationRules": [] + }, { "@id": "bts:Lupusnephritis", "@type": "rdfs:Class", @@ -7347,10 +7443,10 @@ "sms:validationRules": [] }, { - "@id": "bts:VitiligoType", + "@id": "bts:VitiligoPattern", "@type": "rdfs:Class", "rdfs:comment": "A high-level classification of vitiligo based on the distribution and patterning of lesions across the body.", - "rdfs:label": "VitiligoType", + "rdfs:label": "VitiligoPattern", "rdfs:subClassOf": [ { "@id": "bts:Thing" @@ -7373,7 +7469,7 @@ "@id": "bts:Unclassified" } ], - "sms:displayName": "vitiligoType", + "sms:displayName": "vitiligoPattern", "sms:required": "sms:false", "sms:validationRules": [] }, @@ -7384,7 +7480,7 @@ "rdfs:label": "Mixed", "rdfs:subClassOf": [ { - "@id": "bts:VitiligoType" + "@id": "bts:VitiligoPattern" } ], "schema:isPartOf": { @@ -7401,7 +7497,7 @@ "rdfs:label": "Non-segmental", "rdfs:subClassOf": [ { - "@id": "bts:VitiligoType" + "@id": "bts:VitiligoPattern" } ], "schema:isPartOf": { @@ -7418,7 +7514,7 @@ "rdfs:label": "Segmental", "rdfs:subClassOf": [ { - "@id": "bts:VitiligoType" + "@id": "bts:VitiligoPattern" } ], "schema:isPartOf": { @@ -7435,7 +7531,7 @@ "rdfs:label": "Unclassified", "rdfs:subClassOf": [ { - "@id": "bts:VitiligoType" + "@id": "bts:VitiligoPattern" } ], "schema:isPartOf": { @@ -8820,40 +8916,6 @@ "regex search ^CL: error" ] }, - { - "@id": "bts:CellType", - "@type": "rdfs:Class", - "rdfs:comment": "The cell type name from Cell Ontology for the corresponding CL identifier.", - "rdfs:label": "CellType", - "rdfs:subClassOf": [ - { - "@id": "bts:Thing" - } - ], - "schema:isPartOf": { - "@id": "http://schema.biothings.io" - }, - "sms:displayName": "cellType", - "sms:required": "sms:false", - "sms:validationRules": [] - }, - { - "@id": "bts:UserDefinedCellType", - "@type": "rdfs:Class", - "rdfs:comment": "User-defined label of a cell type. Contributors are provided this option to use preferred or custom cell type labels that may vary from options and standards set by Cell Ontology.", - "rdfs:label": "UserDefinedCellType", - "rdfs:subClassOf": [ - { - "@id": "bts:Thing" - } - ], - "schema:isPartOf": { - "@id": "http://schema.biothings.io" - }, - "sms:displayName": "userDefinedCellType", - "sms:required": "sms:false", - "sms:validationRules": [] - }, { "@id": "bts:KrennInflammatory", "@type": "rdfs:Class", @@ -9494,6 +9556,42 @@ "sms:displayName": "altSampleID", "sms:required": "sms:false", "sms:validationRules": [] + }, + { + "@id": "bts:SampleCollectionBatch", + "@type": "rdfs:Class", + "rdfs:comment": "A label indicating batching of sample collection or experiment execution that occurs prior to data collection.", + "rdfs:label": "SampleCollectionBatch", + "rdfs:subClassOf": [ + { + "@id": "bts:Thing" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "sampleCollectionBatch", + "sms:required": "sms:false", + "sms:validationRules": [] + }, + { + "@id": "bts:AssociatedAccession", + "@type": "rdfs:Class", + "rdfs:comment": "This is a File and Dataset annotation attribute indicating additional accessions (i.e., unique identifiers) associated with the data when the data has also been submitted to or can be found in other repositories such as GEO, SRA, dbGaP, etc.", + "rdfs:label": "AssociatedAccession", + "rdfs:subClassOf": [ + { + "@id": "bts:Thing" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "associatedAccession", + "sms:required": "sms:false", + "sms:validationRules": [ + "list like error" + ] } ], "@id": "http://schema.biothings.io/#0.1" diff --git a/model_contexts/singlecell/ark.singlecell_context.csv b/model_contexts/singlecell/ark.singlecell_context.csv index 69cdef6..69df702 100644 --- a/model_contexts/singlecell/ark.singlecell_context.csv +++ b/model_contexts/singlecell/ark.singlecell_context.csv @@ -1,19 +1,19 @@ -Attribute,Description,Valid Values,DependsOn,Properties,Required,Parent,DependsOn Component,Source,Validation Rules,columnType -single specimen,Is a valid value of `specimenModality` that triggers conditional dependencies for additional attributes.,,"biospecimenID, individualID",,,,,,, -resourceType,,"experimental data, metadata",,,TRUE,,,,list like error,string -fileFormat,Standard file format name or file extension,"csv, tsv, txt, xlsx, xls, fam, bim, bed, bam, h5, mtx, bai, rds, tgz, zip, h5ad",,,TRUE,,,,,string -feature barcode sequencing,Is a valid value of `assay` that triggers conditional dependencies for additional attributes.,,"targetPanel, targetPanelSynID, targetPanelSize",,,,,,, -Rds,Is a valid value of 'fileFormat' that triggers conditional dependencies for additional attributes.,,RObjectClass,,,,,,, -experimental data,Is a valid value of 'resourceType' that triggers conditional dependencies for additional attributes.,,processedDataType,,,,,,, -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,,FALSE,,,,, -metadataType,,single-cell metadata,,,TRUE,,,,,string -scRNASeq Processed Data Annotation Template,"A data contributor template outlining metadata to be collected as file annotations for scRNA-seq processed data files (i.e., anything not a fastq file).",,"Component, fileFormat, assay, resourceType, dataLevel, specimenModality, cellRangerOutput",,,,,,, -BDM scRNASeq Processed Data Annotations,"A template outlining metadata to be collected as file annotations for scRNA-seq processed data files (i.e., anything not a fastq file). to be compiled by ARK BDM.",,"Component, fileFormat, assay, resourceType, dataLevel, specimenModality, cellRangerOutput, parentBiospecimenID, biospecimenType, biospecimenSubtype, dataType, dataSubtype, diagnosis, visitID, libraryPrepMethod, nucleicAcidSource, alignmentReference, softwareAndVersion, program, project, species",,,,,,, -snRNASeq Processed Data Annotation Template,"A data contributor template outlining metadata to be collected as file annotations for snRNA-seq processed data files (i.e., anything not a fastq file).",,"Component, fileFormat, assay, resourceType, dataLevel, specimenModality, cellRangerOutput",,,,,,, -BDM snRNASeq Processed Data Annotations,"A template outlining metadata to be collected as file annotations for snRNA-seq processed data files (i.e., anything not a fastq file). to be compiled by ARK BDM.",,"Component, fileFormat, assay, resourceType, dataLevel, specimenModality, cellRangerOutput, parentBiospecimenID, biospecimenType, biospecimenSubtype, dataType, dataSubtype, diagnosis, visitID, libraryPrepMethod, nucleicAcidSource, alignmentReference, softwareAndVersion, program, project, species",,,,,,, -snATACSeq Processed Data Annotation Template,"A data contributor template outlining metadata to be collected as file annotations for snATAC-seq processed data files (i.e., anything not a fastq file).",,"Component, fileFormat, assay, resourceType, dataLevel, specimenModality, cellRangerOutput",,,,,,, -BDM snATACSeq Processed Data Annotations,"A template outlining metadata to be collected as file annotations for snATAC-seq processed data files (i.e., anything not a fastq file). to be compiled by ARK BDM.",,"Component, fileFormat, assay, resourceType, dataLevel, specimenModality, cellRangerOutput, parentBiospecimenID, biospecimenType, biospecimenSubtype, dataType, dataSubtype, diagnosis, visitID, libraryPrepMethod, nucleicAcidSource, alignmentReference, softwareAndVersion, program, project, species",,,,,,, -scVDJSeq Processed Data Annotation Template,"A data contributor template outlining metadata to be collected as file annotations for scVDJ-seq (i.e., immune repertoire profiling) processed data files (i.e., anything not a fastq file).",,"Component, fileFormat, assay, resourceType, dataLevel, specimenModality",,,,,,, -BDM scVDJSeq Processed Data Annotations,"A template outlining metadata to be collected as file annotations for scVDJ-seq (i.e., immune repertoire profiling) processed data files (i.e., anything not a fastq file). to be compiled by ARK BDM.",,"Component, fileFormat, assay, resourceType, dataLevel, specimenModality, parentBiospecimenID, biospecimenType, biospecimenSubtype, dataType, dataSubtype, diagnosis, visitID, libraryPrepMethod, nucleicAcidSource, alignmentReference, softwareAndVersion, program, project, species",,,,,,, -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,,,,,,, -AMP AIM,Accelerating Medicines Partnership Autoimmune and Immune-Mediated Diseases. Is a valid value for 'program' that triggers conditional dependencies for additional attributes.,,visitID,,,,,,, \ No newline at end of file +"Attribute","Description","Valid Values","DependsOn","Properties","Required","Parent","DependsOn Component","Source","Validation Rules","columnType" +"single specimen","Is a valid value of `specimenModality` that triggers conditional dependencies for additional attributes.","","biospecimenID, individualID","","","","","","","" +"resourceType","","experimental data, metadata","","","TRUE","","","","list like error","string" +"fileFormat","Standard file format name or file extension","csv, tsv, txt, xlsx, xls, fam, bim, bed, bam, h5, mtx, bai, rds, tgz, zip, h5ad","","","TRUE","","","","","string" +"feature barcode sequencing","Is a valid value of `assay` that triggers conditional dependencies for additional attributes.","","targetPanel, targetPanelSynID, targetPanelSize","","","","","","","" +"Rds","Is a valid value of 'fileFormat' that triggers conditional dependencies for additional attributes.","","RObjectClass","","","","","","","" +"experimental data","Is a valid value of 'resourceType' that triggers conditional dependencies for additional attributes.","","processedDataType","","","","","","","" +"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","","FALSE","","","","","" +"metadataType","","single-cell metadata","","","TRUE","","","","","string" +"scRNASeq Processed Data Annotation Template","A data contributor template outlining metadata to be collected as file annotations for scRNA-seq processed data files (i.e., anything not a fastq file).","","Component, fileFormat, assay, resourceType, dataLevel, specimenModality, cellRangerOutput","","","","","","","" +"BDM scRNASeq Processed Data Annotations","A template outlining metadata to be collected as file annotations for scRNA-seq processed data files (i.e., anything not a fastq file). to be compiled by ARK BDM.","","Component, fileFormat, assay, resourceType, dataLevel, specimenModality, cellRangerOutput, parentBiospecimenID, biospecimenType, biospecimenSubtype, dataType, dataSubtype, diagnosis, visitID, libraryPrepMethod, nucleicAcidSource, alignmentReference, softwareAndVersion, program, project, species, primaryCellSource, cellType, userDefinedCellType","","","","","","","" +"snRNASeq Processed Data Annotation Template","A data contributor template outlining metadata to be collected as file annotations for snRNA-seq processed data files (i.e., anything not a fastq file).","","Component, fileFormat, assay, resourceType, dataLevel, specimenModality, cellRangerOutput","","","","","","","" +"BDM snRNASeq Processed Data Annotations","A template outlining metadata to be collected as file annotations for snRNA-seq processed data files (i.e., anything not a fastq file). to be compiled by ARK BDM.","","Component, fileFormat, assay, resourceType, dataLevel, specimenModality, cellRangerOutput, parentBiospecimenID, biospecimenType, biospecimenSubtype, dataType, dataSubtype, diagnosis, visitID, libraryPrepMethod, nucleicAcidSource, alignmentReference, softwareAndVersion, program, project, species, primaryCellSource, cellType, userDefinedCellType","","","","","","","" +"snATACSeq Processed Data Annotation Template","A data contributor template outlining metadata to be collected as file annotations for snATAC-seq processed data files (i.e., anything not a fastq file).","","Component, fileFormat, assay, resourceType, dataLevel, specimenModality, cellRangerOutput","","","","","","","" +"BDM snATACSeq Processed Data Annotations","A template outlining metadata to be collected as file annotations for snATAC-seq processed data files (i.e., anything not a fastq file). to be compiled by ARK BDM.","","Component, fileFormat, assay, resourceType, dataLevel, specimenModality, cellRangerOutput, parentBiospecimenID, biospecimenType, biospecimenSubtype, dataType, dataSubtype, diagnosis, visitID, libraryPrepMethod, nucleicAcidSource, alignmentReference, softwareAndVersion, program, project, species, primaryCellSource, cellType, userDefinedCellType","","","","","","","" +"scVDJSeq Processed Data Annotation Template","A data contributor template outlining metadata to be collected as file annotations for scVDJ-seq (i.e., immune repertoire profiling) processed data files (i.e., anything not a fastq file).","","Component, fileFormat, assay, resourceType, dataLevel, specimenModality","","","","","","","" +"BDM scVDJSeq Processed Data Annotations","A template outlining metadata to be collected as file annotations for scVDJ-seq (i.e., immune repertoire profiling) processed data files (i.e., anything not a fastq file). to be compiled by ARK BDM.","","Component, fileFormat, assay, resourceType, dataLevel, specimenModality, parentBiospecimenID, biospecimenType, biospecimenSubtype, dataType, dataSubtype, diagnosis, visitID, libraryPrepMethod, nucleicAcidSource, alignmentReference, softwareAndVersion, program, project, species, primaryCellSource, cellType, userDefinedCellType","","","","","","","" +"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","","","","","","","" +"AMP AIM","Accelerating Medicines Partnership Autoimmune and Immune-Mediated Diseases. Is a valid value for 'program' that triggers conditional dependencies for additional attributes.","","visitID","","","","","","","" diff --git a/model_contexts/singlecell/ark.singlecell_model.csv b/model_contexts/singlecell/ark.singlecell_model.csv index 6264d59..8ee3ad4 100644 --- a/model_contexts/singlecell/ark.singlecell_model.csv +++ b/model_contexts/singlecell/ark.singlecell_model.csv @@ -8,20 +8,20 @@ "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","","FALSE","","","","","" "metadataType","A label further classifying the content of metadata resource.","single-cell metadata","","","TRUE","","","","","string" "scRNASeq Processed Data Annotation Template","A data contributor template outlining metadata to be collected as file annotations for scRNA-seq processed data files (i.e., anything not a fastq file).","","Component, fileFormat, assay, resourceType, dataLevel, specimenModality, cellRangerOutput","","","","","","","" -"BDM scRNASeq Processed Data Annotations","A template outlining metadata to be collected as file annotations for scRNA-seq processed data files (i.e., anything not a fastq file). to be compiled by ARK BDM.","","Component, fileFormat, assay, resourceType, dataLevel, specimenModality, cellRangerOutput, parentBiospecimenID, biospecimenType, biospecimenSubtype, dataType, dataSubtype, diagnosis, visitID, libraryPrepMethod, nucleicAcidSource, alignmentReference, softwareAndVersion, program, project, species","","","","","","","" +"BDM scRNASeq Processed Data Annotations","A template outlining metadata to be collected as file annotations for scRNA-seq processed data files (i.e., anything not a fastq file). to be compiled by ARK BDM.","","Component, fileFormat, assay, resourceType, dataLevel, specimenModality, cellRangerOutput, parentBiospecimenID, biospecimenType, biospecimenSubtype, dataType, dataSubtype, diagnosis, visitID, libraryPrepMethod, nucleicAcidSource, alignmentReference, softwareAndVersion, program, project, species, primaryCellSource, cellType, userDefinedCellType","","","","","","","" "snRNASeq Processed Data Annotation Template","A data contributor template outlining metadata to be collected as file annotations for snRNA-seq processed data files (i.e., anything not a fastq file).","","Component, fileFormat, assay, resourceType, dataLevel, specimenModality, cellRangerOutput","","","","","","","" -"BDM snRNASeq Processed Data Annotations","A template outlining metadata to be collected as file annotations for snRNA-seq processed data files (i.e., anything not a fastq file). to be compiled by ARK BDM.","","Component, fileFormat, assay, resourceType, dataLevel, specimenModality, cellRangerOutput, parentBiospecimenID, biospecimenType, biospecimenSubtype, dataType, dataSubtype, diagnosis, visitID, libraryPrepMethod, nucleicAcidSource, alignmentReference, softwareAndVersion, program, project, species","","","","","","","" +"BDM snRNASeq Processed Data Annotations","A template outlining metadata to be collected as file annotations for snRNA-seq processed data files (i.e., anything not a fastq file). to be compiled by ARK BDM.","","Component, fileFormat, assay, resourceType, dataLevel, specimenModality, cellRangerOutput, parentBiospecimenID, biospecimenType, biospecimenSubtype, dataType, dataSubtype, diagnosis, visitID, libraryPrepMethod, nucleicAcidSource, alignmentReference, softwareAndVersion, program, project, species, primaryCellSource, cellType, userDefinedCellType","","","","","","","" "snATACSeq Processed Data Annotation Template","A data contributor template outlining metadata to be collected as file annotations for snATAC-seq processed data files (i.e., anything not a fastq file).","","Component, fileFormat, assay, resourceType, dataLevel, specimenModality, cellRangerOutput","","","","","","","" -"BDM snATACSeq Processed Data Annotations","A template outlining metadata to be collected as file annotations for snATAC-seq processed data files (i.e., anything not a fastq file). to be compiled by ARK BDM.","","Component, fileFormat, assay, resourceType, dataLevel, specimenModality, cellRangerOutput, parentBiospecimenID, biospecimenType, biospecimenSubtype, dataType, dataSubtype, diagnosis, visitID, libraryPrepMethod, nucleicAcidSource, alignmentReference, softwareAndVersion, program, project, species","","","","","","","" +"BDM snATACSeq Processed Data Annotations","A template outlining metadata to be collected as file annotations for snATAC-seq processed data files (i.e., anything not a fastq file). to be compiled by ARK BDM.","","Component, fileFormat, assay, resourceType, dataLevel, specimenModality, cellRangerOutput, parentBiospecimenID, biospecimenType, biospecimenSubtype, dataType, dataSubtype, diagnosis, visitID, libraryPrepMethod, nucleicAcidSource, alignmentReference, softwareAndVersion, program, project, species, primaryCellSource, cellType, userDefinedCellType","","","","","","","" "scVDJSeq Processed Data Annotation Template","A data contributor template outlining metadata to be collected as file annotations for scVDJ-seq (i.e., immune repertoire profiling) processed data files (i.e., anything not a fastq file).","","Component, fileFormat, assay, resourceType, dataLevel, specimenModality","","","","","","","" -"BDM scVDJSeq Processed Data Annotations","A template outlining metadata to be collected as file annotations for scVDJ-seq (i.e., immune repertoire profiling) processed data files (i.e., anything not a fastq file). to be compiled by ARK BDM.","","Component, fileFormat, assay, resourceType, dataLevel, specimenModality, parentBiospecimenID, biospecimenType, biospecimenSubtype, dataType, dataSubtype, diagnosis, visitID, libraryPrepMethod, nucleicAcidSource, alignmentReference, softwareAndVersion, program, project, species","","","","","","","" +"BDM scVDJSeq Processed Data Annotations","A template outlining metadata to be collected as file annotations for scVDJ-seq (i.e., immune repertoire profiling) processed data files (i.e., anything not a fastq file). to be compiled by ARK BDM.","","Component, fileFormat, assay, resourceType, dataLevel, specimenModality, parentBiospecimenID, biospecimenType, biospecimenSubtype, dataType, dataSubtype, diagnosis, visitID, libraryPrepMethod, nucleicAcidSource, alignmentReference, softwareAndVersion, program, project, species, primaryCellSource, cellType, userDefinedCellType","","","","","","","" "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","","","","","","","" "AMP AIM","Accelerating Medicines Partnership Autoimmune and Immune-Mediated Diseases. Is a valid value for 'program' that triggers conditional dependencies for additional attributes.","","visitID","","","","","","","" "Component","A high-level attribute for grouping attributes into templates.","","","","True","","","","","string" "publicationSynID","The synID of the corresponding Synapse entity that stores metadata about the publication. This is used to differentiate publication-specific files, often consisting of level 4 processed data and expanded subject metadata, in a publication dataset that also includes raw or minimally processed files from experimental datasets. This provides an easy way to distinguish and select for the publication-specific data from which the research findings were derived. When this attribute is used to annotate a Dataset it serves as a way to directly link the Dataset entity with the publication metadata stored in Synapse.","","","","False","","","","regex search ^syn[0-9]{8} error","string" "associatedDataset","The synID of a Dataset entity. This serves to link other Synapse entities to Dataset entities. When used to annotate a publication Dataset this attribute should include the synID for an experimental Datasets from which the publication data was derived. Multiple synID can be specified using a comma-delimited list.","","","","False","","","","list like::regex search ^syn[0-9]{8} error","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, ELLIPSS, LOCKIT, RA, SLE, STAMP, V-CoRT","","","True","","","","list like error","string" +"project","A sub-level attribute of `program` specifying a research initiative working to investigate particular hypotheses.","AIM for RA, ELLIPSS, LOCKIT, RA, SLE, STAMP, UMass V-CoRT","","","True","","","","list like error","string" "programPhase","A label noting which AMP RA/SLE program phase generated the data.","I, II","","","True","","","","list like error","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" "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" @@ -30,7 +30,7 @@ "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" "custom10xProbeSetSynID","If custom modified probe sets were used for collecting 10x Chromium Flex scRNA-seq data, then the probe reference files should be grouped as a zip or tar archive and uploaded as metadata. This attribute links the experimental data back to the probe set archive file via a synapse ID.","","","","True","","","","regex search ^syn[0-9]{8} error","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" -"specimenModality","Label assigned to experimental data files indicating whether the data contained corresponds to a single or multiple biospecimens","multispecimen, single specimen","","","True","","","","","string" +"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" "individualID","Unique identifier assigned to each study participant. For multi-specimen data files provide all IDs in a comma-separated list.","","","","True","","","","#ClinicalMetadataTemplate unique error^^#BiospecimenMetadataTemplate str^^list like error","string" "biospecimenID","A unique identifier assigned to specimens collected from study participants. For multi-specimen data files provide all IDs in a comma-separated list.","","","","True","","","","#BiospecimenMetadataTemplate unique error^^list like error","string" "parentBiospecimenID","The biospecimenID associated with the originating biospecimen for derived or child biospecimens.","","","","False","","","","","string" @@ -45,15 +45,14 @@ "nucleicAcidSource","The source of the nucleic acid used as input for sequencing library fragments. Select all that apply, though in most cases only a single label is expected.","BCR mRNA, CRISPR protospacer feature barcode, TCR mRNA, Tn5-accessible gDNA, antigen capture barcode, gDNA, globin-depleted RNA, intracellular protein feature barcode, multiplexing oligo, poly(A) RNA, rRNA-depleted RNA, surface protein feature barcode","","","True","","","","list like error","string" "biospecimenSubtype","Biospecimen status before sample is processed into a scRNA-seq library. Several scRNA-seq technologies support a variety of sample processing methods which can introduces sources of technical variation.","FFPE tissue, PFA-fixed tissue, cell or tissue lysate, cell suspension, flow-sorted cells, fresh tissue, frozen tissue, nuclei suspension, supernatant","","","False","","","","","string" "cellRangerOutput","10x Genomics Cell Ranger software output several different counts results and formats, some with different processing applied. This label distinguishes between these types and is particularly helpful when multiple files are uploaded with the sample name, e.g., barcodes.tsv.gz","Not Applicable, filtered MEX, filtered_feature_bc_matrix, filtered_peak_bc_matrix, raw MEX, raw_feature_bc_matrix, raw_peak_bc_matrix","","","True","","","","","string" -"alignmentReference","The genomic/transcriptomic reference used for performing read alignment against.","10x Cell Ranger Human GRCh38 2020-A, 10x Cell Ranger Human GRCh38 2024-A, modified GRCh38, unknown, vdj_GRCh38_alts_ensembl-4.0.0","","","True","","","","","string" -"libraryPrepMethod","Sequencing library preparation method or kit used to create the library. If no commercially available kit was used, please select 'in-house library prep'.","10x Chromium Fixed RNA Human Transcriptome, 10x Chromium GEM-X Single Cell 3' v4, 10x Chromium GEM-X Single Cell 5' v3, 10x Chromium Next GEM Single Cell 3', 10x Chromium Next GEM Single Cell 3' 3.1, 10x Chromium Next GEM Single Cell 5' v1.1, 10x Chromium Next GEM Single Cell 5' v2, 10x Chromium Next GEM Single Cell ATAC v2, 10x Chromium Single Cell Human BCR, 10x Chromium Single Cell Human TCR, 10x GEM-X Flex Gene Expression Human, 10x GEM-X Universal 5? Gene Expression v3, CEL-Seq2, Chromium Next GEM Single Cell ATAC v1.1, Fluidigm C1 HT, NEBNext Human Immune Sequencing Kit, NEBNext Ultra II Directional RNA Library, Nextera XT, Nextera XT DNA, QIAseq miRNA Library, SMART-Seq Human BCR with UMI, SMART-Seq Human TCR with UMI, SMART-Seq v4 Ultra Low Input RNA, SMARTer Stranded Total RNA v2, Takara Human BCR profiling for Illumina, Takara Human TCR profiling for Illumina, Takara Human TCRv2 profiling for Illumina, Takara Human scTCR profiling for Illumina, TruSeq Stranded mRNA, custom DASH-treatment, in-house library prep","","","True","","","","","string" +"alignmentReference","The genomic/transcriptomic reference used for performing read alignment against.","10x Cell Ranger Human GRCh38 2020-A, 10x Cell Ranger Human GRCh38 2024-A, GRCh38, modified GRCh38, unknown, vdj_GRCh38_alts_ensembl-4.0.0","","","True","","","","","string" +"libraryPrepMethod","Sequencing library preparation method or kit used to create the library. If no commercially available kit was used, please select 'in-house library prep'.","10x Chromium Fixed RNA Human Transcriptome, 10x Chromium GEM-X Single Cell 3' v4, 10x Chromium GEM-X Single Cell 5' v3, 10x Chromium Next GEM Single Cell 3', 10x Chromium Next GEM Single Cell 3' 3.1, 10x Chromium Next GEM Single Cell 5' v1.1, 10x Chromium Next GEM Single Cell 5' v2, 10x Chromium Next GEM Single Cell ATAC v2, 10x Chromium Single Cell Human BCR, 10x Chromium Single Cell Human TCR, 10x GEM-X Flex Gene Expression Human, 10x GEM-X Universal 5' Gene Expression v3, CEL-Seq2, Chromium Next GEM Single Cell ATAC v1.1, Fluidigm C1 HT, NEBNext Human Immune Sequencing Kit, NEBNext Ultra II Directional RNA Library, Nextera XT, Nextera XT DNA, QIAseq miRNA Library, SMART-Seq Human BCR with UMI, SMART-Seq Human TCR with UMI, SMART-Seq v4 Ultra Low Input RNA, SMARTer Stranded Total RNA v2, Takara Human BCR profiling for Illumina, Takara Human TCR profiling for Illumina, Takara Human TCRv2 profiling for Illumina, Takara Human scTCR profiling for Illumina, TruSeq Stranded mRNA, custom DASH-treatment, in-house library prep","","","True","","","","","string" "datasetType","High-level classification of dataset entity distinguishing between datasets compiled for a specific publication or as a general data resource.","experimental, publication","","","True","","","","","string" "acknowledgmentStatement","A Dataset-specific attribute specifying the path to the wiki subpage within the ARK Portal - backend project that contains the acknowledgement statement that must be included in publications using data from the given dataset as a stipulation of the conditions of use.","syn26710600/wiki/619685","","","True","","","","","string" "datasetDescription","A Dataset-specific attribute specifying the synID of the folder that contains a wiki write-up of the dataset description. This wiki content will be surfaced on the ARK Portal frontend site.","","","","True","","","","regex search ^syn[0-9]{8} error","string" "ARKRelease","A Dataset-specific attribute specifying the ARK Portal release in which this dataset was first made available to the public.","1.0, 2.0, 2024.06.R1, 2024.07.R1, 2024.08.R1, 2024.09.R1, 2024.10.R1, 2024.12.R1, 2025.01.R1, 2025.02.R1, 2025.03.R1, 2025.04.R1, 2025.05.R1, 2025.06.R1, 2025.07.R1, 2025.08.R1, 2025.09.R1, 2025.10.R1, 2025.11.R1, 2025.12.R1","","","True","","","","","string" "RObjectClass","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.","ROCR prediction.object, Seurat object, SummarizedExperiment, Symphony reference, data.frame, list, matrix, sparse matrix, vector","","","False","","","","","string" -"dbGapAccession","NIH policy requires large-scale human genomics studies to be registered in dbGap. This is a Dataset-specific attribute indicating the unique identifier (i.e., accession) of the corresponding study that is registered in dbGap, formatted as a compact URI, e.g., dbgap:phs003417.v2.p1","","","","False","","","","regex search ^dbgap:","string" -"diagnosis","A high-level classifier indicating the disease status of an individual.","At-Risk RA, OA, RA, SLE, Sjogren's disease, control, cutaneous lupus erythematosus, dermatomyositis, lupus nephritis, psoriasis, psoriatic arthritis, scleroderma, unknown, vitiligo","","","True","","","","list like error","string" +"diagnosis","A high-level classifier indicating the disease status of an individual.","At-Risk RA, Not Applicable, OA, RA, SLE, Sjogren's disease, control, cutaneous lupus erythematosus, dermatomyositis, discoid lupus erythematosus, lupus nephritis, psoriasis, psoriatic arthritis, scleroderma, unknown, vitiligo","","","True","","","","list like error","string" "DOID","Disease ontology identifier associated with `diagnosis`. Attribute values are applied by ARK Portal data managers.","","","","True","","","","regex search ^DOID error","string" "libraryID","A library label or name, unique within an experiment, used to distinguish sequencing libraries.","","","","True","","","","","string" "associatedCodeURL","A URL to the repository where associated code is available.","","","","False","","","","","string" @@ -70,7 +69,7 @@ "PMID","PubMed(R) Identifier","","","","True","","","","regex search ^PMID error","string" "DOI","Digital object identifier","","","","True","","","","","string" "anatomicalSite","The anatomical site, i.e., location on or within the body, from which the biospecimen was collected. This attribute is required depending on the value selected for biospecimenType.","left 2nd MCP joint, left ankle joint, left hip joint, left knee joint, left wrist joint, other site, right 1st MTP joint, right 2nd MCP joint, right 2nd MTP joint, right 3rd MCP joint, right ankle joint, right hip joint, right knee joint, right wrist joint, unknown","","","True","","","","","string" -"vitiligoType","A high-level classification of vitiligo based on the distribution and patterning of lesions across the body.","mixed, non-segmental, segmental, unclassified","","","False","","","","","string" +"vitiligoPattern","A high-level classification of vitiligo based on the distribution and patterning of lesions across the body.","mixed, non-segmental, segmental, unclassified","","","False","","","","","string" "vitiligoPhenotype","Classification of vitiligo lesions which correlate with autoimmune activity and result in specific skin and depigmentation manifestations at the lesion site. If N/A please select 'none'. Multiple selections can be provided in a comma-delimited list.","active, confetti, inflammatory, none, trichrome","","","True","","","","list like error","string" "psoriasisType","General type classification of psoriasis disease manifestation.","erythrodermic, guttate, inverse, plaque, pustular","","","False","","","","","string" "ageDiagnosis","Age at which subject was diagnosed with `diagnosis`. If providing this value be sure the unit matches that used for `age`.","","","","False","","","","num error","number" @@ -121,3 +120,5 @@ "treatmentTimepoint","Where applicable, specify the timepoint relative to treatment to distinguish different sets of samples that have undergone the same treatment but for different lengths of time. REQUIRED: please specify the unit of time, e.g., secs, mins, hrs, days, etc.","","","","False","","","","","string" "slideID","A distinct label or name, unique within an experiment, assigned to an imaging slides.","","","","True","","","","","string" "altSampleID","An alternate identifier for a sample. With some assays there can be default or alternate sample identifiers entered into the data collection software. If you will be uploading data collected with an alternate identifier please provide that here. In some cases, the ARK BDM team will use this field to capture original but out-dated identifiers for samples.","","","","False","","","","","string" +"sampleCollectionBatch","A label indicating batching of sample collection or experiment execution that occurs prior to data collection.","","","","False","","","","","string" +"associatedAccession","This is a File and Dataset annotation attribute indicating additional accessions (i.e., unique identifiers) associated with the data when the data has also been submitted to or can be found in other repositories such as GEO, SRA, dbGaP, etc.","","","","False","","","","list like error","string" diff --git a/model_contexts/singlecell/ark.singlecell_model.jsonld b/model_contexts/singlecell/ark.singlecell_model.jsonld index ba96461..256c1bc 100644 --- a/model_contexts/singlecell/ark.singlecell_model.jsonld +++ b/model_contexts/singlecell/ark.singlecell_model.jsonld @@ -922,6 +922,9 @@ }, { "@id": "bts:Singlespecimen" + }, + { + "@id": "bts:Unknown" } ], "sms:displayName": "specimenModality", @@ -1046,6 +1049,15 @@ }, { "@id": "bts:Species" + }, + { + "@id": "bts:PrimaryCellSource" + }, + { + "@id": "bts:CellType" + }, + { + "@id": "bts:UserDefinedCellType" } ], "sms:validationRules": [] @@ -1312,6 +1324,9 @@ { "@id": "bts:At-RiskRA" }, + { + "@id": "bts:NotApplicable" + }, { "@id": "bts:OA" }, @@ -1333,6 +1348,9 @@ { "@id": "bts:Dermatomyositis" }, + { + "@id": "bts:Discoidlupuserythematosus" + }, { "@id": "bts:Lupusnephritis" }, @@ -1423,7 +1441,7 @@ "@id": "bts:10xGEM-XFlexGeneExpressionHuman" }, { - "@id": "bts:10xGEM-XUniversal5?GeneExpressionv3" + "@id": "bts:10xGEM-XUniversal5'GeneExpressionv3" }, { "@id": "bts:CEL-Seq2" @@ -1564,6 +1582,9 @@ { "@id": "bts:10xCellRangerHumanGRCh382024-A" }, + { + "@id": "bts:GRCh38" + }, { "@id": "bts:ModifiedGRCh38" }, @@ -1748,7 +1769,7 @@ "@id": "bts:STAMP" }, { - "@id": "bts:V-CoRT" + "@id": "bts:UMassV-CoRT" } ], "sms:displayName": "project", @@ -1779,6 +1800,89 @@ "sms:required": "sms:true", "sms:validationRules": [] }, + { + "@id": "bts:PrimaryCellSource", + "@type": "rdfs:Class", + "rdfs:comment": "A label indicating the biological source material from which a primary cell culture was derived.", + "rdfs:label": "PrimaryCellSource", + "rdfs:subClassOf": [ + { + "@id": "bts:Thing" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "schema:rangeIncludes": [ + { + "@id": "bts:PBMCs" + }, + { + "@id": "bts:Kidney" + }, + { + "@id": "bts:Pannus-deriveddermis" + }, + { + "@id": "bts:Pannus-derivedepidermis" + }, + { + "@id": "bts:Salivarygland" + }, + { + "@id": "bts:Synovialtissue" + }, + { + "@id": "bts:Totalleukocytes" + }, + { + "@id": "bts:Urine" + }, + { + "@id": "bts:Uvea" + }, + { + "@id": "bts:Wholeblood" + } + ], + "sms:displayName": "primaryCellSource", + "sms:required": "sms:true", + "sms:validationRules": [] + }, + { + "@id": "bts:CellType", + "@type": "rdfs:Class", + "rdfs:comment": "The cell type name from Cell Ontology for the corresponding CL identifier.", + "rdfs:label": "CellType", + "rdfs:subClassOf": [ + { + "@id": "bts:Thing" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "cellType", + "sms:required": "sms:false", + "sms:validationRules": [] + }, + { + "@id": "bts:UserDefinedCellType", + "@type": "rdfs:Class", + "rdfs:comment": "User-defined label of a cell type. Contributors are provided this option to use preferred or custom cell type labels that may vary from options and standards set by Cell Ontology.", + "rdfs:label": "UserDefinedCellType", + "rdfs:subClassOf": [ + { + "@id": "bts:Thing" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "userDefinedCellType", + "sms:required": "sms:false", + "sms:validationRules": [] + }, { "@id": "bts:SnRNASeqProcessedDataAnnotationTemplate", "@type": "rdfs:Class", @@ -1897,6 +2001,15 @@ }, { "@id": "bts:Species" + }, + { + "@id": "bts:PrimaryCellSource" + }, + { + "@id": "bts:CellType" + }, + { + "@id": "bts:UserDefinedCellType" } ], "sms:validationRules": [] @@ -2019,6 +2132,15 @@ }, { "@id": "bts:Species" + }, + { + "@id": "bts:PrimaryCellSource" + }, + { + "@id": "bts:CellType" + }, + { + "@id": "bts:UserDefinedCellType" } ], "sms:validationRules": [] @@ -2135,6 +2257,15 @@ }, { "@id": "bts:Species" + }, + { + "@id": "bts:PrimaryCellSource" + }, + { + "@id": "bts:CellType" + }, + { + "@id": "bts:UserDefinedCellType" } ], "sms:validationRules": [] @@ -2297,10 +2428,10 @@ "rdfs:label": "RA", "rdfs:subClassOf": [ { - "@id": "bts:Diagnosis" + "@id": "bts:Project" }, { - "@id": "bts:Project" + "@id": "bts:Diagnosis" } ], "schema:isPartOf": { @@ -2317,10 +2448,10 @@ "rdfs:label": "SLE", "rdfs:subClassOf": [ { - "@id": "bts:Diagnosis" + "@id": "bts:Project" }, { - "@id": "bts:Project" + "@id": "bts:Diagnosis" } ], "schema:isPartOf": { @@ -2348,10 +2479,10 @@ "sms:validationRules": [] }, { - "@id": "bts:V-CoRT", + "@id": "bts:UMassV-CoRT", "@type": "rdfs:Class", "rdfs:comment": "TBD", - "rdfs:label": "V-CoRT", + "rdfs:label": "UMassV-CoRT", "rdfs:subClassOf": [ { "@id": "bts:Project" @@ -2360,7 +2491,7 @@ "schema:isPartOf": { "@id": "http://schema.biothings.io" }, - "sms:displayName": "V-CoRT", + "sms:displayName": "UMass V-CoRT", "sms:required": "sms:false", "sms:validationRules": [] }, @@ -4247,6 +4378,9 @@ { "@id": "bts:CellRangerOutput" }, + { + "@id": "bts:Diagnosis" + }, { "@id": "bts:Platform" } @@ -4367,10 +4501,10 @@ "rdfs:label": "Unknown", "rdfs:subClassOf": [ { - "@id": "bts:Ethnicity" + "@id": "bts:SpecimenModality" }, { - "@id": "bts:AlignmentReference" + "@id": "bts:Ethnicity" }, { "@id": "bts:SynovialCollectionProcedure" @@ -4381,6 +4515,9 @@ { "@id": "bts:DiabetesType" }, + { + "@id": "bts:AlignmentReference" + }, { "@id": "bts:Race" }, @@ -4779,55 +4916,6 @@ "sms:required": "sms:false", "sms:validationRules": [] }, - { - "@id": "bts:PrimaryCellSource", - "@type": "rdfs:Class", - "rdfs:comment": "A label indicating the biological source material from which a primary cell culture was derived.", - "rdfs:label": "PrimaryCellSource", - "rdfs:subClassOf": [ - { - "@id": "bts:Thing" - } - ], - "schema:isPartOf": { - "@id": "http://schema.biothings.io" - }, - "schema:rangeIncludes": [ - { - "@id": "bts:PBMCs" - }, - { - "@id": "bts:Kidney" - }, - { - "@id": "bts:Pannus-deriveddermis" - }, - { - "@id": "bts:Pannus-derivedepidermis" - }, - { - "@id": "bts:Salivarygland" - }, - { - "@id": "bts:Synovialtissue" - }, - { - "@id": "bts:Totalleukocytes" - }, - { - "@id": "bts:Urine" - }, - { - "@id": "bts:Uvea" - }, - { - "@id": "bts:Wholeblood" - } - ], - "sms:displayName": "primaryCellSource", - "sms:required": "sms:true", - "sms:validationRules": [] - }, { "@id": "bts:Kidney", "@type": "rdfs:Class", @@ -6121,6 +6209,23 @@ "sms:required": "sms:false", "sms:validationRules": [] }, + { + "@id": "bts:GRCh38", + "@type": "rdfs:Class", + "rdfs:comment": "TBD", + "rdfs:label": "GRCh38", + "rdfs:subClassOf": [ + { + "@id": "bts:AlignmentReference" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "GRCh38", + "sms:required": "sms:false", + "sms:validationRules": [] + }, { "@id": "bts:ModifiedGRCh38", "@type": "rdfs:Class", @@ -6343,10 +6448,10 @@ "sms:validationRules": [] }, { - "@id": "bts:10xGEM-XUniversal5?GeneExpressionv3", + "@id": "bts:10xGEM-XUniversal5'GeneExpressionv3", "@type": "rdfs:Class", "rdfs:comment": "TBD", - "rdfs:label": "10xGEM-XUniversal5?GeneExpressionv3", + "rdfs:label": "10xGEM-XUniversal5'GeneExpressionv3", "rdfs:subClassOf": [ { "@id": "bts:LibraryPrepMethod" @@ -6355,7 +6460,7 @@ "schema:isPartOf": { "@id": "http://schema.biothings.io" }, - "sms:displayName": "10x GEM-X Universal 5? Gene Expression v3", + "sms:displayName": "10x GEM-X Universal 5' Gene Expression v3", "sms:required": "sms:false", "sms:validationRules": [] }, @@ -7371,25 +7476,6 @@ "sms:required": "sms:false", "sms:validationRules": [] }, - { - "@id": "bts:DbGapAccession", - "@type": "rdfs:Class", - "rdfs:comment": "NIH policy requires large-scale human genomics studies to be registered in dbGap. This is a Dataset-specific attribute indicating the unique identifier (i.e., accession) of the corresponding study that is registered in dbGap, formatted as a compact URI, e.g., dbgap:phs003417.v2.p1", - "rdfs:label": "DbGapAccession", - "rdfs:subClassOf": [ - { - "@id": "bts:Thing" - } - ], - "schema:isPartOf": { - "@id": "http://schema.biothings.io" - }, - "sms:displayName": "dbGapAccession", - "sms:required": "sms:false", - "sms:validationRules": [ - "regex search ^dbgap:" - ] - }, { "@id": "bts:At-RiskRA", "@type": "rdfs:Class", @@ -7492,6 +7578,23 @@ "sms:required": "sms:false", "sms:validationRules": [] }, + { + "@id": "bts:Discoidlupuserythematosus", + "@type": "rdfs:Class", + "rdfs:comment": "TBD", + "rdfs:label": "Discoidlupuserythematosus", + "rdfs:subClassOf": [ + { + "@id": "bts:Diagnosis" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "discoid lupus erythematosus", + "sms:required": "sms:false", + "sms:validationRules": [] + }, { "@id": "bts:Lupusnephritis", "@type": "rdfs:Class", @@ -8402,10 +8505,10 @@ "sms:validationRules": [] }, { - "@id": "bts:VitiligoType", + "@id": "bts:VitiligoPattern", "@type": "rdfs:Class", "rdfs:comment": "A high-level classification of vitiligo based on the distribution and patterning of lesions across the body.", - "rdfs:label": "VitiligoType", + "rdfs:label": "VitiligoPattern", "rdfs:subClassOf": [ { "@id": "bts:Thing" @@ -8428,7 +8531,7 @@ "@id": "bts:Unclassified" } ], - "sms:displayName": "vitiligoType", + "sms:displayName": "vitiligoPattern", "sms:required": "sms:false", "sms:validationRules": [] }, @@ -8439,7 +8542,7 @@ "rdfs:label": "Mixed", "rdfs:subClassOf": [ { - "@id": "bts:VitiligoType" + "@id": "bts:VitiligoPattern" } ], "schema:isPartOf": { @@ -8456,7 +8559,7 @@ "rdfs:label": "Non-segmental", "rdfs:subClassOf": [ { - "@id": "bts:VitiligoType" + "@id": "bts:VitiligoPattern" } ], "schema:isPartOf": { @@ -8473,7 +8576,7 @@ "rdfs:label": "Segmental", "rdfs:subClassOf": [ { - "@id": "bts:VitiligoType" + "@id": "bts:VitiligoPattern" } ], "schema:isPartOf": { @@ -8490,7 +8593,7 @@ "rdfs:label": "Unclassified", "rdfs:subClassOf": [ { - "@id": "bts:VitiligoType" + "@id": "bts:VitiligoPattern" } ], "schema:isPartOf": { @@ -9895,40 +9998,6 @@ "regex search ^CL: error" ] }, - { - "@id": "bts:CellType", - "@type": "rdfs:Class", - "rdfs:comment": "The cell type name from Cell Ontology for the corresponding CL identifier.", - "rdfs:label": "CellType", - "rdfs:subClassOf": [ - { - "@id": "bts:Thing" - } - ], - "schema:isPartOf": { - "@id": "http://schema.biothings.io" - }, - "sms:displayName": "cellType", - "sms:required": "sms:false", - "sms:validationRules": [] - }, - { - "@id": "bts:UserDefinedCellType", - "@type": "rdfs:Class", - "rdfs:comment": "User-defined label of a cell type. Contributors are provided this option to use preferred or custom cell type labels that may vary from options and standards set by Cell Ontology.", - "rdfs:label": "UserDefinedCellType", - "rdfs:subClassOf": [ - { - "@id": "bts:Thing" - } - ], - "schema:isPartOf": { - "@id": "http://schema.biothings.io" - }, - "sms:displayName": "userDefinedCellType", - "sms:required": "sms:false", - "sms:validationRules": [] - }, { "@id": "bts:KrennInflammatory", "@type": "rdfs:Class", @@ -10553,6 +10622,42 @@ "sms:displayName": "altSampleID", "sms:required": "sms:false", "sms:validationRules": [] + }, + { + "@id": "bts:SampleCollectionBatch", + "@type": "rdfs:Class", + "rdfs:comment": "A label indicating batching of sample collection or experiment execution that occurs prior to data collection.", + "rdfs:label": "SampleCollectionBatch", + "rdfs:subClassOf": [ + { + "@id": "bts:Thing" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "sampleCollectionBatch", + "sms:required": "sms:false", + "sms:validationRules": [] + }, + { + "@id": "bts:AssociatedAccession", + "@type": "rdfs:Class", + "rdfs:comment": "This is a File and Dataset annotation attribute indicating additional accessions (i.e., unique identifiers) associated with the data when the data has also been submitted to or can be found in other repositories such as GEO, SRA, dbGaP, etc.", + "rdfs:label": "AssociatedAccession", + "rdfs:subClassOf": [ + { + "@id": "bts:Thing" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "associatedAccession", + "sms:required": "sms:false", + "sms:validationRules": [ + "list like error" + ] } ], "@id": "http://schema.biothings.io/#0.1" diff --git a/model_contexts/spatial/ark.spatial_context.csv b/model_contexts/spatial/ark.spatial_context.csv index 5d63277..37a9c54 100644 --- a/model_contexts/spatial/ark.spatial_context.csv +++ b/model_contexts/spatial/ark.spatial_context.csv @@ -1,14 +1,14 @@ -Attribute,Description,Valid Values,DependsOn,Properties,Required,Parent,DependsOn Component,Source,Validation Rules,columnType -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",,,,,,, -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 -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,,,,, \ No newline at end of file +"Attribute","Description","Valid Values","DependsOn","Properties","Required","Parent","DependsOn Component","Source","Validation Rules","columnType" +"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" +"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","","","","","" diff --git a/model_contexts/spatial/ark.spatial_model.csv b/model_contexts/spatial/ark.spatial_model.csv index 97ab2e8..6391dfa 100644 --- a/model_contexts/spatial/ark.spatial_model.csv +++ b/model_contexts/spatial/ark.spatial_model.csv @@ -1,7 +1,7 @@ "Attribute","Description","Valid Values","DependsOn","Properties","Required","Parent","DependsOn Component","Source","Validation Rules","columnType" "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","","","","","","","" +"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","High-level classification of the file content","experimental data, metadata","","","TRUE","","","","list like error","string" @@ -13,11 +13,11 @@ "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","","","","","" "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, info, mcd, mtx, parquet, pdf, rds, rec, svs, tbi, tgz, tsv, txt, vcf, xls, xlsx, zip","","","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, info, mcd, mtx, parquet, pdf, py, rds, rec, svs, tbi, tgz, tsv, txt, vcf, xls, xlsx, zip","","","True","","","","","string" "publicationSynID","The synID of the corresponding Synapse entity that stores metadata about the publication. This is used to differentiate publication-specific files, often consisting of level 4 processed data and expanded subject metadata, in a publication dataset that also includes raw or minimally processed files from experimental datasets. This provides an easy way to distinguish and select for the publication-specific data from which the research findings were derived. When this attribute is used to annotate a Dataset it serves as a way to directly link the Dataset entity with the publication metadata stored in Synapse.","","","","False","","","","regex search ^syn[0-9]{8} error","string" "associatedDataset","The synID of a Dataset entity. This serves to link other Synapse entities to Dataset entities. When used to annotate a publication Dataset this attribute should include the synID for an experimental Datasets from which the publication data was derived. Multiple synID can be specified using a comma-delimited list.","","","","False","","","","list like::regex search ^syn[0-9]{8} error","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, ELLIPSS, LOCKIT, RA, SLE, STAMP, V-CoRT","","","True","","","","list like error","string" +"project","A sub-level attribute of `program` specifying a research initiative working to investigate particular hypotheses.","AIM for RA, ELLIPSS, LOCKIT, RA, SLE, STAMP, UMass V-CoRT","","","True","","","","list like error","string" "programPhase","A label noting which AMP RA/SLE program phase generated the data.","I, II","","","True","","","","list like error","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" "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" @@ -25,7 +25,7 @@ "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" "custom10xProbeSetSynID","If custom modified probe sets were used for collecting 10x Chromium Flex scRNA-seq data, then the probe reference files should be grouped as a zip or tar archive and uploaded as metadata. This attribute links the experimental data back to the probe set archive file via a synapse ID.","","","","True","","","","regex search ^syn[0-9]{8} error","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" -"specimenModality","Label assigned to experimental data files indicating whether the data contained corresponds to a single or multiple biospecimens","multispecimen, single specimen","","","True","","","","","string" +"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" "individualID","Unique identifier assigned to each study participant. For multi-specimen data files provide all IDs in a comma-separated list.","","","","True","","","","#ClinicalMetadataTemplate unique error^^#BiospecimenMetadataTemplate str^^list like error","string" "biospecimenID","A unique identifier assigned to specimens collected from study participants. For multi-specimen data files provide all IDs in a comma-separated list.","","","","True","","","","#BiospecimenMetadataTemplate unique error^^list like error","string" "parentBiospecimenID","The biospecimenID associated with the originating biospecimen for derived or child biospecimens.","","","","False","","","","","string" @@ -40,15 +40,14 @@ "nucleicAcidSource","The source of the nucleic acid used as input for sequencing library fragments. Select all that apply, though in most cases only a single label is expected.","BCR mRNA, CRISPR protospacer feature barcode, TCR mRNA, Tn5-accessible gDNA, antigen capture barcode, gDNA, globin-depleted RNA, intracellular protein feature barcode, multiplexing oligo, poly(A) RNA, rRNA-depleted RNA, surface protein feature barcode","","","True","","","","list like error","string" "biospecimenSubtype","Biospecimen status before sample is processed into a scRNA-seq library. Several scRNA-seq technologies support a variety of sample processing methods which can introduces sources of technical variation.","FFPE tissue, PFA-fixed tissue, cell or tissue lysate, cell suspension, flow-sorted cells, fresh tissue, frozen tissue, nuclei suspension, supernatant","","","False","","","","","string" "cellRangerOutput","10x Genomics Cell Ranger software output several different counts results and formats, some with different processing applied. This label distinguishes between these types and is particularly helpful when multiple files are uploaded with the sample name, e.g., barcodes.tsv.gz","Not Applicable, filtered MEX, filtered_feature_bc_matrix, filtered_peak_bc_matrix, raw MEX, raw_feature_bc_matrix, raw_peak_bc_matrix","","","True","","","","","string" -"alignmentReference","The genomic/transcriptomic reference used for performing read alignment against.","10x Cell Ranger Human GRCh38 2020-A, 10x Cell Ranger Human GRCh38 2024-A, modified GRCh38, unknown, vdj_GRCh38_alts_ensembl-4.0.0","","","True","","","","","string" -"libraryPrepMethod","Sequencing library preparation method or kit used to create the library. If no commercially available kit was used, please select 'in-house library prep'.","10x Chromium Fixed RNA Human Transcriptome, 10x Chromium GEM-X Single Cell 3' v4, 10x Chromium GEM-X Single Cell 5' v3, 10x Chromium Next GEM Single Cell 3', 10x Chromium Next GEM Single Cell 3' 3.1, 10x Chromium Next GEM Single Cell 5' v1.1, 10x Chromium Next GEM Single Cell 5' v2, 10x Chromium Next GEM Single Cell ATAC v2, 10x Chromium Single Cell Human BCR, 10x Chromium Single Cell Human TCR, 10x GEM-X Flex Gene Expression Human, 10x GEM-X Universal 5? Gene Expression v3, CEL-Seq2, Chromium Next GEM Single Cell ATAC v1.1, Fluidigm C1 HT, NEBNext Human Immune Sequencing Kit, NEBNext Ultra II Directional RNA Library, Nextera XT, Nextera XT DNA, QIAseq miRNA Library, SMART-Seq Human BCR with UMI, SMART-Seq Human TCR with UMI, SMART-Seq v4 Ultra Low Input RNA, SMARTer Stranded Total RNA v2, Takara Human BCR profiling for Illumina, Takara Human TCR profiling for Illumina, Takara Human TCRv2 profiling for Illumina, Takara Human scTCR profiling for Illumina, TruSeq Stranded mRNA, custom DASH-treatment, in-house library prep","","","True","","","","","string" +"alignmentReference","The genomic/transcriptomic reference used for performing read alignment against.","10x Cell Ranger Human GRCh38 2020-A, 10x Cell Ranger Human GRCh38 2024-A, GRCh38, modified GRCh38, unknown, vdj_GRCh38_alts_ensembl-4.0.0","","","True","","","","","string" +"libraryPrepMethod","Sequencing library preparation method or kit used to create the library. If no commercially available kit was used, please select 'in-house library prep'.","10x Chromium Fixed RNA Human Transcriptome, 10x Chromium GEM-X Single Cell 3' v4, 10x Chromium GEM-X Single Cell 5' v3, 10x Chromium Next GEM Single Cell 3', 10x Chromium Next GEM Single Cell 3' 3.1, 10x Chromium Next GEM Single Cell 5' v1.1, 10x Chromium Next GEM Single Cell 5' v2, 10x Chromium Next GEM Single Cell ATAC v2, 10x Chromium Single Cell Human BCR, 10x Chromium Single Cell Human TCR, 10x GEM-X Flex Gene Expression Human, 10x GEM-X Universal 5' Gene Expression v3, CEL-Seq2, Chromium Next GEM Single Cell ATAC v1.1, Fluidigm C1 HT, NEBNext Human Immune Sequencing Kit, NEBNext Ultra II Directional RNA Library, Nextera XT, Nextera XT DNA, QIAseq miRNA Library, SMART-Seq Human BCR with UMI, SMART-Seq Human TCR with UMI, SMART-Seq v4 Ultra Low Input RNA, SMARTer Stranded Total RNA v2, Takara Human BCR profiling for Illumina, Takara Human TCR profiling for Illumina, Takara Human TCRv2 profiling for Illumina, Takara Human scTCR profiling for Illumina, TruSeq Stranded mRNA, custom DASH-treatment, in-house library prep","","","True","","","","","string" "datasetType","High-level classification of dataset entity distinguishing between datasets compiled for a specific publication or as a general data resource.","experimental, publication","","","True","","","","","string" "acknowledgmentStatement","A Dataset-specific attribute specifying the path to the wiki subpage within the ARK Portal - backend project that contains the acknowledgement statement that must be included in publications using data from the given dataset as a stipulation of the conditions of use.","syn26710600/wiki/619685","","","True","","","","","string" "datasetDescription","A Dataset-specific attribute specifying the synID of the folder that contains a wiki write-up of the dataset description. This wiki content will be surfaced on the ARK Portal frontend site.","","","","True","","","","regex search ^syn[0-9]{8} error","string" "ARKRelease","A Dataset-specific attribute specifying the ARK Portal release in which this dataset was first made available to the public.","1.0, 2.0, 2024.06.R1, 2024.07.R1, 2024.08.R1, 2024.09.R1, 2024.10.R1, 2024.12.R1, 2025.01.R1, 2025.02.R1, 2025.03.R1, 2025.04.R1, 2025.05.R1, 2025.06.R1, 2025.07.R1, 2025.08.R1, 2025.09.R1, 2025.10.R1, 2025.11.R1, 2025.12.R1","","","True","","","","","string" "RObjectClass","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.","ROCR prediction.object, Seurat object, SummarizedExperiment, Symphony reference, data.frame, list, matrix, sparse matrix, vector","","","False","","","","","string" -"dbGapAccession","NIH policy requires large-scale human genomics studies to be registered in dbGap. This is a Dataset-specific attribute indicating the unique identifier (i.e., accession) of the corresponding study that is registered in dbGap, formatted as a compact URI, e.g., dbgap:phs003417.v2.p1","","","","False","","","","regex search ^dbgap:","string" -"diagnosis","A high-level classifier indicating the disease status of an individual.","At-Risk RA, OA, RA, SLE, Sjogren's disease, control, cutaneous lupus erythematosus, dermatomyositis, lupus nephritis, psoriasis, psoriatic arthritis, scleroderma, unknown, vitiligo","","","True","","","","list like error","string" +"diagnosis","A high-level classifier indicating the disease status of an individual.","At-Risk RA, Not Applicable, OA, RA, SLE, Sjogren's disease, control, cutaneous lupus erythematosus, dermatomyositis, discoid lupus erythematosus, lupus nephritis, psoriasis, psoriatic arthritis, scleroderma, unknown, vitiligo","","","True","","","","list like error","string" "DOID","Disease ontology identifier associated with `diagnosis`. Attribute values are applied by ARK Portal data managers.","","","","True","","","","regex search ^DOID error","string" "libraryID","A library label or name, unique within an experiment, used to distinguish sequencing libraries.","","","","True","","","","","string" "associatedCodeURL","A URL to the repository where associated code is available.","","","","False","","","","","string" @@ -65,7 +64,7 @@ "PMID","PubMed(R) Identifier","","","","True","","","","regex search ^PMID error","string" "DOI","Digital object identifier","","","","True","","","","","string" "anatomicalSite","The anatomical site, i.e., location on or within the body, from which the biospecimen was collected. This attribute is required depending on the value selected for biospecimenType.","left 2nd MCP joint, left ankle joint, left hip joint, left knee joint, left wrist joint, other site, right 1st MTP joint, right 2nd MCP joint, right 2nd MTP joint, right 3rd MCP joint, right ankle joint, right hip joint, right knee joint, right wrist joint, unknown","","","True","","","","","string" -"vitiligoType","A high-level classification of vitiligo based on the distribution and patterning of lesions across the body.","mixed, non-segmental, segmental, unclassified","","","False","","","","","string" +"vitiligoPattern","A high-level classification of vitiligo based on the distribution and patterning of lesions across the body.","mixed, non-segmental, segmental, unclassified","","","False","","","","","string" "vitiligoPhenotype","Classification of vitiligo lesions which correlate with autoimmune activity and result in specific skin and depigmentation manifestations at the lesion site. If N/A please select 'none'. Multiple selections can be provided in a comma-delimited list.","active, confetti, inflammatory, none, trichrome","","","True","","","","list like error","string" "psoriasisType","General type classification of psoriasis disease manifestation.","erythrodermic, guttate, inverse, plaque, pustular","","","False","","","","","string" "ageDiagnosis","Age at which subject was diagnosed with `diagnosis`. If providing this value be sure the unit matches that used for `age`.","","","","False","","","","num error","number" @@ -116,3 +115,5 @@ "treatmentTimepoint","Where applicable, specify the timepoint relative to treatment to distinguish different sets of samples that have undergone the same treatment but for different lengths of time. REQUIRED: please specify the unit of time, e.g., secs, mins, hrs, days, etc.","","","","False","","","","","string" "slideID","A distinct label or name, unique within an experiment, assigned to an imaging slides.","","","","True","","","","","string" "altSampleID","An alternate identifier for a sample. With some assays there can be default or alternate sample identifiers entered into the data collection software. If you will be uploading data collected with an alternate identifier please provide that here. In some cases, the ARK BDM team will use this field to capture original but out-dated identifiers for samples.","","","","False","","","","","string" +"sampleCollectionBatch","A label indicating batching of sample collection or experiment execution that occurs prior to data collection.","","","","False","","","","","string" +"associatedAccession","This is a File and Dataset annotation attribute indicating additional accessions (i.e., unique identifiers) associated with the data when the data has also been submitted to or can be found in other repositories such as GEO, SRA, dbGaP, etc.","","","","False","","","","list like error","string" diff --git a/model_contexts/spatial/ark.spatial_model.jsonld b/model_contexts/spatial/ark.spatial_model.jsonld index af83d4a..c36a696 100644 --- a/model_contexts/spatial/ark.spatial_model.jsonld +++ b/model_contexts/spatial/ark.spatial_model.jsonld @@ -126,6 +126,9 @@ }, { "@id": "bts:Singlespecimen" + }, + { + "@id": "bts:Unknown" } ], "sms:displayName": "specimenModality", @@ -329,6 +332,9 @@ { "@id": "bts:Pdf" }, + { + "@id": "bts:Py" + }, { "@id": "bts:Rds" }, @@ -463,6 +469,15 @@ }, { "@id": "bts:Species" + }, + { + "@id": "bts:PrimaryCellSource" + }, + { + "@id": "bts:CellType" + }, + { + "@id": "bts:UserDefinedCellType" } ], "sms:validationRules": [] @@ -729,6 +744,9 @@ { "@id": "bts:At-RiskRA" }, + { + "@id": "bts:NotApplicable" + }, { "@id": "bts:OA" }, @@ -750,6 +768,9 @@ { "@id": "bts:Dermatomyositis" }, + { + "@id": "bts:Discoidlupuserythematosus" + }, { "@id": "bts:Lupusnephritis" }, @@ -853,7 +874,7 @@ "@id": "bts:STAMP" }, { - "@id": "bts:V-CoRT" + "@id": "bts:UMassV-CoRT" } ], "sms:displayName": "project", @@ -884,6 +905,89 @@ "sms:required": "sms:true", "sms:validationRules": [] }, + { + "@id": "bts:PrimaryCellSource", + "@type": "rdfs:Class", + "rdfs:comment": "A label indicating the biological source material from which a primary cell culture was derived.", + "rdfs:label": "PrimaryCellSource", + "rdfs:subClassOf": [ + { + "@id": "bts:Thing" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "schema:rangeIncludes": [ + { + "@id": "bts:PBMCs" + }, + { + "@id": "bts:Kidney" + }, + { + "@id": "bts:Pannus-deriveddermis" + }, + { + "@id": "bts:Pannus-derivedepidermis" + }, + { + "@id": "bts:Salivarygland" + }, + { + "@id": "bts:Synovialtissue" + }, + { + "@id": "bts:Totalleukocytes" + }, + { + "@id": "bts:Urine" + }, + { + "@id": "bts:Uvea" + }, + { + "@id": "bts:Wholeblood" + } + ], + "sms:displayName": "primaryCellSource", + "sms:required": "sms:true", + "sms:validationRules": [] + }, + { + "@id": "bts:CellType", + "@type": "rdfs:Class", + "rdfs:comment": "The cell type name from Cell Ontology for the corresponding CL identifier.", + "rdfs:label": "CellType", + "rdfs:subClassOf": [ + { + "@id": "bts:Thing" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "cellType", + "sms:required": "sms:false", + "sms:validationRules": [] + }, + { + "@id": "bts:UserDefinedCellType", + "@type": "rdfs:Class", + "rdfs:comment": "User-defined label of a cell type. Contributors are provided this option to use preferred or custom cell type labels that may vary from options and standards set by Cell Ontology.", + "rdfs:label": "UserDefinedCellType", + "rdfs:subClassOf": [ + { + "@id": "bts:Thing" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "userDefinedCellType", + "sms:required": "sms:false", + "sms:validationRules": [] + }, { "@id": "bts:Singlespecimen", "@type": "rdfs:Class", @@ -1741,6 +1845,23 @@ "sms:required": "sms:false", "sms:validationRules": [] }, + { + "@id": "bts:Py", + "@type": "rdfs:Class", + "rdfs:comment": "TBD", + "rdfs:label": "Py", + "rdfs:subClassOf": [ + { + "@id": "bts:FileFormat" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "py", + "sms:required": "sms:false", + "sms:validationRules": [] + }, { "@id": "bts:Rec", "@type": "rdfs:Class", @@ -2025,10 +2146,10 @@ "rdfs:label": "RA", "rdfs:subClassOf": [ { - "@id": "bts:Diagnosis" + "@id": "bts:Project" }, { - "@id": "bts:Project" + "@id": "bts:Diagnosis" } ], "schema:isPartOf": { @@ -2045,10 +2166,10 @@ "rdfs:label": "SLE", "rdfs:subClassOf": [ { - "@id": "bts:Diagnosis" + "@id": "bts:Project" }, { - "@id": "bts:Project" + "@id": "bts:Diagnosis" } ], "schema:isPartOf": { @@ -2076,10 +2197,10 @@ "sms:validationRules": [] }, { - "@id": "bts:V-CoRT", + "@id": "bts:UMassV-CoRT", "@type": "rdfs:Class", "rdfs:comment": "TBD", - "rdfs:label": "V-CoRT", + "rdfs:label": "UMassV-CoRT", "rdfs:subClassOf": [ { "@id": "bts:Project" @@ -2088,7 +2209,7 @@ "schema:isPartOf": { "@id": "http://schema.biothings.io" }, - "sms:displayName": "V-CoRT", + "sms:displayName": "UMass V-CoRT", "sms:required": "sms:false", "sms:validationRules": [] }, @@ -3445,6 +3566,9 @@ { "@id": "bts:CellRangerOutput" }, + { + "@id": "bts:Diagnosis" + }, { "@id": "bts:Platform" } @@ -3565,10 +3689,10 @@ "rdfs:label": "Unknown", "rdfs:subClassOf": [ { - "@id": "bts:Ethnicity" + "@id": "bts:SpecimenModality" }, { - "@id": "bts:AlignmentReference" + "@id": "bts:Ethnicity" }, { "@id": "bts:SynovialCollectionProcedure" @@ -3579,6 +3703,9 @@ { "@id": "bts:DiabetesType" }, + { + "@id": "bts:AlignmentReference" + }, { "@id": "bts:Race" }, @@ -3981,55 +4108,6 @@ "sms:required": "sms:false", "sms:validationRules": [] }, - { - "@id": "bts:PrimaryCellSource", - "@type": "rdfs:Class", - "rdfs:comment": "A label indicating the biological source material from which a primary cell culture was derived.", - "rdfs:label": "PrimaryCellSource", - "rdfs:subClassOf": [ - { - "@id": "bts:Thing" - } - ], - "schema:isPartOf": { - "@id": "http://schema.biothings.io" - }, - "schema:rangeIncludes": [ - { - "@id": "bts:PBMCs" - }, - { - "@id": "bts:Kidney" - }, - { - "@id": "bts:Pannus-deriveddermis" - }, - { - "@id": "bts:Pannus-derivedepidermis" - }, - { - "@id": "bts:Salivarygland" - }, - { - "@id": "bts:Synovialtissue" - }, - { - "@id": "bts:Totalleukocytes" - }, - { - "@id": "bts:Urine" - }, - { - "@id": "bts:Uvea" - }, - { - "@id": "bts:Wholeblood" - } - ], - "sms:displayName": "primaryCellSource", - "sms:required": "sms:true", - "sms:validationRules": [] - }, { "@id": "bts:Kidney", "@type": "rdfs:Class", @@ -5515,6 +5593,9 @@ { "@id": "bts:10xCellRangerHumanGRCh382024-A" }, + { + "@id": "bts:GRCh38" + }, { "@id": "bts:ModifiedGRCh38" }, @@ -5563,6 +5644,23 @@ "sms:required": "sms:false", "sms:validationRules": [] }, + { + "@id": "bts:GRCh38", + "@type": "rdfs:Class", + "rdfs:comment": "TBD", + "rdfs:label": "GRCh38", + "rdfs:subClassOf": [ + { + "@id": "bts:AlignmentReference" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "GRCh38", + "sms:required": "sms:false", + "sms:validationRules": [] + }, { "@id": "bts:ModifiedGRCh38", "@type": "rdfs:Class", @@ -5645,7 +5743,7 @@ "@id": "bts:10xGEM-XFlexGeneExpressionHuman" }, { - "@id": "bts:10xGEM-XUniversal5?GeneExpressionv3" + "@id": "bts:10xGEM-XUniversal5'GeneExpressionv3" }, { "@id": "bts:CEL-Seq2" @@ -5897,10 +5995,10 @@ "sms:validationRules": [] }, { - "@id": "bts:10xGEM-XUniversal5?GeneExpressionv3", + "@id": "bts:10xGEM-XUniversal5'GeneExpressionv3", "@type": "rdfs:Class", "rdfs:comment": "TBD", - "rdfs:label": "10xGEM-XUniversal5?GeneExpressionv3", + "rdfs:label": "10xGEM-XUniversal5'GeneExpressionv3", "rdfs:subClassOf": [ { "@id": "bts:LibraryPrepMethod" @@ -5909,7 +6007,7 @@ "schema:isPartOf": { "@id": "http://schema.biothings.io" }, - "sms:displayName": "10x GEM-X Universal 5? Gene Expression v3", + "sms:displayName": "10x GEM-X Universal 5' Gene Expression v3", "sms:required": "sms:false", "sms:validationRules": [] }, @@ -6925,25 +7023,6 @@ "sms:required": "sms:false", "sms:validationRules": [] }, - { - "@id": "bts:DbGapAccession", - "@type": "rdfs:Class", - "rdfs:comment": "NIH policy requires large-scale human genomics studies to be registered in dbGap. This is a Dataset-specific attribute indicating the unique identifier (i.e., accession) of the corresponding study that is registered in dbGap, formatted as a compact URI, e.g., dbgap:phs003417.v2.p1", - "rdfs:label": "DbGapAccession", - "rdfs:subClassOf": [ - { - "@id": "bts:Thing" - } - ], - "schema:isPartOf": { - "@id": "http://schema.biothings.io" - }, - "sms:displayName": "dbGapAccession", - "sms:required": "sms:false", - "sms:validationRules": [ - "regex search ^dbgap:" - ] - }, { "@id": "bts:At-RiskRA", "@type": "rdfs:Class", @@ -7046,6 +7125,23 @@ "sms:required": "sms:false", "sms:validationRules": [] }, + { + "@id": "bts:Discoidlupuserythematosus", + "@type": "rdfs:Class", + "rdfs:comment": "TBD", + "rdfs:label": "Discoidlupuserythematosus", + "rdfs:subClassOf": [ + { + "@id": "bts:Diagnosis" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "discoid lupus erythematosus", + "sms:required": "sms:false", + "sms:validationRules": [] + }, { "@id": "bts:Lupusnephritis", "@type": "rdfs:Class", @@ -7956,10 +8052,10 @@ "sms:validationRules": [] }, { - "@id": "bts:VitiligoType", + "@id": "bts:VitiligoPattern", "@type": "rdfs:Class", "rdfs:comment": "A high-level classification of vitiligo based on the distribution and patterning of lesions across the body.", - "rdfs:label": "VitiligoType", + "rdfs:label": "VitiligoPattern", "rdfs:subClassOf": [ { "@id": "bts:Thing" @@ -7982,7 +8078,7 @@ "@id": "bts:Unclassified" } ], - "sms:displayName": "vitiligoType", + "sms:displayName": "vitiligoPattern", "sms:required": "sms:false", "sms:validationRules": [] }, @@ -7993,7 +8089,7 @@ "rdfs:label": "Mixed", "rdfs:subClassOf": [ { - "@id": "bts:VitiligoType" + "@id": "bts:VitiligoPattern" } ], "schema:isPartOf": { @@ -8010,7 +8106,7 @@ "rdfs:label": "Non-segmental", "rdfs:subClassOf": [ { - "@id": "bts:VitiligoType" + "@id": "bts:VitiligoPattern" } ], "schema:isPartOf": { @@ -8027,7 +8123,7 @@ "rdfs:label": "Segmental", "rdfs:subClassOf": [ { - "@id": "bts:VitiligoType" + "@id": "bts:VitiligoPattern" } ], "schema:isPartOf": { @@ -8044,7 +8140,7 @@ "rdfs:label": "Unclassified", "rdfs:subClassOf": [ { - "@id": "bts:VitiligoType" + "@id": "bts:VitiligoPattern" } ], "schema:isPartOf": { @@ -9429,40 +9525,6 @@ "regex search ^CL: error" ] }, - { - "@id": "bts:CellType", - "@type": "rdfs:Class", - "rdfs:comment": "The cell type name from Cell Ontology for the corresponding CL identifier.", - "rdfs:label": "CellType", - "rdfs:subClassOf": [ - { - "@id": "bts:Thing" - } - ], - "schema:isPartOf": { - "@id": "http://schema.biothings.io" - }, - "sms:displayName": "cellType", - "sms:required": "sms:false", - "sms:validationRules": [] - }, - { - "@id": "bts:UserDefinedCellType", - "@type": "rdfs:Class", - "rdfs:comment": "User-defined label of a cell type. Contributors are provided this option to use preferred or custom cell type labels that may vary from options and standards set by Cell Ontology.", - "rdfs:label": "UserDefinedCellType", - "rdfs:subClassOf": [ - { - "@id": "bts:Thing" - } - ], - "schema:isPartOf": { - "@id": "http://schema.biothings.io" - }, - "sms:displayName": "userDefinedCellType", - "sms:required": "sms:false", - "sms:validationRules": [] - }, { "@id": "bts:KrennInflammatory", "@type": "rdfs:Class", @@ -10036,6 +10098,42 @@ "sms:displayName": "altSampleID", "sms:required": "sms:false", "sms:validationRules": [] + }, + { + "@id": "bts:SampleCollectionBatch", + "@type": "rdfs:Class", + "rdfs:comment": "A label indicating batching of sample collection or experiment execution that occurs prior to data collection.", + "rdfs:label": "SampleCollectionBatch", + "rdfs:subClassOf": [ + { + "@id": "bts:Thing" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "sampleCollectionBatch", + "sms:required": "sms:false", + "sms:validationRules": [] + }, + { + "@id": "bts:AssociatedAccession", + "@type": "rdfs:Class", + "rdfs:comment": "This is a File and Dataset annotation attribute indicating additional accessions (i.e., unique identifiers) associated with the data when the data has also been submitted to or can be found in other repositories such as GEO, SRA, dbGaP, etc.", + "rdfs:label": "AssociatedAccession", + "rdfs:subClassOf": [ + { + "@id": "bts:Thing" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "associatedAccession", + "sms:required": "sms:false", + "sms:validationRules": [ + "list like error" + ] } ], "@id": "http://schema.biothings.io/#0.1" diff --git a/model_json_schema/ark.BiospecimenMetadataTemplate.schema.json b/model_json_schema/ark.BiospecimenMetadataTemplate.schema.json index 9b61b1c..5b65cad 100644 --- a/model_json_schema/ark.BiospecimenMetadataTemplate.schema.json +++ b/model_json_schema/ark.BiospecimenMetadataTemplate.schema.json @@ -4,72 +4,52 @@ "title": "ark", "type": "object", "properties": { - "biospecimenID": { - "not": { - "type": "null" - }, - "minLength": 1 - }, - "altSampleID": {}, - "biospecimenSubtype": { + "notes": {}, + "program": { "enum": [ - "supernatant", - "frozen tissue", - "nuclei suspension", - "fresh tissue", - "cell or tissue lysate", - "PFA-fixed tissue", - "cell suspension", - "flow-sorted cells", - "FFPE tissue", - "" + "AMP AIM", + "Community Contribution", + "AMP RA/SLE" ] }, - "individualID": { - "not": { - "type": "null" - }, - "minLength": 1 - }, "project": { "type": "array", "items": { "enum": [ - "AIM for RA", - "V-CoRT", - "ELLIPSS", + "UMass V-CoRT", "RA", - "SLE", "LOCKIT", - "STAMP" + "AIM for RA", + "ELLIPSS", + "STAMP", + "SLE" ] }, "maxItems": 7 }, - "notes": {}, "biospecimenType": { "enum": [ - "none", - "uvea", "salivary gland", - "total leukocytes", - "cell line", - "stool", - "primary cell culture", + "fibroblast-like synoviocyte", + "suction blister cells", "PBMCs", - "kidney biopsy", - "synovial tissue", + "none", + "saliva", "skin swab", - "plasma", - "serum", - "fibroblast-like synoviocyte", "skin biopsy", - "saliva", - "suction blister fluid", + "primary cell culture", "urine", + "synovial tissue", + "whole blood", + "kidney biopsy", + "cell line", "synovial fluid", - "suction blister cells", - "whole blood" + "plasma", + "uvea", + "suction blister fluid", + "serum", + "stool", + "total leukocytes" ] }, "Component": { @@ -78,134 +58,165 @@ }, "minLength": 1 }, - "program": { + "biospecimenID": { + "not": { + "type": "null" + }, + "minLength": 1 + }, + "individualID": { + "not": { + "type": "null" + }, + "minLength": 1 + }, + "altSampleID": {}, + "parentBiospecimenID": {}, + "sampleCollectionBatch": {}, + "biospecimenSubtype": { "enum": [ - "AMP RA/SLE", - "AMP AIM", - "Community Contribution" + "nuclei suspension", + "cell or tissue lysate", + "FFPE tissue", + "fresh tissue", + "flow-sorted cells", + "frozen tissue", + "cell suspension", + "PFA-fixed tissue", + "supernatant", + "" ] }, - "parentBiospecimenID": {}, - "cellType": {}, - "userDefinedCellType": {}, - "cellOntologyID": {}, - "FACSPopulation": {}, - "primaryCellSource": { + "visitID": {}, + "skinSiteStatus": { "enum": [ - "pannus-derived epidermis", - "urine", - "uvea", - "salivary gland", - "PBMCs", - "total leukocytes", - "pannus-derived dermis", - "whole blood", - "synovial tissue", - "kidney", + "healthy control", + "lesional proximal", + "lesional", + "non-lesional", "" ] }, - "krennStroma": {}, - "krennSynovitisScore": {}, "anatomicalSite": { "enum": [ - "right 1st MTP joint", "right wrist joint", + "right 1st MTP joint", + "right 2nd MTP joint", + "right 2nd MCP joint", + "left hip joint", + "right 3rd MCP joint", "right hip joint", "left ankle joint", - "other site", - "unknown", - "left knee joint", "left wrist joint", - "right 2nd MTP joint", - "right 3rd MCP joint", "right ankle joint", - "right 2nd MCP joint", - "left hip joint", "right knee joint", "left 2nd MCP joint", + "unknown", + "other site", + "left knee joint", "" ] }, - "krennLining": {}, - "krennInflammatory": {}, - "synovialCollectionProcedure": { + "salivaCollectionProcedure": { "enum": [ - "arthroplasty", - "unknown", - "biopsy", - "synovectomy", + "unstimulated", + "stimulated", "" ] }, - "skinSiteStatus": { + "primaryCellSource": { "enum": [ - "lesional proximal", - "healthy control", - "lesional", - "non-lesional", + "salivary gland", + "pannus-derived epidermis", + "uvea", + "PBMCs", + "synovial tissue", + "kidney", + "whole blood", + "pannus-derived dermis", + "urine", + "total leukocytes", "" ] }, - "salivaCollectionProcedure": { + "cellType": {}, + "cellOntologyID": {}, + "krennLining": {}, + "krennInflammatory": {}, + "synovialCollectionProcedure": { "enum": [ - "stimulated", - "unstimulated", + "unknown", + "biopsy", + "synovectomy", + "arthroplasty", "" ] }, - "visitID": {} + "krennStroma": {}, + "krennSynovitisScore": {}, + "userDefinedCellType": {}, + "FACSPopulation": {} }, "required": [ - "biospecimenID", - "individualID", + "program", "project", "biospecimenType", "Component", - "program" + "biospecimenID", + "individualID" ], "allOf": [ { "if": { "properties": { - "biospecimenSubtype": { + "program": { "enum": [ - "cell suspension" + "AMP AIM" ] } }, "required": [ - "biospecimenSubtype" + "program" ] }, "then": { "properties": { - "cellType": {} + "visitID": { + "not": { + "type": "null" + }, + "minLength": 1 + } }, "required": [ - "cellType" + "visitID" ] } }, { "if": { "properties": { - "biospecimenSubtype": { + "program": { "enum": [ - "flow-sorted cells" + "AMP RA/SLE" ] } }, "required": [ - "biospecimenSubtype" + "program" ] }, "then": { "properties": { - "cellType": {} + "visitID": { + "not": { + "type": "null" + }, + "minLength": 1 + } }, "required": [ - "cellType" + "visitID" ] } }, @@ -214,7 +225,7 @@ "properties": { "biospecimenType": { "enum": [ - "cell line" + "suction blister cells" ] } }, @@ -224,10 +235,17 @@ }, "then": { "properties": { - "cellType": {} + "skinSiteStatus": { + "enum": [ + "healthy control", + "lesional proximal", + "lesional", + "non-lesional" + ] + } }, "required": [ - "cellType" + "skinSiteStatus" ] } }, @@ -236,7 +254,7 @@ "properties": { "biospecimenType": { "enum": [ - "primary cell culture" + "skin swab" ] } }, @@ -246,98 +264,155 @@ }, "then": { "properties": { - "cellType": {} + "skinSiteStatus": { + "enum": [ + "healthy control", + "lesional proximal", + "lesional", + "non-lesional" + ] + } }, "required": [ - "cellType" + "skinSiteStatus" ] } }, { "if": { "properties": { - "biospecimenSubtype": { + "biospecimenType": { "enum": [ - "cell suspension" + "skin biopsy" ] } }, "required": [ - "biospecimenSubtype" + "biospecimenType" ] }, "then": { "properties": { - "userDefinedCellType": {} + "skinSiteStatus": { + "enum": [ + "healthy control", + "lesional proximal", + "lesional", + "non-lesional" + ] + } }, "required": [ - "userDefinedCellType" + "skinSiteStatus" ] } }, { "if": { "properties": { - "biospecimenSubtype": { + "biospecimenType": { "enum": [ - "flow-sorted cells" + "suction blister fluid" ] } }, "required": [ - "biospecimenSubtype" + "biospecimenType" ] }, "then": { "properties": { - "userDefinedCellType": {} + "skinSiteStatus": { + "enum": [ + "healthy control", + "lesional proximal", + "lesional", + "non-lesional" + ] + } }, "required": [ - "userDefinedCellType" + "skinSiteStatus" ] } }, { "if": { "properties": { - "biospecimenSubtype": { + "biospecimenType": { "enum": [ - "cell suspension" + "suction blister cells" ] } }, "required": [ - "biospecimenSubtype" + "biospecimenType" ] }, "then": { "properties": { - "cellOntologyID": {} + "anatomicalSite": { + "enum": [ + "right wrist joint", + "right 1st MTP joint", + "right 2nd MTP joint", + "right 2nd MCP joint", + "left hip joint", + "right 3rd MCP joint", + "right hip joint", + "left ankle joint", + "left wrist joint", + "right ankle joint", + "right knee joint", + "left 2nd MCP joint", + "unknown", + "other site", + "left knee joint" + ] + } }, "required": [ - "cellOntologyID" + "anatomicalSite" ] } }, { "if": { "properties": { - "biospecimenSubtype": { + "biospecimenType": { "enum": [ - "flow-sorted cells" + "skin swab" ] } }, "required": [ - "biospecimenSubtype" + "biospecimenType" ] }, "then": { "properties": { - "cellOntologyID": {} + "anatomicalSite": { + "enum": [ + "right wrist joint", + "right 1st MTP joint", + "right 2nd MTP joint", + "right 2nd MCP joint", + "left hip joint", + "right 3rd MCP joint", + "right hip joint", + "left ankle joint", + "left wrist joint", + "right ankle joint", + "right knee joint", + "left 2nd MCP joint", + "unknown", + "other site", + "left knee joint" + ] + } }, "required": [ - "cellOntologyID" + "anatomicalSite" ] } }, @@ -346,7 +421,7 @@ "properties": { "biospecimenType": { "enum": [ - "cell line" + "skin biopsy" ] } }, @@ -356,10 +431,28 @@ }, "then": { "properties": { - "cellOntologyID": {} + "anatomicalSite": { + "enum": [ + "right wrist joint", + "right 1st MTP joint", + "right 2nd MTP joint", + "right 2nd MCP joint", + "left hip joint", + "right 3rd MCP joint", + "right hip joint", + "left ankle joint", + "left wrist joint", + "right ankle joint", + "right knee joint", + "left 2nd MCP joint", + "unknown", + "other site", + "left knee joint" + ] + } }, "required": [ - "cellOntologyID" + "anatomicalSite" ] } }, @@ -368,7 +461,7 @@ "properties": { "biospecimenType": { "enum": [ - "primary cell culture" + "synovial tissue" ] } }, @@ -378,37 +471,68 @@ }, "then": { "properties": { - "cellOntologyID": {} + "anatomicalSite": { + "enum": [ + "right wrist joint", + "right 1st MTP joint", + "right 2nd MTP joint", + "right 2nd MCP joint", + "left hip joint", + "right 3rd MCP joint", + "right hip joint", + "left ankle joint", + "left wrist joint", + "right ankle joint", + "right knee joint", + "left 2nd MCP joint", + "unknown", + "other site", + "left knee joint" + ] + } }, "required": [ - "cellOntologyID" + "anatomicalSite" ] } }, { "if": { "properties": { - "biospecimenSubtype": { + "biospecimenType": { "enum": [ - "flow-sorted cells" + "synovial fluid" ] } }, "required": [ - "biospecimenSubtype" + "biospecimenType" ] }, "then": { "properties": { - "FACSPopulation": { - "not": { - "type": "null" - }, - "minLength": 1 + "anatomicalSite": { + "enum": [ + "right wrist joint", + "right 1st MTP joint", + "right 2nd MTP joint", + "right 2nd MCP joint", + "left hip joint", + "right 3rd MCP joint", + "right hip joint", + "left ankle joint", + "left wrist joint", + "right ankle joint", + "right knee joint", + "left 2nd MCP joint", + "unknown", + "other site", + "left knee joint" + ] } }, "required": [ - "FACSPopulation" + "anatomicalSite" ] } }, @@ -417,7 +541,7 @@ "properties": { "biospecimenType": { "enum": [ - "primary cell culture" + "suction blister fluid" ] } }, @@ -427,231 +551,178 @@ }, "then": { "properties": { - "primaryCellSource": { + "anatomicalSite": { "enum": [ - "pannus-derived epidermis", - "urine", - "uvea", - "salivary gland", - "PBMCs", - "total leukocytes", - "pannus-derived dermis", - "whole blood", - "synovial tissue", - "kidney" + "right wrist joint", + "right 1st MTP joint", + "right 2nd MTP joint", + "right 2nd MCP joint", + "left hip joint", + "right 3rd MCP joint", + "right hip joint", + "left ankle joint", + "left wrist joint", + "right ankle joint", + "right knee joint", + "left 2nd MCP joint", + "unknown", + "other site", + "left knee joint" ] } }, "required": [ - "primaryCellSource" + "anatomicalSite" ] } }, { "if": { "properties": { - "primaryCellSource": { + "biospecimenType": { "enum": [ - "synovial tissue" + "saliva" ] } }, "required": [ - "primaryCellSource" + "biospecimenType" ] }, "then": { "properties": { - "krennStroma": {} + "salivaCollectionProcedure": { + "enum": [ + "unstimulated", + "stimulated" + ] + } }, "required": [ - "krennStroma" + "salivaCollectionProcedure" ] } }, { "if": { "properties": { - "primaryCellSource": { + "biospecimenType": { "enum": [ - "synovial tissue" + "primary cell culture" ] } }, "required": [ - "primaryCellSource" + "biospecimenType" ] }, "then": { - "properties": { - "krennStroma": {} - }, - "required": [ - "krennStroma" - ] - } - }, - { - "if": { "properties": { "primaryCellSource": { "enum": [ - "synovial tissue" + "salivary gland", + "pannus-derived epidermis", + "uvea", + "PBMCs", + "synovial tissue", + "kidney", + "whole blood", + "pannus-derived dermis", + "urine", + "total leukocytes" ] } }, "required": [ "primaryCellSource" ] - }, - "then": { - "properties": { - "krennSynovitisScore": {} - }, - "required": [ - "krennSynovitisScore" - ] } }, { "if": { "properties": { - "primaryCellSource": { + "biospecimenType": { "enum": [ - "synovial tissue" + "primary cell culture" ] } }, "required": [ - "primaryCellSource" + "biospecimenType" ] }, "then": { "properties": { - "krennSynovitisScore": {} + "cellType": {} }, "required": [ - "krennSynovitisScore" + "cellType" ] } }, { "if": { "properties": { - "primaryCellSource": { + "biospecimenType": { "enum": [ - "synovial tissue" + "cell line" ] } }, "required": [ - "primaryCellSource" + "biospecimenType" ] }, "then": { "properties": { - "anatomicalSite": { - "enum": [ - "right 1st MTP joint", - "right wrist joint", - "right hip joint", - "left ankle joint", - "other site", - "unknown", - "left knee joint", - "left wrist joint", - "right 2nd MTP joint", - "right 3rd MCP joint", - "right ankle joint", - "right 2nd MCP joint", - "left hip joint", - "right knee joint", - "left 2nd MCP joint" - ] - } + "cellType": {} }, "required": [ - "anatomicalSite" + "cellType" ] } }, { "if": { "properties": { - "primaryCellSource": { + "biospecimenSubtype": { "enum": [ - "synovial tissue" + "flow-sorted cells" ] } }, "required": [ - "primaryCellSource" + "biospecimenSubtype" ] }, "then": { "properties": { - "anatomicalSite": { - "enum": [ - "right 1st MTP joint", - "right wrist joint", - "right hip joint", - "left ankle joint", - "other site", - "unknown", - "left knee joint", - "left wrist joint", - "right 2nd MTP joint", - "right 3rd MCP joint", - "right ankle joint", - "right 2nd MCP joint", - "left hip joint", - "right knee joint", - "left 2nd MCP joint" - ] - } + "cellType": {} }, "required": [ - "anatomicalSite" + "cellType" ] } }, { "if": { "properties": { - "biospecimenType": { + "biospecimenSubtype": { "enum": [ - "skin swab" + "cell suspension" ] } }, "required": [ - "biospecimenType" + "biospecimenSubtype" ] }, "then": { "properties": { - "anatomicalSite": { - "enum": [ - "right 1st MTP joint", - "right wrist joint", - "right hip joint", - "left ankle joint", - "other site", - "unknown", - "left knee joint", - "left wrist joint", - "right 2nd MTP joint", - "right 3rd MCP joint", - "right ankle joint", - "right 2nd MCP joint", - "left hip joint", - "right knee joint", - "left 2nd MCP joint" - ] - } + "cellType": {} }, "required": [ - "anatomicalSite" + "cellType" ] } }, @@ -660,7 +731,7 @@ "properties": { "biospecimenType": { "enum": [ - "skin biopsy" + "primary cell culture" ] } }, @@ -670,28 +741,10 @@ }, "then": { "properties": { - "anatomicalSite": { - "enum": [ - "right 1st MTP joint", - "right wrist joint", - "right hip joint", - "left ankle joint", - "other site", - "unknown", - "left knee joint", - "left wrist joint", - "right 2nd MTP joint", - "right 3rd MCP joint", - "right ankle joint", - "right 2nd MCP joint", - "left hip joint", - "right knee joint", - "left 2nd MCP joint" - ] - } + "cellOntologyID": {} }, "required": [ - "anatomicalSite" + "cellOntologyID" ] } }, @@ -700,7 +753,7 @@ "properties": { "biospecimenType": { "enum": [ - "suction blister fluid" + "cell line" ] } }, @@ -710,108 +763,54 @@ }, "then": { "properties": { - "anatomicalSite": { - "enum": [ - "right 1st MTP joint", - "right wrist joint", - "right hip joint", - "left ankle joint", - "other site", - "unknown", - "left knee joint", - "left wrist joint", - "right 2nd MTP joint", - "right 3rd MCP joint", - "right ankle joint", - "right 2nd MCP joint", - "left hip joint", - "right knee joint", - "left 2nd MCP joint" - ] - } + "cellOntologyID": {} }, "required": [ - "anatomicalSite" + "cellOntologyID" ] } }, { "if": { "properties": { - "biospecimenType": { + "biospecimenSubtype": { "enum": [ - "synovial fluid" + "flow-sorted cells" ] } }, "required": [ - "biospecimenType" + "biospecimenSubtype" ] }, "then": { "properties": { - "anatomicalSite": { - "enum": [ - "right 1st MTP joint", - "right wrist joint", - "right hip joint", - "left ankle joint", - "other site", - "unknown", - "left knee joint", - "left wrist joint", - "right 2nd MTP joint", - "right 3rd MCP joint", - "right ankle joint", - "right 2nd MCP joint", - "left hip joint", - "right knee joint", - "left 2nd MCP joint" - ] - } + "cellOntologyID": {} }, "required": [ - "anatomicalSite" + "cellOntologyID" ] } }, { "if": { "properties": { - "biospecimenType": { + "biospecimenSubtype": { "enum": [ - "suction blister cells" + "cell suspension" ] } }, "required": [ - "biospecimenType" + "biospecimenSubtype" ] }, "then": { "properties": { - "anatomicalSite": { - "enum": [ - "right 1st MTP joint", - "right wrist joint", - "right hip joint", - "left ankle joint", - "other site", - "unknown", - "left knee joint", - "left wrist joint", - "right 2nd MTP joint", - "right 3rd MCP joint", - "right ankle joint", - "right 2nd MCP joint", - "left hip joint", - "right knee joint", - "left 2nd MCP joint" - ] - } + "cellOntologyID": {} }, "required": [ - "anatomicalSite" + "cellOntologyID" ] } }, @@ -920,10 +919,10 @@ "properties": { "synovialCollectionProcedure": { "enum": [ - "arthroplasty", "unknown", "biopsy", - "synovectomy" + "synovectomy", + "arthroplasty" ] } }, @@ -949,10 +948,10 @@ "properties": { "synovialCollectionProcedure": { "enum": [ - "arthroplasty", "unknown", "biopsy", - "synovectomy" + "synovectomy", + "arthroplasty" ] } }, @@ -978,10 +977,10 @@ "properties": { "synovialCollectionProcedure": { "enum": [ - "arthroplasty", "unknown", "biopsy", - "synovectomy" + "synovectomy", + "arthroplasty" ] } }, @@ -993,189 +992,151 @@ { "if": { "properties": { - "biospecimenType": { + "primaryCellSource": { "enum": [ - "skin swab" + "synovial tissue" ] } }, "required": [ - "biospecimenType" + "primaryCellSource" ] }, "then": { "properties": { - "skinSiteStatus": { - "enum": [ - "lesional proximal", - "healthy control", - "lesional", - "non-lesional" - ] - } + "krennStroma": {} }, "required": [ - "skinSiteStatus" + "krennStroma" ] } }, { "if": { "properties": { - "biospecimenType": { + "primaryCellSource": { "enum": [ - "skin biopsy" + "synovial tissue" ] } }, "required": [ - "biospecimenType" + "primaryCellSource" ] }, "then": { "properties": { - "skinSiteStatus": { - "enum": [ - "lesional proximal", - "healthy control", - "lesional", - "non-lesional" - ] - } + "krennStroma": {} }, "required": [ - "skinSiteStatus" + "krennStroma" ] } }, { "if": { "properties": { - "biospecimenType": { + "primaryCellSource": { "enum": [ - "suction blister fluid" + "synovial tissue" ] } }, "required": [ - "biospecimenType" + "primaryCellSource" ] }, "then": { "properties": { - "skinSiteStatus": { - "enum": [ - "lesional proximal", - "healthy control", - "lesional", - "non-lesional" - ] - } + "krennSynovitisScore": {} }, "required": [ - "skinSiteStatus" + "krennSynovitisScore" ] } }, { "if": { "properties": { - "biospecimenType": { + "primaryCellSource": { "enum": [ - "suction blister cells" + "synovial tissue" ] } }, "required": [ - "biospecimenType" + "primaryCellSource" ] }, "then": { "properties": { - "skinSiteStatus": { - "enum": [ - "lesional proximal", - "healthy control", - "lesional", - "non-lesional" - ] - } + "krennSynovitisScore": {} }, "required": [ - "skinSiteStatus" + "krennSynovitisScore" ] } }, { "if": { "properties": { - "biospecimenType": { + "biospecimenSubtype": { "enum": [ - "saliva" + "flow-sorted cells" ] } }, "required": [ - "biospecimenType" + "biospecimenSubtype" ] }, "then": { "properties": { - "salivaCollectionProcedure": { - "enum": [ - "stimulated", - "unstimulated" - ] - } + "userDefinedCellType": {} }, "required": [ - "salivaCollectionProcedure" + "userDefinedCellType" ] } }, { "if": { "properties": { - "program": { + "biospecimenSubtype": { "enum": [ - "AMP RA/SLE" + "cell suspension" ] } }, "required": [ - "program" + "biospecimenSubtype" ] }, "then": { "properties": { - "visitID": { - "not": { - "type": "null" - }, - "minLength": 1 - } + "userDefinedCellType": {} }, "required": [ - "visitID" + "userDefinedCellType" ] } }, { "if": { "properties": { - "program": { + "biospecimenSubtype": { "enum": [ - "AMP AIM" + "flow-sorted cells" ] } }, "required": [ - "program" + "biospecimenSubtype" ] }, "then": { "properties": { - "visitID": { + "FACSPopulation": { "not": { "type": "null" }, @@ -1183,7 +1144,7 @@ } }, "required": [ - "visitID" + "FACSPopulation" ] } } diff --git a/model_json_schema/ark.BulkATAC-seqAssayMetadataTemplate.schema.json b/model_json_schema/ark.BulkATAC-seqAssayMetadataTemplate.schema.json index 02b0468..eb7004a 100644 --- a/model_json_schema/ark.BulkATAC-seqAssayMetadataTemplate.schema.json +++ b/model_json_schema/ark.BulkATAC-seqAssayMetadataTemplate.schema.json @@ -4,269 +4,268 @@ "title": "ark", "type": "object", "properties": { - "libraryPrepMethod": { + "totalReads": { + "not": { + "type": "null" + }, + "minLength": 1 + }, + "specimenModality": { "enum": [ - "10x Chromium GEM-X Single Cell 3' v4", - "Takara Human TCR profiling for Illumina", - "10x GEM-X Universal 5? Gene Expression v3", - "TruSeq Stranded mRNA", - "SMARTer Stranded Total RNA v2", - "Chromium Next GEM Single Cell ATAC v1.1", - "CEL-Seq2", - "NEBNext Ultra II Directional RNA Library", - "Takara Human TCRv2 profiling for Illumina", - "Takara Human BCR profiling for Illumina", - "10x GEM-X Flex Gene Expression Human", - "10x Chromium Single Cell Human TCR", - "Nextera XT DNA", - "SMART-Seq Human BCR with UMI", - "10x Chromium Fixed RNA Human Transcriptome", - "Nextera XT", - "10x Chromium Next GEM Single Cell 3'", - "SMART-Seq Human TCR with UMI", - "Takara Human scTCR profiling for Illumina", - "10x Chromium Single Cell Human BCR", - "10x Chromium Next GEM Single Cell 5' v2", - "10x Chromium Next GEM Single Cell 3' 3.1", - "10x Chromium Next GEM Single Cell 5' v1.1", - "QIAseq miRNA Library", - "in-house library prep", - "NEBNext Human Immune Sequencing Kit", - "SMART-Seq v4 Ultra Low Input RNA", - "Fluidigm C1 HT", - "10x Chromium Next GEM Single Cell ATAC v2", - "custom DASH-treatment", - "10x Chromium GEM-X Single Cell 5' v3" + "unknown", + "single specimen", + "multispecimen" ] }, "softwareAndVersion": { "enum": [ - "Cell Ranger v7.0.0", - "BD FACSDiva 8.0.1", - "Cell Ranger v3.0.2", - "Cell Ranger v6.1.1", - "Cell Ranger v3.1.0", - "Space Ranger 3.1.1", - "Cell Ranger v7.2.0", - "Space Ranger 3.1.0", - "Cell Ranger v7.0.1", - "demuxlet", - "Cell Ranger v5.0.0", "Cell Ranger v6.0.1", - "Cell Ranger v6.1.0", + "Space Ranger 3.1.0", + "Cell Ranger v5.0.1", "Cell Ranger v9.0.0", - "Cell Ranger v4.0.0", + "Cell Ranger v6.0.0", + "Cell Ranger v7.1.0", + "Cell Ranger v3.0.1", + "Space Ranger 3.1.1", + "Cell Ranger v5.0.0", + "Cell Ranger v6.1.2", + "Cell Ranger v8.0.1", "Cell Ranger ATAC v1.1.0", - "Space Ranger 3.1.3", "Space Ranger 3.0.1", + "Space Ranger 3.1.3", + "BD FACSDiva 8.0.1", + "Cell Ranger v7.2.0", + "demuxlet", + "Cell Ranger v6.1.0", "Cell Ranger v3.0.0", - "Space Ranger 3.1.2", - "Cell Ranger v5.0.1", - "Cell Ranger v6.0.2", - "Cell Ranger v7.1.0", - "Cell Ranger v8.0.1", + "Cell Ranger v7.0.0", + "Cell Ranger v4.0.0", + "Cell Ranger v3.1.0", "Space Ranger 3.0.0", - "Cell Ranger v6.0.0", - "Cell Ranger v8.0.0", "Cell Ranger 9.0.1", - "Cell Ranger v6.1.2", - "Cell Ranger v3.0.1", + "Cell Ranger v7.0.1", + "Cell Ranger v6.1.1", + "Cell Ranger v6.0.2", + "Cell Ranger v8.0.0", + "Space Ranger 3.1.2", + "Cell Ranger v3.0.2", "" ] }, - "totalReads": { + "libraryPrepMethod": { + "enum": [ + "SMART-Seq Human BCR with UMI", + "NEBNext Human Immune Sequencing Kit", + "10x Chromium Next GEM Single Cell 5' v1.1", + "Chromium Next GEM Single Cell ATAC v1.1", + "10x Chromium GEM-X Single Cell 5' v3", + "10x Chromium Fixed RNA Human Transcriptome", + "QIAseq miRNA Library", + "CEL-Seq2", + "Nextera XT", + "Takara Human BCR profiling for Illumina", + "Takara Human TCRv2 profiling for Illumina", + "SMART-Seq v4 Ultra Low Input RNA", + "custom DASH-treatment", + "10x Chromium Next GEM Single Cell ATAC v2", + "10x Chromium GEM-X Single Cell 3' v4", + "Takara Human scTCR profiling for Illumina", + "in-house library prep", + "10x GEM-X Flex Gene Expression Human", + "10x Chromium Next GEM Single Cell 3'", + "Fluidigm C1 HT", + "TruSeq Stranded mRNA", + "SMARTer Stranded Total RNA v2", + "10x Chromium Single Cell Human TCR", + "10x Chromium Next GEM Single Cell 3' 3.1", + "10x Chromium Single Cell Human BCR", + "Nextera XT DNA", + "10x Chromium Next GEM Single Cell 5' v2", + "SMART-Seq Human TCR with UMI", + "Takara Human TCR profiling for Illumina", + "10x GEM-X Universal 5' Gene Expression v3", + "NEBNext Ultra II Directional RNA Library" + ] + }, + "dataCollectionBatch": {}, + "nucleicAcidSource": { + "type": "array", + "items": { + "enum": [ + "TCR mRNA", + "intracellular protein feature barcode", + "Tn5-accessible gDNA", + "antigen capture barcode", + "multiplexing oligo", + "poly(A) RNA", + "rRNA-depleted RNA", + "CRISPR protospacer feature barcode", + "BCR mRNA", + "gDNA", + "surface protein feature barcode", + "globin-depleted RNA" + ] + }, + "maxItems": 12 + }, + "Component": { "not": { "type": "null" }, "minLength": 1 }, + "sampleProcessingBatch": {}, "assay": { "type": "array", "items": { "enum": [ - "Olink Target 48", + "Xenium", + "snRNASeq", + "Visium", + "WGS", + "feature barcode sequencing", + "imaging mass cytometry", "LC-MS/MS", - "multiplexed ELISA", - "Olink Explore HT", - "CITESeq", - "RNASeq", + "NULISA", "VDJSeq", "Olink Target 96", - "Xenium", - "flow cytometry", + "WES", "kiloplex", - "scVDJSeq", "ASAPSeq", + "flow cytometry", "snATACSeq", - "serial IHC", + "SomaScan", "GenePS SeqFISH", - "NULISA", - "imaging mass cytometry", - "Olink Flex", + "Olink Reveal", + "Olink Explore HT", + "RNASeq", + "Olink Target 48", + "imaging mass spectrometry", + "CITESeq", + "CyTOF", + "SNP array", + "scVDJSeq", "scRNASeq", - "WGS", - "WES", "CE-MS", - "feature barcode sequencing", + "Olink Flex", "CosMX", - "SomaScan", + "serial IHC", "Olink Focus", - "Visium", - "snRNASeq", - "Olink Reveal", - "CyTOF", - "imaging mass spectrometry", - "H&E", - "SNP array" + "multiplexed ELISA", + "H&E" ] }, "maxItems": 34 }, + "alignmentReference": { + "enum": [ + "10x Cell Ranger Human GRCh38 2024-A", + "vdj_GRCh38_alts_ensembl-4.0.0", + "modified GRCh38", + "GRCh38", + "unknown", + "10x Cell Ranger Human GRCh38 2020-A" + ] + }, "platform": { "type": "array", "items": { "enum": [ + "Chromium Xo", "Illumina NextSeq 500", + "Chromium GEM-X Single Cell 3' Chip v4", "BD FACSMelody", - "CyTOF XT", - "Chromium Next GEM Chip Q", - "Hyperion", - "Illumina NovaSeq 6000", - "Chromium iX", - "Not Applicable", - "BD FACSymphony S6", - "BD FACSLyric Clinical", - "BD FACSCanto", + "Xenium", "Chromium Next GEM Chip G", - "Illumina HiSeq 2500", "Chromium X", - "Olink Signature Q100", - "Xenium", - "GEM-X OCM 5' Chip", - "Sony MA900", - "BD FACSCanto II", - "BD FACSDiscover S8", - "Chromium Controller", "Fluidigm BioMark", - "Illumina NovaSeq X", - "BD FACSAria III", + "BD FACSLyric Clinical", "unknown", - "BD LSRFortessa", - "Chromium Xo", + "GEM-X Flex Gene Expression Chip", + "Helios Mass Cytometer", + "BD FACSAria Fusion cell sorter", + "Hyperion", + "BD FACSDiscover S8", + "Chromium Next GEM Chip M", "Cytek Aurora", + "Not Applicable", + "CyTOF XT", "Illumina HiSeq X Ten", - "Thermo Fisher Attune CytPix", - "Chromium Next GEM Chip K", - "Thermo Fisher Attune NxT", - "Visium CytAssist", - "GEM-X Flex Gene Expression Chip", + "Illumina NovaSeq X", + "Olink Signature Q100", + "Illumina HiSeq 2500", "BD FACSDiscover A8", - "Chromium Next GEM Chip M", - "BD FACSAria Fusion cell sorter", + "BD FACSymphony S6", + "Illumina NovaSeq 6000", + "Chromium Next GEM Chip K", "none", - "Helios Mass Cytometer", + "Thermo Fisher Attune NxT", + "Chromium Next GEM Chip Q", + "BD FACSAria III", + "Chromium Controller", + "Chromium iX", + "BD FACSCanto", "Thermo Fisher Attune Xenith", - "Cytek Aurora Evo", + "Thermo Fisher Attune CytPix", "Chromium Next GEM Chip H", - "Chromium GEM-X Single Cell 3' Chip v4" + "Cytek Aurora Evo", + "BD LSRFortessa", + "Visium CytAssist", + "GEM-X OCM 5' Chip", + "Sony MA900", + "BD FACSCanto II" ] }, "maxItems": 43 }, - "alignmentReference": { - "enum": [ - "modified GRCh38", - "10x Cell Ranger Human GRCh38 2024-A", - "unknown", - "vdj_GRCh38_alts_ensembl-4.0.0", - "10x Cell Ranger Human GRCh38 2020-A" - ] - }, - "dataCollectionBatch": {}, - "Component": { - "not": { - "type": "null" - }, - "minLength": 1 - }, - "specimenModality": { - "enum": [ - "multispecimen", - "single specimen" - ] - }, - "nucleicAcidSource": { - "type": "array", - "items": { - "enum": [ - "BCR mRNA", - "TCR mRNA", - "antigen capture barcode", - "gDNA", - "globin-depleted RNA", - "intracellular protein feature barcode", - "CRISPR protospacer feature barcode", - "surface protein feature barcode", - "Tn5-accessible gDNA", - "multiplexing oligo", - "poly(A) RNA", - "rRNA-depleted RNA" - ] - }, - "maxItems": 12 - }, - "sampleProcessingBatch": {}, + "biospecimenID": {}, + "libraryID": {}, "10xProbeSetReference": { "enum": [ + "custom probe set", "Flex Human Transcriptome Probe Set v1.0.1", "Visium Human Transcriptome v1", - "custom probe set", - "Flex Human Transcriptome Probe Set v1.1.0", "Visium Human Transcriptome v2", + "Flex Human Transcriptome Probe Set v1.1.0", "" ] - }, - "libraryID": {}, - "biospecimenID": {} + } }, "required": [ - "libraryPrepMethod", "totalReads", + "specimenModality", + "libraryPrepMethod", + "nucleicAcidSource", + "Component", "assay", - "platform", "alignmentReference", - "Component", - "specimenModality", - "nucleicAcidSource" + "platform" ], "allOf": [ { "if": { "properties": { - "libraryPrepMethod": { + "specimenModality": { "enum": [ - "10x GEM-X Flex Gene Expression Human" + "single specimen" ] } }, "required": [ - "libraryPrepMethod" + "specimenModality" ] }, "then": { "properties": { - "10xProbeSetReference": { - "enum": [ - "Flex Human Transcriptome Probe Set v1.0.1", - "Visium Human Transcriptome v1", - "custom probe set", - "Flex Human Transcriptome Probe Set v1.1.0", - "Visium Human Transcriptome v2" - ] + "biospecimenID": { + "not": { + "type": "null" + }, + "minLength": 1 } }, "required": [ - "10xProbeSetReference" + "biospecimenID" ] } }, @@ -300,27 +299,30 @@ { "if": { "properties": { - "specimenModality": { + "libraryPrepMethod": { "enum": [ - "single specimen" + "10x GEM-X Flex Gene Expression Human" ] } }, "required": [ - "specimenModality" + "libraryPrepMethod" ] }, "then": { "properties": { - "biospecimenID": { - "not": { - "type": "null" - }, - "minLength": 1 + "10xProbeSetReference": { + "enum": [ + "custom probe set", + "Flex Human Transcriptome Probe Set v1.0.1", + "Visium Human Transcriptome v1", + "Visium Human Transcriptome v2", + "Flex Human Transcriptome Probe Set v1.1.0" + ] } }, "required": [ - "biospecimenID" + "10xProbeSetReference" ] } } diff --git a/model_json_schema/ark.BulkRNA-seqAssayMetadataTemplate.schema.json b/model_json_schema/ark.BulkRNA-seqAssayMetadataTemplate.schema.json index acecb85..551e6af 100644 --- a/model_json_schema/ark.BulkRNA-seqAssayMetadataTemplate.schema.json +++ b/model_json_schema/ark.BulkRNA-seqAssayMetadataTemplate.schema.json @@ -4,61 +4,13 @@ "title": "ark", "type": "object", "properties": { - "totalReads": { - "not": { - "type": "null" - }, - "minLength": 1 - }, - "assay": { - "type": "array", - "items": { - "enum": [ - "CyTOF", - "GenePS SeqFISH", - "Olink Flex", - "CE-MS", - "Visium", - "WGS", - "SNP array", - "flow cytometry", - "kiloplex", - "CITESeq", - "H&E", - "Olink Reveal", - "scRNASeq", - "imaging mass cytometry", - "snATACSeq", - "LC-MS/MS", - "Olink Focus", - "scVDJSeq", - "WES", - "Olink Target 96", - "Olink Explore HT", - "snRNASeq", - "NULISA", - "SomaScan", - "serial IHC", - "ASAPSeq", - "multiplexed ELISA", - "Olink Target 48", - "RNASeq", - "imaging mass spectrometry", - "CosMX", - "feature barcode sequencing", - "VDJSeq", - "Xenium" - ] - }, - "maxItems": 34 - }, - "alignmentReference": { + "dataCollectionBatch": {}, + "sampleProcessingBatch": {}, + "specimenModality": { "enum": [ "unknown", - "10x Cell Ranger Human GRCh38 2020-A", - "modified GRCh38", - "vdj_GRCh38_alts_ensembl-4.0.0", - "10x Cell Ranger Human GRCh38 2024-A" + "single specimen", + "multispecimen" ] }, "Component": { @@ -67,177 +19,227 @@ }, "minLength": 1 }, - "nucleicAcidSource": { - "type": "array", - "items": { - "enum": [ - "Tn5-accessible gDNA", - "globin-depleted RNA", - "multiplexing oligo", - "gDNA", - "CRISPR protospacer feature barcode", - "antigen capture barcode", - "poly(A) RNA", - "intracellular protein feature barcode", - "BCR mRNA", - "TCR mRNA", - "rRNA-depleted RNA", - "surface protein feature barcode" - ] - }, - "maxItems": 12 - }, - "specimenModality": { - "enum": [ - "single specimen", - "multispecimen" - ] - }, "libraryPrepMethod": { "enum": [ - "Nextera XT DNA", - "TruSeq Stranded mRNA", - "10x Chromium Next GEM Single Cell 3'", - "NEBNext Ultra II Directional RNA Library", - "10x Chromium Next GEM Single Cell 5' v2", - "10x GEM-X Universal 5? Gene Expression v3", "Nextera XT", + "Chromium Next GEM Single Cell ATAC v1.1", "Takara Human TCR profiling for Illumina", - "10x GEM-X Flex Gene Expression Human", - "QIAseq miRNA Library", - "10x Chromium GEM-X Single Cell 5' v3", - "custom DASH-treatment", - "10x Chromium Next GEM Single Cell 5' v1.1", + "10x GEM-X Universal 5' Gene Expression v3", + "10x Chromium Next GEM Single Cell 3'", "NEBNext Human Immune Sequencing Kit", - "Takara Human TCRv2 profiling for Illumina", - "Fluidigm C1 HT", - "10x Chromium GEM-X Single Cell 3' v4", - "CEL-Seq2", - "in-house library prep", "10x Chromium Single Cell Human TCR", - "SMART-Seq Human BCR with UMI", - "10x Chromium Next GEM Single Cell ATAC v2", + "10x Chromium Next GEM Single Cell 5' v1.1", "10x Chromium Next GEM Single Cell 3' 3.1", - "Chromium Next GEM Single Cell ATAC v1.1", - "10x Chromium Single Cell Human BCR", + "TruSeq Stranded mRNA", + "custom DASH-treatment", + "SMART-Seq Human BCR with UMI", + "10x Chromium GEM-X Single Cell 3' v4", + "Takara Human TCRv2 profiling for Illumina", "SMART-Seq v4 Ultra Low Input RNA", "SMARTer Stranded Total RNA v2", - "10x Chromium Fixed RNA Human Transcriptome", "SMART-Seq Human TCR with UMI", + "Nextera XT DNA", "Takara Human BCR profiling for Illumina", - "Takara Human scTCR profiling for Illumina" + "in-house library prep", + "10x Chromium Next GEM Single Cell ATAC v2", + "NEBNext Ultra II Directional RNA Library", + "CEL-Seq2", + "Fluidigm C1 HT", + "QIAseq miRNA Library", + "10x GEM-X Flex Gene Expression Human", + "10x Chromium GEM-X Single Cell 5' v3", + "Takara Human scTCR profiling for Illumina", + "10x Chromium Single Cell Human BCR", + "10x Chromium Fixed RNA Human Transcriptome", + "10x Chromium Next GEM Single Cell 5' v2" ] }, - "dataCollectionBatch": {}, - "sampleProcessingBatch": {}, + "platform": { + "type": "array", + "items": { + "enum": [ + "Visium CytAssist", + "BD FACSCanto II", + "BD FACSMelody", + "Chromium Xo", + "Helios Mass Cytometer", + "Not Applicable", + "Chromium iX", + "Thermo Fisher Attune NxT", + "none", + "BD FACSAria III", + "BD FACSymphony S6", + "BD FACSCanto", + "Chromium Next GEM Chip H", + "Xenium", + "Cytek Aurora Evo", + "Cytek Aurora", + "Chromium Next GEM Chip M", + "GEM-X Flex Gene Expression Chip", + "BD FACSAria Fusion cell sorter", + "Olink Signature Q100", + "GEM-X OCM 5' Chip", + "Illumina NextSeq 500", + "Thermo Fisher Attune Xenith", + "unknown", + "Hyperion", + "BD FACSDiscover A8", + "Chromium Next GEM Chip G", + "Chromium Next GEM Chip Q", + "Chromium X", + "Illumina NovaSeq X", + "Illumina HiSeq X Ten", + "Fluidigm BioMark", + "BD FACSLyric Clinical", + "CyTOF XT", + "Sony MA900", + "Thermo Fisher Attune CytPix", + "Illumina NovaSeq 6000", + "Chromium GEM-X Single Cell 3' Chip v4", + "BD LSRFortessa", + "BD FACSDiscover S8", + "Chromium Controller", + "Illumina HiSeq 2500", + "Chromium Next GEM Chip K" + ] + }, + "maxItems": 43 + }, "softwareAndVersion": { "enum": [ - "Cell Ranger v6.1.0", - "Cell Ranger v7.1.0", - "Cell Ranger v3.0.0", - "Cell Ranger v7.0.0", - "Cell Ranger v5.0.0", "BD FACSDiva 8.0.1", - "Space Ranger 3.1.0", - "Cell Ranger 9.0.1", - "Space Ranger 3.1.3", - "Cell Ranger v7.2.0", - "Cell Ranger v8.0.1", + "Cell Ranger v8.0.0", + "Cell Ranger v6.0.0", + "Cell Ranger v6.1.1", + "Space Ranger 3.0.1", + "Space Ranger 3.1.2", + "Cell Ranger v7.0.0", + "Cell Ranger v6.1.0", "Cell Ranger v5.0.1", + "Cell Ranger ATAC v1.1.0", + "Cell Ranger v3.1.0", "demuxlet", - "Cell Ranger v9.0.0", - "Space Ranger 3.1.2", + "Cell Ranger v7.2.0", + "Cell Ranger v3.0.0", "Space Ranger 3.0.0", - "Space Ranger 3.0.1", - "Space Ranger 3.1.1", - "Cell Ranger v7.0.1", - "Cell Ranger v6.0.0", - "Cell Ranger v3.1.0", + "Cell Ranger v9.0.0", + "Cell Ranger 9.0.1", + "Cell Ranger v7.1.0", "Cell Ranger v4.0.0", - "Cell Ranger ATAC v1.1.0", - "Cell Ranger v6.0.1", - "Cell Ranger v6.1.2", + "Cell Ranger v3.0.2", "Cell Ranger v3.0.1", - "Cell Ranger v8.0.0", - "Cell Ranger v6.1.1", + "Cell Ranger v6.0.1", + "Cell Ranger v5.0.0", + "Space Ranger 3.1.0", "Cell Ranger v6.0.2", - "Cell Ranger v3.0.2", + "Cell Ranger v6.1.2", + "Cell Ranger v7.0.1", + "Cell Ranger v8.0.1", + "Space Ranger 3.1.3", + "Space Ranger 3.1.1", "" ] }, - "platform": { + "totalReads": { + "not": { + "type": "null" + }, + "minLength": 1 + }, + "alignmentReference": { + "enum": [ + "vdj_GRCh38_alts_ensembl-4.0.0", + "modified GRCh38", + "GRCh38", + "unknown", + "10x Cell Ranger Human GRCh38 2024-A", + "10x Cell Ranger Human GRCh38 2020-A" + ] + }, + "nucleicAcidSource": { "type": "array", "items": { "enum": [ - "Chromium Next GEM Chip H", - "Olink Signature Q100", - "unknown", - "Illumina HiSeq X Ten", - "CyTOF XT", - "Illumina NovaSeq X", - "BD FACSAria III", - "Helios Mass Cytometer", - "Thermo Fisher Attune Xenith", - "Chromium iX", - "Thermo Fisher Attune CytPix", - "Fluidigm BioMark", - "BD FACSAria Fusion cell sorter", - "Chromium GEM-X Single Cell 3' Chip v4", - "Chromium Next GEM Chip Q", - "Chromium X", - "Hyperion", - "BD FACSMelody", - "Chromium Xo", - "Cytek Aurora Evo", - "GEM-X Flex Gene Expression Chip", - "Sony MA900", - "BD FACSLyric Clinical", - "Illumina HiSeq 2500", - "Visium CytAssist", - "BD LSRFortessa", - "BD FACSymphony S6", - "Chromium Next GEM Chip G", - "Chromium Controller", - "BD FACSCanto II", - "GEM-X OCM 5' Chip", - "BD FACSCanto", - "Thermo Fisher Attune NxT", - "BD FACSDiscover S8", - "Cytek Aurora", - "Not Applicable", - "Illumina NextSeq 500", - "Illumina NovaSeq 6000", - "Chromium Next GEM Chip M", - "Chromium Next GEM Chip K", - "BD FACSDiscover A8", - "none", - "Xenium" + "gDNA", + "Tn5-accessible gDNA", + "TCR mRNA", + "intracellular protein feature barcode", + "rRNA-depleted RNA", + "CRISPR protospacer feature barcode", + "BCR mRNA", + "poly(A) RNA", + "antigen capture barcode", + "surface protein feature barcode", + "multiplexing oligo", + "globin-depleted RNA" ] }, - "maxItems": 43 + "maxItems": 12 + }, + "assay": { + "type": "array", + "items": { + "enum": [ + "CyTOF", + "Visium", + "imaging mass cytometry", + "SomaScan", + "GenePS SeqFISH", + "Olink Target 96", + "Olink Flex", + "RNASeq", + "Olink Target 48", + "Xenium", + "Olink Explore HT", + "Olink Focus", + "ASAPSeq", + "snRNASeq", + "imaging mass spectrometry", + "H&E", + "feature barcode sequencing", + "serial IHC", + "scVDJSeq", + "scRNASeq", + "LC-MS/MS", + "SNP array", + "flow cytometry", + "NULISA", + "WES", + "WGS", + "multiplexed ELISA", + "kiloplex", + "snATACSeq", + "CITESeq", + "CE-MS", + "Olink Reveal", + "CosMX", + "VDJSeq" + ] + }, + "maxItems": 34 }, "biospecimenID": {}, "libraryID": {}, "10xProbeSetReference": { "enum": [ - "Flex Human Transcriptome Probe Set v1.0.1", - "Visium Human Transcriptome v1", "custom probe set", + "Flex Human Transcriptome Probe Set v1.0.1", "Visium Human Transcriptome v2", "Flex Human Transcriptome Probe Set v1.1.0", + "Visium Human Transcriptome v1", "" ] } }, "required": [ + "specimenModality", + "Component", + "libraryPrepMethod", + "platform", "totalReads", - "assay", "alignmentReference", - "Component", "nucleicAcidSource", - "specimenModality", - "libraryPrepMethod", - "platform" + "assay" ], "allOf": [ { @@ -311,11 +313,11 @@ "properties": { "10xProbeSetReference": { "enum": [ - "Flex Human Transcriptome Probe Set v1.0.1", - "Visium Human Transcriptome v1", "custom probe set", + "Flex Human Transcriptome Probe Set v1.0.1", "Visium Human Transcriptome v2", - "Flex Human Transcriptome Probe Set v1.1.0" + "Flex Human Transcriptome Probe Set v1.1.0", + "Visium Human Transcriptome v1" ] } }, diff --git a/model_json_schema/ark.ClinicalMetadataTemplate.schema.json b/model_json_schema/ark.ClinicalMetadataTemplate.schema.json index 648e67b..657f453 100644 --- a/model_json_schema/ark.ClinicalMetadataTemplate.schema.json +++ b/model_json_schema/ark.ClinicalMetadataTemplate.schema.json @@ -4,109 +4,49 @@ "title": "ark", "type": "object", "properties": { - "individualID": { - "not": { - "type": "null" - }, - "minLength": 1 - }, "heightUnits": { "enum": [ "centimeters", - "meters", "feet", - "inches" - ] - }, - "height": { - "not": { - "type": "null" - }, - "minLength": 1 - }, - "weightUnits": { - "enum": [ - "lb", - "kg", - "oz", - "g" + "inches", + "meters" ] }, - "age": { - "not": { - "type": "null" - }, - "minLength": 1 - }, "comorbidities": { "type": "array", "items": { "enum": [ - "Hashimoto's Thyroiditis", "autoimmune thyroid disease", - "psoriasis", - "cardiovascular disease", - "other", "multiple sclerosis", + "psoriasis", + "systemic lupus erythematosus", "inflammatory bowel disease", "psoriatic arthritis", - "pulmonary disease", - "rheumatoid arthritis", "diabetes", - "systemic lupus erythematosus", + "rheumatoid arthritis", + "Hashimoto's Thyroiditis", + "pulmonary disease", + "other", + "cardiovascular disease", "" ] }, "maxItems": 12 }, - "diagnosis": { - "type": "array", - "items": { - "enum": [ - "Sjogren's disease", - "OA", - "scleroderma", - "unknown", - "psoriasis", - "dermatomyositis", - "At-Risk RA", - "vitiligo", - "SLE", - "control", - "cutaneous lupus erythematosus", - "psoriatic arthritis", - "lupus nephritis", - "RA" - ] - }, - "maxItems": 14 - }, - "project": { - "type": "array", - "items": { - "enum": [ - "STAMP", - "AIM for RA", - "LOCKIT", - "SLE", - "V-CoRT", - "ELLIPSS", - "RA" - ] - }, - "maxItems": 7 - }, - "species": { - "enum": [ - "Homo sapiens" - ] - }, - "Component": { + "age": { "not": { "type": "null" }, "minLength": 1 }, + "ethnicity": { + "enum": [ + "Hispanic or Latino", + "unknown", + "Not Hispanic or Latino", + "" + ] + }, "ageUnits": { "enum": [ "years", @@ -119,82 +59,144 @@ }, "minLength": 1 }, - "sex": { + "program": { "enum": [ - "unknown", - "intersex", - "male", - "female" + "AMP AIM", + "AMP RA/SLE", + "Community Contribution" ] }, - "program": { + "Component": { + "not": { + "type": "null" + }, + "minLength": 1 + }, + "species": { "enum": [ - "AMP AIM", - "Community Contribution", - "AMP RA/SLE" + "Homo sapiens" ] }, - "ethnicity": { + "individualID": { + "not": { + "type": "null" + }, + "minLength": 1 + }, + "sex": { "enum": [ + "intersex", "unknown", - "Hispanic or Latino", - "Not Hispanic or Latino", - "" + "female", + "male" ] }, "race": { "enum": [ "White", "Hispanic", - "unknown", - "other", "Mixed Race", "American Indian or Alaska Native", + "Asian", + "unknown", + "other", "Native Hawaiian or Other Pacific Islander", "Black or African American", - "Asian", "" ] }, + "weightUnits": { + "enum": [ + "g", + "kg", + "oz", + "lb" + ] + }, + "project": { + "type": "array", + "items": { + "enum": [ + "AIM for RA", + "STAMP", + "LOCKIT", + "SLE", + "UMass V-CoRT", + "ELLIPSS", + "RA" + ] + }, + "maxItems": 7 + }, + "height": { + "not": { + "type": "null" + }, + "minLength": 1 + }, + "diagnosis": { + "type": "array", + "items": { + "enum": [ + "dermatomyositis", + "Sjogren's disease", + "cutaneous lupus erythematosus", + "psoriasis", + "vitiligo", + "scleroderma", + "control", + "At-Risk RA", + "OA", + "psoriatic arthritis", + "unknown", + "lupus nephritis", + "SLE", + "discoid lupus erythematosus", + "Not Applicable", + "RA" + ] + }, + "maxItems": 16 + }, "PASI": {}, "diabetesType": { "enum": [ - "type 1", + "gestational", "unknown", + "type 1", "type 2", - "gestational", "" ] }, + "visitID": {}, "CDASI": {}, "VASI": {}, - "VIDA": {}, "VETI": {}, - "vitiligoType": { + "vitiligoPattern": { "enum": [ - "non-segmental", - "segmental", "mixed", "unclassified", + "non-segmental", + "segmental", "" ] }, - "visitID": {} + "VIDA": {} }, "required": [ - "individualID", "heightUnits", - "height", - "weightUnits", "age", - "diagnosis", - "project", - "species", - "Component", "ageUnits", "weight", + "program", + "Component", + "species", + "individualID", "sex", - "program" + "weightUnits", + "project", + "height", + "diagnosis" ], "allOf": [ { @@ -302,10 +304,10 @@ "properties": { "diabetesType": { "enum": [ - "type 1", + "gestational", "unknown", + "type 1", "type 2", - "gestational", "" ] } @@ -318,44 +320,54 @@ { "if": { "properties": { - "diagnosis": { + "program": { "enum": [ - "dermatomyositis" + "AMP AIM" ] } }, "required": [ - "diagnosis" + "program" ] }, "then": { "properties": { - "CDASI": {} + "visitID": { + "not": { + "type": "null" + }, + "minLength": 1 + } }, "required": [ - "CDASI" + "visitID" ] } }, { "if": { "properties": { - "diagnosis": { + "program": { "enum": [ - "vitiligo" + "AMP RA/SLE" ] } }, "required": [ - "diagnosis" + "program" ] }, "then": { "properties": { - "VASI": {} + "visitID": { + "not": { + "type": "null" + }, + "minLength": 1 + } }, "required": [ - "VASI" + "visitID" ] } }, @@ -364,7 +376,7 @@ "properties": { "diagnosis": { "enum": [ - "vitiligo" + "dermatomyositis" ] } }, @@ -374,10 +386,10 @@ }, "then": { "properties": { - "VIDA": {} + "CDASI": {} }, "required": [ - "VIDA" + "CDASI" ] } }, @@ -396,10 +408,10 @@ }, "then": { "properties": { - "VETI": {} + "VASI": {} }, "required": [ - "VETI" + "VASI" ] } }, @@ -418,72 +430,62 @@ }, "then": { "properties": { - "vitiligoType": { - "enum": [ - "non-segmental", - "segmental", - "mixed", - "unclassified", - "" - ] - } + "VETI": {} }, "required": [ - "vitiligoType" + "VETI" ] } }, { "if": { "properties": { - "program": { + "diagnosis": { "enum": [ - "AMP AIM" + "vitiligo" ] } }, "required": [ - "program" + "diagnosis" ] }, "then": { "properties": { - "visitID": { - "not": { - "type": "null" - }, - "minLength": 1 + "vitiligoPattern": { + "enum": [ + "mixed", + "unclassified", + "non-segmental", + "segmental", + "" + ] } }, "required": [ - "visitID" + "vitiligoPattern" ] } }, { "if": { "properties": { - "program": { + "diagnosis": { "enum": [ - "AMP RA/SLE" + "vitiligo" ] } }, "required": [ - "program" + "diagnosis" ] }, "then": { "properties": { - "visitID": { - "not": { - "type": "null" - }, - "minLength": 1 - } + "VIDA": {} }, "required": [ - "visitID" + "VIDA" ] } } diff --git a/model_json_schema/ark.CyTOFAssayMetadataTemplate.schema.json b/model_json_schema/ark.CyTOFAssayMetadataTemplate.schema.json index 96f21e8..208a9c2 100644 --- a/model_json_schema/ark.CyTOFAssayMetadataTemplate.schema.json +++ b/model_json_schema/ark.CyTOFAssayMetadataTemplate.schema.json @@ -4,168 +4,168 @@ "title": "ark", "type": "object", "properties": { + "softwareAndVersion": { + "enum": [ + "Cell Ranger v6.0.2", + "Cell Ranger v3.0.0", + "Cell Ranger 9.0.1", + "Space Ranger 3.1.0", + "Cell Ranger ATAC v1.1.0", + "Cell Ranger v4.0.0", + "Cell Ranger v3.0.2", + "Cell Ranger v9.0.0", + "Space Ranger 3.1.1", + "Cell Ranger v6.0.0", + "Cell Ranger v7.0.0", + "Cell Ranger v5.0.1", + "Cell Ranger v7.2.0", + "Cell Ranger v3.0.1", + "Cell Ranger v5.0.0", + "BD FACSDiva 8.0.1", + "Space Ranger 3.1.2", + "demuxlet", + "Cell Ranger v3.1.0", + "Cell Ranger v6.1.0", + "Space Ranger 3.0.1", + "Cell Ranger v8.0.1", + "Cell Ranger v6.0.1", + "Cell Ranger v7.1.0", + "Space Ranger 3.0.0", + "Cell Ranger v7.0.1", + "Cell Ranger v6.1.1", + "Cell Ranger v6.1.2", + "Space Ranger 3.1.3", + "Cell Ranger v8.0.0", + "" + ] + }, + "dataCollectionBatch": {}, + "Component": { + "not": { + "type": "null" + }, + "minLength": 1 + }, "targetPanelSynID": { "not": { "type": "null" }, "minLength": 1 }, - "targetPanel": { + "biospecimenID": { "not": { "type": "null" }, "minLength": 1 }, + "sampleProcessingBatch": {}, "platform": { "type": "array", "items": { "enum": [ - "Illumina NextSeq 500", - "Chromium Next GEM Chip K", - "Chromium Next GEM Chip M", - "Chromium Controller", - "Cytek Aurora", "BD FACSAria Fusion cell sorter", - "Olink Signature Q100", + "unknown", "GEM-X Flex Gene Expression Chip", - "Illumina NovaSeq 6000", - "BD FACSDiscover S8", - "Thermo Fisher Attune CytPix", - "BD FACSCanto II", - "Chromium GEM-X Single Cell 3' Chip v4", - "BD FACSymphony S6", + "BD FACSCanto", + "BD FACSMelody", + "BD FACSLyric Clinical", + "Illumina HiSeq X Ten", + "Illumina NextSeq 500", "Cytek Aurora Evo", - "Chromium Next GEM Chip H", "Chromium Next GEM Chip Q", - "Thermo Fisher Attune NxT", - "BD FACSDiscover A8", - "Illumina NovaSeq X", - "BD FACSLyric Clinical", - "BD LSRFortessa", - "BD FACSMelody", - "Hyperion", - "unknown", "Helios Mass Cytometer", - "Chromium X", + "BD FACSymphony S6", + "Chromium Controller", + "Chromium Next GEM Chip K", "Fluidigm BioMark", - "CyTOF XT", - "Not Applicable", "GEM-X OCM 5' Chip", - "none", - "BD FACSAria III", - "Illumina HiSeq X Ten", - "Illumina HiSeq 2500", + "CyTOF XT", + "Cytek Aurora", "Xenium", - "Chromium Next GEM Chip G", - "Chromium iX", + "Visium CytAssist", + "Thermo Fisher Attune Xenith", + "BD FACSAria III", + "Chromium X", + "Chromium Next GEM Chip H", + "Illumina NovaSeq X", "Sony MA900", + "Chromium Next GEM Chip G", + "Olink Signature Q100", + "BD LSRFortessa", + "BD FACSDiscover S8", "Chromium Xo", - "BD FACSCanto", - "Thermo Fisher Attune Xenith", - "Visium CytAssist" + "Thermo Fisher Attune NxT", + "BD FACSCanto II", + "none", + "Not Applicable", + "Chromium GEM-X Single Cell 3' Chip v4", + "Illumina HiSeq 2500", + "Chromium Next GEM Chip M", + "BD FACSDiscover A8", + "Hyperion", + "Thermo Fisher Attune CytPix", + "Illumina NovaSeq 6000", + "Chromium iX" ] }, "maxItems": 43 }, - "dataCollectionBatch": {}, + "targetPanelSize": {}, "assay": { "type": "array", "items": { "enum": [ - "imaging mass cytometry", - "CyTOF", - "Olink Target 96", - "SomaScan", - "CE-MS", "H&E", - "WGS", + "VDJSeq", "imaging mass spectrometry", - "Olink Target 48", - "NULISA", - "serial IHC", - "WES", + "RNASeq", "Olink Explore HT", - "Olink Focus", - "CITESeq", + "Olink Target 96", + "Olink Flex", + "kiloplex", + "imaging mass cytometry", "CosMX", - "scRNASeq", "snRNASeq", - "RNASeq", + "CE-MS", + "WES", + "SomaScan", + "Xenium", "ASAPSeq", - "Olink Flex", - "snATACSeq", - "GenePS SeqFISH", - "SNP array", - "LC-MS/MS", + "Olink Target 48", "scVDJSeq", "multiplexed ELISA", - "feature barcode sequencing", - "kiloplex", - "Olink Reveal", + "scRNASeq", + "snATACSeq", + "WGS", "flow cytometry", - "Xenium", - "VDJSeq", - "Visium" + "CITESeq", + "NULISA", + "LC-MS/MS", + "Olink Focus", + "GenePS SeqFISH", + "Visium", + "serial IHC", + "Olink Reveal", + "feature barcode sequencing", + "SNP array", + "CyTOF" ] }, "maxItems": 34 }, - "Component": { - "not": { - "type": "null" - }, - "minLength": 1 - }, - "softwareAndVersion": { - "enum": [ - "Cell Ranger v9.0.0", - "Cell Ranger v3.0.1", - "Space Ranger 3.0.1", - "Cell Ranger v6.0.0", - "Cell Ranger v6.0.2", - "demuxlet", - "Cell Ranger v7.1.0", - "Cell Ranger 9.0.1", - "Cell Ranger v3.0.2", - "Space Ranger 3.0.0", - "Space Ranger 3.1.2", - "Cell Ranger v5.0.0", - "Space Ranger 3.1.0", - "Cell Ranger v7.0.1", - "Cell Ranger v7.2.0", - "Cell Ranger v6.1.1", - "Cell Ranger v8.0.0", - "Cell Ranger v3.1.0", - "Space Ranger 3.1.1", - "Cell Ranger v6.0.1", - "Cell Ranger v3.0.0", - "Cell Ranger v4.0.0", - "Cell Ranger v6.1.0", - "Cell Ranger v8.0.1", - "BD FACSDiva 8.0.1", - "Cell Ranger ATAC v1.1.0", - "Cell Ranger v6.1.2", - "Cell Ranger v5.0.1", - "Cell Ranger v7.0.0", - "Space Ranger 3.1.3", - "" - ] - }, - "biospecimenID": { + "targetPanel": { "not": { "type": "null" }, "minLength": 1 - }, - "targetPanelSize": {}, - "sampleProcessingBatch": {} + } }, "required": [ + "Component", "targetPanelSynID", - "targetPanel", + "biospecimenID", "platform", "assay", - "Component", - "biospecimenID" + "targetPanel" ] } \ No newline at end of file diff --git a/model_json_schema/ark.DatasetAnnotationTemplate.schema.json b/model_json_schema/ark.DatasetAnnotationTemplate.schema.json index 16a1ed6..12fa0e9 100644 --- a/model_json_schema/ark.DatasetAnnotationTemplate.schema.json +++ b/model_json_schema/ark.DatasetAnnotationTemplate.schema.json @@ -4,241 +4,243 @@ "title": "ark", "type": "object", "properties": { - "Component": { - "not": { - "type": "null" - }, - "minLength": 1 - }, - "datasetType": { + "acknowledgmentStatement": { "enum": [ - "publication", - "experimental" + "syn26710600/wiki/619685" ] }, "diagnosis": { "type": "array", "items": { "enum": [ - "OA", - "RA", + "dermatomyositis", + "lupus nephritis", + "psoriatic arthritis", "control", + "Sjogren's disease", + "unknown", "cutaneous lupus erythematosus", - "psoriatic arthritis", - "scleroderma", + "vitiligo", "SLE", - "lupus nephritis", + "scleroderma", "At-Risk RA", - "Sjogren's disease", - "vitiligo", "psoriasis", - "dermatomyositis", - "unknown" + "OA", + "discoid lupus erythematosus", + "RA", + "Not Applicable" ] }, - "maxItems": 14 + "maxItems": 16 }, - "datasetStatus": { + "species": { "enum": [ - "deprecated", - "released", - "unreleased", - "test", - "under peer review" + "Homo sapiens" ] }, - "biospecimenType": { + "associatedCodeURL": {}, + "associatedDataset": {}, + "dataSubtype": { "type": "array", "items": { "enum": [ - "synovial tissue", - "urine", - "primary cell culture", - "suction blister cells", - "skin biopsy", - "salivary gland", - "serum", - "kidney biopsy", - "uvea", - "cell line", - "fibroblast-like synoviocyte", - "skin swab", + "single-cell", + "pseudobulk", + "single-nucleus", "none", - "plasma", - "whole blood", - "synovial fluid", - "PBMCs", - "suction blister fluid", - "stool", - "total leukocytes", - "saliva" + "bulk", + "spatial" ] }, - "maxItems": 21 + "maxItems": 6 }, - "assay": { + "project": { "type": "array", "items": { "enum": [ - "WGS", - "CE-MS", - "Xenium", - "SomaScan", - "Olink Target 96", - "VDJSeq", - "imaging mass cytometry", - "WES", - "kiloplex", - "scRNASeq", - "imaging mass spectrometry", - "snRNASeq", - "Olink Reveal", - "RNASeq", - "scVDJSeq", - "flow cytometry", - "CITESeq", - "NULISA", - "feature barcode sequencing", - "CosMX", - "H&E", - "CyTOF", - "multiplexed ELISA", - "Olink Focus", - "serial IHC", - "snATACSeq", - "GenePS SeqFISH", - "Olink Flex", - "ASAPSeq", - "Olink Target 48", - "Visium", - "Olink Explore HT", - "LC-MS/MS", - "SNP array" + "AIM for RA", + "ELLIPSS", + "LOCKIT", + "STAMP", + "SLE", + "UMass V-CoRT", + "RA" ] }, - "maxItems": 34 - }, - "datasetDescription": { - "not": { - "type": "null" - }, - "minLength": 1 - }, - "acknowledgmentStatement": { - "enum": [ - "syn26710600/wiki/619685" - ] - }, - "biospecimenSubtype": { - "enum": [ - "nuclei suspension", - "FFPE tissue", - "fresh tissue", - "PFA-fixed tissue", - "flow-sorted cells", - "cell suspension", - "supernatant", - "cell or tissue lysate", - "frozen tissue", - "" - ] - }, - "dbGapAccession": {}, - "species": { - "enum": [ - "Homo sapiens" - ] + "maxItems": 7 }, - "associatedCodeURL": {}, "dataType": { "type": "array", "items": { "enum": [ - "transcriptomics", - "lipidomics", - "cytometry", - "epigenomics", - "proteomics", + "immunostaining", "microbiome", - "genomics", "immune repertoire profiling", + "metabolomics", "multimodal", - "immunostaining", + "proteomics", + "transcriptomics", "histology", - "metabolomics" + "epigenomics", + "cytometry", + "lipidomics", + "genomics" ] }, "maxItems": 12 }, - "publicationSynID": {}, - "project": { + "assay": { "type": "array", "items": { "enum": [ - "RA", - "LOCKIT", - "V-CoRT", - "SLE", - "ELLIPSS", - "STAMP", - "AIM for RA" + "Olink Target 48", + "CITESeq", + "flow cytometry", + "LC-MS/MS", + "multiplexed ELISA", + "VDJSeq", + "serial IHC", + "Olink Explore HT", + "Visium", + "GenePS SeqFISH", + "ASAPSeq", + "SomaScan", + "Xenium", + "Olink Flex", + "Olink Target 96", + "Olink Focus", + "CyTOF", + "NULISA", + "feature barcode sequencing", + "imaging mass spectrometry", + "snRNASeq", + "CosMX", + "kiloplex", + "RNASeq", + "scRNASeq", + "WES", + "snATACSeq", + "Olink Reveal", + "CE-MS", + "imaging mass cytometry", + "WGS", + "SNP array", + "H&E", + "scVDJSeq" ] }, - "maxItems": 7 + "maxItems": 34 }, - "program": { - "enum": [ - "Community Contribution", - "AMP AIM", - "AMP RA/SLE" - ] + "ImmPortAccession": {}, + "biospecimenType": { + "type": "array", + "items": { + "enum": [ + "serum", + "suction blister fluid", + "PBMCs", + "uvea", + "skin biopsy", + "plasma", + "fibroblast-like synoviocyte", + "urine", + "whole blood", + "kidney biopsy", + "synovial tissue", + "total leukocytes", + "stool", + "skin swab", + "saliva", + "none", + "salivary gland", + "primary cell culture", + "suction blister cells", + "synovial fluid", + "cell line" + ] + }, + "maxItems": 21 }, - "associatedDataset": {}, + "publicationSynID": {}, "ARKRelease": { "enum": [ - "2024.07.R1", - "2024.08.R1", - "2.0", - "2025.08.R1", - "2025.06.R1", - "2024.06.R1", - "2025.09.R1", - "2025.03.R1", - "2025.07.R1", + "2025.02.R1", "2025.05.R1", - "2025.11.R1", + "2024.07.R1", "2024.12.R1", - "2025.01.R1", + "2025.07.R1", + "2024.10.R1", "1.0", "2025.10.R1", - "2025.02.R1", "2025.04.R1", - "2024.10.R1", + "2025.09.R1", + "2.0", "2024.09.R1", - "2025.12.R1" + "2025.03.R1", + "2025.01.R1", + "2024.08.R1", + "2025.12.R1", + "2025.08.R1", + "2024.06.R1", + "2025.06.R1", + "2025.11.R1" ] }, - "ImmPortAccession": {}, - "dataSubtype": { - "type": "array", - "items": { - "enum": [ - "pseudobulk", - "bulk", - "single-cell", - "single-nucleus", - "none", - "spatial" - ] + "datasetStatus": { + "enum": [ + "test", + "deprecated", + "unreleased", + "released", + "under peer review" + ] + }, + "datasetDescription": { + "not": { + "type": "null" }, - "maxItems": 6 + "minLength": 1 + }, + "associatedAccession": {}, + "Component": { + "not": { + "type": "null" + }, + "minLength": 1 + }, + "datasetType": { + "enum": [ + "experimental", + "publication" + ] + }, + "program": { + "enum": [ + "Community Contribution", + "AMP AIM", + "AMP RA/SLE" + ] + }, + "biospecimenSubtype": { + "enum": [ + "supernatant", + "frozen tissue", + "PFA-fixed tissue", + "FFPE tissue", + "flow-sorted cells", + "cell or tissue lysate", + "fresh tissue", + "nuclei suspension", + "cell suspension", + "" + ] }, "programPhase": { "type": "array", "items": { "enum": [ - "II", "I", + "II", "" ] }, @@ -246,20 +248,20 @@ } }, "required": [ - "Component", - "datasetType", - "diagnosis", - "datasetStatus", - "biospecimenType", - "assay", - "datasetDescription", "acknowledgmentStatement", + "diagnosis", "species", - "dataType", + "dataSubtype", "project", - "program", + "dataType", + "assay", + "biospecimenType", "ARKRelease", - "dataSubtype" + "datasetStatus", + "datasetDescription", + "Component", + "datasetType", + "program" ], "allOf": [ { @@ -281,8 +283,8 @@ "type": "array", "items": { "enum": [ - "II", - "I" + "I", + "II" ] }, "maxItems": 2 diff --git a/model_json_schema/ark.FCSFileAnnotationTemplate.schema.json b/model_json_schema/ark.FCSFileAnnotationTemplate.schema.json index b739e07..66351b4 100644 --- a/model_json_schema/ark.FCSFileAnnotationTemplate.schema.json +++ b/model_json_schema/ark.FCSFileAnnotationTemplate.schema.json @@ -4,16 +4,18 @@ "title": "ark", "type": "object", "properties": { - "specimenModality": { + "fileFormat": { "enum": [ - "single specimen", - "multispecimen" + "fcs", + "" ] }, - "assay": { + "eventCount": {}, + "specimenModality": { "enum": [ - "CyTOF", - "flow cytometry" + "multispecimen", + "single specimen", + "unknown" ] }, "Component": { @@ -22,22 +24,21 @@ }, "minLength": 1 }, - "fileFormat": { + "assay": { "enum": [ - "fcs", - "" + "CyTOF", + "flow cytometry" ] }, - "eventCount": {}, - "biospecimenID": {}, - "individualID": {}, + "dataCollectionBatch": {}, "sampleProcessingBatch": {}, - "dataCollectionBatch": {} + "individualID": {}, + "biospecimenID": {} }, "required": [ "specimenModality", - "assay", - "Component" + "Component", + "assay" ], "allOf": [ { @@ -45,7 +46,7 @@ "properties": { "specimenModality": { "enum": [ - "single specimen" + "multispecimen" ] } }, @@ -55,15 +56,10 @@ }, "then": { "properties": { - "biospecimenID": { - "not": { - "type": "null" - }, - "minLength": 1 - } + "dataCollectionBatch": {} }, "required": [ - "biospecimenID" + "dataCollectionBatch" ] } }, @@ -72,7 +68,7 @@ "properties": { "specimenModality": { "enum": [ - "single specimen" + "multispecimen" ] } }, @@ -82,15 +78,10 @@ }, "then": { "properties": { - "individualID": { - "not": { - "type": "null" - }, - "minLength": 1 - } + "sampleProcessingBatch": {} }, "required": [ - "individualID" + "sampleProcessingBatch" ] } }, @@ -99,7 +90,7 @@ "properties": { "specimenModality": { "enum": [ - "multispecimen" + "single specimen" ] } }, @@ -109,10 +100,15 @@ }, "then": { "properties": { - "sampleProcessingBatch": {} + "individualID": { + "not": { + "type": "null" + }, + "minLength": 1 + } }, "required": [ - "sampleProcessingBatch" + "individualID" ] } }, @@ -121,7 +117,7 @@ "properties": { "specimenModality": { "enum": [ - "multispecimen" + "single specimen" ] } }, @@ -131,10 +127,15 @@ }, "then": { "properties": { - "dataCollectionBatch": {} + "biospecimenID": { + "not": { + "type": "null" + }, + "minLength": 1 + } }, "required": [ - "dataCollectionBatch" + "biospecimenID" ] } } diff --git a/model_json_schema/ark.FastqFileAnnotationTemplate.schema.json b/model_json_schema/ark.FastqFileAnnotationTemplate.schema.json index 675a961..6c3e24c 100644 --- a/model_json_schema/ark.FastqFileAnnotationTemplate.schema.json +++ b/model_json_schema/ark.FastqFileAnnotationTemplate.schema.json @@ -4,73 +4,74 @@ "title": "ark", "type": "object", "properties": { + "Component": { + "not": { + "type": "null" + }, + "minLength": 1 + }, + "fileFormat": { + "enum": [ + "fastq" + ] + }, + "specimenModality": { + "enum": [ + "multispecimen", + "unknown", + "single specimen" + ] + }, "readLength": {}, "assay": { "type": "array", "items": { "enum": [ - "scVDJSeq", + "RNASeq", + "ASAPSeq", "feature barcode sequencing", + "snRNASeq", + "scVDJSeq", "WGS", "VDJSeq", - "CITESeq", - "WES", - "RNASeq", - "ASAPSeq", + "scRNASeq", "snATACSeq", - "snRNASeq", - "scRNASeq" + "WES", + "CITESeq" ] }, "maxItems": 11 }, - "fileFormat": { - "enum": [ - "fastq" - ] - }, - "Component": { - "not": { - "type": "null" - }, - "minLength": 1 - }, - "specimenModality": { - "enum": [ - "single specimen", - "multispecimen" - ] - }, - "targetPanel": {}, - "targetPanelSynID": {}, - "targetPanelSize": {}, + "libraryID": {}, "biospecimenID": {}, "individualID": {}, - "libraryID": {} + "targetPanel": {}, + "targetPanelSynID": {}, + "targetPanelSize": {} }, "required": [ - "assay", - "fileFormat", "Component", - "specimenModality" + "fileFormat", + "specimenModality", + "assay" ], "allOf": [ { "if": { "properties": { - "assay": { + "specimenModality": { "enum": [ - "feature barcode sequencing" + "multispecimen" ] } }, "required": [ - "assay" + "specimenModality" ] }, "then": { "properties": { - "targetPanel": { + "libraryID": { "not": { "type": "null" }, @@ -78,26 +79,26 @@ } }, "required": [ - "targetPanel" + "libraryID" ] } }, { "if": { "properties": { - "assay": { + "specimenModality": { "enum": [ - "feature barcode sequencing" + "single specimen" ] } }, "required": [ - "assay" + "specimenModality" ] }, "then": { "properties": { - "targetPanelSynID": { + "biospecimenID": { "not": { "type": "null" }, @@ -105,48 +106,53 @@ } }, "required": [ - "targetPanelSynID" + "biospecimenID" ] } }, { "if": { "properties": { - "assay": { + "specimenModality": { "enum": [ - "feature barcode sequencing" + "single specimen" ] } }, "required": [ - "assay" + "specimenModality" ] }, "then": { "properties": { - "targetPanelSize": {} + "individualID": { + "not": { + "type": "null" + }, + "minLength": 1 + } }, "required": [ - "targetPanelSize" + "individualID" ] } }, { "if": { "properties": { - "specimenModality": { + "assay": { "enum": [ - "single specimen" + "feature barcode sequencing" ] } }, "required": [ - "specimenModality" + "assay" ] }, "then": { "properties": { - "biospecimenID": { + "targetPanel": { "not": { "type": "null" }, @@ -154,26 +160,26 @@ } }, "required": [ - "biospecimenID" + "targetPanel" ] } }, { "if": { "properties": { - "specimenModality": { + "assay": { "enum": [ - "single specimen" + "feature barcode sequencing" ] } }, "required": [ - "specimenModality" + "assay" ] }, "then": { "properties": { - "individualID": { + "targetPanelSynID": { "not": { "type": "null" }, @@ -181,34 +187,29 @@ } }, "required": [ - "individualID" + "targetPanelSynID" ] } }, { "if": { "properties": { - "specimenModality": { + "assay": { "enum": [ - "multispecimen" + "feature barcode sequencing" ] } }, "required": [ - "specimenModality" + "assay" ] }, "then": { "properties": { - "libraryID": { - "not": { - "type": "null" - }, - "minLength": 1 - } + "targetPanelSize": {} }, "required": [ - "libraryID" + "targetPanelSize" ] } } diff --git a/model_json_schema/ark.InVitroBiospecimenMetadataTemplate.schema.json b/model_json_schema/ark.InVitroBiospecimenMetadataTemplate.schema.json index 38d321c..0fe1770 100644 --- a/model_json_schema/ark.InVitroBiospecimenMetadataTemplate.schema.json +++ b/model_json_schema/ark.InVitroBiospecimenMetadataTemplate.schema.json @@ -4,26 +4,12 @@ "title": "ark", "type": "object", "properties": { - "treatment": { - "not": { - "type": "null" - }, - "minLength": 1 - }, - "project": { - "type": "array", - "items": { - "enum": [ - "STAMP", - "V-CoRT", - "AIM for RA", - "ELLIPSS", - "RA", - "LOCKIT", - "SLE" - ] - }, - "maxItems": 7 + "program": { + "enum": [ + "AMP RA/SLE", + "AMP AIM", + "Community Contribution" + ] }, "biospecimenID": { "not": { @@ -32,147 +18,216 @@ "minLength": 1 }, "notes": {}, - "parentBiospecimenID": {}, "altSampleID": {}, - "Component": { - "not": { - "type": "null" - }, - "minLength": 1 - }, "biospecimenType": { "enum": [ - "total leukocytes", - "whole blood", - "saliva", - "synovial tissue", "fibroblast-like synoviocyte", - "serum", "primary cell culture", - "kidney biopsy", - "uvea", - "skin swab", + "suction blister cells", "synovial fluid", "urine", "salivary gland", - "plasma", - "suction blister cells", + "none", + "skin swab", + "saliva", + "serum", "PBMCs", + "stool", + "kidney biopsy", + "total leukocytes", + "whole blood", + "cell line", "skin biopsy", - "none", + "synovial tissue", + "plasma", "suction blister fluid", - "cell line", - "stool" + "uvea" ] }, "individualID": {}, + "parentBiospecimenID": {}, "biospecimenSubtype": { "enum": [ - "nuclei suspension", - "supernatant", - "frozen tissue", - "cell suspension", - "cell or tissue lysate", "FFPE tissue", - "PFA-fixed tissue", "flow-sorted cells", + "cell suspension", + "frozen tissue", "fresh tissue", + "nuclei suspension", + "supernatant", + "PFA-fixed tissue", + "cell or tissue lysate", "" ] }, + "Component": { + "not": { + "type": "null" + }, + "minLength": 1 + }, + "project": { + "type": "array", + "items": { + "enum": [ + "LOCKIT", + "RA", + "ELLIPSS", + "AIM for RA", + "SLE", + "STAMP", + "UMass V-CoRT" + ] + }, + "maxItems": 7 + }, "treatmentTimepoint": {}, - "program": { - "enum": [ - "AMP RA/SLE", - "Community Contribution", - "AMP AIM" - ] + "sampleCollectionBatch": {}, + "treatment": { + "not": { + "type": "null" + }, + "minLength": 1 }, - "salivaCollectionProcedure": { + "visitID": {}, + "primaryCellSource": { "enum": [ - "stimulated", - "unstimulated", + "synovial tissue", + "pannus-derived epidermis", + "PBMCs", + "pannus-derived dermis", + "total leukocytes", + "urine", + "whole blood", + "salivary gland", + "uvea", + "kidney", "" ] }, - "krennLining": {}, - "krennSynovitisScore": {}, - "krennInflammatory": {}, + "cellType": {}, + "cellOntologyID": {}, "anatomicalSite": { "enum": [ - "right 3rd MCP joint", - "right 2nd MTP joint", + "right knee joint", + "left wrist joint", + "left knee joint", "left ankle joint", - "right ankle joint", + "right 2nd MTP joint", + "right wrist joint", + "left hip joint", "unknown", - "left knee joint", - "left wrist joint", + "left 2nd MCP joint", "right 2nd MCP joint", - "right knee joint", - "left hip joint", "other site", - "left 2nd MCP joint", - "right 1st MTP joint", + "right ankle joint", "right hip joint", - "right wrist joint", + "right 3rd MCP joint", + "right 1st MTP joint", "" ] }, - "krennStroma": {}, - "synovialCollectionProcedure": { + "skinSiteStatus": { "enum": [ - "arthroplasty", - "synovectomy", - "unknown", - "biopsy", + "non-lesional", + "lesional", + "healthy control", + "lesional proximal", "" ] }, - "cellType": {}, - "cellOntologyID": {}, - "primaryCellSource": { + "synovialCollectionProcedure": { "enum": [ - "uvea", - "PBMCs", - "total leukocytes", - "whole blood", - "pannus-derived epidermis", - "urine", - "kidney", - "synovial tissue", - "pannus-derived dermis", - "salivary gland", + "synovectomy", + "biopsy", + "unknown", + "arthroplasty", "" ] }, - "skinSiteStatus": { + "salivaCollectionProcedure": { "enum": [ - "lesional", - "non-lesional", - "healthy control", - "lesional proximal", + "stimulated", + "unstimulated", "" ] }, - "userDefinedCellType": {}, + "krennLining": {}, + "krennInflammatory": {}, + "krennSynovitisScore": {}, + "krennStroma": {}, "FACSPopulation": {}, - "visitID": {} + "userDefinedCellType": {} }, "required": [ - "treatment", - "project", + "program", "biospecimenID", - "Component", "biospecimenType", - "program" + "Component", + "project", + "treatment" ], "allOf": [ + { + "if": { + "properties": { + "program": { + "enum": [ + "AMP RA/SLE" + ] + } + }, + "required": [ + "program" + ] + }, + "then": { + "properties": { + "visitID": { + "not": { + "type": "null" + }, + "minLength": 1 + } + }, + "required": [ + "visitID" + ] + } + }, + { + "if": { + "properties": { + "program": { + "enum": [ + "AMP AIM" + ] + } + }, + "required": [ + "program" + ] + }, + "then": { + "properties": { + "visitID": { + "not": { + "type": "null" + }, + "minLength": 1 + } + }, + "required": [ + "visitID" + ] + } + }, { "if": { "properties": { "biospecimenType": { "enum": [ - "saliva" + "primary cell culture" ] } }, @@ -182,15 +237,23 @@ }, "then": { "properties": { - "salivaCollectionProcedure": { + "primaryCellSource": { "enum": [ - "stimulated", - "unstimulated" + "synovial tissue", + "pannus-derived epidermis", + "PBMCs", + "pannus-derived dermis", + "total leukocytes", + "urine", + "whole blood", + "salivary gland", + "uvea", + "kidney" ] } }, "required": [ - "salivaCollectionProcedure" + "primaryCellSource" ] } }, @@ -199,7 +262,7 @@ "properties": { "biospecimenType": { "enum": [ - "synovial tissue" + "primary cell culture" ] } }, @@ -209,10 +272,10 @@ }, "then": { "properties": { - "krennLining": {} + "cellType": {} }, "required": [ - "krennLining" + "cellType" ] } }, @@ -221,7 +284,7 @@ "properties": { "biospecimenType": { "enum": [ - "synovial tissue" + "cell line" ] } }, @@ -231,10 +294,54 @@ }, "then": { "properties": { - "krennSynovitisScore": {} + "cellType": {} }, "required": [ - "krennSynovitisScore" + "cellType" + ] + } + }, + { + "if": { + "properties": { + "biospecimenSubtype": { + "enum": [ + "flow-sorted cells" + ] + } + }, + "required": [ + "biospecimenSubtype" + ] + }, + "then": { + "properties": { + "cellType": {} + }, + "required": [ + "cellType" + ] + } + }, + { + "if": { + "properties": { + "biospecimenSubtype": { + "enum": [ + "cell suspension" + ] + } + }, + "required": [ + "biospecimenSubtype" + ] + }, + "then": { + "properties": { + "cellType": {} + }, + "required": [ + "cellType" ] } }, @@ -243,7 +350,7 @@ "properties": { "biospecimenType": { "enum": [ - "synovial tissue" + "primary cell culture" ] } }, @@ -253,10 +360,10 @@ }, "then": { "properties": { - "krennInflammatory": {} + "cellOntologyID": {} }, "required": [ - "krennInflammatory" + "cellOntologyID" ] } }, @@ -265,7 +372,7 @@ "properties": { "biospecimenType": { "enum": [ - "synovial tissue" + "cell line" ] } }, @@ -275,28 +382,54 @@ }, "then": { "properties": { - "anatomicalSite": { + "cellOntologyID": {} + }, + "required": [ + "cellOntologyID" + ] + } + }, + { + "if": { + "properties": { + "biospecimenSubtype": { "enum": [ - "right 3rd MCP joint", - "right 2nd MTP joint", - "left ankle joint", - "right ankle joint", - "unknown", - "left knee joint", - "left wrist joint", - "right 2nd MCP joint", - "right knee joint", - "left hip joint", - "other site", - "left 2nd MCP joint", - "right 1st MTP joint", - "right hip joint", - "right wrist joint" + "flow-sorted cells" ] } }, "required": [ - "anatomicalSite" + "biospecimenSubtype" + ] + }, + "then": { + "properties": { + "cellOntologyID": {} + }, + "required": [ + "cellOntologyID" + ] + } + }, + { + "if": { + "properties": { + "biospecimenSubtype": { + "enum": [ + "cell suspension" + ] + } + }, + "required": [ + "biospecimenSubtype" + ] + }, + "then": { + "properties": { + "cellOntologyID": {} + }, + "required": [ + "cellOntologyID" ] } }, @@ -305,7 +438,7 @@ "properties": { "biospecimenType": { "enum": [ - "skin swab" + "suction blister cells" ] } }, @@ -317,21 +450,21 @@ "properties": { "anatomicalSite": { "enum": [ - "right 3rd MCP joint", - "right 2nd MTP joint", + "right knee joint", + "left wrist joint", + "left knee joint", "left ankle joint", - "right ankle joint", + "right 2nd MTP joint", + "right wrist joint", + "left hip joint", "unknown", - "left knee joint", - "left wrist joint", + "left 2nd MCP joint", "right 2nd MCP joint", - "right knee joint", - "left hip joint", "other site", - "left 2nd MCP joint", - "right 1st MTP joint", + "right ankle joint", "right hip joint", - "right wrist joint" + "right 3rd MCP joint", + "right 1st MTP joint" ] } }, @@ -357,21 +490,21 @@ "properties": { "anatomicalSite": { "enum": [ - "right 3rd MCP joint", - "right 2nd MTP joint", + "right knee joint", + "left wrist joint", + "left knee joint", "left ankle joint", - "right ankle joint", + "right 2nd MTP joint", + "right wrist joint", + "left hip joint", "unknown", - "left knee joint", - "left wrist joint", + "left 2nd MCP joint", "right 2nd MCP joint", - "right knee joint", - "left hip joint", "other site", - "left 2nd MCP joint", - "right 1st MTP joint", + "right ankle joint", "right hip joint", - "right wrist joint" + "right 3rd MCP joint", + "right 1st MTP joint" ] } }, @@ -385,7 +518,7 @@ "properties": { "biospecimenType": { "enum": [ - "suction blister cells" + "skin swab" ] } }, @@ -397,21 +530,21 @@ "properties": { "anatomicalSite": { "enum": [ - "right 3rd MCP joint", - "right 2nd MTP joint", + "right knee joint", + "left wrist joint", + "left knee joint", "left ankle joint", - "right ankle joint", + "right 2nd MTP joint", + "right wrist joint", + "left hip joint", "unknown", - "left knee joint", - "left wrist joint", + "left 2nd MCP joint", "right 2nd MCP joint", - "right knee joint", - "left hip joint", "other site", - "left 2nd MCP joint", - "right 1st MTP joint", + "right ankle joint", "right hip joint", - "right wrist joint" + "right 3rd MCP joint", + "right 1st MTP joint" ] } }, @@ -437,21 +570,21 @@ "properties": { "anatomicalSite": { "enum": [ - "right 3rd MCP joint", - "right 2nd MTP joint", + "right knee joint", + "left wrist joint", + "left knee joint", "left ankle joint", - "right ankle joint", + "right 2nd MTP joint", + "right wrist joint", + "left hip joint", "unknown", - "left knee joint", - "left wrist joint", + "left 2nd MCP joint", "right 2nd MCP joint", - "right knee joint", - "left hip joint", "other site", - "left 2nd MCP joint", - "right 1st MTP joint", + "right ankle joint", "right hip joint", - "right wrist joint" + "right 3rd MCP joint", + "right 1st MTP joint" ] } }, @@ -463,35 +596,35 @@ { "if": { "properties": { - "biospecimenType": { + "primaryCellSource": { "enum": [ - "suction blister fluid" + "synovial tissue" ] } }, "required": [ - "biospecimenType" + "primaryCellSource" ] }, "then": { "properties": { "anatomicalSite": { "enum": [ - "right 3rd MCP joint", - "right 2nd MTP joint", + "right knee joint", + "left wrist joint", + "left knee joint", "left ankle joint", - "right ankle joint", + "right 2nd MTP joint", + "right wrist joint", + "left hip joint", "unknown", - "left knee joint", - "left wrist joint", + "left 2nd MCP joint", "right 2nd MCP joint", - "right knee joint", - "left hip joint", "other site", - "left 2nd MCP joint", - "right 1st MTP joint", + "right ankle joint", "right hip joint", - "right wrist joint" + "right 3rd MCP joint", + "right 1st MTP joint" ] } }, @@ -503,22 +636,40 @@ { "if": { "properties": { - "biospecimenType": { + "primaryCellSource": { "enum": [ "synovial tissue" ] } }, "required": [ - "biospecimenType" + "primaryCellSource" ] }, "then": { "properties": { - "krennStroma": {} + "anatomicalSite": { + "enum": [ + "right knee joint", + "left wrist joint", + "left knee joint", + "left ankle joint", + "right 2nd MTP joint", + "right wrist joint", + "left hip joint", + "unknown", + "left 2nd MCP joint", + "right 2nd MCP joint", + "other site", + "right ankle joint", + "right hip joint", + "right 3rd MCP joint", + "right 1st MTP joint" + ] + } }, "required": [ - "krennStroma" + "anatomicalSite" ] } }, @@ -527,7 +678,7 @@ "properties": { "biospecimenType": { "enum": [ - "synovial tissue" + "suction blister fluid" ] } }, @@ -537,17 +688,28 @@ }, "then": { "properties": { - "synovialCollectionProcedure": { + "anatomicalSite": { "enum": [ - "arthroplasty", - "synovectomy", + "right knee joint", + "left wrist joint", + "left knee joint", + "left ankle joint", + "right 2nd MTP joint", + "right wrist joint", + "left hip joint", "unknown", - "biopsy" + "left 2nd MCP joint", + "right 2nd MCP joint", + "other site", + "right ankle joint", + "right hip joint", + "right 3rd MCP joint", + "right 1st MTP joint" ] } }, "required": [ - "synovialCollectionProcedure" + "anatomicalSite" ] } }, @@ -556,7 +718,7 @@ "properties": { "biospecimenType": { "enum": [ - "synovial fluid" + "suction blister cells" ] } }, @@ -566,17 +728,17 @@ }, "then": { "properties": { - "synovialCollectionProcedure": { + "skinSiteStatus": { "enum": [ - "arthroplasty", - "synovectomy", - "unknown", - "biopsy" + "non-lesional", + "lesional", + "healthy control", + "lesional proximal" ] } }, "required": [ - "synovialCollectionProcedure" + "skinSiteStatus" ] } }, @@ -585,7 +747,7 @@ "properties": { "biospecimenType": { "enum": [ - "primary cell culture" + "skin swab" ] } }, @@ -595,10 +757,17 @@ }, "then": { "properties": { - "cellType": {} + "skinSiteStatus": { + "enum": [ + "non-lesional", + "lesional", + "healthy control", + "lesional proximal" + ] + } }, "required": [ - "cellType" + "skinSiteStatus" ] } }, @@ -607,7 +776,7 @@ "properties": { "biospecimenType": { "enum": [ - "cell line" + "skin biopsy" ] } }, @@ -617,337 +786,336 @@ }, "then": { "properties": { - "cellType": {} + "skinSiteStatus": { + "enum": [ + "non-lesional", + "lesional", + "healthy control", + "lesional proximal" + ] + } }, "required": [ - "cellType" + "skinSiteStatus" ] } }, { "if": { "properties": { - "biospecimenSubtype": { + "biospecimenType": { "enum": [ - "cell suspension" + "suction blister fluid" ] } }, "required": [ - "biospecimenSubtype" + "biospecimenType" ] }, "then": { "properties": { - "cellType": {} + "skinSiteStatus": { + "enum": [ + "non-lesional", + "lesional", + "healthy control", + "lesional proximal" + ] + } }, "required": [ - "cellType" + "skinSiteStatus" ] } }, { "if": { "properties": { - "biospecimenSubtype": { + "biospecimenType": { "enum": [ - "flow-sorted cells" + "synovial fluid" ] } }, "required": [ - "biospecimenSubtype" + "biospecimenType" ] }, "then": { "properties": { - "cellType": {} + "synovialCollectionProcedure": { + "enum": [ + "synovectomy", + "biopsy", + "unknown", + "arthroplasty" + ] + } }, "required": [ - "cellType" + "synovialCollectionProcedure" ] } }, { "if": { "properties": { - "biospecimenType": { + "primaryCellSource": { "enum": [ - "primary cell culture" + "synovial tissue" ] } }, "required": [ - "biospecimenType" + "primaryCellSource" ] }, "then": { "properties": { - "cellOntologyID": {} + "synovialCollectionProcedure": { + "enum": [ + "synovectomy", + "biopsy", + "unknown", + "arthroplasty" + ] + } }, "required": [ - "cellOntologyID" + "synovialCollectionProcedure" ] } }, { "if": { "properties": { - "biospecimenType": { + "primaryCellSource": { "enum": [ - "cell line" + "synovial tissue" ] } }, "required": [ - "biospecimenType" + "primaryCellSource" ] }, "then": { "properties": { - "cellOntologyID": {} + "synovialCollectionProcedure": { + "enum": [ + "synovectomy", + "biopsy", + "unknown", + "arthroplasty" + ] + } }, "required": [ - "cellOntologyID" + "synovialCollectionProcedure" ] } }, { "if": { "properties": { - "biospecimenSubtype": { + "biospecimenType": { "enum": [ - "cell suspension" + "saliva" ] } }, "required": [ - "biospecimenSubtype" + "biospecimenType" ] }, "then": { "properties": { - "cellOntologyID": {} + "salivaCollectionProcedure": { + "enum": [ + "stimulated", + "unstimulated" + ] + } }, "required": [ - "cellOntologyID" + "salivaCollectionProcedure" ] } }, { "if": { "properties": { - "biospecimenSubtype": { + "primaryCellSource": { "enum": [ - "flow-sorted cells" + "synovial tissue" ] } }, "required": [ - "biospecimenSubtype" + "primaryCellSource" ] }, "then": { "properties": { - "cellOntologyID": {} + "krennLining": {} }, "required": [ - "cellOntologyID" + "krennLining" ] } }, { "if": { "properties": { - "biospecimenType": { + "primaryCellSource": { "enum": [ - "primary cell culture" + "synovial tissue" ] } }, "required": [ - "biospecimenType" + "primaryCellSource" ] }, "then": { "properties": { - "primaryCellSource": { - "enum": [ - "uvea", - "PBMCs", - "total leukocytes", - "whole blood", - "pannus-derived epidermis", - "urine", - "kidney", - "synovial tissue", - "pannus-derived dermis", - "salivary gland" - ] - } + "krennLining": {} }, "required": [ - "primaryCellSource" + "krennLining" ] } }, { "if": { "properties": { - "biospecimenType": { + "primaryCellSource": { "enum": [ - "skin swab" + "synovial tissue" ] } }, "required": [ - "biospecimenType" + "primaryCellSource" ] }, "then": { "properties": { - "skinSiteStatus": { - "enum": [ - "lesional", - "non-lesional", - "healthy control", - "lesional proximal" - ] - } + "krennInflammatory": {} }, "required": [ - "skinSiteStatus" + "krennInflammatory" ] } }, { "if": { "properties": { - "biospecimenType": { + "primaryCellSource": { "enum": [ - "suction blister cells" + "synovial tissue" ] } }, "required": [ - "biospecimenType" + "primaryCellSource" ] }, "then": { "properties": { - "skinSiteStatus": { - "enum": [ - "lesional", - "non-lesional", - "healthy control", - "lesional proximal" - ] - } + "krennInflammatory": {} }, "required": [ - "skinSiteStatus" + "krennInflammatory" ] } }, { "if": { "properties": { - "biospecimenType": { + "primaryCellSource": { "enum": [ - "skin biopsy" + "synovial tissue" ] } }, "required": [ - "biospecimenType" + "primaryCellSource" ] }, "then": { "properties": { - "skinSiteStatus": { - "enum": [ - "lesional", - "non-lesional", - "healthy control", - "lesional proximal" - ] - } + "krennSynovitisScore": {} }, "required": [ - "skinSiteStatus" + "krennSynovitisScore" ] } }, { "if": { "properties": { - "biospecimenType": { + "primaryCellSource": { "enum": [ - "suction blister fluid" + "synovial tissue" ] } }, "required": [ - "biospecimenType" + "primaryCellSource" ] }, "then": { "properties": { - "skinSiteStatus": { - "enum": [ - "lesional", - "non-lesional", - "healthy control", - "lesional proximal" - ] - } + "krennSynovitisScore": {} }, "required": [ - "skinSiteStatus" + "krennSynovitisScore" ] } }, { "if": { "properties": { - "biospecimenSubtype": { + "primaryCellSource": { "enum": [ - "cell suspension" + "synovial tissue" ] } }, "required": [ - "biospecimenSubtype" + "primaryCellSource" ] }, "then": { "properties": { - "userDefinedCellType": {} + "krennStroma": {} }, "required": [ - "userDefinedCellType" + "krennStroma" ] } }, { "if": { "properties": { - "biospecimenSubtype": { + "primaryCellSource": { "enum": [ - "flow-sorted cells" + "synovial tissue" ] } }, "required": [ - "biospecimenSubtype" + "primaryCellSource" ] }, "then": { "properties": { - "userDefinedCellType": {} + "krennStroma": {} }, "required": [ - "userDefinedCellType" + "krennStroma" ] } }, @@ -981,54 +1149,44 @@ { "if": { "properties": { - "program": { + "biospecimenSubtype": { "enum": [ - "AMP RA/SLE" + "flow-sorted cells" ] } }, "required": [ - "program" + "biospecimenSubtype" ] }, "then": { "properties": { - "visitID": { - "not": { - "type": "null" - }, - "minLength": 1 - } + "userDefinedCellType": {} }, "required": [ - "visitID" + "userDefinedCellType" ] } }, { "if": { "properties": { - "program": { + "biospecimenSubtype": { "enum": [ - "AMP AIM" + "cell suspension" ] } }, "required": [ - "program" + "biospecimenSubtype" ] }, "then": { "properties": { - "visitID": { - "not": { - "type": "null" - }, - "minLength": 1 - } + "userDefinedCellType": {} }, "required": [ - "visitID" + "userDefinedCellType" ] } } diff --git a/model_json_schema/ark.OlinkAssayMetadataTemplate.schema.json b/model_json_schema/ark.OlinkAssayMetadataTemplate.schema.json index 7727f0f..735b1cd 100644 --- a/model_json_schema/ark.OlinkAssayMetadataTemplate.schema.json +++ b/model_json_schema/ark.OlinkAssayMetadataTemplate.schema.json @@ -4,61 +4,61 @@ "title": "ark", "type": "object", "properties": { - "assay": { - "enum": [ - "Olink Target 48", - "Olink Flex", - "Olink Focus", - "Olink Explore HT", - "Olink Reveal", - "Olink Target 96" - ] + "targetPanelSynID": { + "not": { + "type": "null" + }, + "minLength": 1 }, - "plateID": { + "targetPanel": { + "not": { + "type": "null" + }, + "minLength": 1 + }, + "Component": { "not": { "type": "null" }, "minLength": 1 }, + "targetPanelSize": {}, "platform": { "type": "array", "items": { "enum": [ - "Illumina NextSeq 500", "Illumina NovaSeq 6000", - "Olink Signature Q100", "Fluidigm BioMark", + "Olink Signature Q100", "unknown", + "Illumina NextSeq 500", "" ] }, "maxItems": 5 }, - "targetPanelSize": {}, - "targetPanelSynID": { - "not": { - "type": "null" - }, - "minLength": 1 - }, - "Component": { + "plateID": { "not": { "type": "null" }, "minLength": 1 }, - "targetPanel": { - "not": { - "type": "null" - }, - "minLength": 1 + "assay": { + "enum": [ + "Olink Flex", + "Olink Target 96", + "Olink Focus", + "Olink Reveal", + "Olink Explore HT", + "Olink Target 48" + ] } }, "required": [ - "assay", - "plateID", "targetPanelSynID", + "targetPanel", "Component", - "targetPanel" + "plateID", + "assay" ] } \ No newline at end of file diff --git a/model_json_schema/ark.OlinkFileAnnotationTemplate.schema.json b/model_json_schema/ark.OlinkFileAnnotationTemplate.schema.json index 3fe37b0..652bfc3 100644 --- a/model_json_schema/ark.OlinkFileAnnotationTemplate.schema.json +++ b/model_json_schema/ark.OlinkFileAnnotationTemplate.schema.json @@ -4,24 +4,61 @@ "title": "ark", "type": "object", "properties": { - "plateID": { - "not": { - "type": "null" - }, - "minLength": 1 + "fileFormat": { + "enum": [ + "csv", + "geojson", + "svs", + "mtx", + "fastq", + "fcs", + "xlsx", + "tgz", + "czi", + "tsv", + "bai", + "bed", + "pdf", + "docx", + "tbi", + "zip", + "erate", + "rds", + "h5", + "vcf", + "parquet", + "xls", + "rec", + "h5ad", + "mcd", + "txt", + "py", + "bam", + "bim", + "dose", + "info", + "fam" + ] }, "specimenModality": { "enum": [ + "unknown", "multispecimen", "single specimen" ] }, + "plateID": { + "not": { + "type": "null" + }, + "minLength": 1 + }, "resourceType": { "enum": [ - "figure", "metadata", "code", - "experimental data" + "experimental data", + "figure" ] }, "Component": { @@ -29,48 +66,13 @@ "type": "null" }, "minLength": 1 - }, - "fileFormat": { - "enum": [ - "fastq", - "fam", - "svs", - "bai", - "vcf", - "czi", - "tgz", - "geojson", - "pdf", - "txt", - "tbi", - "dose", - "mcd", - "zip", - "parquet", - "bam", - "h5ad", - "info", - "rec", - "xls", - "rds", - "bed", - "csv", - "docx", - "mtx", - "fcs", - "h5", - "erate", - "xlsx", - "tsv", - "bim" - ] } }, "required": [ - "plateID", + "fileFormat", "specimenModality", + "plateID", "resourceType", - "Component", - "fileFormat" + "Component" ] } \ No newline at end of file diff --git a/model_json_schema/ark.PublicationMetadataTemplate.schema.json b/model_json_schema/ark.PublicationMetadataTemplate.schema.json index e23d228..8e29be2 100644 --- a/model_json_schema/ark.PublicationMetadataTemplate.schema.json +++ b/model_json_schema/ark.PublicationMetadataTemplate.schema.json @@ -4,54 +4,33 @@ "title": "ark", "type": "object", "properties": { - "program": { - "enum": [ - "AMP RA/SLE", - "AMP AIM", - "Community Contribution" - ] - }, - "associatedDataset": {}, - "title": { + "PMID": { "not": { "type": "null" }, "minLength": 1 }, - "project": { - "type": "array", - "items": { - "enum": [ - "RA", - "V-CoRT", - "AIM for RA", - "ELLIPSS", - "LOCKIT", - "SLE", - "STAMP" - ] - }, - "maxItems": 7 - }, - "publicationDate": { + "associatedDataset": {}, + "Component": { "not": { "type": "null" }, "minLength": 1 }, - "journal": { + "publicationDate": { "not": { "type": "null" }, "minLength": 1 }, - "Component": { - "not": { - "type": "null" - }, - "minLength": 1 + "publicationType": { + "enum": [ + "correction", + "pre-print", + "peer-reviewed" + ] }, - "year": { + "title": { "not": { "type": "null" }, @@ -64,25 +43,46 @@ "minLength": 1 }, "PMCID": {}, - "PMID": { + "year": { "not": { "type": "null" }, "minLength": 1 }, - "publicationType": { + "program": { "enum": [ - "pre-print", - "correction", - "peer-reviewed" + "AMP AIM", + "Community Contribution", + "AMP RA/SLE" ] }, + "journal": { + "not": { + "type": "null" + }, + "minLength": 1 + }, + "project": { + "type": "array", + "items": { + "enum": [ + "ELLIPSS", + "SLE", + "LOCKIT", + "STAMP", + "RA", + "AIM for RA", + "UMass V-CoRT" + ] + }, + "maxItems": 7 + }, "programPhase": { "type": "array", "items": { "enum": [ - "II", "I", + "II", "" ] }, @@ -90,16 +90,16 @@ } }, "required": [ - "program", - "title", - "project", - "publicationDate", - "journal", + "PMID", "Component", - "year", + "publicationDate", + "publicationType", + "title", "DOI", - "PMID", - "publicationType" + "year", + "program", + "journal", + "project" ], "allOf": [ { @@ -121,8 +121,8 @@ "type": "array", "items": { "enum": [ - "II", - "I" + "I", + "II" ] }, "maxItems": 2 diff --git a/model_json_schema/ark.ScRNASeqAssayMetadataTemplate.schema.json b/model_json_schema/ark.ScRNASeqAssayMetadataTemplate.schema.json index b95f558..0477933 100644 --- a/model_json_schema/ark.ScRNASeqAssayMetadataTemplate.schema.json +++ b/model_json_schema/ark.ScRNASeqAssayMetadataTemplate.schema.json @@ -4,181 +4,226 @@ "title": "ark", "type": "object", "properties": { - "specimenModality": { + "alignmentReference": { "enum": [ - "multispecimen", - "single specimen" + "modified GRCh38", + "unknown", + "GRCh38", + "10x Cell Ranger Human GRCh38 2020-A", + "vdj_GRCh38_alts_ensembl-4.0.0", + "10x Cell Ranger Human GRCh38 2024-A" ] }, - "totalReads": { - "not": { - "type": "null" - }, - "minLength": 1 - }, - "nucleicAcidSource": { + "sampleProcessingBatch": {}, + "dataCollectionBatch": {}, + "assay": { "type": "array", "items": { "enum": [ - "TCR mRNA", - "surface protein feature barcode", - "CRISPR protospacer feature barcode", - "poly(A) RNA", - "rRNA-depleted RNA", - "multiplexing oligo", - "globin-depleted RNA", - "Tn5-accessible gDNA", - "antigen capture barcode", - "BCR mRNA", - "intracellular protein feature barcode", - "gDNA" + "Olink Reveal", + "Olink Flex", + "snRNASeq", + "Olink Explore HT", + "CyTOF", + "CE-MS", + "WES", + "Xenium", + "feature barcode sequencing", + "flow cytometry", + "RNASeq", + "WGS", + "SomaScan", + "kiloplex", + "GenePS SeqFISH", + "snATACSeq", + "VDJSeq", + "Olink Target 48", + "Olink Focus", + "NULISA", + "SNP array", + "imaging mass spectrometry", + "scRNASeq", + "Olink Target 96", + "H&E", + "LC-MS/MS", + "imaging mass cytometry", + "CosMX", + "multiplexed ELISA", + "serial IHC", + "scVDJSeq", + "CITESeq", + "ASAPSeq", + "Visium" ] }, - "maxItems": 12 + "maxItems": 34 }, - "alignmentReference": { + "inputCellCount": { + "not": { + "type": "null" + }, + "minLength": 1 + }, + "libraryPrepMethod": { "enum": [ - "vdj_GRCh38_alts_ensembl-4.0.0", - "unknown", - "10x Cell Ranger Human GRCh38 2024-A", - "10x Cell Ranger Human GRCh38 2020-A", - "modified GRCh38" + "10x Chromium GEM-X Single Cell 3' v4", + "Nextera XT", + "10x Chromium Next GEM Single Cell 5' v1.1", + "Nextera XT DNA", + "in-house library prep", + "SMART-Seq Human TCR with UMI", + "10x GEM-X Flex Gene Expression Human", + "SMARTer Stranded Total RNA v2", + "10x Chromium Next GEM Single Cell 5' v2", + "10x Chromium Single Cell Human TCR", + "Takara Human BCR profiling for Illumina", + "SMART-Seq Human BCR with UMI", + "TruSeq Stranded mRNA", + "NEBNext Ultra II Directional RNA Library", + "10x Chromium Next GEM Single Cell 3'", + "Fluidigm C1 HT", + "Takara Human TCRv2 profiling for Illumina", + "10x Chromium Next GEM Single Cell 3' 3.1", + "Takara Human scTCR profiling for Illumina", + "custom DASH-treatment", + "10x Chromium Fixed RNA Human Transcriptome", + "QIAseq miRNA Library", + "10x Chromium Single Cell Human BCR", + "CEL-Seq2", + "10x GEM-X Universal 5' Gene Expression v3", + "10x Chromium GEM-X Single Cell 5' v3", + "SMART-Seq v4 Ultra Low Input RNA", + "Chromium Next GEM Single Cell ATAC v1.1", + "10x Chromium Next GEM Single Cell ATAC v2", + "Takara Human TCR profiling for Illumina", + "NEBNext Human Immune Sequencing Kit" ] }, + "totalReads": { + "not": { + "type": "null" + }, + "minLength": 1 + }, + "sequencingSaturation": {}, "softwareAndVersion": { "enum": [ - "Cell Ranger v7.1.0", - "Cell Ranger v8.0.0", - "Space Ranger 3.1.2", + "Cell Ranger v3.1.0", "Space Ranger 3.0.1", + "Space Ranger 3.1.2", + "demuxlet", + "Cell Ranger v6.0.1", "Cell Ranger v7.0.1", - "Cell Ranger v8.0.1", - "Space Ranger 3.1.3", - "Cell Ranger v3.0.0", + "Cell Ranger ATAC v1.1.0", + "Cell Ranger v6.0.0", + "Cell Ranger v8.0.0", "Cell Ranger v3.0.1", - "Cell Ranger v4.0.0", "Cell Ranger v5.0.0", + "BD FACSDiva 8.0.1", + "Cell Ranger v3.0.2", + "Cell Ranger v9.0.0", + "Cell Ranger v4.0.0", + "Space Ranger 3.0.0", "Cell Ranger v6.1.0", + "Space Ranger 3.1.3", "Cell Ranger v5.0.1", - "Cell Ranger v6.0.0", - "Space Ranger 3.1.0", - "Cell Ranger v9.0.0", - "Cell Ranger v6.1.2", + "Cell Ranger v7.2.0", "Cell Ranger v6.0.2", - "Cell Ranger v3.0.2", - "Cell Ranger v3.1.0", + "Cell Ranger v3.0.0", + "Cell Ranger v7.0.0", + "Cell Ranger v7.1.0", + "Cell Ranger v6.1.2", "Cell Ranger 9.0.1", - "Cell Ranger ATAC v1.1.0", - "Cell Ranger v7.2.0", + "Cell Ranger v8.0.1", + "Space Ranger 3.1.0", "Space Ranger 3.1.1", - "BD FACSDiva 8.0.1", - "Cell Ranger v6.0.1", - "demuxlet", "Cell Ranger v6.1.1", - "Space Ranger 3.0.0", - "Cell Ranger v7.0.0", "" ] }, + "specimenModality": { + "enum": [ + "unknown", + "single specimen", + "multispecimen" + ] + }, "Component": { "not": { "type": "null" }, "minLength": 1 }, - "libraryPrepMethod": { - "enum": [ - "10x Chromium Single Cell Human BCR", - "10x Chromium Next GEM Single Cell 5' v2", - "10x Chromium Fixed RNA Human Transcriptome", - "10x GEM-X Universal 5? Gene Expression v3", - "in-house library prep", - "10x Chromium Next GEM Single Cell 3'", - "Chromium Next GEM Single Cell ATAC v1.1", - "TruSeq Stranded mRNA", - "SMART-Seq Human TCR with UMI", - "Nextera XT DNA", - "custom DASH-treatment", - "SMARTer Stranded Total RNA v2", - "QIAseq miRNA Library", - "10x Chromium GEM-X Single Cell 5' v3", - "10x Chromium Single Cell Human TCR", - "SMART-Seq Human BCR with UMI", - "Takara Human TCRv2 profiling for Illumina", - "SMART-Seq v4 Ultra Low Input RNA", - "10x Chromium Next GEM Single Cell 3' 3.1", - "Takara Human scTCR profiling for Illumina", - "NEBNext Human Immune Sequencing Kit", - "Fluidigm C1 HT", - "Nextera XT", - "10x GEM-X Flex Gene Expression Human", - "10x Chromium Next GEM Single Cell ATAC v2", - "NEBNext Ultra II Directional RNA Library", - "CEL-Seq2", - "Takara Human BCR profiling for Illumina", - "Takara Human TCR profiling for Illumina", - "10x Chromium GEM-X Single Cell 3' v4", - "10x Chromium Next GEM Single Cell 5' v1.1" - ] - }, - "sampleProcessingBatch": {}, - "dataCollectionBatch": {}, "platform": { "type": "array", "items": { "enum": [ - "Helios Mass Cytometer", - "Chromium Next GEM Chip K", - "Chromium GEM-X Single Cell 3' Chip v4", - "Visium CytAssist", + "Thermo Fisher Attune NxT", + "BD FACSLyric Clinical", + "BD FACSAria III", + "BD FACSCanto II", + "Chromium Controller", + "Thermo Fisher Attune Xenith", + "Chromium X", + "Cytek Aurora Evo", + "Illumina NovaSeq 6000", + "Xenium", "BD FACSymphony S6", - "GEM-X OCM 5' Chip", "Sony MA900", - "unknown", - "Chromium Controller", + "Helios Mass Cytometer", + "Thermo Fisher Attune CytPix", + "Illumina NovaSeq X", + "BD FACSMelody", + "CyTOF XT", + "Chromium GEM-X Single Cell 3' Chip v4", "Chromium Xo", - "Cytek Aurora", "Chromium Next GEM Chip G", - "Hyperion", - "Illumina HiSeq X Ten", + "Illumina HiSeq 2500", "Chromium Next GEM Chip Q", - "Cytek Aurora Evo", - "BD FACSDiscover S8", - "Chromium Next GEM Chip M", + "Cytek Aurora", + "Illumina NextSeq 500", + "unknown", + "Chromium Next GEM Chip K", + "Fluidigm BioMark", + "BD FACSCanto", "BD FACSDiscover A8", - "GEM-X Flex Gene Expression Chip", - "BD FACSCanto II", - "none", "Chromium iX", - "Illumina NextSeq 500", - "Illumina NovaSeq X", - "Illumina NovaSeq 6000", - "Not Applicable", - "Thermo Fisher Attune CytPix", - "BD FACSAria Fusion cell sorter", - "BD FACSMelody", - "BD FACSAria III", - "Thermo Fisher Attune NxT", + "Illumina HiSeq X Ten", "Olink Signature Q100", + "none", "Chromium Next GEM Chip H", - "BD FACSCanto", - "Illumina HiSeq 2500", - "CyTOF XT", - "Thermo Fisher Attune Xenith", - "Chromium X", - "BD FACSLyric Clinical", - "Fluidigm BioMark", - "BD LSRFortessa", - "Xenium" + "Chromium Next GEM Chip M", + "GEM-X Flex Gene Expression Chip", + "BD FACSDiscover S8", + "Visium CytAssist", + "Not Applicable", + "GEM-X OCM 5' Chip", + "BD FACSAria Fusion cell sorter", + "Hyperion", + "BD LSRFortessa" ] }, "maxItems": 43 }, - "inputCellCount": { - "not": { - "type": "null" + "nucleicAcidSource": { + "type": "array", + "items": { + "enum": [ + "poly(A) RNA", + "CRISPR protospacer feature barcode", + "gDNA", + "TCR mRNA", + "multiplexing oligo", + "BCR mRNA", + "globin-depleted RNA", + "intracellular protein feature barcode", + "surface protein feature barcode", + "Tn5-accessible gDNA", + "rRNA-depleted RNA", + "antigen capture barcode" + ] }, - "minLength": 1 + "maxItems": 12 }, "percentCellViability": { "not": { @@ -186,99 +231,59 @@ }, "minLength": 1 }, - "assay": { - "type": "array", - "items": { - "enum": [ - "scRNASeq", - "NULISA", - "Olink Reveal", - "VDJSeq", - "WGS", - "Olink Focus", - "Visium", - "GenePS SeqFISH", - "RNASeq", - "Olink Explore HT", - "snRNASeq", - "imaging mass spectrometry", - "SNP array", - "CosMX", - "flow cytometry", - "Olink Target 96", - "H&E", - "SomaScan", - "feature barcode sequencing", - "CITESeq", - "LC-MS/MS", - "CyTOF", - "ASAPSeq", - "WES", - "scVDJSeq", - "serial IHC", - "snATACSeq", - "Olink Flex", - "kiloplex", - "Olink Target 48", - "imaging mass cytometry", - "multiplexed ELISA", - "Xenium", - "CE-MS" - ] - }, - "maxItems": 34 - }, - "sequencingSaturation": {}, - "libraryID": {}, - "biospecimenID": {}, "10xProbeSetReference": { "enum": [ - "custom probe set", "Flex Human Transcriptome Probe Set v1.1.0", - "Visium Human Transcriptome v2", - "Visium Human Transcriptome v1", "Flex Human Transcriptome Probe Set v1.0.1", + "custom probe set", + "Visium Human Transcriptome v1", + "Visium Human Transcriptome v2", "" ] - } + }, + "biospecimenID": {}, + "libraryID": {} }, "required": [ - "specimenModality", - "totalReads", - "nucleicAcidSource", "alignmentReference", - "Component", + "assay", + "inputCellCount", "libraryPrepMethod", + "totalReads", + "specimenModality", + "Component", "platform", - "inputCellCount", - "percentCellViability", - "assay" + "nucleicAcidSource", + "percentCellViability" ], "allOf": [ { "if": { "properties": { - "specimenModality": { + "libraryPrepMethod": { "enum": [ - "multispecimen" + "10x GEM-X Flex Gene Expression Human" ] } }, "required": [ - "specimenModality" + "libraryPrepMethod" ] }, "then": { "properties": { - "libraryID": { - "not": { - "type": "null" - }, - "minLength": 1 + "10xProbeSetReference": { + "enum": [ + "Flex Human Transcriptome Probe Set v1.1.0", + "Flex Human Transcriptome Probe Set v1.0.1", + "custom probe set", + "Visium Human Transcriptome v1", + "Visium Human Transcriptome v2" + ] } }, "required": [ - "libraryID" + "10xProbeSetReference" ] } }, @@ -312,30 +317,27 @@ { "if": { "properties": { - "libraryPrepMethod": { + "specimenModality": { "enum": [ - "10x GEM-X Flex Gene Expression Human" + "multispecimen" ] } }, "required": [ - "libraryPrepMethod" + "specimenModality" ] }, "then": { "properties": { - "10xProbeSetReference": { - "enum": [ - "custom probe set", - "Flex Human Transcriptome Probe Set v1.1.0", - "Visium Human Transcriptome v2", - "Visium Human Transcriptome v1", - "Flex Human Transcriptome Probe Set v1.0.1" - ] + "libraryID": { + "not": { + "type": "null" + }, + "minLength": 1 } }, "required": [ - "10xProbeSetReference" + "libraryID" ] } } diff --git a/model_json_schema/ark.ScRNASeqProcessedDataAnnotationTemplate.schema.json b/model_json_schema/ark.ScRNASeqProcessedDataAnnotationTemplate.schema.json index c2b1c04..c50476a 100644 --- a/model_json_schema/ark.ScRNASeqProcessedDataAnnotationTemplate.schema.json +++ b/model_json_schema/ark.ScRNASeqProcessedDataAnnotationTemplate.schema.json @@ -4,55 +4,85 @@ "title": "ark", "type": "object", "properties": { + "resourceType": { + "type": "array", + "items": { + "enum": [ + "metadata", + "experimental data" + ] + }, + "maxItems": 2 + }, "assay": { "type": "array", "items": { "enum": [ - "CITESeq", - "Olink Focus", "NULISA", - "Xenium", - "imaging mass spectrometry", + "Olink Target 96", + "serial IHC", + "scRNASeq", + "imaging mass cytometry", "Olink Target 48", - "snATACSeq", - "CosMX", + "Olink Focus", + "CyTOF", + "ASAPSeq", + "Olink Flex", + "H&E", "flow cytometry", - "Visium", + "SomaScan", + "CosMX", + "Xenium", + "kiloplex", + "CITESeq", "VDJSeq", - "serial IHC", - "multiplexed ELISA", - "WES", - "CyTOF", - "RNASeq", "Olink Reveal", - "Olink Flex", "Olink Explore HT", - "SomaScan", - "ASAPSeq", "SNP array", - "CE-MS", - "GenePS SeqFISH", - "kiloplex", - "scRNASeq", + "feature barcode sequencing", "LC-MS/MS", - "H&E", - "imaging mass cytometry", - "snRNASeq", - "Olink Target 96", - "WGS", + "Visium", + "CE-MS", + "imaging mass spectrometry", + "WES", "scVDJSeq", - "feature barcode sequencing" + "multiplexed ELISA", + "snATACSeq", + "snRNASeq", + "RNASeq", + "GenePS SeqFISH", + "WGS" ] }, "maxItems": 34 }, + "fileFormat": { + "enum": [ + "bai", + "fam", + "bim", + "bam", + "mtx", + "tgz", + "xlsx", + "xls", + "txt", + "bed", + "h5", + "tsv", + "csv", + "h5ad", + "Rds", + "zip" + ] + }, "dataLevel": { "enum": [ "1", - "3", - "4", "2", - "5" + "5", + "3", + "4" ] }, "Component": { @@ -63,54 +93,22 @@ }, "cellRangerOutput": { "enum": [ + "raw MEX", "filtered_peak_bc_matrix", - "filtered MEX", - "raw_peak_bc_matrix", "filtered_feature_bc_matrix", - "raw_feature_bc_matrix", "Not Applicable", - "raw MEX" - ] - }, - "resourceType": { - "type": "array", - "items": { - "enum": [ - "metadata", - "experimental data" - ] - }, - "maxItems": 2 - }, - "fileFormat": { - "enum": [ - "bed", - "h5ad", - "zip", - "tsv", - "bam", - "txt", - "h5", - "xlsx", - "Rds", - "fam", - "mtx", - "bim", - "bai", - "tgz", - "csv", - "xls" + "raw_feature_bc_matrix", + "raw_peak_bc_matrix", + "filtered MEX" ] }, "specimenModality": { "enum": [ + "multispecimen", "single specimen", - "multispecimen" + "unknown" ] }, - "targetPanelSynID": {}, - "targetPanelSize": {}, - "targetPanel": {}, "metadataType": { "enum": [ "single-cell metadata", @@ -122,25 +120,28 @@ "items": { "enum": [ "differential expression results", - "gene counts", "epigenomic peaks", + "gene counts", "barcode counts", "" ] }, "maxItems": 4 }, + "targetPanelSize": {}, + "targetPanelSynID": {}, + "targetPanel": {}, "RObjectClass": { "enum": [ "Symphony reference", - "sparse matrix", - "SummarizedExperiment", + "vector", "data.frame", + "sparse matrix", + "ROCR prediction.object", + "list", "matrix", - "vector", + "SummarizedExperiment", "Seurat object", - "list", - "ROCR prediction.object", "" ] }, @@ -148,61 +149,72 @@ "biospecimenID": {} }, "required": [ + "resourceType", "assay", + "fileFormat", "dataLevel", "Component", "cellRangerOutput", - "resourceType", - "fileFormat", "specimenModality" ], "allOf": [ { "if": { "properties": { - "assay": { + "resourceType": { "enum": [ - "feature barcode sequencing" + "metadata" ] } }, "required": [ - "assay" + "resourceType" ] }, "then": { "properties": { - "targetPanelSynID": { - "not": { - "type": "null" - }, - "minLength": 1 + "metadataType": { + "enum": [ + "single-cell metadata" + ] } }, "required": [ - "targetPanelSynID" + "metadataType" ] } }, { "if": { "properties": { - "assay": { + "resourceType": { "enum": [ - "feature barcode sequencing" + "experimental data" ] } }, "required": [ - "assay" + "resourceType" ] }, "then": { "properties": { - "targetPanelSize": {} + "processedDataType": { + "type": "array", + "items": { + "enum": [ + "differential expression results", + "epigenomic peaks", + "gene counts", + "barcode counts", + "" + ] + }, + "maxItems": 4 + } }, "required": [ - "targetPanelSize" + "processedDataType" ] } }, @@ -221,75 +233,64 @@ }, "then": { "properties": { - "targetPanel": { - "not": { - "type": "null" - }, - "minLength": 1 - } + "targetPanelSize": {} }, "required": [ - "targetPanel" + "targetPanelSize" ] } }, { "if": { "properties": { - "resourceType": { + "assay": { "enum": [ - "metadata" + "feature barcode sequencing" ] } }, "required": [ - "resourceType" + "assay" ] }, "then": { "properties": { - "metadataType": { - "enum": [ - "single-cell metadata" - ] + "targetPanelSynID": { + "not": { + "type": "null" + }, + "minLength": 1 } }, "required": [ - "metadataType" + "targetPanelSynID" ] } }, { "if": { "properties": { - "resourceType": { + "assay": { "enum": [ - "experimental data" + "feature barcode sequencing" ] } }, "required": [ - "resourceType" + "assay" ] }, "then": { "properties": { - "processedDataType": { - "type": "array", - "items": { - "enum": [ - "differential expression results", - "gene counts", - "epigenomic peaks", - "barcode counts", - "" - ] + "targetPanel": { + "not": { + "type": "null" }, - "maxItems": 4 + "minLength": 1 } }, "required": [ - "processedDataType" + "targetPanel" ] } }, @@ -311,14 +312,14 @@ "RObjectClass": { "enum": [ "Symphony reference", - "sparse matrix", - "SummarizedExperiment", + "vector", "data.frame", + "sparse matrix", + "ROCR prediction.object", + "list", "matrix", - "vector", + "SummarizedExperiment", "Seurat object", - "list", - "ROCR prediction.object", "" ] } diff --git a/model_json_schema/ark.ScVDJSeqProcessedDataAnnotationTemplate.schema.json b/model_json_schema/ark.ScVDJSeqProcessedDataAnnotationTemplate.schema.json index c8c3aee..f7083bd 100644 --- a/model_json_schema/ark.ScVDJSeqProcessedDataAnnotationTemplate.schema.json +++ b/model_json_schema/ark.ScVDJSeqProcessedDataAnnotationTemplate.schema.json @@ -4,23 +4,13 @@ "title": "ark", "type": "object", "properties": { - "resourceType": { - "type": "array", - "items": { - "enum": [ - "experimental data", - "metadata" - ] - }, - "maxItems": 2 - }, "dataLevel": { "enum": [ - "4", - "1", "2", "5", - "3" + "4", + "3", + "1" ] }, "Component": { @@ -32,179 +22,130 @@ "specimenModality": { "enum": [ "multispecimen", + "unknown", "single specimen" ] }, "fileFormat": { "enum": [ - "xls", - "h5", - "tgz", - "Rds", - "zip", - "txt", - "bed", - "bai", - "bim", "h5ad", "tsv", - "mtx", + "bai", + "zip", "bam", - "csv", "fam", - "xlsx" + "bim", + "mtx", + "Rds", + "h5", + "xlsx", + "xls", + "tgz", + "txt", + "bed", + "csv" ] }, "assay": { "type": "array", "items": { "enum": [ - "H&E", - "multiplexed ELISA", + "NULISA", + "SNP array", + "snRNASeq", + "snATACSeq", + "imaging mass spectrometry", + "scRNASeq", + "kiloplex", + "Olink Target 48", + "Visium", + "Olink Focus", + "imaging mass cytometry", + "serial IHC", + "RNASeq", + "Xenium", + "WES", "flow cytometry", + "Olink Flex", "CITESeq", - "imaging mass cytometry", - "CyTOF", - "scRNASeq", - "snRNASeq", - "NULISA", + "GenePS SeqFISH", + "H&E", + "Olink Explore HT", "Olink Reveal", - "ASAPSeq", + "feature barcode sequencing", "scVDJSeq", - "Olink Explore HT", - "Visium", - "snATACSeq", - "GenePS SeqFISH", "CosMX", - "VDJSeq", + "LC-MS/MS", "CE-MS", + "Olink Target 96", + "VDJSeq", + "ASAPSeq", + "multiplexed ELISA", "SomaScan", "WGS", - "RNASeq", - "Olink Target 96", - "WES", - "LC-MS/MS", - "SNP array", - "kiloplex", - "imaging mass spectrometry", - "Xenium", - "Olink Flex", - "Olink Target 48", - "feature barcode sequencing", - "serial IHC", - "Olink Focus" + "CyTOF" ] }, "maxItems": 34 }, - "processedDataType": { + "resourceType": { "type": "array", "items": { "enum": [ - "epigenomic peaks", - "gene counts", - "barcode counts", - "differential expression results", - "" + "metadata", + "experimental data" ] }, - "maxItems": 4 - }, - "metadataType": { - "enum": [ - "single-cell metadata", - "" - ] + "maxItems": 2 }, "biospecimenID": {}, "individualID": {}, "RObjectClass": { "enum": [ + "vector", "ROCR prediction.object", - "data.frame", + "SummarizedExperiment", + "matrix", + "Symphony reference", "sparse matrix", "list", + "data.frame", "Seurat object", - "Symphony reference", - "SummarizedExperiment", - "vector", - "matrix", "" ] }, - "targetPanelSynID": {}, "targetPanelSize": {}, - "targetPanel": {} + "targetPanelSynID": {}, + "targetPanel": {}, + "metadataType": { + "enum": [ + "single-cell metadata", + "" + ] + }, + "processedDataType": { + "type": "array", + "items": { + "enum": [ + "barcode counts", + "gene counts", + "differential expression results", + "epigenomic peaks", + "" + ] + }, + "maxItems": 4 + } }, "required": [ - "resourceType", "dataLevel", "Component", "specimenModality", "fileFormat", - "assay" + "assay", + "resourceType" ], "allOf": [ - { - "if": { - "properties": { - "resourceType": { - "enum": [ - "experimental data" - ] - } - }, - "required": [ - "resourceType" - ] - }, - "then": { - "properties": { - "processedDataType": { - "type": "array", - "items": { - "enum": [ - "epigenomic peaks", - "gene counts", - "barcode counts", - "differential expression results", - "" - ] - }, - "maxItems": 4 - } - }, - "required": [ - "processedDataType" - ] - } - }, - { - "if": { - "properties": { - "resourceType": { - "enum": [ - "metadata" - ] - } - }, - "required": [ - "resourceType" - ] - }, - "then": { - "properties": { - "metadataType": { - "enum": [ - "single-cell metadata" - ] - } - }, - "required": [ - "metadataType" - ] - } - }, { "if": { "properties": { @@ -276,15 +217,15 @@ "properties": { "RObjectClass": { "enum": [ + "vector", "ROCR prediction.object", - "data.frame", + "SummarizedExperiment", + "matrix", + "Symphony reference", "sparse matrix", "list", + "data.frame", "Seurat object", - "Symphony reference", - "SummarizedExperiment", - "vector", - "matrix", "" ] } @@ -309,15 +250,10 @@ }, "then": { "properties": { - "targetPanelSynID": { - "not": { - "type": "null" - }, - "minLength": 1 - } + "targetPanelSize": {} }, "required": [ - "targetPanelSynID" + "targetPanelSize" ] } }, @@ -336,10 +272,15 @@ }, "then": { "properties": { - "targetPanelSize": {} + "targetPanelSynID": { + "not": { + "type": "null" + }, + "minLength": 1 + } }, "required": [ - "targetPanelSize" + "targetPanelSynID" ] } }, @@ -369,6 +310,66 @@ "targetPanel" ] } + }, + { + "if": { + "properties": { + "resourceType": { + "enum": [ + "metadata" + ] + } + }, + "required": [ + "resourceType" + ] + }, + "then": { + "properties": { + "metadataType": { + "enum": [ + "single-cell metadata" + ] + } + }, + "required": [ + "metadataType" + ] + } + }, + { + "if": { + "properties": { + "resourceType": { + "enum": [ + "experimental data" + ] + } + }, + "required": [ + "resourceType" + ] + }, + "then": { + "properties": { + "processedDataType": { + "type": "array", + "items": { + "enum": [ + "barcode counts", + "gene counts", + "differential expression results", + "epigenomic peaks", + "" + ] + }, + "maxItems": 4 + } + }, + "required": [ + "processedDataType" + ] + } } ] } \ No newline at end of file diff --git a/model_json_schema/ark.SnATAC-seqAssayMetadataTemplate.schema.json b/model_json_schema/ark.SnATAC-seqAssayMetadataTemplate.schema.json index cca6191..857ff39 100644 --- a/model_json_schema/ark.SnATAC-seqAssayMetadataTemplate.schema.json +++ b/model_json_schema/ark.SnATAC-seqAssayMetadataTemplate.schema.json @@ -4,165 +4,128 @@ "title": "ark", "type": "object", "properties": { - "softwareAndVersion": { - "enum": [ - "Cell Ranger v3.0.2", - "BD FACSDiva 8.0.1", - "Cell Ranger v7.0.0", - "Cell Ranger v3.0.0", - "Cell Ranger v6.0.0", - "Cell Ranger v5.0.1", - "Cell Ranger v7.0.1", - "Cell Ranger v7.2.0", - "Space Ranger 3.1.1", - "demuxlet", - "Space Ranger 3.1.2", - "Cell Ranger 9.0.1", - "Cell Ranger v6.0.2", - "Cell Ranger v6.1.1", - "Space Ranger 3.0.1", - "Cell Ranger v4.0.0", - "Space Ranger 3.1.0", - "Space Ranger 3.1.3", - "Cell Ranger v8.0.1", - "Cell Ranger v3.0.1", - "Cell Ranger v5.0.0", - "Cell Ranger v6.1.2", - "Cell Ranger v9.0.0", - "Cell Ranger ATAC v1.1.0", - "Cell Ranger v3.1.0", - "Cell Ranger v7.1.0", - "Cell Ranger v6.0.1", - "Cell Ranger v8.0.0", - "Cell Ranger v6.1.0", - "Space Ranger 3.0.0", - "" - ] - }, - "Component": { - "not": { - "type": "null" + "assay": { + "type": "array", + "items": { + "enum": [ + "kiloplex", + "flow cytometry", + "RNASeq", + "GenePS SeqFISH", + "Olink Target 48", + "SNP array", + "Olink Flex", + "LC-MS/MS", + "CosMX", + "serial IHC", + "snRNASeq", + "imaging mass spectrometry", + "feature barcode sequencing", + "Olink Explore HT", + "H&E", + "Visium", + "WGS", + "scVDJSeq", + "Olink Target 96", + "NULISA", + "CE-MS", + "CITESeq", + "ASAPSeq", + "SomaScan", + "CyTOF", + "Olink Reveal", + "multiplexed ELISA", + "Xenium", + "Olink Focus", + "imaging mass cytometry", + "WES", + "scRNASeq", + "snATACSeq", + "VDJSeq" + ] }, - "minLength": 1 + "maxItems": 34 }, "nucleicAcidSource": { "type": "array", "items": { "enum": [ - "multiplexing oligo", - "BCR mRNA", - "TCR mRNA", - "surface protein feature barcode", + "CRISPR protospacer feature barcode", "globin-depleted RNA", - "rRNA-depleted RNA", + "Tn5-accessible gDNA", "intracellular protein feature barcode", + "BCR mRNA", "poly(A) RNA", - "Tn5-accessible gDNA", - "antigen capture barcode", + "surface protein feature barcode", "gDNA", - "CRISPR protospacer feature barcode" + "rRNA-depleted RNA", + "multiplexing oligo", + "TCR mRNA", + "antigen capture barcode" ] }, "maxItems": 12 }, - "totalReads": { - "not": { - "type": "null" - }, - "minLength": 1 - }, - "percentCellViability": { - "not": { - "type": "null" - }, - "minLength": 1 - }, "specimenModality": { "enum": [ "multispecimen", + "unknown", "single specimen" ] }, - "libraryPrepMethod": { + "dataCollectionBatch": {}, + "softwareAndVersion": { "enum": [ - "CEL-Seq2", - "Takara Human scTCR profiling for Illumina", - "NEBNext Human Immune Sequencing Kit", - "10x Chromium GEM-X Single Cell 3' v4", - "custom DASH-treatment", - "Takara Human BCR profiling for Illumina", - "SMART-Seq Human BCR with UMI", - "NEBNext Ultra II Directional RNA Library", - "SMART-Seq v4 Ultra Low Input RNA", - "SMART-Seq Human TCR with UMI", - "SMARTer Stranded Total RNA v2", - "10x Chromium Next GEM Single Cell 3'", - "10x Chromium Fixed RNA Human Transcriptome", - "10x Chromium Next GEM Single Cell 3' 3.1", - "Nextera XT DNA", - "10x Chromium GEM-X Single Cell 5' v3", - "10x Chromium Next GEM Single Cell 5' v1.1", - "10x GEM-X Flex Gene Expression Human", - "10x GEM-X Universal 5? Gene Expression v3", - "Fluidigm C1 HT", - "QIAseq miRNA Library", - "10x Chromium Single Cell Human BCR", - "10x Chromium Next GEM Single Cell 5' v2", - "Takara Human TCR profiling for Illumina", - "TruSeq Stranded mRNA", - "Nextera XT", - "10x Chromium Single Cell Human TCR", - "Chromium Next GEM Single Cell ATAC v1.1", - "10x Chromium Next GEM Single Cell ATAC v2", - "Takara Human TCRv2 profiling for Illumina", - "in-house library prep" + "Cell Ranger v8.0.0", + "Cell Ranger 9.0.1", + "Cell Ranger ATAC v1.1.0", + "Cell Ranger v3.1.0", + "Space Ranger 3.1.2", + "Cell Ranger v5.0.0", + "Cell Ranger v6.1.2", + "Cell Ranger v9.0.0", + "Cell Ranger v5.0.1", + "Cell Ranger v4.0.0", + "Cell Ranger v7.1.0", + "Space Ranger 3.0.0", + "Cell Ranger v6.1.0", + "Space Ranger 3.1.1", + "demuxlet", + "Cell Ranger v8.0.1", + "Cell Ranger v7.0.0", + "Space Ranger 3.0.1", + "Space Ranger 3.1.0", + "Cell Ranger v6.0.1", + "Cell Ranger v6.1.1", + "Cell Ranger v3.0.0", + "Cell Ranger v7.0.1", + "Cell Ranger v3.0.1", + "Cell Ranger v3.0.2", + "Space Ranger 3.1.3", + "BD FACSDiva 8.0.1", + "Cell Ranger v6.0.2", + "Cell Ranger v6.0.0", + "Cell Ranger v7.2.0", + "" ] }, - "assay": { - "type": "array", - "items": { - "enum": [ - "feature barcode sequencing", - "SNP array", - "Olink Target 48", - "ASAPSeq", - "flow cytometry", - "GenePS SeqFISH", - "serial IHC", - "H&E", - "CyTOF", - "Visium", - "Olink Target 96", - "VDJSeq", - "Olink Reveal", - "CosMX", - "Olink Explore HT", - "Xenium", - "snRNASeq", - "WGS", - "SomaScan", - "snATACSeq", - "Olink Flex", - "scRNASeq", - "kiloplex", - "multiplexed ELISA", - "scVDJSeq", - "CITESeq", - "Olink Focus", - "imaging mass spectrometry", - "RNASeq", - "LC-MS/MS", - "imaging mass cytometry", - "NULISA", - "CE-MS", - "WES" - ] + "alignmentReference": { + "enum": [ + "10x Cell Ranger Human GRCh38 2020-A", + "GRCh38", + "10x Cell Ranger Human GRCh38 2024-A", + "vdj_GRCh38_alts_ensembl-4.0.0", + "unknown", + "modified GRCh38" + ] + }, + "totalReads": { + "not": { + "type": "null" }, - "maxItems": 34 + "minLength": 1 }, - "sequencingSaturation": {}, - "sampleProcessingBatch": {}, - "inputCellCount": { + "percentCellViability": { "not": { "type": "null" }, @@ -172,87 +135,126 @@ "type": "array", "items": { "enum": [ - "none", - "Chromium Xo", - "BD FACSDiscover A8", "BD FACSDiscover S8", - "BD LSRFortessa", - "Chromium GEM-X Single Cell 3' Chip v4", - "Chromium Next GEM Chip G", + "Chromium Xo", + "Visium CytAssist", + "Illumina NovaSeq 6000", "GEM-X Flex Gene Expression Chip", "Cytek Aurora Evo", - "Helios Mass Cytometer", - "Thermo Fisher Attune NxT", - "Fluidigm BioMark", + "none", + "Chromium X", + "BD FACSAria III", + "Olink Signature Q100", + "Hyperion", + "Chromium Controller", + "Illumina HiSeq X Ten", + "Chromium Next GEM Chip G", + "Illumina NextSeq 500", + "Chromium Next GEM Chip H", + "BD FACSMelody", + "BD FACSDiscover A8", "Not Applicable", + "Chromium Next GEM Chip K", + "Chromium GEM-X Single Cell 3' Chip v4", + "Cytek Aurora", + "BD FACSymphony S6", + "BD LSRFortessa", + "Sony MA900", + "Thermo Fisher Attune CytPix", + "Xenium", + "Helios Mass Cytometer", "CyTOF XT", - "Visium CytAssist", + "Fluidigm BioMark", "Chromium Next GEM Chip M", - "Sony MA900", - "Chromium Next GEM Chip H", - "BD FACSAria III", - "Cytek Aurora", - "BD FACSCanto", "Thermo Fisher Attune Xenith", - "Xenium", - "unknown", + "Illumina HiSeq 2500", + "Chromium iX", + "Illumina NovaSeq X", "BD FACSCanto II", + "BD FACSCanto", + "unknown", "BD FACSLyric Clinical", - "Chromium Controller", - "Chromium X", - "BD FACSymphony S6", - "GEM-X OCM 5' Chip", - "Thermo Fisher Attune CytPix", - "Illumina NovaSeq X", - "Olink Signature Q100", - "Illumina NextSeq 500", - "BD FACSMelody", - "Hyperion", - "Chromium Next GEM Chip Q", - "Chromium Next GEM Chip K", "BD FACSAria Fusion cell sorter", - "Illumina HiSeq X Ten", - "Illumina NovaSeq 6000", - "Illumina HiSeq 2500", - "Chromium iX" + "Chromium Next GEM Chip Q", + "GEM-X OCM 5' Chip", + "Thermo Fisher Attune NxT" ] }, "maxItems": 43 }, - "dataCollectionBatch": {}, - "alignmentReference": { + "Component": { + "not": { + "type": "null" + }, + "minLength": 1 + }, + "sequencingSaturation": {}, + "sampleProcessingBatch": {}, + "inputCellCount": { + "not": { + "type": "null" + }, + "minLength": 1 + }, + "libraryPrepMethod": { "enum": [ - "unknown", - "10x Cell Ranger Human GRCh38 2024-A", - "10x Cell Ranger Human GRCh38 2020-A", - "modified GRCh38", - "vdj_GRCh38_alts_ensembl-4.0.0" + "Takara Human TCR profiling for Illumina", + "SMART-Seq Human TCR with UMI", + "10x Chromium GEM-X Single Cell 3' v4", + "Takara Human scTCR profiling for Illumina", + "SMART-Seq v4 Ultra Low Input RNA", + "10x Chromium Next GEM Single Cell 5' v2", + "10x Chromium Next GEM Single Cell 3' 3.1", + "Takara Human BCR profiling for Illumina", + "10x GEM-X Flex Gene Expression Human", + "QIAseq miRNA Library", + "10x Chromium Next GEM Single Cell 5' v1.1", + "Chromium Next GEM Single Cell ATAC v1.1", + "SMARTer Stranded Total RNA v2", + "Takara Human TCRv2 profiling for Illumina", + "10x Chromium Next GEM Single Cell 3'", + "NEBNext Human Immune Sequencing Kit", + "CEL-Seq2", + "10x Chromium Fixed RNA Human Transcriptome", + "10x Chromium Single Cell Human BCR", + "10x Chromium GEM-X Single Cell 5' v3", + "in-house library prep", + "custom DASH-treatment", + "Fluidigm C1 HT", + "TruSeq Stranded mRNA", + "NEBNext Ultra II Directional RNA Library", + "10x GEM-X Universal 5' Gene Expression v3", + "SMART-Seq Human BCR with UMI", + "Nextera XT DNA", + "10x Chromium Single Cell Human TCR", + "Nextera XT", + "10x Chromium Next GEM Single Cell ATAC v2" ] }, "libraryID": {}, "biospecimenID": {}, "10xProbeSetReference": { "enum": [ + "Flex Human Transcriptome Probe Set v1.0.1", + "Visium Human Transcriptome v1", "Flex Human Transcriptome Probe Set v1.1.0", "Visium Human Transcriptome v2", - "Visium Human Transcriptome v1", "custom probe set", - "Flex Human Transcriptome Probe Set v1.0.1", "" ] } }, "required": [ - "Component", + "assay", "nucleicAcidSource", + "specimenModality", + "alignmentReference", "totalReads", "percentCellViability", - "specimenModality", - "libraryPrepMethod", - "assay", - "inputCellCount", "platform", - "alignmentReference" + "Component", + "inputCellCount", + "libraryPrepMethod" ], "allOf": [ { @@ -326,11 +328,11 @@ "properties": { "10xProbeSetReference": { "enum": [ + "Flex Human Transcriptome Probe Set v1.0.1", + "Visium Human Transcriptome v1", "Flex Human Transcriptome Probe Set v1.1.0", "Visium Human Transcriptome v2", - "Visium Human Transcriptome v1", - "custom probe set", - "Flex Human Transcriptome Probe Set v1.0.1" + "custom probe set" ] } }, diff --git a/model_json_schema/ark.SnATACSeqProcessedDataAnnotationTemplate.schema.json b/model_json_schema/ark.SnATACSeqProcessedDataAnnotationTemplate.schema.json index 4525fbc..c956df1 100644 --- a/model_json_schema/ark.SnATACSeqProcessedDataAnnotationTemplate.schema.json +++ b/model_json_schema/ark.SnATACSeqProcessedDataAnnotationTemplate.schema.json @@ -4,121 +4,117 @@ "title": "ark", "type": "object", "properties": { + "assay": { + "type": "array", + "items": { + "enum": [ + "CosMX", + "Olink Flex", + "CyTOF", + "snRNASeq", + "kiloplex", + "Olink Target 48", + "serial IHC", + "Xenium", + "Olink Focus", + "CITESeq", + "flow cytometry", + "NULISA", + "scVDJSeq", + "Visium", + "Olink Target 96", + "ASAPSeq", + "scRNASeq", + "RNASeq", + "snATACSeq", + "feature barcode sequencing", + "CE-MS", + "WES", + "SNP array", + "multiplexed ELISA", + "VDJSeq", + "imaging mass cytometry", + "H&E", + "WGS", + "LC-MS/MS", + "imaging mass spectrometry", + "Olink Explore HT", + "Olink Reveal", + "SomaScan", + "GenePS SeqFISH" + ] + }, + "maxItems": 34 + }, "Component": { "not": { "type": "null" }, "minLength": 1 }, - "cellRangerOutput": { + "resourceType": { + "type": "array", + "items": { + "enum": [ + "metadata", + "experimental data" + ] + }, + "maxItems": 2 + }, + "specimenModality": { "enum": [ - "filtered MEX", - "raw_feature_bc_matrix", - "raw_peak_bc_matrix", - "Not Applicable", - "filtered_peak_bc_matrix", - "raw MEX", - "filtered_feature_bc_matrix" + "unknown", + "multispecimen", + "single specimen" ] }, "fileFormat": { "enum": [ - "tsv", + "xls", + "Rds", + "bim", + "h5", + "h5ad", "bai", - "bed", - "csv", "zip", - "mtx", - "h5ad", - "Rds", - "tgz", - "txt", "fam", - "xls", + "tsv", + "csv", "xlsx", - "bim", - "h5", - "bam" + "bam", + "tgz", + "bed", + "mtx", + "txt" ] }, - "resourceType": { - "type": "array", - "items": { - "enum": [ - "experimental data", - "metadata" - ] - }, - "maxItems": 2 - }, "dataLevel": { "enum": [ - "5", - "2", - "4", "1", - "3" + "3", + "4", + "2", + "5" ] }, - "assay": { - "type": "array", - "items": { - "enum": [ - "Olink Reveal", - "GenePS SeqFISH", - "NULISA", - "Olink Target 48", - "kiloplex", - "LC-MS/MS", - "snATACSeq", - "WES", - "flow cytometry", - "CE-MS", - "Olink Target 96", - "imaging mass spectrometry", - "ASAPSeq", - "Olink Flex", - "Xenium", - "WGS", - "SomaScan", - "scVDJSeq", - "Olink Explore HT", - "Olink Focus", - "H&E", - "Visium", - "CITESeq", - "imaging mass cytometry", - "VDJSeq", - "multiplexed ELISA", - "SNP array", - "snRNASeq", - "CosMX", - "scRNASeq", - "RNASeq", - "feature barcode sequencing", - "serial IHC", - "CyTOF" - ] - }, - "maxItems": 34 - }, - "specimenModality": { + "cellRangerOutput": { "enum": [ - "single specimen", - "multispecimen" + "filtered MEX", + "filtered_feature_bc_matrix", + "raw_feature_bc_matrix", + "Not Applicable", + "filtered_peak_bc_matrix", + "raw MEX", + "raw_peak_bc_matrix" ] }, - "RObjectClass": { + "targetPanelSize": {}, + "targetPanelSynID": {}, + "targetPanel": {}, + "metadataType": { "enum": [ - "Symphony reference", - "SummarizedExperiment", - "list", - "ROCR prediction.object", - "sparse matrix", - "data.frame", - "Seurat object", - "matrix", - "vector", + "single-cell metadata", "" ] }, @@ -127,128 +123,87 @@ "items": { "enum": [ "gene counts", + "epigenomic peaks", "differential expression results", "barcode counts", - "epigenomic peaks", "" ] }, "maxItems": 4 }, - "metadataType": { + "individualID": {}, + "biospecimenID": {}, + "RObjectClass": { "enum": [ - "single-cell metadata", + "vector", + "Symphony reference", + "Seurat object", + "list", + "sparse matrix", + "SummarizedExperiment", + "data.frame", + "matrix", + "ROCR prediction.object", "" ] - }, - "targetPanel": {}, - "targetPanelSynID": {}, - "targetPanelSize": {}, - "individualID": {}, - "biospecimenID": {} + } }, "required": [ + "assay", "Component", - "cellRangerOutput", - "fileFormat", "resourceType", + "specimenModality", + "fileFormat", "dataLevel", - "assay", - "specimenModality" + "cellRangerOutput" ], "allOf": [ { "if": { "properties": { - "fileFormat": { + "assay": { "enum": [ - "Rds" + "feature barcode sequencing" ] } }, "required": [ - "fileFormat" + "assay" ] }, "then": { "properties": { - "RObjectClass": { - "enum": [ - "Symphony reference", - "SummarizedExperiment", - "list", - "ROCR prediction.object", - "sparse matrix", - "data.frame", - "Seurat object", - "matrix", - "vector", - "" - ] - } + "targetPanelSize": {} }, "required": [ - "RObjectClass" + "targetPanelSize" ] } }, { "if": { "properties": { - "resourceType": { + "assay": { "enum": [ - "experimental data" + "feature barcode sequencing" ] } }, "required": [ - "resourceType" + "assay" ] }, "then": { "properties": { - "processedDataType": { - "type": "array", - "items": { - "enum": [ - "gene counts", - "differential expression results", - "barcode counts", - "epigenomic peaks", - "" - ] + "targetPanelSynID": { + "not": { + "type": "null" }, - "maxItems": 4 - } - }, - "required": [ - "processedDataType" - ] - } - }, - { - "if": { - "properties": { - "resourceType": { - "enum": [ - "metadata" - ] - } - }, - "required": [ - "resourceType" - ] - }, - "then": { - "properties": { - "metadataType": { - "enum": [ - "single-cell metadata" - ] + "minLength": 1 } }, "required": [ - "metadataType" + "targetPanelSynID" ] } }, @@ -282,49 +237,60 @@ { "if": { "properties": { - "assay": { + "resourceType": { "enum": [ - "feature barcode sequencing" + "metadata" ] } }, "required": [ - "assay" + "resourceType" ] }, "then": { "properties": { - "targetPanelSynID": { - "not": { - "type": "null" - }, - "minLength": 1 + "metadataType": { + "enum": [ + "single-cell metadata" + ] } }, "required": [ - "targetPanelSynID" + "metadataType" ] } }, { "if": { "properties": { - "assay": { + "resourceType": { "enum": [ - "feature barcode sequencing" + "experimental data" ] } }, "required": [ - "assay" + "resourceType" ] }, "then": { "properties": { - "targetPanelSize": {} + "processedDataType": { + "type": "array", + "items": { + "enum": [ + "gene counts", + "epigenomic peaks", + "differential expression results", + "barcode counts", + "" + ] + }, + "maxItems": 4 + } }, "required": [ - "targetPanelSize" + "processedDataType" ] } }, @@ -381,6 +347,41 @@ "biospecimenID" ] } + }, + { + "if": { + "properties": { + "fileFormat": { + "enum": [ + "Rds" + ] + } + }, + "required": [ + "fileFormat" + ] + }, + "then": { + "properties": { + "RObjectClass": { + "enum": [ + "vector", + "Symphony reference", + "Seurat object", + "list", + "sparse matrix", + "SummarizedExperiment", + "data.frame", + "matrix", + "ROCR prediction.object", + "" + ] + } + }, + "required": [ + "RObjectClass" + ] + } } ] } \ No newline at end of file diff --git a/model_json_schema/ark.SnRNASeqAssayMetadataTemplate.schema.json b/model_json_schema/ark.SnRNASeqAssayMetadataTemplate.schema.json index 382007e..95dfac5 100644 --- a/model_json_schema/ark.SnRNASeqAssayMetadataTemplate.schema.json +++ b/model_json_schema/ark.SnRNASeqAssayMetadataTemplate.schema.json @@ -4,88 +4,79 @@ "title": "ark", "type": "object", "properties": { - "sampleProcessingBatch": {}, - "nucleicAcidSource": { - "type": "array", - "items": { - "enum": [ - "TCR mRNA", - "poly(A) RNA", - "BCR mRNA", - "multiplexing oligo", - "surface protein feature barcode", - "Tn5-accessible gDNA", - "antigen capture barcode", - "intracellular protein feature barcode", - "CRISPR protospacer feature barcode", - "rRNA-depleted RNA", - "gDNA", - "globin-depleted RNA" - ] - }, - "maxItems": 12 - }, - "inputCellCount": { + "dataCollectionBatch": {}, + "percentCellViability": { "not": { "type": "null" }, "minLength": 1 }, - "specimenModality": { + "softwareAndVersion": { "enum": [ - "multispecimen", - "single specimen" + "Cell Ranger v9.0.0", + "Cell Ranger v6.0.1", + "Cell Ranger v7.1.0", + "Cell Ranger ATAC v1.1.0", + "Cell Ranger v6.0.2", + "Space Ranger 3.1.1", + "Cell Ranger v6.1.1", + "Cell Ranger v7.0.1", + "Cell Ranger v4.0.0", + "Cell Ranger v3.0.1", + "Space Ranger 3.1.3", + "Cell Ranger v7.0.0", + "Cell Ranger v5.0.0", + "Cell Ranger v5.0.1", + "Cell Ranger v3.0.0", + "Cell Ranger v8.0.1", + "Cell Ranger v7.2.0", + "Cell Ranger v3.0.2", + "Cell Ranger 9.0.1", + "Cell Ranger v8.0.0", + "Cell Ranger v6.1.0", + "Cell Ranger v3.1.0", + "Cell Ranger v6.1.2", + "Cell Ranger v6.0.0", + "Space Ranger 3.0.0", + "Space Ranger 3.1.0", + "Space Ranger 3.1.2", + "Space Ranger 3.0.1", + "demuxlet", + "BD FACSDiva 8.0.1", + "" ] }, - "assay": { + "alignmentReference": { + "enum": [ + "10x Cell Ranger Human GRCh38 2020-A", + "GRCh38", + "modified GRCh38", + "10x Cell Ranger Human GRCh38 2024-A", + "vdj_GRCh38_alts_ensembl-4.0.0", + "unknown" + ] + }, + "nucleicAcidSource": { "type": "array", "items": { "enum": [ - "Visium", - "snATACSeq", - "Olink Target 48", - "Olink Reveal", - "snRNASeq", - "Olink Target 96", - "WES", - "feature barcode sequencing", - "VDJSeq", - "CosMX", - "serial IHC", - "GenePS SeqFISH", - "imaging mass cytometry", - "Xenium", - "WGS", - "CITESeq", - "RNASeq", - "SNP array", - "Olink Flex", - "ASAPSeq", - "Olink Explore HT", - "LC-MS/MS", - "H&E", - "Olink Focus", - "flow cytometry", - "multiplexed ELISA", - "scRNASeq", - "CE-MS", - "SomaScan", - "kiloplex", - "imaging mass spectrometry", - "scVDJSeq", - "CyTOF", - "NULISA" + "globin-depleted RNA", + "CRISPR protospacer feature barcode", + "poly(A) RNA", + "gDNA", + "antigen capture barcode", + "multiplexing oligo", + "TCR mRNA", + "BCR mRNA", + "surface protein feature barcode", + "rRNA-depleted RNA", + "Tn5-accessible gDNA", + "intracellular protein feature barcode" ] }, - "maxItems": 34 - }, - "totalReads": { - "not": { - "type": "null" - }, - "minLength": 1 + "maxItems": 12 }, - "dataCollectionBatch": {}, + "sampleProcessingBatch": {}, "Component": { "not": { "type": "null" @@ -96,99 +87,103 @@ "type": "array", "items": { "enum": [ - "Illumina NovaSeq 6000", - "Olink Signature Q100", + "BD FACSAria III", + "Illumina NovaSeq X", "BD FACSDiscover A8", - "Hyperion", - "BD FACSMelody", - "Chromium Next GEM Chip G", - "Cytek Aurora", + "Thermo Fisher Attune NxT", + "Chromium GEM-X Single Cell 3' Chip v4", + "GEM-X Flex Gene Expression Chip", + "BD FACSDiscover S8", + "GEM-X OCM 5' Chip", + "BD FACSAria Fusion cell sorter", + "Thermo Fisher Attune Xenith", "Not Applicable", + "Olink Signature Q100", + "Cytek Aurora Evo", + "Chromium Next GEM Chip Q", "Chromium X", "Chromium Xo", - "BD FACSAria III", - "Thermo Fisher Attune CytPix", - "Chromium Next GEM Chip K", - "Chromium Controller", + "BD LSRFortessa", + "CyTOF XT", + "Chromium iX", + "BD FACSCanto", + "Visium CytAssist", + "Chromium Next GEM Chip M", "BD FACSLyric Clinical", - "Illumina NextSeq 500", - "BD FACSymphony S6", - "GEM-X Flex Gene Expression Chip", - "Xenium", "Chromium Next GEM Chip H", - "Chromium GEM-X Single Cell 3' Chip v4", - "unknown", - "BD FACSDiscover S8", - "Chromium iX", - "Sony MA900", + "Chromium Controller", "Helios Mass Cytometer", + "BD FACSMelody", + "Fluidigm BioMark", + "Xenium", + "none", + "Illumina NovaSeq 6000", + "Illumina NextSeq 500", + "Sony MA900", + "Hyperion", + "Chromium Next GEM Chip G", + "Thermo Fisher Attune CytPix", "BD FACSCanto II", - "Cytek Aurora Evo", - "BD FACSAria Fusion cell sorter", - "BD LSRFortessa", - "GEM-X OCM 5' Chip", - "Visium CytAssist", - "Chromium Next GEM Chip Q", "Illumina HiSeq 2500", - "BD FACSCanto", - "Illumina NovaSeq X", - "Chromium Next GEM Chip M", - "none", "Illumina HiSeq X Ten", - "Thermo Fisher Attune NxT", - "Thermo Fisher Attune Xenith", - "Fluidigm BioMark", - "CyTOF XT" + "BD FACSymphony S6", + "unknown", + "Cytek Aurora", + "Chromium Next GEM Chip K" ] }, "maxItems": 43 }, - "softwareAndVersion": { - "enum": [ - "Space Ranger 3.0.0", - "BD FACSDiva 8.0.1", - "Cell Ranger ATAC v1.1.0", - "Cell Ranger v3.0.1", - "Space Ranger 3.1.1", - "Cell Ranger v4.0.0", - "Space Ranger 3.1.0", - "Cell Ranger v5.0.1", - "Cell Ranger v6.1.0", - "Cell Ranger v3.1.0", - "Cell Ranger v6.0.1", - "Cell Ranger 9.0.1", - "Space Ranger 3.1.3", - "Cell Ranger v7.2.0", - "Cell Ranger v5.0.0", - "Cell Ranger v3.0.2", - "Cell Ranger v8.0.1", - "Cell Ranger v8.0.0", - "Cell Ranger v6.1.2", - "Cell Ranger v6.0.2", - "Cell Ranger v9.0.0", - "Cell Ranger v6.1.1", - "Space Ranger 3.0.1", - "Space Ranger 3.1.2", - "Cell Ranger v7.1.0", - "Cell Ranger v7.0.1", - "Cell Ranger v3.0.0", - "Cell Ranger v7.0.0", - "demuxlet", - "Cell Ranger v6.0.0", - "" - ] + "assay": { + "type": "array", + "items": { + "enum": [ + "imaging mass spectrometry", + "imaging mass cytometry", + "snRNASeq", + "Olink Target 96", + "Olink Explore HT", + "RNASeq", + "Visium", + "scVDJSeq", + "multiplexed ELISA", + "GenePS SeqFISH", + "Olink Target 48", + "SomaScan", + "CITESeq", + "ASAPSeq", + "VDJSeq", + "flow cytometry", + "Olink Flex", + "serial IHC", + "WES", + "WGS", + "LC-MS/MS", + "Olink Reveal", + "Olink Focus", + "H&E", + "Xenium", + "kiloplex", + "SNP array", + "CE-MS", + "feature barcode sequencing", + "NULISA", + "CyTOF", + "CosMX", + "scRNASeq", + "snATACSeq" + ] + }, + "maxItems": 34 }, - "alignmentReference": { - "enum": [ - "unknown", - "10x Cell Ranger Human GRCh38 2024-A", - "modified GRCh38", - "10x Cell Ranger Human GRCh38 2020-A", - "vdj_GRCh38_alts_ensembl-4.0.0" - ] + "inputCellCount": { + "not": { + "type": "null" + }, + "minLength": 1 }, "sequencingSaturation": {}, - "percentCellViability": { + "totalReads": { "not": { "type": "null" }, @@ -196,89 +191,99 @@ }, "libraryPrepMethod": { "enum": [ - "10x Chromium GEM-X Single Cell 3' v4", - "CEL-Seq2", - "Takara Human TCRv2 profiling for Illumina", - "NEBNext Ultra II Directional RNA Library", - "Takara Human BCR profiling for Illumina", - "10x Chromium Next GEM Single Cell ATAC v2", - "10x Chromium GEM-X Single Cell 5' v3", - "Nextera XT", - "10x GEM-X Universal 5? Gene Expression v3", + "Nextera XT DNA", "Takara Human scTCR profiling for Illumina", - "Chromium Next GEM Single Cell ATAC v1.1", - "custom DASH-treatment", - "SMART-Seq v4 Ultra Low Input RNA", + "10x GEM-X Flex Gene Expression Human", + "SMARTer Stranded Total RNA v2", "Takara Human TCR profiling for Illumina", "SMART-Seq Human TCR with UMI", - "SMARTer Stranded Total RNA v2", - "10x Chromium Next GEM Single Cell 3'", + "Chromium Next GEM Single Cell ATAC v1.1", + "10x Chromium Fixed RNA Human Transcriptome", + "10x GEM-X Universal 5' Gene Expression v3", + "10x Chromium GEM-X Single Cell 5' v3", + "10x Chromium Next GEM Single Cell 3' 3.1", + "NEBNext Ultra II Directional RNA Library", + "SMART-Seq v4 Ultra Low Input RNA", "SMART-Seq Human BCR with UMI", - "10x Chromium Next GEM Single Cell 5' v1.1", + "Takara Human BCR profiling for Illumina", + "QIAseq miRNA Library", + "10x Chromium Single Cell Human TCR", + "CEL-Seq2", "NEBNext Human Immune Sequencing Kit", - "TruSeq Stranded mRNA", + "10x Chromium Next GEM Single Cell 5' v1.1", + "10x Chromium Next GEM Single Cell 5' v2", "Fluidigm C1 HT", - "10x Chromium Next GEM Single Cell 3' 3.1", - "10x GEM-X Flex Gene Expression Human", + "Takara Human TCRv2 profiling for Illumina", + "Nextera XT", + "10x Chromium Next GEM Single Cell ATAC v2", + "10x Chromium GEM-X Single Cell 3' v4", + "TruSeq Stranded mRNA", "10x Chromium Single Cell Human BCR", - "10x Chromium Single Cell Human TCR", - "10x Chromium Fixed RNA Human Transcriptome", - "Nextera XT DNA", - "QIAseq miRNA Library", - "in-house library prep", - "10x Chromium Next GEM Single Cell 5' v2" + "10x Chromium Next GEM Single Cell 3'", + "custom DASH-treatment", + "in-house library prep" + ] + }, + "specimenModality": { + "enum": [ + "multispecimen", + "unknown", + "single specimen" ] }, - "libraryID": {}, - "biospecimenID": {}, "10xProbeSetReference": { "enum": [ - "Visium Human Transcriptome v2", "custom probe set", "Flex Human Transcriptome Probe Set v1.0.1", - "Visium Human Transcriptome v1", "Flex Human Transcriptome Probe Set v1.1.0", + "Visium Human Transcriptome v1", + "Visium Human Transcriptome v2", "" ] - } + }, + "libraryID": {}, + "biospecimenID": {} }, "required": [ + "percentCellViability", + "alignmentReference", "nucleicAcidSource", - "inputCellCount", - "specimenModality", - "assay", - "totalReads", "Component", "platform", - "alignmentReference", - "percentCellViability", - "libraryPrepMethod" + "assay", + "inputCellCount", + "totalReads", + "libraryPrepMethod", + "specimenModality" ], "allOf": [ { "if": { "properties": { - "specimenModality": { + "libraryPrepMethod": { "enum": [ - "multispecimen" + "10x GEM-X Flex Gene Expression Human" ] } }, "required": [ - "specimenModality" + "libraryPrepMethod" ] }, "then": { "properties": { - "libraryID": { - "not": { - "type": "null" - }, - "minLength": 1 + "10xProbeSetReference": { + "enum": [ + "custom probe set", + "Flex Human Transcriptome Probe Set v1.0.1", + "Flex Human Transcriptome Probe Set v1.1.0", + "Visium Human Transcriptome v1", + "Visium Human Transcriptome v2" + ] } }, "required": [ - "libraryID" + "10xProbeSetReference" ] } }, @@ -287,7 +292,7 @@ "properties": { "specimenModality": { "enum": [ - "single specimen" + "multispecimen" ] } }, @@ -297,7 +302,7 @@ }, "then": { "properties": { - "biospecimenID": { + "libraryID": { "not": { "type": "null" }, @@ -305,37 +310,34 @@ } }, "required": [ - "biospecimenID" + "libraryID" ] } }, { "if": { "properties": { - "libraryPrepMethod": { + "specimenModality": { "enum": [ - "10x GEM-X Flex Gene Expression Human" + "single specimen" ] } }, "required": [ - "libraryPrepMethod" + "specimenModality" ] }, "then": { "properties": { - "10xProbeSetReference": { - "enum": [ - "Visium Human Transcriptome v2", - "custom probe set", - "Flex Human Transcriptome Probe Set v1.0.1", - "Visium Human Transcriptome v1", - "Flex Human Transcriptome Probe Set v1.1.0" - ] + "biospecimenID": { + "not": { + "type": "null" + }, + "minLength": 1 } }, "required": [ - "10xProbeSetReference" + "biospecimenID" ] } } diff --git a/model_json_schema/ark.SnRNASeqProcessedDataAnnotationTemplate.schema.json b/model_json_schema/ark.SnRNASeqProcessedDataAnnotationTemplate.schema.json index 17694c7..4a4e518 100644 --- a/model_json_schema/ark.SnRNASeqProcessedDataAnnotationTemplate.schema.json +++ b/model_json_schema/ark.SnRNASeqProcessedDataAnnotationTemplate.schema.json @@ -4,38 +4,6 @@ "title": "ark", "type": "object", "properties": { - "cellRangerOutput": { - "enum": [ - "filtered_peak_bc_matrix", - "raw_feature_bc_matrix", - "raw_peak_bc_matrix", - "filtered MEX", - "filtered_feature_bc_matrix", - "raw MEX", - "Not Applicable" - ] - }, - "Component": { - "not": { - "type": "null" - }, - "minLength": 1 - }, - "dataLevel": { - "enum": [ - "4", - "5", - "3", - "1", - "2" - ] - }, - "specimenModality": { - "enum": [ - "multispecimen", - "single specimen" - ] - }, "resourceType": { "type": "array", "items": { @@ -48,68 +16,99 @@ }, "fileFormat": { "enum": [ - "tsv", - "csv", - "bam", - "xlsx", - "zip", - "mtx", + "xls", + "fam", "bed", - "tgz", + "bai", + "Rds", "bim", + "tsv", "h5", - "h5ad", - "Rds", - "fam", - "xls", + "tgz", + "zip", + "xlsx", "txt", - "bai" + "mtx", + "bam", + "csv", + "h5ad" + ] + }, + "specimenModality": { + "enum": [ + "multispecimen", + "unknown", + "single specimen" ] }, "assay": { "type": "array", "items": { "enum": [ + "H&E", + "Olink Focus", + "NULISA", + "CosMX", + "Olink Target 48", + "Olink Target 96", + "CITESeq", + "snATACSeq", + "scRNASeq", + "SNP array", + "snRNASeq", + "RNASeq", "GenePS SeqFISH", + "SomaScan", + "Xenium", + "Visium", + "Olink Explore HT", + "CyTOF", "Olink Reveal", + "imaging mass spectrometry", + "serial IHC", "flow cytometry", - "snRNASeq", - "Olink Target 48", - "Olink Explore HT", - "Xenium", - "scRNASeq", - "CosMX", - "multiplexed ELISA", + "LC-MS/MS", + "feature barcode sequencing", + "imaging mass cytometry", "kiloplex", "scVDJSeq", - "snATACSeq", - "WES", + "multiplexed ELISA", "CE-MS", + "WES", "VDJSeq", - "SomaScan", - "Olink Focus", - "CITESeq", - "NULISA", - "Olink Flex", - "Visium", "WGS", - "imaging mass cytometry", - "CyTOF", - "SNP array", - "serial IHC", - "feature barcode sequencing", - "LC-MS/MS", - "imaging mass spectrometry", - "Olink Target 96", - "ASAPSeq", - "RNASeq", - "H&E" + "Olink Flex", + "ASAPSeq" ] }, "maxItems": 34 }, - "biospecimenID": {}, - "individualID": {}, + "cellRangerOutput": { + "enum": [ + "filtered_peak_bc_matrix", + "raw MEX", + "raw_peak_bc_matrix", + "filtered MEX", + "raw_feature_bc_matrix", + "Not Applicable", + "filtered_feature_bc_matrix" + ] + }, + "Component": { + "not": { + "type": "null" + }, + "minLength": 1 + }, + "dataLevel": { + "enum": [ + "1", + "3", + "2", + "4", + "5" + ] + }, "metadataType": { "enum": [ "single-cell metadata", @@ -121,9 +120,9 @@ "items": { "enum": [ "epigenomic peaks", - "differential expression results", "barcode counts", "gene counts", + "differential expression results", "" ] }, @@ -131,178 +130,180 @@ }, "RObjectClass": { "enum": [ - "matrix", "ROCR prediction.object", - "Symphony reference", - "Seurat object", - "vector", + "sparse matrix", "SummarizedExperiment", "list", + "matrix", + "Seurat object", + "vector", "data.frame", - "sparse matrix", + "Symphony reference", "" ] }, + "individualID": {}, + "biospecimenID": {}, "targetPanelSize": {}, "targetPanel": {}, "targetPanelSynID": {} }, "required": [ - "cellRangerOutput", - "Component", - "dataLevel", - "specimenModality", "resourceType", "fileFormat", - "assay" + "specimenModality", + "assay", + "cellRangerOutput", + "Component", + "dataLevel" ], "allOf": [ { "if": { "properties": { - "specimenModality": { + "resourceType": { "enum": [ - "single specimen" + "metadata" ] } }, "required": [ - "specimenModality" + "resourceType" ] }, "then": { "properties": { - "biospecimenID": { - "not": { - "type": "null" - }, - "minLength": 1 + "metadataType": { + "enum": [ + "single-cell metadata" + ] } }, "required": [ - "biospecimenID" + "metadataType" ] } }, { "if": { "properties": { - "specimenModality": { + "resourceType": { "enum": [ - "single specimen" + "experimental data" ] } }, "required": [ - "specimenModality" + "resourceType" ] }, "then": { "properties": { - "individualID": { - "not": { - "type": "null" + "processedDataType": { + "type": "array", + "items": { + "enum": [ + "epigenomic peaks", + "barcode counts", + "gene counts", + "differential expression results", + "" + ] }, - "minLength": 1 + "maxItems": 4 } }, "required": [ - "individualID" + "processedDataType" ] } }, { "if": { "properties": { - "resourceType": { + "fileFormat": { "enum": [ - "metadata" + "Rds" ] } }, "required": [ - "resourceType" + "fileFormat" ] }, "then": { "properties": { - "metadataType": { + "RObjectClass": { "enum": [ - "single-cell metadata" + "ROCR prediction.object", + "sparse matrix", + "SummarizedExperiment", + "list", + "matrix", + "Seurat object", + "vector", + "data.frame", + "Symphony reference", + "" ] } }, "required": [ - "metadataType" + "RObjectClass" ] } }, { "if": { "properties": { - "resourceType": { + "specimenModality": { "enum": [ - "experimental data" + "single specimen" ] } }, "required": [ - "resourceType" + "specimenModality" ] }, "then": { "properties": { - "processedDataType": { - "type": "array", - "items": { - "enum": [ - "epigenomic peaks", - "differential expression results", - "barcode counts", - "gene counts", - "" - ] + "individualID": { + "not": { + "type": "null" }, - "maxItems": 4 + "minLength": 1 } }, "required": [ - "processedDataType" + "individualID" ] } }, { "if": { "properties": { - "fileFormat": { + "specimenModality": { "enum": [ - "Rds" + "single specimen" ] } }, "required": [ - "fileFormat" + "specimenModality" ] }, "then": { "properties": { - "RObjectClass": { - "enum": [ - "matrix", - "ROCR prediction.object", - "Symphony reference", - "Seurat object", - "vector", - "SummarizedExperiment", - "list", - "data.frame", - "sparse matrix", - "" - ] + "biospecimenID": { + "not": { + "type": "null" + }, + "minLength": 1 } }, "required": [ - "RObjectClass" + "biospecimenID" ] } }, diff --git a/model_json_schema/ark.SpatialImagingAssayMetadataTemplate.schema.json b/model_json_schema/ark.SpatialImagingAssayMetadataTemplate.schema.json index b4ae43e..ad31446 100644 --- a/model_json_schema/ark.SpatialImagingAssayMetadataTemplate.schema.json +++ b/model_json_schema/ark.SpatialImagingAssayMetadataTemplate.schema.json @@ -4,7 +4,26 @@ "title": "ark", "type": "object", "properties": { - "targetPanel": { + "targetPanelSize": {}, + "assay": { + "enum": [ + "H&E", + "CosMX", + "serial IHC", + "Xenium", + "GenePS SeqFISH", + "imaging mass cytometry", + "Visium" + ] + }, + "specimenModality": { + "enum": [ + "multispecimen", + "unknown", + "single specimen" + ] + }, + "Component": { "not": { "type": "null" }, @@ -16,41 +35,23 @@ }, "minLength": 1 }, - "assay": { - "enum": [ - "GenePS SeqFISH", - "serial IHC", - "Xenium", - "CosMX", - "Visium", - "H&E", - "imaging mass cytometry" - ] - }, - "specimenModality": { - "enum": [ - "single specimen", - "multispecimen" - ] - }, - "dataCollectionBatch": {}, - "targetPanelSize": {}, "sampleProcessingBatch": {}, - "Component": { + "targetPanel": { "not": { "type": "null" }, "minLength": 1 }, - "biospecimenID": {}, - "slideID": {} + "dataCollectionBatch": {}, + "slideID": {}, + "biospecimenID": {} }, "required": [ - "targetPanel", - "targetPanelSynID", "assay", "specimenModality", - "Component" + "Component", + "targetPanelSynID", + "targetPanel" ], "allOf": [ { @@ -58,7 +59,7 @@ "properties": { "specimenModality": { "enum": [ - "single specimen" + "multispecimen" ] } }, @@ -68,7 +69,7 @@ }, "then": { "properties": { - "biospecimenID": { + "slideID": { "not": { "type": "null" }, @@ -76,7 +77,7 @@ } }, "required": [ - "biospecimenID" + "slideID" ] } }, @@ -85,7 +86,7 @@ "properties": { "specimenModality": { "enum": [ - "multispecimen" + "single specimen" ] } }, @@ -95,7 +96,7 @@ }, "then": { "properties": { - "slideID": { + "biospecimenID": { "not": { "type": "null" }, @@ -103,7 +104,7 @@ } }, "required": [ - "slideID" + "biospecimenID" ] } } diff --git a/model_json_schema/ark.SpatialImagingFileAnnotationTemplate.schema.json b/model_json_schema/ark.SpatialImagingFileAnnotationTemplate.schema.json index 77e03dc..3046bbe 100644 --- a/model_json_schema/ark.SpatialImagingFileAnnotationTemplate.schema.json +++ b/model_json_schema/ark.SpatialImagingFileAnnotationTemplate.schema.json @@ -4,18 +4,59 @@ "title": "ark", "type": "object", "properties": { + "fileFormat": { + "enum": [ + "fcs", + "h5ad", + "h5", + "txt", + "bim", + "geojson", + "tbi", + "vcf", + "tsv", + "mcd", + "erate", + "bai", + "py", + "bed", + "dose", + "czi", + "fastq", + "rds", + "fam", + "xls", + "tgz", + "zip", + "svs", + "parquet", + "xlsx", + "bam", + "pdf", + "rec", + "csv", + "info", + "mtx", + "docx" + ] + }, + "assay": { + "enum": [ + "Visium", + "CosMX", + "GenePS SeqFISH", + "Xenium", + "imaging mass cytometry", + "H&E", + "serial IHC" + ] + }, "Component": { "not": { "type": "null" }, "minLength": 1 }, - "specimenModality": { - "enum": [ - "multispecimen", - "single specimen" - ] - }, "resourceType": { "type": "array", "items": { @@ -26,61 +67,34 @@ }, "maxItems": 2 }, - "assay": { + "specimenModality": { "enum": [ - "serial IHC", - "CosMX", - "Xenium", - "GenePS SeqFISH", - "imaging mass cytometry", - "H&E", - "Visium" + "multispecimen", + "unknown", + "single specimen" ] }, - "fileFormat": { + "RObjectClass": { "enum": [ - "rds", - "svs", - "pdf", - "h5ad", - "tgz", - "dose", - "fam", - "h5", - "info", - "fcs", - "erate", - "tbi", - "zip", - "mcd", - "bai", - "bim", - "geojson", - "bam", - "tsv", - "xlsx", - "vcf", - "csv", - "rec", - "bed", - "czi", - "mtx", - "docx", - "parquet", - "xls", - "fastq", - "txt" + "data.frame", + "sparse matrix", + "Seurat object", + "vector", + "Symphony reference", + "ROCR prediction.object", + "matrix", + "list", + "SummarizedExperiment", + "" ] }, - "slideID": {}, - "biospecimenID": {}, "metadataType": { "enum": [ - "other", - "cell coordinates", "target panel", - "single-cell metadata", + "cell coordinates", "tissue microarray map", + "single-cell metadata", + "other", "" ] }, @@ -88,89 +102,58 @@ "type": "array", "items": { "enum": [ - "barcode counts", "differential expression results", "epigenomic peaks", "gene counts", + "barcode counts", "" ] }, "maxItems": 4 }, - "RObjectClass": { - "enum": [ - "Symphony reference", - "sparse matrix", - "SummarizedExperiment", - "list", - "Seurat object", - "matrix", - "vector", - "data.frame", - "ROCR prediction.object", - "" - ] - } + "slideID": {}, + "biospecimenID": {} }, "required": [ + "fileFormat", + "assay", "Component", - "specimenModality", "resourceType", - "assay", - "fileFormat" + "specimenModality" ], "allOf": [ { "if": { "properties": { - "specimenModality": { + "fileFormat": { "enum": [ - "multispecimen" + "rds" ] } }, "required": [ - "specimenModality" + "fileFormat" ] }, "then": { "properties": { - "slideID": { - "not": { - "type": "null" - }, - "minLength": 1 - } - }, - "required": [ - "slideID" - ] - } - }, - { - "if": { - "properties": { - "specimenModality": { + "RObjectClass": { "enum": [ - "single specimen" + "data.frame", + "sparse matrix", + "Seurat object", + "vector", + "Symphony reference", + "ROCR prediction.object", + "matrix", + "list", + "SummarizedExperiment", + "" ] } }, "required": [ - "specimenModality" - ] - }, - "then": { - "properties": { - "biospecimenID": { - "not": { - "type": "null" - }, - "minLength": 1 - } - }, - "required": [ - "biospecimenID" + "RObjectClass" ] } }, @@ -191,11 +174,11 @@ "properties": { "metadataType": { "enum": [ - "other", - "cell coordinates", "target panel", + "cell coordinates", + "tissue microarray map", "single-cell metadata", - "tissue microarray map" + "other" ] } }, @@ -223,10 +206,10 @@ "type": "array", "items": { "enum": [ - "barcode counts", "differential expression results", "epigenomic peaks", "gene counts", + "barcode counts", "" ] }, @@ -241,35 +224,54 @@ { "if": { "properties": { - "fileFormat": { + "specimenModality": { "enum": [ - "rds" + "multispecimen" ] } }, "required": [ - "fileFormat" + "specimenModality" ] }, "then": { "properties": { - "RObjectClass": { + "slideID": { + "not": { + "type": "null" + }, + "minLength": 1 + } + }, + "required": [ + "slideID" + ] + } + }, + { + "if": { + "properties": { + "specimenModality": { "enum": [ - "Symphony reference", - "sparse matrix", - "SummarizedExperiment", - "list", - "Seurat object", - "matrix", - "vector", - "data.frame", - "ROCR prediction.object", - "" + "single specimen" ] } }, "required": [ - "RObjectClass" + "specimenModality" + ] + }, + "then": { + "properties": { + "biospecimenID": { + "not": { + "type": "null" + }, + "minLength": 1 + } + }, + "required": [ + "biospecimenID" ] } } diff --git a/model_templates/ark.BDMFCSFileAnnotations.csv b/model_templates/ark.BDMFCSFileAnnotations.csv index d951309..6969d8f 100644 --- a/model_templates/ark.BDMFCSFileAnnotations.csv +++ b/model_templates/ark.BDMFCSFileAnnotations.csv @@ -1 +1 @@ -dataSubtype,project,fileFormat,sampleProcessingBatch,resourceType,parentBiospecimenID,program,biospecimenType,Component,biospecimenSubtype,dataType,diagnosis,platform,specimenModality,dataCollectionBatch,species,assay,eventCount,visitID,individualID,biospecimenID +Component,primaryCellSource,parentBiospecimenID,eventCount,diagnosis,sampleProcessingBatch,biospecimenSubtype,cellType,project,assay,species,biospecimenType,platform,specimenModality,dataSubtype,dataCollectionBatch,resourceType,fileFormat,dataType,userDefinedCellType,program,individualID,biospecimenID,visitID diff --git a/model_templates/ark.BDMFCSFileAnnotations.xlsx b/model_templates/ark.BDMFCSFileAnnotations.xlsx index 210d271..81e514c 100644 Binary files a/model_templates/ark.BDMFCSFileAnnotations.xlsx and b/model_templates/ark.BDMFCSFileAnnotations.xlsx differ diff --git a/model_templates/ark.BDMFastqFileAnnotations.csv b/model_templates/ark.BDMFastqFileAnnotations.csv index d1d5d2a..14c9c41 100644 --- a/model_templates/ark.BDMFastqFileAnnotations.csv +++ b/model_templates/ark.BDMFastqFileAnnotations.csv @@ -1 +1 @@ -dataType,resourceType,project,libraryPrepMethod,Component,biospecimenType,nucleicAcidSource,fileFormat,program,species,platform,diagnosis,assay,specimenModality,biospecimenSubtype,readLength,dataSubtype,parentBiospecimenID,visitID,targetPanelSize,targetPanel,targetPanelSynID,biospecimenID,individualID,libraryID +dataType,dataSubtype,diagnosis,nucleicAcidSource,readLength,species,resourceType,parentBiospecimenID,cellType,primaryCellSource,libraryPrepMethod,userDefinedCellType,biospecimenType,program,fileFormat,specimenModality,Component,platform,assay,project,biospecimenSubtype,visitID,libraryID,individualID,biospecimenID,targetPanelSize,targetPanelSynID,targetPanel diff --git a/model_templates/ark.BDMFastqFileAnnotations.xlsx b/model_templates/ark.BDMFastqFileAnnotations.xlsx index 721ba22..ea8843a 100644 Binary files a/model_templates/ark.BDMFastqFileAnnotations.xlsx and b/model_templates/ark.BDMFastqFileAnnotations.xlsx differ diff --git a/model_templates/ark.BDMMetadataFileAnnotations.csv b/model_templates/ark.BDMMetadataFileAnnotations.csv index 89fd099..579cc0e 100644 --- a/model_templates/ark.BDMMetadataFileAnnotations.csv +++ b/model_templates/ark.BDMMetadataFileAnnotations.csv @@ -1 +1 @@ -Component,resourceType,species,dataType,project,fileFormat,program,metadataStandards,metadataType,programPhase,assay +program,dataType,species,project,fileFormat,primaryCellSource,userDefinedCellType,resourceType,cellType,Component,programPhase,metadataType,metadataStandards,assay diff --git a/model_templates/ark.BDMMetadataFileAnnotations.xlsx b/model_templates/ark.BDMMetadataFileAnnotations.xlsx index f6a23d6..b565008 100644 Binary files a/model_templates/ark.BDMMetadataFileAnnotations.xlsx and b/model_templates/ark.BDMMetadataFileAnnotations.xlsx differ diff --git a/model_templates/ark.BDMOlinkFileAnnotations.csv b/model_templates/ark.BDMOlinkFileAnnotations.csv index 634db69..0f13dde 100644 --- a/model_templates/ark.BDMOlinkFileAnnotations.csv +++ b/model_templates/ark.BDMOlinkFileAnnotations.csv @@ -1 +1 @@ -platform,targetPanelSize,visitID,fileFormat,targetPanelSynID,dataType,specimenModality,project,diagnosis,species,plateID,program,Component,biospecimenType,resourceType,dataSubtype,targetPanel,programPhase +cellType,dataSubtype,dataType,plateID,visitID,platform,diagnosis,targetPanel,species,targetPanelSize,resourceType,targetPanelSynID,fileFormat,specimenModality,biospecimenType,program,project,userDefinedCellType,primaryCellSource,Component,programPhase diff --git a/model_templates/ark.BDMOlinkFileAnnotations.xlsx b/model_templates/ark.BDMOlinkFileAnnotations.xlsx index 10e31b9..44d707a 100644 Binary files a/model_templates/ark.BDMOlinkFileAnnotations.xlsx and b/model_templates/ark.BDMOlinkFileAnnotations.xlsx differ diff --git a/model_templates/ark.BDMSpatialImagingFileAnnotations.csv b/model_templates/ark.BDMSpatialImagingFileAnnotations.csv index 0b356dd..7d5b65f 100644 --- a/model_templates/ark.BDMSpatialImagingFileAnnotations.csv +++ b/model_templates/ark.BDMSpatialImagingFileAnnotations.csv @@ -1 +1 @@ -resourceType,targetPanel,targetPanelSynID,visitID,specimenModality,targetPanelSize,project,diagnosis,program,fileFormat,Component,dataSubtype,dataType,species,biospecimenType,parentBiospecimenID,assay,biospecimenSubtype,metadataType,processedDataType,biospecimenID,slideID,RObjectClass +parentBiospecimenID,Component,dataType,biospecimenSubtype,resourceType,program,dataSubtype,specimenModality,targetPanel,project,userDefinedCellType,targetPanelSynID,biospecimenType,primaryCellSource,fileFormat,cellType,visitID,targetPanelSize,assay,diagnosis,species,processedDataType,metadataType,slideID,biospecimenID,RObjectClass diff --git a/model_templates/ark.BDMSpatialImagingFileAnnotations.xlsx b/model_templates/ark.BDMSpatialImagingFileAnnotations.xlsx index cc26724..b0d95ea 100644 Binary files a/model_templates/ark.BDMSpatialImagingFileAnnotations.xlsx and b/model_templates/ark.BDMSpatialImagingFileAnnotations.xlsx differ diff --git a/model_templates/ark.BDMscRNASeqProcessedDataAnnotations.csv b/model_templates/ark.BDMscRNASeqProcessedDataAnnotations.csv index 4e46e6e..1909341 100644 --- a/model_templates/ark.BDMscRNASeqProcessedDataAnnotations.csv +++ b/model_templates/ark.BDMscRNASeqProcessedDataAnnotations.csv @@ -1 +1 @@ -parentBiospecimenID,visitID,project,resourceType,diagnosis,softwareAndVersion,dataType,nucleicAcidSource,fileFormat,alignmentReference,assay,libraryPrepMethod,biospecimenSubtype,dataSubtype,Component,program,biospecimenType,cellRangerOutput,specimenModality,dataLevel,species,metadataType,processedDataType,RObjectClass,targetPanel,targetPanelSize,targetPanelSynID,individualID,biospecimenID +assay,fileFormat,project,biospecimenType,diagnosis,primaryCellSource,dataLevel,visitID,cellRangerOutput,libraryPrepMethod,nucleicAcidSource,program,userDefinedCellType,biospecimenSubtype,species,cellType,specimenModality,softwareAndVersion,resourceType,dataType,dataSubtype,Component,parentBiospecimenID,alignmentReference,targetPanelSize,targetPanelSynID,targetPanel,RObjectClass,individualID,biospecimenID,metadataType,processedDataType diff --git a/model_templates/ark.BDMscRNASeqProcessedDataAnnotations.xlsx b/model_templates/ark.BDMscRNASeqProcessedDataAnnotations.xlsx index 4b1ce05..be39550 100644 Binary files a/model_templates/ark.BDMscRNASeqProcessedDataAnnotations.xlsx and b/model_templates/ark.BDMscRNASeqProcessedDataAnnotations.xlsx differ diff --git a/model_templates/ark.BDMscVDJSeqProcessedDataAnnotations.csv b/model_templates/ark.BDMscVDJSeqProcessedDataAnnotations.csv index 7594753..11f71f3 100644 --- a/model_templates/ark.BDMscVDJSeqProcessedDataAnnotations.csv +++ b/model_templates/ark.BDMscVDJSeqProcessedDataAnnotations.csv @@ -1 +1 @@ -parentBiospecimenID,specimenModality,biospecimenType,softwareAndVersion,dataSubtype,visitID,alignmentReference,program,nucleicAcidSource,biospecimenSubtype,species,Component,dataLevel,project,resourceType,assay,diagnosis,libraryPrepMethod,dataType,fileFormat,individualID,biospecimenID,metadataType,processedDataType,targetPanelSynID,targetPanelSize,targetPanel,RObjectClass +cellType,softwareAndVersion,dataLevel,species,fileFormat,program,visitID,primaryCellSource,specimenModality,dataType,alignmentReference,biospecimenSubtype,parentBiospecimenID,diagnosis,Component,libraryPrepMethod,resourceType,nucleicAcidSource,userDefinedCellType,dataSubtype,project,biospecimenType,assay,RObjectClass,individualID,biospecimenID,metadataType,processedDataType,targetPanel,targetPanelSize,targetPanelSynID diff --git a/model_templates/ark.BDMscVDJSeqProcessedDataAnnotations.xlsx b/model_templates/ark.BDMscVDJSeqProcessedDataAnnotations.xlsx index 81a9dc0..4cb1d08 100644 Binary files a/model_templates/ark.BDMscVDJSeqProcessedDataAnnotations.xlsx and b/model_templates/ark.BDMscVDJSeqProcessedDataAnnotations.xlsx differ diff --git a/model_templates/ark.BDMsnATACSeqProcessedDataAnnotations.csv b/model_templates/ark.BDMsnATACSeqProcessedDataAnnotations.csv index 63e2000..7fc8797 100644 --- a/model_templates/ark.BDMsnATACSeqProcessedDataAnnotations.csv +++ b/model_templates/ark.BDMsnATACSeqProcessedDataAnnotations.csv @@ -1 +1 @@ -dataSubtype,assay,diagnosis,specimenModality,project,dataType,program,softwareAndVersion,resourceType,alignmentReference,Component,biospecimenSubtype,libraryPrepMethod,biospecimenType,fileFormat,parentBiospecimenID,nucleicAcidSource,visitID,species,cellRangerOutput,dataLevel,targetPanelSize,targetPanelSynID,targetPanel,biospecimenID,individualID,processedDataType,metadataType,RObjectClass +biospecimenType,dataLevel,project,dataType,assay,biospecimenSubtype,libraryPrepMethod,resourceType,visitID,diagnosis,parentBiospecimenID,cellRangerOutput,softwareAndVersion,primaryCellSource,userDefinedCellType,specimenModality,cellType,nucleicAcidSource,dataSubtype,alignmentReference,Component,program,species,fileFormat,targetPanelSynID,targetPanelSize,targetPanel,processedDataType,metadataType,biospecimenID,individualID,RObjectClass diff --git a/model_templates/ark.BDMsnATACSeqProcessedDataAnnotations.xlsx b/model_templates/ark.BDMsnATACSeqProcessedDataAnnotations.xlsx index 06545e3..530ad46 100644 Binary files a/model_templates/ark.BDMsnATACSeqProcessedDataAnnotations.xlsx and b/model_templates/ark.BDMsnATACSeqProcessedDataAnnotations.xlsx differ diff --git a/model_templates/ark.BDMsnRNASeqProcessedDataAnnotations.csv b/model_templates/ark.BDMsnRNASeqProcessedDataAnnotations.csv index fc39a13..d0da10d 100644 --- a/model_templates/ark.BDMsnRNASeqProcessedDataAnnotations.csv +++ b/model_templates/ark.BDMsnRNASeqProcessedDataAnnotations.csv @@ -1 +1 @@ -dataLevel,fileFormat,visitID,parentBiospecimenID,assay,species,Component,nucleicAcidSource,dataSubtype,dataType,project,biospecimenType,diagnosis,biospecimenSubtype,softwareAndVersion,libraryPrepMethod,program,cellRangerOutput,alignmentReference,specimenModality,resourceType,RObjectClass,targetPanelSize,targetPanelSynID,targetPanel,biospecimenID,individualID,processedDataType,metadataType +biospecimenType,nucleicAcidSource,libraryPrepMethod,dataSubtype,dataLevel,cellType,cellRangerOutput,biospecimenSubtype,project,visitID,program,softwareAndVersion,specimenModality,primaryCellSource,Component,dataType,resourceType,species,diagnosis,assay,fileFormat,alignmentReference,userDefinedCellType,parentBiospecimenID,individualID,biospecimenID,metadataType,processedDataType,targetPanelSynID,targetPanelSize,targetPanel,RObjectClass diff --git a/model_templates/ark.BDMsnRNASeqProcessedDataAnnotations.xlsx b/model_templates/ark.BDMsnRNASeqProcessedDataAnnotations.xlsx index 2ea1f4e..5616849 100644 Binary files a/model_templates/ark.BDMsnRNASeqProcessedDataAnnotations.xlsx and b/model_templates/ark.BDMsnRNASeqProcessedDataAnnotations.xlsx differ diff --git a/model_templates/ark.BiospecimenMetadataTemplate.csv b/model_templates/ark.BiospecimenMetadataTemplate.csv index 8f17c51..008f3ec 100644 --- a/model_templates/ark.BiospecimenMetadataTemplate.csv +++ b/model_templates/ark.BiospecimenMetadataTemplate.csv @@ -1 +1 @@ -biospecimenID,altSampleID,biospecimenSubtype,individualID,project,notes,biospecimenType,Component,program,parentBiospecimenID,cellType,userDefinedCellType,cellOntologyID,FACSPopulation,primaryCellSource,krennStroma,krennSynovitisScore,anatomicalSite,krennLining,krennInflammatory,synovialCollectionProcedure,skinSiteStatus,salivaCollectionProcedure,visitID +notes,program,project,biospecimenType,Component,biospecimenID,individualID,altSampleID,parentBiospecimenID,sampleCollectionBatch,biospecimenSubtype,visitID,skinSiteStatus,anatomicalSite,salivaCollectionProcedure,primaryCellSource,cellType,cellOntologyID,krennLining,krennInflammatory,synovialCollectionProcedure,krennStroma,krennSynovitisScore,userDefinedCellType,FACSPopulation diff --git a/model_templates/ark.BiospecimenMetadataTemplate.xlsx b/model_templates/ark.BiospecimenMetadataTemplate.xlsx index f0d82f3..109b3b2 100644 Binary files a/model_templates/ark.BiospecimenMetadataTemplate.xlsx and b/model_templates/ark.BiospecimenMetadataTemplate.xlsx differ diff --git a/model_templates/ark.BulkATAC-seqAssayMetadataTemplate.csv b/model_templates/ark.BulkATAC-seqAssayMetadataTemplate.csv index 37eb055..a1059f4 100644 --- a/model_templates/ark.BulkATAC-seqAssayMetadataTemplate.csv +++ b/model_templates/ark.BulkATAC-seqAssayMetadataTemplate.csv @@ -1 +1 @@ -libraryPrepMethod,softwareAndVersion,totalReads,assay,platform,alignmentReference,dataCollectionBatch,Component,specimenModality,nucleicAcidSource,sampleProcessingBatch,10xProbeSetReference,libraryID,biospecimenID +totalReads,specimenModality,softwareAndVersion,libraryPrepMethod,dataCollectionBatch,nucleicAcidSource,Component,sampleProcessingBatch,assay,alignmentReference,platform,biospecimenID,libraryID,10xProbeSetReference diff --git a/model_templates/ark.BulkATAC-seqAssayMetadataTemplate.xlsx b/model_templates/ark.BulkATAC-seqAssayMetadataTemplate.xlsx index 64ff0d5..fc55160 100644 Binary files a/model_templates/ark.BulkATAC-seqAssayMetadataTemplate.xlsx and b/model_templates/ark.BulkATAC-seqAssayMetadataTemplate.xlsx differ diff --git a/model_templates/ark.BulkRNA-seqAssayMetadataTemplate.csv b/model_templates/ark.BulkRNA-seqAssayMetadataTemplate.csv index 561c8bb..ae2aa14 100644 --- a/model_templates/ark.BulkRNA-seqAssayMetadataTemplate.csv +++ b/model_templates/ark.BulkRNA-seqAssayMetadataTemplate.csv @@ -1 +1 @@ -totalReads,assay,alignmentReference,Component,nucleicAcidSource,specimenModality,libraryPrepMethod,dataCollectionBatch,sampleProcessingBatch,softwareAndVersion,platform,biospecimenID,libraryID,10xProbeSetReference +dataCollectionBatch,sampleProcessingBatch,specimenModality,Component,libraryPrepMethod,platform,softwareAndVersion,totalReads,alignmentReference,nucleicAcidSource,assay,biospecimenID,libraryID,10xProbeSetReference diff --git a/model_templates/ark.BulkRNA-seqAssayMetadataTemplate.xlsx b/model_templates/ark.BulkRNA-seqAssayMetadataTemplate.xlsx index 20c0e5d..f4229ad 100644 Binary files a/model_templates/ark.BulkRNA-seqAssayMetadataTemplate.xlsx and b/model_templates/ark.BulkRNA-seqAssayMetadataTemplate.xlsx differ diff --git a/model_templates/ark.ClinicalMetadataTemplate.csv b/model_templates/ark.ClinicalMetadataTemplate.csv index c3dde7d..f9c5459 100644 --- a/model_templates/ark.ClinicalMetadataTemplate.csv +++ b/model_templates/ark.ClinicalMetadataTemplate.csv @@ -1 +1 @@ -individualID,heightUnits,height,weightUnits,age,comorbidities,diagnosis,project,species,Component,ageUnits,weight,sex,program,ethnicity,race,PASI,diabetesType,CDASI,VASI,VIDA,VETI,vitiligoType,visitID +heightUnits,comorbidities,age,ethnicity,ageUnits,weight,program,Component,species,individualID,sex,race,weightUnits,project,height,diagnosis,PASI,diabetesType,visitID,CDASI,VASI,VETI,vitiligoPattern,VIDA diff --git a/model_templates/ark.ClinicalMetadataTemplate.xlsx b/model_templates/ark.ClinicalMetadataTemplate.xlsx index c3d449c..e2304e9 100644 Binary files a/model_templates/ark.ClinicalMetadataTemplate.xlsx and b/model_templates/ark.ClinicalMetadataTemplate.xlsx differ diff --git a/model_templates/ark.CyTOFAssayMetadataTemplate.csv b/model_templates/ark.CyTOFAssayMetadataTemplate.csv index 3d629e2..9644aa5 100644 --- a/model_templates/ark.CyTOFAssayMetadataTemplate.csv +++ b/model_templates/ark.CyTOFAssayMetadataTemplate.csv @@ -1 +1 @@ -targetPanelSynID,targetPanel,platform,dataCollectionBatch,assay,Component,softwareAndVersion,biospecimenID,targetPanelSize,sampleProcessingBatch +softwareAndVersion,dataCollectionBatch,Component,targetPanelSynID,biospecimenID,sampleProcessingBatch,platform,targetPanelSize,assay,targetPanel diff --git a/model_templates/ark.CyTOFAssayMetadataTemplate.xlsx b/model_templates/ark.CyTOFAssayMetadataTemplate.xlsx index 2874f6c..7a7c29c 100644 Binary files a/model_templates/ark.CyTOFAssayMetadataTemplate.xlsx and b/model_templates/ark.CyTOFAssayMetadataTemplate.xlsx differ diff --git a/model_templates/ark.DatasetAnnotationTemplate.csv b/model_templates/ark.DatasetAnnotationTemplate.csv index 5131cf0..fe7f386 100644 --- a/model_templates/ark.DatasetAnnotationTemplate.csv +++ b/model_templates/ark.DatasetAnnotationTemplate.csv @@ -1 +1 @@ -Component,datasetType,diagnosis,datasetStatus,biospecimenType,assay,datasetDescription,acknowledgmentStatement,biospecimenSubtype,dbGapAccession,species,associatedCodeURL,dataType,publicationSynID,project,program,associatedDataset,ARKRelease,ImmPortAccession,dataSubtype,programPhase +acknowledgmentStatement,diagnosis,species,associatedCodeURL,associatedDataset,dataSubtype,project,dataType,assay,ImmPortAccession,biospecimenType,publicationSynID,ARKRelease,datasetStatus,datasetDescription,associatedAccession,Component,datasetType,program,biospecimenSubtype,programPhase diff --git a/model_templates/ark.DatasetAnnotationTemplate.xlsx b/model_templates/ark.DatasetAnnotationTemplate.xlsx index 73ed66c..019be6c 100644 Binary files a/model_templates/ark.DatasetAnnotationTemplate.xlsx and b/model_templates/ark.DatasetAnnotationTemplate.xlsx differ diff --git a/model_templates/ark.FCSFileAnnotationTemplate.csv b/model_templates/ark.FCSFileAnnotationTemplate.csv index ee3e566..80afbcd 100644 --- a/model_templates/ark.FCSFileAnnotationTemplate.csv +++ b/model_templates/ark.FCSFileAnnotationTemplate.csv @@ -1 +1 @@ -specimenModality,assay,Component,fileFormat,eventCount,biospecimenID,individualID,sampleProcessingBatch,dataCollectionBatch +fileFormat,eventCount,specimenModality,Component,assay,dataCollectionBatch,sampleProcessingBatch,individualID,biospecimenID diff --git a/model_templates/ark.FCSFileAnnotationTemplate.xlsx b/model_templates/ark.FCSFileAnnotationTemplate.xlsx index 2800cc1..1bd7930 100644 Binary files a/model_templates/ark.FCSFileAnnotationTemplate.xlsx and b/model_templates/ark.FCSFileAnnotationTemplate.xlsx differ diff --git a/model_templates/ark.FastqFileAnnotationTemplate.csv b/model_templates/ark.FastqFileAnnotationTemplate.csv index 7432d1a..8e828c4 100644 --- a/model_templates/ark.FastqFileAnnotationTemplate.csv +++ b/model_templates/ark.FastqFileAnnotationTemplate.csv @@ -1 +1 @@ -readLength,assay,fileFormat,Component,specimenModality,targetPanel,targetPanelSynID,targetPanelSize,biospecimenID,individualID,libraryID +Component,fileFormat,specimenModality,readLength,assay,libraryID,biospecimenID,individualID,targetPanel,targetPanelSynID,targetPanelSize diff --git a/model_templates/ark.FastqFileAnnotationTemplate.xlsx b/model_templates/ark.FastqFileAnnotationTemplate.xlsx index 8561f64..8adada1 100644 Binary files a/model_templates/ark.FastqFileAnnotationTemplate.xlsx and b/model_templates/ark.FastqFileAnnotationTemplate.xlsx differ diff --git a/model_templates/ark.InVitroBiospecimenMetadataTemplate.csv b/model_templates/ark.InVitroBiospecimenMetadataTemplate.csv index f3df7ec..d56c4e8 100644 --- a/model_templates/ark.InVitroBiospecimenMetadataTemplate.csv +++ b/model_templates/ark.InVitroBiospecimenMetadataTemplate.csv @@ -1 +1 @@ -treatment,project,biospecimenID,notes,parentBiospecimenID,altSampleID,Component,biospecimenType,individualID,biospecimenSubtype,treatmentTimepoint,program,salivaCollectionProcedure,krennLining,krennSynovitisScore,krennInflammatory,anatomicalSite,krennStroma,synovialCollectionProcedure,cellType,cellOntologyID,primaryCellSource,skinSiteStatus,userDefinedCellType,FACSPopulation,visitID +program,biospecimenID,notes,altSampleID,biospecimenType,individualID,parentBiospecimenID,biospecimenSubtype,Component,project,treatmentTimepoint,sampleCollectionBatch,treatment,visitID,primaryCellSource,cellType,cellOntologyID,anatomicalSite,skinSiteStatus,synovialCollectionProcedure,salivaCollectionProcedure,krennLining,krennInflammatory,krennSynovitisScore,krennStroma,FACSPopulation,userDefinedCellType diff --git a/model_templates/ark.InVitroBiospecimenMetadataTemplate.xlsx b/model_templates/ark.InVitroBiospecimenMetadataTemplate.xlsx index d72839b..0c8ad59 100644 Binary files a/model_templates/ark.InVitroBiospecimenMetadataTemplate.xlsx and b/model_templates/ark.InVitroBiospecimenMetadataTemplate.xlsx differ diff --git a/model_templates/ark.OlinkAssayMetadataTemplate.csv b/model_templates/ark.OlinkAssayMetadataTemplate.csv index bbc35e1..2731a7f 100644 --- a/model_templates/ark.OlinkAssayMetadataTemplate.csv +++ b/model_templates/ark.OlinkAssayMetadataTemplate.csv @@ -1 +1 @@ -assay,plateID,platform,targetPanelSize,targetPanelSynID,Component,targetPanel +targetPanelSynID,targetPanel,Component,targetPanelSize,platform,plateID,assay diff --git a/model_templates/ark.OlinkAssayMetadataTemplate.xlsx b/model_templates/ark.OlinkAssayMetadataTemplate.xlsx index bf2a269..cd0ac98 100644 Binary files a/model_templates/ark.OlinkAssayMetadataTemplate.xlsx and b/model_templates/ark.OlinkAssayMetadataTemplate.xlsx differ diff --git a/model_templates/ark.OlinkFileAnnotationTemplate.csv b/model_templates/ark.OlinkFileAnnotationTemplate.csv index 13d4e68..447c233 100644 --- a/model_templates/ark.OlinkFileAnnotationTemplate.csv +++ b/model_templates/ark.OlinkFileAnnotationTemplate.csv @@ -1 +1 @@ -plateID,specimenModality,resourceType,Component,fileFormat +fileFormat,specimenModality,plateID,resourceType,Component diff --git a/model_templates/ark.OlinkFileAnnotationTemplate.xlsx b/model_templates/ark.OlinkFileAnnotationTemplate.xlsx index 3dcda53..777d664 100644 Binary files a/model_templates/ark.OlinkFileAnnotationTemplate.xlsx and b/model_templates/ark.OlinkFileAnnotationTemplate.xlsx differ diff --git a/model_templates/ark.PublicationMetadataTemplate.csv b/model_templates/ark.PublicationMetadataTemplate.csv index def1dea..e13c167 100644 --- a/model_templates/ark.PublicationMetadataTemplate.csv +++ b/model_templates/ark.PublicationMetadataTemplate.csv @@ -1 +1 @@ -program,associatedDataset,title,project,publicationDate,journal,Component,year,DOI,PMCID,PMID,publicationType,programPhase +PMID,associatedDataset,Component,publicationDate,publicationType,title,DOI,PMCID,year,program,journal,project,programPhase diff --git a/model_templates/ark.PublicationMetadataTemplate.xlsx b/model_templates/ark.PublicationMetadataTemplate.xlsx index 5dfc9f8..7584b00 100644 Binary files a/model_templates/ark.PublicationMetadataTemplate.xlsx and b/model_templates/ark.PublicationMetadataTemplate.xlsx differ diff --git a/model_templates/ark.ScRNASeqAssayMetadataTemplate.csv b/model_templates/ark.ScRNASeqAssayMetadataTemplate.csv index 0f93b4c..5d8417e 100644 --- a/model_templates/ark.ScRNASeqAssayMetadataTemplate.csv +++ b/model_templates/ark.ScRNASeqAssayMetadataTemplate.csv @@ -1 +1 @@ -specimenModality,totalReads,nucleicAcidSource,alignmentReference,softwareAndVersion,Component,libraryPrepMethod,sampleProcessingBatch,dataCollectionBatch,platform,inputCellCount,percentCellViability,assay,sequencingSaturation,libraryID,biospecimenID,10xProbeSetReference +alignmentReference,sampleProcessingBatch,dataCollectionBatch,assay,inputCellCount,libraryPrepMethod,totalReads,sequencingSaturation,softwareAndVersion,specimenModality,Component,platform,nucleicAcidSource,percentCellViability,10xProbeSetReference,biospecimenID,libraryID diff --git a/model_templates/ark.ScRNASeqAssayMetadataTemplate.xlsx b/model_templates/ark.ScRNASeqAssayMetadataTemplate.xlsx index 3fcc148..49f5cb7 100644 Binary files a/model_templates/ark.ScRNASeqAssayMetadataTemplate.xlsx and b/model_templates/ark.ScRNASeqAssayMetadataTemplate.xlsx differ diff --git a/model_templates/ark.ScRNASeqProcessedDataAnnotationTemplate.csv b/model_templates/ark.ScRNASeqProcessedDataAnnotationTemplate.csv index baabe47..e017fab 100644 --- a/model_templates/ark.ScRNASeqProcessedDataAnnotationTemplate.csv +++ b/model_templates/ark.ScRNASeqProcessedDataAnnotationTemplate.csv @@ -1 +1 @@ -assay,dataLevel,Component,cellRangerOutput,resourceType,fileFormat,specimenModality,targetPanelSynID,targetPanelSize,targetPanel,metadataType,processedDataType,RObjectClass,individualID,biospecimenID +resourceType,assay,fileFormat,dataLevel,Component,cellRangerOutput,specimenModality,metadataType,processedDataType,targetPanelSize,targetPanelSynID,targetPanel,RObjectClass,individualID,biospecimenID diff --git a/model_templates/ark.ScRNASeqProcessedDataAnnotationTemplate.xlsx b/model_templates/ark.ScRNASeqProcessedDataAnnotationTemplate.xlsx index 3a8a084..886352a 100644 Binary files a/model_templates/ark.ScRNASeqProcessedDataAnnotationTemplate.xlsx and b/model_templates/ark.ScRNASeqProcessedDataAnnotationTemplate.xlsx differ diff --git a/model_templates/ark.ScVDJSeqProcessedDataAnnotationTemplate.csv b/model_templates/ark.ScVDJSeqProcessedDataAnnotationTemplate.csv index 26a6682..76dc5a9 100644 --- a/model_templates/ark.ScVDJSeqProcessedDataAnnotationTemplate.csv +++ b/model_templates/ark.ScVDJSeqProcessedDataAnnotationTemplate.csv @@ -1 +1 @@ -resourceType,dataLevel,Component,specimenModality,fileFormat,assay,processedDataType,metadataType,biospecimenID,individualID,RObjectClass,targetPanelSynID,targetPanelSize,targetPanel +dataLevel,Component,specimenModality,fileFormat,assay,resourceType,biospecimenID,individualID,RObjectClass,targetPanelSize,targetPanelSynID,targetPanel,metadataType,processedDataType diff --git a/model_templates/ark.ScVDJSeqProcessedDataAnnotationTemplate.xlsx b/model_templates/ark.ScVDJSeqProcessedDataAnnotationTemplate.xlsx index 09ae495..0c13537 100644 Binary files a/model_templates/ark.ScVDJSeqProcessedDataAnnotationTemplate.xlsx and b/model_templates/ark.ScVDJSeqProcessedDataAnnotationTemplate.xlsx differ diff --git a/model_templates/ark.SnATAC-seqAssayMetadataTemplate.csv b/model_templates/ark.SnATAC-seqAssayMetadataTemplate.csv index 2f92da3..ff75dde 100644 --- a/model_templates/ark.SnATAC-seqAssayMetadataTemplate.csv +++ b/model_templates/ark.SnATAC-seqAssayMetadataTemplate.csv @@ -1 +1 @@ -softwareAndVersion,Component,nucleicAcidSource,totalReads,percentCellViability,specimenModality,libraryPrepMethod,assay,sequencingSaturation,sampleProcessingBatch,inputCellCount,platform,dataCollectionBatch,alignmentReference,libraryID,biospecimenID,10xProbeSetReference +assay,nucleicAcidSource,specimenModality,dataCollectionBatch,softwareAndVersion,alignmentReference,totalReads,percentCellViability,platform,Component,sequencingSaturation,sampleProcessingBatch,inputCellCount,libraryPrepMethod,libraryID,biospecimenID,10xProbeSetReference diff --git a/model_templates/ark.SnATAC-seqAssayMetadataTemplate.xlsx b/model_templates/ark.SnATAC-seqAssayMetadataTemplate.xlsx index b7593d6..7a280e0 100644 Binary files a/model_templates/ark.SnATAC-seqAssayMetadataTemplate.xlsx and b/model_templates/ark.SnATAC-seqAssayMetadataTemplate.xlsx differ diff --git a/model_templates/ark.SnATACSeqProcessedDataAnnotationTemplate.csv b/model_templates/ark.SnATACSeqProcessedDataAnnotationTemplate.csv index 8bc691a..157f4c0 100644 --- a/model_templates/ark.SnATACSeqProcessedDataAnnotationTemplate.csv +++ b/model_templates/ark.SnATACSeqProcessedDataAnnotationTemplate.csv @@ -1 +1 @@ -Component,cellRangerOutput,fileFormat,resourceType,dataLevel,assay,specimenModality,RObjectClass,processedDataType,metadataType,targetPanel,targetPanelSynID,targetPanelSize,individualID,biospecimenID +assay,Component,resourceType,specimenModality,fileFormat,dataLevel,cellRangerOutput,targetPanelSize,targetPanelSynID,targetPanel,metadataType,processedDataType,individualID,biospecimenID,RObjectClass diff --git a/model_templates/ark.SnATACSeqProcessedDataAnnotationTemplate.xlsx b/model_templates/ark.SnATACSeqProcessedDataAnnotationTemplate.xlsx index 8805370..927c8e7 100644 Binary files a/model_templates/ark.SnATACSeqProcessedDataAnnotationTemplate.xlsx and b/model_templates/ark.SnATACSeqProcessedDataAnnotationTemplate.xlsx differ diff --git a/model_templates/ark.SnRNASeqAssayMetadataTemplate.csv b/model_templates/ark.SnRNASeqAssayMetadataTemplate.csv index 45c623b..e529f24 100644 --- a/model_templates/ark.SnRNASeqAssayMetadataTemplate.csv +++ b/model_templates/ark.SnRNASeqAssayMetadataTemplate.csv @@ -1 +1 @@ -sampleProcessingBatch,nucleicAcidSource,inputCellCount,specimenModality,assay,totalReads,dataCollectionBatch,Component,platform,softwareAndVersion,alignmentReference,sequencingSaturation,percentCellViability,libraryPrepMethod,libraryID,biospecimenID,10xProbeSetReference +dataCollectionBatch,percentCellViability,softwareAndVersion,alignmentReference,nucleicAcidSource,sampleProcessingBatch,Component,platform,assay,inputCellCount,sequencingSaturation,totalReads,libraryPrepMethod,specimenModality,10xProbeSetReference,libraryID,biospecimenID diff --git a/model_templates/ark.SnRNASeqAssayMetadataTemplate.xlsx b/model_templates/ark.SnRNASeqAssayMetadataTemplate.xlsx index 34754d4..81509f5 100644 Binary files a/model_templates/ark.SnRNASeqAssayMetadataTemplate.xlsx and b/model_templates/ark.SnRNASeqAssayMetadataTemplate.xlsx differ diff --git a/model_templates/ark.SnRNASeqProcessedDataAnnotationTemplate.csv b/model_templates/ark.SnRNASeqProcessedDataAnnotationTemplate.csv index 59d9501..fcc7caf 100644 --- a/model_templates/ark.SnRNASeqProcessedDataAnnotationTemplate.csv +++ b/model_templates/ark.SnRNASeqProcessedDataAnnotationTemplate.csv @@ -1 +1 @@ -cellRangerOutput,Component,dataLevel,specimenModality,resourceType,fileFormat,assay,biospecimenID,individualID,metadataType,processedDataType,RObjectClass,targetPanelSize,targetPanel,targetPanelSynID +resourceType,fileFormat,specimenModality,assay,cellRangerOutput,Component,dataLevel,metadataType,processedDataType,RObjectClass,individualID,biospecimenID,targetPanelSize,targetPanel,targetPanelSynID diff --git a/model_templates/ark.SnRNASeqProcessedDataAnnotationTemplate.xlsx b/model_templates/ark.SnRNASeqProcessedDataAnnotationTemplate.xlsx index 78d076a..d38729e 100644 Binary files a/model_templates/ark.SnRNASeqProcessedDataAnnotationTemplate.xlsx and b/model_templates/ark.SnRNASeqProcessedDataAnnotationTemplate.xlsx differ diff --git a/model_templates/ark.SpatialImagingAssayMetadataTemplate.csv b/model_templates/ark.SpatialImagingAssayMetadataTemplate.csv index 9ea2f69..1b5cc61 100644 --- a/model_templates/ark.SpatialImagingAssayMetadataTemplate.csv +++ b/model_templates/ark.SpatialImagingAssayMetadataTemplate.csv @@ -1 +1 @@ -targetPanel,targetPanelSynID,assay,specimenModality,dataCollectionBatch,targetPanelSize,sampleProcessingBatch,Component,biospecimenID,slideID +targetPanelSize,assay,specimenModality,Component,targetPanelSynID,sampleProcessingBatch,targetPanel,dataCollectionBatch,slideID,biospecimenID diff --git a/model_templates/ark.SpatialImagingAssayMetadataTemplate.xlsx b/model_templates/ark.SpatialImagingAssayMetadataTemplate.xlsx index 0b2f7f7..641e79b 100644 Binary files a/model_templates/ark.SpatialImagingAssayMetadataTemplate.xlsx and b/model_templates/ark.SpatialImagingAssayMetadataTemplate.xlsx differ diff --git a/model_templates/ark.SpatialImagingFileAnnotationTemplate.csv b/model_templates/ark.SpatialImagingFileAnnotationTemplate.csv index f73e4d9..d347c01 100644 --- a/model_templates/ark.SpatialImagingFileAnnotationTemplate.csv +++ b/model_templates/ark.SpatialImagingFileAnnotationTemplate.csv @@ -1 +1 @@ -Component,specimenModality,resourceType,assay,fileFormat,slideID,biospecimenID,metadataType,processedDataType,RObjectClass +fileFormat,assay,Component,resourceType,specimenModality,RObjectClass,metadataType,processedDataType,slideID,biospecimenID diff --git a/model_templates/ark.SpatialImagingFileAnnotationTemplate.xlsx b/model_templates/ark.SpatialImagingFileAnnotationTemplate.xlsx index 85a028d..54ec458 100644 Binary files a/model_templates/ark.SpatialImagingFileAnnotationTemplate.xlsx and b/model_templates/ark.SpatialImagingFileAnnotationTemplate.xlsx differ